virtio,pci: features, cleanups

vdpa:
       shadow vq vlan support
       net migration with cvq
 cxl:
      support emulating 4 HDM decoders
      serial number extended capability
 virtio:
       hared dma-buf
 
 Fixes, cleanups all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmUd4/YPHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRpyM8H/02cRbJcQOjYt7j68zPW6GaDXxBI/UmdWDyG
 15LZZbGNOPjyjNd3Vz1M7stQ5rhoKcgo/RdI+0E60a78svgW5JvpXoXR3pksc3Dx
 v28B/akXwHUErYFSZQ+2VHNc8OhCd0v2ehxZxbwPEAYIOAj3hcCIVoPGXTnKJmAJ
 imr5hjH0wZUc0+xdsmn8Vfdv5NTzpwfVObbGiMZejeJsaoh0y6Rt8RANBMY67KQD
 S7/HPlVuDYf/y43t4ZEHNYuV9RaCdZZYlLWwV1scdKaYcofgmtJOKbOdCjHRXgj+
 004Afb3rggIoCfnCzOFzhGx+MLDtLjvEn2N4oLEWCLi+k/3huaA=
 =GAvH
 -----END PGP SIGNATURE-----

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

virtio,pci: features, cleanups

vdpa:
      shadow vq vlan support
      net migration with cvq
cxl:
     support emulating 4 HDM decoders
     serial number extended capability
virtio:
      hared dma-buf

Fixes, cleanups all over the place.

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

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (53 commits)
  libvhost-user: handle shared_object msg
  vhost-user: add shared_object msg
  hw/display: introduce virtio-dmabuf
  util/uuid: add a hash function
  virtio: remove unused next argument from virtqueue_split_read_next_desc()
  virtio: remove unnecessary thread fence while reading next descriptor
  virtio: use shadow_avail_idx while checking number of heads
  libvhost-user.c: add assertion to vu_message_read_default
  pcie_sriov: unregister_vfs(): fix error path
  hw/i386/pc: improve physical address space bound check for 32-bit x86 systems
  amd_iommu: Fix APIC address check
  vdpa net: follow VirtIO initialization properly at cvq isolation probing
  vdpa net: stop probing if cannot set features
  vdpa net: fix error message setting virtio status
  hw/pci-bridge/cxl-upstream: Add serial number extended capability support
  hw/cxl: Support 4 HDM decoders at all levels of topology
  hw/cxl: Fix and use same calculation for HDM decoder block size everywhere
  hw/cxl: Add utility functions decoder interleave ways and target count.
  hw/cxl: Push cxl_decoder_count_enc() and cxl_decode_ig() into .c
  vdpa net: zero vhost_vdpa iova_tree pointer at cleanup
  ...

Conflicts:
  hw/core/machine.c
  Context conflict with commit 314e0a84cd ("hw/core: remove needless
  includes") because it removed an adjacent #include.

include/hw/acpi/acpi_dev_interface.h

@@ -3,7 +3,6 @@
 
 #include "qapi/qapi-types-acpi.h"
 #include "qom/object.h"
-#include "hw/boards.h"
 #include "hw/qdev-core.h"
 
 /* These values are part of guest ABI, and can not be changed */
@@ -52,7 +51,5 @@ struct AcpiDeviceIfClass {
     /* <public> */
     void (*ospm_status)(AcpiDeviceIf *adev, ACPIOSTInfoList ***list);
     void (*send_event)(AcpiDeviceIf *adev, AcpiEventStatusBits ev);
-    void (*madt_cpu)(int uid, const CPUArchIdList *apic_ids, GArray *entry,
-                     bool force_enabled);
 };
 #endif

include/hw/acpi/cpu.h

@@ -15,6 +15,7 @@
 #include "hw/qdev-core.h"
 #include "hw/acpi/acpi.h"
 #include "hw/acpi/aml-build.h"
+#include "hw/boards.h"
 #include "hw/hotplug.h"
 
 typedef struct AcpiCpuStatus {
@@ -55,8 +56,11 @@ typedef struct CPUHotplugFeatures {
     const char *smi_path;
 } CPUHotplugFeatures;
 
+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,
-                    hwaddr io_base,
+                    build_madt_cpu_fn build_madt_cpu, hwaddr io_base,
                     const char *res_root,
                     const char *event_handler_method);
 

include/hw/acpi/generic_event_device.h

@@ -69,8 +69,6 @@
 #define TYPE_ACPI_GED "acpi-ged"
 OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED)
 
-#define TYPE_ACPI_GED_X86 "acpi-ged-x86"
-
 #define ACPI_GED_EVT_SEL_OFFSET    0x0
 #define ACPI_GED_EVT_SEL_LEN       0x4
 

include/hw/cxl/cxl_component.h

@@ -135,6 +135,10 @@ REG32(CXL_RAS_ERR_HEADER0, CXL_RAS_REGISTERS_OFFSET + 0x18)
   REG32(CXL_HDM_DECODER##n##_TARGET_LIST_LO,                                   \
         CXL_HDM_REGISTERS_OFFSET + (0x20 * n) + 0x24)                          \
   REG32(CXL_HDM_DECODER##n##_TARGET_LIST_HI,                                   \
+        CXL_HDM_REGISTERS_OFFSET + (0x20 * n) + 0x28)                          \
+  REG32(CXL_HDM_DECODER##n##_DPA_SKIP_LO,                                      \
+        CXL_HDM_REGISTERS_OFFSET + (0x20 * n) + 0x24)                          \
+  REG32(CXL_HDM_DECODER##n##_DPA_SKIP_HI,                                      \
         CXL_HDM_REGISTERS_OFFSET + (0x20 * n) + 0x28)
 
 REG32(CXL_HDM_DECODER_CAPABILITY, CXL_HDM_REGISTERS_OFFSET)
@@ -147,7 +151,13 @@ REG32(CXL_HDM_DECODER_GLOBAL_CONTROL, CXL_HDM_REGISTERS_OFFSET + 4)
     FIELD(CXL_HDM_DECODER_GLOBAL_CONTROL, POISON_ON_ERR_EN, 0, 1)
     FIELD(CXL_HDM_DECODER_GLOBAL_CONTROL, HDM_DECODER_ENABLE, 1, 1)
 
+/* Support 4 decoders at all levels of topology */
+#define CXL_HDM_DECODER_COUNT 4
+
 HDM_DECODER_INIT(0);
+HDM_DECODER_INIT(1);
+HDM_DECODER_INIT(2);
+HDM_DECODER_INIT(3);
 
 /* 8.2.5.13 - CXL Extended Security Capability Structure (Root complex only) */
 #define EXTSEC_ENTRY_MAX        256
@@ -225,26 +235,14 @@ void cxl_component_create_dvsec(CXLComponentState *cxl_cstate,
                                 enum reg_type cxl_dev_type, uint16_t length,
                                 uint16_t type, uint8_t rev, uint8_t *body);
 
-static inline int cxl_decoder_count_enc(int count)
-{
-    switch (count) {
-    case 1: return 0;
-    case 2: return 1;
-    case 4: return 2;
-    case 6: return 3;
-    case 8: return 4;
-    case 10: return 5;
-    }
-    return 0;
-}
+int cxl_decoder_count_enc(int count);
+int cxl_decoder_count_dec(int enc_cnt);
 
 uint8_t cxl_interleave_ways_enc(int iw, Error **errp);
+int cxl_interleave_ways_dec(uint8_t iw_enc, Error **errp);
 uint8_t cxl_interleave_granularity_enc(uint64_t gran, Error **errp);
 
-static inline hwaddr cxl_decode_ig(int ig)
-{
-    return 1ULL << (ig + 8);
-}
+hwaddr cxl_decode_ig(int ig);
 
 CXLComponentState *cxl_get_hb_cstate(PCIHostState *hb);
 bool cxl_get_hb_passthrough(PCIHostState *hb);

include/hw/i386/pc.h

@@ -129,6 +129,12 @@ struct PCMachineClass {
 
     /* resizable acpi blob compat */
     bool resizable_acpi_blob;
+
+    /*
+     * whether the machine type implements broken 32-bit address space bound
+     * check for memory.
+     */
+    bool broken_32bit_mem_addr_check;
 };
 
 #define TYPE_PC_MACHINE "generic-pc-machine"

include/hw/pci/pci_bridge.h

@@ -77,6 +77,9 @@ struct PCIBridge {
 
     pci_map_irq_fn map_irq;
     const char *bus_name;
+
+    /* SLT is RO for PCIE to PCIE bridges, but old QEMU versions had it RW */
+    bool pcie_writeable_slt_bug;
 };
 
 #define PCI_BRIDGE_DEV_PROP_CHASSIS_NR "chassis_nr"

include/hw/virtio/vhost-backend.h

@@ -196,4 +196,7 @@ int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,
 
 int vhost_user_gpu_set_socket(struct vhost_dev *dev, int fd);
 
+int vhost_user_get_shared_object(struct vhost_dev *dev, unsigned char *uuid,
+                                        int *dmabuf_fd);
+
 #endif /* VHOST_BACKEND_H */

include/hw/virtio/vhost-user-device.h

@@ -0,0 +1,46 @@
+/*
+ * Vhost-user generic virtio device
+ *
+ * Copyright (c) 2023 Linaro Ltd
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef QEMU_VHOST_USER_DEVICE_H
+#define QEMU_VHOST_USER_DEVICE_H
+
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user.h"
+
+#define TYPE_VHOST_USER_BASE "vhost-user-base"
+
+OBJECT_DECLARE_TYPE(VHostUserBase, VHostUserBaseClass, VHOST_USER_BASE)
+
+struct VHostUserBase {
+    VirtIODevice parent;
+    /* Properties */
+    CharBackend chardev;
+    uint16_t virtio_id;
+    uint32_t num_vqs;
+    uint32_t config_size;
+    /* State tracking */
+    VhostUserState vhost_user;
+    struct vhost_virtqueue *vhost_vq;
+    struct vhost_dev vhost_dev;
+    GPtrArray *vqs;
+    bool connected;
+};
+
+    /* needed so we can use the base realize after specialisation
+       tweaks */
+struct VHostUserBaseClass {
+    /*< private >*/
+    VirtioDeviceClass parent_class;
+    /*< public >*/
+    DeviceRealize parent_realize;
+};
+
+/* shared for the benefit of the derived pci class */
+#define TYPE_VHOST_USER_DEVICE "vhost-user-device"
+
+#endif /* QEMU_VHOST_USER_DEVICE_H */

include/hw/virtio/vhost-user.h

@@ -11,6 +11,28 @@
 #include "chardev/char-fe.h"
 #include "hw/virtio/virtio.h"
 
+enum VhostUserProtocolFeature {
+    VHOST_USER_PROTOCOL_F_MQ = 0,
+    VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
+    VHOST_USER_PROTOCOL_F_RARP = 2,
+    VHOST_USER_PROTOCOL_F_REPLY_ACK = 3,
+    VHOST_USER_PROTOCOL_F_NET_MTU = 4,
+    VHOST_USER_PROTOCOL_F_BACKEND_REQ = 5,
+    VHOST_USER_PROTOCOL_F_CROSS_ENDIAN = 6,
+    VHOST_USER_PROTOCOL_F_CRYPTO_SESSION = 7,
+    VHOST_USER_PROTOCOL_F_PAGEFAULT = 8,
+    VHOST_USER_PROTOCOL_F_CONFIG = 9,
+    VHOST_USER_PROTOCOL_F_BACKEND_SEND_FD = 10,
+    VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11,
+    VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD = 12,
+    VHOST_USER_PROTOCOL_F_RESET_DEVICE = 13,
+    VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS = 14,
+    VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS = 15,
+    VHOST_USER_PROTOCOL_F_STATUS = 16,
+    VHOST_USER_PROTOCOL_F_SHARED_OBJECT = 17,
+    VHOST_USER_PROTOCOL_F_MAX
+};
+
 /**
  * VhostUserHostNotifier - notifier information for one queue
  * @rcu: rcu_head for cleanup

include/hw/virtio/vhost-vdpa.h

@@ -57,6 +57,7 @@ typedef struct vhost_vdpa {
 } VhostVDPA;
 
 int vhost_vdpa_get_iova_range(int fd, struct vhost_vdpa_iova_range *iova_range);
+int vhost_vdpa_set_vring_ready(struct vhost_vdpa *v, unsigned idx);
 
 int vhost_vdpa_dma_map(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
                        hwaddr size, void *vaddr, bool readonly);

include/hw/virtio/virtio-dmabuf.h

@@ -0,0 +1,100 @@
+/*
+ * Virtio Shared dma-buf
+ *
+ * Copyright Red Hat, Inc. 2023
+ *
+ * Authors:
+ *     Albert Esteve <aesteve@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef VIRTIO_DMABUF_H
+#define VIRTIO_DMABUF_H
+
+#include "qemu/uuid.h"
+#include "vhost.h"
+
+typedef enum SharedObjectType {
+    TYPE_INVALID = 0,
+    TYPE_DMABUF,
+    TYPE_VHOST_DEV,
+} SharedObjectType;
+
+typedef struct VirtioSharedObject {
+    SharedObjectType type;
+    gpointer value;
+} VirtioSharedObject;
+
+/**
+ * virtio_add_dmabuf() - Add a new dma-buf resource to the lookup table
+ * @uuid: new resource's UUID
+ * @dmabuf_fd: the dma-buf descriptor that will be stored and shared with
+ *             other virtio devices. The caller retains ownership over the
+ *             descriptor and its lifecycle.
+ *
+ * Note: @dmabuf_fd must be a valid (non-negative) file descriptor.
+ *
+ * Return: true if the UUID did not exist and the resource has been added,
+ * false if another resource with the same UUID already existed.
+ * Note that if it finds a repeated UUID, the resource is not inserted in
+ * the lookup table.
+ */
+bool virtio_add_dmabuf(QemuUUID *uuid, int dmabuf_fd);
+
+/**
+ * virtio_add_vhost_device() - Add a new exporter vhost device that holds the
+ * resource with the associated UUID
+ * @uuid: new resource's UUID
+ * @dev: the pointer to the vhost device that holds the resource. The caller
+ *       retains ownership over the device struct and its lifecycle.
+ *
+ * Return: true if the UUID did not exist and the device has been tracked,
+ * false if another resource with the same UUID already existed.
+ * Note that if it finds a repeated UUID, the resource is not inserted in
+ * the lookup table.
+ */
+bool virtio_add_vhost_device(QemuUUID *uuid, struct vhost_dev *dev);
+
+/**
+ * virtio_remove_resource() - Removes a resource from the lookup table
+ * @uuid: resource's UUID
+ *
+ * Return: true if the UUID has been found and removed from the lookup table.
+ */
+bool virtio_remove_resource(const QemuUUID *uuid);
+
+/**
+ * virtio_lookup_dmabuf() - Looks for a dma-buf resource in the lookup table
+ * @uuid: resource's UUID
+ *
+ * Return: the dma-buf file descriptor integer, or -1 if the key is not found.
+ */
+int virtio_lookup_dmabuf(const QemuUUID *uuid);
+
+/**
+ * virtio_lookup_vhost_device() - Looks for an exporter vhost device in the
+ * lookup table
+ * @uuid: resource's UUID
+ *
+ * Return: pointer to the vhost_dev struct, or NULL if the key is not found.
+ */
+struct vhost_dev *virtio_lookup_vhost_device(const QemuUUID *uuid);
+
+/**
+ * virtio_object_type() - Looks for the type of resource in the lookup table
+ * @uuid: resource's UUID
+ *
+ * Return: the type of resource associated with the UUID, or TYPE_INVALID if
+ * the key is not found.
+ */
+SharedObjectType virtio_object_type(const QemuUUID *uuid);
+
+/**
+ * virtio_free_resources() - Destroys all keys and values of the shared
+ * resources lookup table, and frees them
+ */
+void virtio_free_resources(void);
+
+#endif /* VIRTIO_DMABUF_H */

include/hw/virtio/virtio-net.h

@@ -38,6 +38,12 @@ OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET)
 /* Maximum VIRTIO_NET_CTRL_MAC_TABLE_SET unicast + multicast entries. */
 #define MAC_TABLE_ENTRIES    64
 
+/*
+ * The maximum number of VLANs in the VLAN filter table
+ * added by VIRTIO_NET_CTRL_VLAN_ADD
+ */
+#define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */
+
 typedef struct virtio_net_conf
 {
     uint32_t txtimer;