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

virtio,pc,pci: features, cleanups, fixes

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

fixes, cleanups all over the place.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmXw0TMPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8x4H+gLMoGwaGAX7gDGPgn2Ix4j/3kO77ZJ9X9k/
# 1KqZu/9eMS1j2Ei+vZqf05w7qRjxxhwDq3ilEXF/+UFqgAehLqpRRB8j5inqvzYt
# +jv0DbL11PBp/oFjWcytm5CbiVsvq8KlqCF29VNzc162XdtcduUOWagL96y8lJfZ
# uPrOoyeR7SMH9lp3LLLHWgu+9W4nOS03RroZ6Umj40y5B7yR0Rrppz8lMw5AoQtr
# 0gMRnFhYXeiW6CXdz+Tzcr7XfvkkYDi/j7ibiNSURLBfOpZa6Y8+kJGKxz5H1K1G
# 6ZY4PBcOpQzl+NMrktPHogczgJgOK10t+1i/R3bGZYw2Qn/93Eg=
# =C0UU
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 12 Mar 2024 22:03:31 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

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

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

# Conflicts:
#	hw/core/machine.c

14 files changed, 118 insertions, 5 deletions

diff --git a/include/hw/acpi/acpi_generic_initiator.h b/include/hw/acpi/acpi_generic_initiator.h
new file mode 100644
index 0000000000..a304bad73e
--- /dev/null
+++ b/include/hw/acpi/acpi_generic_initiator.h
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#ifndef ACPI_GENERIC_INITIATOR_H
+#define ACPI_GENERIC_INITIATOR_H
+
+#include "qom/object_interfaces.h"
+
+#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
+
+typedef struct AcpiGenericInitiator {
+    /* private */
+    Object parent;
+
+    /* public */
+    char *pci_dev;
+    uint16_t node;
+} AcpiGenericInitiator;
+
+/*
+ * ACPI 6.3:
+ * Table 5-81 Flags – Generic Initiator Affinity Structure
+ */
+typedef enum {
+    /*
+     * If clear, the OSPM ignores the contents of the Generic
+     * Initiator/Port Affinity Structure. This allows system firmware
+     * to populate the SRAT with a static number of structures, but only
+     * enable them as necessary.
+     */
+    GEN_AFFINITY_ENABLED = (1 << 0),
+} GenericAffinityFlags;
+
+/*
+ * ACPI 6.3:
+ * Table 5-80 Device Handle - PCI
+ */
+typedef struct PCIDeviceHandle {
+    uint16_t segment;
+    uint16_t bdf;
+} PCIDeviceHandle;
+
+void build_srat_generic_pci_initiator(GArray *table_data);
+
+#endif
diff --git a/include/hw/audio/virtio-snd.h b/include/hw/audio/virtio-snd.h
index c3767f442b..3d79181364 100644
--- a/include/hw/audio/virtio-snd.h
+++ b/include/hw/audio/virtio-snd.h
@@ -230,6 +230,7 @@ struct virtio_snd_ctrl_command {
     VirtQueue *vq;
     virtio_snd_hdr ctrl;
     virtio_snd_hdr resp;
+    size_t payload_size;
     QTAILQ_ENTRY(virtio_snd_ctrl_command) next;
 };
 #endif
diff --git a/include/hw/cxl/cxl_component.h b/include/hw/cxl/cxl_component.h
index 0e5d35c263..5012fab6f7 100644
--- a/include/hw/cxl/cxl_component.h
+++ b/include/hw/cxl/cxl_component.h
@@ -25,6 +25,7 @@ enum reg_type {
     CXL2_TYPE3_DEVICE,
     CXL2_LOGICAL_DEVICE,
     CXL2_ROOT_PORT,
+    CXL2_RC,
     CXL2_UPSTREAM_PORT,
     CXL2_DOWNSTREAM_PORT,
     CXL3_SWITCH_MAILBOX_CCI,
diff --git a/include/hw/cxl/cxl_pci.h b/include/hw/cxl/cxl_pci.h
index 265db6c407..d0855ed78b 100644
--- a/include/hw/cxl/cxl_pci.h
+++ b/include/hw/cxl/cxl_pci.h
@@ -92,8 +92,9 @@ typedef struct CXLDVSECDevice {
     uint32_t range2_base_hi;
     uint32_t range2_base_lo;
     uint16_t cap3;
+    uint16_t resv;
 } QEMU_PACKED CXLDVSECDevice;
-QEMU_BUILD_BUG_ON(sizeof(CXLDVSECDevice) != 0x3A);
+QEMU_BUILD_BUG_ON(sizeof(CXLDVSECDevice) != PCIE_CXL_DEVICE_DVSEC_LENGTH);
 
 /*
  * CXL r3.1 Section 8.1.5: CXL Extensions DVSEC for Ports
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 6e514982d4..c21b8d3285 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -211,6 +211,23 @@ struct smbios_type_8 {
     uint8_t port_type;
 } QEMU_PACKED;
 
+/* SMBIOS type 9 - System Slots (v2.1+) */
+struct smbios_type_9 {
+    struct smbios_structure_header header;
+    uint8_t slot_designation;
+    uint8_t slot_type;
+    uint8_t slot_data_bus_width;
+    uint8_t current_usage;
+    uint8_t slot_length;
+    uint16_t slot_id;
+    uint8_t slot_characteristics1;
+    uint8_t slot_characteristics2;
+    /* SMBIOS spec v2.6+ */
+    uint16_t segment_group_number;
+    uint8_t bus_number;
+    uint8_t device_number;
+} QEMU_PACKED;
+
 /* SMBIOS type 11 - OEM strings */
 struct smbios_type_11 {
     struct smbios_structure_header header;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index b958023187..27a68071d7 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -178,8 +178,6 @@ void pc_basic_device_init(struct PCMachineState *pcms,
                           ISADevice *rtc_state,
                           bool create_fdctrl,
                           uint32_t hpet_irqs);
-void pc_cmos_init(PCMachineState *pcms,
-                  ISADevice *s);
 void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus);
 
 void pc_i8259_create(ISABus *isa_bus, qemu_irq *i8259_irqs);
@@ -190,6 +188,8 @@ void pc_i8259_create(ISABus *isa_bus, qemu_irq *i8259_irqs);
 #define TYPE_PORT92 "port92"
 
 /* pc_sysfw.c */
+void pc_system_flash_create(PCMachineState *pcms);
+void pc_system_flash_cleanup_unused(PCMachineState *pcms);
 void pc_system_firmware_init(PCMachineState *pcms, MemoryRegion *rom_memory);
 bool pc_system_ovmf_table_find(const char *entry, uint8_t **data,
                                int *data_len);
diff --git a/include/hw/pci/pcie_regs.h b/include/hw/pci/pcie_regs.h
index 4972106c42..9d3b6868dc 100644
--- a/include/hw/pci/pcie_regs.h
+++ b/include/hw/pci/pcie_regs.h
@@ -39,6 +39,8 @@ typedef enum PCIExpLinkSpeed {
     QEMU_PCI_EXP_LNK_5GT,
     QEMU_PCI_EXP_LNK_8GT,
     QEMU_PCI_EXP_LNK_16GT,
+    QEMU_PCI_EXP_LNK_32GT,
+    QEMU_PCI_EXP_LNK_64GT,
 } PCIExpLinkSpeed;
 
 #define QEMU_PCI_EXP_LNKCAP_MLS(speed)  (speed)
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
index 095fb0c9ed..b77eb7bf58 100644
--- a/include/hw/pci/pcie_sriov.h
+++ b/include/hw/pci/pcie_sriov.h
@@ -58,8 +58,8 @@ void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize);
 void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
                              uint32_t val, int len);
 
-/* Reset SR/IOV VF Enable bit to unregister all VFs */
-void pcie_sriov_pf_disable_vfs(PCIDevice *dev);
+/* Reset SR/IOV */
+void pcie_sriov_pf_reset(PCIDevice *dev);
 
 /* Get logical VF number of a VF - only valid for VFs */
 uint16_t pcie_sriov_vf_number(PCIDevice *dev);
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index 8f54e5edd4..0a9575b469 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -30,6 +30,12 @@ typedef struct VhostVDPAHostNotifier {
     void *addr;
 } VhostVDPAHostNotifier;
 
+typedef enum SVQTransitionState {
+    SVQ_TSTATE_DISABLING = -1,
+    SVQ_TSTATE_DONE,
+    SVQ_TSTATE_ENABLING
+} SVQTransitionState;
+
 /* Info shared by all vhost_vdpa device models */
 typedef struct vhost_vdpa_shared {
     int device_fd;
@@ -47,6 +53,9 @@ typedef struct vhost_vdpa_shared {
 
     /* Vdpa must send shadow addresses as IOTLB key for data queues, not GPA */
     bool shadow_data;
+
+    /* SVQ switching is in progress, or already completed? */
+    SVQTransitionState svq_switching;
 } VhostVDPAShared;
 
 typedef struct vhost_vdpa {
diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h
index 781ebaea8f..83a52cc446 100644
--- a/include/hw/virtio/virtio-iommu.h
+++ b/include/hw/virtio/virtio-iommu.h
@@ -24,6 +24,7 @@
 #include "hw/virtio/virtio.h"
 #include "hw/pci/pci.h"
 #include "qom/object.h"
+#include "qapi/qapi-types-virtio.h"
 
 #define TYPE_VIRTIO_IOMMU "virtio-iommu-device"
 #define TYPE_VIRTIO_IOMMU_PCI "virtio-iommu-pci"
@@ -66,6 +67,8 @@ struct VirtIOIOMMU {
     bool boot_bypass;
     Notifier machine_done;
     bool granule_frozen;
+    GranuleMode granule_mode;
+    uint8_t aw_bits;
 };
 
 #endif
diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h
index 59d88018c1..4d57a9c751 100644
--- a/include/hw/virtio/virtio-pci.h
+++ b/include/hw/virtio/virtio-pci.h
@@ -43,6 +43,7 @@ enum {
     VIRTIO_PCI_FLAG_INIT_FLR_BIT,
     VIRTIO_PCI_FLAG_AER_BIT,
     VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED_BIT,
+    VIRTIO_PCI_FLAG_VDPA_BIT,
 };
 
 /* Need to activate work-arounds for buggy guests at vmstate load. */
@@ -89,6 +90,9 @@ enum {
 #define VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED \
   (1 << VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED_BIT)
 
+/* VDPA supported flags */
+#define VIRTIO_PCI_FLAG_VDPA (1 << VIRTIO_PCI_FLAG_VDPA_BIT)
+
 typedef struct {
     MSIMessage msg;
     int virq;
@@ -140,6 +144,7 @@ struct VirtIOPCIProxy {
         };
         VirtIOPCIRegion regs[5];
     };
+    VirtIOPCIRegion lm;
     MemoryRegion modern_bar;
     MemoryRegion io_bar;
     uint32_t legacy_io_bar_idx;
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index c8f72850bc..b3c74a1bca 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -35,6 +35,9 @@
                                 (0x1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | \
                                 (0x1ULL << VIRTIO_F_ANY_LAYOUT))
 
+#define LM_DISABLE      0x00
+#define LM_ENABLE       0x01
+
 struct VirtQueue;
 
 static inline hwaddr vring_align(hwaddr addr,
@@ -95,6 +98,11 @@ enum virtio_device_endian {
     VIRTIO_DEVICE_ENDIAN_BIG,
 };
 
+typedef struct BitmapMemoryRegionCaches {
+    struct rcu_head rcu;
+    MemoryRegionCache bitmap;
+} BitmapMemoryRegionCaches;
+
 /**
  * struct VirtIODevice - common VirtIO structure
  * @name: name of the device
@@ -128,6 +136,14 @@ struct VirtIODevice
     uint32_t generation;
     int nvectors;
     VirtQueue *vq;
+    uint8_t lm_logging_ctrl;
+    uint32_t lm_base_addr_low;
+    uint32_t lm_base_addr_high;
+    uint32_t lm_end_addr_low;
+    uint32_t lm_end_addr_high;
+
+    BitmapMemoryRegionCaches *caches;
+
     MemoryListener listener;
     uint16_t device_id;
     /* @vm_running: current VM running state via virtio_vmstate_change() */
@@ -379,8 +395,11 @@ hwaddr virtio_queue_get_desc_size(VirtIODevice *vdev, int n);
 hwaddr virtio_queue_get_avail_size(VirtIODevice *vdev, int n);
 hwaddr virtio_queue_get_used_size(VirtIODevice *vdev, int n);
 unsigned int virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n);
+unsigned int virtio_queue_get_vring_states(VirtIODevice *vdev, int n);
 void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n,
                                      unsigned int idx);
+void virtio_queue_set_vring_states(VirtIODevice *vdev, int n,
+                                   unsigned int idx);
 void virtio_queue_restore_last_avail_idx(VirtIODevice *vdev, int n);
 void virtio_queue_invalidate_signalled_used(VirtIODevice *vdev, int n);
 void virtio_queue_update_used_idx(VirtIODevice *vdev, int n);
diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h
index 3e2bc2c97e..86733278ba 100644
--- a/include/standard-headers/linux/virtio_pci.h
+++ b/include/standard-headers/linux/virtio_pci.h
@@ -221,6 +221,13 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_ADM_Q_IDX	60
 #define VIRTIO_PCI_COMMON_ADM_Q_NUM	62
 
+#define LM_LOGGING_CTRL                 0
+#define LM_BASE_ADDR_LOW                4
+#define LM_BASE_ADDR_HIGH               8
+#define LM_END_ADDR_LOW                 12
+#define LM_END_ADDR_HIGH                16
+#define LM_VRING_STATE_OFFSET           0x20
+
 #endif /* VIRTIO_PCI_NO_MODERN */
 
 /* Admin command status. */
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 4173ef2afa..825cfe86bc 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -41,6 +41,7 @@ struct NodeInfo {
     struct HostMemoryBackend *node_memdev;
     bool present;
     bool has_cpu;
+    bool has_gi;
     uint8_t lb_info_provided;
     uint16_t initiator;
     uint8_t distance[MAX_NODES];