Merge tag 'pull-vfio-20250704' of https://github.com/legoater/qemu into staging

vfio queue:

* Added small cleanups for b4 and scope
* Restricted TDX build to 64-bit target
* Fixed issues introduced in first part of VFIO live update support
* Added full VFIO live update support

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmhnlBMACgkQUaNDx8/7
# 7KFOxw//dIPpGcYIjEGpIkIh6NF3VK6xmDAG0aZEeM+5fCzdor2DPkD7ZPyqND3S
# /YkR8GSOHd+Qm5W+73LHOdV5RFMt4wagyHiAKUMpEFHY7ZLduxIXlACoUo+F5cnh
# SUnhC6KX7Gu1/Nndb4X4w6SNOyhoRKtQ2EqpRsrGdIaBkX8s6w2jF/INPTPdpg73
# lulJZCAFNzyIWytck9ohJf8To9IsvkCXTF6mcywURa9MBaAarRttXoFjuZsXb7zn
# NqGVtantNAaJmKu26X3ScUWn9P02WryhPB6KT7+B3G/b87Su1cnbAwYakNSFPJIx
# I/gaw0EPzHM+b6mavA4IdvKDJGR7GMvpJEGqUEpntc6FJ3+g1B7qsedgeBUc/RKB
# UaRmtYbvlMv5wSmaLcxsT3S3BnABbrd4EedZX5uOBFMrtnTiOqrMUEcoMaf5ogvN
# KlJkrjNQkfHxTbp5G+nXHuTzae3k2Ylm196b2yhgARfUL70jiak/B+ADeezVcVmW
# 6ZpotrAvMxu9RlFdxTSbL0/lR0rfKZTecqMOSFA+FlmjcTJ0QW1SbweMdsfgW/uU
# /2Hfmw6zUQ80/tMqYMztFWsiov7C8a8ZMmuZwDQp+AdCVGgFEigfNJVQYgujbqKz
# g9Ta9cNPyvF5hpnml5u8IzAzM95HrhIPFmmpUBZyWOCeL6chSHk=
# =Cu7b
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 04 Jul 2025 04:42:59 EDT
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@redhat.com>" [full]
# gpg:                 aka "Cédric Le Goater <clg@kaod.org>" [full]
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20250704' of https://github.com/legoater/qemu: (27 commits)
  vfio: doc changes for cpr
  vfio/container: delete old cpr register
  iommufd: preserve DMA mappings
  vfio/iommufd: change process
  vfio/iommufd: reconstruct hwpt
  vfio/iommufd: reconstruct device
  vfio/iommufd: preserve descriptors
  vfio/iommufd: cpr state
  migration: vfio cpr state hook
  vfio/iommufd: register container for cpr
  vfio/iommufd: device name blocker
  vfio/iommufd: add vfio_device_free_name
  vfio/iommufd: invariant device name
  vfio/iommufd: use IOMMU_IOAS_MAP_FILE
  physmem: qemu_ram_get_fd_offset
  backends/iommufd: change process ioctl
  backends/iommufd: iommufd_backend_map_file_dma
  migration: cpr_get_fd_param helper
  migration: close kvm after cpr
  vfio-pci: preserve INTx
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

7 files changed, 71 insertions, 6 deletions

diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index a684855..9b658a3 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -85,6 +85,7 @@ void qemu_ram_unset_idstr(RAMBlock *block);
 const char *qemu_ram_get_idstr(RAMBlock *rb);
 void *qemu_ram_get_host_addr(RAMBlock *rb);
 ram_addr_t qemu_ram_get_offset(RAMBlock *rb);
+ram_addr_t qemu_ram_get_fd_offset(RAMBlock *rb);
 ram_addr_t qemu_ram_get_used_length(RAMBlock *rb);
 ram_addr_t qemu_ram_get_max_length(RAMBlock *rb);
 bool qemu_ram_is_shared(RAMBlock *rb);
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 3cd86ec..bded6e9 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -168,6 +168,21 @@ struct VFIOIOMMUClass {
                    hwaddr iova, ram_addr_t size,
                    void *vaddr, bool readonly, MemoryRegion *mr);
     /**
+     * @dma_map_file
+     *
+     * Map a file range for the container.
+     *
+     * @bcontainer: #VFIOContainerBase to use for map
+     * @iova: start address to map
+     * @size: size of the range to map
+     * @fd: descriptor of the file to map
+     * @start: starting file offset of the range to map
+     * @readonly: map read only if true
+     */
+    int (*dma_map_file)(const VFIOContainerBase *bcontainer,
+                        hwaddr iova, ram_addr_t size,
+                        int fd, unsigned long start, bool readonly);
+    /**
      * @dma_unmap
      *
      * Unmap an address range from the container.
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index 8bf85b9..80ad20d 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -15,19 +15,27 @@
 struct VFIOContainer;
 struct VFIOContainerBase;
 struct VFIOGroup;
+struct VFIODevice;
+struct VFIOPCIDevice;
+struct VFIOIOMMUFDContainer;
+struct IOMMUFDBackend;
+
+typedef int (*dma_map_fn)(const struct VFIOContainerBase *bcontainer,
+                          hwaddr iova, ram_addr_t size, void *vaddr,
+                          bool readonly, MemoryRegion *mr);
 
 typedef struct VFIOContainerCPR {
     Error *blocker;
     bool vaddr_unmapped;
     NotifierWithReturn transfer_notifier;
     MemoryListener remap_listener;
-    int (*saved_dma_map)(const struct VFIOContainerBase *bcontainer,
-                         hwaddr iova, ram_addr_t size,
-                         void *vaddr, bool readonly, MemoryRegion *mr);
 } VFIOContainerCPR;
 
 typedef struct VFIODeviceCPR {
     Error *mdev_blocker;
+    Error *id_blocker;
+    uint32_t hwpt_id;
+    uint32_t ioas_id;
 } VFIODeviceCPR;
 
 bool vfio_legacy_cpr_register_container(struct VFIOContainer *container,
@@ -37,9 +45,15 @@ void vfio_legacy_cpr_unregister_container(struct VFIOContainer *container);
 int vfio_cpr_reboot_notifier(NotifierWithReturn *notifier, MigrationEvent *e,
                              Error **errp);
 
-bool vfio_cpr_register_container(struct VFIOContainerBase *bcontainer,
-                                 Error **errp);
-void vfio_cpr_unregister_container(struct VFIOContainerBase *bcontainer);
+bool vfio_iommufd_cpr_register_container(struct VFIOIOMMUFDContainer *container,
+                                         Error **errp);
+void vfio_iommufd_cpr_unregister_container(
+    struct VFIOIOMMUFDContainer *container);
+bool vfio_iommufd_cpr_register_iommufd(struct IOMMUFDBackend *be, Error **errp);
+void vfio_iommufd_cpr_unregister_iommufd(struct IOMMUFDBackend *be);
+void vfio_iommufd_cpr_register_device(struct VFIODevice *vbasedev);
+void vfio_iommufd_cpr_unregister_device(struct VFIODevice *vbasedev);
+void vfio_cpr_load_device(struct VFIODevice *vbasedev);
 
 int vfio_cpr_group_get_device_fd(int d, const char *name);
 
@@ -52,6 +66,16 @@ void vfio_cpr_giommu_remap(struct VFIOContainerBase *bcontainer,
 bool vfio_cpr_ram_discard_register_listener(
     struct VFIOContainerBase *bcontainer, MemoryRegionSection *section);
 
+void vfio_cpr_save_vector_fd(struct VFIOPCIDevice *vdev, const char *name,
+                             int nr, int fd);
+int vfio_cpr_load_vector_fd(struct VFIOPCIDevice *vdev, const char *name,
+                            int nr);
+void vfio_cpr_delete_vector_fd(struct VFIOPCIDevice *vdev, const char *name,
+                               int nr);
+
 extern const VMStateDescription vfio_cpr_pci_vmstate;
+extern const VMStateDescription vmstate_cpr_vfio_devices;
+
+void vfio_cpr_add_kvm_notifier(void);
 
 #endif /* HW_VFIO_VFIO_CPR_H */
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index c616652..1901a35 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -279,8 +279,11 @@ int vfio_device_get_irq_info(VFIODevice *vbasedev, int index,
 
 /* Returns 0 on success, or a negative errno. */
 bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp);
+void vfio_device_free_name(VFIODevice *vbasedev);
 void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
 void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
                       DeviceState *dev, bool ram_discard);
 int vfio_device_get_aw_bits(VFIODevice *vdev);
+
+void vfio_kvm_device_close(void);
 #endif /* HW_VFIO_VFIO_COMMON_H */
diff --git a/include/migration/cpr.h b/include/migration/cpr.h
index 07858e9..3fc19a7 100644
--- a/include/migration/cpr.h
+++ b/include/migration/cpr.h
@@ -9,11 +9,23 @@
 #define MIGRATION_CPR_H
 
 #include "qapi/qapi-types-migration.h"
+#include "qemu/queue.h"
 
 #define MIG_MODE_NONE           -1
 
 #define QEMU_CPR_FILE_MAGIC     0x51435052
 #define QEMU_CPR_FILE_VERSION   0x00000001
+#define CPR_STATE "CprState"
+
+typedef QLIST_HEAD(CprFdList, CprFd) CprFdList;
+typedef QLIST_HEAD(CprVFIODeviceList, CprVFIODevice) CprVFIODeviceList;
+
+typedef struct CprState {
+    CprFdList fds;
+    CprVFIODeviceList vfio_devices;
+} CprState;
+
+extern CprState cpr_state;
 
 void cpr_save_fd(const char *name, int id, int fd);
 void cpr_delete_fd(const char *name, int id);
@@ -32,6 +44,8 @@ void cpr_state_close(void);
 struct QIOChannel *cpr_state_ioc(void);
 
 bool cpr_incoming_needed(void *opaque);
+int cpr_get_fd_param(const char *name, const char *fdname, int index,
+                     Error **errp);
 
 QEMUFile *cpr_transfer_output(MigrationChannel *channel, Error **errp);
 QEMUFile *cpr_transfer_input(MigrationChannel *channel, Error **errp);
diff --git a/include/system/iommufd.h b/include/system/iommufd.h
index 283861b..c9c72ff 100644
--- a/include/system/iommufd.h
+++ b/include/system/iommufd.h
@@ -32,6 +32,7 @@ struct IOMMUFDBackend {
     /*< protected >*/
     int fd;            /* /dev/iommu file descriptor */
     bool owned;        /* is the /dev/iommu opened internally */
+    Error *cpr_blocker;/* set if be does not support CPR */
     uint32_t users;
 
     /*< public >*/
@@ -43,6 +44,9 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be);
 bool iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id,
                                 Error **errp);
 void iommufd_backend_free_id(IOMMUFDBackend *be, uint32_t id);
+int iommufd_backend_map_file_dma(IOMMUFDBackend *be, uint32_t ioas_id,
+                                 hwaddr iova, ram_addr_t size, int fd,
+                                 unsigned long start, bool readonly);
 int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova,
                             ram_addr_t size, void *vaddr, bool readonly);
 int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
@@ -66,6 +70,9 @@ bool iommufd_backend_invalidate_cache(IOMMUFDBackend *be, uint32_t id,
                                       uint32_t *entry_num, void *data,
                                       Error **errp);
 
+bool iommufd_change_process_capable(IOMMUFDBackend *be);
+bool iommufd_change_process(IOMMUFDBackend *be, Error **errp);
+
 #define TYPE_HOST_IOMMU_DEVICE_IOMMUFD TYPE_HOST_IOMMU_DEVICE "-iommufd"
 OBJECT_DECLARE_TYPE(HostIOMMUDeviceIOMMUFD, HostIOMMUDeviceIOMMUFDClass,
                     HOST_IOMMU_DEVICE_IOMMUFD)
diff --git a/include/system/kvm.h b/include/system/kvm.h
index 7cc60d2..4896a3c 100644
--- a/include/system/kvm.h
+++ b/include/system/kvm.h
@@ -195,6 +195,7 @@ bool kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_max_nested_state_length(void);
 int kvm_has_gsi_routing(void);
+void kvm_close(void);
 
 /**
  * kvm_arm_supports_user_irq