Merge tag 'pull-vfio-20250306' of https://github.com/legoater/qemu into staging

vfio queue:

* Added property documentation
* Added Minor fixes
* Implemented basic PCI PM capability backing
* Promoted new IGD maintainer
* Deprecated vfio-plaform
* Extended VFIO migration with multifd support

# -----BEGIN PGP SIGNATURE-----
#
# iQIyBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmfJrZoACgkQUaNDx8/7
# 7KFE2A/0Dmief9u/dDJIKGIDa+iawcf4hu8iX4v5pB0DlGniT3rgK8WMGnhDpPxq
# Q4wsKfo+JJ2q6msInrT7Ckqyydu9nQztI3vwmfMuWxLhTMyH28K96ptwPqIZBjOx
# rPTEXfnVX4W3tpn1+48S+vefWVa/gkBkIvv7RpK18rMBXv1kDeyOvc/d2dbAt7ft
# zJc4f8gH3jfQzGwmnYVZU1yPrZN7p6zhYR/AD3RQOY97swgZIEyYxXhOuTPiCuEC
# zC+2AMKi9nmnCG6x/mnk7l2yJXSlv7lJdqcjYZhJ9EOIYfiUGTREYIgQbARcafE/
# 4KSg2QR35BoUd4YrmEWxXJCRf3XnyWXDY36dDKVhC0OHng1F/U44HuL4QxwoTIay
# s1SP/DHcvDiPAewVTvdgt7Iwfn9xGhcQO2pkrxBoNLB5JYwW+R6mG7WXeDv1o3GT
# QosTu1fXZezQqFd4v6+q5iRNS2KtBZLTspwAmVdywEFUs+ZLBRlC+bodYlinZw6B
# Yl/z0LfAEh4J55QmX2espbp8MH1+mALuW2H2tgSGSrTBX1nwxZFI5veFzPepgF2S
# eTx69BMjiNMwzIjq1T7e9NpDCceiW0fXDu7IK1MzYhqg1nM9lX9AidhFTeiF2DB2
# EPb3ljy/8fyxcPKa1T9X47hQaSjbMwofaO8Snoh0q0jokY246Q==
# =hIBw
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 06 Mar 2025 22:13:46 HKT
# 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-20250306' of https://github.com/legoater/qemu: (42 commits)
  hw/core/machine: Add compat for x-migration-multifd-transfer VFIO property
  vfio/migration: Make x-migration-multifd-transfer VFIO property mutable
  vfio/migration: Add x-migration-multifd-transfer VFIO property
  vfio/migration: Multifd device state transfer support - send side
  vfio/migration: Multifd device state transfer support - config loading support
  migration/qemu-file: Define g_autoptr() cleanup function for QEMUFile
  vfio/migration: Multifd device state transfer support - load thread
  vfio/migration: Multifd device state transfer support - received buffers queuing
  vfio/migration: Setup and cleanup multifd transfer in these general methods
  vfio/migration: Multifd setup/cleanup functions and associated VFIOMultifd
  vfio/migration: Multifd device state transfer - add support checking function
  vfio/migration: Multifd device state transfer support - basic types
  vfio/migration: Move migration channel flags to vfio-common.h header file
  vfio/migration: Add vfio_add_bytes_transferred()
  vfio/migration: Convert bytes_transferred counter to atomic
  vfio/migration: Add load_device_config_state_start trace event
  migration: Add save_live_complete_precopy_thread handler
  migration/multifd: Add multifd_device_state_supported()
  migration/multifd: Make MultiFDSendData a struct
  migration/multifd: Device state transfer support - send side
  ...

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

11 files changed, 184 insertions, 13 deletions

diff --git a/include/block/aio.h b/include/block/aio.h
index 43883a8a33..b2ab3514de 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -54,7 +54,7 @@ typedef void QEMUBHFunc(void *opaque);
 typedef bool AioPollFn(void *opaque);
 typedef void IOHandler(void *opaque);
 
-struct ThreadPool;
+struct ThreadPoolAio;
 struct LinuxAioState;
 typedef struct LuringState LuringState;
 
@@ -207,7 +207,7 @@ struct AioContext {
     /* Thread pool for performing work and receiving completion callbacks.
      * Has its own locking.
      */
-    struct ThreadPool *thread_pool;
+    struct ThreadPoolAio *thread_pool;
 
 #ifdef CONFIG_LINUX_AIO
     struct LinuxAioState *linux_aio;
@@ -500,8 +500,8 @@ void aio_set_event_notifier_poll(AioContext *ctx,
  */
 GSource *aio_get_g_source(AioContext *ctx);
 
-/* Return the ThreadPool bound to this AioContext */
-struct ThreadPool *aio_get_thread_pool(AioContext *ctx);
+/* Return the ThreadPoolAio bound to this AioContext */
+struct ThreadPoolAio *aio_get_thread_pool(AioContext *ctx);
 
 /* Setup the LinuxAioState bound to this AioContext */
 struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp);
diff --git a/include/block/thread-pool.h b/include/block/thread-pool.h
index 948ff5f30c..dd48cf07e8 100644
--- a/include/block/thread-pool.h
+++ b/include/block/thread-pool.h
@@ -24,20 +24,70 @@
 
 typedef int ThreadPoolFunc(void *opaque);
 
-typedef struct ThreadPool ThreadPool;
+typedef struct ThreadPoolAio ThreadPoolAio;
 
-ThreadPool *thread_pool_new(struct AioContext *ctx);
-void thread_pool_free(ThreadPool *pool);
+ThreadPoolAio *thread_pool_new_aio(struct AioContext *ctx);
+void thread_pool_free_aio(ThreadPoolAio *pool);
 
 /*
- * thread_pool_submit* API: submit I/O requests in the thread's
+ * thread_pool_submit_{aio,co} API: submit I/O requests in the thread's
  * current AioContext.
  */
 BlockAIOCB *thread_pool_submit_aio(ThreadPoolFunc *func, void *arg,
                                    BlockCompletionFunc *cb, void *opaque);
 int coroutine_fn thread_pool_submit_co(ThreadPoolFunc *func, void *arg);
-void thread_pool_submit(ThreadPoolFunc *func, void *arg);
+void thread_pool_update_params(ThreadPoolAio *pool, struct AioContext *ctx);
+
+/* ------------------------------------------- */
+/* Generic thread pool types and methods below */
+typedef struct ThreadPool ThreadPool;
+
+/* Create a new thread pool. Never returns NULL. */
+ThreadPool *thread_pool_new(void);
+
+/*
+ * Free the thread pool.
+ * Waits for all the previously submitted work to complete before performing
+ * the actual freeing operation.
+ */
+void thread_pool_free(ThreadPool *pool);
+
+/*
+ * Submit a new work (task) for the pool.
+ *
+ * @opaque_destroy is an optional GDestroyNotify for the @opaque argument
+ * to the work function at @func.
+ */
+void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func,
+                        void *opaque, GDestroyNotify opaque_destroy);
+
+/*
+ * Submit a new work (task) for the pool, making sure it starts getting
+ * processed immediately, launching a new thread for it if necessary.
+ *
+ * @opaque_destroy is an optional GDestroyNotify for the @opaque argument
+ * to the work function at @func.
+ */
+void thread_pool_submit_immediate(ThreadPool *pool, ThreadPoolFunc *func,
+                                  void *opaque, GDestroyNotify opaque_destroy);
+
+/*
+ * Wait for all previously submitted work to complete before returning.
+ *
+ * Can be used as a barrier between two sets of tasks executed on a thread
+ * pool without destroying it or in a performance sensitive path where the
+ * caller just wants to wait for all tasks to complete while deferring the
+ * pool free operation for later, less performance sensitive time.
+ */
+void thread_pool_wait(ThreadPool *pool);
 
-void thread_pool_update_params(ThreadPool *pool, struct AioContext *ctx);
+/* Set the maximum number of threads in the pool. */
+bool thread_pool_set_max_threads(ThreadPool *pool, int max_threads);
+
+/*
+ * Adjust the maximum number of threads in the pool to give each task its
+ * own thread (exactly one thread per task).
+ */
+bool thread_pool_adjust_max_threads_to_work(ThreadPool *pool);
 
 #endif
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 4002bbeebd..c220cc8449 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -216,6 +216,8 @@ enum {
     QEMU_PCIE_ARI_NEXTFN_1 = (1 << QEMU_PCIE_ARI_NEXTFN_1_BITNR),
 #define QEMU_PCIE_EXT_TAG_BITNR 13
     QEMU_PCIE_EXT_TAG = (1 << QEMU_PCIE_EXT_TAG_BITNR),
+#define QEMU_PCI_CAP_PM_BITNR 14
+    QEMU_PCI_CAP_PM = (1 << QEMU_PCI_CAP_PM_BITNR),
 };
 
 typedef struct PCIINTxRoute {
@@ -676,5 +678,6 @@ static inline void pci_irq_deassert(PCIDevice *pci_dev)
 MSIMessage pci_get_msi_message(PCIDevice *dev, int vector);
 void pci_set_enabled(PCIDevice *pci_dev, bool state);
 void pci_set_power(PCIDevice *pci_dev, bool state);
+int pci_pm_init(PCIDevice *pci_dev, uint8_t offset, Error **errp);
 
 #endif
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index add208edfa..345b12eaac 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -105,6 +105,9 @@ struct PCIDevice {
     /* Capability bits */
     uint32_t cap_present;
 
+    /* Offset of PM capability in config space */
+    uint8_t pm_cap;
+
     /* Offset of MSI-X capability in config space */
     uint8_t msix_cap;
 
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index b8d59732bc..70a5de09de 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -58,8 +58,6 @@ typedef enum {
 struct PCIExpressDevice {
     /* Offset of express capability in config space */
     uint8_t exp_cap;
-    /* Offset of Power Management capability in config space */
-    uint8_t pm_cap;
 
     /* SLOT */
     bool hpev_notified; /* Logical AND of conditions for hot plug event.
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index ac35136a11..04b123a6c9 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -36,6 +36,23 @@
 
 #define VFIO_MSG_PREFIX "vfio %s: "
 
+/*
+ * Flags to be used as unique delimiters for VFIO devices in the migration
+ * stream. These flags are composed as:
+ * 0xffffffff => MSB 32-bit all 1s
+ * 0xef10     => Magic ID, represents emulated (virtual) function IO
+ * 0x0000     => 16-bits reserved for flags
+ *
+ * The beginning of state information is marked by _DEV_CONFIG_STATE,
+ * _DEV_SETUP_STATE, or _DEV_DATA_STATE, respectively. The end of a
+ * certain state information is marked by _END_OF_STATE.
+ */
+#define VFIO_MIG_FLAG_END_OF_STATE      (0xffffffffef100001ULL)
+#define VFIO_MIG_FLAG_DEV_CONFIG_STATE  (0xffffffffef100002ULL)
+#define VFIO_MIG_FLAG_DEV_SETUP_STATE   (0xffffffffef100003ULL)
+#define VFIO_MIG_FLAG_DEV_DATA_STATE    (0xffffffffef100004ULL)
+#define VFIO_MIG_FLAG_DEV_INIT_DATA_SENT (0xffffffffef100005ULL)
+
 enum {
     VFIO_DEVICE_TYPE_PCI = 0,
     VFIO_DEVICE_TYPE_PLATFORM = 1,
@@ -61,6 +78,8 @@ typedef struct VFIORegion {
     uint8_t nr; /* cache the region number for debug */
 } VFIORegion;
 
+typedef struct VFIOMultifd VFIOMultifd;
+
 typedef struct VFIOMigration {
     struct VFIODevice *vbasedev;
     VMChangeStateEntry *vm_state;
@@ -72,6 +91,8 @@ typedef struct VFIOMigration {
     uint64_t mig_flags;
     uint64_t precopy_init_size;
     uint64_t precopy_dirty_size;
+    bool multifd_transfer;
+    VFIOMultifd *multifd;
     bool initial_data_sent;
 
     bool event_save_iterate_started;
@@ -133,6 +154,7 @@ typedef struct VFIODevice {
     bool no_mmap;
     bool ram_block_discard_allowed;
     OnOffAuto enable_migration;
+    OnOffAuto migration_multifd_transfer;
     bool migration_events;
     VFIODeviceOps *ops;
     unsigned int num_irqs;
@@ -274,9 +296,13 @@ void vfio_unblock_multiple_devices_migration(void);
 bool vfio_viommu_preset(VFIODevice *vbasedev);
 int64_t vfio_mig_bytes_transferred(void);
 void vfio_reset_bytes_transferred(void);
+void vfio_mig_add_bytes_transferred(unsigned long val);
 bool vfio_device_state_is_running(VFIODevice *vbasedev);
 bool vfio_device_state_is_precopy(VFIODevice *vbasedev);
 
+int vfio_save_device_config_state(QEMUFile *f, void *opaque, Error **errp);
+int vfio_load_device_config_state(QEMUFile *f, void *opaque);
+
 #ifdef CONFIG_LINUX
 int vfio_get_region_info(VFIODevice *vbasedev, int index,
                          struct vfio_region_info **info);
@@ -291,6 +317,11 @@ struct vfio_info_cap_header *
 vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id);
 struct vfio_info_cap_header *
 vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id);
+
+int vfio_migration_set_state(VFIODevice *vbasedev,
+                             enum vfio_device_mig_state new_state,
+                             enum vfio_device_mig_state recover_state,
+                             Error **errp);
 #endif
 
 bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp);
diff --git a/include/migration/client-options.h b/include/migration/client-options.h
index 59f4b55cf4..289c9d7762 100644
--- a/include/migration/client-options.h
+++ b/include/migration/client-options.h
@@ -10,6 +10,10 @@
 #ifndef QEMU_MIGRATION_CLIENT_OPTIONS_H
 #define QEMU_MIGRATION_CLIENT_OPTIONS_H
 
+
+/* properties */
+bool migrate_send_switchover_start(void);
+
 /* capabilities */
 
 bool migrate_background_snapshot(void);
diff --git a/include/migration/misc.h b/include/migration/misc.h
index c660be8095..8fd36eba1d 100644
--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@@ -45,9 +45,12 @@ bool migrate_ram_is_ignored(RAMBlock *block);
 /* migration/block.c */
 
 AnnounceParameters *migrate_announce_params(void);
+
 /* migration/savevm.c */
 
 void dump_vmstate_json_to_file(FILE *out_fp);
+void qemu_loadvm_start_load_thread(MigrationLoadThread function,
+                                   void *opaque);
 
 /* migration/migration.c */
 void migration_object_init(void);
@@ -115,4 +118,26 @@ bool migrate_is_uri(const char *uri);
 bool migrate_uri_parse(const char *uri, MigrationChannel **channel,
                        Error **errp);
 
+/* migration/multifd-device-state.c */
+typedef struct SaveLiveCompletePrecopyThreadData {
+    SaveLiveCompletePrecopyThreadHandler hdlr;
+    char *idstr;
+    uint32_t instance_id;
+    void *handler_opaque;
+} SaveLiveCompletePrecopyThreadData;
+
+bool multifd_queue_device_state(char *idstr, uint32_t instance_id,
+                                char *data, size_t len);
+bool multifd_device_state_supported(void);
+
+void
+multifd_spawn_device_state_save_thread(SaveLiveCompletePrecopyThreadHandler hdlr,
+                                       char *idstr, uint32_t instance_id,
+                                       void *opaque);
+
+bool multifd_device_state_save_thread_should_exit(void);
+
+void multifd_abort_device_state_save_threads(void);
+bool multifd_join_device_state_save_threads(void);
+
 #endif
diff --git a/include/migration/register.h b/include/migration/register.h
index f60e797894..c041ce32f2 100644
--- a/include/migration/register.h
+++ b/include/migration/register.h
@@ -69,7 +69,9 @@ typedef struct SaveVMHandlers {
     /**
      * @save_cleanup
      *
-     * Uninitializes the data structures on the source
+     * Uninitializes the data structures on the source.
+     * Note that this handler can be called even if save_setup
+     * wasn't called earlier.
      *
      * @opaque: data pointer passed to register_savevm_live()
      */
@@ -103,6 +105,25 @@ typedef struct SaveVMHandlers {
      */
     int (*save_live_complete_precopy)(QEMUFile *f, void *opaque);
 
+    /**
+     * @save_live_complete_precopy_thread (invoked in a separate thread)
+     *
+     * Called at the end of a precopy phase from a separate worker thread
+     * in configurations where multifd device state transfer is supported
+     * in order to perform asynchronous transmission of the remaining data in
+     * parallel with @save_live_complete_precopy handlers.
+     * When postcopy is enabled, devices that support postcopy will skip this
+     * step.
+     *
+     * @d: a #SaveLiveCompletePrecopyThreadData containing parameters that the
+     * handler may need, including this device section idstr and instance_id,
+     * and opaque data pointer passed to register_savevm_live().
+     * @errp: pointer to Error*, to store an error if it happens.
+     *
+     * Returns true to indicate success and false for errors.
+     */
+    SaveLiveCompletePrecopyThreadHandler save_live_complete_precopy_thread;
+
     /* This runs both outside and inside the BQL.  */
 
     /**
@@ -228,6 +249,21 @@ typedef struct SaveVMHandlers {
     int (*load_state)(QEMUFile *f, void *opaque, int version_id);
 
     /**
+     * @load_state_buffer (invoked outside the BQL)
+     *
+     * Load device state buffer provided to qemu_loadvm_load_state_buffer().
+     *
+     * @opaque: data pointer passed to register_savevm_live()
+     * @buf: the data buffer to load
+     * @len: the data length in buffer
+     * @errp: pointer to Error*, to store an error if it happens.
+     *
+     * Returns true to indicate success and false for errors.
+     */
+    bool (*load_state_buffer)(void *opaque, char *buf, size_t len,
+                              Error **errp);
+
+    /**
      * @load_setup
      *
      * Initializes the data structures on the destination.
@@ -244,6 +280,8 @@ typedef struct SaveVMHandlers {
      * @load_cleanup
      *
      * Uninitializes the data structures on the destination.
+     * Note that this handler can be called even if load_setup
+     * wasn't called earlier.
      *
      * @opaque: data pointer passed to register_savevm_live()
      *
@@ -275,6 +313,18 @@ typedef struct SaveVMHandlers {
      * otherwise
      */
     bool (*switchover_ack_needed)(void *opaque);
+
+    /**
+     * @switchover_start
+     *
+     * Notifies that the switchover has started. Called only on
+     * the destination.
+     *
+     * @opaque: data pointer passed to register_savevm_live()
+     *
+     * Returns zero to indicate success and negative for error
+     */
+    int (*switchover_start)(void *opaque);
 } SaveVMHandlers;
 
 /**
diff --git a/include/qapi/error.h b/include/qapi/error.h
index f5fe216262..41e3816380 100644
--- a/include/qapi/error.h
+++ b/include/qapi/error.h
@@ -437,6 +437,8 @@ Error *error_copy(const Error *err);
  */
 void error_free(Error *err);
 
+G_DEFINE_AUTOPTR_CLEANUP_FUNC(Error, error_free)
+
 /*
  * Convenience function to assert that *@errp is set, then silently free it.
  */
diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h
index 3d84efcac4..42ed4e6be1 100644
--- a/include/qemu/typedefs.h
+++ b/include/qemu/typedefs.h
@@ -108,6 +108,7 @@ typedef struct QString QString;
 typedef struct RAMBlock RAMBlock;
 typedef struct Range Range;
 typedef struct ReservedRegion ReservedRegion;
+typedef struct SaveLiveCompletePrecopyThreadData SaveLiveCompletePrecopyThreadData;
 typedef struct SHPCDevice SHPCDevice;
 typedef struct SSIBus SSIBus;
 typedef struct TCGCPUOps TCGCPUOps;
@@ -131,5 +132,9 @@ typedef struct IRQState *qemu_irq;
  * Function types
  */
 typedef void (*qemu_irq_handler)(void *opaque, int n, int level);
+typedef bool (*MigrationLoadThread)(void *opaque, bool *should_quit,
+                                    Error **errp);
+typedef bool (*SaveLiveCompletePrecopyThreadHandler)(SaveLiveCompletePrecopyThreadData *d,
+                                                     Error **errp);
 
 #endif /* QEMU_TYPEDEFS_H */