Merge tag 'staging-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration/Memory Pull for 10.2

- PeterX's fix on tls warning for preempt channel when migratino completes
- Arun's series to enhance error reporting for vTPM and migration framework
- PeterX's patch to cleanup multifd send TLS BYE messages
- Juraj's fix on postcopy start state transition when switchover failed
- Yanfei's fix to migrate APIC before VFIO-PCI to avoid irq fallbacks
- Dan's cleanup to simplify error reporting in qemu_fill_buffer()
- PeterM's fix on address space leak when cpu hot plug / unplug
- Steve's cpr-exec wholeset

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCaN/uIhIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wZ+mAEA1l2RS9sZS1W3vXQMCNb+Nu8Uo2p+e5Qj
# Uu6J0WVV+XsBANtzGZk2UM/frqlABywW3/ozJ4qBvIPKo758Mr6/lqUH
# =asUv
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 03 Oct 2025 08:39:14 AM PDT
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [unknown]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [unknown]
# 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: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'staging-pull-request' of https://gitlab.com/peterx/qemu: (45 commits)
  migration-test: test cpr-exec
  vfio: cpr-exec mode
  migration: cpr-exec docs
  migration: cpr-exec mode
  migration: cpr-exec save and load
  migration: cpr-exec-command parameter
  oslib: qemu_clear_cloexec
  migration: add cpr_walk_fd
  migration: multi-mode notifier
  migration: simplify error reporting after channel read
  physmem: Destroy all CPU AddressSpaces on unrealize
  memory: New AS helper to serialize destroy+free
  include/system/memory.h: Clarify address_space_destroy() behaviour
  migration: ensure APIC is loaded prior to VFIO PCI devices
  migration: Fix state transition in postcopy_start() error handling
  migration/multifd/tls: Cleanup BYE message processing on sender side
  migration: HMP: Adjust the order of output fields
  migration: Make migration_has_failed() work even for CANCELLING
  io/crypto: Move tls premature termination handling into QIO layer
  backends/tpm: Propagate vTPM error on migration failure
  ...

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

include/crypto/tlssession.h

@@ -110,6 +110,7 @@
 typedef struct QCryptoTLSSession QCryptoTLSSession;
 
 #define QCRYPTO_TLS_SESSION_ERR_BLOCK -2
+#define QCRYPTO_TLS_SESSION_PREMATURE_TERMINATION -3
 
 /**
  * qcrypto_tls_session_new:
@@ -259,7 +260,6 @@ ssize_t qcrypto_tls_session_write(QCryptoTLSSession *sess,
  * @sess: the TLS session object
  * @buf: to fill with plain text received
  * @len: the length of @buf
- * @gracefulTermination: treat premature termination as graceful EOF
  * @errp: pointer to hold returned error object
  *
  * Receive up to @len bytes of data from the remote peer
@@ -267,22 +267,18 @@ ssize_t qcrypto_tls_session_write(QCryptoTLSSession *sess,
  * qcrypto_tls_session_set_callbacks(), decrypt it and
  * store it in @buf.
  *
- * If @gracefulTermination is true, then a premature termination
- * of the TLS session will be treated as indicating EOF, as
- * opposed to an error.
- *
  * It is an error to call this before
  * qcrypto_tls_session_handshake() returns
  * QCRYPTO_TLS_HANDSHAKE_COMPLETE
  *
  * Returns: the number of bytes received,
  * or QCRYPTO_TLS_SESSION_ERR_BLOCK if the receive would block,
- * or -1 on error.
+ * or QCRYPTO_TLS_SESSION_PREMATURE_TERMINATION if a premature termination
+ * is detected, or -1 on error.
  */
 ssize_t qcrypto_tls_session_read(QCryptoTLSSession *sess,
                                  char *buf,
                                  size_t len,
-                                 bool gracefulTermination,
                                  Error **errp);
 
 /**

include/exec/cpu-common.h

@@ -123,13 +123,13 @@ 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
+ * cpu_destroy_address_spaces:
+ * @cpu: CPU for which address spaces need to be destroyed
  *
- * Note that with KVM only one address space is supported.
+ * Destroy all address spaces associated with this CPU; this
+ * is called as part of unrealizing the CPU.
  */
-void cpu_address_space_destroy(CPUState *cpu, int asidx);
+void cpu_destroy_address_spaces(CPUState *cpu);
 
 void cpu_physical_memory_rw(hwaddr addr, void *buf,
                             hwaddr len, bool is_write);

include/hw/core/cpu.h

@@ -515,7 +515,6 @@ 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/migration/colo.h

@@ -25,7 +25,7 @@ void migrate_start_colo_process(MigrationState *s);
 bool migration_in_colo_state(void);
 
 /* loadvm */
-int migration_incoming_enable_colo(void);
+int migration_incoming_enable_colo(Error **errp);
 void migration_incoming_disable_colo(void);
 bool migration_incoming_colo_enabled(void);
 bool migration_incoming_in_colo_state(void);

include/migration/cpr.h

@@ -34,6 +34,9 @@ void cpr_resave_fd(const char *name, int id, int fd);
 int cpr_open_fd(const char *path, int flags, const char *name, int id,
                 Error **errp);
 
+typedef bool (*cpr_walk_fd_cb)(int fd);
+bool cpr_walk_fd(cpr_walk_fd_cb cb);
+
 MigMode cpr_get_incoming_mode(void);
 void cpr_set_incoming_mode(MigMode mode);
 bool cpr_is_incoming(void);
@@ -50,4 +53,11 @@ int cpr_get_fd_param(const char *name, const char *fdname, int index,
 QEMUFile *cpr_transfer_output(MigrationChannel *channel, Error **errp);
 QEMUFile *cpr_transfer_input(MigrationChannel *channel, Error **errp);
 
+void cpr_exec_init(void);
+QEMUFile *cpr_exec_output(Error **errp);
+QEMUFile *cpr_exec_input(Error **errp);
+void cpr_exec_persist_state(QEMUFile *f);
+bool cpr_exec_has_state(void);
+void cpr_exec_unpersist_state(void);
+void cpr_exec_unpreserve_fds(void);
 #endif

include/migration/misc.h

@@ -95,7 +95,19 @@ void migration_add_notifier(NotifierWithReturn *notify,
 void migration_add_notifier_mode(NotifierWithReturn *notify,
                                  MigrationNotifyFunc func, MigMode mode);
 
+/*
+ * Same as migration_add_notifier, but applies to all @mode in the argument
+ * list.  The list is terminated by -1 or MIG_MODE_ALL.  For the latter,
+ * the notifier is added for all modes.
+ */
+void migration_add_notifier_modes(NotifierWithReturn *notify,
+                                  MigrationNotifyFunc func, MigMode mode, ...);
+
+/*
+ * Remove a notifier from all modes.
+ */
 void migration_remove_notifier(NotifierWithReturn *notify);
+
 void migration_file_set_error(int ret, Error *err);
 
 /* True if incoming migration entered POSTCOPY_INCOMING_DISCARD */

include/migration/vmstate.h

@@ -163,6 +163,7 @@ typedef enum {
     MIG_PRI_IOMMU,              /* Must happen before PCI devices */
     MIG_PRI_PCI_BUS,            /* Must happen before IOMMU */
     MIG_PRI_VIRTIO_MEM,         /* Must happen before IOMMU */
+    MIG_PRI_APIC,               /* Must happen before PCI devices */
     MIG_PRI_GICV3_ITS,          /* Must happen before PCI devices */
     MIG_PRI_GICV3,              /* Must happen before the ITS */
     MIG_PRI_MAX,
@@ -200,14 +201,28 @@ struct VMStateDescription {
      * exclusive. For this reason, also early_setup VMSDs are migrated in a
      * QEMU_VM_SECTION_FULL section, while save_setup() data is migrated in
      * a QEMU_VM_SECTION_START section.
+     *
+     * There are duplicate impls of the post/pre save/load hooks.
+     * New impls should preferentally use 'errp' variants of these
+     * methods and existing impls incrementally converted.
+     * The variants without 'errp' are intended to be removed
+     * once all usage is converted.
+     *
+     * For the errp variants,
+     * Returns: 0 on success,
+     *          <0 on error where -value is an error number from errno.h
      */
+
     bool early_setup;
     int version_id;
     int minimum_version_id;
     MigrationPriority priority;
     int (*pre_load)(void *opaque);
+    int (*pre_load_errp)(void *opaque, Error **errp);
     int (*post_load)(void *opaque, int version_id);
+    int (*post_load_errp)(void *opaque, int version_id, Error **errp);
     int (*pre_save)(void *opaque);
+    int (*pre_save_errp)(void *opaque, Error **errp);
     int (*post_save)(void *opaque);
     bool (*needed)(void *opaque);
     bool (*dev_unplug_pending)(void *opaque);
@@ -1206,10 +1221,8 @@ extern const VMStateInfo vmstate_info_qlist;
     }
 
 int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
-                       void *opaque, int version_id);
+                       void *opaque, int version_id, Error **errp);
 int vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd,
-                       void *opaque, JSONWriter *vmdesc);
-int vmstate_save_state_with_err(QEMUFile *f, const VMStateDescription *vmsd,
                        void *opaque, JSONWriter *vmdesc, Error **errp);
 int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd,
                          void *opaque, JSONWriter *vmdesc,

include/qemu/osdep.h

@@ -689,6 +689,15 @@ ssize_t qemu_write_full(int fd, const void *buf, size_t count)
 void qemu_set_cloexec(int fd);
 bool qemu_set_blocking(int fd, bool block, Error **errp);
 
+/*
+ * Clear FD_CLOEXEC for a descriptor.
+ *
+ * The caller must guarantee that no other fork+exec's occur before the
+ * exec that is intended to inherit this descriptor, eg by suspending CPUs
+ * and blocking monitor commands.
+ */
+void qemu_clear_cloexec(int fd);
+
 /* Return a dynamically allocated directory path that is appropriate for storing
  * local state.
  *

include/system/memory.h

@@ -2727,14 +2727,32 @@ void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name);
 /**
  * address_space_destroy: destroy an address space
  *
- * Releases all resources associated with an address space.  After an address space
- * is destroyed, its root memory region (given by address_space_init()) may be destroyed
- * as well.
+ * Releases all resources associated with an address space.  After an
+ * address space is destroyed, the reference the AddressSpace had to
+ * its root memory region is dropped, which may result in the
+ * destruction of that memory region as well.
+ *
+ * Note that destruction of the AddressSpace is done via RCU;
+ * it is therefore not valid to free the memory the AddressSpace
+ * struct is in until after that RCU callback has completed.
+ * If you want to g_free() the AddressSpace after destruction you
+ * can do that with address_space_destroy_free().
  *
  * @as: address space to be destroyed
  */
 void address_space_destroy(AddressSpace *as);
 
+/**
+ * address_space_destroy_free: destroy an address space and free it
+ *
+ * This does the same thing as address_space_destroy(), and then also
+ * frees (via g_free()) the AddressSpace itself once the destruction
+ * is complete.
+ *
+ * @as: address space to be destroyed
+ */
+void address_space_destroy_free(AddressSpace *as);
+
 /**
  * address_space_remove_listeners: unregister all listeners of an address space
  *