Merge tag 'migration-20240423-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull for 9.1

- Het's new test cases for "channels"
- Het's fix for a typo for vsock parsing
- Cedric's VFIO error report series
- Cedric's one more patch for dirty-bitmap error reports
- Zhijian's rdma deprecation patch
- Yuan's zeropage optimization to fix double faults on anon mem
- Zhijian's COLO fix on a crash

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZig4HxIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wbQiwD/V5nSJzSuAG4Ra1Fjo+LRG2TT6qk8eNCi
# fIytehSw6cYA/0wqarxOF0tr7ikeyhtG3w4xFf44kk6KcPkoVSl1tqoL
# =pJmQ
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 Apr 2024 03:37:19 PM 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: This key 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 'migration-20240423-pull-request' of https://gitlab.com/peterx/qemu: (26 commits)
  migration/colo: Fix bdrv_graph_rdlock_main_loop: Assertion `!qemu_in_coroutine()' failed.
  migration/multifd: solve zero page causing multiple page faults
  migration: Add Error** argument to add_bitmaps_to_list()
  migration: Modify ram_init_bitmaps() to report dirty tracking errors
  migration: Add Error** argument to xbzrle_init()
  migration: Add Error** argument to ram_state_init()
  memory: Add Error** argument to the global_dirty_log routines
  migration: Introduce ram_bitmaps_destroy()
  memory: Add Error** argument to .log_global_start() handler
  migration: Add Error** argument to .load_setup() handler
  migration: Add Error** argument to .save_setup() handler
  migration: Add Error** argument to qemu_savevm_state_setup()
  migration: Add Error** argument to vmstate_save()
  migration: Always report an error in ram_save_setup()
  migration: Always report an error in block_save_setup()
  vfio: Always report an error in vfio_save_setup()
  s390/stattrib: Add Error** argument to set_migrationmode() handler
  tests/qtest/migration: Fix typo for vsock in SocketAddress_to_str
  tests/qtest/migration: Add negative tests to validate migration QAPIs
  tests/qtest/migration: Add multifd_tcp_plain test using list of channels instead of uri
  ...

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

hw/i386/xen/xen-hvm.c

@@ -457,11 +457,12 @@ static void xen_log_sync(MemoryListener *listener, MemoryRegionSection *section)
                           int128_get64(section->size));
 }
 
-static void xen_log_global_start(MemoryListener *listener)
+static bool xen_log_global_start(MemoryListener *listener, Error **errp)
 {
     if (xen_enabled()) {
         xen_in_migration = true;
     }
+    return true;
 }
 
 static void xen_log_global_stop(MemoryListener *listener)
@@ -668,7 +669,7 @@ void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length)
 void qmp_xen_set_global_dirty_log(bool enable, Error **errp)
 {
     if (enable) {
-        memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
+        memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION, errp);
     } else {
         memory_global_dirty_log_stop(GLOBAL_DIRTY_MIGRATION);
     }

hw/ppc/spapr.c

@@ -2174,7 +2174,7 @@ static const VMStateDescription vmstate_spapr = {
     }
 };
 
-static int htab_save_setup(QEMUFile *f, void *opaque)
+static int htab_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     SpaprMachineState *spapr = opaque;
 

hw/s390x/s390-stattrib-kvm.c

@@ -17,6 +17,7 @@
 #include "sysemu/kvm.h"
 #include "exec/ram_addr.h"
 #include "kvm/kvm_s390x.h"
+#include "qapi/error.h"
 
 Object *kvm_s390_stattrib_create(void)
 {
@@ -137,14 +138,21 @@ static void kvm_s390_stattrib_synchronize(S390StAttribState *sa)
     }
 }
 
-static int kvm_s390_stattrib_set_migrationmode(S390StAttribState *sa, bool val)
+static int kvm_s390_stattrib_set_migrationmode(S390StAttribState *sa, bool val,
+                                               Error **errp)
 {
     struct kvm_device_attr attr = {
         .group = KVM_S390_VM_MIGRATION,
         .attr = val,
         .addr = 0,
     };
-    return kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
+    int r;
+
+    r = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
+    if (r) {
+        error_setg_errno(errp, -r, "setting KVM_S390_VM_MIGRATION failed");
+    }
+    return r;
 }
 
 static long long kvm_s390_stattrib_get_dirtycount(S390StAttribState *sa)

hw/s390x/s390-stattrib.c

@@ -60,11 +60,13 @@ void hmp_migrationmode(Monitor *mon, const QDict *qdict)
     S390StAttribState *sas = s390_get_stattrib_device();
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
     uint64_t what = qdict_get_int(qdict, "mode");
+    Error *local_err = NULL;
     int r;
 
-    r = sac->set_migrationmode(sas, what);
+    r = sac->set_migrationmode(sas, what, &local_err);
     if (r < 0) {
-        monitor_printf(mon, "Error: %s", strerror(-r));
+        monitor_printf(mon, "Error: %s", error_get_pretty(local_err));
+        error_free(local_err);
     }
 }
 
@@ -166,7 +168,7 @@ static int cmma_load(QEMUFile *f, void *opaque, int version_id)
     return ret;
 }
 
-static int cmma_save_setup(QEMUFile *f, void *opaque)
+static int cmma_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     S390StAttribState *sas = S390_STATTRIB(opaque);
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
@@ -175,7 +177,7 @@ static int cmma_save_setup(QEMUFile *f, void *opaque)
      * Signal that we want to start a migration, thus needing PGSTE dirty
      * tracking.
      */
-    res = sac->set_migrationmode(sas, 1);
+    res = sac->set_migrationmode(sas, true, errp);
     if (res) {
         return res;
     }
@@ -260,7 +262,7 @@ static void cmma_save_cleanup(void *opaque)
 {
     S390StAttribState *sas = S390_STATTRIB(opaque);
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
-    sac->set_migrationmode(sas, 0);
+    sac->set_migrationmode(sas, false, NULL);
 }
 
 static bool cmma_active(void *opaque)
@@ -293,7 +295,8 @@ static long long qemu_s390_get_dirtycount_stub(S390StAttribState *sa)
 {
     return 0;
 }
-static int qemu_s390_set_migrationmode_stub(S390StAttribState *sa, bool value)
+static int qemu_s390_set_migrationmode_stub(S390StAttribState *sa, bool value,
+                                            Error **errp)
 {
     return 0;
 }

hw/vfio/common.c

@@ -1066,7 +1066,8 @@ out:
     return ret;
 }
 
-static void vfio_listener_log_global_start(MemoryListener *listener)
+static bool vfio_listener_log_global_start(MemoryListener *listener,
+                                           Error **errp)
 {
     VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
                                                  listener);
@@ -1083,6 +1084,7 @@ static void vfio_listener_log_global_start(MemoryListener *listener)
                      ret, strerror(-ret));
         vfio_set_migration_error(ret);
     }
+    return !ret;
 }
 
 static void vfio_listener_log_global_stop(MemoryListener *listener)

hw/vfio/migration.c

@@ -376,11 +376,12 @@ static int vfio_save_prepare(void *opaque, Error **errp)
     return 0;
 }
 
-static int vfio_save_setup(QEMUFile *f, void *opaque)
+static int vfio_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
     uint64_t stop_copy_size = VFIO_MIG_DEFAULT_DATA_BUFFER_SIZE;
+    int ret;
 
     qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE);
 
@@ -389,19 +390,19 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
                                       stop_copy_size);
     migration->data_buffer = g_try_malloc0(migration->data_buffer_size);
     if (!migration->data_buffer) {
-        error_report("%s: Failed to allocate migration data buffer",
-                     vbasedev->name);
+        error_setg(errp, "%s: Failed to allocate migration data buffer",
+                   vbasedev->name);
         return -ENOMEM;
     }
 
     if (vfio_precopy_supported(vbasedev)) {
-        int ret;
-
         switch (migration->device_state) {
         case VFIO_DEVICE_STATE_RUNNING:
             ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_PRE_COPY,
                                            VFIO_DEVICE_STATE_RUNNING);
             if (ret) {
+                error_setg(errp, "%s: Failed to set new PRE_COPY state",
+                           vbasedev->name);
                 return ret;
             }
 
@@ -412,6 +413,8 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
             /* vfio_save_complete_precopy() will go to STOP_COPY */
             break;
         default:
+            error_setg(errp, "%s: Invalid device state %d", vbasedev->name,
+                       migration->device_state);
             return -EINVAL;
         }
     }
@@ -420,7 +423,12 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
 
     qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
 
-    return qemu_file_get_error(f);
+    ret = qemu_file_get_error(f);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "%s: save setup failed", vbasedev->name);
+    }
+
+    return ret;
 }
 
 static void vfio_save_cleanup(void *opaque)
@@ -580,12 +588,17 @@ static void vfio_save_state(QEMUFile *f, void *opaque)
     }
 }
 
-static int vfio_load_setup(QEMUFile *f, void *opaque)
+static int vfio_load_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     VFIODevice *vbasedev = opaque;
+    int ret;
 
-    return vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
+    ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
                                    vbasedev->migration->device_state);
+    if (ret) {
+        error_setg(errp, "%s: Failed to set RESUMING state", vbasedev->name);
+    }
+    return ret;
 }
 
 static int vfio_load_cleanup(void *opaque)

hw/virtio/vhost.c

@@ -1044,7 +1044,7 @@ check_dev_state:
     return r;
 }
 
-static void vhost_log_global_start(MemoryListener *listener)
+static bool vhost_log_global_start(MemoryListener *listener, Error **errp)
 {
     int r;
 
@@ -1052,6 +1052,7 @@ static void vhost_log_global_start(MemoryListener *listener)
     if (r < 0) {
         abort();
     }
+    return true;
 }
 
 static void vhost_log_global_stop(MemoryListener *listener)

include/exec/memory.h

@@ -1001,8 +1001,11 @@ struct MemoryListener {
      * active at that time.
      *
      * @listener: The #MemoryListener.
+     * @errp: pointer to Error*, to store an error if it happens.
+     *
+     * Return: true on success, else false setting @errp with error.
      */
-    void (*log_global_start)(MemoryListener *listener);
+    bool (*log_global_start)(MemoryListener *listener, Error **errp);
 
     /**
      * @log_global_stop:
@@ -2581,8 +2584,11 @@ void memory_listener_unregister(MemoryListener *listener);
  * memory_global_dirty_log_start: begin dirty logging for all regions
  *
  * @flags: purpose of starting dirty log, migration or dirty rate
+ * @errp: pointer to Error*, to store an error if it happens.
+ *
+ * Return: true on success, else false setting @errp with error.
  */
-void memory_global_dirty_log_start(unsigned int flags);
+bool memory_global_dirty_log_start(unsigned int flags, Error **errp);
 
 /**
  * memory_global_dirty_log_stop: end dirty logging for all regions

include/exec/ramblock.h

@@ -58,7 +58,7 @@ struct RAMBlock {
     off_t bitmap_offset;
     uint64_t pages_offset;
 
-    /* bitmap of already received pages in postcopy */
+    /* Bitmap of already received pages.  Only used on destination side. */
     unsigned long *receivedmap;
 
     /*

include/hw/s390x/storage-attributes.h

@@ -39,7 +39,7 @@ struct S390StAttribClass {
     int (*set_stattr)(S390StAttribState *sa, uint64_t start_gfn,
                       uint32_t count, uint8_t *values);
     void (*synchronize)(S390StAttribState *sa);
-    int (*set_migrationmode)(S390StAttribState *sa, bool value);
+    int (*set_migrationmode)(S390StAttribState *sa, bool value, Error **errp);
     int (*get_active)(S390StAttribState *sa);
     long long (*get_dirtycount)(S390StAttribState *sa);
 };

include/migration/register.h

@@ -60,10 +60,11 @@ typedef struct SaveVMHandlers {
      *
      * @f: QEMUFile where to send the data
      * @opaque: data pointer passed to register_savevm_live()
+     * @errp: pointer to Error*, to store an error if it happens.
      *
      * Returns zero to indicate success and negative for error
      */
-    int (*save_setup)(QEMUFile *f, void *opaque);
+    int (*save_setup)(QEMUFile *f, void *opaque, Error **errp);
 
     /**
      * @save_cleanup
@@ -233,10 +234,11 @@ typedef struct SaveVMHandlers {
      *
      * @f: QEMUFile where to receive the data
      * @opaque: data pointer passed to register_savevm_live()
+     * @errp: pointer to Error*, to store an error if it happens.
      *
      * Returns zero to indicate success and negative for error
      */
-    int (*load_setup)(QEMUFile *f, void *opaque);
+    int (*load_setup)(QEMUFile *f, void *opaque, Error **errp);
 
     /**
      * @load_cleanup

migration/block-dirty-bitmap.c

@@ -481,13 +481,13 @@ static void dirty_bitmap_do_save_cleanup(DBMSaveState *s)
 
 /* Called with the BQL taken. */
 static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
-                               const char *bs_name, GHashTable *alias_map)
+                               const char *bs_name, GHashTable *alias_map,
+                               Error **errp)
 {
     BdrvDirtyBitmap *bitmap;
     SaveBitmapState *dbms;
     GHashTable *bitmap_aliases;
     const char *node_alias, *bitmap_name, *bitmap_alias;
-    Error *local_err = NULL;
 
     /* When an alias map is given, @bs_name must be @bs's node name */
     assert(!alias_map || !strcmp(bs_name, bdrv_get_node_name(bs)));
@@ -504,8 +504,8 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
     bitmap_name = bdrv_dirty_bitmap_name(bitmap);
 
     if (!bs_name || strcmp(bs_name, "") == 0) {
-        error_report("Bitmap '%s' in unnamed node can't be migrated",
-                     bitmap_name);
+        error_setg(errp, "Bitmap '%s' in unnamed node can't be migrated",
+                   bitmap_name);
         return -1;
     }
 
@@ -525,9 +525,9 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
     }
 
     if (node_alias[0] == '#') {
-        error_report("Bitmap '%s' in a node with auto-generated "
-                     "name '%s' can't be migrated",
-                     bitmap_name, node_alias);
+        error_setg(errp, "Bitmap '%s' in a node with auto-generated "
+                   "name '%s' can't be migrated",
+                   bitmap_name, node_alias);
         return -1;
     }
 
@@ -538,8 +538,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
             continue;
         }
 
-        if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, &local_err)) {
-            error_report_err(local_err);
+        if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, errp)) {
             return -1;
         }
 
@@ -558,9 +557,9 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
             }
         } else {
             if (strlen(bitmap_name) > UINT8_MAX) {
-                error_report("Cannot migrate bitmap '%s' on node '%s': "
-                             "Name is longer than %u bytes",
-                             bitmap_name, bs_name, UINT8_MAX);
+                error_setg(errp, "Cannot migrate bitmap '%s' on node '%s': "
+                           "Name is longer than %u bytes",
+                           bitmap_name, bs_name, UINT8_MAX);
                 return -1;
             }
             bitmap_alias = bitmap_name;
@@ -599,7 +598,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
 }
 
 /* Called with the BQL taken. */
-static int init_dirty_bitmap_migration(DBMSaveState *s)
+static int init_dirty_bitmap_migration(DBMSaveState *s, Error **errp)
 {
     BlockDriverState *bs;
     SaveBitmapState *dbms;
@@ -643,7 +642,7 @@ static int init_dirty_bitmap_migration(DBMSaveState *s)
             }
 
             if (bs && bs->drv && !bs->drv->is_filter) {
-                if (add_bitmaps_to_list(s, bs, name, NULL)) {
+                if (add_bitmaps_to_list(s, bs, name, NULL, errp)) {
                     goto fail;
                 }
                 g_hash_table_add(handled_by_blk, bs);
@@ -656,7 +655,8 @@ static int init_dirty_bitmap_migration(DBMSaveState *s)
             continue;
         }
 
-        if (add_bitmaps_to_list(s, bs, bdrv_get_node_name(bs), alias_map)) {
+        if (add_bitmaps_to_list(s, bs, bdrv_get_node_name(bs), alias_map,
+                                errp)) {
             goto fail;
         }
     }
@@ -1213,12 +1213,12 @@ fail:
     return ret;
 }
 
-static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque)
+static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     DBMSaveState *s = &((DBMState *)opaque)->save;
     SaveBitmapState *dbms = NULL;
 
-    if (init_dirty_bitmap_migration(s) < 0) {
+    if (init_dirty_bitmap_migration(s, errp) < 0) {
         return -1;
     }
 

migration/block.c

@@ -367,7 +367,7 @@ static void unset_dirty_tracking(void)
     }
 }
 
-static int init_blk_migration(QEMUFile *f)
+static int init_blk_migration(QEMUFile *f, Error **errp)
 {
     BlockDriverState *bs;
     BlkMigDevState *bmds;
@@ -378,7 +378,6 @@ static int init_blk_migration(QEMUFile *f)
         BlkMigDevState *bmds;
         BlockDriverState *bs;
     } *bmds_bs;
-    Error *local_err = NULL;
     int ret;
 
     GRAPH_RDLOCK_GUARD_MAINLOOP();
@@ -406,6 +405,8 @@ static int init_blk_migration(QEMUFile *f)
             continue;
         }
         if (sectors < 0) {
+            error_setg(errp, "Error getting length of block device %s",
+                       bdrv_get_device_name(bs));
             ret = sectors;
             bdrv_next_cleanup(&it);
             goto out;
@@ -442,9 +443,8 @@ static int init_blk_migration(QEMUFile *f)
         bs = bmds_bs[i].bs;
 
         if (bmds) {
-            ret = blk_insert_bs(bmds->blk, bs, &local_err);
+            ret = blk_insert_bs(bmds->blk, bs, errp);
             if (ret < 0) {
-                error_report_err(local_err);
                 goto out;
             }
 
@@ -711,7 +711,7 @@ static void block_migration_cleanup(void *opaque)
     blk_mig_unlock();
 }
 
-static int block_save_setup(QEMUFile *f, void *opaque)
+static int block_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     int ret;
 
@@ -721,7 +721,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
     warn_report("block migration is deprecated;"
                 " use blockdev-mirror with NBD instead");
 
-    ret = init_blk_migration(f);
+    ret = init_blk_migration(f, errp);
     if (ret < 0) {
         return ret;
     }
@@ -729,10 +729,15 @@ static int block_save_setup(QEMUFile *f, void *opaque)
     /* start track dirty blocks */
     ret = set_dirty_tracking();
     if (ret) {
+        error_setg_errno(errp, -ret, "Failed to start block dirty tracking");
         return ret;
     }
 
     ret = flush_blks(f);
+    if (ret) {
+        error_setg_errno(errp, -ret, "Flushing block failed");
+        return ret;
+    }
     blk_mig_reset_dirty_cursor();
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
 

migration/colo.c

@@ -835,6 +835,16 @@ static void *colo_process_incoming_thread(void *opaque)
         return NULL;
     }
 
+    /* Make sure all file formats throw away their mutable metadata */
+    bql_lock();
+    bdrv_activate_all(&local_err);
+    if (local_err) {
+        bql_unlock();
+        error_report_err(local_err);
+        return NULL;
+    }
+    bql_unlock();
+
     failover_init_state();
 
     mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
@@ -922,7 +932,6 @@ out:
 int coroutine_fn colo_incoming_co(void)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
-    Error *local_err = NULL;
     QemuThread th;
 
     assert(bql_locked());
@@ -931,13 +940,6 @@ int coroutine_fn colo_incoming_co(void)
         return 0;
     }
 
-    /* Make sure all file formats throw away their mutable metadata */
-    bdrv_activate_all(&local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return -EINVAL;
-    }
-
     qemu_thread_create(&th, "COLO incoming", colo_process_incoming_thread,
                        mis, QEMU_THREAD_JOINABLE);
 

migration/dirtyrate.c

@@ -90,9 +90,15 @@ static int64_t do_calculate_dirtyrate(DirtyPageRecord dirty_pages,
 
 void global_dirty_log_change(unsigned int flag, bool start)
 {
+    Error *local_err = NULL;
+    bool ret;
+
     bql_lock();
     if (start) {
-        memory_global_dirty_log_start(flag);
+        ret = memory_global_dirty_log_start(flag, &local_err);
+        if (!ret) {
+            error_report_err(local_err);
+        }
     } else {
         memory_global_dirty_log_stop(flag);
     }
@@ -608,9 +614,12 @@ static void calculate_dirtyrate_dirty_bitmap(struct DirtyRateConfig config)
 {
     int64_t start_time;
     DirtyPageRecord dirty_pages;
+    Error *local_err = NULL;
 
     bql_lock();
-    memory_global_dirty_log_start(GLOBAL_DIRTY_DIRTY_RATE);
+    if (!memory_global_dirty_log_start(GLOBAL_DIRTY_DIRTY_RATE, &local_err)) {
+        error_report_err(local_err);
+    }
 
     /*
      * 1'round of log sync may return all 1 bits with

migration/migration.c

@@ -3431,6 +3431,8 @@ static void *migration_thread(void *opaque)
     int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     MigThrError thr_error;
     bool urgent = false;
+    Error *local_err = NULL;
+    int ret;
 
     thread = migration_threads_add("live_migration", qemu_get_thread_id());
 
@@ -3474,12 +3476,24 @@ static void *migration_thread(void *opaque)
     }
 
     bql_lock();
-    qemu_savevm_state_setup(s->to_dst_file);
+    ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
     bql_unlock();
 
     qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
                                MIGRATION_STATUS_ACTIVE);
 
+    /*
+     * Handle SETUP failures after waiting for virtio-net-failover
+     * devices to unplug. This to preserve migration state transitions.
+     */
+    if (ret) {
+        migrate_set_error(s, local_err);
+        error_free(local_err);
+        migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+        goto out;
+    }
+
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
 
     trace_migration_thread_setup_complete();
@@ -3553,6 +3567,8 @@ static void *bg_migration_thread(void *opaque)
     MigThrError thr_error;
     QEMUFile *fb;
     bool early_fail = true;
+    Error *local_err = NULL;
+    int ret;
 
     rcu_register_thread();
     object_ref(OBJECT(s));
@@ -3586,12 +3602,24 @@ static void *bg_migration_thread(void *opaque)
 
     bql_lock();
     qemu_savevm_state_header(s->to_dst_file);
-    qemu_savevm_state_setup(s->to_dst_file);
+    ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
     bql_unlock();
 
     qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
                                MIGRATION_STATUS_ACTIVE);
 
+    /*
+     * Handle SETUP failures after waiting for virtio-net-failover
+     * devices to unplug. This to preserve migration state transitions.
+     */
+    if (ret) {
+        migrate_set_error(s, local_err);
+        error_free(local_err);
+        migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+        goto fail_setup;
+    }
+
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
 
     trace_migration_thread_setup_complete();
@@ -3660,6 +3688,7 @@ fail:
         bql_unlock();
     }
 
+fail_setup:
     bg_migration_iteration_finish(s);
 
     qemu_fclose(fb);

migration/multifd-zero-page.c

@@ -80,8 +80,10 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p)
 {
     for (int i = 0; i < p->zero_num; i++) {
         void *page = p->host + p->zero[i];
-        if (!buffer_is_zero(page, p->page_size)) {
+        if (ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i])) {
             memset(page, 0, p->page_size);
+        } else {
+            ramblock_recv_bitmap_set_offset(p->block, p->zero[i]);
         }
     }
 }

migration/multifd-zlib.c

@@ -284,6 +284,7 @@ static int zlib_recv(MultiFDRecvParams *p, Error **errp)
         int flush = Z_NO_FLUSH;
         unsigned long start = zs->total_out;
 
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
         if (i == p->normal_num - 1) {
             flush = Z_SYNC_FLUSH;
         }

migration/multifd-zstd.c

@@ -278,6 +278,7 @@ static int zstd_recv(MultiFDRecvParams *p, Error **errp)
     z->in.pos = 0;
 
     for (i = 0; i < p->normal_num; i++) {
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
         z->out.dst = p->host + p->normal[i];
         z->out.size = p->page_size;
         z->out.pos = 0;

migration/multifd.c

@@ -277,6 +277,7 @@ static int nocomp_recv(MultiFDRecvParams *p, Error **errp)
     for (int i = 0; i < p->normal_num; i++) {
         p->iov[i].iov_base = p->host + p->normal[i];
         p->iov[i].iov_len = p->page_size;
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
     }
     return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
 }