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>

13 files changed, 198 insertions, 94 deletions

diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c
index 2708abf3d7..a7d55048c2 100644
--- a/migration/block-dirty-bitmap.c
+++ b/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;
     }
 
diff --git a/migration/block.c b/migration/block.c
index 2b9054889a..bae6e94891 100644
--- a/migration/block.c
+++ b/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);
 
diff --git a/migration/colo.c b/migration/colo.c
index 84632a603e..5600a43d78 100644
--- a/migration/colo.c
+++ b/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);
 
diff --git a/migration/dirtyrate.c b/migration/dirtyrate.c
index 1d2e85746f..d02d70b7b4 100644
--- a/migration/dirtyrate.c
+++ b/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
diff --git a/migration/migration.c b/migration/migration.c
index 86bf76e925..696762bc64 100644
--- a/migration/migration.c
+++ b/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);
diff --git a/migration/multifd-zero-page.c b/migration/multifd-zero-page.c
index 1ba38be636..e1b8370f88 100644
--- a/migration/multifd-zero-page.c
+++ b/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]);
         }
     }
 }
diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c
index 99821cd4d5..737a9645d2 100644
--- a/migration/multifd-zlib.c
+++ b/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;
         }
diff --git a/migration/multifd-zstd.c b/migration/multifd-zstd.c
index 02112255ad..256858df0a 100644
--- a/migration/multifd-zstd.c
+++ b/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;
diff --git a/migration/multifd.c b/migration/multifd.c
index 2802afe79d..f317bff077 100644
--- a/migration/multifd.c
+++ b/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);
 }
diff --git a/migration/ram.c b/migration/ram.c
index 8deb84984f..a975c5af16 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -275,6 +275,10 @@ void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr,
                       nr);
 }
 
+void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset)
+{
+    set_bit_atomic(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap);
+}
 #define  RAMBLOCK_RECV_BITMAP_ENDING  (0x0123456789abcdefULL)
 
 /*
@@ -2438,10 +2442,23 @@ static void xbzrle_cleanup(void)
     XBZRLE_cache_unlock();
 }
 
+static void ram_bitmaps_destroy(void)
+{
+    RAMBlock *block;
+
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+        g_free(block->clear_bmap);
+        block->clear_bmap = NULL;
+        g_free(block->bmap);
+        block->bmap = NULL;
+        g_free(block->file_bmap);
+        block->file_bmap = NULL;
+    }
+}
+
 static void ram_save_cleanup(void *opaque)
 {
     RAMState **rsp = opaque;
-    RAMBlock *block;
 
     /* We don't use dirty log with background snapshots */
     if (!migrate_background_snapshot()) {
@@ -2458,12 +2475,7 @@ static void ram_save_cleanup(void *opaque)
         }
     }
 
-    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
-        g_free(block->clear_bmap);
-        block->clear_bmap = NULL;
-        g_free(block->bmap);
-        block->bmap = NULL;
-    }
+    ram_bitmaps_destroy();
 
     xbzrle_cleanup();
     compress_threads_save_cleanup();
@@ -2719,44 +2731,41 @@ int ram_discard_range(const char *rbname, uint64_t start, size_t length)
  * For every allocation, we will try not to crash the VM if the
  * allocation failed.
  */
-static int xbzrle_init(void)
+static bool xbzrle_init(Error **errp)
 {
-    Error *local_err = NULL;
-
     if (!migrate_xbzrle()) {
-        return 0;
+        return true;
     }
 
     XBZRLE_cache_lock();
 
     XBZRLE.zero_target_page = g_try_malloc0(TARGET_PAGE_SIZE);
     if (!XBZRLE.zero_target_page) {
-        error_report("%s: Error allocating zero page", __func__);
+        error_setg(errp, "%s: Error allocating zero page", __func__);
         goto err_out;
     }
 
     XBZRLE.cache = cache_init(migrate_xbzrle_cache_size(),
-                              TARGET_PAGE_SIZE, &local_err);
+                              TARGET_PAGE_SIZE, errp);
     if (!XBZRLE.cache) {
-        error_report_err(local_err);
         goto free_zero_page;
     }
 
     XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
     if (!XBZRLE.encoded_buf) {
-        error_report("%s: Error allocating encoded_buf", __func__);
+        error_setg(errp, "%s: Error allocating encoded_buf", __func__);
         goto free_cache;
     }
 
     XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
     if (!XBZRLE.current_buf) {
-        error_report("%s: Error allocating current_buf", __func__);
+        error_setg(errp, "%s: Error allocating current_buf", __func__);
         goto free_encoded_buf;
     }
 
     /* We are all good */
     XBZRLE_cache_unlock();
-    return 0;
+    return true;
 
 free_encoded_buf:
     g_free(XBZRLE.encoded_buf);
@@ -2769,16 +2778,16 @@ free_zero_page:
     XBZRLE.zero_target_page = NULL;
 err_out:
     XBZRLE_cache_unlock();
-    return -ENOMEM;
+    return false;
 }
 
-static int ram_state_init(RAMState **rsp)
+static bool ram_state_init(RAMState **rsp, Error **errp)
 {
     *rsp = g_try_new0(RAMState, 1);
 
     if (!*rsp) {
-        error_report("%s: Init ramstate fail", __func__);
-        return -1;
+        error_setg(errp, "%s: Init ramstate fail", __func__);
+        return false;
     }
 
     qemu_mutex_init(&(*rsp)->bitmap_mutex);
@@ -2794,7 +2803,7 @@ static int ram_state_init(RAMState **rsp)
     (*rsp)->migration_dirty_pages = (*rsp)->ram_bytes_total >> TARGET_PAGE_BITS;
     ram_state_reset(*rsp);
 
-    return 0;
+    return true;
 }
 
 static void ram_list_init_bitmaps(void)
@@ -2852,39 +2861,53 @@ static void migration_bitmap_clear_discarded_pages(RAMState *rs)
     }
 }
 
-static void ram_init_bitmaps(RAMState *rs)
+static bool ram_init_bitmaps(RAMState *rs, Error **errp)
 {
+    bool ret = true;
+
     qemu_mutex_lock_ramlist();
 
     WITH_RCU_READ_LOCK_GUARD() {
         ram_list_init_bitmaps();
         /* We don't use dirty log with background snapshots */
         if (!migrate_background_snapshot()) {
-            memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
+            ret = memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION, errp);
+            if (!ret) {
+                goto out_unlock;
+            }
             migration_bitmap_sync_precopy(rs, false);
         }
     }
+out_unlock:
     qemu_mutex_unlock_ramlist();
 
+    if (!ret) {
+        ram_bitmaps_destroy();
+        return false;
+    }
+
     /*
      * After an eventual first bitmap sync, fixup the initial bitmap
      * containing all 1s to exclude any discarded pages from migration.
      */
     migration_bitmap_clear_discarded_pages(rs);
+    return true;
 }
 
-static int ram_init_all(RAMState **rsp)
+static int ram_init_all(RAMState **rsp, Error **errp)
 {
-    if (ram_state_init(rsp)) {
+    if (!ram_state_init(rsp, errp)) {
         return -1;
     }
 
-    if (xbzrle_init()) {
+    if (!xbzrle_init(errp)) {
         ram_state_cleanup(rsp);
         return -1;
     }
 
-    ram_init_bitmaps(*rsp);
+    if (!ram_init_bitmaps(*rsp, errp)) {
+        return -1;
+    }
 
     return 0;
 }
@@ -3066,20 +3089,22 @@ static bool mapped_ram_read_header(QEMUFile *file, MappedRamHeader *header,
  *
  * @f: QEMUFile where to send the data
  * @opaque: RAMState pointer
+ * @errp: pointer to Error*, to store an error if it happens.
  */
-static int ram_save_setup(QEMUFile *f, void *opaque)
+static int ram_save_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     RAMState **rsp = opaque;
     RAMBlock *block;
     int ret, max_hg_page_size;
 
     if (compress_threads_save_setup()) {
+        error_setg(errp, "%s: failed to start compress threads", __func__);
         return -1;
     }
 
     /* migration has already setup the bitmap, reuse it. */
     if (!migration_in_colo_state()) {
-        if (ram_init_all(rsp) != 0) {
+        if (ram_init_all(rsp, errp) != 0) {
             compress_threads_save_cleanup();
             return -1;
         }
@@ -3116,12 +3141,14 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 
     ret = rdma_registration_start(f, RAM_CONTROL_SETUP);
     if (ret < 0) {
+        error_setg(errp, "%s: failed to start RDMA registration", __func__);
         qemu_file_set_error(f, ret);
         return ret;
     }
 
     ret = rdma_registration_stop(f, RAM_CONTROL_SETUP);
     if (ret < 0) {
+        error_setg(errp, "%s: failed to stop RDMA registration", __func__);
         qemu_file_set_error(f, ret);
         return ret;
     }
@@ -3138,6 +3165,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     ret = multifd_send_sync_main();
     bql_lock();
     if (ret < 0) {
+        error_setg(errp, "%s: multifd synchronization failed", __func__);
         return ret;
     }
 
@@ -3147,7 +3175,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     }
 
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-    return qemu_fflush(f);
+    ret = qemu_fflush(f);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "%s failed", __func__);
+    }
+    return ret;
 }
 
 static void ram_save_file_bmap(QEMUFile *f)
@@ -3592,7 +3624,11 @@ void ram_handle_zero(void *host, uint64_t size)
 
 static void colo_init_ram_state(void)
 {
-    ram_state_init(&ram_state);
+    Error *local_err = NULL;
+
+    if (!ram_state_init(&ram_state, &local_err)) {
+        error_report_err(local_err);
+    }
 }
 
 /*
@@ -3647,6 +3683,8 @@ int colo_init_ram_cache(void)
 void colo_incoming_start_dirty_log(void)
 {
     RAMBlock *block = NULL;
+    Error *local_err = NULL;
+
     /* For memory_global_dirty_log_start below. */
     bql_lock();
     qemu_mutex_lock_ramlist();
@@ -3658,7 +3696,10 @@ void colo_incoming_start_dirty_log(void)
             /* Discard this dirty bitmap record */
             bitmap_zero(block->bmap, block->max_length >> TARGET_PAGE_BITS);
         }
-        memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
+        if (!memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION,
+                                           &local_err)) {
+            error_report_err(local_err);
+        }
     }
     ram_state->migration_dirty_pages = 0;
     qemu_mutex_unlock_ramlist();
@@ -3694,8 +3735,9 @@ void colo_release_ram_cache(void)
  *
  * @f: QEMUFile where to receive the data
  * @opaque: RAMState pointer
+ * @errp: pointer to Error*, to store an error if it happens.
  */
-static int ram_load_setup(QEMUFile *f, void *opaque)
+static int ram_load_setup(QEMUFile *f, void *opaque, Error **errp)
 {
     xbzrle_load_setup();
     ramblock_recv_map_init();
diff --git a/migration/ram.h b/migration/ram.h
index 08feecaf51..bc0318b834 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -69,6 +69,7 @@ int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
 bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset);
 void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
 void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr);
+void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset);
 int64_t ramblock_recv_bitmap_send(QEMUFile *file,
                                   const char *block_name);
 bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp);
diff --git a/migration/savevm.c b/migration/savevm.c
index e7c1215671..5d200cf42a 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1009,11 +1009,10 @@ static void save_section_footer(QEMUFile *f, SaveStateEntry *se)
     }
 }
 
-static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc)
+static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc,
+                        Error **errp)
 {
     int ret;
-    Error *local_err = NULL;
-    MigrationState *s = migrate_get_current();
 
     if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
         return 0;
@@ -1035,10 +1034,9 @@ static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc)
     if (!se->vmsd) {
         vmstate_save_old_style(f, se, vmdesc);
     } else {
-        ret = vmstate_save_state_with_err(f, se->vmsd, se->opaque, vmdesc, &local_err);
+        ret = vmstate_save_state_with_err(f, se->vmsd, se->opaque, vmdesc,
+                                          errp);
         if (ret) {
-            migrate_set_error(s, local_err);
-            error_report_err(local_err);
             return ret;
         }
     }
@@ -1312,11 +1310,11 @@ int qemu_savevm_state_prepare(Error **errp)
     return 0;
 }
 
-void qemu_savevm_state_setup(QEMUFile *f)
+int qemu_savevm_state_setup(QEMUFile *f, Error **errp)
 {
+    ERRP_GUARD();
     MigrationState *ms = migrate_get_current();
     SaveStateEntry *se;
-    Error *local_err = NULL;
     int ret = 0;
 
     json_writer_int64(ms->vmdesc, "page_size", qemu_target_page_size());
@@ -1325,8 +1323,9 @@ void qemu_savevm_state_setup(QEMUFile *f)
     trace_savevm_state_setup();
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
         if (se->vmsd && se->vmsd->early_setup) {
-            ret = vmstate_save(f, se, ms->vmdesc);
+            ret = vmstate_save(f, se, ms->vmdesc, errp);
             if (ret) {
+                migrate_set_error(ms, *errp);
                 qemu_file_set_error(f, ret);
                 break;
             }
@@ -1343,7 +1342,7 @@ void qemu_savevm_state_setup(QEMUFile *f)
         }
         save_section_header(f, se, QEMU_VM_SECTION_START);
 
-        ret = se->ops->save_setup(f, se->opaque);
+        ret = se->ops->save_setup(f, se->opaque, errp);
         save_section_footer(f, se);
         if (ret < 0) {
             qemu_file_set_error(f, ret);
@@ -1352,12 +1351,11 @@ void qemu_savevm_state_setup(QEMUFile *f)
     }
 
     if (ret) {
-        return;
+        return ret;
     }
 
-    if (precopy_notify(PRECOPY_NOTIFY_SETUP, &local_err)) {
-        error_report_err(local_err);
-    }
+    /* TODO: Should we check that errp is set in case of failure ? */
+    return precopy_notify(PRECOPY_NOTIFY_SETUP, errp);
 }
 
 int qemu_savevm_state_resume_prepare(MigrationState *s)
@@ -1542,6 +1540,7 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
     JSONWriter *vmdesc = ms->vmdesc;
     int vmdesc_len;
     SaveStateEntry *se;
+    Error *local_err = NULL;
     int ret;
 
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
@@ -1552,8 +1551,10 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
 
         start_ts_each = qemu_clock_get_us(QEMU_CLOCK_REALTIME);
 
-        ret = vmstate_save(f, se, vmdesc);
+        ret = vmstate_save(f, se, vmdesc, &local_err);
         if (ret) {
+            migrate_set_error(ms, local_err);
+            error_report_err(local_err);
             qemu_file_set_error(f, ret);
             return ret;
         }
@@ -1568,7 +1569,6 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
          * bdrv_activate_all() on the other end won't fail. */
         ret = bdrv_inactivate_all();
         if (ret) {
-            Error *local_err = NULL;
             error_setg(&local_err, "%s: bdrv_inactivate_all() failed (%d)",
                        __func__, ret);
             migrate_set_error(ms, local_err);
@@ -1723,7 +1723,10 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
     ms->to_dst_file = f;
 
     qemu_savevm_state_header(f);
-    qemu_savevm_state_setup(f);
+    ret = qemu_savevm_state_setup(f, errp);
+    if (ret) {
+        goto cleanup;
+    }
 
     while (qemu_file_get_error(f) == 0) {
         if (qemu_savevm_state_iterate(f, false) > 0) {
@@ -1736,10 +1739,11 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
         qemu_savevm_state_complete_precopy(f, false, false);
         ret = qemu_file_get_error(f);
     }
-    qemu_savevm_state_cleanup();
     if (ret != 0) {
         error_setg_errno(errp, -ret, "Error while writing VM state");
     }
+cleanup:
+    qemu_savevm_state_cleanup();
 
     if (ret != 0) {
         status = MIGRATION_STATUS_FAILED;
@@ -1764,6 +1768,8 @@ void qemu_savevm_live_state(QEMUFile *f)
 
 int qemu_save_device_state(QEMUFile *f)
 {
+    MigrationState *ms = migrate_get_current();
+    Error *local_err = NULL;
     SaveStateEntry *se;
 
     if (!migration_in_colo_state()) {
@@ -1778,8 +1784,10 @@ int qemu_save_device_state(QEMUFile *f)
         if (se->is_ram) {
             continue;
         }
-        ret = vmstate_save(f, se, NULL);
+        ret = vmstate_save(f, se, NULL, &local_err);
         if (ret) {
+            migrate_set_error(ms, local_err);
+            error_report_err(local_err);
             return ret;
         }
     }
@@ -2760,8 +2768,9 @@ static void qemu_loadvm_state_switchover_ack_needed(MigrationIncomingState *mis)
     trace_loadvm_state_switchover_ack_needed(mis->switchover_ack_pending_num);
 }
 
-static int qemu_loadvm_state_setup(QEMUFile *f)
+static int qemu_loadvm_state_setup(QEMUFile *f, Error **errp)
 {
+    ERRP_GUARD();
     SaveStateEntry *se;
     int ret;
 
@@ -2776,10 +2785,11 @@ static int qemu_loadvm_state_setup(QEMUFile *f)
             }
         }
 
-        ret = se->ops->load_setup(f, se->opaque);
+        ret = se->ops->load_setup(f, se->opaque, errp);
         if (ret < 0) {
+            error_prepend(errp, "Load state of device %s failed: ",
+                          se->idstr);
             qemu_file_set_error(f, ret);
-            error_report("Load state of device %s failed", se->idstr);
             return ret;
         }
     }
@@ -2960,7 +2970,8 @@ int qemu_loadvm_state(QEMUFile *f)
         return ret;
     }
 
-    if (qemu_loadvm_state_setup(f) != 0) {
+    if (qemu_loadvm_state_setup(f, &local_err) != 0) {
+        error_report_err(local_err);
         return -EINVAL;
     }
 
diff --git a/migration/savevm.h b/migration/savevm.h
index 74669733dd..9ec96a995c 100644
--- a/migration/savevm.h
+++ b/migration/savevm.h
@@ -32,7 +32,7 @@
 bool qemu_savevm_state_blocked(Error **errp);
 void qemu_savevm_non_migratable_list(strList **reasons);
 int qemu_savevm_state_prepare(Error **errp);
-void qemu_savevm_state_setup(QEMUFile *f);
+int qemu_savevm_state_setup(QEMUFile *f, Error **errp);
 bool qemu_savevm_state_guest_unplug_pending(void);
 int qemu_savevm_state_resume_prepare(MigrationState *s);
 void qemu_savevm_state_header(QEMUFile *f);