Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20210513a' into staging

Migration pull 2021-05-13

Fix of the 2021-05-11 version, with a fix to build on the armhf
cross.

The largest change in this set is David's changes for ram block size
changing; then there's a pile of other cleanups and fixes.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# gpg: Signature made Thu 13 May 2021 18:36:06 BST
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20210513a:
  tests/migration: introduce multifd into guestperf
  tests/qtest/migration-test: Use g_autofree to avoid leaks on error paths
  tests/migration-test: Fix "true" vs true
  migration/ram: Use offset_in_ramblock() in range checks
  migration/multifd: Print used_length of memory block
  migration/ram: Handle RAM block resizes during postcopy
  migration/ram: Simplify host page handling in ram_load_postcopy()
  migration/ram: Discard RAM when growing RAM blocks after ram_postcopy_incoming_init()
  exec: Relax range check in ram_block_discard_range()
  migration/ram: Handle RAM block resizes during precopy
  numa: Make all callbacks of ram block notifiers optional
  numa: Teach ram block notifiers about resizeable ram blocks
  util: vfio-helpers: Factor out and fix processing of existing ram blocks
  migration: Drop redundant query-migrate result @blocked
  migration/ram: Optimize ram_save_host_page()
  migration/ram: Reduce unnecessary rate limiting
  migrate/ram: remove "ram_bulk_stage" and "fpo_enabled"

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

25 files changed, 367 insertions, 250 deletions

diff --git a/hw/core/numa.c b/hw/core/numa.c
index ac6bed5817..1058d3697b 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -802,9 +802,27 @@ void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms)
     }
 }
 
+static int ram_block_notify_add_single(RAMBlock *rb, void *opaque)
+{
+    const ram_addr_t max_size = qemu_ram_get_max_length(rb);
+    const ram_addr_t size = qemu_ram_get_used_length(rb);
+    void *host = qemu_ram_get_host_addr(rb);
+    RAMBlockNotifier *notifier = opaque;
+
+    if (host) {
+        notifier->ram_block_added(notifier, host, size, max_size);
+    }
+    return 0;
+}
+
 void ram_block_notifier_add(RAMBlockNotifier *n)
 {
     QLIST_INSERT_HEAD(&ram_list.ramblock_notifiers, n, next);
+
+    /* Notify about all existing ram blocks. */
+    if (n->ram_block_added) {
+        qemu_ram_foreach_block(ram_block_notify_add_single, n);
+    }
 }
 
 void ram_block_notifier_remove(RAMBlockNotifier *n)
@@ -812,20 +830,35 @@ void ram_block_notifier_remove(RAMBlockNotifier *n)
     QLIST_REMOVE(n, next);
 }
 
-void ram_block_notify_add(void *host, size_t size)
+void ram_block_notify_add(void *host, size_t size, size_t max_size)
+{
+    RAMBlockNotifier *notifier;
+
+    QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
+        if (notifier->ram_block_added) {
+            notifier->ram_block_added(notifier, host, size, max_size);
+        }
+    }
+}
+
+void ram_block_notify_remove(void *host, size_t size, size_t max_size)
 {
     RAMBlockNotifier *notifier;
 
     QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
-        notifier->ram_block_added(notifier, host, size);
+        if (notifier->ram_block_removed) {
+            notifier->ram_block_removed(notifier, host, size, max_size);
+        }
     }
 }
 
-void ram_block_notify_remove(void *host, size_t size)
+void ram_block_notify_resize(void *host, size_t old_size, size_t new_size)
 {
     RAMBlockNotifier *notifier;
 
     QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) {
-        notifier->ram_block_removed(notifier, host, size);
+        if (notifier->ram_block_resized) {
+            notifier->ram_block_resized(notifier, host, old_size, new_size);
+        }
     }
 }
diff --git a/hw/i386/xen/xen-mapcache.c b/hw/i386/xen/xen-mapcache.c
index e82b7dcdd2..bd47c3d672 100644
--- a/hw/i386/xen/xen-mapcache.c
+++ b/hw/i386/xen/xen-mapcache.c
@@ -169,7 +169,8 @@ static void xen_remap_bucket(MapCacheEntry *entry,
 
     if (entry->vaddr_base != NULL) {
         if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
-            ram_block_notify_remove(entry->vaddr_base, entry->size);
+            ram_block_notify_remove(entry->vaddr_base, entry->size,
+                                    entry->size);
         }
 
         /*
@@ -224,7 +225,7 @@ static void xen_remap_bucket(MapCacheEntry *entry,
     }
 
     if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
-        ram_block_notify_add(vaddr_base, size);
+        ram_block_notify_add(vaddr_base, size, size);
     }
 
     entry->vaddr_base = vaddr_base;
@@ -465,7 +466,7 @@ static void xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer)
     }
 
     pentry->next = entry->next;
-    ram_block_notify_remove(entry->vaddr_base, entry->size);
+    ram_block_notify_remove(entry->vaddr_base, entry->size, entry->size);
     if (munmap(entry->vaddr_base, entry->size) != 0) {
         perror("unmap fails");
         exit(-1);
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index d120bf8f43..4b5d9e5e50 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -663,9 +663,6 @@ virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data)
     }
 
     switch (pnd->reason) {
-    case PRECOPY_NOTIFY_SETUP:
-        precopy_enable_free_page_optimization();
-        break;
     case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC:
         virtio_balloon_free_page_stop(dev);
         break;
@@ -685,6 +682,7 @@ virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data)
          */
         virtio_balloon_free_page_done(dev);
         break;
+    case PRECOPY_NOTIFY_SETUP:
     case PRECOPY_NOTIFY_COMPLETE:
         break;
     default:
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index 655824ff81..75aa7d6f1b 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -902,9 +902,6 @@ static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data)
     PrecopyNotifyData *pnd = data;
 
     switch (pnd->reason) {
-    case PRECOPY_NOTIFY_SETUP:
-        precopy_enable_free_page_optimization();
-        break;
     case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
         virtio_mem_precopy_exclude_unplugged(vmem);
         break;
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 5a0a2d93e0..ccabed4003 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -57,6 +57,7 @@ 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_used_length(RAMBlock *rb);
+ram_addr_t qemu_ram_get_max_length(RAMBlock *rb);
 bool qemu_ram_is_shared(RAMBlock *rb);
 bool qemu_ram_is_uf_zeroable(RAMBlock *rb);
 void qemu_ram_set_uf_zeroable(RAMBlock *rb);
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 5728a681b2..c8b9088924 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -131,7 +131,7 @@ typedef struct IOMMUTLBEvent {
 #define RAM_SHARED     (1 << 1)
 
 /* Only a portion of RAM (used_length) is actually used, and migrated.
- * This used_length size can change across reboots.
+ * Resizing RAM while migrating can result in the migration being canceled.
  */
 #define RAM_RESIZEABLE (1 << 2)
 
@@ -955,7 +955,9 @@ void memory_region_init_ram_shared_nomigrate(MemoryRegion *mr,
  *                                     RAM.  Accesses into the region will
  *                                     modify memory directly.  Only an initial
  *                                     portion of this RAM is actually used.
- *                                     The used size can change across reboots.
+ *                                     Changing the size while migrating
+ *                                     can result in the migration being
+ *                                     canceled.
  *
  * @mr: the #MemoryRegion to be initialized.
  * @owner: the object that tracks the region's reference count
@@ -1586,8 +1588,8 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr);
 
 /* memory_region_ram_resize: Resize a RAM region.
  *
- * Only legal before guest might have detected the memory size: e.g. on
- * incoming migration, or right after reset.
+ * Resizing RAM while migrating can result in the migration being canceled.
+ * Care has to be taken if the guest might have already detected the memory.
  *
  * @mr: a memory region created with @memory_region_init_resizeable_ram.
  * @newsize: the new size the region
diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h
index 07d50864d8..664701b759 100644
--- a/include/exec/ramblock.h
+++ b/include/exec/ramblock.h
@@ -59,6 +59,16 @@ struct RAMBlock {
      */
     unsigned long *clear_bmap;
     uint8_t clear_bmap_shift;
+
+    /*
+     * RAM block length that corresponds to the used_length on the migration
+     * source (after RAM block sizes were synchronized). Especially, after
+     * starting to run the guest, used_length and postcopy_length can differ.
+     * Used to register/unregister uffd handlers and as the size of the received
+     * bitmap. Receiving any page beyond this length will bail out, as it
+     * could not have been valid on the source.
+     */
+    ram_addr_t postcopy_length;
 };
 #endif
 #endif
diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h
index 26704aa3b0..ece6497ee2 100644
--- a/include/exec/ramlist.h
+++ b/include/exec/ramlist.h
@@ -65,15 +65,20 @@ void qemu_mutex_lock_ramlist(void);
 void qemu_mutex_unlock_ramlist(void);
 
 struct RAMBlockNotifier {
-    void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size);
-    void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size);
+    void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size,
+                            size_t max_size);
+    void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size,
+                              size_t max_size);
+    void (*ram_block_resized)(RAMBlockNotifier *n, void *host, size_t old_size,
+                              size_t new_size);
     QLIST_ENTRY(RAMBlockNotifier) next;
 };
 
 void ram_block_notifier_add(RAMBlockNotifier *n);
 void ram_block_notifier_remove(RAMBlockNotifier *n);
-void ram_block_notify_add(void *host, size_t size);
-void ram_block_notify_remove(void *host, size_t size);
+void ram_block_notify_add(void *host, size_t size, size_t max_size);
+void ram_block_notify_remove(void *host, size_t size, size_t max_size);
+void ram_block_notify_resize(void *host, size_t old_size, size_t new_size);
 
 void ram_block_dump(Monitor *mon);
 
diff --git a/include/migration/misc.h b/include/migration/misc.h
index 738675ef52..465906710d 100644
--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@@ -37,7 +37,6 @@ void precopy_infrastructure_init(void);
 void precopy_add_notifier(NotifierWithReturn *n);
 void precopy_remove_notifier(NotifierWithReturn *n);
 int precopy_notify(PrecopyNotifyReason reason, Error **errp);
-void precopy_enable_free_page_optimization(void);
 
 void ram_mig_init(void);
 void qemu_guest_free_page_hint(void *addr, size_t len);
diff --git a/migration/migration.c b/migration/migration.c
index 8ca034136b..4698b47442 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -223,13 +223,18 @@ void migration_object_init(void)
     dirty_bitmap_mig_init();
 }
 
+void migration_cancel(void)
+{
+    migrate_fd_cancel(current_migration);
+}
+
 void migration_shutdown(void)
 {
     /*
      * Cancel the current migration - that will (eventually)
      * stop the migration using this structure
      */
-    migrate_fd_cancel(current_migration);
+    migration_cancel();
     object_unref(OBJECT(current_migration));
 
     /*
@@ -1073,27 +1078,24 @@ static void populate_vfio_info(MigrationInfo *info)
 static void fill_source_migration_info(MigrationInfo *info)
 {
     MigrationState *s = migrate_get_current();
+    GSList *cur_blocker = migration_blockers;
 
-    info->blocked = migration_is_blocked(NULL);
-    info->has_blocked_reasons = info->blocked;
     info->blocked_reasons = NULL;
-    if (info->blocked) {
-        GSList *cur_blocker = migration_blockers;
 
-        /*
-         * There are two types of reasons a migration might be blocked;
-         * a) devices marked in VMState as non-migratable, and
-         * b) Explicit migration blockers
-         * We need to add both of them here.
-         */
-        qemu_savevm_non_migratable_list(&info->blocked_reasons);
+    /*
+     * There are two types of reasons a migration might be blocked;
+     * a) devices marked in VMState as non-migratable, and
+     * b) Explicit migration blockers
+     * We need to add both of them here.
+     */
+    qemu_savevm_non_migratable_list(&info->blocked_reasons);
 
-        while (cur_blocker) {
-            QAPI_LIST_PREPEND(info->blocked_reasons,
-                              g_strdup(error_get_pretty(cur_blocker->data)));
-            cur_blocker = g_slist_next(cur_blocker);
-        }
+    while (cur_blocker) {
+        QAPI_LIST_PREPEND(info->blocked_reasons,
+                          g_strdup(error_get_pretty(cur_blocker->data)));
+        cur_blocker = g_slist_next(cur_blocker);
     }
+    info->has_blocked_reasons = info->blocked_reasons != NULL;
 
     switch (s->state) {
     case MIGRATION_STATUS_NONE:
@@ -2310,7 +2312,7 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
 
 void qmp_migrate_cancel(Error **errp)
 {
-    migrate_fd_cancel(migrate_get_current());
+    migration_cancel();
 }
 
 void qmp_migrate_continue(MigrationStatus state, Error **errp)
diff --git a/migration/migration.h b/migration/migration.h
index db6708326b..f7b388d718 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -375,5 +375,6 @@ int foreach_not_ignored_block(RAMBlockIterFunc func, void *opaque);
 void migration_make_urgent_request(void);
 void migration_consume_urgent_request(void);
 bool migration_rate_limit(void);
+void migration_cancel(void);
 
 #endif
diff --git a/migration/multifd.c b/migration/multifd.c
index a6677c45c8..0a4803cfcc 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -361,7 +361,7 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
         if (offset > (block->used_length - qemu_target_page_size())) {
             error_setg(errp, "multifd: offset too long %" PRIu64
                        " (max " RAM_ADDR_FMT ")",
-                       offset, block->max_length);
+                       offset, block->used_length);
             return -1;
         }
         p->pages->iov[i].iov_base = block->host + offset;
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index ab482adef1..2e9697bdd2 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -17,6 +17,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/rcu.h"
 #include "exec/target_page.h"
 #include "migration.h"
 #include "qemu-file.h"
@@ -30,6 +31,7 @@
 #include "qemu/error-report.h"
 #include "trace.h"
 #include "hw/boards.h"
+#include "exec/ramblock.h"
 
 /* Arbitrary limit on size of each discard command,
  * keeps them around ~200 bytes
@@ -453,6 +455,13 @@ static int init_range(RAMBlock *rb, void *opaque)
     trace_postcopy_init_range(block_name, host_addr, offset, length);
 
     /*
+     * Save the used_length before running the guest. In case we have to
+     * resize RAM blocks when syncing RAM block sizes from the source during
+     * precopy, we'll update it manually via the ram block notifier.
+     */
+    rb->postcopy_length = length;
+
+    /*
      * We need the whole of RAM to be truly empty for postcopy, so things
      * like ROMs and any data tables built during init must be zero'd
      * - we're going to get the copy from the source anyway.
@@ -474,7 +483,7 @@ static int cleanup_range(RAMBlock *rb, void *opaque)
     const char *block_name = qemu_ram_get_idstr(rb);
     void *host_addr = qemu_ram_get_host_addr(rb);
     ram_addr_t offset = qemu_ram_get_offset(rb);
-    ram_addr_t length = qemu_ram_get_used_length(rb);
+    ram_addr_t length = rb->postcopy_length;
     MigrationIncomingState *mis = opaque;
     struct uffdio_range range_struct;
     trace_postcopy_cleanup_range(block_name, host_addr, offset, length);
@@ -580,7 +589,7 @@ static int nhp_range(RAMBlock *rb, void *opaque)
     const char *block_name = qemu_ram_get_idstr(rb);
     void *host_addr = qemu_ram_get_host_addr(rb);
     ram_addr_t offset = qemu_ram_get_offset(rb);
-    ram_addr_t length = qemu_ram_get_used_length(rb);
+    ram_addr_t length = rb->postcopy_length;
     trace_postcopy_nhp_range(block_name, host_addr, offset, length);
 
     /*
@@ -624,7 +633,7 @@ static int ram_block_enable_notify(RAMBlock *rb, void *opaque)
     struct uffdio_register reg_struct;
 
     reg_struct.range.start = (uintptr_t)qemu_ram_get_host_addr(rb);
-    reg_struct.range.len = qemu_ram_get_used_length(rb);
+    reg_struct.range.len = rb->postcopy_length;
     reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
 
     /* Now tell our userfault_fd that it's responsible for this area */
diff --git a/migration/ram.c b/migration/ram.c
index ace8ad431c..60ea913c54 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -240,7 +240,7 @@ int64_t ramblock_recv_bitmap_send(QEMUFile *file,
         return -1;
     }
 
-    nbits = block->used_length >> TARGET_PAGE_BITS;
+    nbits = block->postcopy_length >> TARGET_PAGE_BITS;
 
     /*
      * Make sure the tmp bitmap buffer is big enough, e.g., on 32bit
@@ -311,10 +311,6 @@ struct RAMState {
     ram_addr_t last_page;
     /* last ram version we have seen */
     uint32_t last_version;
-    /* We are in the first round */
-    bool ram_bulk_stage;
-    /* The free page optimization is enabled */
-    bool fpo_enabled;
     /* How many times we have dirty too many pages */
     int dirty_rate_high_cnt;
     /* these variables are used for bitmap sync */
@@ -330,6 +326,8 @@ struct RAMState {
     uint64_t xbzrle_pages_prev;
     /* Amount of xbzrle encoded bytes since the beginning of the period */
     uint64_t xbzrle_bytes_prev;
+    /* Start using XBZRLE (e.g., after the first round). */
+    bool xbzrle_enabled;
 
     /* compression statistics since the beginning of the period */
     /* amount of count that no free thread to compress data */
@@ -383,15 +381,6 @@ int precopy_notify(PrecopyNotifyReason reason, Error **errp)
     return notifier_with_return_list_notify(&precopy_notifier_list, &pnd);
 }
 
-void precopy_enable_free_page_optimization(void)
-{
-    if (!ram_state) {
-        return;
-    }
-
-    ram_state->fpo_enabled = true;
-}
-
 uint64_t ram_bytes_remaining(void)
 {
     return ram_state ? (ram_state->migration_dirty_pages * TARGET_PAGE_SIZE) :
@@ -664,7 +653,7 @@ static void mig_throttle_guest_down(uint64_t bytes_dirty_period,
  */
 static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr)
 {
-    if (rs->ram_bulk_stage || !migrate_use_xbzrle()) {
+    if (!rs->xbzrle_enabled) {
         return;
     }
 
@@ -792,23 +781,12 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb,
 {
     unsigned long size = rb->used_length >> TARGET_PAGE_BITS;
     unsigned long *bitmap = rb->bmap;
-    unsigned long next;
 
     if (ramblock_is_ignored(rb)) {
         return size;
     }
 
-    /*
-     * When the free page optimization is enabled, we need to check the bitmap
-     * to send the non-free pages rather than all the pages in the bulk stage.
-     */
-    if (!rs->fpo_enabled && rs->ram_bulk_stage && start > 0) {
-        next = start + 1;
-    } else {
-        next = find_next_bit(bitmap, size, start);
-    }
-
-    return next;
+    return find_next_bit(bitmap, size, start);
 }
 
 static inline bool migration_bitmap_clear_dirty(RAMState *rs,
@@ -1185,8 +1163,7 @@ static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage)
     trace_ram_save_page(block->idstr, (uint64_t)offset, p);
 
     XBZRLE_cache_lock();
-    if (!rs->ram_bulk_stage && !migration_in_postcopy() &&
-        migrate_use_xbzrle()) {
+    if (rs->xbzrle_enabled && !migration_in_postcopy()) {
         pages = save_xbzrle_page(rs, &p, current_addr, block,
                                  offset, last_stage);
         if (!last_stage) {
@@ -1365,8 +1342,8 @@ static bool find_dirty_block(RAMState *rs, PageSearchStatus *pss, bool *again)
         *again = false;
         return false;
     }
-    if ((((ram_addr_t)pss->page) << TARGET_PAGE_BITS)
-        >= pss->block->used_length) {
+    if (!offset_in_ramblock(pss->block,
+                            ((ram_addr_t)pss->page) << TARGET_PAGE_BITS)) {
         /* Didn't find anything in this RAM Block */
         pss->page = 0;
         pss->block = QLIST_NEXT_RCU(pss->block, next);
@@ -1386,7 +1363,10 @@ static bool find_dirty_block(RAMState *rs, PageSearchStatus *pss, bool *again)
             pss->block = QLIST_FIRST_RCU(&ram_list.blocks);
             /* Flag that we've looped */
             pss->complete_round = true;
-            rs->ram_bulk_stage = false;
+            /* After the first round, enable XBZRLE. */
+            if (migrate_use_xbzrle()) {
+                rs->xbzrle_enabled = true;
+            }
         }
         /* Didn't find anything this time, but try again on the new block */
         *again = true;
@@ -1801,14 +1781,6 @@ static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
 
     if (block) {
         /*
-         * As soon as we start servicing pages out of order, then we have
-         * to kill the bulk stage, since the bulk stage assumes
-         * in (migration_bitmap_find_and_reset_dirty) that every page is
-         * dirty, that's no longer true.
-         */
-        rs->ram_bulk_stage = false;
-
-        /*
          * We want the background search to continue from the queued page
          * since the guest is likely to want other pages near to the page
          * it just requested.
@@ -1891,7 +1863,7 @@ int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
         rs->last_req_rb = ramblock;
     }
     trace_ram_save_queue_pages(ramblock->idstr, start, len);
-    if (start + len > ramblock->used_length) {
+    if (!offset_in_ramblock(ramblock, start + len - 1)) {
         error_report("%s request overrun start=" RAM_ADDR_FMT " len="
                      RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT,
                      __func__, start, len, ramblock->used_length);
@@ -1920,15 +1892,15 @@ static bool save_page_use_compression(RAMState *rs)
     }
 
     /*
-     * If xbzrle is on, stop using the data compression after first
-     * round of migration even if compression is enabled. In theory,
-     * xbzrle can do better than compression.
+     * If xbzrle is enabled (e.g., after first round of migration), stop
+     * using the data compression. In theory, xbzrle can do better than
+     * compression.
      */
-    if (rs->ram_bulk_stage || !migrate_use_xbzrle()) {
-        return true;
+    if (rs->xbzrle_enabled) {
+        return false;
     }
 
-    return false;
+    return true;
 }
 
 /*
@@ -2041,6 +2013,8 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
     int tmppages, pages = 0;
     size_t pagesize_bits =
         qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
+    unsigned long hostpage_boundary =
+        QEMU_ALIGN_UP(pss->page + 1, pagesize_bits);
     unsigned long start_page = pss->page;
     int res;
 
@@ -2051,25 +2025,27 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
 
     do {
         /* Check the pages is dirty and if it is send it */
-        if (!migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
-            pss->page++;
-            continue;
-        }
+        if (migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
+            tmppages = ram_save_target_page(rs, pss, last_stage);
+            if (tmppages < 0) {
+                return tmppages;
+            }
 
-        tmppages = ram_save_target_page(rs, pss, last_stage);
-        if (tmppages < 0) {
-            return tmppages;
+            pages += tmppages;
+            /*
+             * Allow rate limiting to happen in the middle of huge pages if
+             * something is sent in the current iteration.
+             */
+            if (pagesize_bits > 1 && tmppages > 0) {
+                migration_rate_limit();
+            }
         }
-
-        pages += tmppages;
-        pss->page++;
-        /* Allow rate limiting to happen in the middle of huge pages */
-        migration_rate_limit();
-    } while ((pss->page & (pagesize_bits - 1)) &&
+        pss->page = migration_bitmap_find_dirty(rs, pss->block, pss->page);
+    } while ((pss->page < hostpage_boundary) &&
              offset_in_ramblock(pss->block,
                                 ((ram_addr_t)pss->page) << TARGET_PAGE_BITS));
-    /* The offset we leave with is the last one we looked at */
-    pss->page--;
+    /* The offset we leave with is the min boundary of host page and block */
+    pss->page = MIN(pss->page, hostpage_boundary) - 1;
 
     res = ram_save_release_protection(rs, pss, start_page);
     return (res < 0 ? res : pages);
@@ -2235,8 +2211,7 @@ static void ram_state_reset(RAMState *rs)
     rs->last_sent_block = NULL;
     rs->last_page = 0;
     rs->last_version = ram_list.version;
-    rs->ram_bulk_stage = true;
-    rs->fpo_enabled = false;
+    rs->xbzrle_enabled = false;
 }
 
 #define MAX_WAIT 50 /* ms, half buffered_file limit */
@@ -2720,15 +2695,7 @@ static void ram_state_resume_prepare(RAMState *rs, QEMUFile *out)
     /* This may not be aligned with current bitmaps. Recalculate. */
     rs->migration_dirty_pages = pages;
 
-    rs->last_seen_block = NULL;
-    rs->last_sent_block = NULL;
-    rs->last_page = 0;
-    rs->last_version = ram_list.version;
-    /*
-     * Disable the bulk stage, otherwise we'll resend the whole RAM no
-     * matter what we have sent.
-     */
-    rs->ram_bulk_stage = false;
+    ram_state_reset(rs);
 
     /* Update RAMState cache of output QEMUFile */
     rs->f = out;
@@ -3118,6 +3085,20 @@ static inline void *host_from_ram_block_offset(RAMBlock *block,
     return block->host + offset;
 }
 
+static void *host_page_from_ram_block_offset(RAMBlock *block,
+                                             ram_addr_t offset)
+{
+    /* Note: Explicitly no check against offset_in_ramblock(). */
+    return (void *)QEMU_ALIGN_DOWN((uintptr_t)(block->host + offset),
+                                   block->page_size);
+}
+
+static ram_addr_t host_page_offset_from_ram_block_offset(RAMBlock *block,
+                                                         ram_addr_t offset)
+{
+    return ((uintptr_t)block->host + offset) & (block->page_size - 1);
+}
+
 static inline void *colo_cache_from_block_offset(RAMBlock *block,
                              ram_addr_t offset, bool record_bitmap)
 {
@@ -3345,16 +3326,9 @@ static void decompress_data_with_multi_threads(QEMUFile *f,
     }
 }
 
- /*
-  * we must set ram_bulk_stage to false, otherwise in
-  * migation_bitmap_find_dirty the bitmap will be unused and
-  * all the pages in ram cache wil be flushed to the ram of
-  * secondary VM.
-  */
 static void colo_init_ram_state(void)
 {
     ram_state_init(&ram_state);
-    ram_state->ram_bulk_stage = false;
 }
 
 /*
@@ -3521,13 +3495,12 @@ static int ram_load_postcopy(QEMUFile *f)
     MigrationIncomingState *mis = migration_incoming_get_current();
     /* Temporary page that is later 'placed' */
     void *postcopy_host_page = mis->postcopy_tmp_page;
-    void *this_host = NULL;
+    void *host_page = NULL;
     bool all_zero = true;
     int target_pages = 0;
 
     while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
         ram_addr_t addr;
-        void *host = NULL;
         void *page_buffer = NULL;
         void *place_source = NULL;
         RAMBlock *block = NULL;
@@ -3552,9 +3525,18 @@ static int ram_load_postcopy(QEMUFile *f)
         if (flags & (RAM_SAVE_FLAG_ZERO | RAM_SAVE_FLAG_PAGE |
                      RAM_SAVE_FLAG_COMPRESS_PAGE)) {
             block = ram_block_from_stream(f, flags);
+            if (!block) {
+                ret = -EINVAL;
+                break;
+            }
 
-            host = host_from_ram_block_offset(block, addr);
-            if (!host) {
+            /*
+             * Relying on used_length is racy and can result in false positives.
+             * We might place pages beyond used_length in case RAM was shrunk
+             * while in postcopy, which is fine - trying to place via
+             * UFFDIO_COPY/UFFDIO_ZEROPAGE will never segfault.
+             */
+            if (!block->host || addr >= block->postcopy_length) {
                 error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
                 break;
@@ -3572,19 +3554,17 @@ static int ram_load_postcopy(QEMUFile *f)
              * of a host page in one chunk.
              */
             page_buffer = postcopy_host_page +
-                          ((uintptr_t)host & (block->page_size - 1));
+                          host_page_offset_from_ram_block_offset(block, addr);
+            /* If all TP are zero then we can optimise the place */
             if (target_pages == 1) {
-                this_host = (void *)QEMU_ALIGN_DOWN((uintptr_t)host,
-                                                    block->page_size);
-            } else {
+                host_page = host_page_from_ram_block_offset(block, addr);
+            } else if (host_page != host_page_from_ram_block_offset(block,
+                                                                    addr)) {
                 /* not the 1st TP within the HP */
-                if (QEMU_ALIGN_DOWN((uintptr_t)host, block->page_size) !=
-                    (uintptr_t)this_host) {
-                    error_report("Non-same host page %p/%p",
-                                  host, this_host);
-                    ret = -EINVAL;
-                    break;
-                }
+                error_report("Non-same host page %p/%p", host_page,
+                             host_page_from_ram_block_offset(block, addr));
+                ret = -EINVAL;
+                break;
             }
 
             /*
@@ -3663,16 +3643,11 @@ static int ram_load_postcopy(QEMUFile *f)
         }
 
         if (!ret && place_needed) {
-            /* This gets called at the last target page in the host page */
-            void *place_dest = (void *)QEMU_ALIGN_DOWN((uintptr_t)host,
-                                                       block->page_size);
-
             if (all_zero) {
-                ret = postcopy_place_page_zero(mis, place_dest,
-                                               block);
+                ret = postcopy_place_page_zero(mis, host_page, block);
             } else {
-                ret = postcopy_place_page(mis, place_dest,
-                                          place_source, block);
+                ret = postcopy_place_page(mis, host_page, place_source,
+                                          block);
             }
             place_needed = false;
             target_pages = 0;
@@ -3721,8 +3696,8 @@ void colo_flush_ram_cache(void)
         while (block) {
             offset = migration_bitmap_find_dirty(ram_state, block, offset);
 
-            if (((ram_addr_t)offset) << TARGET_PAGE_BITS
-                >= block->used_length) {
+            if (!offset_in_ramblock(block,
+                                    ((ram_addr_t)offset) << TARGET_PAGE_BITS)) {
                 offset = 0;
                 block = QLIST_NEXT_RCU(block, next);
             } else {
@@ -4136,8 +4111,69 @@ static SaveVMHandlers savevm_ram_handlers = {
     .resume_prepare = ram_resume_prepare,
 };
 
+static void ram_mig_ram_block_resized(RAMBlockNotifier *n, void *host,
+                                      size_t old_size, size_t new_size)
+{
+    PostcopyState ps = postcopy_state_get();
+    ram_addr_t offset;
+    RAMBlock *rb = qemu_ram_block_from_host(host, false, &offset);
+    Error *err = NULL;
+
+    if (ramblock_is_ignored(rb)) {
+        return;
+    }
+
+    if (!migration_is_idle()) {
+        /*
+         * Precopy code on the source cannot deal with the size of RAM blocks
+         * changing at random points in time - especially after sending the
+         * RAM block sizes in the migration stream, they must no longer change.
+         * Abort and indicate a proper reason.
+         */
+        error_setg(&err, "RAM block '%s' resized during precopy.", rb->idstr);
+        migrate_set_error(migrate_get_current(), err);
+        error_free(err);
+        migration_cancel();
+    }
+
+    switch (ps) {
+    case POSTCOPY_INCOMING_ADVISE:
+        /*
+         * Update what ram_postcopy_incoming_init()->init_range() does at the
+         * time postcopy was advised. Syncing RAM blocks with the source will
+         * result in RAM resizes.
+         */
+        if (old_size < new_size) {
+            if (ram_discard_range(rb->idstr, old_size, new_size - old_size)) {
+                error_report("RAM block '%s' discard of resized RAM failed",
+                             rb->idstr);
+            }
+        }
+        rb->postcopy_length = new_size;
+        break;
+    case POSTCOPY_INCOMING_NONE:
+    case POSTCOPY_INCOMING_RUNNING:
+    case POSTCOPY_INCOMING_END:
+        /*
+         * Once our guest is running, postcopy does no longer care about
+         * resizes. When growing, the new memory was not available on the
+         * source, no handler needed.
+         */
+        break;
+    default:
+        error_report("RAM block '%s' resized during postcopy state: %d",
+                     rb->idstr, ps);
+        exit(-1);
+    }
+}
+
+static RAMBlockNotifier ram_mig_ram_notifier = {
+    .ram_block_resized = ram_mig_ram_block_resized,
+};
+
 void ram_mig_init(void)
 {
     qemu_mutex_init(&XBZRLE.lock);
     register_savevm_live("ram", 0, 4, &savevm_ram_handlers, &ram_state);
+    ram_block_notifier_add(&ram_mig_ram_notifier);
 }
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 0ad5b77477..d9bef63373 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -224,7 +224,7 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
 
     migration_global_dump(mon);
 
-    if (info->blocked) {
+    if (info->blocked_reasons) {
         strList *reasons = info->blocked_reasons;
         monitor_printf(mon, "Outgoing migration blocked:\n");
         while (reasons) {
diff --git a/qapi/migration.json b/qapi/migration.json
index 0b17cce46b..7a5bdf9a0d 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -228,11 +228,6 @@
 #                   Present and non-empty when migration is blocked.
 #                   (since 6.0)
 #
-# @blocked: True if outgoing migration is blocked (since 6.0)
-#
-# Features:
-# @deprecated: Member @blocked is deprecated.  Use @blocked-reasons instead.
-#
 # Since: 0.14
 ##
 { 'struct': 'MigrationInfo',
@@ -246,7 +241,6 @@
            '*setup-time': 'int',
            '*cpu-throttle-percentage': 'int',
            '*error-desc': 'str',
-           'blocked': { 'type': 'bool', 'features': [ 'deprecated' ] },
            '*blocked-reasons': ['str'],
            '*postcopy-blocktime' : 'uint32',
            '*postcopy-vcpu-blocktime': ['uint32'],
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 5232696571..e1da81ed2f 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -1694,6 +1694,11 @@ ram_addr_t qemu_ram_get_used_length(RAMBlock *rb)
     return rb->used_length;
 }
 
+ram_addr_t qemu_ram_get_max_length(RAMBlock *rb)
+{
+    return rb->max_length;
+}
+
 bool qemu_ram_is_shared(RAMBlock *rb)
 {
     return rb->flags & RAM_SHARED;
@@ -1793,8 +1798,9 @@ static int memory_try_enable_merging(void *addr, size_t len)
     return qemu_madvise(addr, len, QEMU_MADV_MERGEABLE);
 }
 
-/* Only legal before guest might have detected the memory size: e.g. on
- * incoming migration, or right after reset.
+/*
+ * Resizing RAM while migrating can result in the migration being canceled.
+ * Care has to be taken if the guest might have already detected the memory.
  *
  * As memory core doesn't know how is memory accessed, it is up to
  * resize callback to update device state and/or add assertions to detect
@@ -1802,6 +1808,7 @@ static int memory_try_enable_merging(void *addr, size_t len)
  */
 int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
 {
+    const ram_addr_t oldsize = block->used_length;
     const ram_addr_t unaligned_size = newsize;
 
     assert(block);
@@ -1838,6 +1845,11 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
         return -EINVAL;
     }
 
+    /* Notify before modifying the ram block and touching the bitmaps. */
+    if (block->host) {
+        ram_block_notify_resize(block->host, oldsize, newsize);
+    }
+
     cpu_physical_memory_clear_dirty_range(block->offset, block->used_length);
     block->used_length = newsize;
     cpu_physical_memory_set_dirty_range(block->offset, block->used_length,
@@ -2005,7 +2017,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
             qemu_madvise(new_block->host, new_block->max_length,
                          QEMU_MADV_DONTFORK);
         }
-        ram_block_notify_add(new_block->host, new_block->max_length);
+        ram_block_notify_add(new_block->host, new_block->used_length,
+                             new_block->max_length);
     }
 }
 
@@ -2184,7 +2197,8 @@ void qemu_ram_free(RAMBlock *block)
     }
 
     if (block->host) {
-        ram_block_notify_remove(block->host, block->max_length);
+        ram_block_notify_remove(block->host, block->used_length,
+                                block->max_length);
     }
 
     qemu_mutex_lock_ramlist();
@@ -3486,7 +3500,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
         goto err;
     }
 
-    if ((start + length) <= rb->used_length) {
+    if ((start + length) <= rb->max_length) {
         bool need_madvise, need_fallocate;
         if (!QEMU_IS_ALIGNED(length, rb->page_size)) {
             error_report("ram_block_discard_range: Unaligned length: %zx",
@@ -3553,7 +3567,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
     } else {
         error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
                      "/%zx/" RAM_ADDR_FMT")",
-                     rb->idstr, start, length, rb->used_length);
+                     rb->idstr, start, length, rb->max_length);
     }
 
 err:
diff --git a/target/i386/hax/hax-mem.c b/target/i386/hax/hax-mem.c
index 35495f5e82..8d44edbffd 100644
--- a/target/i386/hax/hax-mem.c
+++ b/target/i386/hax/hax-mem.c
@@ -293,7 +293,8 @@ static MemoryListener hax_memory_listener = {
     .priority = 10,
 };
 
-static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
+static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size,
+                                size_t max_size)
 {
     /*
      * We must register each RAM block with the HAXM kernel module, or
@@ -304,7 +305,7 @@ static void hax_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
      * host physical pages for the RAM block as part of this registration
      * process, hence the name hax_populate_ram().
      */
-    if (hax_populate_ram((uint64_t)(uintptr_t)host, size) < 0) {
+    if (hax_populate_ram((uint64_t)(uintptr_t)host, max_size) < 0) {
         fprintf(stderr, "HAX failed to populate RAM\n");
         abort();
     }
diff --git a/target/i386/sev.c b/target/i386/sev.c
index 9a43be11cb..41f7800b5f 100644
--- a/target/i386/sev.c
+++ b/target/i386/sev.c
@@ -180,7 +180,8 @@ sev_set_guest_state(SevGuestState *sev, SevState new_state)
 }
 
 static void
-sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
+sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size,
+                    size_t max_size)
 {
     int r;
     struct kvm_enc_region range;
@@ -197,19 +198,20 @@ sev_ram_block_added(RAMBlockNotifier *n, void *host, size_t size)
     }
 
     range.addr = (__u64)(unsigned long)host;
-    range.size = size;
+    range.size = max_size;
 
-    trace_kvm_memcrypt_register_region(host, size);
+    trace_kvm_memcrypt_register_region(host, max_size);
     r = kvm_vm_ioctl(kvm_state, KVM_MEMORY_ENCRYPT_REG_REGION, &range);
     if (r) {
         error_report("%s: failed to register region (%p+%#zx) error '%s'",
-                     __func__, host, size, strerror(errno));
+                     __func__, host, max_size, strerror(errno));
         exit(1);
     }
 }
 
 static void
-sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size)
+sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size,
+                      size_t max_size)
 {
     int r;
     struct kvm_enc_region range;
@@ -226,13 +228,13 @@ sev_ram_block_removed(RAMBlockNotifier *n, void *host, size_t size)
     }
 
     range.addr = (__u64)(unsigned long)host;
-    range.size = size;
+    range.size = max_size;
 
-    trace_kvm_memcrypt_unregister_region(host, size);
+    trace_kvm_memcrypt_unregister_region(host, max_size);
     r = kvm_vm_ioctl(kvm_state, KVM_MEMORY_ENCRYPT_UNREG_REGION, &range);
     if (r) {
         error_report("%s: failed to unregister region (%p+%#zx)",
-                     __func__, host, size);
+                     __func__, host, max_size);
     }
 }
 
diff --git a/tests/migration/guestperf/comparison.py b/tests/migration/guestperf/comparison.py
index ba2edbe546..c03b3f6d7e 100644
--- a/tests/migration/guestperf/comparison.py
+++ b/tests/migration/guestperf/comparison.py
@@ -121,4 +121,18 @@ COMPARISONS = [
         Scenario("compr-xbzrle-cache-50",
                  compression_xbzrle=True, compression_xbzrle_cache=50),
     ]),
+
+
+    # Looking at effect of multifd with
+    # varying numbers of channels
+    Comparison("compr-multifd", scenarios = [
+        Scenario("compr-multifd-channels-4",
+                 multifd=True, multifd_channels=2),
+        Scenario("compr-multifd-channels-8",
+                 multifd=True, multifd_channels=8),
+        Scenario("compr-multifd-channels-32",
+                 multifd=True, multifd_channels=32),
+        Scenario("compr-multifd-channels-64",
+                 multifd=True, multifd_channels=64),
+    ]),
 ]
diff --git a/tests/migration/guestperf/engine.py b/tests/migration/guestperf/engine.py
index 6b49aed579..208e095794 100644
--- a/tests/migration/guestperf/engine.py
+++ b/tests/migration/guestperf/engine.py
@@ -188,6 +188,22 @@ class Engine(object):
                                    1024 * 1024 * 1024 / 100 *
                                    scenario._compression_xbzrle_cache))
 
+        if scenario._multifd:
+            resp = src.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "multifd",
+                                     "state": True }
+                               ])
+            resp = src.command("migrate-set-parameters",
+                               multifd_channels=scenario._multifd_channels)
+            resp = dst.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "multifd",
+                                     "state": True }
+                               ])
+            resp = dst.command("migrate-set-parameters",
+                               multifd_channels=scenario._multifd_channels)
+
         resp = src.command("migrate", uri=connect_uri)
 
         post_copy = False
diff --git a/tests/migration/guestperf/scenario.py b/tests/migration/guestperf/scenario.py
index 28ef36c26d..de70d9b2f5 100644
--- a/tests/migration/guestperf/scenario.py
+++ b/tests/migration/guestperf/scenario.py
@@ -29,7 +29,8 @@ class Scenario(object):
                  post_copy=False, post_copy_iters=5,
                  auto_converge=False, auto_converge_step=10,
                  compression_mt=False, compression_mt_threads=1,
-                 compression_xbzrle=False, compression_xbzrle_cache=10):
+                 compression_xbzrle=False, compression_xbzrle_cache=10,
+                 multifd=False, multifd_channels=2):
 
         self._name = name
 
@@ -56,6 +57,9 @@ class Scenario(object):
         self._compression_xbzrle = compression_xbzrle
         self._compression_xbzrle_cache = compression_xbzrle_cache # percentage of guest RAM
 
+        self._multifd = multifd
+        self._multifd_channels = multifd_channels
+
     def serialize(self):
         return {
             "name": self._name,
@@ -73,6 +77,8 @@ class Scenario(object):
             "compression_mt_threads": self._compression_mt_threads,
             "compression_xbzrle": self._compression_xbzrle,
             "compression_xbzrle_cache": self._compression_xbzrle_cache,
+            "multifd": self._multifd,
+            "multifd_channels": self._multifd_channels,
         }
 
     @classmethod
@@ -92,4 +98,6 @@ class Scenario(object):
             data["compression_mt"],
             data["compression_mt_threads"],
             data["compression_xbzrle"],
-            data["compression_xbzrle_cache"])
+            data["compression_xbzrle_cache"],
+            data["multifd"],
+            data["multifd_channels"])
diff --git a/tests/migration/guestperf/shell.py b/tests/migration/guestperf/shell.py
index f838888809..8a809e3dda 100644
--- a/tests/migration/guestperf/shell.py
+++ b/tests/migration/guestperf/shell.py
@@ -122,6 +122,11 @@ class Shell(BaseShell):
         parser.add_argument("--compression-xbzrle", dest="compression_xbzrle", default=False, action="store_true")
         parser.add_argument("--compression-xbzrle-cache", dest="compression_xbzrle_cache", default=10, type=int)
 
+        parser.add_argument("--multifd", dest="multifd", default=False,
+                            action="store_true")
+        parser.add_argument("--multifd-channels", dest="multifd_channels",
+                            default=2, type=int)
+
     def get_scenario(self, args):
         return Scenario(name="perfreport",
                         downtime=args.downtime,
@@ -142,7 +147,10 @@ class Shell(BaseShell):
                         compression_mt_threads=args.compression_mt_threads,
 
                         compression_xbzrle=args.compression_xbzrle,
-                        compression_xbzrle_cache=args.compression_xbzrle_cache)
+                        compression_xbzrle_cache=args.compression_xbzrle_cache,
+
+                        multifd=args.multifd,
+                        multifd_channels=args.multifd_channels)
 
     def run(self, argv):
         args = self._parser.parse_args(argv)
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 3a711bb492..2b028df687 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -110,13 +110,12 @@ static void init_bootfile(const char *bootpath, void *content, size_t len)
  */
 static void wait_for_serial(const char *side)
 {
-    char *serialpath = g_strdup_printf("%s/%s", tmpfs, side);
+    g_autofree char *serialpath = g_strdup_printf("%s/%s", tmpfs, side);
     FILE *serialfile = fopen(serialpath, "r");
     const char *arch = qtest_get_arch();
     int started = (strcmp(side, "src_serial") == 0 &&
                    strcmp(arch, "ppc64") == 0) ? 0 : 1;
 
-    g_free(serialpath);
     do {
         int readvalue = fgetc(serialfile);
 
@@ -274,10 +273,9 @@ static void check_guests_ram(QTestState *who)
 
 static void cleanup(const char *filename)
 {
-    char *path = g_strdup_printf("%s/%s", tmpfs, filename);
+    g_autofree char *path = g_strdup_printf("%s/%s", tmpfs, filename);
 
     unlink(path);
-    g_free(path);
 }
 
 static char *SocketAddress_to_str(SocketAddress *addr)
@@ -374,11 +372,8 @@ static char *migrate_get_parameter_str(QTestState *who,
 static void migrate_check_parameter_str(QTestState *who, const char *parameter,
                                         const char *value)
 {
-    char *result;
-
-    result = migrate_get_parameter_str(who, parameter);
+    g_autofree char *result = migrate_get_parameter_str(who, parameter);
     g_assert_cmpstr(result, ==, value);
-    g_free(result);
 }
 
 static void migrate_set_parameter_str(QTestState *who, const char *parameter,
@@ -495,12 +490,14 @@ static void migrate_start_destroy(MigrateStart *args)
 static int test_migrate_start(QTestState **from, QTestState **to,
                               const char *uri, MigrateStart *args)
 {
-    gchar *arch_source, *arch_target;
-    gchar *cmd_source, *cmd_target;
+    g_autofree gchar *arch_source = NULL;
+    g_autofree gchar *arch_target = NULL;
+    g_autofree gchar *cmd_source = NULL;
+    g_autofree gchar *cmd_target = NULL;
     const gchar *ignore_stderr;
-    char *bootpath = NULL;
-    char *shmem_opts;
-    char *shmem_path;
+    g_autofree char *bootpath = NULL;
+    g_autofree char *shmem_opts = NULL;
+    g_autofree char *shmem_path = NULL;
     const char *arch = qtest_get_arch();
     const char *machine_opts = NULL;
     const char *memory_size;
@@ -559,8 +556,6 @@ static int test_migrate_start(QTestState **from, QTestState **to,
         g_assert_not_reached();
     }
 
-    g_free(bootpath);
-
     if (!getenv("QTEST_LOG") && args->hide_stderr) {
         ignore_stderr = "2>/dev/null";
     } else {
@@ -588,11 +583,9 @@ static int test_migrate_start(QTestState **from, QTestState **to,
                                  memory_size, tmpfs,
                                  arch_source, shmem_opts, args->opts_source,
                                  ignore_stderr);
-    g_free(arch_source);
     if (!args->only_target) {
         *from = qtest_init(cmd_source);
     }
-    g_free(cmd_source);
 
     cmd_target = g_strdup_printf("-accel kvm -accel tcg%s%s "
                                  "-name target,debug-threads=on "
@@ -605,18 +598,14 @@ static int test_migrate_start(QTestState **from, QTestState **to,
                                  memory_size, tmpfs, uri,
                                  arch_target, shmem_opts,
                                  args->opts_target, ignore_stderr);
-    g_free(arch_target);
     *to = qtest_init(cmd_target);
-    g_free(cmd_target);
 
-    g_free(shmem_opts);
     /*
      * Remove shmem file immediately to avoid memory leak in test failed case.
      * It's valid becase QEMU has already opened this file
      */
     if (args->use_shmem) {
         unlink(shmem_path);
-        g_free(shmem_path);
     }
 
 out:
@@ -662,7 +651,7 @@ static int migrate_postcopy_prepare(QTestState **from_ptr,
                                     QTestState **to_ptr,
                                     MigrateStart *args)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     QTestState *from, *to;
 
     if (test_migrate_start(&from, &to, uri, args)) {
@@ -684,7 +673,6 @@ static int migrate_postcopy_prepare(QTestState **from_ptr,
     wait_for_serial("src_serial");
 
     migrate_qmp(from, uri, "{}");
-    g_free(uri);
 
     wait_for_migration_pass(from);
 
@@ -724,7 +712,7 @@ static void test_postcopy_recovery(void)
 {
     MigrateStart *args = migrate_start_new();
     QTestState *from, *to;
-    char *uri;
+    g_autofree char *uri = NULL;
 
     args->hide_stderr = true;
 
@@ -775,7 +763,6 @@ static void test_postcopy_recovery(void)
                               (const char * []) { "failed", "active",
                                                   "completed", NULL });
     migrate_qmp(from, uri, "{'resume': true}");
-    g_free(uri);
 
     /* Restore the postcopy bandwidth to unlimited */
     migrate_set_parameter_int(from, "max-postcopy-bandwidth", 0);
@@ -800,7 +787,7 @@ static void test_baddest(void)
 
 static void test_precopy_unix(void)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     MigrateStart *args = migrate_start_new();
     QTestState *from, *to;
 
@@ -836,14 +823,13 @@ static void test_precopy_unix(void)
     wait_for_migration_complete(from);
 
     test_migrate_end(from, to, true);
-    g_free(uri);
 }
 
 #if 0
 /* Currently upset on aarch64 TCG */
 static void test_ignore_shared(void)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     QTestState *from, *to;
 
     if (test_migrate_start(&from, &to, uri, false, true, NULL, NULL)) {
@@ -873,7 +859,6 @@ static void test_ignore_shared(void)
     g_assert_cmpint(read_ram_property_int(from, "transferred"), <, 1024 * 1024);
 
     test_migrate_end(from, to, true);
-    g_free(uri);
 }
 #endif
 
@@ -898,8 +883,8 @@ static void test_xbzrle(const char *uri)
 
     migrate_set_parameter_int(from, "xbzrle-cache-size", 33554432);
 
-    migrate_set_capability(from, "xbzrle", "true");
-    migrate_set_capability(to, "xbzrle", "true");
+    migrate_set_capability(from, "xbzrle", true);
+    migrate_set_capability(to, "xbzrle", true);
     /* Wait for the first serial output from the source */
     wait_for_serial("src_serial");
 
@@ -925,16 +910,15 @@ static void test_xbzrle(const char *uri)
 
 static void test_xbzrle_unix(void)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
 
     test_xbzrle(uri);
-    g_free(uri);
 }
 
 static void test_precopy_tcp(void)
 {
     MigrateStart *args = migrate_start_new();
-    char *uri;
+    g_autofree char *uri = NULL;
     QTestState *from, *to;
 
     if (test_migrate_start(&from, &to, "tcp:127.0.0.1:0", args)) {
@@ -971,7 +955,6 @@ static void test_precopy_tcp(void)
     wait_for_migration_complete(from);
 
     test_migrate_end(from, to, true);
-    g_free(uri);
 }
 
 static void test_migrate_fd_proto(void)
@@ -1060,7 +1043,7 @@ static void test_migrate_fd_proto(void)
 
 static void do_test_validate_uuid(MigrateStart *args, bool should_fail)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     QTestState *from, *to;
 
     if (test_migrate_start(&from, &to, uri, args)) {
@@ -1088,7 +1071,6 @@ static void do_test_validate_uuid(MigrateStart *args, bool should_fail)
     }
 
     test_migrate_end(from, to, false);
-    g_free(uri);
 }
 
 static void test_validate_uuid(void)
@@ -1136,7 +1118,7 @@ static void test_validate_uuid_dst_not_set(void)
 
 static void test_migrate_auto_converge(void)
 {
-    char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
+    g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs);
     MigrateStart *args = migrate_start_new();
     QTestState *from, *to;
     int64_t remaining, percentage;
@@ -1214,7 +1196,6 @@ static void test_migrate_auto_converge(void)
     wait_for_serial("dest_serial");
     wait_for_migration_complete(from);
 
-    g_free(uri);
 
     test_migrate_end(from, to, true);
 }
@@ -1224,7 +1205,7 @@ static void test_multifd_tcp(const char *method)
     MigrateStart *args = migrate_start_new();
     QTestState *from, *to;
     QDict *rsp;
-    char *uri;
+    g_autofree char *uri = NULL;
 
     if (test_migrate_start(&from, &to, "defer", args)) {
         return;
@@ -1246,8 +1227,8 @@ static void test_multifd_tcp(const char *method)
     migrate_set_parameter_str(from, "multifd-compression", method);
     migrate_set_parameter_str(to, "multifd-compression", method);
 
-    migrate_set_capability(from, "multifd", "true");
-    migrate_set_capability(to, "multifd", "true");
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
     rsp = wait_command(to, "{ 'execute': 'migrate-incoming',"
@@ -1273,7 +1254,6 @@ static void test_multifd_tcp(const char *method)
     wait_for_serial("dest_serial");
     wait_for_migration_complete(from);
     test_migrate_end(from, to, true);
-    g_free(uri);
 }
 
 static void test_multifd_tcp_none(void)
@@ -1309,7 +1289,7 @@ static void test_multifd_tcp_cancel(void)
     MigrateStart *args = migrate_start_new();
     QTestState *from, *to, *to2;
     QDict *rsp;
-    char *uri;
+    g_autofree char *uri = NULL;
 
     args->hide_stderr = true;
 
@@ -1330,8 +1310,8 @@ static void test_multifd_tcp_cancel(void)
     migrate_set_parameter_int(from, "multifd-channels", 16);
     migrate_set_parameter_int(to, "multifd-channels", 16);
 
-    migrate_set_capability(from, "multifd", "true");
-    migrate_set_capability(to, "multifd", "true");
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
     rsp = wait_command(to, "{ 'execute': 'migrate-incoming',"
@@ -1358,7 +1338,7 @@ static void test_multifd_tcp_cancel(void)
 
     migrate_set_parameter_int(to2, "multifd-channels", 16);
 
-    migrate_set_capability(to2, "multifd", "true");
+    migrate_set_capability(to2, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
     rsp = wait_command(to2, "{ 'execute': 'migrate-incoming',"
@@ -1387,7 +1367,6 @@ static void test_multifd_tcp_cancel(void)
     wait_for_serial("dest_serial");
     wait_for_migration_complete(from);
     test_migrate_end(from, to2, true);
-    g_free(uri);
 }
 
 int main(int argc, char **argv)
diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
index 97dfa3fd57..911115b86e 100644
--- a/util/vfio-helpers.c
+++ b/util/vfio-helpers.c
@@ -459,51 +459,38 @@ fail_container:
     return ret;
 }
 
-static void qemu_vfio_ram_block_added(RAMBlockNotifier *n,
-                                      void *host, size_t size)
+static void qemu_vfio_ram_block_added(RAMBlockNotifier *n, void *host,
+                                      size_t size, size_t max_size)
 {
     QEMUVFIOState *s = container_of(n, QEMUVFIOState, ram_notifier);
-    trace_qemu_vfio_ram_block_added(s, host, size);
-    qemu_vfio_dma_map(s, host, size, false, NULL);
+    int ret;
+
+    trace_qemu_vfio_ram_block_added(s, host, max_size);
+    ret = qemu_vfio_dma_map(s, host, max_size, false, NULL);
+    if (ret) {
+        error_report("qemu_vfio_dma_map(%p, %zu) failed: %s", host, max_size,
+                     strerror(-ret));
+    }
 }
 
-static void qemu_vfio_ram_block_removed(RAMBlockNotifier *n,
-                                        void *host, size_t size)
+static void qemu_vfio_ram_block_removed(RAMBlockNotifier *n, void *host,
+                                        size_t size, size_t max_size)
 {
     QEMUVFIOState *s = container_of(n, QEMUVFIOState, ram_notifier);
     if (host) {
-        trace_qemu_vfio_ram_block_removed(s, host, size);
+        trace_qemu_vfio_ram_block_removed(s, host, max_size);
         qemu_vfio_dma_unmap(s, host);
     }
 }
 
-static int qemu_vfio_init_ramblock(RAMBlock *rb, void *opaque)
-{
-    void *host_addr = qemu_ram_get_host_addr(rb);
-    ram_addr_t length = qemu_ram_get_used_length(rb);
-    int ret;
-    QEMUVFIOState *s = opaque;
-
-    if (!host_addr) {
-        return 0;
-    }
-    ret = qemu_vfio_dma_map(s, host_addr, length, false, NULL);
-    if (ret) {
-        fprintf(stderr, "qemu_vfio_init_ramblock: failed %p %" PRId64 "\n",
-                host_addr, (uint64_t)length);
-    }
-    return 0;
-}
-
 static void qemu_vfio_open_common(QEMUVFIOState *s)
 {
     qemu_mutex_init(&s->lock);
     s->ram_notifier.ram_block_added = qemu_vfio_ram_block_added;
     s->ram_notifier.ram_block_removed = qemu_vfio_ram_block_removed;
-    ram_block_notifier_add(&s->ram_notifier);
     s->low_water_mark = QEMU_VFIO_IOVA_MIN;
     s->high_water_mark = QEMU_VFIO_IOVA_MAX;
-    qemu_ram_foreach_block(qemu_vfio_init_ramblock, s);
+    ram_block_notifier_add(&s->ram_notifier);
 }
 
 /**