Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20…

…210511a' into staging

Migration pull 2021-05-11

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 Tue 11 May 2021 16:06:42 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-20210511a:
  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>

hw/core/numa.c

@@ -802,30 +802,63 @@ 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)
 {
     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);
+        }
     }
 }

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);

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:

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;

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);

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

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

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);
 

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);

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)

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

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;

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
@@ -452,6 +454,13 @@ static int init_range(RAMBlock *rb, void *opaque)
     ram_addr_t length = qemu_ram_get_used_length(rb);
     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
@@ -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 */