Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20180710a' into staging

Migration pull 2018-07-10 (for 3.0)

Migration fixes and migration test fixes, mostly
around postcopy and postcopy recovery

# gpg: Signature made Tue 10 Jul 2018 16:27:19 BST
# gpg:                using RSA key 0516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <[email protected]>"
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20180710a:
  migration: reorder MIG_CMD_POSTCOPY_RESUME
  tests: hide stderr for postcopy recovery test
  tests: add postcopy recovery test
  tests: introduce wait_for_migration_status()
  tests: introduce migrate_query*() helpers
  tests: allow migrate() to take extra flags
  tests: introduce migrate_postcopy_* helpers
  migration: show pause/recover state on dst host
  migration: fix incorrect bitmap size calculation
  migration: loosen recovery check when load vm
  migration: simplify check to use qemu file buffer
  migration: unify incoming processing
  migration: unbreak postcopy recovery
  migration: move income process out of multifd
  migration: delay postcopy paused state

Signed-off-by: Peter Maydell <[email protected]>

Author: pm215

migration/exec.c

@@ -49,9 +49,6 @@ static gboolean exec_accept_incoming_migration(QIOChannel *ioc,
 {
     migration_channel_process_incoming(ioc);
     object_unref(OBJECT(ioc));
-    if (!migrate_use_multifd()) {
-        migration_incoming_process();
-    }
     return G_SOURCE_REMOVE;
 }
 

migration/fd.c

@@ -49,9 +49,6 @@ static gboolean fd_accept_incoming_migration(QIOChannel *ioc,
 {
     migration_channel_process_incoming(ioc);
     object_unref(OBJECT(ioc));
-    if (!migrate_use_multifd()) {
-        migration_incoming_process();
-    }
     return G_SOURCE_REMOVE;
 }
 

migration/migration.c

@@ -466,7 +466,8 @@ void migration_incoming_process(void)
     qemu_coroutine_enter(co);
 }
 
-void migration_fd_process_incoming(QEMUFile *f)
+/* Returns true if recovered from a paused migration, otherwise false */
+static bool postcopy_try_recover(QEMUFile *f)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
 
@@ -491,23 +492,52 @@ void migration_fd_process_incoming(QEMUFile *f)
          * that source is ready to reply to page requests.
          */
         qemu_sem_post(&mis->postcopy_pause_sem_dst);
-    } else {
-        /* New incoming migration */
-        migration_incoming_setup(f);
-        migration_incoming_process();
+        return true;
+    }
+
+    return false;
+}
+
+void migration_fd_process_incoming(QEMUFile *f)
+{
+    if (postcopy_try_recover(f)) {
+        return;
     }
+
+    migration_incoming_setup(f);
+    migration_incoming_process();
 }
 
 void migration_ioc_process_incoming(QIOChannel *ioc)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
+    bool start_migration;
 
     if (!mis->from_src_file) {
+        /* The first connection (multifd may have multiple) */
         QEMUFile *f = qemu_fopen_channel_input(ioc);
+
+        /* If it's a recovery, we're done */
+        if (postcopy_try_recover(f)) {
+            return;
+        }
+
         migration_incoming_setup(f);
-        return;
+
+        /*
+         * Common migration only needs one channel, so we can start
+         * right now.  Multifd needs more than one channel, we wait.
+         */
+        start_migration = !migrate_use_multifd();
+    } else {
+        /* Multiple connections */
+        assert(migrate_use_multifd());
+        start_migration = multifd_recv_new_channel(ioc);
+    }
+
+    if (start_migration) {
+        migration_incoming_process();
     }
-    multifd_recv_new_channel(ioc);
 }
 
 /**
@@ -881,6 +911,8 @@ static void fill_destination_migration_info(MigrationInfo *info)
     case MIGRATION_STATUS_CANCELLED:
     case MIGRATION_STATUS_ACTIVE:
     case MIGRATION_STATUS_POSTCOPY_ACTIVE:
+    case MIGRATION_STATUS_POSTCOPY_PAUSED:
+    case MIGRATION_STATUS_POSTCOPY_RECOVER:
     case MIGRATION_STATUS_FAILED:
     case MIGRATION_STATUS_COLO:
         info->has_status = true;

migration/ram.c

@@ -235,7 +235,7 @@ int64_t ramblock_recv_bitmap_send(QEMUFile *file,
     bitmap_to_le(le_bitmap, block->receivedmap, nbits);
 
     /* Size of the bitmap, in bytes */
-    size = nbits / 8;
+    size = DIV_ROUND_UP(nbits, 8);
 
     /*
      * size is always aligned to 8 bytes for 64bit machines, but it
@@ -1311,7 +1311,8 @@ bool multifd_recv_all_channels_created(void)
     return thread_count == atomic_read(&multifd_recv_state->count);
 }
 
-void multifd_recv_new_channel(QIOChannel *ioc)
+/* Return true if multifd is ready for the migration, otherwise false */
+bool multifd_recv_new_channel(QIOChannel *ioc)
 {
     MultiFDRecvParams *p;
     Error *local_err = NULL;
@@ -1320,15 +1321,15 @@ void multifd_recv_new_channel(QIOChannel *ioc)
     id = multifd_recv_initial_packet(ioc, &local_err);
     if (id < 0) {
         multifd_recv_terminate_threads(local_err);
-        return;
+        return false;
     }
 
     p = &multifd_recv_state->params[id];
     if (p->c != NULL) {
         error_setg(&local_err, "multifd: received id '%d' already setup'",
                    id);
         multifd_recv_terminate_threads(local_err);
-        return;
+        return false;
     }
     p->c = ioc;
     object_ref(OBJECT(ioc));
@@ -1339,9 +1340,7 @@ void multifd_recv_new_channel(QIOChannel *ioc)
     qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
                        QEMU_THREAD_JOINABLE);
     atomic_inc(&multifd_recv_state->count);
-    if (multifd_recv_state->count == migrate_multifd_channels()) {
-        migration_incoming_process();
-    }
+    return multifd_recv_state->count == migrate_multifd_channels();
 }
 
 /**
@@ -3581,7 +3580,7 @@ static int ram_load_postcopy(QEMUFile *f)
 {
     int flags = 0, ret = 0;
     bool place_needed = false;
-    bool matching_page_sizes = false;
+    bool matches_target_page_size = false;
     MigrationIncomingState *mis = migration_incoming_get_current();
     /* Temporary page that is later 'placed' */
     void *postcopy_host_page = postcopy_get_tmp_page(mis);
@@ -3621,7 +3620,7 @@ static int ram_load_postcopy(QEMUFile *f)
                 ret = -EINVAL;
                 break;
             }
-            matching_page_sizes = block->page_size == TARGET_PAGE_SIZE;
+            matches_target_page_size = block->page_size == TARGET_PAGE_SIZE;
             /*
              * Postcopy requires that we place whole host pages atomically;
              * these may be huge pages for RAMBlocks that are backed by
@@ -3669,12 +3668,17 @@ static int ram_load_postcopy(QEMUFile *f)
 
         case RAM_SAVE_FLAG_PAGE:
             all_zero = false;
-            if (!place_needed || !matching_page_sizes) {
+            if (!matches_target_page_size) {
+                /* For huge pages, we always use temporary buffer */
                 qemu_get_buffer(f, page_buffer, TARGET_PAGE_SIZE);
             } else {
-                /* Avoids the qemu_file copy during postcopy, which is
-                 * going to do a copy later; can only do it when we
-                 * do this read in one go (matching page sizes)
+                /*
+                 * For small pages that matches target page size, we
+                 * avoid the qemu_file copy.  Instead we directly use
+                 * the buffer of QEMUFile to place the page.  Note: we
+                 * cannot do any QEMUFile operation before using that
+                 * buffer to make sure the buffer is valid when
+                 * placing the page.
                  */
                 qemu_get_buffer_in_place(f, (uint8_t **)&place_source,
                                          TARGET_PAGE_SIZE);
@@ -3940,7 +3944,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
     int ret = -EINVAL;
     QEMUFile *file = s->rp_state.from_dst_file;
     unsigned long *le_bitmap, nbits = block->used_length >> TARGET_PAGE_BITS;
-    uint64_t local_size = nbits / 8;
+    uint64_t local_size = DIV_ROUND_UP(nbits, 8);
     uint64_t size, end_mark;
 
     trace_ram_dirty_bitmap_reload_begin(block->idstr);

migration/ram.h

@@ -46,7 +46,7 @@ int multifd_save_cleanup(Error **errp);
 int multifd_load_setup(void);
 int multifd_load_cleanup(Error **errp);
 bool multifd_recv_all_channels_created(void);
-void multifd_recv_new_channel(QIOChannel *ioc);
+bool multifd_recv_new_channel(QIOChannel *ioc);
 
 uint64_t ram_pagesize_summary(void);
 int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len);

migration/savevm.c

@@ -81,8 +81,8 @@ enum qemu_vm_cmd {
     MIG_CMD_POSTCOPY_RAM_DISCARD,  /* A list of pages to discard that
                                       were previously sent during
                                       precopy but are dirty. */
-    MIG_CMD_POSTCOPY_RESUME,       /* resume postcopy on dest */
     MIG_CMD_PACKAGED,          /* Send a wrapped stream within this stream */
+    MIG_CMD_POSTCOPY_RESUME,   /* resume postcopy on dest */
     MIG_CMD_RECV_BITMAP,       /* Request for recved bitmap on dst */
     MIG_CMD_MAX
 };
@@ -2194,9 +2194,6 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
     /* Clear the triggered bit to allow one recovery */
     mis->postcopy_recover_triggered = false;
 
-    migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
-                      MIGRATION_STATUS_POSTCOPY_PAUSED);
-
     assert(mis->from_src_file);
     qemu_file_shutdown(mis->from_src_file);
     qemu_fclose(mis->from_src_file);
@@ -2209,6 +2206,9 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
     mis->to_src_file = NULL;
     qemu_mutex_unlock(&mis->rp_mutex);
 
+    migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+                      MIGRATION_STATUS_POSTCOPY_PAUSED);
+
     /* Notify the fault thread for the invalidated file handle */
     postcopy_fault_thread_notify(mis);
 
@@ -2276,18 +2276,14 @@ static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis)
         qemu_file_set_error(f, ret);
 
         /*
-         * Detect whether it is:
-         *
-         * 1. postcopy running (after receiving all device data, which
-         *    must be in POSTCOPY_INCOMING_RUNNING state.  Note that
-         *    POSTCOPY_INCOMING_LISTENING is still not enough, it's
-         *    still receiving device states).
-         * 2. network failure (-EIO)
-         *
-         * If so, we try to wait for a recovery.
+         * If we are during an active postcopy, then we pause instead
+         * of bail out to at least keep the VM's dirty data.  Note
+         * that POSTCOPY_INCOMING_LISTENING stage is still not enough,
+         * during which we're still receiving device states and we
+         * still haven't yet started the VM on destination.
          */
         if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING &&
-            ret == -EIO && postcopy_pause_incoming(mis)) {
+            postcopy_pause_incoming(mis)) {
             /* Reset f to point to the newly created channel */
             f = mis->from_src_file;
             goto retry;

migration/socket.c

@@ -168,12 +168,7 @@ static void socket_accept_incoming_migration(QIONetListener *listener,
     if (migration_has_all_channels()) {
         /* Close listening socket as its no longer needed */
         qio_net_listener_disconnect(listener);
-
         object_unref(OBJECT(listener));
-
-        if (!migrate_use_multifd()) {
-            migration_incoming_process();
-        }
     }
 }