Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20200601a' into staging

Migration/virtio/hmp pull 2020-06-01

A mixed pull with:
  - RDMA migration fix (CID 1428762)
  - HMP qom-get addition and qom-set cleanup
  - a virtiofsd fix
  - COLO fixes

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

# gpg: Signature made Mon 01 Jun 2020 19:37:15 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-20200601a:
  migration/migration.c: Fix hang in ram_save_host_page
  migration/colo.c: Move colo_notify_compares_event to the right place
  migration/colo.c: Relaunch failover even if there was an error
  migration/colo.c: Flush ram cache only after receiving device state
  migration/colo.c: Use cpu_synchronize_all_states()
  migration/colo.c: Use event instead of semaphore
  migration/vmstate: Remove unnecessary MemoryRegion forward declaration
  virtiofsd: remove symlink fallbacks
  hmp: Simplify qom-set
  hmp: Implement qom-get HMP command
  migration/rdma: cleanup rdma context before g_free to avoid memleaks
  migration/rdma: fix potential nullptr access in rdma_start_incoming_migration

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

6 files changed, 40 insertions, 25 deletions

diff --git a/migration/colo.c b/migration/colo.c
index d015d4f..ea7d1e9 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -436,11 +436,6 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
         goto out;
     }
 
-    colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err);
-    if (local_err) {
-        goto out;
-    }
-
     /* Disable block migration */
     migrate_set_block_enabled(false, &local_err);
     if (local_err) {
@@ -502,6 +497,12 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
         goto out;
     }
 
+    qemu_event_reset(&s->colo_checkpoint_event);
+    colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err);
+    if (local_err) {
+        goto out;
+    }
+
     colo_receive_check_message(s->rp_state.from_dst_file,
                        COLO_MESSAGE_VMSTATE_LOADED, &local_err);
     if (local_err) {
@@ -589,7 +590,7 @@ static void colo_process_checkpoint(MigrationState *s)
             goto out;
         }
 
-        qemu_sem_wait(&s->colo_checkpoint_sem);
+        qemu_event_wait(&s->colo_checkpoint_event);
 
         if (s->state != MIGRATION_STATUS_COLO) {
             goto out;
@@ -637,7 +638,7 @@ out:
     colo_compare_unregister_notifier(&packets_compare_notifier);
     timer_del(s->colo_delay_timer);
     timer_free(s->colo_delay_timer);
-    qemu_sem_destroy(&s->colo_checkpoint_sem);
+    qemu_event_destroy(&s->colo_checkpoint_event);
 
     /*
      * Must be called after failover BH is completed,
@@ -654,7 +655,7 @@ void colo_checkpoint_notify(void *opaque)
     MigrationState *s = opaque;
     int64_t next_notify_time;
 
-    qemu_sem_post(&s->colo_checkpoint_sem);
+    qemu_event_set(&s->colo_checkpoint_event);
     s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     next_notify_time = s->colo_checkpoint_time +
                     s->parameters.x_checkpoint_delay;
@@ -664,7 +665,7 @@ void colo_checkpoint_notify(void *opaque)
 void migrate_start_colo_process(MigrationState *s)
 {
     qemu_mutex_unlock_iothread();
-    qemu_sem_init(&s->colo_checkpoint_sem, 0);
+    qemu_event_init(&s->colo_checkpoint_event, false);
     s->colo_delay_timer =  timer_new_ms(QEMU_CLOCK_HOST,
                                 colo_checkpoint_notify, s);
 
@@ -704,7 +705,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     }
 
     qemu_mutex_lock_iothread();
-    cpu_synchronize_all_pre_loadvm();
+    cpu_synchronize_all_states();
     ret = qemu_loadvm_state_main(mis->from_src_file, mis);
     qemu_mutex_unlock_iothread();
 
@@ -747,9 +748,11 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
 
     qemu_mutex_lock_iothread();
     vmstate_loading = true;
+    colo_flush_ram_cache();
     ret = qemu_load_device_state(fb);
     if (ret < 0) {
         error_setg(errp, "COLO: load device state failed");
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -758,6 +761,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     replication_get_error_all(&local_err);
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -766,6 +770,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     replication_do_checkpoint_all(&local_err);
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -777,6 +782,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
 
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -787,9 +793,6 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     qemu_mutex_unlock_iothread();
 
     if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
-        failover_set_state(FAILOVER_STATUS_RELAUNCH,
-                        FAILOVER_STATUS_NONE);
-        failover_request_active(NULL);
         return;
     }
 
@@ -888,6 +891,14 @@ void *colo_process_incoming_thread(void *opaque)
             error_report_err(local_err);
             break;
         }
+
+        if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+            failover_set_state(FAILOVER_STATUS_RELAUNCH,
+                            FAILOVER_STATUS_NONE);
+            failover_request_active(NULL);
+            break;
+        }
+
         if (failover_get_state() != FAILOVER_STATUS_NONE) {
             error_report("failover request");
             break;
@@ -895,8 +906,6 @@ void *colo_process_incoming_thread(void *opaque)
     }
 
 out:
-    vmstate_loading = false;
-
     /*
      * There are only two reasons we can get here, some error happened
      * or the user triggered failover.
diff --git a/migration/migration.c b/migration/migration.c
index 0bb042a..b63ad91 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3361,6 +3361,10 @@ bool migration_rate_limit(void)
     bool urgent = false;
     migration_update_counters(s, now);
     if (qemu_file_rate_limit(s->to_dst_file)) {
+
+        if (qemu_file_get_error(s->to_dst_file)) {
+            return false;
+        }
         /*
          * Wait for a delay to do rate limiting OR
          * something urgent to post the semaphore.
diff --git a/migration/migration.h b/migration/migration.h
index 507284e..f617960 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -215,8 +215,8 @@ struct MigrationState
     /* The semaphore is used to notify COLO thread that failover is finished */
     QemuSemaphore colo_exit_sem;
 
-    /* The semaphore is used to notify COLO thread to do checkpoint */
-    QemuSemaphore colo_checkpoint_sem;
+    /* The event is used to notify COLO thread to do checkpoint */
+    QemuEvent colo_checkpoint_event;
     int64_t colo_checkpoint_time;
     QEMUTimer *colo_delay_timer;
 
diff --git a/migration/ram.c b/migration/ram.c
index 859f835..41cc530 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -3360,7 +3360,7 @@ static bool postcopy_is_running(void)
  * Flush content of RAM cache into SVM's memory.
  * Only flush the pages that be dirtied by PVM or SVM or both.
  */
-static void colo_flush_ram_cache(void)
+void colo_flush_ram_cache(void)
 {
     RAMBlock *block = NULL;
     void *dst_host;
@@ -3632,9 +3632,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
     }
     trace_ram_load_complete(ret, seq_iter);
 
-    if (!ret  && migration_incoming_in_colo_state()) {
-        colo_flush_ram_cache();
-    }
     return ret;
 }
 
diff --git a/migration/ram.h b/migration/ram.h
index 5ceaff7..2eeaacf 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -65,6 +65,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb);
 
 /* ram cache */
 int colo_init_ram_cache(void);
+void colo_flush_ram_cache(void);
 void colo_release_ram_cache(void);
 void colo_incoming_start_dirty_log(void);
 
diff --git a/migration/rdma.c b/migration/rdma.c
index 967fda5..ec45d33 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -4056,7 +4056,9 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp)
     return;
 err:
     error_propagate(errp, local_err);
-    g_free(rdma->host);
+    if (rdma) {
+        g_free(rdma->host);
+    }
     g_free(rdma);
     g_free(rdma_return_path);
 }
@@ -4092,20 +4094,20 @@ void rdma_start_outgoing_migration(void *opaque,
         rdma_return_path = qemu_rdma_data_init(host_port, errp);
 
         if (rdma_return_path == NULL) {
-            goto err;
+            goto return_path_err;
         }
 
         ret = qemu_rdma_source_init(rdma_return_path,
             s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp);
 
         if (ret) {
-            goto err;
+            goto return_path_err;
         }
 
         ret = qemu_rdma_connect(rdma_return_path, errp);
 
         if (ret) {
-            goto err;
+            goto return_path_err;
         }
 
         rdma->return_path = rdma_return_path;
@@ -4118,6 +4120,8 @@ void rdma_start_outgoing_migration(void *opaque,
     s->to_dst_file = qemu_fopen_rdma(rdma, "wb");
     migrate_fd_connect(s, NULL);
     return;
+return_path_err:
+    qemu_rdma_cleanup(rdma);
 err:
     g_free(rdma);
     g_free(rdma_return_path);