[Qemu-devel] [PATCH v2] migration: re-active images while migration been canceled after inactive them

[zhanghailiang <zhang.zhanghailiang@huawei.com>]

commit fe904ea8242cbae2d7e69c052c754b8f5f1ba1d6 fixed a case
which migration aborted QEMU because it didn't regain the control
of images while some errors happened.

Actually, there are another two cases can trigger the same error reports:
" bdrv_co_do_pwritev: Assertion `!(bs->open_flags & 0x0800)' failed",

Case 1, codes path:
migration_thread()
    migration_completion()
        bdrv_inactivate_all() ----------------> inactivate images
        qemu_savevm_state_complete_precopy()
            socket_writev_buffer() --------> error because destination fails
                qemu_fflush() ----------------> set error on migration stream
-> qmp_migrate_cancel() ----------------> user cancelled migration concurrently
    -> migrate_set_state() ------------------> set migrate CANCELLIN
    migration_completion() -----------------> go on to fail_invalidate
	if (s->state == MIGRATION_STATUS_ACTIVE) -> Jump this branch

Case 2, codes path:
migration_thread()
    migration_completion()
        bdrv_inactivate_all() ----------------> inactivate images
    migreation_completion() finished
-> qmp_migrate_cancel() ---------------> user cancelled migration concurrently
    qemu_mutex_lock_iothread();
    qemu_bh_schedule (s->cleanup_bh);

As we can see from above, qmp_migrate_cancel can slip in whenever
migration_thread does not hold the global lock. If this happens after
bdrv_inactive_all() been called, the above error reports will appear.

To prevent this, we can call bdrv_invalidate_cache_all() in qmp_migrate_cancel()
directly if we find images become inactive.

Besides, bdrv_invalidate_cache_all() in migration_completion() doesn't have the
protection of big lock, fix it by add the missing qemu_mutex_lock_iothread();

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
---
v2:
 - Fix a bug introduced by commit fe904 which didn't get big lock
   before call bdrv_invalidate_cache_all. (Suggested by Dave)
---
 include/migration/migration.h |  3 +++
 migration/migration.c         | 15 +++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index c309d23..2d5b724 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -177,6 +177,9 @@ struct MigrationState
     /* Flag set once the migration thread is running (and needs joining) */
     bool migration_thread_running;
 
+    /* Flag set once the migration thread called bdrv_inactivate_all */
+    bool block_inactive;
+
     /* Queue of outstanding page requests from the destination */
     QemuMutex src_page_req_mutex;
     QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests;
diff --git a/migration/migration.c b/migration/migration.c
index f498ab8..5b50afe 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1006,6 +1006,16 @@ static void migrate_fd_cancel(MigrationState *s)
     if (s->state == MIGRATION_STATUS_CANCELLING && f) {
         qemu_file_shutdown(f);
     }
+    if (s->state == MIGRATION_STATUS_CANCELLING && s->block_inactive) {
+        Error *local_err = NULL;
+
+        bdrv_invalidate_cache_all(&local_err);
+        if (local_err) {
+            error_report_err(local_err);
+        } else {
+            s->block_inactive = false;
+        }
+    }
 }
 
 void add_migration_state_change_notifier(Notifier *notify)
@@ -1705,6 +1715,7 @@ static void migration_completion(MigrationState *s, int current_active_state,
             if (ret >= 0) {
                 qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
                 qemu_savevm_state_complete_precopy(s->to_dst_file, false);
+                s->block_inactive = true;
             }
         }
         qemu_mutex_unlock_iothread();
@@ -1755,10 +1766,14 @@ fail_invalidate:
     if (s->state == MIGRATION_STATUS_ACTIVE) {
         Error *local_err = NULL;
 
+        qemu_mutex_lock_iothread();
         bdrv_invalidate_cache_all(&local_err);
         if (local_err) {
             error_report_err(local_err);
+        } else {
+            s->block_inactive = false;
         }
+        qemu_mutex_unlock_iothread();
     }
 
 fail:
-- 
1.8.3.1