[1/2] migration: move bdrv_invalidate_cache_all of of coroutine context

Commit Message

Denis V. Lunev Feb. 9, 2016, 10:16 a.m. UTC

There is a possibility to hit assert qcow2_get_specific_info that
s->qcow_version is undefined. This happens when VM in starting from
suspended state, i.e. it processes incoming migration, and in the same
time 'info block' is called.

The problem is that in the qcow2_invalidate_cache closes and the image
and memsets BDRVQcowState in the middle.

The patch moves out processing of bdrv_invalidate_cache_all out of
coroutine context for standard migration to avoid that.

Signed-off-by: Denis V. Lunev <[e-mail]>
CC: Paolo Bonzini <[e-mail]>
CC: Juan Quintela <[e-mail]>
CC: Amit Shah <[e-mail]>
---
 migration/migration.c | 89 ++++++++++++++++++++++++++++-----------------------
 1 file changed, 49 insertions(+), 40 deletions(-)

Comments

Eric Blake Feb. 9, 2016, 3:26 p.m. UTC | #1

On 02/09/2016 03:16 AM, Denis V. Lunev wrote:

When sending a 2-patch series, please include a 0/2 cover letter.  The
only time a cover letter is not necessary is for a single patch.

> There is a possibility to hit assert qcow2_get_specific_info that
> s->qcow_version is undefined. This happens when VM in starting from
> suspended state, i.e. it processes incoming migration, and in the same
> time 'info block' is called.
> 
> The problem is that in the qcow2_invalidate_cache closes and the image
> and memsets BDRVQcowState in the middle.

Grammar; I suggest:

The problem is that qcow2_invalidate_cache() closes the image and
memset()s BDRVQcowState in the middle.

> 
> The patch moves out processing of bdrv_invalidate_cache_all out of

s/moves out/moves/

> coroutine context for standard migration to avoid that.
> 
> Signed-off-by: Denis V. Lunev <[e-mail]>
> CC: Paolo Bonzini <[e-mail]>
> CC: Juan Quintela <[e-mail]>
> CC: Amit Shah <[e-mail]>
> ---
>  migration/migration.c | 89 ++++++++++++++++++++++++++++-----------------------
>  1 file changed, 49 insertions(+), 40 deletions(-)
> 

I'll leave the migration experts to give a positive review, but I didn't
see anything obviously wrong in the refactor.

Patch

diff --git a/migration/migration.c b/migration/migration.c
index 82604d2..c2269a6 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -323,13 +323,59 @@  void qemu_start_incoming_migration(const char *uri, Error **errp)
     }
 }
 
+static void process_incoming_migration_bh(void *opaque)
+{
+    Error *local_err = NULL;
+    MigrationIncomingState *mis = opaque;
+
+    /* Make sure all file formats flush their mutable metadata */
+    bdrv_invalidate_cache_all(&local_err);
+    if (local_err) {
+        migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+        error_report_err(local_err);
+        migrate_decompress_threads_join();
+        exit(EXIT_FAILURE);
+    }
+
+    /*
+     * This must happen after all error conditions are dealt with and
+     * we're sure the VM is going to be running on this host.
+     */
+    qemu_announce_self();
+
+    /* If global state section was not received or we are in running
+       state, we need to obey autostart. Any other state is set with
+       runstate_set. */
+
+    if (!global_state_received() ||
+        global_state_get_runstate() == RUN_STATE_RUNNING) {
+        if (autostart) {
+            vm_start();
+        } else {
+            runstate_set(RUN_STATE_PAUSED);
+        }
+    } else {
+        runstate_set(global_state_get_runstate());
+    }
+    migrate_decompress_threads_join();
+    /*
+     * This must happen after any state changes since as soon as an external
+     * observer sees this event they might start to prod at the VM assuming
+     * it's ready to use.
+     */
+    migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
+                      MIGRATION_STATUS_COMPLETED);
+    migration_incoming_state_destroy();
+}
+
 static void process_incoming_migration_co(void *opaque)
 {
     QEMUFile *f = opaque;
-    Error *local_err = NULL;
     MigrationIncomingState *mis;
     PostcopyState ps;
     int ret;
+    QEMUBH *bh;
 
     mis = migration_incoming_state_new(f);
     postcopy_state_set(POSTCOPY_INCOMING_NONE);
@@ -369,45 +415,8 @@  static void process_incoming_migration_co(void *opaque)
         exit(EXIT_FAILURE);
     }
 
-    /* Make sure all file formats flush their mutable metadata */
-    bdrv_invalidate_cache_all(&local_err);
-    if (local_err) {
-        migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
-                          MIGRATION_STATUS_FAILED);
-        error_report_err(local_err);
-        migrate_decompress_threads_join();
-        exit(EXIT_FAILURE);
-    }
-
-    /*
-     * This must happen after all error conditions are dealt with and
-     * we're sure the VM is going to be running on this host.
-     */
-    qemu_announce_self();
-
-    /* If global state section was not received or we are in running
-       state, we need to obey autostart. Any other state is set with
-       runstate_set. */
-
-    if (!global_state_received() ||
-        global_state_get_runstate() == RUN_STATE_RUNNING) {
-        if (autostart) {
-            vm_start();
-        } else {
-            runstate_set(RUN_STATE_PAUSED);
-        }
-    } else {
-        runstate_set(global_state_get_runstate());
-    }
-    migrate_decompress_threads_join();
-    /*
-     * This must happen after any state changes since as soon as an external
-     * observer sees this event they might start to prod at the VM assuming
-     * it's ready to use.
-     */
-    migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
-                      MIGRATION_STATUS_COMPLETED);
-    migration_incoming_state_destroy();
+    bh = qemu_bh_new(process_incoming_migration_bh, mis);
+    qemu_bh_schedule(bh);
 }
 
 void process_incoming_migration(QEMUFile *f)