bdrv_activate_all() should not be called from the coroutine context, move
it to the QEMU thread colo_process_incoming_thread() with the bql_lock
protected.

The backtrace is as follows:
 #4  0x0000561af7948362 in bdrv_graph_rdlock_main_loop () at ../block/graph-lock.c:260
 #5  0x0000561af7907a68 in graph_lockable_auto_lock_mainloop (x=0x7fd29810be7b) at /patch/to/qemu/include/block/graph-lock.h:259
 #6  0x0000561af79167d1 in bdrv_activate_all (errp=0x7fd29810bed0) at ../block.c:6906
 #7  0x0000561af762b4af in colo_incoming_co () at ../migration/colo.c:935
 #8  0x0000561af7607e57 in process_incoming_migration_co (opaque=0x0) at ../migration/migration.c:793
 #9  0x0000561af7adbeeb in coroutine_trampoline (i0=-106876144, i1=22042) at ../util/coroutine-ucontext.c:175
 #10 0x00007fd2a5cf21c0 in  () at /lib64/libc.so.6

CC: Fabiano Rosas <farosas@suse.de>
Closes: https://gitlab.com/qemu-project/qemu/-/issues/2277
Fixes: 2b3912f135 ("block: Mark bdrv_first_blk() and bdrv_is_root_node() GRAPH_RDLOCK")
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
 migration/colo.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/migration/colo.c b/migration/colo.c
index 84632a603e..94942fba32 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -835,6 +835,15 @@ static void *colo_process_incoming_thread(void *opaque)
         return NULL;
     }
 
+    /* Make sure all file formats throw away their mutable metadata */
+    bql_lock();
+    bdrv_activate_all(&local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return NULL;
+    }
+    bql_unlock();
+
     failover_init_state();
 
     mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
@@ -922,7 +931,6 @@ out:
 int coroutine_fn colo_incoming_co(void)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
-    Error *local_err = NULL;
     QemuThread th;
 
     assert(bql_locked());
@@ -931,13 +939,6 @@ int coroutine_fn colo_incoming_co(void)
         return 0;
     }
 
-    /* Make sure all file formats throw away their mutable metadata */
-    bdrv_activate_all(&local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return -EINVAL;
-    }
-
     qemu_thread_create(&th, "COLO incoming", colo_process_incoming_thread,
                        mis, QEMU_THREAD_JOINABLE);
 
-- 
2.31.1

On 17/04/2024 10:44, Li Zhijian wrote:
> bdrv_activate_all() should not be called from the coroutine context, move
> it to the QEMU thread colo_process_incoming_thread() with the bql_lock
> protected.
> 
> The backtrace is as follows:
>   #4  0x0000561af7948362 in bdrv_graph_rdlock_main_loop () at ../block/graph-lock.c:260
>   #5  0x0000561af7907a68 in graph_lockable_auto_lock_mainloop (x=0x7fd29810be7b) at /patch/to/qemu/include/block/graph-lock.h:259
>   #6  0x0000561af79167d1 in bdrv_activate_all (errp=0x7fd29810bed0) at ../block.c:6906
>   #7  0x0000561af762b4af in colo_incoming_co () at ../migration/colo.c:935
>   #8  0x0000561af7607e57 in process_incoming_migration_co (opaque=0x0) at ../migration/migration.c:793
>   #9  0x0000561af7adbeeb in coroutine_trampoline (i0=-106876144, i1=22042) at ../util/coroutine-ucontext.c:175
>   #10 0x00007fd2a5cf21c0 in  () at /lib64/libc.so.6
> 
> CC: Fabiano Rosas<farosas@suse.de>
> Closes:https://gitlab.com/qemu-project/qemu/-/issues/2277
> Fixes: 2b3912f135 ("block: Mark bdrv_first_blk() and bdrv_is_root_node() GRAPH_RDLOCK")
> Signed-off-by: Li Zhijian<lizhijian@fujitsu.com>
> ---
>   migration/colo.c | 17 +++++++++--------
>   1 file changed, 9 insertions(+), 8 deletions(-)
> 
> diff --git a/migration/colo.c b/migration/colo.c
> index 84632a603e..94942fba32 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -835,6 +835,15 @@ static void *colo_process_incoming_thread(void *opaque)
>           return NULL;
>       }
>   
> +    /* Make sure all file formats throw away their mutable metadata */
> +    bql_lock();
> +    bdrv_activate_all(&local_err);
> +    if (local_err) {

Here bql_unlock() is missing, posted V2 to fix it.

Thanks
Zhijian



> +        error_report_err(local_err);
> +        return NULL;
> +    }
> +    bql_unlock();
> +