diff mbox series

[v5,2/3] migration: split migration_incoming_co

Message ID 20230515130640.46035-3-vsementsov@yandex-team.ru
State New
Headers show
Series COLO: improve build options | expand

Commit Message

Vladimir Sementsov-Ogievskiy May 15, 2023, 1:06 p.m. UTC
Originally, migration_incoming_co was introduced by
25d0c16f625feb3b6
   "migration: Switch to COLO process after finishing loadvm"
to be able to enter from COLO code to one specific yield point, added
by 25d0c16f625feb3b6.

Later in 923709896b1b0
 "migration: poll the cm event for destination qemu"
we reused this variable to wake the migration incoming coroutine from
RDMA code.

That was doubtful idea. Entering coroutines is a very fragile thing:
you should be absolutely sure which yield point you are going to enter.

I don't know how much is it safe to enter during qemu_loadvm_state()
which I think what RDMA want to do. But for sure RDMA shouldn't enter
the special COLO-related yield-point. As well, COLO code doesn't want
to enter during qemu_loadvm_state(), it want to enter it's own specific
yield-point.

As well, when in 8e48ac95865ac97d
 "COLO: Add block replication into colo process" we added
bdrv_invalidate_cache_all() call (now it's called activate_all())
it became possible to enter the migration incoming coroutine during
that call which is wrong too.

So, let't make these things separate and disjoint: loadvm_co for RDMA,
non-NULL during qemu_loadvm_state(), and colo_incoming_co for COLO,
non-NULL only around specific yield.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
---
 migration/colo.c      | 4 ++--
 migration/migration.c | 8 ++++++--
 migration/migration.h | 9 ++++++++-
 migration/rdma.c      | 5 ++---
 4 files changed, 18 insertions(+), 8 deletions(-)

Comments

Juan Quintela May 15, 2023, 1:57 p.m. UTC | #1
Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> wrote:
> Originally, migration_incoming_co was introduced by
> 25d0c16f625feb3b6
>    "migration: Switch to COLO process after finishing loadvm"
> to be able to enter from COLO code to one specific yield point, added
> by 25d0c16f625feb3b6.
>
> Later in 923709896b1b0
>  "migration: poll the cm event for destination qemu"
> we reused this variable to wake the migration incoming coroutine from
> RDMA code.
>
> That was doubtful idea. Entering coroutines is a very fragile thing:
> you should be absolutely sure which yield point you are going to enter.
>
> I don't know how much is it safe to enter during qemu_loadvm_state()
> which I think what RDMA want to do. But for sure RDMA shouldn't enter
> the special COLO-related yield-point. As well, COLO code doesn't want
> to enter during qemu_loadvm_state(), it want to enter it's own specific
> yield-point.
>
> As well, when in 8e48ac95865ac97d
>  "COLO: Add block replication into colo process" we added
> bdrv_invalidate_cache_all() call (now it's called activate_all())
> it became possible to enter the migration incoming coroutine during
> that call which is wrong too.
>
> So, let't make these things separate and disjoint: loadvm_co for RDMA,
> non-NULL during qemu_loadvm_state(), and colo_incoming_co for COLO,
> non-NULL only around specific yield.
>
> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>

Reviewed-by: Juan Quintela <quintela@redhat.com>
diff mbox series

Patch

diff --git a/migration/colo.c b/migration/colo.c
index 6c7c313956..a688ac553a 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -145,8 +145,8 @@  static void secondary_vm_do_failover(void)
     qemu_sem_post(&mis->colo_incoming_sem);
 
     /* For Secondary VM, jump to incoming co */
-    if (mis->migration_incoming_co) {
-        qemu_coroutine_enter(mis->migration_incoming_co);
+    if (mis->colo_incoming_co) {
+        qemu_coroutine_enter(mis->colo_incoming_co);
     }
 }
 
diff --git a/migration/migration.c b/migration/migration.c
index 439e8651df..e66b06d3ec 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -520,12 +520,14 @@  process_incoming_migration_co(void *opaque)
         goto fail;
     }
 
-    mis->migration_incoming_co = qemu_coroutine_self();
     mis->largest_page_size = qemu_ram_pagesize_largest();
     postcopy_state_set(POSTCOPY_INCOMING_NONE);
     migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
                       MIGRATION_STATUS_ACTIVE);
+
+    mis->loadvm_co = qemu_coroutine_self();
     ret = qemu_loadvm_state(mis->from_src_file);
+    mis->loadvm_co = NULL;
 
     ps = postcopy_state_get();
     trace_process_incoming_migration_co_end(ret, ps);
@@ -566,7 +568,10 @@  process_incoming_migration_co(void *opaque)
 
         qemu_thread_create(&colo_incoming_thread, "COLO incoming",
              colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE);
+
+        mis->colo_incoming_co = qemu_coroutine_self();
         qemu_coroutine_yield();
+        mis->colo_incoming_co = NULL;
 
         qemu_mutex_unlock_iothread();
         /* Wait checkpoint incoming thread exit before free resource */
@@ -578,7 +583,6 @@  process_incoming_migration_co(void *opaque)
 
     mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
     qemu_bh_schedule(mis->bh);
-    mis->migration_incoming_co = NULL;
     return;
 fail:
     local_err = NULL;
diff --git a/migration/migration.h b/migration/migration.h
index 7721c7658b..48a46123a0 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -162,8 +162,15 @@  struct MigrationIncomingState {
 
     int state;
 
+    /*
+     * The incoming migration coroutine, non-NULL during qemu_loadvm_state().
+     * Used to wake the migration incoming coroutine from rdma code. How much is
+     * it safe - it's a question.
+     */
+    Coroutine *loadvm_co;
+
     /* The coroutine we should enter (back) after failover */
-    Coroutine *migration_incoming_co;
+    Coroutine *colo_incoming_co;
     QemuSemaphore colo_incoming_sem;
 
     /*
diff --git a/migration/rdma.c b/migration/rdma.c
index 2cd8f1cc66..2e4dcff1c9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -3342,9 +3342,8 @@  static void rdma_cm_poll_handler(void *opaque)
             }
         }
         rdma_ack_cm_event(cm_event);
-
-        if (mis->migration_incoming_co) {
-            qemu_coroutine_enter(mis->migration_incoming_co);
+        if (mis->loadvm_co) {
+            qemu_coroutine_enter(mis->loadvm_co);
         }
         return;
     }