qemu: fix race between disk mirror fail and cancel

If a VM migration is aborted, a disk mirror may be failed by QEMU before
libvirt has a chance to cancel it. The disk->mirrorState remains at
_ABORT in this case, and this breaks subsequent mirrorings of that disk.

We should instead check the mirrorState directly and transition to _NONE
if it is already aborted. Do the check *after* aborting the block job in
QEMU to avoid a race.

Signed-off-by: Michael Chapman <mike@very.puzzling.org>
(cherry picked from commit e5d729ba42d86eb3afa9799bca2944700fde41bb)

diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 21432c0b9830ba44d61e95e53239fe2a14706074..39ca37c1a22cc4b388522425bf2fee7814a9142d 100644 (file)
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -1852,6 +1852,10 @@ qemuMigrationDriveMirror(virQEMUDriverPtr driver,
         } else {
             VIR_WARN("Unable to enter monitor. No block job cancelled");
         }
+
+        /* If disk mirror is already aborted, clear the mirror state now */
+        if (disk->mirrorState == VIR_DOMAIN_DISK_MIRROR_STATE_ABORT)
+            disk->mirrorState = VIR_DOMAIN_DISK_MIRROR_STATE_NONE;
     }
     if (err)
         virSetError(err);
@@ -1920,6 +1924,10 @@ qemuMigrationCancelDriveMirror(qemuMigrationCookiePtr mig,
             ret = -1;
             goto cleanup;
         }
+
+        /* If disk mirror is already aborted, clear the mirror state now */
+        if (disk->mirrorState == VIR_DOMAIN_DISK_MIRROR_STATE_ABORT)
+            disk->mirrorState = VIR_DOMAIN_DISK_MIRROR_STATE_NONE;
     }
 
  cleanup: