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>

diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 724e3ff24b8378cbfa27b810f9b36d8a19f645b2..155333ea6f15b13b5dcfc3cd9b0b033f994eb201 100644 (file)
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -1853,6 +1853,10 @@ 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);
@@ -1921,6 +1925,10 @@ 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: