From 64a914839cf44c7ed309fb827ab40c94dcb7c0d0 Mon Sep 17 00:00:00 2001
Message-ID: <64a914839cf44c7ed309fb827ab40c94dcb7c0d0.1739824249.git.jdenemar@redhat.com>
From: Peter Krempa <pkrempa@redhat.com>
Date: Mon, 10 Feb 2025 19:49:10 +0100
Subject: [PATCH] qemu: migration: Reactivate block nodes after migration if VM
 is left paused

On incoming migration qemu doesn't activate the block graph nodes right
away. This is to properly facilitate locking of the images.

The block nodes are normally re-activated when starting the CPUs after
migration, but in cases (e.g. when a paused VM was migrated) when the VM
is left paused the block nodes are not re-activated by qemu.

This means that blockjobs which would want to write to an existing
backing chain member would fail. Generally read-only jobs would succeed
with older qemu's but this was not intended.

Instead with new qemu you'll always get an error if attempting to access
a inactive node:

 error: internal error: unable to execute QEMU command 'blockdev-mirror': Inactive 'libvirt-1-storage' can't be a backing child of active '#block052'

This is the case for explicit blockjobs (virsh blockcopy) but also for
non shared-storage migration (virsh migrate --copy-storage-all).

Since qemu now provides 'blockdev-set-active' QMP command which can
on-demand re-activate the nodes we can re-activate them in similar cases
as when we'd be starting vCPUs if the VM weren't left paused.

The only exception is on the source in case of a failed post-copy
migration as the VM already ran on destination so it won't ever run on
the source even when recovered.

Resolves: https://issues.redhat.com/browse/RHEL-78398
Signed-off-by: Peter Krempa <pkrempa@redhat.com>
Reviewed-by: Jiri Denemark <jdenemar@redhat.com>
(cherry picked from commit 2626fa0569781c0f42db247f4b7116c33cd88b43)

https://issues.redhat.com/browse/RHEL-79095
---
 src/qemu/qemu_migration.c | 55 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 52 insertions(+), 3 deletions(-)

diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 4112e95a1e..62da892254 100644
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -220,6 +220,43 @@ qemuMigrationSrcStoreDomainState(virDomainObj *vm)
 }
 
 
+/**
+ * qemuMigrationBlockNodesReactivate:
+ *
+ * In case when we're keeping the VM paused qemu will not re-activate the block
+ * device backend tree so blockjobs would fail. In case when qemu supports the
+ * 'blockdev-set-active' command this function will re-activate the block nodes.
+ */
+static void
+qemuMigrationBlockNodesReactivate(virDomainObj *vm,
+                                  virDomainAsyncJob asyncJob)
+{
+    virErrorPtr orig_err;
+    qemuDomainObjPrivate *priv = vm->privateData;
+    int rc;
+
+    if (!virQEMUCapsGet(priv->qemuCaps, QEMU_CAPS_BLOCKDEV_SET_ACTIVE))
+        return;
+
+    VIR_DEBUG("re-activating block nodes");
+
+    virErrorPreserveLast(&orig_err);
+
+    if (qemuDomainObjEnterMonitorAsync(vm, asyncJob) < 0)
+        goto cleanup;
+
+    rc = qemuMonitorBlockdevSetActive(priv->mon, NULL, true);
+
+    qemuDomainObjExitMonitor(vm);
+
+    if (rc < 0)
+        VIR_WARN("failed to re-activate block nodes after migration of VM '%s'", vm->def->name);
+
+ cleanup:
+    virErrorRestore(&orig_err);
+}
+
+
 static void
 qemuMigrationSrcRestoreDomainState(virQEMUDriver *driver, virDomainObj *vm)
 {
@@ -236,14 +273,17 @@ qemuMigrationSrcRestoreDomainState(virQEMUDriver *driver, virDomainObj *vm)
               virDomainStateTypeToString(state),
               virDomainStateReasonToString(state, reason));
 
-    if (preMigrationState != VIR_DOMAIN_RUNNING ||
-        state != VIR_DOMAIN_PAUSED ||
+    if (state == VIR_DOMAIN_PAUSED &&
         reason == VIR_DOMAIN_PAUSED_POSTCOPY_FAILED)
         return;
 
+    if (preMigrationState != VIR_DOMAIN_RUNNING ||
+        state != VIR_DOMAIN_PAUSED)
+        goto reactivate;
+
     if (reason == VIR_DOMAIN_PAUSED_IOERROR) {
         VIR_DEBUG("Domain is paused due to I/O error, skipping resume");
-        return;
+        goto reactivate;
     }
 
     VIR_DEBUG("Restoring pre-migration state due to migration error");
@@ -266,7 +306,14 @@ qemuMigrationSrcRestoreDomainState(virQEMUDriver *driver, virDomainObj *vm)
                                                       VIR_DOMAIN_EVENT_SUSPENDED_API_ERROR);
             virObjectEventStateQueue(driver->domainEventState, event);
         }
+
+        goto reactivate;
     }
+
+    return;
+
+ reactivate:
+    qemuMigrationBlockNodesReactivate(vm, VIR_ASYNC_JOB_MIGRATION_OUT);
 }
 
 
@@ -6781,6 +6828,8 @@ qemuMigrationDstFinishFresh(virQEMUDriver *driver,
 
         if (*inPostCopy)
             *doKill = false;
+    } else {
+        qemuMigrationBlockNodesReactivate(vm, VIR_ASYNC_JOB_MIGRATION_IN);
     }
 
     if (mig->jobData) {
-- 
2.48.1