[PATCH qemu-server v2 6/9] partially fix #7836: allow mirror for drive with read-only flag when using blockdev

[Fiona Ebner <f.ebner@proxmox.com>]

The switch to -blockdev in Proxmox VE 9 introduced a regression,
making clone of a VM with a read-only drive fail. The reason is that
the target node is also attached as read-only and thus cannot serve as
the mirror target. To fix the issue, open the mirror target as
writeable initially and in case the VM switched to the new drive,
re-open as read-only later. Note that the drive device is always
read-only for the guest, because the top throttle node is.

Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
---

Changes in v2:
* Use a callback directly rather than passing data around and calling
  a new helper function.
* In v1 the reopen was done directly after 'job-complete', but this
  might be racy. Reopen only after the job actually finished.

 src/PVE/QemuServer/BlockJob.pm | 33 ++++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/src/PVE/QemuServer/BlockJob.pm b/src/PVE/QemuServer/BlockJob.pm
index 2e4e275e..bedcdc9d 100644
--- a/src/PVE/QemuServer/BlockJob.pm
+++ b/src/PVE/QemuServer/BlockJob.pm
@@ -121,7 +121,13 @@ sub monitor {
                 my $complete = defined($jobs->{$job_id}->{complete}) && $vanished;
                 if ($complete || ($vanished && $completion eq 'auto')) {
                     print "$job_id: $op-job finished\n";
-                    delete $jobs->{$job_id};
+                    my $job_info = delete $jobs->{$job_id};
+
+                    if ($completion ne 'cancel' && $job_info->{'reopen-after-switch'}) {
+                        eval { $job_info->{'reopen-after-switch'}->(); };
+                        warn "reopen after switch: $@" if $@;
+                    }
+
                     next;
                 }
 
@@ -521,6 +527,14 @@ sub blockdev_mirror {
         }
     }
 
+    # If the drive is configured as read-only, attach the mirror target as writeable initially and
+    # re-open it as read-only later. For the guest, the drive will be seen as read-only if the
+    # throttle node is, even in case mirror switches to the new target.
+    my $dest_is_read_only = $dest_drive->{ro};
+    if ($dest_is_read_only) {
+        $attach_dest_opts->{'read-only'} = 0;
+    }
+
     # Note that if 'aio' is not explicitly set, i.e. default, it can change if source and target
     # don't both allow or both not allow 'io_uring' as the default.
     my ($target_node_name) =
@@ -533,6 +547,23 @@ sub blockdev_mirror {
         'target-node-name' => $target_node_name,
     };
 
+    if ($dest_is_read_only) {
+        my $reopen_opts = { $attach_dest_opts->%* };
+        delete($reopen_opts->{'read-only'}); # remove the override for re-opening later
+
+        $jobs->{$jobid}->{'reopen-after-switch'} = sub {
+            eval {
+                PVE::QemuServer::Blockdev::reopen($storecfg, $vmid, $dest_drive, $reopen_opts);
+            };
+            if (my $err = $@) {
+                # For the guest, the drive will be seen as read-only if the throttle node already
+                # is, so a failure here is not too bad.
+                my $drive_id = PVE::QemuServer::Drive::get_drive_id($dest_drive);
+                print "$drive_id: failed to re-apply read-only flag below throttle - $err\n";
+            }
+        };
+    }
+
     my $qmp_opts = common_mirror_qmp_options(
         $vmid, $device_id, $target_node_name, $source->{bitmap}, $options->{bwlimit},
     );
-- 
2.47.3