Merge "Special case lenovo UEFI boot setup" into unmaintained/yoga

ironic/drivers/modules/agent_base.py

@@ -1334,11 +1334,28 @@ class AgentDeployMixin(HeartbeatMixin, AgentOobStepsMixin):
 
         try:
             persistent = True
+            # NOTE(TheJulia): We *really* only should be doing this in bios
+            # boot mode. In UEFI this might just get disregarded, or cause
+            # issues/failures.
             if node.driver_info.get('force_persistent_boot_device',
                                     'Default') == 'Never':
                 persistent = False
-            deploy_utils.try_set_boot_device(task, boot_devices.DISK,
+
-                                             persistent=persistent)
+            vendor = task.node.properties.get('vendor', None)
+            if not (vendor and vendor.lower() == 'lenovo'
+                    and target_boot_mode == 'uefi'):
+                # Lenovo hardware is modeled on a "just update"
+                # UEFI nvram model of use, and if multiple actions
+                # get requested, you can end up in cases where NVRAM
+                # changes are deleted as the host "restores" to the
+                # backup. For more information see
+                # https://bugs.launchpad.net/ironic/+bug/2053064
+                # NOTE(TheJulia): We likely just need to do this with
+                # all hosts in uefi mode, but libvirt VMs don't handle
+                # nvram only changes *and* this pattern is known to generally
+                # work for Ironic operators.
+                deploy_utils.try_set_boot_device(task, boot_devices.DISK,
+                                                 persistent=persistent)
         except Exception as e:
             msg = (_("Failed to change the boot device to %(boot_dev)s "
                      "when deploying node %(node)s: %(error)s") %

ironic/drivers/modules/pxe_base.py

@@ -332,6 +332,19 @@ class PXEBaseMixin(object):
         # NOTE(pas-ha) do not re-set boot device on ACTIVE nodes
         # during takeover
         if boot_device and task.node.provision_state != states.ACTIVE:
+            vendor = task.node.properties.get('vendor', None)
+            boot_mode = boot_mode_utils.get_boot_mode(task.node)
+            if (task.node.provision_state == states.DEPLOYING
+                    and vendor and vendor.lower() == 'lenovo'
+                    and boot_mode == 'uefi'
+                    and boot_device == boot_devices.DISK):
+                # Lenovo hardware is modeled on a "just update"
+                # UEFI nvram model of use, and if multiple actions
+                # get requested, you can end up in cases where NVRAM
+                # changes are deleted as the host "restores" to the
+                # backup. For more information see
+                # https://bugs.launchpad.net/ironic/+bug/2053064
+                return
             manager_utils.node_set_boot_device(task, boot_device,
                                                persistent=True)
 

ironic/tests/unit/drivers/modules/test_agent_base.py

@@ -943,6 +943,33 @@ class AgentDeployMixinTest(AgentDeployMixinBaseTest):
                 target_boot_mode='whatever', software_raid=False
             )
 
+    @mock.patch.object(agent_client.AgentClient, 'install_bootloader',
+                       autospec=True)
+    @mock.patch.object(deploy_utils, 'try_set_boot_device', autospec=True)
+    @mock.patch.object(boot_mode_utils, 'get_boot_mode', autospec=True,
+                       return_value='uefi')
+    def test_configure_local_boot_lenovo(self, boot_mode_mock,
+                                         try_set_boot_device_mock,
+                                         install_bootloader_mock):
+        install_bootloader_mock.return_value = {
+            'command_status': 'SUCCESS', 'command_error': None}
+        props = self.node.properties
+        props['vendor'] = 'Lenovo'
+        props['capabilities'] = 'boot_mode:uefi'
+        self.node.properties = props
+        self.node.save()
+        with task_manager.acquire(self.context, self.node['uuid'],
+                                  shared=False) as task:
+            task.node.driver_internal_info['is_whole_disk_image'] = False
+            self.deploy.configure_local_boot(task, root_uuid='some-root-uuid')
+            try_set_boot_device_mock.assert_not_called()
+            boot_mode_mock.assert_called_once_with(task.node)
+            install_bootloader_mock.assert_called_once_with(
+                mock.ANY, task.node, root_uuid='some-root-uuid',
+                efi_system_part_uuid=None, prep_boot_part_uuid=None,
+                target_boot_mode='uefi', software_raid=False
+            )
+
     @mock.patch.object(agent_client.AgentClient, 'install_bootloader',
                        autospec=True)
     @mock.patch.object(deploy_utils, 'try_set_boot_device', autospec=True)

ironic/tests/unit/drivers/modules/test_pxe.py

@@ -728,6 +728,25 @@ class PXEBootTestCase(db_base.DbTestCase):
                                                          persistent=True)
             secure_boot_mock.assert_called_once_with(task)
 
+    @mock.patch.object(boot_mode_utils, 'configure_secure_boot_if_needed',
+                       autospec=True)
+    @mock.patch.object(manager_utils, 'node_set_boot_device', autospec=True)
+    @mock.patch.object(pxe_utils, 'clean_up_pxe_config', autospec=True)
+    def test_prepare_instance_lenovo(self, clean_up_pxe_config_mock,
+                                     set_boot_device_mock, secure_boot_mock):
+        props = self.node.properties
+        props['vendor'] = 'Lenovo'
+        props['capabilities'] = 'boot_mode:uefi'
+        self.node.properties = props
+        self.node.provision_state = states.DEPLOYING
+        self.node.save()
+        with task_manager.acquire(self.context, self.node.uuid) as task:
+            task.driver.boot.prepare_instance(task)
+            clean_up_pxe_config_mock.assert_called_once_with(
+                task, ipxe_enabled=False)
+            set_boot_device_mock.assert_not_called()
+            secure_boot_mock.assert_called_once_with(task)
+
     @mock.patch.object(manager_utils, 'node_set_boot_device', autospec=True)
     @mock.patch.object(pxe_utils, 'clean_up_pxe_config', autospec=True)
     def test_prepare_instance_localboot_active(self, clean_up_pxe_config_mock,

releasenotes/notes/limit-boot-to-disk-calls-lenovo-39763bfc98f602d8.yaml

@@ -0,0 +1,13 @@
+---
+fixes:
+  - |
+    Fixes issues with Lenovo hardware where the system firmware may display
+    a blue "Boot Option Restoration" screen after the agent writes an image
+    to the host in UEFI boot mode, requiring manual intervention before the
+    deployed node boots. This issue is rooted in multiple changes being made
+    to the underlying NVRAM configuration of the node. Lenovo engineers
+    have suggested to *only* change the UEFI NVRAM and not perform
+    any further changes via the BMC to configure the next boot. Ironic now
+    does such on Lenovo hardware. More information and background on this
+    issue can be discovered in
+    `bug 2053064 <https://bugs.launchpad.net/ironic/+bug/2053064>`_.