drm/xe: Take PM ref in delayed snapshot capture worker

[ Upstream commit aef0b4a07277f715bfc2a0d76a16da2bc4e89205 ]

The delayed snapshot capture worker can access the GPU or VRAM both of
which require a PM reference. Take a reference in this worker.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: 4f04d07c0a ("drm/xe: Faster devcoredump")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241126174615.2665852-5-matthew.brost@intel.com
(cherry picked from commit 1c6878af115a4586a40d6c14d530fa9f93e0bd83)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Stable-dep-of: 5dce85fecb87 ("drm/xe: Move the coredump registration to the worker thread")
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/gpu/drm/xe/xe_devcoredump.c

@@ -20,6 +20,7 @@
 #include "xe_guc_ct.h"
 #include "xe_guc_submit.h"
 #include "xe_hw_engine.h"
+#include "xe_pm.h"
 #include "xe_sched_job.h"
 #include "xe_vm.h"
 
@@ -147,8 +148,11 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 {
 	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
 	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
+	struct xe_device *xe = coredump_to_xe(coredump);
 	unsigned int fw_ref;
 
+	xe_pm_runtime_get(xe);
+
 	/* keep going if fw fails as we still want to save the memory and SW data */
 	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
 	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
@@ -157,6 +161,8 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
 	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
 
+	xe_pm_runtime_put(xe);
+
 	/* Calculate devcoredump size */
 	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump);