drm/xe: Fix taking invalid lock on wedge

If device wedges on e.g. GuC upload, the submission is not yet enabled
and the state is not even initialized. Protect the wedge call so it does
nothing in this case. It fixes the following splat:

	[] xe 0000:bf:00.0: [drm] device wedged, needs recovery
	[] ------------[ cut here ]------------
	[] DEBUG_LOCKS_WARN_ON(lock->magic != lock)
	[] WARNING: CPU: 48 PID: 312 at kernel/locking/mutex.c:564 __mutex_lock+0x8a1/0xe60
	...
	[] RIP: 0010:__mutex_lock+0x8a1/0xe60
	[]  mutex_lock_nested+0x1b/0x30
	[]  xe_guc_submit_wedge+0x80/0x2b0 [xe]

Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://lore.kernel.org/r/20250402-warn-after-wedge-v1-1-93e971511fa5@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
This commit is contained in:
Lucas De Marchi 2025-04-02 22:38:05 -07:00
parent f350747a99
commit 1e1981b16b
2 changed files with 14 additions and 0 deletions

View File

@ -300,6 +300,8 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
primelockdep(guc);
guc->submission_state.initialized = true;
return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
}
@ -834,6 +836,13 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
/*
* If device is being wedged even before submission_state is
* initialized, there's nothing to do here.
*/
if (!guc->submission_state.initialized)
return;
err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {

View File

@ -89,6 +89,11 @@ struct xe_guc {
struct mutex lock;
/** @submission_state.enabled: submission is enabled */
bool enabled;
/**
* @submission_state.initialized: mark when submission state is
* even initialized - before that not even the lock is valid
*/
bool initialized;
/** @submission_state.fini_wq: submit fini wait queue */
wait_queue_head_t fini_wq;
} submission_state;