[PATCH 1/2] drm/xe: Always capture exec queues on snapshot
Rodrigo Vivi
rodrigo.vivi at intel.com
Mon Apr 8 18:32:41 UTC 2024
On Fri, Apr 05, 2024 at 02:16:31PM -0700, Matthew Brost wrote:
> Always capture exec queues on snapshot regardless if exec queue has
> pending jobs or not. Having jobs or not does indicate whether the exec
> queue capture is useful.
>
> Example bugs that would not be easily detected by skipping capture when
> pending job list is empty:
> - Jobs pending on exec queue have dependencies
> - Leaking exec queue refs
> - GuC protocol issues (i.e. losing G2H)
>
> In addition to above bugs, in general it just useful to see every exec
> queue registered with the GuC and its state.
>
> Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
> drivers/gpu/drm/xe/xe_devcoredump.c | 2 +-
> drivers/gpu/drm/xe/xe_guc_submit.c | 25 +++----------------------
> drivers/gpu/drm/xe/xe_guc_submit.h | 4 ++--
> 3 files changed, 6 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
> index a951043b2943..283ca7518aff 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump.c
> +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
> @@ -188,7 +188,7 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
>
> coredump->snapshot.ct = xe_guc_ct_snapshot_capture(&guc->ct, true);
> - coredump->snapshot.ge = xe_guc_exec_queue_snapshot_capture(job);
> + coredump->snapshot.ge = xe_guc_exec_queue_snapshot_capture(q);
> coredump->snapshot.job = xe_sched_job_snapshot_capture(job);
> coredump->snapshot.vm = xe_vm_snapshot_capture(q->vm);
>
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 9c30bd9ac8c0..cc1890e322cb 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1777,7 +1777,7 @@ guc_exec_queue_wq_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps
>
> /**
> * xe_guc_exec_queue_snapshot_capture - Take a quick snapshot of the GuC Engine.
> - * @job: faulty Xe scheduled job.
> + * @q: faulty exec queue
> *
> * This can be printed out in a later stage like during dev_coredump
> * analysis.
> @@ -1786,9 +1786,8 @@ guc_exec_queue_wq_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps
> * caller, using `xe_guc_exec_queue_snapshot_free`.
> */
> struct xe_guc_submit_exec_queue_snapshot *
> -xe_guc_exec_queue_snapshot_capture(struct xe_sched_job *job)
> +xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q)
> {
> - struct xe_exec_queue *q = job->q;
> struct xe_gpu_scheduler *sched = &q->guc->sched;
> struct xe_guc_submit_exec_queue_snapshot *snapshot;
> int i;
> @@ -1944,28 +1943,10 @@ void xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *s
> static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p)
> {
> struct xe_guc_submit_exec_queue_snapshot *snapshot;
> - struct xe_gpu_scheduler *sched = &q->guc->sched;
> - struct xe_sched_job *job;
> - bool found = false;
>
> - spin_lock(&sched->base.job_list_lock);
> - list_for_each_entry(job, &sched->base.pending_list, drm.list) {
> - if (job->q == q) {
> - xe_sched_job_get(job);
> - found = true;
> - break;
> - }
> - }
> - spin_unlock(&sched->base.job_list_lock);
> -
> - if (!found)
> - return;
> -
> - snapshot = xe_guc_exec_queue_snapshot_capture(job);
> + snapshot = xe_guc_exec_queue_snapshot_capture(q);
> xe_guc_exec_queue_snapshot_print(snapshot, p);
> xe_guc_exec_queue_snapshot_free(snapshot);
> -
> - xe_sched_job_put(job);
> }
>
> /**
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
> index 2f14dfd04722..fad0421ead36 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.h
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.h
> @@ -9,8 +9,8 @@
> #include <linux/types.h>
>
> struct drm_printer;
> +struct xe_exec_queue;
> struct xe_guc;
> -struct xe_sched_job;
>
> int xe_guc_submit_init(struct xe_guc *guc);
>
> @@ -27,7 +27,7 @@ int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
> int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len);
>
> struct xe_guc_submit_exec_queue_snapshot *
> -xe_guc_exec_queue_snapshot_capture(struct xe_sched_job *job);
> +xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q);
> void
> xe_guc_exec_queue_snapshot_capture_delayed(struct xe_guc_submit_exec_queue_snapshot *snapshot);
> void
> --
> 2.34.1
>
More information about the Intel-xe
mailing list