diff options
Diffstat (limited to 'drivers/gpu/drm/xe/xe_exec_queue.c')
| -rw-r--r-- | drivers/gpu/drm/xe/xe_exec_queue.c | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 395de93579fa..fa6dc996eca8 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -769,6 +769,43 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q) q->lrc[0].fence_ctx.next_seqno - 1; } +/** + * xe_exec_queue_update_runtime() - Update runtime for this exec queue from hw + * @q: The exec queue + * + * Update the timestamp saved by HW for this exec queue and save runtime + * calculated by using the delta from last update. On multi-lrc case, only the + * first is considered. + */ +void xe_exec_queue_update_runtime(struct xe_exec_queue *q) +{ + struct xe_file *xef; + struct xe_lrc *lrc; + u32 old_ts, new_ts; + + /* + * Jobs that are run during driver load may use an exec_queue, but are + * not associated with a user xe file, so avoid accumulating busyness + * for kernel specific work. + */ + if (!q->vm || !q->vm->xef) + return; + + xef = q->vm->xef; + + /* + * Only sample the first LRC. For parallel submission, all of them are + * scheduled together and we compensate that below by multiplying by + * width - this may introduce errors if that premise is not true and + * they don't exit 100% aligned. On the other hand, looping through + * the LRCs and reading them in different time could also introduce + * errors. + */ + lrc = &q->lrc[0]; + new_ts = xe_lrc_update_timestamp(lrc, &old_ts); + xef->runtime[q->class] += (new_ts - old_ts) * q->width; +} + void xe_exec_queue_kill(struct xe_exec_queue *q) { struct xe_exec_queue *eq = q, *next; |