drm/xe: Add helper to accumulate exec queue runtime

Add a helper to accumulate per-client runtime of all its
exec queues. This is called every time a sched job is finished.

v2:
  - Use guc_exec_queue_free_job() and execlist_job_free() to accumulate
    runtime when job is finished since xe_sched_job_completed() is not a
    notification that job finished.
  - Stop trying to update runtime from xe_exec_queue_fini() - that is
    redundant and may happen after xef is closed, leading to a
    use-after-free
  - Do not special case the first timestamp read: the default LRC sets
    CTX_TIMESTAMP to zero, so even the first sample should be a valid
    one.
  - Handle the parallel submission case by multiplying the runtime by
    width.
v3: Update comments

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240517204310.88854-6-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

drivers/gpu/drm/xe/xe_device_types.h

@@ -559,6 +559,9 @@ struct xe_file {
 		struct mutex lock;
 	} exec_queue;
 
+	/** @runtime: hw engine class runtime in ticks for this drm client */
+	u64 runtime[XE_ENGINE_CLASS_MAX];
+
 	/** @client: drm client */
 	struct xe_drm_client *client;
 };

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;

drivers/gpu/drm/xe/xe_exec_queue.h

@@ -75,5 +75,6 @@ struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *e,
 					       struct xe_vm *vm);
 void xe_exec_queue_last_fence_set(struct xe_exec_queue *e, struct xe_vm *vm,
 				  struct dma_fence *fence);
+void xe_exec_queue_update_runtime(struct xe_exec_queue *q);
 
 #endif

drivers/gpu/drm/xe/xe_execlist.c

@@ -306,6 +306,7 @@ static void execlist_job_free(struct drm_sched_job *drm_job)
 {
 	struct xe_sched_job *job = to_xe_sched_job(drm_job);
 
+	xe_exec_queue_update_runtime(job->q);
 	xe_sched_job_put(job);
 }
 

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -749,6 +749,8 @@ static void guc_exec_queue_free_job(struct drm_sched_job *drm_job)
 {
 	struct xe_sched_job *job = to_xe_sched_job(drm_job);
 
+	xe_exec_queue_update_runtime(job->q);
+
 	trace_xe_sched_job_free(job);
 	xe_sched_job_put(job);
 }