drm/i915: Track hw reported context runtime

GPU saves accumulated context runtime (in CS timestamp units) in PPHWSP
which will be useful for us in cases when we are not able to track context
busyness ourselves (like with GuC). Keep a copy of this in struct
intel_context from where it can be easily read even if the context is not
pinned.

v2:
 (Chris)
 * Do not store pphwsp address in intel_context.
 * Log CS wrap-around.
 * Simplify calculation by relying on integer wraparound.
v3:
 * Include total/avg in traces and error state for debugging

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200216133620.394962-1-chris@chris-wilson.co.uk

1 files changed, 44 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index c3d7727021db..78e854440949 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1195,6 +1195,42 @@ static void reset_active(struct i915_request *rq,
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
 
+static u32 intel_context_get_runtime(const struct intel_context *ce)
+{
+	/*
+	 * We can use either ppHWSP[16] which is recorded before the context
+	 * switch (and so excludes the cost of context switches) or use the
+	 * value from the context image itself, which is saved/restored earlier
+	 * and so includes the cost of the save.
+	 */
+	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
+}
+
+static void intel_context_update_runtime(struct intel_context *ce)
+{
+	u32 old;
+	s32 dt;
+
+	if (intel_context_is_barrier(ce))
+		return;
+
+	old = ce->runtime.last;
+	ce->runtime.last = intel_context_get_runtime(ce);
+	dt = ce->runtime.last - old;
+
+	if (unlikely(dt <= 0)) {
+		CE_TRACE(ce, "runtime underflow: last=%u, new=%u, delta=%d\n",
+			 old, ce->runtime.last, dt);
+		I915_SELFTEST_ONLY(ce->runtime.num_underflow += dt < 0);
+		I915_SELFTEST_ONLY(ce->runtime.max_underflow =
+				   max_t(u32, ce->runtime.max_underflow, -dt));
+		return;
+	}
+
+	ewma_runtime_add(&ce->runtime.avg, dt);
+	ce->runtime.total += dt;
+}
+
 static inline struct intel_engine_cs *
 __execlists_schedule_in(struct i915_request *rq)
 {
@@ -1278,6 +1314,7 @@ __execlists_schedule_out(struct i915_request *rq,
 	    i915_request_completed(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
+	intel_context_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
 	intel_gt_pm_put_async(engine->gt);
@@ -4607,8 +4644,13 @@ populate_lr_context(struct intel_context *ce,
 		inhibit = false;
 	}
 
-	/* The second page of the context object contains some fields which must
-	 * be set up prior to the first execution. */
+	/* Clear the ppHWSP (inc. per-context counters) */
+	memset(vaddr, 0, PAGE_SIZE);
+
+	/*
+	 * The second page of the context object contains some registers which
+	 * must be set up prior to the first execution.
+	 */
 	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
 				 ce, engine, ring, inhibit);