[Intel-gfx] [PATCH 01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Intel-gfx] [PATCH 01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Chris Wilson]

Rather than having special case code for opportunistically calling
process_csb() and performing a direct submit while holding the engine
spinlock for submitting the request, simply call the tasklet directly.
This allows us to retain the direct submission path, including the CS
draining to allow fast/immediate submissions, without requiring any
duplicated code paths, and most importantly greatly simplifying the
control flow by removing reentrancy. This will enable us to close a few
races in the virtual engines in the next few patches.

The trickiest part here is to ensure that paired operations (such as
schedule_in/schedule_out) remain under consistent locking domains,
e.g. when pulled outside of the engine->active.lock

v2: Use bh kicking, see commit 3c53776e29f8 ("Mark HI and TASKLET
softirq synchronous").
v3: Update engine-reset to be tasklet aware

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  35 +++--
 drivers/gpu/drm/i915/gt/intel_engine_pm.c     |   2 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |   3 +-
 .../drm/i915/gt/intel_execlists_submission.c  | 140 +++++++-----------
 drivers/gpu/drm/i915/gt/intel_reset.c         |  60 +++++---
 drivers/gpu/drm/i915/gt/intel_reset.h         |   2 +
 drivers/gpu/drm/i915/gt/selftest_context.c    |   2 +-
 drivers/gpu/drm/i915/gt/selftest_execlists.c  |  10 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  |   7 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |  17 ++-
 drivers/gpu/drm/i915/gt/selftest_reset.c      |   8 +-
 drivers/gpu/drm/i915/i915_request.c           |  12 +-
 drivers/gpu/drm/i915/i915_request.h           |   1 +
 drivers/gpu/drm/i915/i915_scheduler.c         |   4 -
 drivers/gpu/drm/i915/selftests/i915_request.c |   6 +-
 drivers/gpu/drm/i915/selftests/igt_spinner.c  |   3 +
 16 files changed, 162 insertions(+), 150 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 8acb922b69f9..1847d3c2ea99 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1019,32 +1019,39 @@ static unsigned long stop_timeout(const struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.stop_timeout_ms);
 }
 
-int intel_engine_stop_cs(struct intel_engine_cs *engine)
+static int __intel_engine_stop_cs(struct intel_engine_cs *engine,
+				  int fast_timeout_us,
+				  int slow_timeout_ms)
 {
 	struct intel_uncore *uncore = engine->uncore;
-	const u32 base = engine->mmio_base;
-	const i915_reg_t mode = RING_MI_MODE(base);
+	const i915_reg_t mode = RING_MI_MODE(engine->mmio_base);
 	int err;
 
+	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
+	err = __intel_wait_for_register_fw(engine->uncore, mode,
+					   MODE_IDLE, MODE_IDLE,
+					   fast_timeout_us,
+					   slow_timeout_ms,
+					   NULL);
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	intel_uncore_posting_read_fw(uncore, mode);
+	return err;
+}
+
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+	int err = 0;
+
 	if (INTEL_GEN(engine->i915) < 3)
 		return -ENODEV;
 
 	ENGINE_TRACE(engine, "\n");
-
-	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
-
-	err = 0;
-	if (__intel_wait_for_register_fw(uncore,
-					 mode, MODE_IDLE, MODE_IDLE,
-					 1000, stop_timeout(engine),
-					 NULL)) {
+	if (__intel_engine_stop_cs(engine, 1000, stop_timeout(engine))) {
 		ENGINE_TRACE(engine, "timed out on STOP_RING -> IDLE\n");
 		err = -ETIMEDOUT;
 	}
 
-	/* A final mmio read to let GPU writes be hopefully flushed to memory */
-	intel_uncore_posting_read_fw(uncore, mode);
-
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 8b353bc8c100..2843db731b7d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -144,7 +144,7 @@ __queue_and_release_pm(struct i915_request *rq,
 		list_add_tail(&tl->link, &timelines->active_list);
 
 	/* Hand the request over to HW and so engine_retire() */
-	__i915_request_queue(rq, NULL);
+	__i915_request_queue_bh(rq);
 
 	/* Let new submissions commence (and maybe retire this timeline) */
 	__intel_wakeref_defer_park(&engine->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 02ee1e736982..c28f4e190fe6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -184,7 +184,8 @@ struct intel_engine_execlists {
 	 * Reserve the upper 16b for tracking internal errors.
 	 */
 	u32 error_interrupt;
-#define ERROR_CSB BIT(31)
+#define ERROR_CSB	BIT(31)
+#define ERROR_PREEMPT	BIT(30)
 
 	/**
 	 * @reset_ccid: Active CCID [EXECLISTS_STATUS_HI] at the time of reset
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 695a2d566d76..ac3e19da1a7d 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -571,8 +571,7 @@ __execlists_schedule_in(struct i915_request *rq)
 	return engine;
 }
 
-static inline struct i915_request *
-execlists_schedule_in(struct i915_request *rq, int idx)
+static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 {
 	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *old;
@@ -589,7 +588,6 @@ execlists_schedule_in(struct i915_request *rq, int idx)
 	} while (!try_cmpxchg(&ce->inflight, &old, ptr_inc(old)));
 
 	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
-	return i915_request_get(rq);
 }
 
 static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
@@ -1257,8 +1255,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
-	struct i915_request * const *active;
-	struct i915_request *last;
+	struct i915_request *last = *execlists->active;
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -1284,6 +1281,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
+	spin_lock(&engine->active.lock);
+
 	for (rb = rb_first_cached(&execlists->virtual); rb; ) {
 		struct virtual_engine *ve =
 			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
@@ -1311,10 +1310,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * the active context to interject the preemption request,
 	 * i.e. we will retrigger preemption following the ack in case
 	 * of trouble.
-	 */
-	active = READ_ONCE(execlists->active);
-
-	/*
+	 *
 	 * In theory we can skip over completed contexts that have not
 	 * yet been processed by events (as those events are in flight):
 	 *
@@ -1326,7 +1322,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * completed and barf.
 	 */
 
-	if ((last = *active)) {
+	if (last) {
 		if (i915_request_completed(last)) {
 			goto check_secondary;
 		} else if (need_preempt(engine, last, rb)) {
@@ -1399,6 +1395,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
+				spin_unlock(&engine->active.lock);
 				start_timeslice(engine, queue_prio(execlists));
 				return;
 			}
@@ -1434,6 +1431,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
+				spin_unlock(&engine->active.lock);
 				start_timeslice(engine, rq_prio(rq));
 				return; /* leave this for another sibling */
 			}
@@ -1551,8 +1549,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (__i915_request_submit(rq)) {
 				if (!merge) {
-					*port = execlists_schedule_in(last, port - execlists->pending);
-					port++;
+					*port++ = i915_request_get(last);
 					last = NULL;
 				}
 
@@ -1571,8 +1568,9 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		rb_erase_cached(&p->node, &execlists->queue);
 		i915_priolist_free(p);
 	}
-
 done:
+	*port++ = i915_request_get(last);
+
 	/*
 	 * Here be a bit of magic! Or sleight-of-hand, whichever you prefer.
 	 *
@@ -1590,36 +1588,45 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * interrupt for secondary ports).
 	 */
 	execlists->queue_priority_hint = queue_prio(execlists);
+	spin_unlock(&engine->active.lock);
 
 	if (submit) {
-		*port = execlists_schedule_in(last, port - execlists->pending);
-		execlists->switch_priority_hint =
-			switch_prio(engine, *execlists->pending);
-
 		/*
 		 * Skip if we ended up with exactly the same set of requests,
 		 * e.g. trying to timeslice a pair of ordered contexts
 		 */
-		if (!memcmp(active, execlists->pending,
-			    (port - execlists->pending + 1) * sizeof(*port))) {
-			do
-				execlists_schedule_out(fetch_and_zero(port));
-			while (port-- != execlists->pending);
-
+		if (!memcmp(execlists->active,
+			    execlists->pending,
+			    (port - execlists->pending) * sizeof(*port)))
 			goto skip_submit;
-		}
-		clear_ports(port + 1, last_port - port);
+
+		*port = NULL;
+		while (port-- != execlists->pending)
+			execlists_schedule_in(*port, port - execlists->pending);
+
+		execlists->switch_priority_hint =
+			switch_prio(engine, *execlists->pending);
 
 		WRITE_ONCE(execlists->yield, -1);
-		set_preempt_timeout(engine, *active);
+		set_preempt_timeout(engine, *execlists->active);
 		execlists_submit_ports(engine);
 	} else {
 		start_timeslice(engine, execlists->queue_priority_hint);
 skip_submit:
 		ring_set_paused(engine, 0);
+		while (port-- != execlists->pending)
+			i915_request_put(*port);
+		*execlists->pending = NULL;
 	}
 }
 
+static void execlists_dequeue_irq(struct intel_engine_cs *engine)
+{
+	local_irq_disable(); /* Suspend interrupts across request submission */
+	execlists_dequeue(engine);
+	local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */
+}
+
 static void
 cancel_port_requests(struct intel_engine_execlists * const execlists)
 {
@@ -1962,16 +1969,6 @@ static void process_csb(struct intel_engine_cs *engine)
 	invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
 }
 
-static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
-{
-	lockdep_assert_held(&engine->active.lock);
-	if (!READ_ONCE(engine->execlists.pending[0])) {
-		rcu_read_lock(); /* protect peeking at execlists->active */
-		execlists_dequeue(engine);
-		rcu_read_unlock();
-	}
-}
-
 static void __execlists_hold(struct i915_request *rq)
 {
 	LIST_HEAD(list);
@@ -2363,7 +2360,7 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
 	if (!timer_expired(t))
 		return false;
 
-	return READ_ONCE(engine->execlists.pending[0]);
+	return engine->execlists.pending[0];
 }
 
 /*
@@ -2373,10 +2370,14 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
 static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
-	bool timeout = preempt_timeout(engine);
 
 	process_csb(engine);
 
+	if (unlikely(preempt_timeout(engine))) {
+		cancel_timer(&engine->execlists.preempt);
+		engine->execlists.error_interrupt |= ERROR_PREEMPT;
+	}
+
 	if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) {
 		const char *msg;
 
@@ -2385,6 +2386,8 @@ static void execlists_submission_tasklet(unsigned long data)
 			msg = "CS error"; /* thrown by a user payload */
 		else if (engine->execlists.error_interrupt & ERROR_CSB)
 			msg = "invalid CSB event";
+		else if (engine->execlists.error_interrupt & ERROR_PREEMPT)
+			msg = "preemption time out";
 		else
 			msg = "internal error";
 
@@ -2392,19 +2395,8 @@ static void execlists_submission_tasklet(unsigned long data)
 		execlists_reset(engine, msg);
 	}
 
-	if (!READ_ONCE(engine->execlists.pending[0]) || timeout) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&engine->active.lock, flags);
-		__execlists_submission_tasklet(engine);
-		spin_unlock_irqrestore(&engine->active.lock, flags);
-
-		/* Recheck after serialising with direct-submission */
-		if (unlikely(timeout && preempt_timeout(engine))) {
-			cancel_timer(&engine->execlists.preempt);
-			execlists_reset(engine, "preemption time out");
-		}
-	}
+	if (!engine->execlists.pending[0])
+		execlists_dequeue_irq(engine);
 }
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
@@ -2435,26 +2427,16 @@ static void queue_request(struct intel_engine_cs *engine,
 	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
-static void __submit_queue_imm(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
-	if (reset_in_progress(execlists))
-		return; /* defer until we restart the engine following reset */
-
-	__execlists_submission_tasklet(engine);
-}
-
-static void submit_queue(struct intel_engine_cs *engine,
+static bool submit_queue(struct intel_engine_cs *engine,
 			 const struct i915_request *rq)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
 
 	if (rq_prio(rq) <= execlists->queue_priority_hint)
-		return;
+		return false;
 
 	execlists->queue_priority_hint = rq_prio(rq);
-	__submit_queue_imm(engine);
+	return true;
 }
 
 static bool ancestor_on_hold(const struct intel_engine_cs *engine,
@@ -2464,25 +2446,11 @@ static bool ancestor_on_hold(const struct intel_engine_cs *engine,
 	return !list_empty(&engine->active.hold) && hold_request(rq);
 }
 
-static void flush_csb(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists *el = &engine->execlists;
-
-	if (READ_ONCE(el->pending[0]) && tasklet_trylock(&el->tasklet)) {
-		if (!reset_in_progress(el))
-			process_csb(engine);
-		tasklet_unlock(&el->tasklet);
-	}
-}
-
 static void execlists_submit_request(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 	unsigned long flags;
 
-	/* Hopefully we clear execlists->pending[] to let us through */
-	flush_csb(engine);
-
 	/* Will be called from irq-context when using foreign fences. */
 	spin_lock_irqsave(&engine->active.lock, flags);
 
@@ -2496,7 +2464,8 @@ static void execlists_submit_request(struct i915_request *request)
 		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 		GEM_BUG_ON(list_empty(&request->sched.link));
 
-		submit_queue(engine, request);
+		if (submit_queue(engine, request))
+			__execlists_kick(&engine->execlists);
 	}
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
@@ -2837,7 +2806,6 @@ static int execlists_resume(struct intel_engine_cs *engine)
 static void execlists_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	unsigned long flags;
 
 	ENGINE_TRACE(engine, "depth<-%d\n",
 		     atomic_read(&execlists->tasklet.count));
@@ -2854,10 +2822,6 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	__tasklet_disable_sync_once(&execlists->tasklet);
 	GEM_BUG_ON(!reset_in_progress(execlists));
 
-	/* And flush any current direct submission. */
-	spin_lock_irqsave(&engine->active.lock, flags);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
-
 	/*
 	 * We stop engines, otherwise we might get failed reset and a
 	 * dead gpu (on elk). Also as modern gpu as kbl can suffer
@@ -3082,12 +3046,12 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	 * to sleep before we restart and reload a context.
 	 */
 	GEM_BUG_ON(!reset_in_progress(execlists));
-	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
-		execlists->tasklet.func(execlists->tasklet.data);
+	GEM_BUG_ON(engine->execlists.pending[0]);
 
+	/* And kick in case we missed a new request submission. */
 	if (__tasklet_enable(&execlists->tasklet))
-		/* And kick in case we missed a new request submission. */
-		tasklet_hi_schedule(&execlists->tasklet);
+		__execlists_kick(execlists);
+
 	ENGINE_TRACE(engine, "depth->%d\n",
 		     atomic_read(&execlists->tasklet.count));
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 000d63588e9e..b85b6f3dcd60 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -40,20 +40,19 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 	intel_uncore_rmw_fw(uncore, reg, clr, 0);
 }
 
-static void engine_skip_context(struct i915_request *rq)
+static void skip_context(struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = rq->engine;
 	struct intel_context *hung_ctx = rq->context;
 
-	if (!i915_request_is_active(rq))
-		return;
+	list_for_each_entry_from_rcu(rq, &hung_ctx->timeline->requests, link) {
+		if (!i915_request_is_active(rq))
+			return;
 
-	lockdep_assert_held(&engine->active.lock);
-	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->context == hung_ctx) {
 			i915_request_set_error_once(rq, -EIO);
 			__i915_request_skip(rq);
 		}
+	}
 }
 
 static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
@@ -160,7 +159,7 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		i915_request_set_error_once(rq, -EIO);
 		__i915_request_skip(rq);
 		if (mark_guilty(rq))
-			engine_skip_context(rq);
+			skip_context(rq);
 	} else {
 		i915_request_set_error_once(rq, -EAGAIN);
 		mark_innocent(rq);
@@ -753,8 +752,10 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 	if (err)
 		return err;
 
+	local_bh_disable();
 	for_each_engine(engine, gt, id)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
+	local_bh_enable();
 
 	intel_ggtt_restore_fences(gt->ggtt);
 
@@ -832,9 +833,11 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	set_bit(I915_WEDGED, &gt->reset.flags);
 
 	/* Mark all executing requests as skipped */
+	local_bh_disable();
 	for_each_engine(engine, gt, id)
 		if (engine->reset.cancel)
 			engine->reset.cancel(engine);
+	local_bh_enable();
 
 	reset_finish(gt, awake);
 
@@ -1109,20 +1112,7 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 	return __intel_gt_reset(engine->gt, engine->mask);
 }
 
-/**
- * intel_engine_reset - reset GPU engine to recover from a hang
- * @engine: engine to reset
- * @msg: reason for GPU reset; or NULL for no drm_notice()
- *
- * Reset a specific GPU engine. Useful if a hang is detected.
- * Returns zero on successful reset or otherwise an error code.
- *
- * Procedure is:
- *  - identifies the request that caused the hang and it is dropped
- *  - reset engine (which will force the engine to idle)
- *  - re-init/configure engine
- */
-int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
+int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 {
 	struct intel_gt *gt = engine->gt;
 	bool uses_guc = intel_engine_in_guc_submission_mode(engine);
@@ -1172,6 +1162,30 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 	return ret;
 }
 
+/**
+ * intel_engine_reset - reset GPU engine to recover from a hang
+ * @engine: engine to reset
+ * @msg: reason for GPU reset; or NULL for no drm_notice()
+ *
+ * Reset a specific GPU engine. Useful if a hang is detected.
+ * Returns zero on successful reset or otherwise an error code.
+ *
+ * Procedure is:
+ *  - identifies the request that caused the hang and it is dropped
+ *  - reset engine (which will force the engine to idle)
+ *  - re-init/configure engine
+ */
+int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
+{
+	int err;
+
+	local_bh_disable();
+	err = __intel_engine_reset_bh(engine, msg);
+	local_bh_enable();
+
+	return err;
+}
+
 static void intel_gt_reset_global(struct intel_gt *gt,
 				  u32 engine_mask,
 				  const char *reason)
@@ -1258,18 +1272,20 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * single reset fails.
 	 */
 	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
+		local_bh_disable();
 		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					     &gt->reset.flags))
 				continue;
 
-			if (intel_engine_reset(engine, msg) == 0)
+			if (__intel_engine_reset_bh(engine, msg) == 0)
 				engine_mask &= ~engine->mask;
 
 			clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
 					      &gt->reset.flags);
 		}
+		local_bh_enable();
 	}
 
 	if (!engine_mask)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index a0eec7c11c0c..7dbf5cc8a333 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -34,6 +34,8 @@ void intel_gt_reset(struct intel_gt *gt,
 		    const char *reason);
 int intel_engine_reset(struct intel_engine_cs *engine,
 		       const char *reason);
+int __intel_engine_reset_bh(struct intel_engine_cs *engine,
+			    const char *reason);
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 1f4020e906a8..db738d400168 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -25,7 +25,7 @@ static int request_sync(struct i915_request *rq)
 	/* Opencode i915_request_add() so we can keep the timeline locked. */
 	__i915_request_commit(rq);
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
-	__i915_request_queue(rq, NULL);
+	__i915_request_queue_bh(rq);
 
 	timeout = i915_request_wait(rq, 0, HZ / 10);
 	if (timeout < 0)
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index fa51cf6d840a..47b12ce4b132 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -599,8 +599,10 @@ static int live_hold_reset(void *arg)
 
 		/* We have our request executing, now remove it and reset */
 
+		local_bh_disable();
 		if (test_and_set_bit(I915_RESET_ENGINE + id,
 				     &gt->reset.flags)) {
+			local_bh_enable();
 			intel_gt_set_wedged(gt);
 			err = -EBUSY;
 			goto out;
@@ -614,12 +616,13 @@ static int live_hold_reset(void *arg)
 		execlists_hold(engine, rq);
 		GEM_BUG_ON(!i915_request_on_hold(rq));
 
-		intel_engine_reset(engine, NULL);
+		__intel_engine_reset_bh(engine, NULL);
 		GEM_BUG_ON(rq->fence.error != -EIO);
 
 		tasklet_enable(&engine->execlists.tasklet);
 		clear_and_wake_up_bit(I915_RESET_ENGINE + id,
 				      &gt->reset.flags);
+		local_bh_enable();
 
 		/* Check that we do not resubmit the held request */
 		if (!i915_request_wait(rq, 0, HZ / 5)) {
@@ -4546,8 +4549,10 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(engine == ve->engine);
 
 	/* Take ownership of the reset and tasklet */
+	local_bh_disable();
 	if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 			     &gt->reset.flags)) {
+		local_bh_enable();
 		intel_gt_set_wedged(gt);
 		err = -EBUSY;
 		goto out_heartbeat;
@@ -4567,12 +4572,13 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	execlists_hold(engine, rq);
 	GEM_BUG_ON(!i915_request_on_hold(rq));
 
-	intel_engine_reset(engine, NULL);
+	__intel_engine_reset_bh(engine, NULL);
 	GEM_BUG_ON(rq->fence.error != -EIO);
 
 	/* Release our grasp on the engine, letting CS flow again */
 	tasklet_enable(&engine->execlists.tasklet);
 	clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags);
+	local_bh_enable();
 
 	/* Check that we do not resubmit the held request */
 	i915_request_get(rq);
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index fb5ebf930ab2..c28d1fcad673 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1576,12 +1576,17 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 		  engine->name, mode, p->name);
 
 	tasklet_disable(t);
+	if (strcmp(p->name, "softirq"))
+		local_bh_disable();
 	p->critical_section_begin();
 
-	err = intel_engine_reset(engine, NULL);
+	err = __intel_engine_reset_bh(engine, NULL);
 
 	p->critical_section_end();
+	if (strcmp(p->name, "softirq"))
+		local_bh_enable();
 	tasklet_enable(t);
+	tasklet_hi_schedule(t);
 
 	if (err)
 		pr_err("i915_reset_engine(%s:%s) failed under %s\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index d55421f6a250..ba6c2be5c8ff 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1607,16 +1607,17 @@ static void garbage_reset(struct intel_engine_cs *engine,
 	const unsigned int bit = I915_RESET_ENGINE + engine->id;
 	unsigned long *lock = &engine->gt->reset.flags;
 
-	if (test_and_set_bit(bit, lock))
-		return;
+	local_bh_disable();
+	if (!test_and_set_bit(bit, lock)) {
+		tasklet_disable(&engine->execlists.tasklet);
 
-	tasklet_disable(&engine->execlists.tasklet);
+		if (!rq->fence.error)
+			__intel_engine_reset_bh(engine, NULL);
 
-	if (!rq->fence.error)
-		intel_engine_reset(engine, NULL);
-
-	tasklet_enable(&engine->execlists.tasklet);
-	clear_and_wake_up_bit(bit, lock);
+		tasklet_enable(&engine->execlists.tasklet);
+		clear_and_wake_up_bit(bit, lock);
+	}
+	local_bh_enable();
 }
 
 static struct i915_request *garbage(struct intel_context *ce,
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index e4645c8bb00a..5ec8d4e9983f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -327,11 +327,16 @@ static int igt_atomic_engine_reset(void *arg)
 		for (p = igt_atomic_phases; p->name; p++) {
 			GEM_TRACE("intel_engine_reset(%s) under %s\n",
 				  engine->name, p->name);
+			if (strcmp(p->name, "softirq"))
+				local_bh_disable();
 
 			p->critical_section_begin();
-			err = intel_engine_reset(engine, NULL);
+			err = __intel_engine_reset_bh(engine, NULL);
 			p->critical_section_end();
 
+			if (strcmp(p->name, "softirq"))
+				local_bh_enable();
+
 			if (err) {
 				pr_err("intel_engine_reset(%s) failed under %s\n",
 				       engine->name, p->name);
@@ -341,6 +346,7 @@ static int igt_atomic_engine_reset(void *arg)
 
 		intel_engine_pm_put(engine);
 		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 45744c3ef7c4..6578faf6eed8 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1584,6 +1584,12 @@ struct i915_request *__i915_request_commit(struct i915_request *rq)
 	return __i915_request_add_to_timeline(rq);
 }
 
+void __i915_request_queue_bh(struct i915_request *rq)
+{
+	i915_sw_fence_commit(&rq->semaphore);
+	i915_sw_fence_commit(&rq->submit);
+}
+
 void __i915_request_queue(struct i915_request *rq,
 			  const struct i915_sched_attr *attr)
 {
@@ -1600,8 +1606,10 @@ void __i915_request_queue(struct i915_request *rq,
 	 */
 	if (attr && rq->engine->schedule)
 		rq->engine->schedule(rq, attr);
-	i915_sw_fence_commit(&rq->semaphore);
-	i915_sw_fence_commit(&rq->submit);
+
+	local_bh_disable();
+	__i915_request_queue_bh(rq);
+	local_bh_enable(); /* kick tasklets */
 }
 
 void i915_request_add(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 7c4453e60323..a8c413203f72 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -315,6 +315,7 @@ void __i915_request_skip(struct i915_request *rq);
 struct i915_request *__i915_request_commit(struct i915_request *request);
 void __i915_request_queue(struct i915_request *rq,
 			  const struct i915_sched_attr *attr);
+void __i915_request_queue_bh(struct i915_request *rq);
 
 bool i915_request_retire(struct i915_request *rq);
 void i915_request_retire_upto(struct i915_request *rq);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index b9cf9931ebd7..318e359bf5c3 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -458,14 +458,10 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 	if (!dep)
 		return -ENOMEM;
 
-	local_bh_disable();
-
 	if (!__i915_sched_node_add_dependency(node, signal, dep,
 					      flags | I915_DEPENDENCY_ALLOC))
 		i915_dependency_free(dep);
 
-	local_bh_enable(); /* kick submission tasklet */
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index e424a6d1a68c..b8c5920d1ff3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -1932,9 +1932,7 @@ static int measure_inter_request(struct intel_context *ce)
 		intel_ring_advance(rq, cs);
 		i915_request_add(rq);
 	}
-	local_bh_disable();
 	i915_sw_fence_commit(submit);
-	local_bh_enable();
 	intel_engine_flush_submission(ce->engine);
 	heap_fence_put(submit);
 
@@ -2220,11 +2218,9 @@ static int measure_completion(struct intel_context *ce)
 		intel_ring_advance(rq, cs);
 
 		dma_fence_add_callback(&rq->fence, &cb.base, signal_cb);
-
-		local_bh_disable();
 		i915_request_add(rq);
-		local_bh_enable();
 
+		intel_engine_flush_submission(ce->engine);
 		if (wait_for(READ_ONCE(sema[i]) == -1, 50)) {
 			err = -EIO;
 			goto err;
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index 1216d919185e..83f6e5f31fb3 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -220,6 +220,9 @@ void igt_spinner_fini(struct igt_spinner *spin)
 
 bool igt_wait_for_spinner(struct igt_spinner *spin, struct i915_request *rq)
 {
+	if (i915_request_is_ready(rq))
+		intel_engine_flush_submission(rq->engine);
+
 	return !(wait_for_us(i915_seqno_passed(hws_seqno(spin, rq),
 					       rq->fence.seqno),
 			     100) &&
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 02/62] drm/i915/gt: Use virtual_engine during execlists_dequeue

[Chris Wilson]

Rather than going back and forth between the rb_node entry and the
virtual_engine type, store the ve local and reuse it. As the
container_of conversion from rb_node to virtual_engine requires a
variable offset, performing that conversion just once shaves off a bit
of code.

v2: Keep a single virtual engine lookup, for typical use.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 239 ++++++++----------
 1 file changed, 105 insertions(+), 134 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index ac3e19da1a7d..ddfd6b271b3b 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -293,9 +293,15 @@ static int queue_prio(const struct intel_engine_execlists *execlists)
 	return ((p->priority + 1) << I915_USER_PRIORITY_SHIFT) - ffs(p->used);
 }
 
+static int virtual_prio(const struct intel_engine_execlists *el)
+{
+	struct rb_node *rb = rb_first_cached(&el->virtual);
+
+	return rb ? rb_entry(rb, struct ve_node, rb)->prio : INT_MIN;
+}
+
 static inline bool need_preempt(const struct intel_engine_cs *engine,
-				const struct i915_request *rq,
-				struct rb_node *rb)
+				const struct i915_request *rq)
 {
 	int last_prio;
 
@@ -332,25 +338,6 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	    rq_prio(list_next_entry(rq, sched.link)) > last_prio)
 		return true;
 
-	if (rb) {
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		bool preempt = false;
-
-		if (engine == ve->siblings[0]) { /* only preempt one sibling */
-			struct i915_request *next;
-
-			rcu_read_lock();
-			next = READ_ONCE(ve->request);
-			if (next)
-				preempt = rq_prio(next) > last_prio;
-			rcu_read_unlock();
-		}
-
-		if (preempt)
-			return preempt;
-	}
-
 	/*
 	 * If the inflight context did not trigger the preemption, then maybe
 	 * it was the set of queued requests? Pick the highest priority in
@@ -361,7 +348,8 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	 * ELSP[0] or ELSP[1] as, thanks again to PI, if it was the same
 	 * context, it's priority would not exceed ELSP[0] aka last_prio.
 	 */
-	return queue_prio(&engine->execlists) > last_prio;
+	return max(virtual_prio(&engine->execlists),
+		   queue_prio(&engine->execlists)) > last_prio;
 }
 
 __maybe_unused static inline bool
@@ -997,6 +985,35 @@ static bool virtual_matches(const struct virtual_engine *ve,
 	return true;
 }
 
+static struct virtual_engine *
+first_virtual_engine(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *el = &engine->execlists;
+	struct rb_node *rb = rb_first_cached(&el->virtual);
+
+	while (rb) {
+		struct virtual_engine *ve =
+			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+		struct i915_request *rq = READ_ONCE(ve->request);
+
+		/* lazily cleanup after another engine handled rq */
+		if (!rq) {
+			rb_erase_cached(rb, &el->virtual);
+			RB_CLEAR_NODE(rb);
+			rb = rb_first_cached(&el->virtual);
+			continue;
+		}
+
+		if (!virtual_matches(ve, rq, engine)) {
+			rb = rb_next(rb);
+			continue;
+		}
+		return ve;
+	}
+
+	return NULL;
+}
+
 static void virtual_xfer_context(struct virtual_engine *ve,
 				 struct intel_engine_cs *engine)
 {
@@ -1084,32 +1101,15 @@ static void defer_active(struct intel_engine_cs *engine)
 
 static bool
 need_timeslice(const struct intel_engine_cs *engine,
-	       const struct i915_request *rq,
-	       const struct rb_node *rb)
+	       const struct i915_request *rq)
 {
 	int hint;
 
 	if (!intel_engine_has_timeslices(engine))
 		return false;
 
-	hint = engine->execlists.queue_priority_hint;
-
-	if (rb) {
-		const struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		const struct intel_engine_cs *inflight =
-			intel_context_inflight(&ve->context);
-
-		if (!inflight || inflight == engine) {
-			struct i915_request *next;
-
-			rcu_read_lock();
-			next = READ_ONCE(ve->request);
-			if (next)
-				hint = max(hint, rq_prio(next));
-			rcu_read_unlock();
-		}
-	}
+	hint = max(engine->execlists.queue_priority_hint,
+		   virtual_prio(&engine->execlists));
 
 	if (!list_is_last(&rq->sched.link, &engine->active.requests))
 		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
@@ -1256,6 +1256,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
 	struct i915_request *last = *execlists->active;
+	struct virtual_engine *ve;
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -1283,26 +1284,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 	spin_lock(&engine->active.lock);
 
-	for (rb = rb_first_cached(&execlists->virtual); rb; ) {
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		struct i915_request *rq = READ_ONCE(ve->request);
-
-		if (!rq) { /* lazily cleanup after another engine handled rq */
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
-			rb = rb_first_cached(&execlists->virtual);
-			continue;
-		}
-
-		if (!virtual_matches(ve, rq, engine)) {
-			rb = rb_next(rb);
-			continue;
-		}
-
-		break;
-	}
-
 	/*
 	 * If the queue is higher priority than the last
 	 * request in the currently active context, submit afresh.
@@ -1325,7 +1306,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	if (last) {
 		if (i915_request_completed(last)) {
 			goto check_secondary;
-		} else if (need_preempt(engine, last, rb)) {
+		} else if (need_preempt(engine, last)) {
 			ENGINE_TRACE(engine,
 				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
 				     last->fence.context,
@@ -1351,7 +1332,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			__unwind_incomplete_requests(engine);
 
 			last = NULL;
-		} else if (need_timeslice(engine, last, rb) &&
+		} else if (need_timeslice(engine, last) &&
 			   timeslice_expired(execlists, last)) {
 			ENGINE_TRACE(engine,
 				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
@@ -1402,96 +1383,86 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 	}
 
-	while (rb) { /* XXX virtual is always taking precedence */
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+	/* XXX virtual is always taking precedence */
+	while ((ve = first_virtual_engine(engine))) {
 		struct i915_request *rq;
 
 		spin_lock(&ve->base.active.lock);
 
 		rq = ve->request;
-		if (unlikely(!rq)) { /* lost the race to a sibling */
-			spin_unlock(&ve->base.active.lock);
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
-			rb = rb_first_cached(&execlists->virtual);
-			continue;
-		}
+		if (unlikely(!rq)) /* lost the race to a sibling */
+			goto unlock;
 
-		GEM_BUG_ON(rq != ve->request);
 		GEM_BUG_ON(rq->engine != &ve->base);
 		GEM_BUG_ON(rq->context != &ve->context);
 
-		if (rq_prio(rq) >= queue_prio(execlists)) {
-			if (!virtual_matches(ve, rq, engine)) {
-				spin_unlock(&ve->base.active.lock);
-				rb = rb_next(rb);
-				continue;
-			}
+		if (unlikely(rq_prio(rq) < queue_prio(execlists))) {
+			spin_unlock(&ve->base.active.lock);
+			break;
+		}
 
-			if (last && !can_merge_rq(last, rq)) {
-				spin_unlock(&ve->base.active.lock);
-				spin_unlock(&engine->active.lock);
-				start_timeslice(engine, rq_prio(rq));
-				return; /* leave this for another sibling */
-			}
+		GEM_BUG_ON(!virtual_matches(ve, rq, engine));
 
-			ENGINE_TRACE(engine,
-				     "virtual rq=%llx:%lld%s, new engine? %s\n",
-				     rq->fence.context,
-				     rq->fence.seqno,
-				     i915_request_completed(rq) ? "!" :
-				     i915_request_started(rq) ? "*" :
-				     "",
-				     yesno(engine != ve->siblings[0]));
-
-			WRITE_ONCE(ve->request, NULL);
-			WRITE_ONCE(ve->base.execlists.queue_priority_hint,
-				   INT_MIN);
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
+		if (last && !can_merge_rq(last, rq)) {
+			spin_unlock(&ve->base.active.lock);
+			spin_unlock(&engine->active.lock);
+			start_timeslice(engine, rq_prio(rq));
+			return; /* leave this for another sibling */
+		}
 
-			GEM_BUG_ON(!(rq->execution_mask & engine->mask));
-			WRITE_ONCE(rq->engine, engine);
+		ENGINE_TRACE(engine,
+			     "virtual rq=%llx:%lld%s, new engine? %s\n",
+			     rq->fence.context,
+			     rq->fence.seqno,
+			     i915_request_completed(rq) ? "!" :
+			     i915_request_started(rq) ? "*" :
+			     "",
+			     yesno(engine != ve->siblings[0]));
 
-			if (__i915_request_submit(rq)) {
-				/*
-				 * Only after we confirm that we will submit
-				 * this request (i.e. it has not already
-				 * completed), do we want to update the context.
-				 *
-				 * This serves two purposes. It avoids
-				 * unnecessary work if we are resubmitting an
-				 * already completed request after timeslicing.
-				 * But more importantly, it prevents us altering
-				 * ve->siblings[] on an idle context, where
-				 * we may be using ve->siblings[] in
-				 * virtual_context_enter / virtual_context_exit.
-				 */
-				virtual_xfer_context(ve, engine);
-				GEM_BUG_ON(ve->siblings[0] != engine);
+		WRITE_ONCE(ve->request, NULL);
+		WRITE_ONCE(ve->base.execlists.queue_priority_hint, INT_MIN);
 
-				submit = true;
-				last = rq;
-			}
-			i915_request_put(rq);
+		rb = &ve->nodes[engine->id].rb;
+		rb_erase_cached(rb, &execlists->virtual);
+		RB_CLEAR_NODE(rb);
+
+		GEM_BUG_ON(!(rq->execution_mask & engine->mask));
+		WRITE_ONCE(rq->engine, engine);
 
+		if (__i915_request_submit(rq)) {
 			/*
-			 * Hmm, we have a bunch of virtual engine requests,
-			 * but the first one was already completed (thanks
-			 * preempt-to-busy!). Keep looking at the veng queue
-			 * until we have no more relevant requests (i.e.
-			 * the normal submit queue has higher priority).
+			 * Only after we confirm that we will submit
+			 * this request (i.e. it has not already
+			 * completed), do we want to update the context.
+			 *
+			 * This serves two purposes. It avoids
+			 * unnecessary work if we are resubmitting an
+			 * already completed request after timeslicing.
+			 * But more importantly, it prevents us altering
+			 * ve->siblings[] on an idle context, where
+			 * we may be using ve->siblings[] in
+			 * virtual_context_enter / virtual_context_exit.
 			 */
-			if (!submit) {
-				spin_unlock(&ve->base.active.lock);
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
+			virtual_xfer_context(ve, engine);
+			GEM_BUG_ON(ve->siblings[0] != engine);
+
+			submit = true;
+			last = rq;
 		}
 
+		i915_request_put(rq);
+unlock:
 		spin_unlock(&ve->base.active.lock);
-		break;
+
+		/*
+		 * Hmm, we have a bunch of virtual engine requests,
+		 * but the first one was already completed (thanks
+		 * preempt-to-busy!). Keep looking at the veng queue
+		 * until we have no more relevant requests (i.e.
+		 * the normal submit queue has higher priority).
+		 */
+		if (submit)
+			break;
 	}
 
 	while ((rb = rb_first_cached(&execlists->queue))) {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 03/62] drm/i915/gt: Decouple inflight virtual engines

[Chris Wilson]

Once a virtual engine has been bound to a sibling, it will remain bound
until we finally schedule out the last active request. We can not rebind
the context to a new sibling while it is inflight as the context save
will conflict, hence we wait. As we cannot then use any other sibliing
while the context is inflight, only kick the bound sibling while it
inflight and upon scheduling out the kick the rest (so that we can swap
engines on timeslicing if the previously bound engine becomes
oversubscribed).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 28 ++++++++-----------
 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index ddfd6b271b3b..fbd0572ed834 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -581,9 +581,8 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
-	struct i915_request *next = READ_ONCE(ve->request);
 
-	if (next == rq || (next && next->execution_mask & ~rq->execution_mask))
+	if (READ_ONCE(ve->request))
 		tasklet_hi_schedule(&ve->base.execlists.tasklet);
 }
 
@@ -997,17 +996,13 @@ first_virtual_engine(struct intel_engine_cs *engine)
 		struct i915_request *rq = READ_ONCE(ve->request);
 
 		/* lazily cleanup after another engine handled rq */
-		if (!rq) {
+		if (!rq || !virtual_matches(ve, rq, engine)) {
 			rb_erase_cached(rb, &el->virtual);
 			RB_CLEAR_NODE(rb);
 			rb = rb_first_cached(&el->virtual);
 			continue;
 		}
 
-		if (!virtual_matches(ve, rq, engine)) {
-			rb = rb_next(rb);
-			continue;
-		}
 		return ve;
 	}
 
@@ -3435,7 +3430,6 @@ static void virtual_submission_tasklet(unsigned long data)
 	if (unlikely(!mask))
 		return;
 
-	local_irq_disable();
 	for (n = 0; n < ve->num_siblings; n++) {
 		struct intel_engine_cs *sibling = READ_ONCE(ve->siblings[n]);
 		struct ve_node * const node = &ve->nodes[sibling->id];
@@ -3445,20 +3439,19 @@ static void virtual_submission_tasklet(unsigned long data)
 		if (!READ_ONCE(ve->request))
 			break; /* already handled by a sibling's tasklet */
 
+		spin_lock_irq(&sibling->active.lock);
+
 		if (unlikely(!(mask & sibling->mask))) {
 			if (!RB_EMPTY_NODE(&node->rb)) {
-				spin_lock(&sibling->active.lock);
 				rb_erase_cached(&node->rb,
 						&sibling->execlists.virtual);
 				RB_CLEAR_NODE(&node->rb);
-				spin_unlock(&sibling->active.lock);
 			}
-			continue;
-		}
 
-		spin_lock(&sibling->active.lock);
+			goto unlock_engine;
+		}
 
-		if (!RB_EMPTY_NODE(&node->rb)) {
+		if (unlikely(!RB_EMPTY_NODE(&node->rb))) {
 			/*
 			 * Cheat and avoid rebalancing the tree if we can
 			 * reuse this node in situ.
@@ -3498,9 +3491,12 @@ static void virtual_submission_tasklet(unsigned long data)
 		if (first && prio > sibling->execlists.queue_priority_hint)
 			tasklet_hi_schedule(&sibling->execlists.tasklet);
 
-		spin_unlock(&sibling->active.lock);
+unlock_engine:
+		spin_unlock_irq(&sibling->active.lock);
+
+		if (intel_context_inflight(&ve->context))
+			break;
 	}
-	local_irq_enable();
 }
 
 static void virtual_submit_request(struct i915_request *rq)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 04/62] drm/i915/gt: Defer schedule_out until after the next dequeue

[Chris Wilson]

Inside schedule_out, we do extra work upon idling the context, such as
updating the runtime, kicking off retires, kicking virtual engines.
However, if we are in a series of processing single requests per
contexts, we may find ourselves scheduling out the context, only to
immediately schedule it back in during dequeue. This is just extra work
that we can avoid if we keep the context marked as inflight across the
dequeue. This becomes more significant later on for minimising virtual
engine misses.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context_types.h |   8 +-
 .../drm/i915/gt/intel_execlists_submission.c  | 174 +++++++++++-------
 2 files changed, 115 insertions(+), 67 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 52fa9c132746..f7a0fb6f3a2e 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -58,8 +58,12 @@ struct intel_context {
 
 	struct intel_engine_cs *engine;
 	struct intel_engine_cs *inflight;
-#define intel_context_inflight(ce) ptr_mask_bits(READ_ONCE((ce)->inflight), 2)
-#define intel_context_inflight_count(ce) ptr_unmask_bits(READ_ONCE((ce)->inflight), 2)
+#define __intel_context_inflight(engine) ptr_mask_bits(engine, 3)
+#define __intel_context_inflight_count(engine) ptr_unmask_bits(engine, 3)
+#define intel_context_inflight(ce) \
+	__intel_context_inflight(READ_ONCE((ce)->inflight))
+#define intel_context_inflight_count(ce) \
+	__intel_context_inflight_count(READ_ONCE((ce)->inflight))
 
 	struct i915_address_space *vm;
 	struct i915_gem_context __rcu *gem_context;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index fbd0572ed834..b5f256be73dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -205,7 +205,7 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
 
 static void mark_eio(struct i915_request *rq)
 {
-	if (i915_request_completed(rq))
+	if (__i915_request_is_complete(rq))
 		return;
 
 	GEM_BUG_ON(i915_request_signaled(rq));
@@ -221,7 +221,7 @@ active_request(const struct intel_timeline * const tl, struct i915_request *rq)
 
 	rcu_read_lock();
 	list_for_each_entry_continue_reverse(rq, &tl->requests, link) {
-		if (i915_request_completed(rq))
+		if (__i915_request_is_complete(rq))
 			break;
 
 		active = rq;
@@ -381,7 +381,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	list_for_each_entry_safe_reverse(rq, rn,
 					 &engine->active.requests,
 					 sched.link) {
-		if (i915_request_completed(rq)) {
+		if (__i915_request_is_complete(rq)) {
 			list_del_init(&rq->sched.link);
 			continue;
 		}
@@ -506,7 +506,7 @@ static void reset_active(struct i915_request *rq,
 		     rq->fence.context, rq->fence.seqno);
 
 	/* On resubmission of the active request, payload will be scrubbed */
-	if (i915_request_completed(rq))
+	if (__i915_request_is_complete(rq))
 		head = rq->tail;
 	else
 		head = active_request(ce->timeline, rq)->head;
@@ -607,7 +607,7 @@ __execlists_schedule_out(struct i915_request *rq,
 	 * idle and we want to re-enter powersaving.
 	 */
 	if (list_is_last_rcu(&rq->link, &ce->timeline->requests) &&
-	    i915_request_completed(rq))
+	    __i915_request_is_complete(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
 	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
@@ -728,8 +728,8 @@ dump_port(char *buf, int buflen, const char *prefix, struct i915_request *rq)
 		 prefix,
 		 rq->context->lrc.ccid,
 		 rq->fence.context, rq->fence.seqno,
-		 i915_request_completed(rq) ? "!" :
-		 i915_request_started(rq) ? "*" :
+		 __i915_request_is_complete(rq) ? "!" :
+		 __i915_request_has_started(rq) ? "*" :
 		 "",
 		 rq_prio(rq));
 
@@ -831,7 +831,7 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		if (!spin_trylock_irqsave(&rq->lock, flags))
 			continue;
 
-		if (i915_request_completed(rq))
+		if (__i915_request_is_complete(rq))
 			goto unlock;
 
 		if (i915_active_is_idle(&ce->active) &&
@@ -944,7 +944,7 @@ static bool can_merge_rq(const struct i915_request *prev,
 	 * contexts, despite the best efforts of preempt-to-busy to confuse
 	 * us.
 	 */
-	if (i915_request_completed(next))
+	if (__i915_request_is_complete(next))
 		return true;
 
 	if (unlikely((i915_request_flags(prev) ^ i915_request_flags(next)) &
@@ -1065,8 +1065,8 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 
 			/* No waiter should start before its signaler */
 			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
-				   i915_request_started(w) &&
-				   !i915_request_completed(rq));
+				   __i915_request_has_started(w) &&
+				   !__i915_request_is_complete(rq));
 
 			GEM_BUG_ON(i915_request_is_active(w));
 			if (!i915_request_is_ready(w))
@@ -1159,7 +1159,7 @@ static unsigned long active_timeslice(const struct intel_engine_cs *engine)
 	const struct intel_engine_execlists *execlists = &engine->execlists;
 	const struct i915_request *rq = *execlists->active;
 
-	if (!rq || i915_request_completed(rq))
+	if (!rq || __i915_request_is_complete(rq))
 		return 0;
 
 	if (READ_ONCE(execlists->switch_priority_hint) < effective_prio(rq))
@@ -1232,19 +1232,6 @@ static void set_preempt_timeout(struct intel_engine_cs *engine,
 		     active_preempt_timeout(engine, rq));
 }
 
-static inline void clear_ports(struct i915_request **ports, int count)
-{
-	memset_p((void **)ports, NULL, count);
-}
-
-static inline void
-copy_ports(struct i915_request **dst, struct i915_request **src, int count)
-{
-	/* A memcpy_p() would be very useful here! */
-	while (count--)
-		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
-}
-
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1299,7 +1286,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 */
 
 	if (last) {
-		if (i915_request_completed(last)) {
+		if (__i915_request_is_complete(last)) {
 			goto check_secondary;
 		} else if (need_preempt(engine, last)) {
 			ENGINE_TRACE(engine,
@@ -1409,8 +1396,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			     "virtual rq=%llx:%lld%s, new engine? %s\n",
 			     rq->fence.context,
 			     rq->fence.seqno,
-			     i915_request_completed(rq) ? "!" :
-			     i915_request_started(rq) ? "*" :
+			     __i915_request_is_complete(rq) ? "!" :
+			     __i915_request_has_started(rq) ? "*" :
 			     "",
 			     yesno(engine != ve->siblings[0]));
 
@@ -1593,18 +1580,32 @@ static void execlists_dequeue_irq(struct intel_engine_cs *engine)
 	local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */
 }
 
-static void
-cancel_port_requests(struct intel_engine_execlists * const execlists)
+static inline void clear_ports(struct i915_request **ports, int count)
+{
+	memset_p((void **)ports, NULL, count);
+}
+
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
+static struct i915_request **
+cancel_port_requests(struct intel_engine_execlists * const execlists,
+		     struct i915_request **inactive)
 {
 	struct i915_request * const *port;
 
 	for (port = execlists->pending; *port; port++)
-		execlists_schedule_out(*port);
+		*inactive++ = *port;
 	clear_ports(execlists->pending, ARRAY_SIZE(execlists->pending));
 
 	/* Mark the end of active before we overwrite *active */
 	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
-		execlists_schedule_out(*port);
+		*inactive++ = *port;
 	clear_ports(execlists->inflight, ARRAY_SIZE(execlists->inflight));
 
 	smp_wmb(); /* complete the seqlock for execlists_active() */
@@ -1614,6 +1615,8 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 	GEM_BUG_ON(execlists->pending[0]);
 	cancel_timer(&execlists->timer);
 	cancel_timer(&execlists->preempt);
+
+	return inactive;
 }
 
 static inline void
@@ -1741,7 +1744,8 @@ csb_read(const struct intel_engine_cs *engine, u64 * const csb)
 	return entry;
 }
 
-static void process_csb(struct intel_engine_cs *engine)
+static struct i915_request **
+process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	u64 * const buf = execlists->csb_status;
@@ -1770,7 +1774,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	head = execlists->csb_head;
 	tail = READ_ONCE(*execlists->csb_write);
 	if (unlikely(head == tail))
-		return;
+		return inactive;
 
 	/*
 	 * We will consume all events from HW, or at least pretend to.
@@ -1850,7 +1854,7 @@ static void process_csb(struct intel_engine_cs *engine)
 			/* cancel old inflight, prepare for switch */
 			trace_ports(execlists, "preempted", old);
 			while (*old)
-				execlists_schedule_out(*old++);
+				*inactive++ = *old++;
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
@@ -1884,7 +1888,7 @@ static void process_csb(struct intel_engine_cs *engine)
 			 * itself...
 			 */
 			if (GEM_SHOW_DEBUG() &&
-			    !i915_request_completed(*execlists->active)) {
+			    !__i915_request_is_complete(*execlists->active)) {
 				struct i915_request *rq = *execlists->active;
 				const u32 *regs __maybe_unused =
 					rq->context->lrc_reg_state;
@@ -1912,7 +1916,7 @@ static void process_csb(struct intel_engine_cs *engine)
 					     regs[CTX_RING_TAIL]);
 			}
 
-			execlists_schedule_out(*execlists->active++);
+			*inactive++ = *execlists->active++;
 
 			GEM_BUG_ON(execlists->active - execlists->inflight >
 				   execlists_num_ports(execlists));
@@ -1933,6 +1937,15 @@ static void process_csb(struct intel_engine_cs *engine)
 	 * invalidation before.
 	 */
 	invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
+
+	return inactive;
+}
+
+static void post_process_csb(struct i915_request **port,
+			     struct i915_request **last)
+{
+	while (port != last)
+		execlists_schedule_out(*port++);
 }
 
 static void __execlists_hold(struct i915_request *rq)
@@ -1961,7 +1974,7 @@ static void __execlists_hold(struct i915_request *rq)
 			if (!i915_request_is_ready(w))
 				continue;
 
-			if (i915_request_completed(w))
+			if (__i915_request_is_complete(w))
 				continue;
 
 			if (i915_request_on_hold(w))
@@ -1982,7 +1995,7 @@ static bool execlists_hold(struct intel_engine_cs *engine,
 
 	spin_lock_irq(&engine->active.lock);
 
-	if (i915_request_completed(rq)) { /* too late! */
+	if (__i915_request_is_complete(rq)) { /* too late! */
 		rq = NULL;
 		goto unlock;
 	}
@@ -2208,8 +2221,8 @@ active_context(struct intel_engine_cs *engine, u32 ccid)
 	for (port = el->active; (rq = *port); port++) {
 		if (rq->context->lrc.ccid == ccid) {
 			ENGINE_TRACE(engine,
-				     "ccid found at active:%zd\n",
-				     port - el->active);
+				     "ccid:%x found at active:%zd\n",
+				     ccid, port - el->active);
 			return rq;
 		}
 	}
@@ -2217,8 +2230,8 @@ active_context(struct intel_engine_cs *engine, u32 ccid)
 	for (port = el->pending; (rq = *port); port++) {
 		if (rq->context->lrc.ccid == ccid) {
 			ENGINE_TRACE(engine,
-				     "ccid found at pending:%zd\n",
-				     port - el->pending);
+				     "ccid:%x found at pending:%zd\n",
+				     ccid, port - el->pending);
 			return rq;
 		}
 	}
@@ -2336,8 +2349,12 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine)
 static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	struct i915_request *post[2 * EXECLIST_MAX_PORTS];
+	struct i915_request **inactive;
 
-	process_csb(engine);
+	rcu_read_lock();
+	inactive = process_csb(engine, post);
+	GEM_BUG_ON(inactive - post > ARRAY_SIZE(post));
 
 	if (unlikely(preempt_timeout(engine))) {
 		cancel_timer(&engine->execlists.preempt);
@@ -2363,6 +2380,9 @@ static void execlists_submission_tasklet(unsigned long data)
 
 	if (!engine->execlists.pending[0])
 		execlists_dequeue_irq(engine);
+
+	post_process_csb(post, inactive);
+	rcu_read_unlock();
 }
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
@@ -2735,8 +2755,6 @@ static void enable_execlists(struct intel_engine_cs *engine)
 	ENGINE_POSTING_READ(engine, RING_HWS_PGA);
 
 	enable_error_interrupt(engine);
-
-	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -2806,22 +2824,30 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	engine->execlists.reset_ccid = active_ccid(engine);
 }
 
-static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
+static struct i915_request **
+reset_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct intel_context *ce;
-	struct i915_request *rq;
-	u32 head;
 
 	mb(); /* paranoia: read the CSB pointers from after the reset */
 	clflush(execlists->csb_write);
 	mb();
 
-	process_csb(engine); /* drain preemption events */
+	inactive = process_csb(engine, inactive); /* drain preemption events */
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
 	reset_csb_pointers(engine);
 
+	return inactive;
+}
+
+static void
+execlists_reset_active(struct intel_engine_cs *engine, bool stalled)
+{
+	struct intel_context *ce;
+	struct i915_request *rq;
+	u32 head;
+
 	/*
 	 * Save the currently executing context, even if we completed
 	 * its request, it was still running at the time of the
@@ -2829,12 +2855,12 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 */
 	rq = active_context(engine, engine->execlists.reset_ccid);
 	if (!rq)
-		goto unwind;
+		return;
 
 	ce = rq->context;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
-	if (i915_request_completed(rq)) {
+	if (__i915_request_is_complete(rq)) {
 		/* Idle context; tidy up the ring so we can restart afresh */
 		head = intel_ring_wrap(ce->ring, rq->tail);
 		goto out_replay;
@@ -2862,7 +2888,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * Otherwise, if we have not started yet, the request should replay
 	 * perfectly and we do not need to flag the result as being erroneous.
 	 */
-	if (!i915_request_started(rq))
+	if (!__i915_request_has_started(rq))
 		goto out_replay;
 
 	/*
@@ -2891,11 +2917,22 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 		     head, ce->ring->tail);
 	lrc_reset_regs(ce, engine);
 	ce->lrc.lrca = lrc_update_regs(ce, engine, head);
+}
 
-unwind:
-	/* Push back any incomplete requests for replay after the reset. */
-	cancel_port_requests(execlists);
-	__unwind_incomplete_requests(engine);
+static void execlists_reset_csb(struct intel_engine_cs *engine, bool stalled)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_request *post[2 * EXECLIST_MAX_PORTS];
+	struct i915_request **inactive;
+
+	rcu_read_lock();
+	inactive = reset_csb(engine, post);
+
+	execlists_reset_active(engine, true);
+
+	inactive = cancel_port_requests(execlists, inactive);
+	post_process_csb(post, inactive);
+	rcu_read_unlock();
 }
 
 static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
@@ -2904,11 +2941,15 @@ static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 
 	ENGINE_TRACE(engine, "\n");
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-
-	__execlists_reset(engine, stalled);
+	/* Process the csb, find the guilty context and throw away */
+	execlists_reset_csb(engine, stalled);
 
+	/* Push back any incomplete requests for replay after the reset. */
+	rcu_read_lock();
+	spin_lock_irqsave(&engine->active.lock, flags);
+	__unwind_incomplete_requests(engine);
 	spin_unlock_irqrestore(&engine->active.lock, flags);
+	rcu_read_unlock();
 }
 
 static void nop_submission_tasklet(unsigned long data)
@@ -2942,9 +2983,10 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	 * submission's irq state, we also wish to remind ourselves that
 	 * it is irq state.)
 	 */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	execlists_reset_csb(engine, true);
 
-	__execlists_reset(engine, true);
+	rcu_read_lock();
+	spin_lock_irqsave(&engine->active.lock, flags);
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->active.requests, sched.link)
@@ -3000,6 +3042,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	execlists->tasklet.func = nop_submission_tasklet;
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
+	rcu_read_unlock();
 }
 
 static void execlists_reset_finish(struct intel_engine_cs *engine)
@@ -3211,6 +3254,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	else
 		execlists->csb_size = GEN11_CSB_ENTRIES;
 
+	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
 	if (INTEL_GEN(engine->i915) >= 11) {
 		execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
 		execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32);
@@ -3515,12 +3559,12 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	old = ve->request;
 	if (old) { /* background completion event from preempt-to-busy */
-		GEM_BUG_ON(!i915_request_completed(old));
+		GEM_BUG_ON(!__i915_request_is_complete(old));
 		__i915_request_submit(old);
 		i915_request_put(old);
 	}
 
-	if (i915_request_completed(rq)) {
+	if (__i915_request_is_complete(rq)) {
 		__i915_request_submit(rq);
 
 		ve->base.execlists.queue_priority_hint = INT_MIN;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 05/62] drm/i915/gt: Remove virtual breadcrumb before transfer

[Chris Wilson]

The issue with stale virtual breadcrumbs remain. Now we have the problem
that if the irq-signaler is still referencing the stale breadcrumb as we
transfer it to a new sibling, the list becomes spaghetti. This is a very
small window, but that doesn't stop it being hit infrequently. To
prevent the lists being tangled (the iterator starting on one engine's
b->signalers but walking onto another list), always decouple the virtual
breadcrumb on schedule-out and make sure that the walker has stepped out
of the lists.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c       |  5 +++--
 .../gpu/drm/i915/gt/intel_execlists_submission.c  | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index f96cd7d9b419..8f7c8595ba08 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -451,15 +451,16 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 {
 	struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
 	struct intel_context *ce = rq->context;
+	unsigned long flags;
 	bool release;
 
 	if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
 		return;
 
-	spin_lock(&ce->signal_lock);
+	spin_lock_irqsave(&ce->signal_lock, flags);
 	list_del_rcu(&rq->signal_link);
 	release = remove_signaling_context(b, ce);
-	spin_unlock(&ce->signal_lock);
+	spin_unlock_irqrestore(&ce->signal_lock, flags);
 	if (release)
 		intel_context_put(ce);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index b5f256be73dd..1f6e9fe5bcc0 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -581,6 +581,21 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
+	struct intel_engine_cs *engine = rq->engine;
+
+	/* Flush concurrent rcu iterators in signal_irq_work */
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) {
+		/*
+		 * After this point, the rq may be transferred to a new
+		 * sibling, so before we clear ce->inflight make sure that
+		 * the context has been removed from the b->signalers and
+		 * furthermore we need to make sure that the concurrent
+		 * iterator in signal_irq_work is no longer following
+		 * ce->signal_link.
+		 */
+		i915_request_cancel_breadcrumb(rq);
+		irq_work_sync(&engine->breadcrumbs->irq_work);
+	}
 
 	if (READ_ONCE(ve->request))
 		tasklet_hi_schedule(&ve->base.execlists.tasklet);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 06/62] drm/i915/gt: Shrink the critical section for irq signaling

[Chris Wilson]

Let's only wait for the list iterator when decoupling the virtual
breadcrumb, as the signaling of all the requests may take a long time,
during which we do not want to keep the tasklet spinning.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c          | 2 ++
 drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h    | 1 +
 drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 3 ++-
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 8f7c8595ba08..2eabb9ab5d47 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -234,6 +234,7 @@ static void signal_irq_work(struct irq_work *work)
 		intel_breadcrumbs_disarm_irq(b);
 
 	rcu_read_lock();
+	atomic_inc(&b->signaler_active);
 	list_for_each_entry_rcu(ce, &b->signalers, signal_link) {
 		struct i915_request *rq;
 
@@ -269,6 +270,7 @@ static void signal_irq_work(struct irq_work *work)
 			}
 		}
 	}
+	atomic_dec(&b->signaler_active);
 	rcu_read_unlock();
 
 	llist_for_each_safe(signal, sn, signal) {
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
index d85a6f74fb87..3a084ce8ff5e 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
@@ -34,6 +34,7 @@ struct intel_breadcrumbs {
 	spinlock_t signalers_lock; /* protects the list of signalers */
 	struct list_head signalers;
 	struct llist_head signaled_requests;
+	atomic_t signaler_active;
 
 	spinlock_t irq_lock; /* protects the interrupt from hardirq context */
 	struct irq_work irq_work; /* for use from inside irq_lock */
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 1f6e9fe5bcc0..ba8229c0c75a 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -594,7 +594,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 		 * ce->signal_link.
 		 */
 		i915_request_cancel_breadcrumb(rq);
-		irq_work_sync(&engine->breadcrumbs->irq_work);
+		while (atomic_read(&engine->breadcrumbs->signaler_active))
+			cpu_relax();
 	}
 
 	if (READ_ONCE(ve->request))
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 07/62] drm/i915/gt: Resubmit the virtual engine on schedule-out

[Chris Wilson]

Having recognised that we do not change the sibling until we schedule
out, we can then defer the decision to resubmit the virtual engine from
the unwind of the active queue to scheduling out of the virtual context.
This improves our resilence in virtual engine scheduling, and should
eliminate the rare cases of gem_exec_balance failing.

By keeping the unwind order intact on the local engine, we can preserve
data dependency ordering while doing a preempt-to-busy pass until we
have determined the new ELSP. This means that if we try to timeslice
between a virtual engine and a data-dependent ordinary request, the pair
will maintain their relative ordering and we will avoid the
resubmission, cancelling the timeslicing until further change.

The dilemma though is that we then may end up in a situation where the
'demotion' of the virtual request to an ordinary request in the engine
queue results in filling the ELSP[] with virtual requests instead of
spreading the load across the engines. To compensate for this, we mark
each virtual request and refuse to resubmit a virtual request in the
secondary ELSP slots, thus forcing subsequent virtual requests to be
scheduled out after timeslicing. By delaying the decision until we
schedule out, we will avoid unnecessary resubmission.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2079
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2098
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 126 +++++++++++-------
 drivers/gpu/drm/i915/gt/selftest_execlists.c  |   2 +-
 2 files changed, 79 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index ba8229c0c75a..2d7a1440c31a 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -388,38 +388,23 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 
 		__i915_request_unsubmit(rq);
 
-		/*
-		 * Push the request back into the queue for later resubmission.
-		 * If this request is not native to this physical engine (i.e.
-		 * it came from a virtual source), push it back onto the virtual
-		 * engine so that it can be moved across onto another physical
-		 * engine as load dictates.
-		 */
-		if (likely(rq->execution_mask == engine->mask)) {
-			GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
-			if (rq_prio(rq) != prio) {
-				prio = rq_prio(rq);
-				pl = i915_sched_lookup_priolist(engine, prio);
-			}
-			GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
+		if (rq_prio(rq) != prio) {
+			prio = rq_prio(rq);
+			pl = i915_sched_lookup_priolist(engine, prio);
+		}
+		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 
-			list_move(&rq->sched.link, pl);
-			set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		list_move(&rq->sched.link, pl);
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
-			/* Check in case we rollback so far we wrap [size/2] */
-			if (intel_ring_direction(rq->ring,
-						 rq->tail,
-						 rq->ring->tail + 8) > 0)
-				rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
+		/* Check in case we rollback so far we wrap [size/2] */
+		if (intel_ring_direction(rq->ring,
+					 rq->tail,
+					 rq->ring->tail + 8) > 0)
+			rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 
-			active = rq;
-		} else {
-			struct intel_engine_cs *owner = rq->context->engine;
-
-			WRITE_ONCE(rq->engine, owner);
-			owner->submit_request(rq);
-			active = NULL;
-		}
+		active = rq;
 	}
 
 	return active;
@@ -578,9 +563,9 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 }
 
-static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
+static void
+resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
 {
-	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
 	struct intel_engine_cs *engine = rq->engine;
 
 	/* Flush concurrent rcu iterators in signal_irq_work */
@@ -598,6 +583,30 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 			cpu_relax();
 	}
 
+	spin_lock_irq(&engine->active.lock);
+
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	WRITE_ONCE(rq->engine, &ve->base);
+	ve->base.submit_request(rq);
+
+	spin_unlock_irq(&engine->active.lock);
+}
+
+static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
+{
+	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
+	struct intel_engine_cs *engine = rq->engine;
+
+	/*
+	 * This engine is now too busy to run this virtual request, so
+	 * see if we can find an alternative engine for it to execute on.
+	 * Once a request has become bonded to this engine, we treat it the
+	 * same as other native request.
+	 */
+	if (i915_request_in_priority_queue(rq) &&
+	    rq->execution_mask != engine->mask)
+		resubmit_virtual_request(rq, ve);
+
 	if (READ_ONCE(ve->request))
 		tasklet_hi_schedule(&ve->base.execlists.tasklet);
 }
@@ -843,6 +852,20 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 		}
 		sentinel = i915_request_has_sentinel(rq);
 
+		/*
+		 * We want virtual requests to only be in the first slot so
+		 * that they are never stuck behind a hog and can be immediately
+		 * transferred onto the next idle engine.
+		 */
+		if (rq->execution_mask != engine->mask &&
+		    port != execlists->pending) {
+			GEM_TRACE_ERR("%s: virtual engine:%llx not in prime position[%zd]\n",
+				      engine->name,
+				      ce->timeline->fence_context,
+				      port - execlists->pending);
+			return false;
+		}
+
 		/* Hold tightly onto the lock to prevent concurrent retires! */
 		if (!spin_trylock_irqsave(&rq->lock, flags))
 			continue;
@@ -1502,6 +1525,15 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				if (i915_request_has_sentinel(last))
 					goto done;
 
+				/*
+				 * We avoid submitting virtual requests into
+				 * the secondary ports so that we can migrate
+				 * the request immediately to another engine
+				 * rather than wait for the primary request.
+				 */
+				if (rq->execution_mask != engine->mask)
+					goto done;
+
 				/*
 				 * If GVT overrides us we only ever submit
 				 * port[0], leaving port[1] empty. Note that we
@@ -3562,7 +3594,6 @@ static void virtual_submission_tasklet(unsigned long data)
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
-	struct i915_request *old;
 	unsigned long flags;
 
 	ENGINE_TRACE(&ve->base, "rq=%llx:%lld\n",
@@ -3573,28 +3604,27 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	spin_lock_irqsave(&ve->base.active.lock, flags);
 
-	old = ve->request;
-	if (old) { /* background completion event from preempt-to-busy */
-		GEM_BUG_ON(!__i915_request_is_complete(old));
-		__i915_request_submit(old);
-		i915_request_put(old);
-	}
-
+	/* By the time we resubmit a request, it may be completed */
 	if (__i915_request_is_complete(rq)) {
 		__i915_request_submit(rq);
+		goto unlock;
+	}
 
-		ve->base.execlists.queue_priority_hint = INT_MIN;
-		ve->request = NULL;
-	} else {
-		ve->base.execlists.queue_priority_hint = rq_prio(rq);
-		ve->request = i915_request_get(rq);
+	if (ve->request) { /* background completion from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(ve->request));
+		__i915_request_submit(ve->request);
+		i915_request_put(ve->request);
+	}
 
-		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
-		list_move_tail(&rq->sched.link, virtual_queue(ve));
+	ve->base.execlists.queue_priority_hint = rq_prio(rq);
+	ve->request = i915_request_get(rq);
 
-		tasklet_hi_schedule(&ve->base.execlists.tasklet);
-	}
+	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	list_move_tail(&rq->sched.link, virtual_queue(ve));
+
+	tasklet_hi_schedule(&ve->base.execlists.tasklet);
 
+unlock:
 	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 47b12ce4b132..080b63000a4e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -4566,7 +4566,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	spin_lock_irq(&engine->active.lock);
 	__unwind_incomplete_requests(engine);
 	spin_unlock_irq(&engine->active.lock);
-	GEM_BUG_ON(rq->engine != ve->engine);
+	GEM_BUG_ON(rq->engine != engine);
 
 	/* Reset the engine while keeping our active request on hold */
 	execlists_hold(engine, rq);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 08/62] drm/i915/gt: Simplify virtual engine handling for execlists_hold()

[Chris Wilson]

Now that the tasklet completely controls scheduling of the requests, and
we postpone scheduling out the old requests, we can keep a hanging
virtual request bound to the engine on which it hung, and remove it from
te queue. On release, it will be returned to the same engine and remain
in its queue until it is scheduled; after which point it will become
eligible for transfer to a sibling. Instead, we could opt to resubmit the
request along the virtual engine on unhold, making it eligible for load
balancing immediately -- but that seems like a pointless optimisation
for a hanging context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 29 -------------------
 1 file changed, 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2d7a1440c31a..dc1312d862ed 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2048,35 +2048,6 @@ static bool execlists_hold(struct intel_engine_cs *engine,
 		goto unlock;
 	}
 
-	if (rq->engine != engine) { /* preempted virtual engine */
-		struct virtual_engine *ve = to_virtual_engine(rq->engine);
-
-		/*
-		 * intel_context_inflight() is only protected by virtue
-		 * of process_csb() being called only by the tasklet (or
-		 * directly from inside reset while the tasklet is suspended).
-		 * Assert that neither of those are allowed to run while we
-		 * poke at the request queues.
-		 */
-		GEM_BUG_ON(!reset_in_progress(&engine->execlists));
-
-		/*
-		 * An unsubmitted request along a virtual engine will
-		 * remain on the active (this) engine until we are able
-		 * to process the context switch away (and so mark the
-		 * context as no longer in flight). That cannot have happened
-		 * yet, otherwise we would not be hanging!
-		 */
-		spin_lock(&ve->base.active.lock);
-		GEM_BUG_ON(intel_context_inflight(rq->context) != engine);
-		GEM_BUG_ON(ve->request != rq);
-		ve->request = NULL;
-		spin_unlock(&ve->base.active.lock);
-		i915_request_put(rq);
-
-		rq->engine = engine;
-	}
-
 	/*
 	 * Transfer this request onto the hold queue to prevent it
 	 * being resumbitted to HW (and potentially completed) before we have
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 09/62] drm/i915/gt: ce->inflight updates are now serialised

[Chris Wilson]

Since schedule-in and schedule-out are now both always under the tasklet
bitlock, we can reduce the individual atomic operations to simple
instructions and worry less.

This notably eliminates the race observed with intel_context_inflight in
__engine_unpark().

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2583
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 52 +++++++++----------
 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index dc1312d862ed..1fae6c6f3868 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -524,11 +524,11 @@ __execlists_schedule_in(struct i915_request *rq)
 		ce->lrc.ccid = ce->tag;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		unsigned int tag = ffs(READ_ONCE(engine->context_tag));
+		unsigned int tag = __ffs(engine->context_tag);
 
-		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
-		clear_bit(tag - 1, &engine->context_tag);
-		ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32);
+		GEM_BUG_ON(tag >= BITS_PER_LONG);
+		__clear_bit(tag, &engine->context_tag);
+		ce->lrc.ccid = (1 + tag) << (GEN11_SW_CTX_ID_SHIFT - 32);
 
 		BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID);
 	}
@@ -541,6 +541,8 @@ __execlists_schedule_in(struct i915_request *rq)
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
 
+	CE_TRACE(ce, "schedule-in, ccid:%x\n", ce->lrc.ccid);
+
 	return engine;
 }
 
@@ -552,13 +554,10 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 	GEM_BUG_ON(!intel_engine_pm_is_awake(rq->engine));
 	trace_i915_request_in(rq, idx);
 
-	old = READ_ONCE(ce->inflight);
-	do {
-		if (!old) {
-			WRITE_ONCE(ce->inflight, __execlists_schedule_in(rq));
-			break;
-		}
-	} while (!try_cmpxchg(&ce->inflight, &old, ptr_inc(old)));
+	old = ce->inflight;
+	if (!old)
+		old = __execlists_schedule_in(rq);
+	WRITE_ONCE(ce->inflight, ptr_inc(old));
 
 	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 }
@@ -611,12 +610,11 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 		tasklet_hi_schedule(&ve->base.execlists.tasklet);
 }
 
-static inline void
-__execlists_schedule_out(struct i915_request *rq,
-			 struct intel_engine_cs * const engine,
-			 unsigned int ccid)
+static inline void __execlists_schedule_out(struct i915_request *rq)
 {
 	struct intel_context * const ce = rq->context;
+	struct intel_engine_cs * const engine = rq->engine;
+	unsigned int ccid;
 
 	/*
 	 * NB process_csb() is not under the engine->active.lock and hence
@@ -624,6 +622,8 @@ __execlists_schedule_out(struct i915_request *rq,
 	 * refrain from doing non-trivial work here.
 	 */
 
+	CE_TRACE(ce, "schedule-out, ccid:%x\n", ce->lrc.ccid);
+
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		lrc_check_regs(ce, engine, "after");
 
@@ -635,12 +635,13 @@ __execlists_schedule_out(struct i915_request *rq,
 	    __i915_request_is_complete(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
+	ccid = ce->lrc.ccid;
 	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
 	ccid &= GEN12_MAX_CONTEXT_HW_ID;
 	if (ccid < BITS_PER_LONG) {
 		GEM_BUG_ON(ccid == 0);
 		GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
-		set_bit(ccid - 1, &engine->context_tag);
+		__set_bit(ccid - 1, &engine->context_tag);
 	}
 
 	lrc_update_runtime(ce);
@@ -661,26 +662,23 @@ __execlists_schedule_out(struct i915_request *rq,
 	 */
 	if (ce->engine != engine)
 		kick_siblings(rq, ce);
-
-	intel_context_put(ce);
 }
 
 static inline void
 execlists_schedule_out(struct i915_request *rq)
 {
 	struct intel_context * const ce = rq->context;
-	struct intel_engine_cs *cur, *old;
-	u32 ccid;
 
 	trace_i915_request_out(rq);
 
-	ccid = rq->context->lrc.ccid;
-	old = READ_ONCE(ce->inflight);
-	do
-		cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL;
-	while (!try_cmpxchg(&ce->inflight, &old, cur));
-	if (!cur)
-		__execlists_schedule_out(rq, old, ccid);
+	GEM_BUG_ON(!ce->inflight);
+	ce->inflight = ptr_dec(ce->inflight);
+	if (!__intel_context_inflight_count(ce->inflight)) {
+		GEM_BUG_ON(ce->inflight != rq->engine);
+		__execlists_schedule_out(rq);
+		WRITE_ONCE(ce->inflight, NULL);
+		intel_context_put(ce);
+	}
 
 	i915_request_put(rq);
 }
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 10/62] drm/i915/selftests: Confirm CS_TIMESTAMP / CTX_TIMESTAMP share a clock

[Chris Wilson]

We assume that both timestamps are driven off the same clock [reported
to userspace as I915_PARAM_CS_TIMESTAMP_FREQUENCY]. Verify that this is
so by reading the timestamp registers around a busywait (on an otherwise
idle engine so there should be no preemptions).

v2: Icelake (not ehl, nor tgl) seems to be using a fixed 80ns interval
for, and only for, CTX_TIMESTAMP -- or it may be GPU frequency and the
test is always running at maximum frequency?. As far as I can tell, this
isolated change in behaviour is undocumented.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/selftest_engine_pm.c | 203 ++++++++++++++++++-
 1 file changed, 202 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 163a10b07f85..d88504a5d69c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -4,15 +4,215 @@
  * Copyright © 2018 Intel Corporation
  */
 
-#include "intel_gpu_commands.h"
+#include <linux/sort.h>
 
 #include "i915_selftest.h"
+#include "intel_gpu_commands.h"
+#include "intel_gt_clock_utils.h"
 #include "selftest_engine.h"
 #include "selftest_engine_heartbeat.h"
 #include "selftests/igt_atomic.h"
 #include "selftests/igt_flush_test.h"
 #include "selftests/igt_spinner.h"
 
+#define COUNT 5
+
+static int cmp_u64(const void *A, const void *B)
+{
+	const u64 *a = A, *b = B;
+
+	return *a - *b;
+}
+
+static u64 trifilter(u64 *a)
+{
+	sort(a, COUNT, sizeof(*a), cmp_u64, NULL);
+	return (a[1] + 2 * a[2] + a[3]) >> 2;
+}
+
+static u32 *emit_wait(u32 *cs, u32 offset, int op, u32 value)
+{
+	*cs++ = MI_SEMAPHORE_WAIT |
+		MI_SEMAPHORE_GLOBAL_GTT |
+		MI_SEMAPHORE_POLL |
+		op;
+	*cs++ = value;
+	*cs++ = offset;
+	*cs++ = 0;
+
+	return cs;
+}
+
+static u32 *emit_store(u32 *cs, u32 offset, u32 value)
+{
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = offset;
+	*cs++ = 0;
+	*cs++ = value;
+
+	return cs;
+}
+
+static u32 *emit_srm(u32 *cs, i915_reg_t reg, u32 offset)
+{
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+	*cs++ = i915_mmio_reg_offset(reg);
+	*cs++ = offset;
+	*cs++ = 0;
+
+	return cs;
+}
+
+static void write_semaphore(u32 *x, u32 value)
+{
+	WRITE_ONCE(*x, value);
+	wmb();
+}
+
+static int __measure_timestamps(struct intel_context *ce,
+				u64 *dt, u64 *d_ring, u64 *d_ctx)
+{
+	struct intel_engine_cs *engine = ce->engine;
+	u32 *sema = memset32(engine->status_page.addr + 1000, 0, 5);
+	u32 offset = i915_ggtt_offset(engine->status_page.vma);
+	struct i915_request *rq;
+	u32 *cs;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	cs = intel_ring_begin(rq, 28);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return PTR_ERR(cs);
+	}
+
+	/* Signal & wait for start */
+	cs = emit_store(cs, offset + 4008, 1);
+	cs = emit_wait(cs, offset + 4008, MI_SEMAPHORE_SAD_NEQ_SDD, 1);
+
+	cs = emit_srm(cs, RING_TIMESTAMP(engine->mmio_base), offset + 4000);
+	cs = emit_srm(cs, RING_CTX_TIMESTAMP(engine->mmio_base), offset + 4004);
+
+	/* Busy wait */
+	cs = emit_wait(cs, offset + 4008, MI_SEMAPHORE_SAD_EQ_SDD, 1);
+
+	cs = emit_srm(cs, RING_TIMESTAMP(engine->mmio_base), offset + 4016);
+	cs = emit_srm(cs, RING_CTX_TIMESTAMP(engine->mmio_base), offset + 4012);
+
+	intel_ring_advance(rq, cs);
+	i915_request_get(rq);
+	i915_request_add(rq);
+	intel_engine_flush_submission(engine);
+
+	/* Wait for the request to start executing, that then waits for us */
+	while (READ_ONCE(sema[2]) == 0)
+		cpu_relax();
+
+	/* Run the request for a 100us, sampling timestamps before/after */
+	preempt_disable();
+	*dt = ktime_get_raw_fast_ns();
+	write_semaphore(&sema[2], 0);
+	udelay(100);
+	write_semaphore(&sema[2], 1);
+	*dt = ktime_get_raw_fast_ns() - *dt;
+	preempt_enable();
+
+	if (i915_request_wait(rq, 0, HZ / 2) < 0) {
+		i915_request_put(rq);
+		return -ETIME;
+	}
+	i915_request_put(rq);
+
+	pr_debug("%s CTX_TIMESTAMP: [%x, %x], RING_TIMESTAMP: [%x, %x]\n",
+		 engine->name, sema[1], sema[3], sema[0], sema[4]);
+
+	*d_ctx = sema[3] - sema[1];
+	*d_ring = sema[4] - sema[0];
+	return 0;
+}
+
+static int __live_engine_timestamps(struct intel_engine_cs *engine)
+{
+	u64 s_ring[COUNT], s_ctx[COUNT], st[COUNT], d_ring, d_ctx, dt;
+	struct intel_context *ce;
+	int i, err = 0;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	for (i = 0; i < COUNT; i++) {
+		err = __measure_timestamps(ce, &st[i], &s_ring[i], &s_ctx[i]);
+		if (err)
+			break;
+	}
+	intel_context_put(ce);
+	if (err)
+		return err;
+
+	dt = trifilter(st);
+	d_ring = trifilter(s_ring);
+	d_ctx = trifilter(s_ctx);
+
+	pr_info("%s elapsed:%lldns, CTX_TIMESTAMP:%dns, RING_TIMESTAMP:%dns\n",
+		engine->name, dt,
+		intel_gt_clock_interval_to_ns(engine->gt, d_ctx),
+		intel_gt_clock_interval_to_ns(engine->gt, d_ring));
+
+	d_ring = intel_gt_clock_interval_to_ns(engine->gt, d_ring);
+	if (3 * dt > 4 * d_ring || 4 * dt < 3 * d_ring) {
+		pr_err("%s Mismatch between ring timestamp and walltime!\n",
+		       engine->name);
+		return -EINVAL;
+	}
+
+	d_ring = trifilter(s_ring);
+	d_ctx = trifilter(s_ctx);
+
+	d_ctx *= RUNTIME_INFO(engine->i915)->cs_timestamp_frequency_hz;
+	if (IS_ICELAKE(engine->i915))
+		d_ring *= 12500000; /* Fixed 80ns for icl ctx timestamp? */
+	else
+		d_ring *= RUNTIME_INFO(engine->i915)->cs_timestamp_frequency_hz;
+
+	if (3 * d_ctx > 4 * d_ring || 4 * d_ctx < 3 * d_ring) {
+		pr_err("%s Mismatch between ring and context timestamps!\n",
+		       engine->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int live_engine_timestamps(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/*
+	 * Check that CS_TIMESTAMP / CTX_TIMESTAMP are in sync, i.e. share
+	 * the same CS clock.
+	 */
+
+	if (INTEL_GEN(gt->i915) < 8)
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		int err;
+
+		st_engine_heartbeat_disable(engine);
+		err = __live_engine_timestamps(engine);
+		st_engine_heartbeat_enable(engine);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int live_engine_busy_stats(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -179,6 +379,7 @@ static int live_engine_pm(void *arg)
 int live_engine_pm_selftests(struct intel_gt *gt)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(live_engine_timestamps),
 		SUBTEST(live_engine_busy_stats),
 		SUBTEST(live_engine_pm),
 	};
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 11/62] drm/i915/gt: Consolidate the CS timestamp clocks

[Chris Wilson]

Pull the GT clock information [used to derive CS timestamps and PM
interval] under the GT so that is it local to the users. In doing so, we
consolidate the two references for the same information, of which the
runtime-info took note of a potential clock source override and scaling
factors.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/debugfs_gt_pm.c       |  20 +-
 drivers/gpu/drm/i915/gt/intel_context.h       |   6 +-
 drivers/gpu/drm/i915/gt/intel_gt.c            |   4 +-
 .../gpu/drm/i915/gt/intel_gt_clock_utils.c    | 197 ++++++++++++++----
 .../gpu/drm/i915/gt/intel_gt_clock_utils.h    |   8 +-
 drivers/gpu/drm/i915/gt/intel_gt_types.h      |   1 +
 drivers/gpu/drm/i915/gt/selftest_engine_pm.c  |   6 +-
 drivers/gpu/drm/i915/gt/selftest_gt_pm.c      |   8 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |  19 +-
 drivers/gpu/drm/i915/i915_drv.h               |  12 --
 drivers/gpu/drm/i915/i915_getparam.c          |   2 +-
 drivers/gpu/drm/i915/i915_gpu_error.c         |   2 +-
 drivers/gpu/drm/i915/i915_perf.c              |  11 +-
 drivers/gpu/drm/i915/intel_device_info.c      | 157 --------------
 drivers/gpu/drm/i915/intel_device_info.h      |   3 -
 drivers/gpu/drm/i915/selftests/i915_perf.c    |   2 +-
 drivers/gpu/drm/i915/selftests/i915_request.c |   3 +-
 17 files changed, 205 insertions(+), 256 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
index 8975717ace06..a0f10e8bbd21 100644
--- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -404,34 +404,34 @@ static int frequency_show(struct seq_file *m, void *unused)
 		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
-		seq_printf(m, "RP CUR UP EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR UP EI: %d (%lldns)\n",
 			   rpcurupei,
 			   intel_gt_pm_interval_to_ns(gt, rpcurupei));
-		seq_printf(m, "RP CUR UP: %d (%dns)\n",
+		seq_printf(m, "RP CUR UP: %d (%lldns)\n",
 			   rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup));
-		seq_printf(m, "RP PREV UP: %d (%dns)\n",
+		seq_printf(m, "RP PREV UP: %d (%lldns)\n",
 			   rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup));
 		seq_printf(m, "Up threshold: %d%%\n",
 			   rps->power.up_threshold);
-		seq_printf(m, "RP UP EI: %d (%dns)\n",
+		seq_printf(m, "RP UP EI: %d (%lldns)\n",
 			   rpupei, intel_gt_pm_interval_to_ns(gt, rpupei));
-		seq_printf(m, "RP UP THRESHOLD: %d (%dns)\n",
+		seq_printf(m, "RP UP THRESHOLD: %d (%lldns)\n",
 			   rpupt, intel_gt_pm_interval_to_ns(gt, rpupt));
 
-		seq_printf(m, "RP CUR DOWN EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN EI: %d (%lldns)\n",
 			   rpcurdownei,
 			   intel_gt_pm_interval_to_ns(gt, rpcurdownei));
-		seq_printf(m, "RP CUR DOWN: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN: %d (%lldns)\n",
 			   rpcurdown,
 			   intel_gt_pm_interval_to_ns(gt, rpcurdown));
-		seq_printf(m, "RP PREV DOWN: %d (%dns)\n",
+		seq_printf(m, "RP PREV DOWN: %d (%lldns)\n",
 			   rpprevdown,
 			   intel_gt_pm_interval_to_ns(gt, rpprevdown));
 		seq_printf(m, "Down threshold: %d%%\n",
 			   rps->power.down_threshold);
-		seq_printf(m, "RP DOWN EI: %d (%dns)\n",
+		seq_printf(m, "RP DOWN EI: %d (%lldns)\n",
 			   rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei));
-		seq_printf(m, "RP DOWN THRESHOLD: %d (%dns)\n",
+		seq_printf(m, "RP DOWN THRESHOLD: %d (%lldns)\n",
 			   rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt));
 
 		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index fda2eba81e22..2ce2ec639ba2 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -248,16 +248,14 @@ intel_context_clear_nopreempt(struct intel_context *ce)
 
 static inline u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
 {
-	const u32 period =
-		RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
+	const u32 period = ce->engine->gt->clock_period_ns;
 
 	return READ_ONCE(ce->runtime.total) * period;
 }
 
 static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
 {
-	const u32 period =
-		RUNTIME_INFO(ce->engine->i915)->cs_timestamp_period_ns;
+	const u32 period = ce->engine->gt->clock_period_ns;
 
 	return mul_u32_u32(ewma_runtime_read(&ce->runtime.avg), period);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 44f1d51e5ae5..d8e1ab412634 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -46,6 +46,8 @@ void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
 
 int intel_gt_init_mmio(struct intel_gt *gt)
 {
+	intel_gt_init_clock_frequency(gt);
+
 	intel_uc_init_mmio(&gt->uc);
 	intel_sseu_info_init(gt);
 
@@ -546,8 +548,6 @@ int intel_gt_init(struct intel_gt *gt)
 	 */
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 
-	intel_gt_init_clock_frequency(gt);
-
 	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
 	if (err)
 		goto out_fw;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 999079686846..a4242ca8dcd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -7,34 +7,146 @@
 #include "intel_gt.h"
 #include "intel_gt_clock_utils.h"
 
-#define MHZ_12   12000000 /* 12MHz (24MHz/2), 83.333ns */
-#define MHZ_12_5 12500000 /* 12.5MHz (25MHz/2), 80ns */
-#define MHZ_19_2 19200000 /* 19.2MHz, 52.083ns */
+static u32 read_reference_ts_freq(struct intel_uncore *uncore)
+{
+	u32 ts_override = intel_uncore_read(uncore, GEN9_TIMESTAMP_OVERRIDE);
+	u32 base_freq, frac_freq;
+
+	base_freq = ((ts_override & GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK) >>
+		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_SHIFT) + 1;
+	base_freq *= 1000000;
+
+	frac_freq = ((ts_override &
+		      GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK) >>
+		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_SHIFT);
+	frac_freq = 1000000 / (frac_freq + 1);
+
+	return base_freq + frac_freq;
+}
+
+static u32 gen10_get_crystal_clock_freq(struct intel_uncore *uncore,
+					u32 rpm_config_reg)
+{
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+	u32 crystal_clock =
+		(rpm_config_reg & GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+		GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
 
-static u32 read_clock_frequency(const struct intel_gt *gt)
+	switch (crystal_clock) {
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
+static u32 gen11_get_crystal_clock_freq(struct intel_uncore *uncore,
+					u32 rpm_config_reg)
 {
-	if (INTEL_GEN(gt->i915) >= 11) {
-		u32 config;
-
-		config = intel_uncore_read(gt->uncore, RPM_CONFIG0);
-		config &= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK;
-		config >>= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
-
-		switch (config) {
-		case 0: return MHZ_12;
-		case 1:
-		case 2: return MHZ_19_2;
-		default:
-		case 3: return MHZ_12_5;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+	u32 f25_mhz = 25000000;
+	u32 f38_4_mhz = 38400000;
+	u32 crystal_clock =
+		(rpm_config_reg & GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+		GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
+
+	switch (crystal_clock) {
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ:
+		return f38_4_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ:
+		return f25_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
+static u32 read_clock_frequency(struct intel_uncore *uncore)
+{
+	u32 f12_5_mhz = 12500000;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+
+	if (INTEL_GEN(uncore->i915) <= 4) {
+		/*
+		 * PRMs say:
+		 *
+		 *     "The value in this register increments once every 16
+		 *      hclks." (through the “Clocking Configuration”
+		 *      (“CLKCFG”) MCHBAR register)
+		 */
+		return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16;
+	} else if (INTEL_GEN(uncore->i915) <= 8) {
+		/*
+		 * PRMs say:
+		 *
+		 *     "The PCU TSC counts 10ns increments; this timestamp
+		 *      reflects bits 38:3 of the TSC (i.e. 80ns granularity,
+		 *      rolling over every 1.5 hours).
+		 */
+		return f12_5_mhz;
+	} else if (INTEL_GEN(uncore->i915) <= 9) {
+		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
+		u32 freq = 0;
+
+		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
+			freq = read_reference_ts_freq(uncore);
+		} else {
+			freq = IS_GEN9_LP(uncore->i915) ? f19_2_mhz : f24_mhz;
+
+			/*
+			 * Now figure out how the command stream's timestamp
+			 * register increments from this frequency (it might
+			 * increment only every few clock cycle).
+			 */
+			freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >>
+				      CTC_SHIFT_PARAMETER_SHIFT);
 		}
-	} else if (INTEL_GEN(gt->i915) >= 9) {
-		if (IS_GEN9_LP(gt->i915))
-			return MHZ_19_2;
-		else
-			return MHZ_12;
-	} else {
-		return MHZ_12_5;
+
+		return freq;
+	} else if (INTEL_GEN(uncore->i915) <= 12) {
+		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
+		u32 freq = 0;
+
+		/*
+		 * First figure out the reference frequency. There are 2 ways
+		 * we can compute the frequency, either through the
+		 * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE
+		 * tells us which one we should use.
+		 */
+		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
+			freq = read_reference_ts_freq(uncore);
+		} else {
+			u32 c0 = intel_uncore_read(uncore, RPM_CONFIG0);
+
+			if (INTEL_GEN(uncore->i915) <= 10)
+				freq = gen10_get_crystal_clock_freq(uncore, c0);
+			else
+				freq = gen11_get_crystal_clock_freq(uncore, c0);
+
+			/*
+			 * Now figure out how the command stream's timestamp
+			 * register increments from this frequency (it might
+			 * increment only every few clock cycle).
+			 */
+			freq >>= 3 - ((c0 & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
+				      GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT);
+		}
+
+		return freq;
 	}
+
+	MISSING_CASE("Unknown gen, unable to read command streamer timestamp frequency\n");
+	return 0;
 }
 
 void intel_gt_init_clock_frequency(struct intel_gt *gt)
@@ -43,20 +155,27 @@ void intel_gt_init_clock_frequency(struct intel_gt *gt)
 	 * Note that on gen11+, the clock frequency may be reconfigured.
 	 * We do not, and we assume nobody else does.
 	 */
-	gt->clock_frequency = read_clock_frequency(gt);
+	gt->clock_frequency = read_clock_frequency(gt->uncore);
+	if (gt->clock_frequency)
+		gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1);
+
 	GT_TRACE(gt,
-		 "Using clock frequency: %dkHz\n",
-		 gt->clock_frequency / 1000);
+		 "Using clock frequency: %dkHz, period: %dns, wrap: %lldms\n",
+		 gt->clock_frequency / 1000,
+		 gt->clock_period_ns,
+		 div_u64(mul_u32_u32(gt->clock_period_ns, S32_MAX),
+			 USEC_PER_SEC));
+
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 void intel_gt_check_clock_frequency(const struct intel_gt *gt)
 {
-	if (gt->clock_frequency != read_clock_frequency(gt)) {
+	if (gt->clock_frequency != read_clock_frequency(gt->uncore)) {
 		dev_err(gt->i915->drm.dev,
 			"GT clock frequency changed, was %uHz, now %uHz!\n",
 			gt->clock_frequency,
-			read_clock_frequency(gt));
+			read_clock_frequency(gt->uncore));
 	}
 }
 #endif
@@ -66,26 +185,24 @@ static u64 div_u64_roundup(u64 nom, u32 den)
 	return div_u64(nom + den - 1, den);
 }
 
-u32 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u32 count)
+u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
-	return div_u64_roundup(mul_u32_u32(count, 1000 * 1000 * 1000),
-			       gt->clock_frequency);
+	return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency);
 }
 
-u32 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u32 count)
+u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
 	return intel_gt_clock_interval_to_ns(gt, 16 * count);
 }
 
-u32 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u32 ns)
+u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns)
 {
-	return div_u64_roundup(mul_u32_u32(gt->clock_frequency, ns),
-			       1000 * 1000 * 1000);
+	return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC);
 }
 
-u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns)
+u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns)
 {
-	u32 val;
+	u64 val;
 
 	/*
 	 * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
@@ -94,9 +211,9 @@ u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns)
 	 * EI/thresholds are "bad", leading to a very sluggish or even
 	 * frozen machine.
 	 */
-	val = DIV_ROUND_UP(intel_gt_ns_to_clock_interval(gt, ns), 16);
+	val = div_u64_roundup(intel_gt_ns_to_clock_interval(gt, ns), 16);
 	if (IS_GEN(gt->i915, 6))
-		val = roundup(val, 25);
+		val = div_u64_roundup(val, 25) * 25;
 
 	return val;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h
index f793c89f2cbd..8b03e97a85df 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.h
@@ -18,10 +18,10 @@ void intel_gt_check_clock_frequency(const struct intel_gt *gt);
 static inline void intel_gt_check_clock_frequency(const struct intel_gt *gt) {}
 #endif
 
-u32 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u32 count);
-u32 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u32 count);
+u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count);
+u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count);
 
-u32 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u32 ns);
-u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns);
+u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns);
+u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns);
 
 #endif /* __INTEL_GT_CLOCK_UTILS_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index c7bde529feab..a83d3e18254d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -75,6 +75,7 @@ struct intel_gt {
 	intel_wakeref_t awake;
 
 	u32 clock_frequency;
+	u32 clock_period_ns;
 
 	struct intel_llc llc;
 	struct intel_rc6 rc6;
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index d88504a5d69c..ca080445695e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -156,7 +156,7 @@ static int __live_engine_timestamps(struct intel_engine_cs *engine)
 	d_ring = trifilter(s_ring);
 	d_ctx = trifilter(s_ctx);
 
-	pr_info("%s elapsed:%lldns, CTX_TIMESTAMP:%dns, RING_TIMESTAMP:%dns\n",
+	pr_info("%s elapsed:%lldns, CTX_TIMESTAMP:%lldns, RING_TIMESTAMP:%lldns\n",
 		engine->name, dt,
 		intel_gt_clock_interval_to_ns(engine->gt, d_ctx),
 		intel_gt_clock_interval_to_ns(engine->gt, d_ring));
@@ -171,11 +171,11 @@ static int __live_engine_timestamps(struct intel_engine_cs *engine)
 	d_ring = trifilter(s_ring);
 	d_ctx = trifilter(s_ctx);
 
-	d_ctx *= RUNTIME_INFO(engine->i915)->cs_timestamp_frequency_hz;
+	d_ctx *= engine->gt->clock_frequency;
 	if (IS_ICELAKE(engine->i915))
 		d_ring *= 12500000; /* Fixed 80ns for icl ctx timestamp? */
 	else
-		d_ring *= RUNTIME_INFO(engine->i915)->cs_timestamp_frequency_hz;
+		d_ring *= engine->gt->clock_frequency;
 
 	if (3 * d_ctx > 4 * d_ring || 4 * d_ctx < 3 * d_ring) {
 		pr_err("%s Mismatch between ring and context timestamps!\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index 6180a47c1b51..5d911f724ebe 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -71,7 +71,7 @@ static int live_gt_clocks(void *arg)
 	enum intel_engine_id id;
 	int err = 0;
 
-	if (!RUNTIME_INFO(gt->i915)->cs_timestamp_frequency_hz) { /* unknown */
+	if (!gt->clock_frequency) { /* unknown */
 		pr_info("CS_TIMESTAMP frequency unknown\n");
 		return 0;
 	}
@@ -112,12 +112,12 @@ static int live_gt_clocks(void *arg)
 
 		measure_clocks(engine, &cycles, &dt);
 
-		time = i915_cs_timestamp_ticks_to_ns(engine->i915, cycles);
-		expected = i915_cs_timestamp_ns_to_ticks(engine->i915, dt);
+		time = intel_gt_clock_interval_to_ns(engine->gt, cycles);
+		expected = intel_gt_ns_to_clock_interval(engine->gt, dt);
 
 		pr_info("%s: TIMESTAMP %d cycles [%lldns] in %lldns [%d cycles], using CS clock frequency of %uKHz\n",
 			engine->name, cycles, time, dt, expected,
-			RUNTIME_INFO(engine->i915)->cs_timestamp_frequency_hz / 1000);
+			engine->gt->clock_frequency / 1000);
 
 		if (9 * time < 8 * dt || 8 * time > 9 * dt) {
 			pr_err("%s: CS ticks did not match walltime!\n",
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c72160e3702f..7332478a3dd5 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -635,27 +635,27 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
-		seq_printf(m, "RP CUR UP EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR UP EI: %d (%lldns)\n",
 			   rpupei,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpupei));
-		seq_printf(m, "RP CUR UP: %d (%dun)\n",
+		seq_printf(m, "RP CUR UP: %d (%lldun)\n",
 			   rpcurup,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpcurup));
-		seq_printf(m, "RP PREV UP: %d (%dns)\n",
+		seq_printf(m, "RP PREV UP: %d (%lldns)\n",
 			   rpprevup,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpprevup));
 		seq_printf(m, "Up threshold: %d%%\n",
 			   rps->power.up_threshold);
 
-		seq_printf(m, "RP CUR DOWN EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN EI: %d (%lldns)\n",
 			   rpdownei,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpdownei));
-		seq_printf(m, "RP CUR DOWN: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN: %d (%lldns)\n",
 			   rpcurdown,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpcurdown));
-		seq_printf(m, "RP PREV DOWN: %d (%dns)\n",
+		seq_printf(m, "RP PREV DOWN: %d (%lldns)\n",
 			   rpprevdown,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpprevdown));
@@ -862,8 +862,9 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 		   yesno(i915->gt.awake),
 		   atomic_read(&i915->gt.wakeref.count),
 		   ktime_to_ms(intel_gt_get_awake_time(&i915->gt)));
-	seq_printf(m, "CS timestamp frequency: %u Hz\n",
-		   RUNTIME_INFO(i915)->cs_timestamp_frequency_hz);
+	seq_printf(m, "CS timestamp frequency: %u Hz, %d ns\n",
+		   i915->gt.clock_frequency,
+		   i915->gt.clock_period_ns);
 
 	p = drm_seq_file_printer(m);
 	for_each_uabi_engine(engine, i915)
@@ -949,7 +950,7 @@ i915_perf_noa_delay_set(void *data, u64 val)
 	 * This would lead to infinite waits as we're doing timestamp
 	 * difference on the CS with only 32bits.
 	 */
-	if (i915_cs_timestamp_ns_to_ticks(i915, val) > U32_MAX)
+	if (intel_gt_ns_to_clock_interval(&i915->gt, val) > U32_MAX)
 		return -EINVAL;
 
 	atomic64_set(&i915->perf.noa_programming_delay, val);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a8ff2a899a5..e38a10d5c128 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2003,16 +2003,4 @@ i915_coherent_map_type(struct drm_i915_private *i915)
 	return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
 }
 
-static inline u64 i915_cs_timestamp_ns_to_ticks(struct drm_i915_private *i915, u64 val)
-{
-	return DIV_ROUND_UP_ULL(val * RUNTIME_INFO(i915)->cs_timestamp_frequency_hz,
-				1000000000);
-}
-
-static inline u64 i915_cs_timestamp_ticks_to_ns(struct drm_i915_private *i915, u64 val)
-{
-	return div_u64(val * 1000000000,
-		       RUNTIME_INFO(i915)->cs_timestamp_frequency_hz);
-}
-
 #endif
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index f96032c60a12..75c3bfc2486e 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -154,7 +154,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			return -ENODEV;
 		break;
 	case I915_PARAM_CS_TIMESTAMP_FREQUENCY:
-		value = RUNTIME_INFO(i915)->cs_timestamp_frequency_hz;
+		value = i915->gt.clock_frequency;
 		break;
 	case I915_PARAM_MMAP_GTT_COHERENT:
 		value = INTEL_INFO(i915)->has_coherent_ggtt;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d8cac4c5881f..8b163ee1b86d 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -485,7 +485,7 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
 				const struct i915_gem_context_coredump *ctx)
 {
-	const u32 period = RUNTIME_INFO(m->i915)->cs_timestamp_period_ns;
+	const u32 period = m->i915->gt.clock_period_ns;
 
 	err_printf(m, "%s%s[%d] prio %d, guilty %d active %d, runtime total %lluns, avg %lluns\n",
 		   header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index f65c32bd970e..112ba5f2ce90 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -201,6 +201,7 @@
 #include "gt/intel_execlists_submission.h"
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_clock_utils.h"
 #include "gt/intel_lrc.h"
 #include "gt/intel_ring.h"
 
@@ -1637,7 +1638,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	const u64 delay_ticks = 0xffffffffffffffff -
-		i915_cs_timestamp_ns_to_ticks(i915, atomic64_read(&stream->perf->noa_programming_delay));
+		intel_gt_ns_to_clock_interval(stream->perf->i915->ggtt.vm.gt,
+					      atomic64_read(&stream->perf->noa_programming_delay));
 	const u32 base = stream->engine->mmio_base;
 #define CS_GPR(x) GEN8_RING_CS_GPR(base, x)
 	u32 *batch, *ts0, *cs, *jump;
@@ -3518,7 +3520,8 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 
 static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
 {
-	return i915_cs_timestamp_ticks_to_ns(perf->i915, 2ULL << exponent);
+	return intel_gt_clock_interval_to_ns(perf->i915->ggtt.vm.gt,
+					     2ULL << exponent);
 }
 
 /**
@@ -4372,8 +4375,8 @@ void i915_perf_init(struct drm_i915_private *i915)
 	if (perf->ops.enable_metric_set) {
 		mutex_init(&perf->lock);
 
-		oa_sample_rate_hard_limit =
-			RUNTIME_INFO(i915)->cs_timestamp_frequency_hz / 2;
+		/* Choose a representative limit */
+		oa_sample_rate_hard_limit = i915->gt.clock_frequency / 2;
 
 		mutex_init(&perf->metrics_lock);
 		idr_init_base(&perf->metrics_idr, 1);
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index ef767f04c37c..f2d5ae59081e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -117,150 +117,6 @@ void intel_device_info_print_runtime(const struct intel_runtime_info *info,
 				     struct drm_printer *p)
 {
 	drm_printf(p, "rawclk rate: %u kHz\n", info->rawclk_freq);
-	drm_printf(p, "CS timestamp frequency: %u Hz\n",
-		   info->cs_timestamp_frequency_hz);
-}
-
-static u32 read_reference_ts_freq(struct drm_i915_private *dev_priv)
-{
-	u32 ts_override = intel_uncore_read(&dev_priv->uncore,
-					    GEN9_TIMESTAMP_OVERRIDE);
-	u32 base_freq, frac_freq;
-
-	base_freq = ((ts_override & GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK) >>
-		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_SHIFT) + 1;
-	base_freq *= 1000000;
-
-	frac_freq = ((ts_override &
-		      GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK) >>
-		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_SHIFT);
-	frac_freq = 1000000 / (frac_freq + 1);
-
-	return base_freq + frac_freq;
-}
-
-static u32 gen10_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
-					u32 rpm_config_reg)
-{
-	u32 f19_2_mhz = 19200000;
-	u32 f24_mhz = 24000000;
-	u32 crystal_clock = (rpm_config_reg &
-			     GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
-			    GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
-
-	switch (crystal_clock) {
-	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
-		return f19_2_mhz;
-	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
-		return f24_mhz;
-	default:
-		MISSING_CASE(crystal_clock);
-		return 0;
-	}
-}
-
-static u32 gen11_get_crystal_clock_freq(struct drm_i915_private *dev_priv,
-					u32 rpm_config_reg)
-{
-	u32 f19_2_mhz = 19200000;
-	u32 f24_mhz = 24000000;
-	u32 f25_mhz = 25000000;
-	u32 f38_4_mhz = 38400000;
-	u32 crystal_clock = (rpm_config_reg &
-			     GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
-			    GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
-
-	switch (crystal_clock) {
-	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
-		return f24_mhz;
-	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
-		return f19_2_mhz;
-	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ:
-		return f38_4_mhz;
-	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ:
-		return f25_mhz;
-	default:
-		MISSING_CASE(crystal_clock);
-		return 0;
-	}
-}
-
-static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv)
-{
-	struct intel_uncore *uncore = &dev_priv->uncore;
-	u32 f12_5_mhz = 12500000;
-	u32 f19_2_mhz = 19200000;
-	u32 f24_mhz = 24000000;
-
-	if (INTEL_GEN(dev_priv) <= 4) {
-		/* PRMs say:
-		 *
-		 *     "The value in this register increments once every 16
-		 *      hclks." (through the “Clocking Configuration”
-		 *      (“CLKCFG”) MCHBAR register)
-		 */
-		return RUNTIME_INFO(dev_priv)->rawclk_freq * 1000 / 16;
-	} else if (INTEL_GEN(dev_priv) <= 8) {
-		/* PRMs say:
-		 *
-		 *     "The PCU TSC counts 10ns increments; this timestamp
-		 *      reflects bits 38:3 of the TSC (i.e. 80ns granularity,
-		 *      rolling over every 1.5 hours).
-		 */
-		return f12_5_mhz;
-	} else if (INTEL_GEN(dev_priv) <= 9) {
-		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
-		u32 freq = 0;
-
-		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
-			freq = read_reference_ts_freq(dev_priv);
-		} else {
-			freq = IS_GEN9_LP(dev_priv) ? f19_2_mhz : f24_mhz;
-
-			/* Now figure out how the command stream's timestamp
-			 * register increments from this frequency (it might
-			 * increment only every few clock cycle).
-			 */
-			freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >>
-				      CTC_SHIFT_PARAMETER_SHIFT);
-		}
-
-		return freq;
-	} else if (INTEL_GEN(dev_priv) <= 12) {
-		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
-		u32 freq = 0;
-
-		/* First figure out the reference frequency. There are 2 ways
-		 * we can compute the frequency, either through the
-		 * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE
-		 * tells us which one we should use.
-		 */
-		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
-			freq = read_reference_ts_freq(dev_priv);
-		} else {
-			u32 rpm_config_reg = intel_uncore_read(uncore, RPM_CONFIG0);
-
-			if (INTEL_GEN(dev_priv) <= 10)
-				freq = gen10_get_crystal_clock_freq(dev_priv,
-								rpm_config_reg);
-			else
-				freq = gen11_get_crystal_clock_freq(dev_priv,
-								rpm_config_reg);
-
-			/* Now figure out how the command stream's timestamp
-			 * register increments from this frequency (it might
-			 * increment only every few clock cycle).
-			 */
-			freq >>= 3 - ((rpm_config_reg &
-				       GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
-				      GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT);
-		}
-
-		return freq;
-	}
-
-	MISSING_CASE("Unknown gen, unable to read command streamer timestamp frequency\n");
-	return 0;
 }
 
 #undef INTEL_VGA_DEVICE
@@ -505,19 +361,6 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 	runtime->rawclk_freq = intel_read_rawclk(dev_priv);
 	drm_dbg(&dev_priv->drm, "rawclk rate: %d kHz\n", runtime->rawclk_freq);
 
-	/* Initialize command stream timestamp frequency */
-	runtime->cs_timestamp_frequency_hz =
-		read_timestamp_frequency(dev_priv);
-	if (runtime->cs_timestamp_frequency_hz) {
-		runtime->cs_timestamp_period_ns =
-			i915_cs_timestamp_ticks_to_ns(dev_priv, 1);
-		drm_dbg(&dev_priv->drm,
-			"CS timestamp wraparound in %lldms\n",
-			div_u64(mul_u32_u32(runtime->cs_timestamp_period_ns,
-					    S32_MAX),
-				USEC_PER_SEC));
-	}
-
 	if (!HAS_DISPLAY(dev_priv)) {
 		dev_priv->drm.driver_features &= ~(DRIVER_MODESET |
 						   DRIVER_ATOMIC);
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index d92fa041c700..17d0fdb94d2d 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -224,9 +224,6 @@ struct intel_runtime_info {
 	u8 num_scalers[I915_MAX_PIPES];
 
 	u32 rawclk_freq;
-
-	u32 cs_timestamp_frequency_hz;
-	u32 cs_timestamp_period_ns;
 };
 
 struct intel_driver_caps {
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index debbac660519..e9d86dab8677 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -262,7 +262,7 @@ static int live_noa_delay(void *arg)
 
 	delay = intel_read_status_page(stream->engine, 0x102);
 	delay -= intel_read_status_page(stream->engine, 0x100);
-	delay = i915_cs_timestamp_ticks_to_ns(i915, delay);
+	delay = intel_gt_clock_interval_to_ns(stream->engine->gt, delay);
 	pr_info("GPU delay: %uns, expected %lluns\n",
 		delay, expected);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index b8c5920d1ff3..d2a678a2497e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -33,6 +33,7 @@
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_clock_utils.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/selftest_engine_heartbeat.h"
 
@@ -1560,7 +1561,7 @@ static u32 trifilter(u32 *a)
 
 static u64 cycles_to_ns(struct intel_engine_cs *engine, u32 cycles)
 {
-	u64 ns = i915_cs_timestamp_ticks_to_ns(engine->i915, cycles);
+	u64 ns = intel_gt_clock_interval_to_ns(engine->gt, cycles);
 
 	return DIV_ROUND_CLOSEST(ns, 1 << TF_BIAS);
 }
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 12/62] drm/i915: Drop i915_request.lock serialisation around await_start

[Chris Wilson]

Originally, we used the signal->lock as a means of following the
previous link in its timeline and peeking at the previous fence.
However, we have replaced the explicit serialisation with a series of
very careful probes that anticipate the links being deleted and the
fences recycled before we are able to acquire a strong reference to it.
We do not need the signal->lock crutch anymore, nor want the contention.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_request.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 6578faf6eed8..33c4f6f7024a 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -963,9 +963,16 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	if (i915_request_started(signal))
 		return 0;
 
+	/*
+	 * The caller holds a reference on @signal, but we do not serialise
+	 * against it being retired and removed from the lists.
+	 *
+	 * We do not hold a reference to the request before @signal, and
+	 * so must be very careful to ensure that it is not _recycled_ as
+	 * we follow the link backwards.
+	 */
 	fence = NULL;
 	rcu_read_lock();
-	spin_lock_irq(&signal->lock);
 	do {
 		struct list_head *pos = READ_ONCE(signal->link.prev);
 		struct i915_request *prev;
@@ -996,7 +1003,6 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 
 		fence = &prev->fence;
 	} while (0);
-	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
 		return 0;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 13/62] drm/i915: Drop i915_request.lock requirement for intel_rps_boost()

[Chris Wilson]

Since we use a flag within i915_request.flags to indicate when we have
boosted the request (so that we only apply the boost) once, this can be
used as the serialisation with i915_request_retire() to avoid having to
explicitly take the i915_request.lock which is more heavily contended.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_rps.c | 15 ++++++---------
 drivers/gpu/drm/i915/i915_request.c |  4 +---
 2 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index f74d5e09e176..e1397b8d3586 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -917,17 +917,15 @@ void intel_rps_park(struct intel_rps *rps)
 
 void intel_rps_boost(struct i915_request *rq)
 {
-	struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
-	unsigned long flags;
-
-	if (i915_request_signaled(rq) || !intel_rps_is_active(rps))
+	if (i915_request_signaled(rq) || i915_request_has_waitboost(rq))
 		return;
 
 	/* Serializes with i915_request_retire() */
-	spin_lock_irqsave(&rq->lock, flags);
-	if (!i915_request_has_waitboost(rq) &&
-	    !dma_fence_is_signaled_locked(&rq->fence)) {
-		set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
+	if (!test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) {
+		struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
+
+		if (!intel_rps_is_active(rps))
+			return;
 
 		GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
 			 rq->fence.context, rq->fence.seqno);
@@ -938,7 +936,6 @@ void intel_rps_boost(struct i915_request *rq)
 
 		atomic_inc(&rps->boosts);
 	}
-	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 int intel_rps_set(struct intel_rps *rps, u8 val)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 33c4f6f7024a..b5de7cf8585b 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -307,10 +307,8 @@ bool i915_request_retire(struct i915_request *rq)
 		spin_unlock_irq(&rq->lock);
 	}
 
-	if (i915_request_has_waitboost(rq)) {
-		GEM_BUG_ON(!atomic_read(&rq->engine->gt->rps.num_waiters));
+	if (test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags))
 		atomic_dec(&rq->engine->gt->rps.num_waiters);
-	}
 
 	/*
 	 * We only loosely track inflight requests across preemption,
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 14/62] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source

[Chris Wilson]

When cloning the engines from the source context, we need to ensure that
the engines are not freed as we copy them, and that the flags we clone
from the source correspond with the engines we copy across. To do this
we need only take a reference to the src->engines, rather than hold the
src->engine_mutex, so long as we verify that nothing changed under the
read.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 24 +++++++++++++--------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index c7363036765a..d117fc039702 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -714,7 +714,8 @@ __create_context(struct drm_i915_private *i915)
 }
 
 static inline struct i915_gem_engines *
-__context_engines_await(const struct i915_gem_context *ctx)
+__context_engines_await(const struct i915_gem_context *ctx,
+			bool *user_engines)
 {
 	struct i915_gem_engines *engines;
 
@@ -723,6 +724,10 @@ __context_engines_await(const struct i915_gem_context *ctx)
 		engines = rcu_dereference(ctx->engines);
 		GEM_BUG_ON(!engines);
 
+		if (user_engines)
+			*user_engines = i915_gem_context_user_engines(ctx);
+
+		/* successful await => strong mb */
 		if (unlikely(!i915_sw_fence_await(&engines->fence)))
 			continue;
 
@@ -746,7 +751,7 @@ context_apply_all(struct i915_gem_context *ctx,
 	struct intel_context *ce;
 	int err = 0;
 
-	e = __context_engines_await(ctx);
+	e = __context_engines_await(ctx, NULL);
 	for_each_gem_engine(ce, e, it) {
 		err = fn(ce, data);
 		if (err)
@@ -1072,7 +1077,7 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 		return err;
 	}
 
-	e = __context_engines_await(ctx);
+	e = __context_engines_await(ctx, NULL);
 	if (!e) {
 		i915_active_release(&cb->base);
 		return -ENOENT;
@@ -2092,11 +2097,14 @@ static int copy_ring_size(struct intel_context *dst,
 static int clone_engines(struct i915_gem_context *dst,
 			 struct i915_gem_context *src)
 {
-	struct i915_gem_engines *e = i915_gem_context_lock_engines(src);
-	struct i915_gem_engines *clone;
+	struct i915_gem_engines *clone, *e;
 	bool user_engines;
 	unsigned long n;
 
+	e = __context_engines_await(src, &user_engines);
+	if (!e)
+		return -ENOENT;
+
 	clone = alloc_engines(e->num_engines);
 	if (!clone)
 		goto err_unlock;
@@ -2138,9 +2146,7 @@ static int clone_engines(struct i915_gem_context *dst,
 		}
 	}
 	clone->num_engines = n;
-
-	user_engines = i915_gem_context_user_engines(src);
-	i915_gem_context_unlock_engines(src);
+	i915_sw_fence_complete(&e->fence);
 
 	/* Serialised by constructor */
 	engines_idle_release(dst, rcu_replace_pointer(dst->engines, clone, 1));
@@ -2151,7 +2157,7 @@ static int clone_engines(struct i915_gem_context *dst,
 	return 0;
 
 err_unlock:
-	i915_gem_context_unlock_engines(src);
+	i915_sw_fence_complete(&e->fence);
 	return -ENOMEM;
 }
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 15/62] drm/i915/gem: Reduce ctx->engines_mutex for get_engines()

[Chris Wilson]

Take a snapshot of the ctx->engines, so we can avoid taking the
ctx->engines_mutex for a mere read in get_engines().

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 39 +++++----------------
 1 file changed, 8 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index d117fc039702..db8901cc2c8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1840,27 +1840,6 @@ set_engines(struct i915_gem_context *ctx,
 	return 0;
 }
 
-static struct i915_gem_engines *
-__copy_engines(struct i915_gem_engines *e)
-{
-	struct i915_gem_engines *copy;
-	unsigned int n;
-
-	copy = alloc_engines(e->num_engines);
-	if (!copy)
-		return ERR_PTR(-ENOMEM);
-
-	for (n = 0; n < e->num_engines; n++) {
-		if (e->engines[n])
-			copy->engines[n] = intel_context_get(e->engines[n]);
-		else
-			copy->engines[n] = NULL;
-	}
-	copy->num_engines = n;
-
-	return copy;
-}
-
 static int
 get_engines(struct i915_gem_context *ctx,
 	    struct drm_i915_gem_context_param *args)
@@ -1868,19 +1847,17 @@ get_engines(struct i915_gem_context *ctx,
 	struct i915_context_param_engines __user *user;
 	struct i915_gem_engines *e;
 	size_t n, count, size;
+	bool user_engines;
 	int err = 0;
 
-	err = mutex_lock_interruptible(&ctx->engines_mutex);
-	if (err)
-		return err;
+	e = __context_engines_await(ctx, &user_engines);
+	if (!e)
+		return -ENOENT;
 
-	e = NULL;
-	if (i915_gem_context_user_engines(ctx))
-		e = __copy_engines(i915_gem_context_engines(ctx));
-	mutex_unlock(&ctx->engines_mutex);
-	if (IS_ERR_OR_NULL(e)) {
+	if (!user_engines) {
+		i915_sw_fence_complete(&e->fence);
 		args->size = 0;
-		return PTR_ERR_OR_ZERO(e);
+		return 0;
 	}
 
 	count = e->num_engines;
@@ -1931,7 +1908,7 @@ get_engines(struct i915_gem_context *ctx,
 	args->size = size;
 
 err_free:
-	free_engines(e);
+	i915_sw_fence_complete(&e->fence);
 	return err;
 }
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 16/62] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()

[Chris Wilson]

Avoid the full blown memory barrier of test_and_set_bit() by noting the
completed request and removing it from the lists.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_request.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index b5de7cf8585b..2ed8cb0d248f 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -539,8 +539,10 @@ bool __i915_request_submit(struct i915_request *request)
 	 * dropped upon retiring. (Otherwise if resubmit a *retired*
 	 * request, this would be a horrible use-after-free.)
 	 */
-	if (i915_request_completed(request))
-		goto xfer;
+	if (i915_request_completed(request)) {
+		list_del_init(&request->sched.link);
+		goto active;
+	}
 
 	if (unlikely(intel_context_is_closed(request->context) &&
 		     !intel_engine_has_heartbeat(engine)))
@@ -579,11 +581,11 @@ bool __i915_request_submit(struct i915_request *request)
 	engine->serial++;
 	result = true;
 
-xfer:
-	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) {
-		list_move_tail(&request->sched.link, &engine->active.requests);
-		clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
-	}
+	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
+	list_move_tail(&request->sched.link, &engine->active.requests);
+active:
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
+	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
 
 	/*
 	 * XXX Rollback bonded-execution on __i915_request_unsubmit()?
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 17/62] drm/i915/gt: Drop atomic for engine->fw_active tracking

[Chris Wilson]

Since schedule-in/out is now entirely serialised by the tasklet bitlock,
we do not need to worry about concurrent in/out operations and so reduce
the atomic operations to plain instructions.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c            | 2 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h         | 2 +-
 drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 1847d3c2ea99..dd6c0d67d189 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1657,7 +1657,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   ktime_to_ms(intel_engine_get_busy_time(engine,
 								  &dummy)));
 	drm_printf(m, "\tForcewake: %x domains, %d active\n",
-		   engine->fw_domain, atomic_read(&engine->fw_active));
+		   engine->fw_domain, READ_ONCE(engine->fw_active));
 
 	rcu_read_lock();
 	rq = READ_ONCE(engine->heartbeat.systole);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index c28f4e190fe6..1fbee35cb5ad 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -329,7 +329,7 @@ struct intel_engine_cs {
 	 * as possible.
 	 */
 	enum forcewake_domains fw_domain;
-	atomic_t fw_active;
+	unsigned int fw_active;
 
 	unsigned long context_tag;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 1fae6c6f3868..2025e74958e6 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -536,7 +536,7 @@ __execlists_schedule_in(struct i915_request *rq)
 	ce->lrc.ccid |= engine->execlists.ccid;
 
 	__intel_gt_pm_get(engine->gt);
-	if (engine->fw_domain && !atomic_fetch_inc(&engine->fw_active))
+	if (engine->fw_domain && !engine->fw_active++)
 		intel_uncore_forcewake_get(engine->uncore, engine->fw_domain);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -647,7 +647,7 @@ static inline void __execlists_schedule_out(struct i915_request *rq)
 	lrc_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
-	if (engine->fw_domain && !atomic_dec_return(&engine->fw_active))
+	if (engine->fw_domain && !--engine->fw_active)
 		intel_uncore_forcewake_put(engine->uncore, engine->fw_domain);
 	intel_gt_pm_put_async(engine->gt);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 18/62] drm/i915/gt: Extract busy-stats for ring-scheduler

[Chris Wilson]

Lift the busy-stats context-in/out implementation out of intel_lrc, so
that we can reuse it for other scheduler implementations.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_stats.h  | 49 +++++++++++++++++++
 .../drm/i915/gt/intel_execlists_submission.c  | 34 +------------
 2 files changed, 50 insertions(+), 33 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_engine_stats.h

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_stats.h b/drivers/gpu/drm/i915/gt/intel_engine_stats.h
new file mode 100644
index 000000000000..58491eae3482
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_engine_stats.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_ENGINE_STATS_H__
+#define __INTEL_ENGINE_STATS_H__
+
+#include <linux/atomic.h>
+#include <linux/ktime.h>
+#include <linux/seqlock.h>
+
+#include "i915_gem.h" /* GEM_BUG_ON */
+#include "intel_engine.h"
+
+static inline void intel_engine_context_in(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (atomic_add_unless(&engine->stats.active, 1, 0))
+		return;
+
+	write_seqlock_irqsave(&engine->stats.lock, flags);
+	if (!atomic_add_unless(&engine->stats.active, 1, 0)) {
+		engine->stats.start = ktime_get();
+		atomic_inc(&engine->stats.active);
+	}
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+}
+
+static inline void intel_engine_context_out(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	GEM_BUG_ON(!atomic_read(&engine->stats.active));
+
+	if (atomic_add_unless(&engine->stats.active, -1, 1))
+		return;
+
+	write_seqlock_irqsave(&engine->stats.lock, flags);
+	if (atomic_dec_and_test(&engine->stats.active)) {
+		engine->stats.total =
+			ktime_add(engine->stats.total,
+				  ktime_sub(ktime_get(), engine->stats.start));
+	}
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+}
+
+#endif /* __INTEL_ENGINE_STATS_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2025e74958e6..7d411d7eb0d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -115,6 +115,7 @@
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
+#include "intel_engine_stats.h"
 #include "intel_execlists_submission.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -433,39 +434,6 @@ execlists_context_status_change(struct i915_request *rq, unsigned long status)
 				   status, rq);
 }
 
-static void intel_engine_context_in(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	if (atomic_add_unless(&engine->stats.active, 1, 0))
-		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (!atomic_add_unless(&engine->stats.active, 1, 0)) {
-		engine->stats.start = ktime_get();
-		atomic_inc(&engine->stats.active);
-	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-}
-
-static void intel_engine_context_out(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	GEM_BUG_ON(!atomic_read(&engine->stats.active));
-
-	if (atomic_add_unless(&engine->stats.active, -1, 1))
-		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (atomic_dec_and_test(&engine->stats.active)) {
-		engine->stats.total =
-			ktime_add(engine->stats.total,
-				  ktime_sub(ktime_get(), engine->stats.start));
-	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-}
-
 static void reset_active(struct i915_request *rq,
 			 struct intel_engine_cs *engine)
 {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 19/62] drm/i915/gt: Convert stats.active to plain unsigned int

[Chris Wilson]

As context-in/out is now always serialised, we do not have to worry
about concurrent enabling/disable of the busy-stats and can reduce the
atomic_t active to a plain unsigned int, and the seqlock to a seqcount.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  8 ++--
 drivers/gpu/drm/i915/gt/intel_engine_stats.h | 45 ++++++++++++--------
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  4 +-
 3 files changed, 34 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index dd6c0d67d189..75911dd0483e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -341,7 +341,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->schedule = NULL;
 
 	ewma__engine_latency_init(&engine->latency);
-	seqlock_init(&engine->stats.lock);
+	seqcount_init(&engine->stats.lock);
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
@@ -1735,7 +1735,7 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine,
 	 * add it to the total.
 	 */
 	*now = ktime_get();
-	if (atomic_read(&engine->stats.active))
+	if (READ_ONCE(engine->stats.active))
 		total = ktime_add(total, ktime_sub(*now, engine->stats.start));
 
 	return total;
@@ -1754,9 +1754,9 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 	ktime_t total;
 
 	do {
-		seq = read_seqbegin(&engine->stats.lock);
+		seq = read_seqcount_begin(&engine->stats.lock);
 		total = __intel_engine_get_busy_time(engine, now);
-	} while (read_seqretry(&engine->stats.lock, seq));
+	} while (read_seqcount_retry(&engine->stats.lock, seq));
 
 	return total;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_stats.h b/drivers/gpu/drm/i915/gt/intel_engine_stats.h
index 58491eae3482..24fbdd94351a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_stats.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_stats.h
@@ -17,33 +17,44 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	if (atomic_add_unless(&engine->stats.active, 1, 0))
+	if (engine->stats.active) {
+		engine->stats.active++;
 		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (!atomic_add_unless(&engine->stats.active, 1, 0)) {
-		engine->stats.start = ktime_get();
-		atomic_inc(&engine->stats.active);
 	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+
+	/* The writer is serialised; but the pmu reader may be from hardirq */
+	local_irq_save(flags);
+	write_seqcount_begin(&engine->stats.lock);
+
+	engine->stats.start = ktime_get();
+	engine->stats.active++;
+
+	write_seqcount_end(&engine->stats.lock);
+	local_irq_restore(flags);
+
+	GEM_BUG_ON(!engine->stats.active);
 }
 
 static inline void intel_engine_context_out(struct intel_engine_cs *engine)
 {
 	unsigned long flags;
 
-	GEM_BUG_ON(!atomic_read(&engine->stats.active));
-
-	if (atomic_add_unless(&engine->stats.active, -1, 1))
+	GEM_BUG_ON(!engine->stats.active);
+	if (engine->stats.active > 1) {
+		engine->stats.active--;
 		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-	if (atomic_dec_and_test(&engine->stats.active)) {
-		engine->stats.total =
-			ktime_add(engine->stats.total,
-				  ktime_sub(ktime_get(), engine->stats.start));
 	}
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+
+	local_irq_save(flags);
+	write_seqcount_begin(&engine->stats.lock);
+
+	engine->stats.active--;
+	engine->stats.total =
+		ktime_add(engine->stats.total,
+			  ktime_sub(ktime_get(), engine->stats.start));
+
+	write_seqcount_end(&engine->stats.lock);
+	local_irq_restore(flags);
 }
 
 #endif /* __INTEL_ENGINE_STATS_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 1fbee35cb5ad..fdec129a6317 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -526,12 +526,12 @@ struct intel_engine_cs {
 		/**
 		 * @active: Number of contexts currently scheduled in.
 		 */
-		atomic_t active;
+		unsigned int active;
 
 		/**
 		 * @lock: Lock protecting the below fields.
 		 */
-		seqlock_t lock;
+		seqcount_t lock;
 
 		/**
 		 * @total: Total time this engine was busy.
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 20/62] drm/i915/gt: Refactor heartbeat request construction and submission

[Chris Wilson]

Pull the individual strands of creating a custom heartbeat requests into
a pair of common functions. This will reduce the number of changes we
will need to make in future.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  | 59 +++++++++++++------
 1 file changed, 41 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 9060385cd69e..d7be2b9339f9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -37,6 +37,18 @@ static bool next_heartbeat(struct intel_engine_cs *engine)
 	return true;
 }
 
+static struct i915_request *
+heartbeat_create(struct intel_context *ce, gfp_t gfp)
+{
+	struct i915_request *rq;
+
+	intel_context_enter(ce);
+	rq = __i915_request_create(ce, gfp);
+	intel_context_exit(ce);
+
+	return rq;
+}
+
 static void idle_pulse(struct intel_engine_cs *engine, struct i915_request *rq)
 {
 	engine->wakeref_serial = READ_ONCE(engine->serial) + 1;
@@ -45,6 +57,15 @@ static void idle_pulse(struct intel_engine_cs *engine, struct i915_request *rq)
 		engine->heartbeat.systole = i915_request_get(rq);
 }
 
+static void heartbeat_commit(struct i915_request *rq,
+			     const struct i915_sched_attr *attr)
+{
+	idle_pulse(rq->engine, rq);
+
+	__i915_request_commit(rq);
+	__i915_request_queue(rq, attr);
+}
+
 static void show_heartbeat(const struct i915_request *rq,
 			   struct intel_engine_cs *engine)
 {
@@ -139,16 +160,11 @@ static void heartbeat(struct work_struct *wrk)
 		goto out;
 	}
 
-	intel_context_enter(ce);
-	rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN);
-	intel_context_exit(ce);
+	rq = heartbeat_create(ce, GFP_NOWAIT | __GFP_NOWARN);
 	if (IS_ERR(rq))
 		goto unlock;
 
-	idle_pulse(engine, rq);
-
-	__i915_request_commit(rq);
-	__i915_request_queue(rq, &attr);
+	heartbeat_commit(rq, &attr);
 
 unlock:
 	mutex_unlock(&ce->timeline->mutex);
@@ -187,17 +203,13 @@ static int __intel_engine_pulse(struct intel_engine_cs *engine)
 	GEM_BUG_ON(!intel_engine_has_preemption(engine));
 	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 
-	intel_context_enter(ce);
-	rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN);
-	intel_context_exit(ce);
+	rq = heartbeat_create(ce, GFP_NOWAIT | __GFP_NOWARN);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
 	__set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
-	idle_pulse(engine, rq);
 
-	__i915_request_commit(rq);
-	__i915_request_queue(rq, &attr);
+	heartbeat_commit(rq, &attr);
 	GEM_BUG_ON(rq->sched.attr.priority < I915_PRIORITY_BARRIER);
 
 	return 0;
@@ -273,8 +285,12 @@ int intel_engine_pulse(struct intel_engine_cs *engine)
 
 int intel_engine_flush_barriers(struct intel_engine_cs *engine)
 {
+	struct i915_sched_attr attr = {
+		.priority = I915_USER_PRIORITY(I915_PRIORITY_MIN),
+	};
+	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
-	int err = 0;
+	int err;
 
 	if (llist_empty(&engine->barrier_tasks))
 		return 0;
@@ -282,15 +298,22 @@ int intel_engine_flush_barriers(struct intel_engine_cs *engine)
 	if (!intel_engine_pm_get_if_awake(engine))
 		return 0;
 
-	rq = i915_request_create(engine->kernel_context);
+	if (mutex_lock_interruptible(&ce->timeline->mutex)) {
+		err = -EINTR;
+		goto out_rpm;
+	}
+
+	rq = heartbeat_create(ce, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
-		goto out_rpm;
+		goto out_unlock;
 	}
 
-	idle_pulse(engine, rq);
-	i915_request_add(rq);
+	heartbeat_commit(rq, &attr);
 
+	err = 0;
+out_unlock:
+	mutex_unlock(&ce->timeline->mutex);
 out_rpm:
 	intel_engine_pm_put(engine);
 	return err;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 21/62] drm/i915/gt: Do not suspend bonded requests if one hangs

[Chris Wilson]

Treat the dependency between bonded requests as weak and leave the
remainder of the pair on the GPU if one hangs.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 7d411d7eb0d2..fe16a7453f9b 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1981,6 +1981,9 @@ static void __execlists_hold(struct i915_request *rq)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
 			/* Leave semaphores spinning on the other engines */
 			if (w->engine != rq->engine)
 				continue;
@@ -2079,6 +2082,9 @@ static void __execlists_unhold(struct i915_request *rq)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
 			/* Propagate any change in error status */
 			if (rq->fence.error)
 				i915_request_set_error_once(w, rq->fence.error);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 22/62] drm/i915/gt: Remove timeslice suppression

[Chris Wilson]

In the next patch, we remove the strict priority system and continuously
re-evaluate the relative priority of tasks. As such we need to enable
the timeslice whenever there is more than one context in the pipeline.
This simplifies the decision and removes some of the tweaks to suppress
timeslicing, allowing us to lift the timeslice enabling to a common spot
at the end of running the submission tasklet.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |  10 --
 .../drm/i915/gt/intel_execlists_submission.c  | 149 +++++++-----------
 2 files changed, 53 insertions(+), 106 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index fdec129a6317..f850179a583f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -238,16 +238,6 @@ struct intel_engine_execlists {
 	 */
 	unsigned int port_mask;
 
-	/**
-	 * @switch_priority_hint: Second context priority.
-	 *
-	 * We submit multiple contexts to the HW simultaneously and would
-	 * like to occasionally switch between them to emulate timeslicing.
-	 * To know when timeslicing is suitable, we track the priority of
-	 * the context submitted second.
-	 */
-	int switch_priority_hint;
-
 	/**
 	 * @queue_priority_hint: Highest pending priority.
 	 *
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index fe16a7453f9b..ebe81fe987f0 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1099,25 +1099,6 @@ static void defer_active(struct intel_engine_cs *engine)
 	defer_request(rq, i915_sched_lookup_priolist(engine, rq_prio(rq)));
 }
 
-static bool
-need_timeslice(const struct intel_engine_cs *engine,
-	       const struct i915_request *rq)
-{
-	int hint;
-
-	if (!intel_engine_has_timeslices(engine))
-		return false;
-
-	hint = max(engine->execlists.queue_priority_hint,
-		   virtual_prio(&engine->execlists));
-
-	if (!list_is_last(&rq->sched.link, &engine->active.requests))
-		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
-
-	GEM_BUG_ON(hint >= I915_PRIORITY_UNPREEMPTABLE);
-	return hint >= effective_prio(rq);
-}
-
 static bool
 timeslice_yield(const struct intel_engine_execlists *el,
 		const struct i915_request *rq)
@@ -1137,76 +1118,63 @@ timeslice_yield(const struct intel_engine_execlists *el,
 	return rq->context->lrc.ccid == READ_ONCE(el->yield);
 }
 
-static bool
-timeslice_expired(const struct intel_engine_execlists *el,
-		  const struct i915_request *rq)
+static bool needs_timeslice(const struct intel_engine_cs *engine,
+			    const struct i915_request *rq)
 {
-	return timer_expired(&el->timer) || timeslice_yield(el, rq);
-}
+	/* If not currently active, or about to switch, wait for next event */
+	if (!rq || __i915_request_is_complete(rq))
+		return false;
 
-static int
-switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq)
-{
-	if (list_is_last(&rq->sched.link, &engine->active.requests))
-		return engine->execlists.queue_priority_hint;
+	/* We do not need to start the timeslice until after the ACK */
+	if (READ_ONCE(engine->execlists.pending[0]))
+		return false;
 
-	return rq_prio(list_next_entry(rq, sched.link));
-}
+	/* If ELSP[1] is occupied, always check to see if worth slicing */
+	if (!list_is_last_rcu(&rq->sched.link, &engine->active.requests))
+		return true;
 
-static inline unsigned long
-timeslice(const struct intel_engine_cs *engine)
-{
-	return READ_ONCE(engine->props.timeslice_duration_ms);
+	/* Otherwise, ELSP[0] is by itself, but may be waiting in the queue */
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
+		return true;
+
+	return !RB_EMPTY_ROOT(&engine->execlists.virtual.rb_root);
 }
 
-static unsigned long active_timeslice(const struct intel_engine_cs *engine)
+static bool
+timeslice_expired(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
-	const struct intel_engine_execlists *execlists = &engine->execlists;
-	const struct i915_request *rq = *execlists->active;
+	const struct intel_engine_execlists *el = &engine->execlists;
 
-	if (!rq || __i915_request_is_complete(rq))
-		return 0;
+	if (!intel_engine_has_timeslices(engine))
+		return false;
 
-	if (READ_ONCE(execlists->switch_priority_hint) < effective_prio(rq))
-		return 0;
+	if (i915_request_has_nopreempt(rq) && __i915_request_has_started(rq))
+		return false;
+
+	if (!needs_timeslice(engine, rq))
+		return false;
 
-	return timeslice(engine);
+	return timer_expired(&el->timer) || timeslice_yield(el, rq);
 }
 
-static void set_timeslice(struct intel_engine_cs *engine)
+static unsigned long timeslice(const struct intel_engine_cs *engine)
 {
-	unsigned long duration;
-
-	if (!intel_engine_has_timeslices(engine))
-		return;
-
-	duration = active_timeslice(engine);
-	ENGINE_TRACE(engine, "bump timeslicing, interval:%lu", duration);
-
-	set_timer_ms(&engine->execlists.timer, duration);
+	return READ_ONCE(engine->props.timeslice_duration_ms);
 }
 
-static void start_timeslice(struct intel_engine_cs *engine, int prio)
+static void start_timeslice(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists *execlists = &engine->execlists;
 	unsigned long duration;
 
 	if (!intel_engine_has_timeslices(engine))
 		return;
 
-	WRITE_ONCE(execlists->switch_priority_hint, prio);
-	if (prio == INT_MIN)
-		return;
-
-	if (timer_pending(&execlists->timer))
-		return;
-
-	duration = timeslice(engine);
-	ENGINE_TRACE(engine,
-		     "start timeslicing, prio:%d, interval:%lu",
-		     prio, duration);
+	/* Disable the timer if there is nothing to switch to */
+	duration = 0;
+	if (needs_timeslice(engine, execlists_active(&engine->execlists)))
+		duration = timeslice(engine);
 
-	set_timer_ms(&execlists->timer, duration);
+	set_timer_ms(&engine->execlists.timer, duration);
 }
 
 static void record_preemption(struct intel_engine_execlists *execlists)
@@ -1319,13 +1287,12 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			__unwind_incomplete_requests(engine);
 
 			last = NULL;
-		} else if (need_timeslice(engine, last) &&
-			   timeslice_expired(execlists, last)) {
+		} else if (timeslice_expired(engine, last)) {
 			ENGINE_TRACE(engine,
-				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
-				     last->fence.context,
-				     last->fence.seqno,
-				     last->sched.attr.priority,
+				     "expired:%s last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
+				     yesno(timer_expired(&execlists->timer)),
+				     last->fence.context, last->fence.seqno,
+				     rq_prio(last),
 				     execlists->queue_priority_hint,
 				     yesno(timeslice_yield(execlists, last)));
 
@@ -1364,7 +1331,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * of timeslices, our queue might be.
 				 */
 				spin_unlock(&engine->active.lock);
-				start_timeslice(engine, queue_prio(execlists));
 				return;
 			}
 		}
@@ -1393,7 +1359,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		if (last && !can_merge_rq(last, rq)) {
 			spin_unlock(&ve->base.active.lock);
 			spin_unlock(&engine->active.lock);
-			start_timeslice(engine, rq_prio(rq));
 			return; /* leave this for another sibling */
 		}
 
@@ -1557,29 +1522,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	execlists->queue_priority_hint = queue_prio(execlists);
 	spin_unlock(&engine->active.lock);
 
-	if (submit) {
-		/*
-		 * Skip if we ended up with exactly the same set of requests,
-		 * e.g. trying to timeslice a pair of ordered contexts
-		 */
-		if (!memcmp(execlists->active,
-			    execlists->pending,
-			    (port - execlists->pending) * sizeof(*port)))
-			goto skip_submit;
-
+	/*
+	 * We can skip poking the HW if we ended up with exactly the same set
+	 * of requests as currently running, e.g. trying to timeslice a pair
+	 * of ordered contexts.
+	 */
+	if (submit &&
+	    memcmp(execlists->active,
+		   execlists->pending,
+		   (port - execlists->pending) * sizeof(*port))) {
 		*port = NULL;
 		while (port-- != execlists->pending)
 			execlists_schedule_in(*port, port - execlists->pending);
 
-		execlists->switch_priority_hint =
-			switch_prio(engine, *execlists->pending);
-
 		WRITE_ONCE(execlists->yield, -1);
 		set_preempt_timeout(engine, *execlists->active);
 		execlists_submit_ports(engine);
 	} else {
-		start_timeslice(engine, execlists->queue_priority_hint);
-skip_submit:
 		ring_set_paused(engine, 0);
 		while (port-- != execlists->pending)
 			i915_request_put(*port);
@@ -1937,8 +1896,6 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 		}
 	} while (head != tail);
 
-	set_timeslice(engine);
-
 	/*
 	 * Gen11 has proven to fail wrt global observation point between
 	 * entry and tail update, failing on the ordering and thus
@@ -1951,6 +1908,7 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 	 * invalidation before.
 	 */
 	invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
+	cancel_timer(&execlists->timer);
 
 	return inactive;
 }
@@ -2369,8 +2327,10 @@ static void execlists_submission_tasklet(unsigned long data)
 		execlists_reset(engine, msg);
 	}
 
-	if (!engine->execlists.pending[0])
+	if (!engine->execlists.pending[0]) {
 		execlists_dequeue_irq(engine);
+		start_timeslice(engine);
+	}
 
 	post_process_csb(post, inactive);
 	rcu_read_unlock();
@@ -3846,9 +3806,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 		show_request(m, last, "\t\t", 0);
 	}
 
-	if (execlists->switch_priority_hint != INT_MIN)
-		drm_printf(m, "\t\tSwitch priority hint: %d\n",
-			   READ_ONCE(execlists->switch_priority_hint));
 	if (execlists->queue_priority_hint != INT_MIN)
 		drm_printf(m, "\t\tQueue priority hint: %d\n",
 			   READ_ONCE(execlists->queue_priority_hint));
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 23/62] drm/i915: Strip out internal priorities

[Chris Wilson]

Since we are not using any internal priority levels, and in the next few
patches will introduce a new index for which the optimisation is not so
lear cut, discard the small table within the priolist.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  |  2 +-
 .../drm/i915/gt/intel_execlists_submission.c  | 22 ++------
 drivers/gpu/drm/i915/gt/selftest_execlists.c  |  1 -
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |  1 -
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c |  6 +--
 drivers/gpu/drm/i915/i915_priolist_types.h    |  8 +--
 drivers/gpu/drm/i915/i915_scheduler.c         | 51 +++----------------
 drivers/gpu/drm/i915/i915_scheduler.h         | 16 ++----
 8 files changed, 20 insertions(+), 87 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index d7be2b9339f9..1732a42e9075 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -125,7 +125,7 @@ static void heartbeat(struct work_struct *wrk)
 			 * low latency and no jitter] the chance to naturally
 			 * complete before being preempted.
 			 */
-			attr.priority = I915_PRIORITY_MASK;
+			attr.priority = 0;
 			if (rq->sched.attr.priority >= attr.priority)
 				attr.priority |= I915_USER_PRIORITY(I915_PRIORITY_HEARTBEAT);
 			if (rq->sched.attr.priority >= attr.priority)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index ebe81fe987f0..5e603fb752cd 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -276,22 +276,13 @@ static int effective_prio(const struct i915_request *rq)
 
 static int queue_prio(const struct intel_engine_execlists *execlists)
 {
-	struct i915_priolist *p;
 	struct rb_node *rb;
 
 	rb = rb_first_cached(&execlists->queue);
 	if (!rb)
 		return INT_MIN;
 
-	/*
-	 * As the priolist[] are inverted, with the highest priority in [0],
-	 * we have to flip the index value to become priority.
-	 */
-	p = to_priolist(rb);
-	if (!I915_USER_PRIORITY_SHIFT)
-		return p->priority;
-
-	return ((p->priority + 1) << I915_USER_PRIORITY_SHIFT) - ffs(p->used);
+	return to_priolist(rb)->priority;
 }
 
 static int virtual_prio(const struct intel_engine_execlists *el)
@@ -1420,9 +1411,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			bool merge = true;
 
 			/*
@@ -2947,9 +2937,8 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			mark_eio(rq);
 			__i915_request_submit(rq);
 		}
@@ -3220,7 +3209,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 
 static struct list_head *virtual_queue(struct virtual_engine *ve)
 {
-	return &ve->base.execlists.default_priolist.requests[0];
+	return &ve->base.execlists.default_priolist.requests;
 }
 
 static void rcu_virtual_context_destroy(struct work_struct *wrk)
@@ -3814,9 +3803,8 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 	count = 0;
 	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
-		int i;
 
-		priolist_for_each_request(rq, p, i) {
+		priolist_for_each_request(rq, p) {
 			if (count++ < max - 1)
 				show_request(m, rq, "\t\t", 0);
 			else
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 080b63000a4e..2e49b31be96f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -1078,7 +1078,6 @@ create_rewinder(struct intel_context *ce,
 
 	intel_ring_advance(rq, cs);
 
-	rq->sched.attr.priority = I915_PRIORITY_MASK;
 	err = 0;
 err:
 	i915_request_get(rq);
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index ba6c2be5c8ff..f449c56e0946 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -730,7 +730,6 @@ create_timestamp(struct intel_context *ce, void *slot, int idx)
 
 	intel_ring_advance(rq, cs);
 
-	rq->sched.attr.priority = I915_PRIORITY_MASK;
 	err = 0;
 err:
 	i915_request_get(rq);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 694ee424b4ee..6a70f3a2c002 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -313,9 +313,8 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			if (last && rq->context != last->context) {
 				if (port == last_port)
 					goto done;
@@ -486,9 +485,8 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			list_del_init(&rq->sched.link);
 			__i915_request_submit(rq);
 			dma_fence_set_error(&rq->fence, -EIO);
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 8aa7866ec6b6..9a7657bb002e 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -27,11 +27,8 @@ enum {
 #define I915_USER_PRIORITY_SHIFT 0
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
-#define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
-#define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
-
 /* Smallest priority value that cannot be bumped. */
-#define I915_PRIORITY_INVALID (INT_MIN | (u8)I915_PRIORITY_MASK)
+#define I915_PRIORITY_INVALID (INT_MIN)
 
 /*
  * Requests containing performance queries must not be preempted by
@@ -45,9 +42,8 @@ enum {
 #define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
 
 struct i915_priolist {
-	struct list_head requests[I915_PRIORITY_COUNT];
+	struct list_head requests;
 	struct rb_node node;
-	unsigned long used;
 	int priority;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 318e359bf5c3..1f033eab9a1c 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -43,7 +43,7 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 static void assert_priolists(struct intel_engine_execlists * const execlists)
 {
 	struct rb_node *rb;
-	long last_prio, i;
+	long last_prio;
 
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
@@ -57,14 +57,6 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 
 		GEM_BUG_ON(p->priority > last_prio);
 		last_prio = p->priority;
-
-		GEM_BUG_ON(!p->used);
-		for (i = 0; i < ARRAY_SIZE(p->requests); i++) {
-			if (list_empty(&p->requests[i]))
-				continue;
-
-			GEM_BUG_ON(!(p->used & BIT(i)));
-		}
 	}
 }
 
@@ -75,13 +67,10 @@ i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
 	struct i915_priolist *p;
 	struct rb_node **parent, *rb;
 	bool first = true;
-	int idx, i;
 
 	lockdep_assert_held(&engine->active.lock);
 	assert_priolists(execlists);
 
-	/* buckets sorted from highest [in slot 0] to lowest priority */
-	idx = I915_PRIORITY_COUNT - (prio & I915_PRIORITY_MASK) - 1;
 	prio >>= I915_USER_PRIORITY_SHIFT;
 	if (unlikely(execlists->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
@@ -99,7 +88,7 @@ i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
 			parent = &rb->rb_right;
 			first = false;
 		} else {
-			goto out;
+			return &p->requests;
 		}
 	}
 
@@ -125,15 +114,12 @@ i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
 	}
 
 	p->priority = prio;
-	for (i = 0; i < ARRAY_SIZE(p->requests); i++)
-		INIT_LIST_HEAD(&p->requests[i]);
+	INIT_LIST_HEAD(&p->requests);
+
 	rb_link_node(&p->node, rb, parent);
 	rb_insert_color_cached(&p->node, &execlists->queue, first);
-	p->used = 0;
 
-out:
-	p->used |= BIT(idx);
-	return &p->requests[idx];
+	return &p->requests;
 }
 
 void __i915_priolist_free(struct i915_priolist *p)
@@ -363,30 +349,6 @@ void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr)
 	spin_unlock_irq(&schedule_lock);
 }
 
-static void __bump_priority(struct i915_sched_node *node, unsigned int bump)
-{
-	struct i915_sched_attr attr = node->attr;
-
-	if (attr.priority & bump)
-		return;
-
-	attr.priority |= bump;
-	__i915_schedule(node, &attr);
-}
-
-void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
-{
-	unsigned long flags;
-
-	GEM_BUG_ON(bump & ~I915_PRIORITY_MASK);
-	if (READ_ONCE(rq->sched.attr.priority) & bump)
-		return;
-
-	spin_lock_irqsave(&schedule_lock, flags);
-	__bump_priority(&rq->sched, bump);
-	spin_unlock_irqrestore(&schedule_lock, flags);
-}
-
 void i915_sched_node_init(struct i915_sched_node *node)
 {
 	INIT_LIST_HEAD(&node->signalers_list);
@@ -553,8 +515,7 @@ int __init i915_global_scheduler_init(void)
 	if (!global.slab_dependencies)
 		return -ENOMEM;
 
-	global.slab_priorities = KMEM_CACHE(i915_priolist,
-					    SLAB_HWCACHE_ALIGN);
+	global.slab_priorities = KMEM_CACHE(i915_priolist, 0);
 	if (!global.slab_priorities)
 		goto err_priorities;
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 4501e5ac2637..858a0938f47a 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -15,17 +15,11 @@
 
 struct drm_printer;
 
-#define priolist_for_each_request(it, plist, idx) \
-	for (idx = 0; idx < ARRAY_SIZE((plist)->requests); idx++) \
-		list_for_each_entry(it, &(plist)->requests[idx], sched.link)
+#define priolist_for_each_request(it, plist) \
+	list_for_each_entry(it, &(plist)->requests, sched.link)
 
-#define priolist_for_each_request_consume(it, n, plist, idx) \
-	for (; \
-	     (plist)->used ? (idx = __ffs((plist)->used)), 1 : 0; \
-	     (plist)->used &= ~BIT(idx)) \
-		list_for_each_entry_safe(it, n, \
-					 &(plist)->requests[idx], \
-					 sched.link)
+#define priolist_for_each_request_consume(it, n, plist) \
+	list_for_each_entry_safe(it, n, &(plist)->requests, sched.link)
 
 void i915_sched_node_init(struct i915_sched_node *node);
 void i915_sched_node_reinit(struct i915_sched_node *node);
@@ -44,8 +38,6 @@ void i915_sched_node_fini(struct i915_sched_node *node);
 void i915_schedule(struct i915_request *request,
 		   const struct i915_sched_attr *attr);
 
-void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump);
-
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 24/62] drm/i915: Remove I915_USER_PRIORITY_SHIFT

[Chris Wilson]

As we do not have any internal priority levels, the priority can be set
directed from the user values.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c  |  4 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  6 +--
 .../i915/gem/selftests/i915_gem_object_blt.c  |  4 +-
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  | 10 ++---
 drivers/gpu/drm/i915/gt/selftest_execlists.c  | 44 +++++++------------
 drivers/gpu/drm/i915/i915_priolist_types.h    |  3 --
 drivers/gpu/drm/i915/i915_scheduler.c         |  1 -
 7 files changed, 24 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index f2c48e5cdb43..112e3a3d2dab 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15613,9 +15613,7 @@ void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state)
 
 static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
 {
-	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_DISPLAY),
-	};
+	struct i915_sched_attr attr = { .priority = I915_PRIORITY_DISPLAY };
 
 	i915_gem_object_wait_priority(obj, 0, &attr);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index db8901cc2c8e..52711aaf71e1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -676,7 +676,7 @@ __create_context(struct drm_i915_private *i915)
 
 	kref_init(&ctx->ref);
 	ctx->i915 = i915;
-	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
+	ctx->sched.priority = I915_PRIORITY_NORMAL;
 	mutex_init(&ctx->mutex);
 	INIT_LIST_HEAD(&ctx->link);
 
@@ -1956,7 +1956,7 @@ static int set_priority(struct i915_gem_context *ctx,
 	    !capable(CAP_SYS_NICE))
 		return -EPERM;
 
-	ctx->sched.priority = I915_USER_PRIORITY(priority);
+	ctx->sched.priority = priority;
 	context_apply_all(ctx, __apply_priority, ctx);
 
 	return 0;
@@ -2460,7 +2460,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 
 	case I915_CONTEXT_PARAM_PRIORITY:
 		args->size = 0;
-		args->value = ctx->sched.priority >> I915_USER_PRIORITY_SHIFT;
+		args->value = ctx->sched.priority;
 		break;
 
 	case I915_CONTEXT_PARAM_SSEU:
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index 23b6e11bbc3e..c4c04fb97d14 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -220,7 +220,7 @@ static int igt_fill_blt_thread(void *arg)
 			return PTR_ERR(ctx);
 
 		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-		ctx->sched.priority = I915_USER_PRIORITY(prio);
+		ctx->sched.priority = prio;
 	}
 
 	ce = i915_gem_context_get_engine(ctx, 0);
@@ -338,7 +338,7 @@ static int igt_copy_blt_thread(void *arg)
 			return PTR_ERR(ctx);
 
 		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-		ctx->sched.priority = I915_USER_PRIORITY(prio);
+		ctx->sched.priority = prio;
 	}
 
 	ce = i915_gem_context_get_engine(ctx, 0);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 1732a42e9075..ed03c08737f5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -81,9 +81,7 @@ static void show_heartbeat(const struct i915_request *rq,
 
 static void heartbeat(struct work_struct *wrk)
 {
-	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_MIN),
-	};
+	struct i915_sched_attr attr = { .priority = I915_PRIORITY_MIN };
 	struct intel_engine_cs *engine =
 		container_of(wrk, typeof(*engine), heartbeat.work.work);
 	struct intel_context *ce = engine->kernel_context;
@@ -127,7 +125,7 @@ static void heartbeat(struct work_struct *wrk)
 			 */
 			attr.priority = 0;
 			if (rq->sched.attr.priority >= attr.priority)
-				attr.priority |= I915_USER_PRIORITY(I915_PRIORITY_HEARTBEAT);
+				attr.priority = I915_PRIORITY_HEARTBEAT;
 			if (rq->sched.attr.priority >= attr.priority)
 				attr.priority = I915_PRIORITY_BARRIER;
 
@@ -285,9 +283,7 @@ int intel_engine_pulse(struct intel_engine_cs *engine)
 
 int intel_engine_flush_barriers(struct intel_engine_cs *engine)
 {
-	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_MIN),
-	};
+	struct i915_sched_attr attr = { .priority = I915_PRIORITY_MIN };
 	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 	int err;
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 2e49b31be96f..5152cf3f59a7 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -321,7 +321,7 @@ static int live_unlite_switch(void *arg)
 
 static int live_unlite_preempt(void *arg)
 {
-	return live_unlite_restore(arg, I915_USER_PRIORITY(I915_PRIORITY_MAX));
+	return live_unlite_restore(arg, I915_PRIORITY_MAX);
 }
 
 static int live_unlite_ring(void *arg)
@@ -1308,9 +1308,7 @@ static int live_timeslice_queue(void *arg)
 		goto err_pin;
 
 	for_each_engine(engine, gt, id) {
-		struct i915_sched_attr attr = {
-			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
-		};
+		struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 		struct i915_request *rq, *nop;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1525,14 +1523,12 @@ static int live_busywait_preempt(void *arg)
 	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		return -ENOMEM;
-	ctx_hi->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
 	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
 
 	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
@@ -1735,14 +1731,12 @@ static int live_preempt(void *arg)
 	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
-	ctx_hi->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
 	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
 
 	for_each_engine(engine, gt, id) {
 		struct igt_live_test t;
@@ -1838,7 +1832,7 @@ static int live_late_preempt(void *arg)
 		goto err_ctx_hi;
 
 	/* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */
-	ctx_lo->sched.priority = I915_USER_PRIORITY(1);
+	ctx_lo->sched.priority = 1;
 
 	for_each_engine(engine, gt, id) {
 		struct igt_live_test t;
@@ -1879,7 +1873,7 @@ static int live_late_preempt(void *arg)
 			goto err_wedged;
 		}
 
-		attr.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX);
+		attr.priority = I915_PRIORITY_MAX;
 		engine->schedule(rq, &attr);
 
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
@@ -1963,7 +1957,7 @@ static int live_nopreempt(void *arg)
 		return -ENOMEM;
 	if (preempt_client_init(gt, &b))
 		goto err_client_a;
-	b.ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX);
+	b.ctx->sched.priority = I915_PRIORITY_MAX;
 
 	for_each_engine(engine, gt, id) {
 		struct i915_request *rq_a, *rq_b;
@@ -2356,11 +2350,9 @@ static int live_preempt_cancel(void *arg)
 
 static int live_suppress_self_preempt(void *arg)
 {
+	struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX)
-	};
 	struct preempt_client a, b;
 	enum intel_engine_id id;
 	int err = -ENOMEM;
@@ -2497,9 +2489,7 @@ static int live_chain_preempt(void *arg)
 		goto err_client_hi;
 
 	for_each_engine(engine, gt, id) {
-		struct i915_sched_attr attr = {
-			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
-		};
+		struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 		struct igt_live_test t;
 		struct i915_request *rq;
 		int ring_size, count, i;
@@ -2917,9 +2907,7 @@ static int live_preempt_gang(void *arg)
 			return -EIO;
 
 		do {
-			struct i915_sched_attr attr = {
-				.priority = I915_USER_PRIORITY(prio++),
-			};
+			struct i915_sched_attr attr = { .priority = prio++ };
 
 			err = create_gang(engine, &rq);
 			if (err)
@@ -2955,7 +2943,7 @@ static int live_preempt_gang(void *arg)
 					drm_info_printer(engine->i915->drm.dev);
 
 				pr_err("Failed to flush chain of %d requests, at %d\n",
-				       prio, rq_prio(rq) >> I915_USER_PRIORITY_SHIFT);
+				       prio, rq_prio(rq));
 				intel_engine_dump(engine, &p,
 						  "%s\n", engine->name);
 
@@ -3329,14 +3317,12 @@ static int live_preempt_timeout(void *arg)
 	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
-	ctx_hi->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
 
 	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority =
-		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
 
 	for_each_engine(engine, gt, id) {
 		unsigned long saved_timeout;
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 9a7657bb002e..bc2fa84f98a8 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -24,9 +24,6 @@ enum {
 	I915_PRIORITY_DISPLAY,
 };
 
-#define I915_USER_PRIORITY_SHIFT 0
-#define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
-
 /* Smallest priority value that cannot be bumped. */
 #define I915_PRIORITY_INVALID (INT_MIN)
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 1f033eab9a1c..a57353191d12 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -71,7 +71,6 @@ i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
 	lockdep_assert_held(&engine->active.lock);
 	assert_priolists(execlists);
 
-	prio >>= I915_USER_PRIORITY_SHIFT;
 	if (unlikely(execlists->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 25/62] drm/i915: Replace engine->schedule() with a known request operation

[Chris Wilson]

Looking to the future, we want to set the scheduling attributes
explicitly and so replace the generic engine->schedule() with the more
direct i915_request_set_priority()

What it loses in removing the 'schedule' name from the function, it
gains in having an explicit entry point with a stated goal.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c  |  9 +----
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |  1 -
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_wait.c      | 27 +++++----------
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  3 --
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  |  4 +--
 drivers/gpu/drm/i915/gt/intel_engine_types.h  | 29 ++++++++--------
 drivers/gpu/drm/i915/gt/intel_engine_user.c   |  2 +-
 .../drm/i915/gt/intel_execlists_submission.c  |  3 +-
 drivers/gpu/drm/i915/gt/selftest_execlists.c  | 33 +++++--------------
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  | 11 +++----
 drivers/gpu/drm/i915/i915_request.c           | 10 +++---
 drivers/gpu/drm/i915/i915_scheduler.c         | 15 +++++----
 drivers/gpu/drm/i915/i915_scheduler.h         |  3 +-
 14 files changed, 56 insertions(+), 96 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 112e3a3d2dab..f25ab2b15ca1 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15611,13 +15611,6 @@ void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state)
 		intel_unpin_fb_vma(vma, old_plane_state->flags);
 }
 
-static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
-{
-	struct i915_sched_attr attr = { .priority = I915_PRIORITY_DISPLAY };
-
-	i915_gem_object_wait_priority(obj, 0, &attr);
-}
-
 /**
  * intel_prepare_plane_fb - Prepare fb for usage on plane
  * @_plane: drm plane to prepare for
@@ -15694,7 +15687,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 	if (ret)
 		return ret;
 
-	fb_obj_bump_render_priority(obj);
+	i915_gem_object_wait_priority(obj, 0, I915_PRIORITY_DISPLAY);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB);
 
 	if (!new_plane_state->uapi.fence) { /* implicit fencing */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 0cf9e79325a8..60e9d9135e08 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2651,7 +2651,6 @@ static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb, bool throt
 	int err;
 
 	GEM_BUG_ON(eb->args->flags & __EXEC_ENGINE_PINNED);
-
 	if (unlikely(intel_context_is_banned(ce)))
 		return ERR_PTR(-EIO);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index be14486f63a7..b106bc81c303 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -517,7 +517,7 @@ int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 long timeout);
 int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 				  unsigned int flags,
-				  const struct i915_sched_attr *attr);
+				  int prio);
 
 void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
 					 enum fb_op_origin origin);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index 8af55cd3e690..cefbbb3d9b52 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -93,28 +93,17 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
 	return timeout;
 }
 
-static void __fence_set_priority(struct dma_fence *fence,
-				 const struct i915_sched_attr *attr)
+static void __fence_set_priority(struct dma_fence *fence, int prio)
 {
-	struct i915_request *rq;
-	struct intel_engine_cs *engine;
-
 	if (dma_fence_is_signaled(fence) || !dma_fence_is_i915(fence))
 		return;
 
-	rq = to_request(fence);
-	engine = rq->engine;
-
 	local_bh_disable();
-	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
-	if (engine->schedule)
-		engine->schedule(rq, attr);
-	rcu_read_unlock();
+	i915_request_set_priority(to_request(fence), prio);
 	local_bh_enable(); /* kick the tasklets if queues were reprioritised */
 }
 
-static void fence_set_priority(struct dma_fence *fence,
-			       const struct i915_sched_attr *attr)
+static void fence_set_priority(struct dma_fence *fence, int prio)
 {
 	/* Recurse once into a fence-array */
 	if (dma_fence_is_array(fence)) {
@@ -122,16 +111,16 @@ static void fence_set_priority(struct dma_fence *fence,
 		int i;
 
 		for (i = 0; i < array->num_fences; i++)
-			__fence_set_priority(array->fences[i], attr);
+			__fence_set_priority(array->fences[i], prio);
 	} else {
-		__fence_set_priority(fence, attr);
+		__fence_set_priority(fence, prio);
 	}
 }
 
 int
 i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			      unsigned int flags,
-			      const struct i915_sched_attr *attr)
+			      int prio)
 {
 	struct dma_fence *excl;
 
@@ -146,7 +135,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			return ret;
 
 		for (i = 0; i < count; i++) {
-			fence_set_priority(shared[i], attr);
+			fence_set_priority(shared[i], prio);
 			dma_fence_put(shared[i]);
 		}
 
@@ -156,7 +145,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 	}
 
 	if (excl) {
-		fence_set_priority(excl, attr);
+		fence_set_priority(excl, prio);
 		dma_fence_put(excl);
 	}
 	return 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 75911dd0483e..bc3fca62b628 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -337,9 +337,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	if (engine->context_size)
 		DRIVER_CAPS(i915)->has_logical_contexts = true;
 
-	/* Nothing to do here, execute in order of dependencies */
-	engine->schedule = NULL;
-
 	ewma__engine_latency_init(&engine->latency);
 	seqcount_init(&engine->stats.lock);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index ed03c08737f5..bccbb932a315 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -115,7 +115,7 @@ static void heartbeat(struct work_struct *wrk)
 			 * but all other contexts, including the kernel
 			 * context are stuck waiting for the signal.
 			 */
-		} else if (engine->schedule &&
+		} else if (intel_engine_has_scheduler(engine) &&
 			   rq->sched.attr.priority < I915_PRIORITY_BARRIER) {
 			/*
 			 * Gradually raise the priority of the heartbeat to
@@ -130,7 +130,7 @@ static void heartbeat(struct work_struct *wrk)
 				attr.priority = I915_PRIORITY_BARRIER;
 
 			local_bh_disable();
-			engine->schedule(rq, &attr);
+			i915_request_set_priority(rq, attr.priority);
 			local_bh_enable();
 		} else {
 			if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index f850179a583f..08ed958292af 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -454,14 +454,6 @@ struct intel_engine_cs {
 	void            (*bond_execute)(struct i915_request *rq,
 					struct dma_fence *signal);
 
-	/*
-	 * Call when the priority on a request has changed and it and its
-	 * dependencies may need rescheduling. Note the request itself may
-	 * not be ready to run!
-	 */
-	void		(*schedule)(struct i915_request *request,
-				    const struct i915_sched_attr *attr);
-
 	void		(*release)(struct intel_engine_cs *engine);
 
 	struct intel_engine_execlists execlists;
@@ -479,13 +471,14 @@ struct intel_engine_cs {
 
 #define I915_ENGINE_USING_CMD_PARSER BIT(0)
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
-#define I915_ENGINE_HAS_PREEMPTION   BIT(2)
-#define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
-#define I915_ENGINE_HAS_TIMESLICES   BIT(4)
-#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5)
-#define I915_ENGINE_IS_VIRTUAL       BIT(6)
-#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7)
-#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8)
+#define I915_ENGINE_HAS_SCHEDULER    BIT(2)
+#define I915_ENGINE_HAS_PREEMPTION   BIT(3)
+#define I915_ENGINE_HAS_SEMAPHORES   BIT(4)
+#define I915_ENGINE_HAS_TIMESLICES   BIT(5)
+#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(6)
+#define I915_ENGINE_IS_VIRTUAL       BIT(7)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(8)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(9)
 	unsigned int flags;
 
 	/*
@@ -571,6 +564,12 @@ intel_engine_supports_stats(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_SUPPORTS_STATS;
 }
 
+static inline bool
+intel_engine_has_scheduler(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_HAS_SCHEDULER;
+}
+
 static inline bool
 intel_engine_has_preemption(const struct intel_engine_cs *engine)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 34e6096f196e..6b5a4fdc14a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -108,7 +108,7 @@ static void set_scheduler_caps(struct drm_i915_private *i915)
 	for_each_uabi_engine(engine, i915) { /* all engines must agree! */
 		int i;
 
-		if (engine->schedule)
+		if (intel_engine_has_scheduler(engine))
 			enabled |= (I915_SCHEDULER_CAP_ENABLED |
 				    I915_SCHEDULER_CAP_PRIORITY);
 		else
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 5e603fb752cd..bb462159688b 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3026,7 +3026,6 @@ static void execlists_park(struct intel_engine_cs *engine)
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
-	engine->schedule = i915_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
@@ -3037,6 +3036,7 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->park = execlists_park;
 	engine->unpark = NULL;
 
+	engine->flags |= I915_ENGINE_HAS_SCHEDULER;
 	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
 	if (!intel_vgpu_active(engine->i915)) {
 		engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
@@ -3607,7 +3607,6 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
 
-	ve->base.schedule = i915_schedule;
 	ve->base.submit_request = virtual_submit_request;
 	ve->base.bond_execute = virtual_bond_execute;
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 5152cf3f59a7..0a2952bf1dcb 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -269,12 +269,8 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		i915_request_put(rq[0]);
 
 		if (prio) {
-			struct i915_sched_attr attr = {
-				.priority = prio,
-			};
-
 			/* Alternatively preempt the spinner with ce[1] */
-			engine->schedule(rq[1], &attr);
+			i915_request_set_priority(rq[1], prio);
 		}
 
 		/* And switch back to ce[0] for good measure */
@@ -874,9 +870,6 @@ release_queue(struct intel_engine_cs *engine,
 	      struct i915_vma *vma,
 	      int idx, int prio)
 {
-	struct i915_sched_attr attr = {
-		.priority = prio,
-	};
 	struct i915_request *rq;
 	u32 *cs;
 
@@ -901,7 +894,7 @@ release_queue(struct intel_engine_cs *engine,
 	i915_request_add(rq);
 
 	local_bh_disable();
-	engine->schedule(rq, &attr);
+	i915_request_set_priority(rq, prio);
 	local_bh_enable(); /* kick tasklet */
 
 	i915_request_put(rq);
@@ -1308,7 +1301,6 @@ static int live_timeslice_queue(void *arg)
 		goto err_pin;
 
 	for_each_engine(engine, gt, id) {
-		struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 		struct i915_request *rq, *nop;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1323,7 +1315,7 @@ static int live_timeslice_queue(void *arg)
 			err = PTR_ERR(rq);
 			goto err_heartbeat;
 		}
-		engine->schedule(rq, &attr);
+		i915_request_set_priority(rq, I915_PRIORITY_MAX);
 		err = wait_for_submit(engine, rq, HZ / 2);
 		if (err) {
 			pr_err("%s: Timed out trying to submit semaphores\n",
@@ -1810,7 +1802,6 @@ static int live_late_preempt(void *arg)
 	struct i915_gem_context *ctx_hi, *ctx_lo;
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
-	struct i915_sched_attr attr = {};
 	enum intel_engine_id id;
 	int err = -ENOMEM;
 
@@ -1873,8 +1864,7 @@ static int live_late_preempt(void *arg)
 			goto err_wedged;
 		}
 
-		attr.priority = I915_PRIORITY_MAX;
-		engine->schedule(rq, &attr);
+		i915_request_set_priority(rq, I915_PRIORITY_MAX);
 
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			pr_err("High priority context failed to preempt the low priority context\n");
@@ -2350,7 +2340,6 @@ static int live_preempt_cancel(void *arg)
 
 static int live_suppress_self_preempt(void *arg)
 {
-	struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct preempt_client a, b;
@@ -2421,7 +2410,7 @@ static int live_suppress_self_preempt(void *arg)
 			i915_request_add(rq_b);
 
 			GEM_BUG_ON(i915_request_completed(rq_a));
-			engine->schedule(rq_a, &attr);
+			i915_request_set_priority(rq_a, I915_PRIORITY_MAX);
 			igt_spinner_end(&a.spin);
 
 			if (!igt_wait_for_spinner(&b.spin, rq_b)) {
@@ -2489,7 +2478,6 @@ static int live_chain_preempt(void *arg)
 		goto err_client_hi;
 
 	for_each_engine(engine, gt, id) {
-		struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX };
 		struct igt_live_test t;
 		struct i915_request *rq;
 		int ring_size, count, i;
@@ -2556,7 +2544,7 @@ static int live_chain_preempt(void *arg)
 
 			i915_request_get(rq);
 			i915_request_add(rq);
-			engine->schedule(rq, &attr);
+			i915_request_set_priority(rq, I915_PRIORITY_MAX);
 
 			igt_spinner_end(&hi.spin);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
@@ -2907,14 +2895,12 @@ static int live_preempt_gang(void *arg)
 			return -EIO;
 
 		do {
-			struct i915_sched_attr attr = { .priority = prio++ };
-
 			err = create_gang(engine, &rq);
 			if (err)
 				break;
 
 			/* Submit each spinner at increasing priority */
-			engine->schedule(rq, &attr);
+			i915_request_set_priority(rq, prio++);
 		} while (prio <= I915_PRIORITY_MAX &&
 			 !__igt_timeout(end_time, NULL));
 		pr_debug("%s: Preempt chain of %d requests\n",
@@ -3135,9 +3121,6 @@ static int preempt_user(struct intel_engine_cs *engine,
 			struct i915_vma *global,
 			int id)
 {
-	struct i915_sched_attr attr = {
-		.priority = I915_PRIORITY_MAX
-	};
 	struct i915_request *rq;
 	int err = 0;
 	u32 *cs;
@@ -3162,7 +3145,7 @@ static int preempt_user(struct intel_engine_cs *engine,
 	i915_request_get(rq);
 	i915_request_add(rq);
 
-	engine->schedule(rq, &attr);
+	i915_request_set_priority(rq, I915_PRIORITY_MAX);
 
 	if (i915_request_wait(rq, 0, HZ / 2) < 0)
 		err = -ETIME;
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index c28d1fcad673..927d54c702f4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -726,12 +726,11 @@ static int active_engine(void *data)
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 
-		if (engine->schedule && arg->flags & TEST_PRIORITY) {
-			struct i915_sched_attr attr = {
-				.priority =
-					i915_prandom_u32_max_state(512, &prng),
-			};
-			engine->schedule(rq[idx], &attr);
+		if (intel_engine_has_scheduler(engine) &&
+		    arg->flags & TEST_PRIORITY) {
+			int prio = i915_prandom_u32_max_state(512, &prng);
+
+			i915_request_set_priority(rq[idx], prio);
 		}
 
 		err = active_request_put(old);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 2ed8cb0d248f..a2ea0aec8680 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1210,7 +1210,7 @@ __i915_request_await_execution(struct i915_request *to,
 	}
 
 	/* Couple the dependency tree for PI on this exposed to->fence */
-	if (to->engine->schedule) {
+	if (intel_engine_has_scheduler(to->engine)) {
 		err = i915_sched_node_add_dependency(&to->sched,
 						     &from->sched,
 						     I915_DEPENDENCY_WEAK);
@@ -1351,7 +1351,7 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 		return 0;
 	}
 
-	if (to->engine->schedule) {
+	if (intel_engine_has_scheduler(to->engine)) {
 		ret = i915_sched_node_add_dependency(&to->sched,
 						     &from->sched,
 						     I915_DEPENDENCY_EXTERNAL);
@@ -1538,7 +1538,7 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 			__i915_sw_fence_await_dma_fence(&rq->submit,
 							&prev->fence,
 							&rq->dmaq);
-		if (rq->engine->schedule)
+		if (intel_engine_has_scheduler(rq->engine))
 			__i915_sched_node_add_dependency(&rq->sched,
 							 &prev->sched,
 							 &rq->dep,
@@ -1610,8 +1610,8 @@ void __i915_request_queue(struct i915_request *rq,
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	if (attr && rq->engine->schedule)
-		rq->engine->schedule(rq, attr);
+	if (attr)
+		i915_request_set_priority(rq, attr->priority);
 
 	local_bh_disable();
 	__i915_request_queue_bh(rq);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index a57353191d12..264ed53821d8 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -216,10 +216,8 @@ static void kick_submission(struct intel_engine_cs *engine,
 	rcu_read_unlock();
 }
 
-static void __i915_schedule(struct i915_sched_node *node,
-			    const struct i915_sched_attr *attr)
+static void __i915_schedule(struct i915_sched_node *node, int prio)
 {
-	const int prio = max(attr->priority, node->attr.priority);
 	struct intel_engine_cs *engine;
 	struct i915_dependency *dep, *p;
 	struct i915_dependency stack;
@@ -233,6 +231,8 @@ static void __i915_schedule(struct i915_sched_node *node,
 	if (node_signaled(node))
 		return;
 
+	prio = max(prio, node->attr.priority);
+
 	stack.signaler = node;
 	list_add(&stack.dfs_link, &dfs);
 
@@ -286,7 +286,7 @@ static void __i915_schedule(struct i915_sched_node *node,
 	 */
 	if (node->attr.priority == I915_PRIORITY_INVALID) {
 		GEM_BUG_ON(!list_empty(&node->link));
-		node->attr = *attr;
+		node->attr.priority = prio;
 
 		if (stack.dfs_link.next == stack.dfs_link.prev)
 			return;
@@ -341,10 +341,13 @@ static void __i915_schedule(struct i915_sched_node *node,
 	spin_unlock(&engine->active.lock);
 }
 
-void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr)
+void i915_request_set_priority(struct i915_request *rq, int prio)
 {
+	if (!intel_engine_has_scheduler(rq->engine))
+		return;
+
 	spin_lock_irq(&schedule_lock);
-	__i915_schedule(&rq->sched, attr);
+	__i915_schedule(&rq->sched, prio);
 	spin_unlock_irq(&schedule_lock);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 858a0938f47a..ccee506c9a26 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -35,8 +35,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 
 void i915_sched_node_fini(struct i915_sched_node *node);
 
-void i915_schedule(struct i915_request *request,
-		   const struct i915_sched_attr *attr);
+void i915_request_set_priority(struct i915_request *request, int prio);
 
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 26/62] drm/i915: Teach the i915_dependency to use a double-lock

[Chris Wilson]

Currently, we construct and teardown the i915_dependency chains using a
global spinlock. As the lists are entirely local, it should be possible
to use an double-lock with an explicit nesting [signaler -> waiter,
always] and so avoid the costly convenience of a global spinlock.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_request.c         |  2 +-
 drivers/gpu/drm/i915/i915_scheduler.c       | 63 ++++++++++++++-------
 drivers/gpu/drm/i915/i915_scheduler.h       |  2 +-
 drivers/gpu/drm/i915/i915_scheduler_types.h |  2 +
 4 files changed, 45 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a2ea0aec8680..8408b7317ebc 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -330,7 +330,7 @@ bool i915_request_retire(struct i915_request *rq)
 	intel_context_unpin(rq->context);
 
 	free_capture_list(rq);
-	i915_sched_node_fini(&rq->sched);
+	i915_sched_node_retire(&rq->sched);
 	i915_request_put(rq);
 
 	return true;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 264ed53821d8..8391841d927d 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -19,6 +19,17 @@ static struct i915_global_scheduler {
 
 static DEFINE_SPINLOCK(schedule_lock);
 
+static struct i915_sched_node *node_get(struct i915_sched_node *node)
+{
+	i915_request_get(container_of(node, struct i915_request, sched));
+	return node;
+}
+
+static void node_put(struct i915_sched_node *node)
+{
+	i915_request_put(container_of(node, struct i915_request, sched));
+}
+
 static const struct i915_request *
 node_to_request(const struct i915_sched_node *node)
 {
@@ -353,6 +364,8 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 
 void i915_sched_node_init(struct i915_sched_node *node)
 {
+	spin_lock_init(&node->lock);
+
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
@@ -377,10 +390,17 @@ i915_dependency_alloc(void)
 	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
 }
 
+static void
+rcu_dependency_free(struct rcu_head *rcu)
+{
+	kmem_cache_free(global.slab_dependencies,
+			container_of(rcu, typeof(struct i915_dependency), rcu));
+}
+
 static void
 i915_dependency_free(struct i915_dependency *dep)
 {
-	kmem_cache_free(global.slab_dependencies, dep);
+	call_rcu(&dep->rcu, rcu_dependency_free);
 }
 
 bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
@@ -390,24 +410,27 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 {
 	bool ret = false;
 
-	spin_lock_irq(&schedule_lock);
+	/* The signal->lock is always the outer lock in this double-lock. */
+	spin_lock(&signal->lock);
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
 		dep->signaler = signal;
-		dep->waiter = node;
+		dep->waiter = node_get(node);
 		dep->flags = flags;
 
 		/* All set, now publish. Beware the lockless walkers. */
+		spin_lock_nested(&node->lock, SINGLE_DEPTH_NESTING);
 		list_add_rcu(&dep->signal_link, &node->signalers_list);
 		list_add_rcu(&dep->wait_link, &signal->waiters_list);
+		spin_unlock(&node->lock);
 
 		/* Propagate the chains */
 		node->flags |= signal->flags;
 		ret = true;
 	}
 
-	spin_unlock_irq(&schedule_lock);
+	spin_unlock(&signal->lock);
 
 	return ret;
 }
@@ -429,39 +452,36 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 	return 0;
 }
 
-void i915_sched_node_fini(struct i915_sched_node *node)
+void i915_sched_node_retire(struct i915_sched_node *node)
 {
 	struct i915_dependency *dep, *tmp;
 
-	spin_lock_irq(&schedule_lock);
-
 	/*
 	 * Everyone we depended upon (the fences we wait to be signaled)
 	 * should retire before us and remove themselves from our list.
 	 * However, retirement is run independently on each timeline and
-	 * so we may be called out-of-order.
+	 * so we may be called out-of-order. As we need to avoid taking
+	 * the signaler's lock, just mark up our completion and be wary
+	 * in traversing the signalers->waiters_list.
 	 */
-	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del_rcu(&dep->wait_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
-	}
-	INIT_LIST_HEAD(&node->signalers_list);
 
 	/* Remove ourselves from everyone who depends upon us */
+	spin_lock(&node->lock);
 	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
+		struct i915_sched_node *w = dep->waiter;
+
 		GEM_BUG_ON(dep->signaler != node);
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
 
+		spin_lock_nested(&w->lock, SINGLE_DEPTH_NESTING);
 		list_del_rcu(&dep->signal_link);
+		spin_unlock(&w->lock);
+		node_put(w);
+
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
-	INIT_LIST_HEAD(&node->waiters_list);
-
-	spin_unlock_irq(&schedule_lock);
+	INIT_LIST_HEAD_RCU(&node->waiters_list);
+	spin_unlock(&node->lock);
 }
 
 void i915_request_show_with_schedule(struct drm_printer *m,
@@ -512,8 +532,7 @@ static struct i915_global_scheduler global = { {
 int __init i915_global_scheduler_init(void)
 {
 	global.slab_dependencies = KMEM_CACHE(i915_dependency,
-					      SLAB_HWCACHE_ALIGN |
-					      SLAB_TYPESAFE_BY_RCU);
+					      SLAB_HWCACHE_ALIGN);
 	if (!global.slab_dependencies)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index ccee506c9a26..a045be784c67 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -33,7 +33,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 				   struct i915_sched_node *signal,
 				   unsigned long flags);
 
-void i915_sched_node_fini(struct i915_sched_node *node);
+void i915_sched_node_retire(struct i915_sched_node *node);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 343ed44d5ed4..623bf41fcf35 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -60,6 +60,7 @@ struct i915_sched_attr {
  * others.
  */
 struct i915_sched_node {
+	spinlock_t lock; /* protect the lists */
 	struct list_head signalers_list; /* those before us, we depend upon */
 	struct list_head waiters_list; /* those after us, they depend upon us */
 	struct list_head link;
@@ -75,6 +76,7 @@ struct i915_dependency {
 	struct list_head signal_link;
 	struct list_head wait_link;
 	struct list_head dfs_link;
+	struct rcu_head rcu;
 	unsigned long flags;
 #define I915_DEPENDENCY_ALLOC		BIT(0)
 #define I915_DEPENDENCY_EXTERNAL	BIT(1)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 27/62] drm/i915: Restructure priority inheritance

[Chris Wilson]

In anticipation of wanting to be able to call pi from underneath an
engine's active.lock, rework the priority inheritance to primarily work
along an engine's priority queue, delegating any other engine that the
chain may traverse to a worker. This reduces the global spinlock from
governing the multi-entire priority inheritance depth-first search, to a
smaller lock on each engine around a single list on that engine.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |   2 +
 drivers/gpu/drm/i915/gt/intel_engine_types.h |   3 +
 drivers/gpu/drm/i915/i915_scheduler.c        | 338 ++++++++++++-------
 drivers/gpu/drm/i915/i915_scheduler.h        |   2 +
 drivers/gpu/drm/i915/i915_scheduler_types.h  |  19 +-
 5 files changed, 229 insertions(+), 135 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index bc3fca62b628..78b41dc36cd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -594,6 +594,8 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
 
 	execlists->queue_priority_hint = INT_MIN;
 	execlists->queue = RB_ROOT_CACHED;
+
+	i915_sched_init_ipi(&execlists->ipi);
 }
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 08ed958292af..d19710191690 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -21,6 +21,7 @@
 #include "i915_gem.h"
 #include "i915_pmu.h"
 #include "i915_priolist_types.h"
+#include "i915_scheduler_types.h"
 #include "i915_selftest.h"
 #include "intel_breadcrumbs_types.h"
 #include "intel_sseu.h"
@@ -258,6 +259,8 @@ struct intel_engine_execlists {
 	struct rb_root_cached queue;
 	struct rb_root_cached virtual;
 
+	struct i915_sched_ipi ipi;
+
 	/**
 	 * @csb_write: control register for Context Switch buffer
 	 *
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 8391841d927d..5fda1d29381b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -17,8 +17,6 @@ static struct i915_global_scheduler {
 	struct kmem_cache *slab_priorities;
 } global;
 
-static DEFINE_SPINLOCK(schedule_lock);
-
 static struct i915_sched_node *node_get(struct i915_sched_node *node)
 {
 	i915_request_get(container_of(node, struct i915_request, sched));
@@ -30,15 +28,114 @@ static void node_put(struct i915_sched_node *node)
 	i915_request_put(container_of(node, struct i915_request, sched));
 }
 
-static const struct i915_request *
-node_to_request(const struct i915_sched_node *node)
+static inline int rq_prio(const struct i915_request *rq)
 {
-	return container_of(node, const struct i915_request, sched);
+	return READ_ONCE(rq->sched.attr.priority);
+}
+
+static int ipi_get_prio(struct i915_request *rq)
+{
+	if (READ_ONCE(rq->sched.ipi_priority) == I915_PRIORITY_INVALID)
+		return I915_PRIORITY_INVALID;
+
+	return xchg(&rq->sched.ipi_priority, I915_PRIORITY_INVALID);
+}
+
+static void ipi_schedule(struct work_struct *wrk)
+{
+	struct i915_sched_ipi *ipi = container_of(wrk, typeof(*ipi), work);
+	struct i915_request *rq = xchg(&ipi->list, NULL);
+
+	do {
+		struct i915_request *rn = xchg(&rq->sched.ipi_link, NULL);
+		int prio;
+
+		prio = ipi_get_prio(rq);
+
+		/*
+		 * For cross-engine scheduling to work we rely on one of two
+		 * things:
+		 *
+		 * a) The requests are using dma-fence fences and so will not
+		 * be scheduled until the previous engine is completed, and
+		 * so we cannot cross back onto the original engine and end up
+		 * queuing an earlier request after the first (due to the
+		 * interrupted DFS).
+		 *
+		 * b) The requests are using semaphores and so may be already
+		 * be in flight, in which case if we cross back onto the same
+		 * engine, we will already have put the interrupted DFS into
+		 * the priolist, and the continuation will now be queued
+		 * afterwards [out-of-order]. However, since we are using
+		 * semaphores in this case, we also perform yield on semaphore
+		 * waits and so will reorder the requests back into the correct
+		 * sequence. This occurrence (of promoting a request chain
+		 * that crosses the engines using semaphores back unto itself)
+		 * should be unlikely enough that it probably does not matter...
+		 */
+		local_bh_disable();
+		i915_request_set_priority(rq, prio);
+		local_bh_enable();
+
+		i915_request_put(rq);
+		rq = ptr_mask_bits(rn, 1);
+	} while (rq);
+}
+
+void i915_sched_init_ipi(struct i915_sched_ipi *ipi)
+{
+	INIT_WORK(&ipi->work, ipi_schedule);
+	ipi->list = NULL;
+}
+
+static void __ipi_add(struct i915_request *rq)
+{
+#define STUB ((struct i915_request *)1)
+	struct intel_engine_cs *engine = READ_ONCE(rq->engine);
+	struct i915_request *first;
+
+	if (!i915_request_get_rcu(rq))
+		return;
+
+	if (__i915_request_is_complete(rq) ||
+	    cmpxchg(&rq->sched.ipi_link, NULL, STUB)) { /* already queued */
+		i915_request_put(rq);
+		return;
+	}
+
+	first = READ_ONCE(engine->execlists.ipi.list);
+	do
+		rq->sched.ipi_link = ptr_pack_bits(first, 1, 1);
+	while (!try_cmpxchg(&engine->execlists.ipi.list, &first, rq));
+
+	if (!first)
+		queue_work(system_unbound_wq, &engine->execlists.ipi.work);
 }
 
-static inline bool node_started(const struct i915_sched_node *node)
+/*
+ * Virtual engines complicate acquiring the engine timeline lock,
+ * as their rq->engine pointer is not stable until under that
+ * engine lock. The simple ploy we use is to take the lock then
+ * check that the rq still belongs to the newly locked engine.
+ */
+#define lock_engine_irqsave(rq, flags) ({ \
+	struct i915_request * const rq__ = (rq); \
+	struct intel_engine_cs *engine__ = READ_ONCE(rq__->engine); \
+\
+	spin_lock_irqsave(&engine__->active.lock, (flags)); \
+	while (engine__ != READ_ONCE((rq__)->engine)) { \
+		spin_unlock(&engine__->active.lock); \
+		engine__ = READ_ONCE(rq__->engine); \
+		spin_lock(&engine__->active.lock); \
+	} \
+\
+	engine__; \
+})
+
+static const struct i915_request *
+node_to_request(const struct i915_sched_node *node)
 {
-	return i915_request_started(node_to_request(node));
+	return container_of(node, const struct i915_request, sched);
 }
 
 static inline bool node_signaled(const struct i915_sched_node *node)
@@ -137,42 +234,6 @@ void __i915_priolist_free(struct i915_priolist *p)
 	kmem_cache_free(global.slab_priorities, p);
 }
 
-struct sched_cache {
-	struct list_head *priolist;
-};
-
-static struct intel_engine_cs *
-sched_lock_engine(const struct i915_sched_node *node,
-		  struct intel_engine_cs *locked,
-		  struct sched_cache *cache)
-{
-	const struct i915_request *rq = node_to_request(node);
-	struct intel_engine_cs *engine;
-
-	GEM_BUG_ON(!locked);
-
-	/*
-	 * Virtual engines complicate acquiring the engine timeline lock,
-	 * as their rq->engine pointer is not stable until under that
-	 * engine lock. The simple ploy we use is to take the lock then
-	 * check that the rq still belongs to the newly locked engine.
-	 */
-	while (locked != (engine = READ_ONCE(rq->engine))) {
-		spin_unlock(&locked->active.lock);
-		memset(cache, 0, sizeof(*cache));
-		spin_lock(&engine->active.lock);
-		locked = engine;
-	}
-
-	GEM_BUG_ON(locked != engine);
-	return locked;
-}
-
-static inline int rq_prio(const struct i915_request *rq)
-{
-	return rq->sched.attr.priority;
-}
-
 static inline bool need_preempt(int prio, int active)
 {
 	/*
@@ -198,19 +259,17 @@ static void kick_submission(struct intel_engine_cs *engine,
 	if (prio <= engine->execlists.queue_priority_hint)
 		return;
 
-	rcu_read_lock();
-
 	/* Nothing currently active? We're overdue for a submission! */
 	inflight = execlists_active(&engine->execlists);
 	if (!inflight)
-		goto unlock;
+		return;
 
 	/*
 	 * If we are already the currently executing context, don't
 	 * bother evaluating if we should preempt ourselves.
 	 */
 	if (inflight->context == rq->context)
-		goto unlock;
+		return;
 
 	ENGINE_TRACE(engine,
 		     "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
@@ -222,30 +281,28 @@ static void kick_submission(struct intel_engine_cs *engine,
 	engine->execlists.queue_priority_hint = prio;
 	if (need_preempt(prio, rq_prio(inflight)))
 		tasklet_hi_schedule(&engine->execlists.tasklet);
-
-unlock:
-	rcu_read_unlock();
 }
 
-static void __i915_schedule(struct i915_sched_node *node, int prio)
+static void ipi_priority(struct i915_request *rq, int prio)
 {
-	struct intel_engine_cs *engine;
-	struct i915_dependency *dep, *p;
-	struct i915_dependency stack;
-	struct sched_cache cache;
-	LIST_HEAD(dfs);
+	int old = READ_ONCE(rq->sched.ipi_priority);
 
-	/* Needed in order to use the temporary link inside i915_dependency */
-	lockdep_assert_held(&schedule_lock);
-	GEM_BUG_ON(prio == I915_PRIORITY_INVALID);
+	do {
+		if (prio <= old)
+			return;
+	} while (!try_cmpxchg(&rq->sched.ipi_priority, &old, prio));
 
-	if (node_signaled(node))
-		return;
+	__ipi_add(rq);
+}
 
-	prio = max(prio, node->attr.priority);
+static void __i915_request_set_priority(struct i915_request *rq, int prio)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	struct i915_request *rn;
+	struct list_head *plist;
+	LIST_HEAD(dfs);
 
-	stack.signaler = node;
-	list_add(&stack.dfs_link, &dfs);
+	list_add(&rq->sched.dfs, &dfs);
 
 	/*
 	 * Recursively bump all dependent priorities to match the new request.
@@ -265,66 +322,41 @@ static void __i915_schedule(struct i915_sched_node *node, int prio)
 	 * end result is a topological list of requests in reverse order, the
 	 * last element in the list is the request we must execute first.
 	 */
-	list_for_each_entry(dep, &dfs, dfs_link) {
-		struct i915_sched_node *node = dep->signaler;
+	list_for_each_entry(rq, &dfs, sched.dfs) {
+		struct i915_dependency *p;
 
-		/* If we are already flying, we know we have no signalers */
-		if (node_started(node))
-			continue;
+		/* Also release any children on this engine that are ready */
+		GEM_BUG_ON(rq->engine != engine);
 
-		/*
-		 * Within an engine, there can be no cycle, but we may
-		 * refer to the same dependency chain multiple times
-		 * (redundant dependencies are not eliminated) and across
-		 * engines.
-		 */
-		list_for_each_entry(p, &node->signalers_list, signal_link) {
-			GEM_BUG_ON(p == dep); /* no cycles! */
+		for_each_signaler(p, rq) {
+			struct i915_request *s =
+				container_of(p->signaler, typeof(*s), sched);
 
-			if (node_signaled(p->signaler))
-				continue;
+			GEM_BUG_ON(s == rq);
 
-			if (prio > READ_ONCE(p->signaler->attr.priority))
-				list_move_tail(&p->dfs_link, &dfs);
-		}
-	}
+			if (rq_prio(s) >= prio)
+				continue;
 
-	/*
-	 * If we didn't need to bump any existing priorities, and we haven't
-	 * yet submitted this request (i.e. there is no potential race with
-	 * execlists_submit_request()), we can set our own priority and skip
-	 * acquiring the engine locks.
-	 */
-	if (node->attr.priority == I915_PRIORITY_INVALID) {
-		GEM_BUG_ON(!list_empty(&node->link));
-		node->attr.priority = prio;
+			if (__i915_request_is_complete(s))
+				continue;
 
-		if (stack.dfs_link.next == stack.dfs_link.prev)
-			return;
+			if (s->engine != rq->engine) {
+				ipi_priority(s, prio);
+				continue;
+			}
 
-		__list_del_entry(&stack.dfs_link);
+			list_move_tail(&s->sched.dfs, &dfs);
+		}
 	}
 
-	memset(&cache, 0, sizeof(cache));
-	engine = node_to_request(node)->engine;
-	spin_lock(&engine->active.lock);
-
-	/* Fifo and depth-first replacement ensure our deps execute before us */
-	engine = sched_lock_engine(node, engine, &cache);
-	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
-		INIT_LIST_HEAD(&dep->dfs_link);
+	plist = i915_sched_lookup_priolist(engine, prio);
 
-		node = dep->signaler;
-		engine = sched_lock_engine(node, engine, &cache);
-		lockdep_assert_held(&engine->active.lock);
-
-		/* Recheck after acquiring the engine->timeline.lock */
-		if (prio <= node->attr.priority || node_signaled(node))
-			continue;
+	/* Fifo and depth-first replacement ensure our deps execute first */
+	list_for_each_entry_safe_reverse(rq, rn, &dfs, sched.dfs) {
+		GEM_BUG_ON(rq->engine != engine);
 
-		GEM_BUG_ON(node_to_request(node)->engine != engine);
-
-		WRITE_ONCE(node->attr.priority, prio);
+		INIT_LIST_HEAD(&rq->sched.dfs);
+		WRITE_ONCE(rq->sched.attr.priority, prio);
 
 		/*
 		 * Once the request is ready, it will be placed into the
@@ -334,32 +366,73 @@ static void __i915_schedule(struct i915_sched_node *node, int prio)
 		 * any preemption required, be dealt with upon submission.
 		 * See engine->submit_request()
 		 */
-		if (list_empty(&node->link))
+		if (!i915_request_is_ready(rq))
 			continue;
 
-		if (i915_request_in_priority_queue(node_to_request(node))) {
-			if (!cache.priolist)
-				cache.priolist =
-					i915_sched_lookup_priolist(engine,
-								   prio);
-			list_move_tail(&node->link, cache.priolist);
-		}
+		if (i915_request_in_priority_queue(rq))
+			list_move_tail(&rq->sched.link, plist);
 
-		/* Defer (tasklet) submission until after all of our updates. */
-		kick_submission(engine, node_to_request(node), prio);
+		/* Defer (tasklet) submission until after all updates. */
+		kick_submission(engine, rq, prio);
 	}
-
-	spin_unlock(&engine->active.lock);
 }
 
 void i915_request_set_priority(struct i915_request *rq, int prio)
 {
-	if (!intel_engine_has_scheduler(rq->engine))
+	struct intel_engine_cs *engine;
+	unsigned long flags;
+
+	if (prio <= rq_prio(rq))
 		return;
 
-	spin_lock_irq(&schedule_lock);
-	__i915_schedule(&rq->sched, prio);
-	spin_unlock_irq(&schedule_lock);
+	/*
+	 * If we are setting the priority before being submitted, see if we
+	 * can quickly adjust our own priority in-situ and avoid taking
+	 * the contended engine->active.lock. If we need priority inheritance,
+	 * take the slow route.
+	 */
+	if (rq_prio(rq) == I915_PRIORITY_INVALID) {
+		struct i915_dependency *p;
+
+		rcu_read_lock();
+		for_each_signaler(p, rq) {
+			struct i915_request *s =
+				container_of(p->signaler, typeof(*s), sched);
+
+			if (rq_prio(s) >= prio)
+				continue;
+
+			if (__i915_request_is_complete(s))
+				continue;
+
+			break;
+		}
+		rcu_read_unlock();
+
+		if (&p->signal_link == &rq->sched.signalers_list &&
+		    cmpxchg(&rq->sched.attr.priority,
+			    I915_PRIORITY_INVALID,
+			    prio) == I915_PRIORITY_INVALID)
+			return;
+	}
+
+	engine = lock_engine_irqsave(rq, flags);
+	if (!intel_engine_has_scheduler(engine))
+		goto unlock;
+
+	if (i915_request_completed(rq))
+		goto unlock;
+
+	if (prio <= rq_prio(rq))
+		goto unlock;
+
+	rcu_read_lock();
+	__i915_request_set_priority(rq, prio);
+	rcu_read_unlock();
+	GEM_BUG_ON(rq_prio(rq) != prio);
+
+unlock:
+	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
 void i915_sched_node_init(struct i915_sched_node *node)
@@ -369,6 +442,9 @@ void i915_sched_node_init(struct i915_sched_node *node)
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
+	INIT_LIST_HEAD(&node->dfs);
+
+	node->ipi_link = NULL;
 
 	i915_sched_node_reinit(node);
 }
@@ -379,6 +455,9 @@ void i915_sched_node_reinit(struct i915_sched_node *node)
 	node->semaphores = 0;
 	node->flags = 0;
 
+	GEM_BUG_ON(node->ipi_link);
+	node->ipi_priority = I915_PRIORITY_INVALID;
+
 	GEM_BUG_ON(!list_empty(&node->signalers_list));
 	GEM_BUG_ON(!list_empty(&node->waiters_list));
 	GEM_BUG_ON(!list_empty(&node->link));
@@ -414,7 +493,6 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 	spin_lock(&signal->lock);
 
 	if (!node_signaled(signal)) {
-		INIT_LIST_HEAD(&dep->dfs_link);
 		dep->signaler = signal;
 		dep->waiter = node_get(node);
 		dep->flags = flags;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index a045be784c67..5be7f90e7896 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -35,6 +35,8 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 
 void i915_sched_node_retire(struct i915_sched_node *node);
 
+void i915_sched_init_ipi(struct i915_sched_ipi *ipi);
+
 void i915_request_set_priority(struct i915_request *request, int prio);
 
 struct list_head *
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 623bf41fcf35..5a84d59134ee 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -8,8 +8,8 @@
 #define _I915_SCHEDULER_TYPES_H_
 
 #include <linux/list.h>
+#include <linux/workqueue.h>
 
-#include "gt/intel_engine_types.h"
 #include "i915_priolist_types.h"
 
 struct drm_i915_private;
@@ -61,13 +61,23 @@ struct i915_sched_attr {
  */
 struct i915_sched_node {
 	spinlock_t lock; /* protect the lists */
+
 	struct list_head signalers_list; /* those before us, we depend upon */
 	struct list_head waiters_list; /* those after us, they depend upon us */
-	struct list_head link;
+	struct list_head link; /* guarded by engine->active.lock */
+	struct list_head dfs; /* guarded by engine->active.lock */
 	struct i915_sched_attr attr;
-	unsigned int flags;
+	unsigned long flags;
 #define I915_SCHED_HAS_EXTERNAL_CHAIN	BIT(0)
-	intel_engine_mask_t semaphores;
+	unsigned long semaphores;
+
+	struct i915_request *ipi_link;
+	int ipi_priority;
+};
+
+struct i915_sched_ipi {
+	struct i915_request *list;
+	struct work_struct work;
 };
 
 struct i915_dependency {
@@ -75,7 +85,6 @@ struct i915_dependency {
 	struct i915_sched_node *waiter;
 	struct list_head signal_link;
 	struct list_head wait_link;
-	struct list_head dfs_link;
 	struct rcu_head rcu;
 	unsigned long flags;
 #define I915_DEPENDENCY_ALLOC		BIT(0)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 28/62] drm/i915/selftests: Measure set-priority duration

[Chris Wilson]

As a topological sort, we expect it to run in linear graph time,
O(V+E). In removing the recursion, it is no longer a DFS but rather a
BFS, and performs as O(VE). Let's demonstrate how bad this is with a few
examples, and build a few test cases to verify a potential fix.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_scheduler.c         |   4 +
 .../drm/i915/selftests/i915_live_selftests.h  |   1 +
 .../drm/i915/selftests/i915_perf_selftests.h  |   1 +
 .../gpu/drm/i915/selftests/i915_scheduler.c   | 679 ++++++++++++++++++
 4 files changed, 685 insertions(+)
 create mode 100644 drivers/gpu/drm/i915/selftests/i915_scheduler.c

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 5fda1d29381b..8f2bfba9df7d 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -590,6 +590,10 @@ void i915_request_show_with_schedule(struct drm_printer *m,
 	rcu_read_unlock();
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_scheduler.c"
+#endif
+
 static void i915_global_scheduler_shrink(void)
 {
 	kmem_cache_shrink(global.slab_dependencies);
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index a92c0e9b7e6b..2200a5baa68e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -26,6 +26,7 @@ selftest(gt_mocs, intel_mocs_live_selftests)
 selftest(gt_pm, intel_gt_pm_live_selftests)
 selftest(gt_heartbeat, intel_heartbeat_live_selftests)
 selftest(requests, i915_request_live_selftests)
+selftest(scheduler, i915_scheduler_live_selftests)
 selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
 selftest(mman, i915_gem_mman_live_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
index c2389f8a257d..137e35283fee 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
@@ -17,5 +17,6 @@
  */
 selftest(engine_cs, intel_engine_cs_perf_selftests)
 selftest(request, i915_request_perf_selftests)
+selftest(scheduler, i915_scheduler_perf_selftests)
 selftest(blt, i915_gem_object_blt_perf_selftests)
 selftest(region, intel_memory_region_perf_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
new file mode 100644
index 000000000000..b68c5b6fb598
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -0,0 +1,679 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_selftest.h"
+
+#include "gt/intel_context.h"
+#include "gt/intel_gpu_commands.h"
+#include "gt/selftest_engine_heartbeat.h"
+#include "selftests/igt_spinner.h"
+#include "selftests/i915_random.h"
+
+static void scheduling_disable(struct intel_engine_cs *engine)
+{
+	engine->props.preempt_timeout_ms = 0;
+	engine->props.timeslice_duration_ms = 0;
+
+	st_engine_heartbeat_disable(engine);
+}
+
+static void scheduling_enable(struct intel_engine_cs *engine)
+{
+	st_engine_heartbeat_enable(engine);
+
+	engine->props.preempt_timeout_ms =
+		engine->defaults.preempt_timeout_ms;
+	engine->props.timeslice_duration_ms =
+		engine->defaults.timeslice_duration_ms;
+}
+
+static int first_engine(struct drm_i915_private *i915,
+			int (*chain)(struct intel_engine_cs *engine,
+				     unsigned long param,
+				     bool (*fn)(struct i915_request *rq,
+						unsigned long v,
+						unsigned long e)),
+			unsigned long param,
+			bool (*fn)(struct i915_request *rq,
+				   unsigned long v, unsigned long e))
+{
+	struct intel_engine_cs *engine;
+
+	for_each_uabi_engine(engine, i915) {
+		if (!intel_engine_has_scheduler(engine))
+			continue;
+
+		return chain(engine, param, fn);
+	}
+
+	return 0;
+}
+
+static int all_engines(struct drm_i915_private *i915,
+		       int (*chain)(struct intel_engine_cs *engine,
+				    unsigned long param,
+				    bool (*fn)(struct i915_request *rq,
+					       unsigned long v,
+					       unsigned long e)),
+		       unsigned long param,
+		       bool (*fn)(struct i915_request *rq,
+				  unsigned long v, unsigned long e))
+{
+	struct intel_engine_cs *engine;
+	int err;
+
+	for_each_uabi_engine(engine, i915) {
+		if (!intel_engine_has_scheduler(engine))
+			continue;
+
+		err = chain(engine, param, fn);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool check_context_order(struct intel_engine_cs *engine)
+{
+	u64 last_seqno, last_context;
+	unsigned long count;
+	bool result = false;
+	struct rb_node *rb;
+	int last_prio;
+
+	/* We expect the execution order to follow ascending fence-context */
+	spin_lock_irq(&engine->active.lock);
+
+	count = 0;
+	last_context = 0;
+	last_seqno = 0;
+	last_prio = 0;
+	for (rb = rb_first_cached(&engine->execlists.queue); rb; rb = rb_next(rb)) {
+		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
+		struct i915_request *rq;
+
+		priolist_for_each_request(rq, p) {
+			if (rq->fence.context < last_context ||
+			    (rq->fence.context == last_context &&
+			     rq->fence.seqno < last_seqno)) {
+				pr_err("[%lu] %llx:%lld [prio:%d] after %llx:%lld [prio:%d]\n",
+				       count,
+				       rq->fence.context,
+				       rq->fence.seqno,
+				       rq_prio(rq),
+				       last_context,
+				       last_seqno,
+				       last_prio);
+				goto out_unlock;
+			}
+
+			last_context = rq->fence.context;
+			last_seqno = rq->fence.seqno;
+			last_prio = rq_prio(rq);
+			count++;
+		}
+	}
+	result = true;
+out_unlock:
+	spin_unlock_irq(&engine->active.lock);
+
+	return result;
+}
+
+static int __single_chain(struct intel_engine_cs *engine, unsigned long length,
+			  bool (*fn)(struct i915_request *rq,
+				     unsigned long v, unsigned long e))
+{
+	struct intel_context *ce;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	unsigned long count;
+	unsigned long min;
+	int err = 0;
+
+	if (!intel_engine_can_store_dword(engine))
+		return 0;
+
+	scheduling_disable(engine);
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		err = -ENOMEM;
+		goto err_heartbeat;
+	}
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce)) {
+		err = PTR_ERR(ce);
+		goto err_spin;
+	}
+	ce->ring = __intel_context_ring_size(SZ_512K);
+
+	rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_context;
+	}
+	i915_request_add(rq);
+	min = ce->ring->size - ce->ring->space;
+
+	count = 1;
+	while (count < length && ce->ring->space > min) {
+		rq = intel_context_create_request(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+		i915_request_add(rq);
+		count++;
+	}
+	intel_engine_flush_submission(engine);
+
+	tasklet_disable(&engine->execlists.tasklet);
+	local_bh_disable();
+	if (fn(rq, count, count - 1) && !check_context_order(engine))
+		err = -EINVAL;
+	local_bh_enable();
+	tasklet_enable(&engine->execlists.tasklet);
+
+	igt_spinner_end(&spin);
+err_context:
+	intel_context_put(ce);
+err_spin:
+	igt_spinner_fini(&spin);
+err_heartbeat:
+	scheduling_enable(engine);
+	return err;
+}
+
+static int __wide_chain(struct intel_engine_cs *engine, unsigned long width,
+			bool (*fn)(struct i915_request *rq,
+				   unsigned long v, unsigned long e))
+{
+	struct intel_context **ce;
+	struct i915_request **rq;
+	struct igt_spinner spin;
+	unsigned long count;
+	unsigned long i, j;
+	int err = 0;
+
+	if (!intel_engine_can_store_dword(engine))
+		return 0;
+
+	scheduling_disable(engine);
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		err = -ENOMEM;
+		goto err_heartbeat;
+	}
+
+	ce = kmalloc_array(width, sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		err = -ENOMEM;
+		goto err_spin;
+	}
+
+	for (i = 0; i < width; i++) {
+		ce[i] = intel_context_create(engine);
+		if (IS_ERR(ce[i])) {
+			err = PTR_ERR(ce[i]);
+			width = i;
+			goto err_context;
+		}
+	}
+
+	rq = kmalloc_array(width, sizeof(*rq), GFP_KERNEL);
+	if (!rq) {
+		err = -ENOMEM;
+		goto err_context;
+	}
+
+	rq[0] = igt_spinner_create_request(&spin, ce[0], MI_NOOP);
+	if (IS_ERR(rq[0])) {
+		err = PTR_ERR(rq[0]);
+		goto err_free;
+	}
+	i915_request_add(rq[0]);
+
+	count = 0;
+	for (i = 1; i < width; i++) {
+		GEM_BUG_ON(i915_request_completed(rq[0]));
+
+		rq[i] = intel_context_create_request(ce[i]);
+		if (IS_ERR(rq[i])) {
+			err = PTR_ERR(rq[i]);
+			break;
+		}
+		for (j = 0; j < i; j++) {
+			err = i915_request_await_dma_fence(rq[i],
+							   &rq[j]->fence);
+			if (err)
+				break;
+			count++;
+		}
+		i915_request_add(rq[i]);
+	}
+	intel_engine_flush_submission(engine);
+
+	tasklet_disable(&engine->execlists.tasklet);
+	local_bh_disable();
+	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
+		err = -EINVAL;
+	local_bh_enable();
+	tasklet_enable(&engine->execlists.tasklet);
+
+	igt_spinner_end(&spin);
+err_free:
+	kfree(rq);
+err_context:
+	for (i = 0; i < width; i++)
+		intel_context_put(ce[i]);
+	kfree(ce);
+err_spin:
+	igt_spinner_fini(&spin);
+err_heartbeat:
+	scheduling_enable(engine);
+	return err;
+}
+
+static int __inv_chain(struct intel_engine_cs *engine, unsigned long width,
+		       bool (*fn)(struct i915_request *rq,
+				  unsigned long v, unsigned long e))
+{
+	struct intel_context **ce;
+	struct i915_request **rq;
+	struct igt_spinner spin;
+	unsigned long count;
+	unsigned long i, j;
+	int err = 0;
+
+	if (!intel_engine_can_store_dword(engine))
+		return 0;
+
+	scheduling_disable(engine);
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		err = -ENOMEM;
+		goto err_heartbeat;
+	}
+
+	ce = kmalloc_array(width, sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		err = -ENOMEM;
+		goto err_spin;
+	}
+
+	for (i = 0; i < width; i++) {
+		ce[i] = intel_context_create(engine);
+		if (IS_ERR(ce[i])) {
+			err = PTR_ERR(ce[i]);
+			width = i;
+			goto err_context;
+		}
+	}
+
+	rq = kmalloc_array(width, sizeof(*rq), GFP_KERNEL);
+	if (!rq) {
+		err = -ENOMEM;
+		goto err_context;
+	}
+
+	rq[0] = igt_spinner_create_request(&spin, ce[0], MI_NOOP);
+	if (IS_ERR(rq[0])) {
+		err = PTR_ERR(rq[0]);
+		goto err_free;
+	}
+	i915_request_add(rq[0]);
+
+	count = 0;
+	for (i = 1; i < width; i++) {
+		GEM_BUG_ON(i915_request_completed(rq[0]));
+
+		rq[i] = intel_context_create_request(ce[i]);
+		if (IS_ERR(rq[i])) {
+			err = PTR_ERR(rq[i]);
+			break;
+		}
+		for (j = i; j > 0; j--) {
+			err = i915_request_await_dma_fence(rq[i],
+							   &rq[j - 1]->fence);
+			if (err)
+				break;
+			count++;
+		}
+		i915_request_add(rq[i]);
+	}
+	intel_engine_flush_submission(engine);
+
+	tasklet_disable(&engine->execlists.tasklet);
+	local_bh_disable();
+	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
+		err = -EINVAL;
+	local_bh_enable();
+	tasklet_enable(&engine->execlists.tasklet);
+
+	igt_spinner_end(&spin);
+err_free:
+	kfree(rq);
+err_context:
+	for (i = 0; i < width; i++)
+		intel_context_put(ce[i]);
+	kfree(ce);
+err_spin:
+	igt_spinner_fini(&spin);
+err_heartbeat:
+	scheduling_enable(engine);
+	return err;
+}
+
+static int __sparse_chain(struct intel_engine_cs *engine, unsigned long width,
+			  bool (*fn)(struct i915_request *rq,
+				     unsigned long v, unsigned long e))
+{
+	struct intel_context **ce;
+	struct i915_request **rq;
+	struct igt_spinner spin;
+	I915_RND_STATE(prng);
+	unsigned long count;
+	unsigned long i, j;
+	int err = 0;
+
+	if (!intel_engine_can_store_dword(engine))
+		return 0;
+
+	scheduling_disable(engine);
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		err = -ENOMEM;
+		goto err_heartbeat;
+	}
+
+	ce = kmalloc_array(width, sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		err = -ENOMEM;
+		goto err_spin;
+	}
+
+	for (i = 0; i < width; i++) {
+		ce[i] = intel_context_create(engine);
+		if (IS_ERR(ce[i])) {
+			err = PTR_ERR(ce[i]);
+			width = i;
+			goto err_context;
+		}
+	}
+
+	rq = kmalloc_array(width, sizeof(*rq), GFP_KERNEL);
+	if (!rq) {
+		err = -ENOMEM;
+		goto err_context;
+	}
+
+	rq[0] = igt_spinner_create_request(&spin, ce[0], MI_NOOP);
+	if (IS_ERR(rq[0])) {
+		err = PTR_ERR(rq[0]);
+		goto err_free;
+	}
+	i915_request_add(rq[0]);
+
+	count = 0;
+	for (i = 1; i < width; i++) {
+		GEM_BUG_ON(i915_request_completed(rq[0]));
+
+		rq[i] = intel_context_create_request(ce[i]);
+		if (IS_ERR(rq[i])) {
+			err = PTR_ERR(rq[i]);
+			break;
+		}
+
+		if (err == 0 && i > 1) {
+			j = i915_prandom_u32_max_state(i - 1, &prng);
+			err = i915_request_await_dma_fence(rq[i],
+							   &rq[j]->fence);
+			count++;
+		}
+
+		if (err == 0) {
+			err = i915_request_await_dma_fence(rq[i],
+							   &rq[i - 1]->fence);
+			count++;
+		}
+
+		if (err == 0 && i > 2) {
+			j = i915_prandom_u32_max_state(i - 2, &prng);
+			err = i915_request_await_dma_fence(rq[i],
+							   &rq[j]->fence);
+			count++;
+		}
+
+		i915_request_add(rq[i]);
+		if (err)
+			break;
+	}
+	intel_engine_flush_submission(engine);
+
+	tasklet_disable(&engine->execlists.tasklet);
+	local_bh_disable();
+	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
+		err = -EINVAL;
+	local_bh_enable();
+	tasklet_enable(&engine->execlists.tasklet);
+
+	igt_spinner_end(&spin);
+err_free:
+	kfree(rq);
+err_context:
+	for (i = 0; i < width; i++)
+		intel_context_put(ce[i]);
+	kfree(ce);
+err_spin:
+	igt_spinner_fini(&spin);
+err_heartbeat:
+	scheduling_enable(engine);
+	return err;
+}
+
+static int igt_schedule_chains(struct drm_i915_private *i915,
+			       bool (*fn)(struct i915_request *rq,
+					  unsigned long v, unsigned long e))
+{
+	static int (* const chains[])(struct intel_engine_cs *engine,
+				      unsigned long length,
+				      bool (*fn)(struct i915_request *rq,
+						 unsigned long v, unsigned long e)) = {
+		__single_chain,
+		__wide_chain,
+		__inv_chain,
+		__sparse_chain,
+	};
+	int n, err;
+
+	for (n = 0; n < ARRAY_SIZE(chains); n++) {
+		err = all_engines(i915, chains[n], 17, fn);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool igt_priority(struct i915_request *rq,
+			 unsigned long v, unsigned long e)
+{
+	i915_request_set_priority(rq, I915_PRIORITY_BARRIER);
+	GEM_BUG_ON(rq_prio(rq) != I915_PRIORITY_BARRIER);
+	return true;
+}
+
+static int igt_priority_chains(void *arg)
+{
+	return igt_schedule_chains(arg, igt_priority);
+}
+
+int i915_scheduler_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_priority_chains),
+	};
+
+	return i915_subtests(tests, i915);
+}
+
+static int chains(struct drm_i915_private *i915,
+		  int (*chain)(struct drm_i915_private *i915,
+			       unsigned long length,
+			       bool (*fn)(struct i915_request *rq,
+					  unsigned long v, unsigned long e)),
+		  bool (*fn)(struct i915_request *rq,
+			     unsigned long v, unsigned long e))
+{
+	unsigned long x[] = { 1, 4, 16, 64, 128, 256, 512, 1024, 4096 };
+	int i, err;
+
+	for (i = 0; i < ARRAY_SIZE(x); i++) {
+		IGT_TIMEOUT(end_time);
+
+		err = chain(i915, x[i], fn);
+		if (err)
+			return err;
+
+		if (__igt_timeout(end_time, NULL))
+			break;
+	}
+
+	return 0;
+}
+
+static int single_chain(struct drm_i915_private *i915,
+			unsigned long length,
+			bool (*fn)(struct i915_request *rq,
+				   unsigned long v, unsigned long e))
+{
+	return first_engine(i915, __single_chain, length, fn);
+}
+
+static int single(struct drm_i915_private *i915,
+		  bool (*fn)(struct i915_request *rq,
+			     unsigned long v, unsigned long e))
+{
+	return chains(i915, single_chain, fn);
+}
+
+static int wide_chain(struct drm_i915_private *i915,
+		      unsigned long width,
+		      bool (*fn)(struct i915_request *rq,
+				 unsigned long v, unsigned long e))
+{
+	return first_engine(i915, __wide_chain, width, fn);
+}
+
+static int wide(struct drm_i915_private *i915,
+		bool (*fn)(struct i915_request *rq,
+			   unsigned long v, unsigned long e))
+{
+	return chains(i915, wide_chain, fn);
+}
+
+static int inv_chain(struct drm_i915_private *i915,
+		     unsigned long width,
+		     bool (*fn)(struct i915_request *rq,
+				unsigned long v, unsigned long e))
+{
+	return first_engine(i915, __inv_chain, width, fn);
+}
+
+static int inv(struct drm_i915_private *i915,
+	       bool (*fn)(struct i915_request *rq,
+			  unsigned long v, unsigned long e))
+{
+	return chains(i915, inv_chain, fn);
+}
+
+static int sparse_chain(struct drm_i915_private *i915,
+			unsigned long width,
+			bool (*fn)(struct i915_request *rq,
+				   unsigned long v, unsigned long e))
+{
+	return first_engine(i915, __sparse_chain, width, fn);
+}
+
+static int sparse(struct drm_i915_private *i915,
+		  bool (*fn)(struct i915_request *rq,
+			     unsigned long v, unsigned long e))
+{
+	return chains(i915, sparse_chain, fn);
+}
+
+static void report(const char *what, unsigned long v, unsigned long e, u64 dt)
+{
+	pr_info("(%4lu, %7lu), %s:%10lluns\n", v, e, what, dt);
+}
+
+static u64 __set_priority(struct i915_request *rq, int prio)
+{
+	u64 dt;
+
+	preempt_disable();
+	dt = ktime_get_raw_fast_ns();
+	i915_request_set_priority(rq, prio);
+	dt = ktime_get_raw_fast_ns() - dt;
+	preempt_enable();
+
+	return dt;
+}
+
+static bool set_priority(struct i915_request *rq,
+			 unsigned long v, unsigned long e)
+{
+	report("set-priority", v, e, __set_priority(rq, I915_PRIORITY_BARRIER));
+	return true;
+}
+
+static int single_priority(void *arg)
+{
+	return single(arg, set_priority);
+}
+
+static int wide_priority(void *arg)
+{
+	return wide(arg, set_priority);
+}
+
+static int inv_priority(void *arg)
+{
+	return inv(arg, set_priority);
+}
+
+static int sparse_priority(void *arg)
+{
+	return sparse(arg, set_priority);
+}
+
+int i915_scheduler_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(single_priority),
+		SUBTEST(wide_priority),
+		SUBTEST(inv_priority),
+		SUBTEST(sparse_priority),
+	};
+	static const struct {
+		const char *name;
+		size_t sz;
+	} types[] = {
+#define T(t) { #t, sizeof(struct t) }
+		T(i915_priolist),
+		T(i915_sched_attr),
+		T(i915_sched_node),
+#undef T
+		{}
+	};
+	typeof(*types) *t;
+
+	for (t = types; t->name; t++)
+		pr_info("sizeof%s): %zx\n", t->name, t->sz);
+
+	return i915_subtests(tests, i915);
+}
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 29/62] drm/i915/selftests: Exercise priority inheritance around an engine loop

[Chris Wilson]

Exercise rescheduling priority inheritance around a sequence of requests
that wrap around all the engines.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/selftests/i915_scheduler.c   | 219 ++++++++++++++++++
 1 file changed, 219 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index b68c5b6fb598..83739131d478 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -7,6 +7,7 @@
 
 #include "gt/intel_context.h"
 #include "gt/intel_gpu_commands.h"
+#include "gt/intel_ring.h"
 #include "gt/selftest_engine_heartbeat.h"
 #include "selftests/igt_spinner.h"
 #include "selftests/i915_random.h"
@@ -512,10 +513,228 @@ static int igt_priority_chains(void *arg)
 	return igt_schedule_chains(arg, igt_priority);
 }
 
+static struct i915_request *
+__write_timestamp(struct intel_engine_cs *engine,
+		  struct drm_i915_gem_object *obj,
+		  int slot,
+		  struct i915_request *prev)
+{
+	struct i915_request *rq = ERR_PTR(-EINVAL);
+	struct intel_context *ce;
+	struct i915_vma *vma;
+	int err = 0;
+	u32 *cs;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_ce;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto out_ce;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_unpin;
+	}
+
+	i915_vma_lock(vma);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unlock(vma);
+	if (err)
+		goto out_request;
+
+	if (prev) {
+		err = i915_request_await_dma_fence(rq, &prev->fence);
+		if (err)
+			goto out_request;
+	}
+
+	if (engine->emit_init_breadcrumb) {
+		err = engine->emit_init_breadcrumb(rq);
+		if (err)
+			goto out_request;
+	}
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto out_request;
+	}
+
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8;
+	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(engine->mmio_base));
+	*cs++ = lower_32_bits(vma->node.start) + sizeof(u32) * slot;
+	*cs++ = upper_32_bits(vma->node.start);
+	intel_ring_advance(rq, cs);
+
+	i915_request_get(rq);
+out_request:
+	i915_request_add(rq);
+out_unpin:
+	i915_vma_unpin(vma);
+out_ce:
+	intel_context_put(ce);
+	i915_request_put(prev);
+	return err ? ERR_PTR(err) : rq;
+}
+
+static struct i915_request *create_spinner(struct drm_i915_private *i915,
+					   struct igt_spinner *spin)
+{
+	struct intel_engine_cs *engine;
+
+	for_each_uabi_engine(engine, i915) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		if (igt_spinner_init(spin, engine->gt))
+			return ERR_PTR(-ENOMEM);
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			return ERR_CAST(ce);
+
+		rq = igt_spinner_create_request(spin, ce, MI_NOOP);
+		intel_context_put(ce);
+		if (rq == ERR_PTR(-ENODEV))
+			continue;
+		if (IS_ERR(rq))
+			return rq;
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+		return rq;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static int __igt_schedule_cycle(struct drm_i915_private *i915,
+				bool (*fn)(struct i915_request *rq,
+					   unsigned long v, unsigned long e))
+{
+	struct intel_engine_cs *engine;
+	struct drm_i915_gem_object *obj;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	unsigned long count, n;
+	u32 *time, last;
+	int err;
+
+	/*
+	 * Queue a bunch of ordered requests (each waiting on the previous)
+	 * around the engines a couple of times. Each request will write
+	 * the timestamp it executes at into the scratch, with the expectation
+	 * that the timestamp will be in our desired execution order.
+	 */
+
+	if (INTEL_GEN(i915) < 8)
+		return 0;
+
+	obj = i915_gem_object_create_internal(i915, SZ_64K);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	time = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(time)) {
+		err = PTR_ERR(time);
+		goto out_obj;
+	}
+
+	rq = create_spinner(i915, &spin);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_obj;
+	}
+
+	err = 0;
+	count = 0;
+	for_each_uabi_engine(engine, i915) {
+		if (!intel_engine_has_scheduler(engine))
+			continue;
+
+		rq = __write_timestamp(engine, obj, count, rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		count++;
+	}
+	for_each_uabi_engine(engine, i915) {
+		if (!intel_engine_has_scheduler(engine))
+			continue;
+
+		rq = __write_timestamp(engine, obj, count, rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		count++;
+	}
+	GEM_BUG_ON(count * sizeof(u32) > obj->base.size);
+	if (err || !count)
+		goto out_spin;
+
+	fn(rq, count + 1, count);
+	igt_spinner_end(&spin);
+
+	if (i915_request_wait(rq, 0, HZ / 2) < 0) {
+		err = -ETIME;
+		goto out_request;
+	}
+
+	last = time[0];
+	for (n = 1; n < count; n++) {
+		if (i915_seqno_passed(last, time[n])) {
+			pr_err("Timestamp[%lu] %x before previous %x\n",
+			       n, time[n], last);
+			err = -EINVAL;
+			break;
+		}
+		last = time[n];
+	}
+
+out_request:
+	i915_request_put(rq);
+out_spin:
+	igt_spinner_fini(&spin);
+out_obj:
+	i915_gem_object_put(obj);
+	return 0;
+}
+
+static bool noop(struct i915_request *rq, unsigned long v, unsigned long e)
+{
+	return true;
+}
+
+static int igt_schedule_cycle(void *arg)
+{
+	return __igt_schedule_cycle(arg, noop);
+}
+
+static int igt_priority_cycle(void *arg)
+{
+	return __igt_schedule_cycle(arg, igt_priority);
+}
+
 int i915_scheduler_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_priority_chains),
+
+		SUBTEST(igt_schedule_cycle),
+		SUBTEST(igt_priority_cycle),
 	};
 
 	return i915_subtests(tests, i915);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 30/62] drm/i915: Improve DFS for priority inheritance

[Chris Wilson]

The core of the scheduling algorithm is that we compute the topological
order of the fence DAG. Knowing that we have a DAG, we should be able to
use a DFS to compute the topological sort in linear time. However,
during the conversion of the recursive algorithm into an iterative one,
the memorization of how far we had progressed down a branch was
forgotten.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_scheduler.c | 58 ++++++++++++++++-----------
 1 file changed, 34 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 8f2bfba9df7d..c3605da21dec 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -234,6 +234,26 @@ void __i915_priolist_free(struct i915_priolist *p)
 	kmem_cache_free(global.slab_priorities, p);
 }
 
+static struct i915_request *
+stack_push(struct i915_request *rq,
+	   struct i915_request *stack,
+	   struct list_head *pos)
+{
+	stack->sched.dfs.prev = pos;
+	rq->sched.dfs.next = (struct list_head *)stack;
+	return rq;
+}
+
+static struct i915_request *
+stack_pop(struct i915_request *rq,
+	  struct list_head **pos)
+{
+	rq = (struct i915_request *)rq->sched.dfs.next;
+	if (rq)
+		*pos = rq->sched.dfs.prev;
+	return rq;
+}
+
 static inline bool need_preempt(int prio, int active)
 {
 	/*
@@ -298,11 +318,10 @@ static void ipi_priority(struct i915_request *rq, int prio)
 static void __i915_request_set_priority(struct i915_request *rq, int prio)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_request *rn;
+	struct list_head *pos = &rq->sched.signalers_list;
 	struct list_head *plist;
-	LIST_HEAD(dfs);
 
-	list_add(&rq->sched.dfs, &dfs);
+	plist = i915_sched_lookup_priolist(engine, prio);
 
 	/*
 	 * Recursively bump all dependent priorities to match the new request.
@@ -322,40 +341,31 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 	 * end result is a topological list of requests in reverse order, the
 	 * last element in the list is the request we must execute first.
 	 */
-	list_for_each_entry(rq, &dfs, sched.dfs) {
-		struct i915_dependency *p;
-
-		/* Also release any children on this engine that are ready */
-		GEM_BUG_ON(rq->engine != engine);
-
-		for_each_signaler(p, rq) {
+	rq->sched.dfs.next = NULL;
+	do {
+		list_for_each_continue(pos, &rq->sched.signalers_list) {
+			struct i915_dependency *p =
+				list_entry(pos, typeof(*p), signal_link);
 			struct i915_request *s =
 				container_of(p->signaler, typeof(*s), sched);
 
-			GEM_BUG_ON(s == rq);
-
 			if (rq_prio(s) >= prio)
 				continue;
 
 			if (__i915_request_is_complete(s))
 				continue;
 
-			if (s->engine != rq->engine) {
+			if (s->engine != engine) {
 				ipi_priority(s, prio);
 				continue;
 			}
 
-			list_move_tail(&s->sched.dfs, &dfs);
+			/* Remember our position along this branch */
+			rq = stack_push(s, rq, pos);
+			pos = &rq->sched.signalers_list;
 		}
-	}
-
-	plist = i915_sched_lookup_priolist(engine, prio);
-
-	/* Fifo and depth-first replacement ensure our deps execute first */
-	list_for_each_entry_safe_reverse(rq, rn, &dfs, sched.dfs) {
-		GEM_BUG_ON(rq->engine != engine);
 
-		INIT_LIST_HEAD(&rq->sched.dfs);
+		RQ_TRACE(rq, "set-priority:%d\n", prio);
 		WRITE_ONCE(rq->sched.attr.priority, prio);
 
 		/*
@@ -369,12 +379,13 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 		if (!i915_request_is_ready(rq))
 			continue;
 
+		GEM_BUG_ON(rq->engine != engine);
 		if (i915_request_in_priority_queue(rq))
 			list_move_tail(&rq->sched.link, plist);
 
 		/* Defer (tasklet) submission until after all updates. */
 		kick_submission(engine, rq, prio);
-	}
+	} while ((rq = stack_pop(rq, &pos)));
 }
 
 void i915_request_set_priority(struct i915_request *rq, int prio)
@@ -442,7 +453,6 @@ void i915_sched_node_init(struct i915_sched_node *node)
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
-	INIT_LIST_HEAD(&node->dfs);
 
 	node->ipi_link = NULL;
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 31/62] drm/i915: Extract request submission from execlists

[Chris Wilson]

In the process of preparing to reuse the request submission logic for
other backends, lift it out of the execlists backend. It already
operates on the common structs, so just a matter of moving and renaming.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 55 +------------
 drivers/gpu/drm/i915/i915_scheduler.c         | 82 +++++++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler.h         |  2 +
 3 files changed, 85 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index bb462159688b..1ac940fb8846 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2345,59 +2345,6 @@ static void execlists_preempt(struct timer_list *timer)
 	execlists_kick(timer, preempt);
 }
 
-static void queue_request(struct intel_engine_cs *engine,
-			  struct i915_request *rq)
-{
-	GEM_BUG_ON(!list_empty(&rq->sched.link));
-	list_add_tail(&rq->sched.link,
-		      i915_sched_lookup_priolist(engine, rq_prio(rq)));
-	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-}
-
-static bool submit_queue(struct intel_engine_cs *engine,
-			 const struct i915_request *rq)
-{
-	struct intel_engine_execlists *execlists = &engine->execlists;
-
-	if (rq_prio(rq) <= execlists->queue_priority_hint)
-		return false;
-
-	execlists->queue_priority_hint = rq_prio(rq);
-	return true;
-}
-
-static bool ancestor_on_hold(const struct intel_engine_cs *engine,
-			     const struct i915_request *rq)
-{
-	GEM_BUG_ON(i915_request_on_hold(rq));
-	return !list_empty(&engine->active.hold) && hold_request(rq);
-}
-
-static void execlists_submit_request(struct i915_request *request)
-{
-	struct intel_engine_cs *engine = request->engine;
-	unsigned long flags;
-
-	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
-
-	if (unlikely(ancestor_on_hold(engine, request))) {
-		RQ_TRACE(request, "ancestor on hold\n");
-		list_add_tail(&request->sched.link, &engine->active.hold);
-		i915_request_set_hold(request);
-	} else {
-		queue_request(engine, request);
-
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
-		GEM_BUG_ON(list_empty(&request->sched.link));
-
-		if (submit_queue(engine, request))
-			__execlists_kick(&engine->execlists);
-	}
-
-	spin_unlock_irqrestore(&engine->active.lock, flags);
-}
-
 static int execlists_context_pre_pin(struct intel_context *ce,
 				     struct i915_gem_ww_ctx *ww,
 				     void **vaddr)
@@ -3025,7 +2972,7 @@ static void execlists_park(struct intel_engine_cs *engine)
 
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
-	engine->submit_request = execlists_submit_request;
+	engine->submit_request = i915_request_enqueue;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index c3605da21dec..38dc9f8715bd 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -446,6 +446,88 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void queue_request(struct intel_engine_cs *engine,
+			  struct i915_request *rq)
+{
+	GEM_BUG_ON(!list_empty(&rq->sched.link));
+	list_add_tail(&rq->sched.link,
+		      i915_sched_lookup_priolist(engine, rq_prio(rq)));
+	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+}
+
+static bool submit_queue(struct intel_engine_cs *engine,
+			 const struct i915_request *rq)
+{
+	struct intel_engine_execlists *execlists = &engine->execlists;
+
+	if (rq_prio(rq) <= execlists->queue_priority_hint)
+		return false;
+
+	execlists->queue_priority_hint = rq_prio(rq);
+	return true;
+}
+
+static bool hold_request(const struct i915_request *rq)
+{
+	struct i915_dependency *p;
+	bool result = false;
+
+	/*
+	 * If one of our ancestors is on hold, we must also be put on hold,
+	 * otherwise we will bypass it and execute before it.
+	 */
+	rcu_read_lock();
+	for_each_signaler(p, rq) {
+		const struct i915_request *s =
+			container_of(p->signaler, typeof(*s), sched);
+
+		if (s->engine != rq->engine)
+			continue;
+
+		result = i915_request_on_hold(s);
+		if (result)
+			break;
+	}
+	rcu_read_unlock();
+
+	return result;
+}
+
+static bool ancestor_on_hold(const struct intel_engine_cs *engine,
+			     const struct i915_request *rq)
+{
+	GEM_BUG_ON(i915_request_on_hold(rq));
+	return unlikely(!list_empty(&engine->active.hold)) && hold_request(rq);
+}
+
+void i915_request_enqueue(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	unsigned long flags;
+	bool kick = false;
+
+	/* Will be called from irq-context when using foreign fences. */
+	spin_lock_irqsave(&engine->active.lock, flags);
+	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
+
+	if (unlikely(ancestor_on_hold(engine, rq))) {
+		RQ_TRACE(rq, "ancestor on hold\n");
+		list_add_tail(&rq->sched.link, &engine->active.hold);
+		i915_request_set_hold(rq);
+	} else {
+		queue_request(engine, rq);
+
+		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+
+		kick = submit_queue(engine, rq);
+	}
+
+	GEM_BUG_ON(list_empty(&rq->sched.link));
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+	if (kick)
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
 void i915_sched_node_init(struct i915_sched_node *node)
 {
 	spin_lock_init(&node->lock);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 5be7f90e7896..c4c086d56f81 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -39,6 +39,8 @@ void i915_sched_init_ipi(struct i915_sched_ipi *ipi);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
 
+void i915_request_enqueue(struct i915_request *request);
+
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 32/62] drm/i915: Extract request rewinding from execlists

[Chris Wilson]

In the process of preparing to reuse the request submission logic for
other backends, lift it out of the execlists backend.

While this operates on the common structs, we do have a bit of backend
knowledge, which is harmless for !lrc but still unsightly.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine.h        |  3 -
 .../drm/i915/gt/intel_execlists_submission.c  | 58 ++-----------------
 drivers/gpu/drm/i915/gt/intel_lrc_reg.h       |  3 +
 drivers/gpu/drm/i915/gt/selftest_execlists.c  |  2 +-
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c |  2 +-
 drivers/gpu/drm/i915/i915_scheduler.c         | 44 ++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler.h         |  3 +
 7 files changed, 56 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 47ee8578e511..20974415e7d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,9 +136,6 @@ execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
 	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
 }
 
-struct i915_request *
-execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
-
 static inline u32
 intel_read_status_page(const struct intel_engine_cs *engine, int reg)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 1ac940fb8846..ada2f64c6c8b 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -361,56 +361,6 @@ assert_priority_queue(const struct i915_request *prev,
 	return rq_prio(prev) >= rq_prio(next);
 }
 
-static struct i915_request *
-__unwind_incomplete_requests(struct intel_engine_cs *engine)
-{
-	struct i915_request *rq, *rn, *active = NULL;
-	struct list_head *pl;
-	int prio = I915_PRIORITY_INVALID;
-
-	lockdep_assert_held(&engine->active.lock);
-
-	list_for_each_entry_safe_reverse(rq, rn,
-					 &engine->active.requests,
-					 sched.link) {
-		if (__i915_request_is_complete(rq)) {
-			list_del_init(&rq->sched.link);
-			continue;
-		}
-
-		__i915_request_unsubmit(rq);
-
-		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
-		if (rq_prio(rq) != prio) {
-			prio = rq_prio(rq);
-			pl = i915_sched_lookup_priolist(engine, prio);
-		}
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
-
-		list_move(&rq->sched.link, pl);
-		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-
-		/* Check in case we rollback so far we wrap [size/2] */
-		if (intel_ring_direction(rq->ring,
-					 rq->tail,
-					 rq->ring->tail + 8) > 0)
-			rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
-
-		active = rq;
-	}
-
-	return active;
-}
-
-struct i915_request *
-execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists)
-{
-	struct intel_engine_cs *engine =
-		container_of(execlists, typeof(*engine), execlists);
-
-	return __unwind_incomplete_requests(engine);
-}
-
 static inline void
 execlists_context_status_change(struct i915_request *rq, unsigned long status)
 {
@@ -1083,7 +1033,7 @@ static void defer_active(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
 
-	rq = __unwind_incomplete_requests(engine);
+	rq = __intel_engine_rewind_requests(engine);
 	if (!rq)
 		return;
 
@@ -1275,7 +1225,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * the preemption, some of the unwound requests may
 			 * complete!
 			 */
-			__unwind_incomplete_requests(engine);
+			__intel_engine_rewind_requests(engine);
 
 			last = NULL;
 		} else if (timeslice_expired(engine, last)) {
@@ -2217,7 +2167,7 @@ static void execlists_capture(struct intel_engine_cs *engine)
 	 * which we return it to the queue for signaling.
 	 *
 	 * By removing them from the execlists queue, we also remove the
-	 * requests from being processed by __unwind_incomplete_requests()
+	 * requests from being processed by __intel_engine_rewind_requests()
 	 * during the intel_engine_reset(), and so they will *not* be replayed
 	 * afterwards.
 	 *
@@ -2835,7 +2785,7 @@ static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 	/* Push back any incomplete requests for replay after the reset. */
 	rcu_read_lock();
 	spin_lock_irqsave(&engine->active.lock, flags);
-	__unwind_incomplete_requests(engine);
+	__intel_engine_rewind_requests(engine);
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 	rcu_read_unlock();
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 65fe76738335..9eda2ef8a497 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -93,4 +93,7 @@
 /* in Gen12 ID 0x7FF is reserved to indicate idle */
 #define GEN12_MAX_CONTEXT_HW_ID	(GEN11_MAX_CONTEXT_HW_ID - 1)
 
+#define CTX_DESC_RELOAD_PD BIT_ULL(1)
+#define CTX_DESC_FORCE_RESTORE BIT_ULL(2)
+
 #endif /* _INTEL_LRC_REG_H_ */
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 0a2952bf1dcb..276743d553a9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -4532,7 +4532,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 
 	/* Fake a preemption event; failed of course */
 	spin_lock_irq(&engine->active.lock);
-	__unwind_incomplete_requests(engine);
+	__intel_engine_rewind_requests(engine);
 	spin_unlock_irq(&engine->active.lock);
 	GEM_BUG_ON(rq->engine != engine);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 6a70f3a2c002..7097aece016a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -434,7 +434,7 @@ static void guc_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 	cancel_port_requests(execlists);
 
 	/* Push back any incomplete requests for replay after the reset. */
-	rq = execlists_unwind_incomplete_requests(execlists);
+	rq = __intel_engine_rewind_requests(engine);
 	if (!rq)
 		goto out_unlock;
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 38dc9f8715bd..24bb0d0c8ed0 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -6,6 +6,9 @@
 
 #include <linux/mutex.h>
 
+#include "gt/intel_ring.h"
+#include "gt/intel_lrc_reg.h"
+
 #include "i915_drv.h"
 #include "i915_globals.h"
 #include "i915_request.h"
@@ -528,6 +531,47 @@ void i915_request_enqueue(struct i915_request *rq)
 		tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
+struct i915_request *
+__intel_engine_rewind_requests(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq, *rn, *active = NULL;
+	struct list_head *pl;
+	int prio = I915_PRIORITY_INVALID;
+
+	lockdep_assert_held(&engine->active.lock);
+
+	list_for_each_entry_safe_reverse(rq, rn,
+					 &engine->active.requests,
+					 sched.link) {
+		if (__i915_request_is_complete(rq)) {
+			list_del_init(&rq->sched.link);
+			continue;
+		}
+
+		__i915_request_unsubmit(rq);
+
+		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
+		if (rq_prio(rq) != prio) {
+			prio = rq_prio(rq);
+			pl = i915_sched_lookup_priolist(engine, prio);
+		}
+		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+
+		list_move(&rq->sched.link, pl);
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+
+		/* Check in case we rollback so far we wrap [size/2] */
+		if (intel_ring_direction(rq->ring,
+					 rq->tail,
+					 rq->ring->tail + 8) > 0)
+			rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
+
+		active = rq;
+	}
+
+	return active;
+}
+
 void i915_sched_node_init(struct i915_sched_node *node)
 {
 	spin_lock_init(&node->lock);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index c4c086d56f81..50fdc7168d38 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -41,6 +41,9 @@ void i915_request_set_priority(struct i915_request *request, int prio);
 
 void i915_request_enqueue(struct i915_request *request);
 
+struct i915_request *
+__intel_engine_rewind_requests(struct intel_engine_cs *engine);
+
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 33/62] drm/i915: Extract request suspension from the execlists backend

[Chris Wilson]

Make the ability to suspend and resume a request and its dependents
generic.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 148 +-----------------
 drivers/gpu/drm/i915/i915_scheduler.c         | 120 ++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler.h         |   5 +
 3 files changed, 129 insertions(+), 144 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index ada2f64c6c8b..c2780b1c2fc8 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1860,166 +1860,26 @@ static void post_process_csb(struct i915_request **port,
 		execlists_schedule_out(*port++);
 }
 
-static void __execlists_hold(struct i915_request *rq)
-{
-	LIST_HEAD(list);
-
-	do {
-		struct i915_dependency *p;
-
-		if (i915_request_is_active(rq))
-			__i915_request_unsubmit(rq);
-
-		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-		list_move_tail(&rq->sched.link, &rq->engine->active.hold);
-		i915_request_set_hold(rq);
-		RQ_TRACE(rq, "on hold\n");
-
-		for_each_waiter(p, rq) {
-			struct i915_request *w =
-				container_of(p->waiter, typeof(*w), sched);
-
-			if (p->flags & I915_DEPENDENCY_WEAK)
-				continue;
-
-			/* Leave semaphores spinning on the other engines */
-			if (w->engine != rq->engine)
-				continue;
-
-			if (!i915_request_is_ready(w))
-				continue;
-
-			if (__i915_request_is_complete(w))
-				continue;
-
-			if (i915_request_on_hold(w))
-				continue;
-
-			list_move_tail(&w->sched.link, &list);
-		}
-
-		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
-	} while (rq);
-}
-
 static bool execlists_hold(struct intel_engine_cs *engine,
 			   struct i915_request *rq)
 {
+	bool result;
+
 	if (i915_request_on_hold(rq))
 		return false;
 
 	spin_lock_irq(&engine->active.lock);
-
-	if (__i915_request_is_complete(rq)) { /* too late! */
-		rq = NULL;
-		goto unlock;
-	}
-
-	/*
-	 * Transfer this request onto the hold queue to prevent it
-	 * being resumbitted to HW (and potentially completed) before we have
-	 * released it. Since we may have already submitted following
-	 * requests, we need to remove those as well.
-	 */
-	GEM_BUG_ON(i915_request_on_hold(rq));
-	GEM_BUG_ON(rq->engine != engine);
-	__execlists_hold(rq);
-	GEM_BUG_ON(list_empty(&engine->active.hold));
-
-unlock:
+	result = __intel_engine_hold_request(engine, rq);
 	spin_unlock_irq(&engine->active.lock);
-	return rq;
-}
-
-static bool hold_request(const struct i915_request *rq)
-{
-	struct i915_dependency *p;
-	bool result = false;
-
-	/*
-	 * If one of our ancestors is on hold, we must also be on hold,
-	 * otherwise we will bypass it and execute before it.
-	 */
-	rcu_read_lock();
-	for_each_signaler(p, rq) {
-		const struct i915_request *s =
-			container_of(p->signaler, typeof(*s), sched);
-
-		if (s->engine != rq->engine)
-			continue;
-
-		result = i915_request_on_hold(s);
-		if (result)
-			break;
-	}
-	rcu_read_unlock();
 
 	return result;
 }
 
-static void __execlists_unhold(struct i915_request *rq)
-{
-	LIST_HEAD(list);
-
-	do {
-		struct i915_dependency *p;
-
-		RQ_TRACE(rq, "hold release\n");
-
-		GEM_BUG_ON(!i915_request_on_hold(rq));
-		GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
-
-		i915_request_clear_hold(rq);
-		list_move_tail(&rq->sched.link,
-			       i915_sched_lookup_priolist(rq->engine,
-							  rq_prio(rq)));
-		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-
-		/* Also release any children on this engine that are ready */
-		for_each_waiter(p, rq) {
-			struct i915_request *w =
-				container_of(p->waiter, typeof(*w), sched);
-
-			if (p->flags & I915_DEPENDENCY_WEAK)
-				continue;
-
-			/* Propagate any change in error status */
-			if (rq->fence.error)
-				i915_request_set_error_once(w, rq->fence.error);
-
-			if (w->engine != rq->engine)
-				continue;
-
-			if (!i915_request_on_hold(w))
-				continue;
-
-			/* Check that no other parents are also on hold */
-			if (hold_request(w))
-				continue;
-
-			list_move_tail(&w->sched.link, &list);
-		}
-
-		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
-	} while (rq);
-}
-
 static void execlists_unhold(struct intel_engine_cs *engine,
 			     struct i915_request *rq)
 {
 	spin_lock_irq(&engine->active.lock);
-
-	/*
-	 * Move this request back to the priority queue, and all of its
-	 * children and grandchildren that were suspended along with it.
-	 */
-	__execlists_unhold(rq);
-
-	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
-		engine->execlists.queue_priority_hint = rq_prio(rq);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-	}
-
+	__intel_engine_unhold_request(engine, rq);
 	spin_unlock_irq(&engine->active.lock);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 24bb0d0c8ed0..6ad0acd96cd2 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -572,6 +572,126 @@ __intel_engine_rewind_requests(struct intel_engine_cs *engine)
 	return active;
 }
 
+bool __intel_engine_hold_request(struct intel_engine_cs *engine,
+				 struct i915_request *rq)
+{
+	LIST_HEAD(list);
+
+	lockdep_assert_held(&engine->active.lock);
+	GEM_BUG_ON(i915_request_on_hold(rq));
+	GEM_BUG_ON(rq->engine != engine);
+
+	if (__i915_request_is_complete(rq)) /* too late! */
+		return false;
+
+	/*
+	 * Transfer this request onto the hold queue to prevent it
+	 * being resumbitted to HW (and potentially completed) before we have
+	 * released it. Since we may have already submitted following
+	 * requests, we need to remove those as well.
+	 */
+	do {
+		struct i915_dependency *p;
+
+		if (i915_request_is_active(rq))
+			__i915_request_unsubmit(rq);
+
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		list_move_tail(&rq->sched.link, &rq->engine->active.hold);
+		i915_request_set_hold(rq);
+		RQ_TRACE(rq, "on hold\n");
+
+		for_each_waiter(p, rq) {
+			struct i915_request *w =
+				container_of(p->waiter, typeof(*w), sched);
+
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
+			/* Leave semaphores spinning on the other engines */
+			if (w->engine != engine)
+				continue;
+
+			if (!i915_request_is_ready(w))
+				continue;
+
+			if (__i915_request_is_complete(w))
+				continue;
+
+			if (i915_request_on_hold(w)) /* acts as a visited bit */
+				continue;
+
+			list_move_tail(&w->sched.link, &list);
+		}
+
+		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
+	} while (rq);
+
+	GEM_BUG_ON(list_empty(&engine->active.hold));
+
+	return true;
+}
+
+void __intel_engine_unhold_request(struct intel_engine_cs *engine,
+				   struct i915_request *rq)
+{
+	LIST_HEAD(list);
+
+	lockdep_assert_held(&engine->active.lock);
+
+	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
+		engine->execlists.queue_priority_hint = rq_prio(rq);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+	}
+
+	/*
+	 * Move this request back to the priority queue, and all of its
+	 * children and grandchildren that were suspended along with it.
+	 */
+	do {
+		struct i915_dependency *p;
+
+		RQ_TRACE(rq, "hold release\n");
+
+		GEM_BUG_ON(!i915_request_on_hold(rq));
+		GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
+
+		i915_request_clear_hold(rq);
+		list_move_tail(&rq->sched.link,
+			       i915_sched_lookup_priolist(rq->engine,
+							  rq_prio(rq)));
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+
+		/* Also release any children on this engine that are ready */
+		for_each_waiter(p, rq) {
+			struct i915_request *w =
+				container_of(p->waiter, typeof(*w), sched);
+
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
+			/* Propagate any change in error status */
+			if (rq->fence.error)
+				i915_request_set_error_once(w, rq->fence.error);
+
+			if (w->engine != engine)
+				continue;
+
+			/* We also treat the on-hold status as a visited bit */
+			if (!i915_request_on_hold(w))
+				continue;
+
+			/* Check that no other parents are also on hold [BFS] */
+			if (hold_request(w))
+				continue;
+
+			list_move_tail(&w->sched.link, &list);
+		}
+
+		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
+	} while (rq);
+}
+
 void i915_sched_node_init(struct i915_sched_node *node)
 {
 	spin_lock_init(&node->lock);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 50fdc7168d38..b4b722982870 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -44,6 +44,11 @@ void i915_request_enqueue(struct i915_request *request);
 struct i915_request *
 __intel_engine_rewind_requests(struct intel_engine_cs *engine);
 
+bool __intel_engine_hold_request(struct intel_engine_cs *engine,
+				 struct i915_request *request);
+void __intel_engine_unhold_request(struct intel_engine_cs *engine,
+				   struct i915_request *request);
+
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 34/62] drm/i915: Extract the ability to defer and rerun a request later

[Chris Wilson]

Lift the ability to defer a request until later from execlists into the
common layer.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 55 ++--------------
 drivers/gpu/drm/i915/i915_scheduler.c         | 66 ++++++++++++++++---
 drivers/gpu/drm/i915/i915_scheduler.h         |  5 +-
 3 files changed, 67 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index c2780b1c2fc8..c0aefbe145d1 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -981,9 +981,13 @@ static void virtual_xfer_context(struct virtual_engine *ve,
 	}
 }
 
-static void defer_request(struct i915_request *rq, struct list_head * const pl)
+static void defer_active(struct intel_engine_cs *engine)
 {
-	LIST_HEAD(list);
+	struct i915_request *rq;
+
+	rq = __intel_engine_rewind_requests(engine);
+	if (!rq)
+		return;
 
 	/*
 	 * We want to move the interrupted request to the back of
@@ -992,52 +996,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 	 * flight and were waiting for the interrupted request to
 	 * be run after it again.
 	 */
-	do {
-		struct i915_dependency *p;
-
-		GEM_BUG_ON(i915_request_is_active(rq));
-		list_move_tail(&rq->sched.link, pl);
-
-		for_each_waiter(p, rq) {
-			struct i915_request *w =
-				container_of(p->waiter, typeof(*w), sched);
-
-			if (p->flags & I915_DEPENDENCY_WEAK)
-				continue;
-
-			/* Leave semaphores spinning on the other engines */
-			if (w->engine != rq->engine)
-				continue;
-
-			/* No waiter should start before its signaler */
-			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
-				   __i915_request_has_started(w) &&
-				   !__i915_request_is_complete(rq));
-
-			GEM_BUG_ON(i915_request_is_active(w));
-			if (!i915_request_is_ready(w))
-				continue;
-
-			if (rq_prio(w) < rq_prio(rq))
-				continue;
-
-			GEM_BUG_ON(rq_prio(w) > rq_prio(rq));
-			list_move_tail(&w->sched.link, &list);
-		}
-
-		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
-	} while (rq);
-}
-
-static void defer_active(struct intel_engine_cs *engine)
-{
-	struct i915_request *rq;
-
-	rq = __intel_engine_rewind_requests(engine);
-	if (!rq)
-		return;
-
-	defer_request(rq, i915_sched_lookup_priolist(engine, rq_prio(rq)));
+	__intel_engine_defer_request(engine, rq);
 }
 
 static bool
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 6ad0acd96cd2..399d69144c4e 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -171,8 +171,8 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 	}
 }
 
-struct list_head *
-i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio)
+static struct list_head *
+lookup_priolist(struct intel_engine_cs *engine, int prio)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_priolist *p;
@@ -324,7 +324,7 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 	struct list_head *pos = &rq->sched.signalers_list;
 	struct list_head *plist;
 
-	plist = i915_sched_lookup_priolist(engine, prio);
+	plist = lookup_priolist(engine, prio);
 
 	/*
 	 * Recursively bump all dependent priorities to match the new request.
@@ -449,12 +449,63 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+void __intel_engine_defer_request(struct intel_engine_cs *engine,
+				  struct i915_request *rq)
+{
+	struct list_head *pl;
+	LIST_HEAD(list);
+
+	lockdep_assert_held(&engine->active.lock);
+	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
+
+	/*
+	 * When we defer a request, we must maintain its order with respect
+	 * to those that are waiting upon it. So we traverse its chain of
+	 * waiters and move any that are earlier than the request to after it.
+	 */
+	pl = lookup_priolist(engine, rq_prio(rq));
+	do {
+		struct i915_dependency *p;
+
+		GEM_BUG_ON(i915_request_is_active(rq));
+		list_move_tail(&rq->sched.link, pl);
+
+		for_each_waiter(p, rq) {
+			struct i915_request *w =
+				container_of(p->waiter, typeof(*w), sched);
+
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
+			/* Leave semaphores spinning on the other engines */
+			if (w->engine != engine)
+				continue;
+
+			/* No waiter should start before its signaler */
+			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
+				   __i915_request_has_started(w) &&
+				   !__i915_request_is_complete(rq));
+
+			GEM_BUG_ON(i915_request_is_active(w));
+			if (!i915_request_is_ready(w))
+				continue;
+
+			if (rq_prio(w) < rq_prio(rq))
+				continue;
+
+			GEM_BUG_ON(rq_prio(w) > rq_prio(rq));
+			list_move_tail(&w->sched.link, &list);
+		}
+
+		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
+	} while (rq);
+}
+
 static void queue_request(struct intel_engine_cs *engine,
 			  struct i915_request *rq)
 {
 	GEM_BUG_ON(!list_empty(&rq->sched.link));
-	list_add_tail(&rq->sched.link,
-		      i915_sched_lookup_priolist(engine, rq_prio(rq)));
+	list_add_tail(&rq->sched.link, lookup_priolist(engine, rq_prio(rq)));
 	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
@@ -553,7 +604,7 @@ __intel_engine_rewind_requests(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
 		if (rq_prio(rq) != prio) {
 			prio = rq_prio(rq);
-			pl = i915_sched_lookup_priolist(engine, prio);
+			pl = lookup_priolist(engine, prio);
 		}
 		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 
@@ -658,8 +709,7 @@ void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 
 		i915_request_clear_hold(rq);
 		list_move_tail(&rq->sched.link,
-			       i915_sched_lookup_priolist(rq->engine,
-							  rq_prio(rq)));
+			       lookup_priolist(rq->engine, rq_prio(rq)));
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
 		/* Also release any children on this engine that are ready */
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index b4b722982870..152faac61468 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -43,15 +43,14 @@ void i915_request_enqueue(struct i915_request *request);
 
 struct i915_request *
 __intel_engine_rewind_requests(struct intel_engine_cs *engine);
+void __intel_engine_defer_request(struct intel_engine_cs *engine,
+				  struct i915_request *request);
 
 bool __intel_engine_hold_request(struct intel_engine_cs *engine,
 				 struct i915_request *request);
 void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 				   struct i915_request *request);
 
-struct list_head *
-i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
-
 void __i915_priolist_free(struct i915_priolist *p);
 static inline void i915_priolist_free(struct i915_priolist *p)
 {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 35/62] drm/i915: Fix the iterative dfs for defering requests

[Chris Wilson]

The current implementation of walking the children of a deferred
requests lacks the backtracking required to reduce the dfs to linear.
Having pulled it from execlists into the common layer, we can reuse the
dfs code for priority inheritance.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_scheduler.c | 58 +++++++++++++++++++--------
 1 file changed, 42 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 399d69144c4e..c04de6c2ddce 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -452,25 +452,26 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 void __intel_engine_defer_request(struct intel_engine_cs *engine,
 				  struct i915_request *rq)
 {
-	struct list_head *pl;
-	LIST_HEAD(list);
+	struct list_head *pos = &rq->sched.waiters_list;
+	struct i915_request *rn;
+	LIST_HEAD(dfs);
+	int prio;
 
 	lockdep_assert_held(&engine->active.lock);
 	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
 
+	prio = rq_prio(rq);
+
 	/*
 	 * When we defer a request, we must maintain its order with respect
 	 * to those that are waiting upon it. So we traverse its chain of
 	 * waiters and move any that are earlier than the request to after it.
 	 */
-	pl = lookup_priolist(engine, rq_prio(rq));
+	rq->sched.dfs.next = NULL;
 	do {
-		struct i915_dependency *p;
-
-		GEM_BUG_ON(i915_request_is_active(rq));
-		list_move_tail(&rq->sched.link, pl);
-
-		for_each_waiter(p, rq) {
+		list_for_each_continue(pos, &rq->sched.waiters_list) {
+			struct i915_dependency *p =
+				list_entry(pos, typeof(*p), wait_link);
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
@@ -486,19 +487,44 @@ void __intel_engine_defer_request(struct intel_engine_cs *engine,
 				   __i915_request_has_started(w) &&
 				   !__i915_request_is_complete(rq));
 
-			GEM_BUG_ON(i915_request_is_active(w));
-			if (!i915_request_is_ready(w))
+			if (!i915_request_in_priority_queue(w))
 				continue;
 
-			if (rq_prio(w) < rq_prio(rq))
+			/*
+			 * We also need to reorder within the same priority.
+			 *
+			 * This is unlike priority-inheritance, where if the
+			 * signaler already has a higher priority [earlier
+			 * deadline] than us, we can ignore as it will be
+			 * scheduled first. If a waiter already has the
+			 * same priority, we still have to push it to the end
+			 * of the list. This unfortunately means we cannot
+			 * use the rq_deadline() itself as a 'visited' bit.
+			 */
+			if (rq_prio(w) < prio)
 				continue;
 
-			GEM_BUG_ON(rq_prio(w) > rq_prio(rq));
-			list_move_tail(&w->sched.link, &list);
+			GEM_BUG_ON(rq_prio(w) != prio);
+
+			/* Remember our position along this branch */
+			rq = stack_push(w, rq, pos);
+			pos = &rq->sched.waiters_list;
 		}
 
-		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
-	} while (rq);
+		/* Note list is reversed for waiters wrt signal hierarchy */
+		GEM_BUG_ON(rq->engine != engine);
+		GEM_BUG_ON(!i915_request_in_priority_queue(rq));
+		list_move(&rq->sched.link, &dfs);
+
+		/* Track our visit, and prevent duplicate processing */
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	} while ((rq = stack_pop(rq, &pos)));
+
+	pos = lookup_priolist(engine, prio);
+	list_for_each_entry_safe(rq, rn, &dfs, sched.link) {
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		list_add_tail(&rq->sched.link, pos);
+	}
 }
 
 static void queue_request(struct intel_engine_cs *engine,
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 36/62] drm/i915: Move common active lists from engine to i915_scheduler

[Chris Wilson]

Extract the scheduler lists into a related structure, stop sprawling
over struct intel_engine_cs

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     | 26 +-------------
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |  8 +----
 .../drm/i915/gt/intel_execlists_submission.c  |  2 +-
 drivers/gpu/drm/i915/gt/mock_engine.c         |  2 +-
 drivers/gpu/drm/i915/i915_scheduler.c         | 34 ++++++++++++++++---
 drivers/gpu/drm/i915/i915_scheduler.h         |  3 +-
 drivers/gpu/drm/i915/i915_scheduler_types.h   |  8 +++++
 7 files changed, 43 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 78b41dc36cd7..88092a6f2e98 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -594,8 +594,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
 
 	execlists->queue_priority_hint = INT_MIN;
 	execlists->queue = RB_ROOT_CACHED;
-
-	i915_sched_init_ipi(&execlists->ipi);
 }
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
@@ -711,7 +709,7 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 		goto err_status;
 	}
 
-	intel_engine_init_active(engine, ENGINE_PHYSICAL);
+	i915_sched_init_engine(&engine->active, ENGINE_PHYSICAL);
 	intel_engine_init_execlists(engine);
 	intel_engine_init_cmd_parser(engine);
 	intel_engine_init__pm(engine);
@@ -776,28 +774,6 @@ static int measure_breadcrumb_dw(struct intel_context *ce)
 	return dw;
 }
 
-void
-intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
-{
-	INIT_LIST_HEAD(&engine->active.requests);
-	INIT_LIST_HEAD(&engine->active.hold);
-
-	spin_lock_init(&engine->active.lock);
-	lockdep_set_subclass(&engine->active.lock, subclass);
-
-	/*
-	 * Due to an interesting quirk in lockdep's internal debug tracking,
-	 * after setting a subclass we must ensure the lock is used. Otherwise,
-	 * nr_unused_locks is incremented once too often.
-	 */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	local_irq_disable();
-	lock_map_acquire(&engine->active.lock.dep_map);
-	lock_map_release(&engine->active.lock.dep_map);
-	local_irq_enable();
-#endif
-}
-
 static struct intel_context *
 create_pinned_context(struct intel_engine_cs *engine,
 		      unsigned int hwsp,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index d19710191690..6379b1e0b7ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -259,8 +259,6 @@ struct intel_engine_execlists {
 	struct rb_root_cached queue;
 	struct rb_root_cached virtual;
 
-	struct i915_sched_ipi ipi;
-
 	/**
 	 * @csb_write: control register for Context Switch buffer
 	 *
@@ -330,11 +328,7 @@ struct intel_engine_cs {
 
 	struct intel_sseu sseu;
 
-	struct {
-		spinlock_t lock;
-		struct list_head requests;
-		struct list_head hold; /* ready requests, but on hold */
-	} active;
+	struct i915_sched_engine active;
 
 	/* keep a request in reserve for a [pm] barrier under oom */
 	struct i915_request *request_pool;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index c0aefbe145d1..71bea6d533db 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3317,7 +3317,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
 
-	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
+	i915_sched_init_engine(&ve->base.active, ENGINE_VIRTUAL);
 	intel_engine_init_execlists(&ve->base);
 
 	ve->base.cops = &virtual_context_ops;
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 2f830017c51d..c00bc0f4afec 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -355,7 +355,7 @@ int mock_engine_init(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
-	intel_engine_init_active(engine, ENGINE_MOCK);
+	i915_sched_init_engine(&engine->active, ENGINE_MOCK);
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
 	intel_engine_init_retire(engine);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index c04de6c2ddce..82734ac417b8 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -85,12 +85,36 @@ static void ipi_schedule(struct work_struct *wrk)
 	} while (rq);
 }
 
-void i915_sched_init_ipi(struct i915_sched_ipi *ipi)
+static void i915_sched_init_ipi(struct i915_sched_ipi *ipi)
 {
 	INIT_WORK(&ipi->work, ipi_schedule);
 	ipi->list = NULL;
 }
 
+void i915_sched_init_engine(struct i915_sched_engine *se,
+			    unsigned int subclass)
+{
+	spin_lock_init(&se->lock);
+	lockdep_set_subclass(&se->lock, subclass);
+
+	INIT_LIST_HEAD(&se->requests);
+	INIT_LIST_HEAD(&se->hold);
+
+	i915_sched_init_ipi(&se->ipi);
+
+	/*
+	 * Due to an interesting quirk in lockdep's internal debug tracking,
+	 * after setting a subclass we must ensure the lock is used. Otherwise,
+	 * nr_unused_locks is incremented once too often.
+	 */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	local_irq_disable();
+	lock_map_acquire(&se->lock.dep_map);
+	lock_map_release(&se->lock.dep_map);
+	local_irq_enable();
+#endif
+}
+
 static void __ipi_add(struct i915_request *rq)
 {
 #define STUB ((struct i915_request *)1)
@@ -106,13 +130,13 @@ static void __ipi_add(struct i915_request *rq)
 		return;
 	}
 
-	first = READ_ONCE(engine->execlists.ipi.list);
-	do
+	first = READ_ONCE(engine->active.ipi.list);
+	do {
 		rq->sched.ipi_link = ptr_pack_bits(first, 1, 1);
-	while (!try_cmpxchg(&engine->execlists.ipi.list, &first, rq));
+	} while (!try_cmpxchg(&engine->active.ipi.list, &first, rq));
 
 	if (!first)
-		queue_work(system_unbound_wq, &engine->execlists.ipi.work);
+		queue_work(system_unbound_wq, &engine->active.ipi.work);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 152faac61468..ea5595188f8e 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -35,7 +35,8 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 
 void i915_sched_node_retire(struct i915_sched_node *node);
 
-void i915_sched_init_ipi(struct i915_sched_ipi *ipi);
+void i915_sched_init_engine(struct i915_sched_engine *se,
+			    unsigned int subclass);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 5a84d59134ee..5f21f5ac6dd9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -80,6 +80,14 @@ struct i915_sched_ipi {
 	struct work_struct work;
 };
 
+struct i915_sched_engine {
+	spinlock_t lock;
+	struct list_head requests;
+	struct list_head hold; /* ready requests, but on hold */
+
+	struct i915_sched_ipi ipi;
+};
+
 struct i915_dependency {
 	struct i915_sched_node *signaler;
 	struct i915_sched_node *waiter;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 37/62] drm/i915: Move scheduler queue

[Chris Wilson]

Extract the scheduling queue from "execlists" into the per-engine
scheduling structs, for reuse by other backends.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_context_types.h |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_wait.c      |  1 +
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  5 +--
 drivers/gpu/drm/i915/gt/intel_engine_pm.c     |  3 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h  | 14 -------
 .../drm/i915/gt/intel_execlists_submission.c  | 29 +++++++-------
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 11 +++---
 drivers/gpu/drm/i915/i915_drv.h               |  1 -
 drivers/gpu/drm/i915/i915_request.h           |  2 +-
 drivers/gpu/drm/i915/i915_scheduler.c         | 38 ++++++++++++-------
 drivers/gpu/drm/i915/i915_scheduler.h         | 15 ++++++++
 drivers/gpu/drm/i915/i915_scheduler_types.h   | 15 ++++++++
 .../gpu/drm/i915/selftests/i915_scheduler.c   |  2 +-
 13 files changed, 84 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 1449f54924e0..99bd7b4f4ffe 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -19,7 +19,7 @@
 
 #include "gt/intel_context_types.h"
 
-#include "i915_scheduler.h"
+#include "i915_scheduler_types.h"
 #include "i915_sw_fence.h"
 
 struct pid;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index cefbbb3d9b52..483139bd05c1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -11,6 +11,7 @@
 
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
+#include "i915_scheduler.h"
 
 static long
 i915_gem_object_wait_fence(struct dma_fence *fence,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 88092a6f2e98..c111bbc4c02a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -593,7 +593,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
 		memset(execlists->inflight, 0, sizeof(execlists->inflight));
 
 	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
 }
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
@@ -915,7 +914,7 @@ int intel_engines_init(struct intel_gt *gt)
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
-	GEM_BUG_ON(!list_empty(&engine->active.requests));
+	i915_sched_fini_engine(&engine->active);
 	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
 	intel_breadcrumbs_free(engine->breadcrumbs);
@@ -1236,7 +1235,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	}
 
 	/* ELSP is empty, but there are ready requests? E.g. after reset */
-	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
+	if (!i915_sched_is_idle(&engine->active))
 		return false;
 
 	/* Ring stopped? */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 2843db731b7d..14378e3a7a50 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -5,6 +5,7 @@
  */
 
 #include "i915_drv.h"
+#include "i915_scheduler.h"
 
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
@@ -277,7 +278,7 @@ static int __engine_park(struct intel_wakeref *wf)
 	if (engine->park)
 		engine->park(engine);
 
-	engine->execlists.no_priolist = false;
+	i915_sched_park_engine(&engine->active);
 
 	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
 	intel_gt_pm_put_async(engine->gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 6379b1e0b7ea..a2a49e51b92d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -154,11 +154,6 @@ struct intel_engine_execlists {
 	 */
 	struct timer_list preempt;
 
-	/**
-	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
-	 */
-	struct i915_priolist default_priolist;
-
 	/**
 	 * @ccid: identifier for contexts submitted to this engine
 	 */
@@ -193,11 +188,6 @@ struct intel_engine_execlists {
 	 */
 	u32 reset_ccid;
 
-	/**
-	 * @no_priolist: priority lists disabled
-	 */
-	bool no_priolist;
-
 	/**
 	 * @submit_reg: gen-specific execlist submission register
 	 * set to the ExecList Submission Port (elsp) register pre-Gen11 and to
@@ -253,10 +243,6 @@ struct intel_engine_execlists {
 	 */
 	int queue_priority_hint;
 
-	/**
-	 * @queue: queue of requests, in priority lists
-	 */
-	struct rb_root_cached queue;
 	struct rb_root_cached virtual;
 
 	/**
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 71bea6d533db..b111d780f657 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -274,11 +274,11 @@ static int effective_prio(const struct i915_request *rq)
 	return prio;
 }
 
-static int queue_prio(const struct intel_engine_execlists *execlists)
+static int queue_prio(const struct i915_sched_engine *se)
 {
 	struct rb_node *rb;
 
-	rb = rb_first_cached(&execlists->queue);
+	rb = rb_first_cached(&se->queue);
 	if (!rb)
 		return INT_MIN;
 
@@ -341,7 +341,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	 * context, it's priority would not exceed ELSP[0] aka last_prio.
 	 */
 	return max(virtual_prio(&engine->execlists),
-		   queue_prio(&engine->execlists)) > last_prio;
+		   queue_prio(&engine->active)) > last_prio;
 }
 
 __maybe_unused static inline bool
@@ -1030,11 +1030,11 @@ static bool needs_timeslice(const struct intel_engine_cs *engine,
 		return false;
 
 	/* If ELSP[1] is occupied, always check to see if worth slicing */
-	if (!list_is_last_rcu(&rq->sched.link, &engine->active.requests))
+	if (!i915_sched_is_last_request(&engine->active, rq))
 		return true;
 
 	/* Otherwise, ELSP[0] is by itself, but may be waiting in the queue */
-	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
+	if (!i915_sched_is_idle(&engine->active))
 		return true;
 
 	return !RB_EMPTY_ROOT(&engine->execlists.virtual.rb_root);
@@ -1249,7 +1249,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq->engine != &ve->base);
 		GEM_BUG_ON(rq->context != &ve->context);
 
-		if (unlikely(rq_prio(rq) < queue_prio(execlists))) {
+		if (unlikely(rq_prio(rq) < queue_prio(&engine->active))) {
 			spin_unlock(&ve->base.active.lock);
 			break;
 		}
@@ -1317,7 +1317,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			break;
 	}
 
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&engine->active.queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -1396,7 +1396,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			}
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &engine->active.queue);
 		i915_priolist_free(p);
 	}
 done:
@@ -1418,7 +1418,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * request triggering preemption on the next dequeue (or subsequent
 	 * interrupt for secondary ports).
 	 */
-	execlists->queue_priority_hint = queue_prio(execlists);
+	execlists->queue_priority_hint = queue_prio(&engine->active);
 	spin_unlock(&engine->active.lock);
 
 	/*
@@ -2651,7 +2651,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&engine->active.queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		priolist_for_each_request_consume(rq, rn, p) {
@@ -2659,9 +2659,10 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 			__i915_request_submit(rq);
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &engine->active.queue);
 		i915_priolist_free(p);
 	}
+	GEM_BUG_ON(!i915_sched_is_idle(&engine->active));
 
 	/* On-hold requests will be flushed to timeline upon their release */
 	list_for_each_entry(rq, &engine->active.hold, sched.link)
@@ -2692,7 +2693,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
+	engine->active.queue = RB_ROOT_CACHED;
 
 	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
 	execlists->tasklet.func = nop_submission_tasklet;
@@ -2925,7 +2926,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 
 static struct list_head *virtual_queue(struct virtual_engine *ve)
 {
-	return &ve->base.execlists.default_priolist.requests;
+	return &ve->base.active.default_priolist.requests;
 }
 
 static void rcu_virtual_context_destroy(struct work_struct *wrk)
@@ -3516,7 +3517,7 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 
 	last = NULL;
 	count = 0;
-	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&engine->active.queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
 
 		priolist_for_each_request(rq, p) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 7097aece016a..6d97b5ad09b5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -310,7 +310,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 	 * event.
 	 */
 	port = first;
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&engine->active.queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -330,7 +330,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 			last = rq;
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &engine->active.queue);
 		i915_priolist_free(p);
 	}
 done:
@@ -483,7 +483,7 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&execlists->queue))) {
+	while ((rb = rb_first_cached(&engine->active.queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		priolist_for_each_request_consume(rq, rn, p) {
@@ -493,14 +493,15 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 			i915_request_mark_complete(rq);
 		}
 
-		rb_erase_cached(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &engine->active.queue);
 		i915_priolist_free(p);
 	}
+	GEM_BUG_ON(!i915_sched_is_idle(&engine->active));
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority_hint = INT_MIN;
-	execlists->queue = RB_ROOT_CACHED;
+	engine->active.queue = RB_ROOT_CACHED;
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e38a10d5c128..795be17ce239 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -97,7 +97,6 @@
 #include "i915_gpu_error.h"
 #include "i915_perf_types.h"
 #include "i915_request.h"
-#include "i915_scheduler.h"
 #include "gt/intel_timeline.h"
 #include "i915_vma.h"
 #include "i915_irq.h"
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index a8c413203f72..adfe863f778e 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -35,7 +35,7 @@
 #include "gt/intel_timeline_types.h"
 
 #include "i915_gem.h"
-#include "i915_scheduler.h"
+#include "i915_scheduler_types.h"
 #include "i915_selftest.h"
 #include "i915_sw_fence.h"
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 82734ac417b8..9d77dae93be9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -99,6 +99,7 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
 
 	INIT_LIST_HEAD(&se->requests);
 	INIT_LIST_HEAD(&se->hold);
+	se->queue = RB_ROOT_CACHED;
 
 	i915_sched_init_ipi(&se->ipi);
 
@@ -115,6 +116,17 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
 #endif
 }
 
+void i915_sched_park_engine(struct i915_sched_engine *se)
+{
+	GEM_BUG_ON(!i915_sched_is_idle(se));
+	se->no_priolist = false;
+}
+
+void i915_sched_fini_engine(struct i915_sched_engine *se)
+{
+	GEM_BUG_ON(!list_empty(&se->requests));
+}
+
 static void __ipi_add(struct i915_request *rq)
 {
 #define STUB ((struct i915_request *)1)
@@ -175,7 +187,7 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 	return rb_entry(rb, struct i915_priolist, node);
 }
 
-static void assert_priolists(struct intel_engine_execlists * const execlists)
+static void assert_priolists(struct i915_sched_engine * const se)
 {
 	struct rb_node *rb;
 	long last_prio;
@@ -183,11 +195,11 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
 
-	GEM_BUG_ON(rb_first_cached(&execlists->queue) !=
-		   rb_first(&execlists->queue.rb_root));
+	GEM_BUG_ON(rb_first_cached(&se->queue) !=
+		   rb_first(&se->queue.rb_root));
 
 	last_prio = INT_MAX;
-	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&se->queue); rb; rb = rb_next(rb)) {
 		const struct i915_priolist *p = to_priolist(rb);
 
 		GEM_BUG_ON(p->priority > last_prio);
@@ -198,21 +210,21 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
 static struct list_head *
 lookup_priolist(struct intel_engine_cs *engine, int prio)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_sched_engine * const se = &engine->active;
 	struct i915_priolist *p;
 	struct rb_node **parent, *rb;
 	bool first = true;
 
 	lockdep_assert_held(&engine->active.lock);
-	assert_priolists(execlists);
+	assert_priolists(se);
 
-	if (unlikely(execlists->no_priolist))
+	if (unlikely(se->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
 
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_root.rb_node;
+	parent = &se->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -227,7 +239,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 	}
 
 	if (prio == I915_PRIORITY_NORMAL) {
-		p = &execlists->default_priolist;
+		p = &se->default_priolist;
 	} else {
 		p = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
 		/* Convert an allocation failure to a priority bump */
@@ -242,7 +254,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 			 * requests, so if userspace lied about their
 			 * dependencies that reordering may be visible.
 			 */
-			execlists->no_priolist = true;
+			se->no_priolist = true;
 			goto find_priolist;
 		}
 	}
@@ -251,7 +263,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 	INIT_LIST_HEAD(&p->requests);
 
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color_cached(&p->node, &execlists->queue, first);
+	rb_insert_color_cached(&p->node, &se->queue, first);
 
 	return &p->requests;
 }
@@ -621,7 +633,7 @@ void i915_request_enqueue(struct i915_request *rq)
 	} else {
 		queue_request(engine, rq);
 
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(i915_sched_is_idle(&engine->active));
 
 		kick = submit_queue(engine, rq);
 	}
@@ -656,7 +668,7 @@ __intel_engine_rewind_requests(struct intel_engine_cs *engine)
 			prio = rq_prio(rq);
 			pl = lookup_priolist(engine, prio);
 		}
-		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(i915_sched_is_idle(&engine->active));
 
 		list_move(&rq->sched.link, pl);
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index ea5595188f8e..6bb9d8c3519a 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 
 #include "i915_scheduler_types.h"
+#include "i915_request.h"
 
 struct drm_printer;
 
@@ -37,6 +38,8 @@ void i915_sched_node_retire(struct i915_sched_node *node);
 
 void i915_sched_init_engine(struct i915_sched_engine *se,
 			    unsigned int subclass);
+void i915_sched_park_engine(struct i915_sched_engine *se);
+void i915_sched_fini_engine(struct i915_sched_engine *se);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
 
@@ -59,6 +62,18 @@ static inline void i915_priolist_free(struct i915_priolist *p)
 		__i915_priolist_free(p);
 }
 
+static inline bool i915_sched_is_idle(const struct i915_sched_engine *se)
+{
+	return RB_EMPTY_ROOT(&se->queue.rb_root);
+}
+
+static inline bool
+i915_sched_is_last_request(const struct i915_sched_engine *se,
+			   const struct i915_request *rq)
+{
+	return list_is_last_rcu(&rq->sched.link, &se->requests);
+}
+
 void i915_request_show_with_schedule(struct drm_printer *m,
 				     const struct i915_request *rq,
 				     const char *prefix,
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 5f21f5ac6dd9..1a4cf7e52186 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -82,10 +82,25 @@ struct i915_sched_ipi {
 
 struct i915_sched_engine {
 	spinlock_t lock;
+
 	struct list_head requests;
 	struct list_head hold; /* ready requests, but on hold */
+	/**
+	 * @queue: queue of requests, in priority lists
+	 */
+	struct rb_root_cached queue;
 
 	struct i915_sched_ipi ipi;
+
+	/**
+	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
+	 */
+	struct i915_priolist default_priolist;
+
+	/**
+	 * @no_priolist: priority lists disabled
+	 */
+	bool no_priolist;
 };
 
 struct i915_dependency {
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index 83739131d478..63431b6b85dd 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -92,7 +92,7 @@ static bool check_context_order(struct intel_engine_cs *engine)
 	last_context = 0;
 	last_seqno = 0;
 	last_prio = 0;
-	for (rb = rb_first_cached(&engine->execlists.queue); rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&engine->active.queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
 		struct i915_request *rq;
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 38/62] drm/i915: Move tasklet from execlists to sched

[Chris Wilson]

Move the scheduling tasklists out of the execlists backend into the
per-engine scheduling bookkeeping.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine.h        | 14 -----
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     | 11 ++--
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |  5 --
 .../drm/i915/gt/intel_execlists_submission.c  | 62 +++++++++----------
 drivers/gpu/drm/i915/gt/intel_gt_irq.c        |  2 +-
 drivers/gpu/drm/i915/gt/selftest_execlists.c  | 16 ++---
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  |  2 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |  6 +-
 drivers/gpu/drm/i915/gt/selftest_reset.c      |  6 +-
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 14 ++---
 drivers/gpu/drm/i915/i915_scheduler.c         | 14 +++--
 drivers/gpu/drm/i915/i915_scheduler.h         | 20 ++++++
 drivers/gpu/drm/i915/i915_scheduler_types.h   |  6 ++
 .../gpu/drm/i915/selftests/i915_scheduler.c   | 16 ++---
 14 files changed, 98 insertions(+), 96 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 20974415e7d8..801ae54cf60d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -122,20 +122,6 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return active;
 }
 
-static inline void
-execlists_active_lock_bh(struct intel_engine_execlists *execlists)
-{
-	local_bh_disable(); /* prevent local softirq and lock recursion */
-	tasklet_lock(&execlists->tasklet);
-}
-
-static inline void
-execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
-{
-	tasklet_unlock(&execlists->tasklet);
-	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
-}
-
 static inline u32
 intel_read_status_page(const struct intel_engine_cs *engine, int reg)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c111bbc4c02a..74aa0bf8c087 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -915,7 +915,6 @@ int intel_engines_init(struct intel_gt *gt)
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
 	i915_sched_fini_engine(&engine->active);
-	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
 	intel_breadcrumbs_free(engine->breadcrumbs);
 
@@ -1189,7 +1188,7 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 
 void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync)
 {
-	struct tasklet_struct *t = &engine->execlists.tasklet;
+	struct tasklet_struct *t = &engine->active.tasklet;
 
 	if (!t->func)
 		return;
@@ -1454,8 +1453,8 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 		drm_printf(m, "\tExeclist tasklet queued? %s (%s), preempt? %s, timeslice? %s\n",
 			   yesno(test_bit(TASKLET_STATE_SCHED,
-					  &engine->execlists.tasklet.state)),
-			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)),
+					  &engine->active.tasklet.state)),
+			   enableddisabled(!atomic_read(&engine->active.tasklet.count)),
 			   repr_timer(&engine->execlists.preempt),
 			   repr_timer(&engine->execlists.timer));
 
@@ -1479,7 +1478,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		execlists_active_lock_bh(execlists);
+		i915_sched_lock_bh(&engine->active);
 		rcu_read_lock();
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[160];
@@ -1510,7 +1509,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			i915_request_show(m, rq, hdr, 0);
 		}
 		rcu_read_unlock();
-		execlists_active_unlock_bh(execlists);
+		i915_sched_unlock_bh(&engine->active);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index a2a49e51b92d..694d2e04ba6a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -139,11 +139,6 @@ struct st_preempt_hang {
  * driver and the hardware state for execlist mode of submission.
  */
 struct intel_engine_execlists {
-	/**
-	 * @tasklet: softirq tasklet for bottom handler
-	 */
-	struct tasklet_struct tasklet;
-
 	/**
 	 * @timer: kick the current context if its timeslice expires
 	 */
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index b111d780f657..0a14b2d305d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -516,7 +516,7 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 		resubmit_virtual_request(rq, ve);
 
 	if (READ_ONCE(ve->request))
-		tasklet_hi_schedule(&ve->base.execlists.tasklet);
+		i915_sched_kick(&ve->base.active);
 }
 
 static inline void __execlists_schedule_out(struct i915_request *rq)
@@ -686,9 +686,9 @@ trace_ports(const struct intel_engine_execlists *execlists,
 }
 
 static inline bool
-reset_in_progress(const struct intel_engine_execlists *execlists)
+reset_in_progress(const struct intel_engine_cs *engine)
 {
-	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
+	return unlikely(!__tasklet_is_enabled(&engine->active.tasklet));
 }
 
 static __maybe_unused bool
@@ -705,7 +705,7 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 	trace_ports(execlists, msg, execlists->pending);
 
 	/* We may be messing around with the lists during reset, lalala */
-	if (reset_in_progress(execlists))
+	if (reset_in_progress(engine))
 		return true;
 
 	if (!execlists->pending[0]) {
@@ -1629,8 +1629,8 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 	 * access. Either we are inside the tasklet, or the tasklet is disabled
 	 * and we assume that is only inside the reset paths and so serialised.
 	 */
-	GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) &&
-		   !reset_in_progress(execlists));
+	GEM_BUG_ON(!tasklet_is_locked(&engine->active.tasklet) &&
+		   !reset_in_progress(engine));
 	GEM_BUG_ON(!intel_engine_in_execlists_submission_mode(engine));
 
 	/*
@@ -2027,13 +2027,13 @@ static void execlists_reset(struct intel_engine_cs *engine, const char *msg)
 	ENGINE_TRACE(engine, "reset for %s\n", msg);
 
 	/* Mark this tasklet as disabled to avoid waiting for it to complete */
-	tasklet_disable_nosync(&engine->execlists.tasklet);
+	tasklet_disable_nosync(&engine->active.tasklet);
 
 	ring_set_paused(engine, 1); /* Freeze the current request in place */
 	execlists_capture(engine);
 	intel_engine_reset(engine, msg);
 
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 	clear_and_wake_up_bit(bit, lock);
 }
 
@@ -2097,8 +2097,10 @@ static void execlists_submission_tasklet(unsigned long data)
 
 static void __execlists_kick(struct intel_engine_execlists *execlists)
 {
-	/* Kick the tasklet for some interrupt coalescing and reset handling */
-	tasklet_hi_schedule(&execlists->tasklet);
+	struct intel_engine_cs *engine =
+		container_of(execlists, typeof(*engine), execlists);
+
+	i915_sched_kick(&engine->active);
 }
 
 #define execlists_kick(t, member) \
@@ -2446,10 +2448,8 @@ static int execlists_resume(struct intel_engine_cs *engine)
 
 static void execlists_reset_prepare(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
 	ENGINE_TRACE(engine, "depth<-%d\n",
-		     atomic_read(&execlists->tasklet.count));
+		     atomic_read(&engine->active.tasklet.count));
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -2460,8 +2460,8 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	 * Turning off the execlists->tasklet until the reset is over
 	 * prevents the race.
 	 */
-	__tasklet_disable_sync_once(&execlists->tasklet);
-	GEM_BUG_ON(!reset_in_progress(execlists));
+	__tasklet_disable_sync_once(&engine->active.tasklet);
+	GEM_BUG_ON(!reset_in_progress(engine));
 
 	/*
 	 * We stop engines, otherwise we might get failed reset and a
@@ -2695,8 +2695,8 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	execlists->queue_priority_hint = INT_MIN;
 	engine->active.queue = RB_ROOT_CACHED;
 
-	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
-	execlists->tasklet.func = nop_submission_tasklet;
+	GEM_BUG_ON(__tasklet_is_enabled(&engine->active.tasklet));
+	engine->active.tasklet.func = nop_submission_tasklet;
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 	rcu_read_unlock();
@@ -2704,22 +2704,20 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 
 static void execlists_reset_finish(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
 	/*
 	 * After a GPU reset, we may have requests to replay. Do so now while
 	 * we still have the forcewake to be sure that the GPU is not allowed
 	 * to sleep before we restart and reload a context.
 	 */
-	GEM_BUG_ON(!reset_in_progress(execlists));
+	GEM_BUG_ON(!reset_in_progress(engine));
 	GEM_BUG_ON(engine->execlists.pending[0]);
 
 	/* And kick in case we missed a new request submission. */
-	if (__tasklet_enable(&execlists->tasklet))
-		__execlists_kick(execlists);
+	if (__tasklet_enable(&engine->active.tasklet))
+		i915_sched_kick(&engine->active);
 
 	ENGINE_TRACE(engine, "depth->%d\n",
-		     atomic_read(&execlists->tasklet.count));
+		     atomic_read(&engine->active.tasklet.count));
 }
 
 static void gen8_logical_ring_enable_irq(struct intel_engine_cs *engine)
@@ -2743,7 +2741,7 @@ static void execlists_park(struct intel_engine_cs *engine)
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = i915_request_enqueue;
-	engine->execlists.tasklet.func = execlists_submission_tasklet;
+	engine->active.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
 	engine->reset.rewind = execlists_reset_rewind;
@@ -2778,7 +2776,7 @@ static void execlists_shutdown(struct intel_engine_cs *engine)
 	/* Synchronise with residual timers and any softirq they raise */
 	del_timer_sync(&engine->execlists.timer);
 	del_timer_sync(&engine->execlists.preempt);
-	tasklet_kill(&engine->execlists.tasklet);
+	tasklet_kill(&engine->active.tasklet);
 }
 
 static void execlists_release(struct intel_engine_cs *engine)
@@ -2871,7 +2869,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	struct intel_uncore *uncore = engine->uncore;
 	u32 base = engine->mmio_base;
 
-	tasklet_init(&engine->execlists.tasklet,
+	tasklet_init(&engine->active.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
 	timer_setup(&engine->execlists.preempt, execlists_preempt, 0);
@@ -2960,7 +2958,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 	 * rbtrees as in the case it is running in parallel, it may reinsert
 	 * the rb_node into a sibling.
 	 */
-	tasklet_kill(&ve->base.execlists.tasklet);
+	tasklet_kill(&ve->base.active.tasklet);
 
 	/* Decouple ourselves from the siblings, no more access allowed. */
 	for (n = 0; n < ve->num_siblings; n++) {
@@ -2978,7 +2976,7 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 
 		spin_unlock_irq(&sibling->active.lock);
 	}
-	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet));
+	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.active.tasklet));
 	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
 
 	lrc_fini(&ve->context);
@@ -3190,7 +3188,7 @@ static void virtual_submission_tasklet(unsigned long data)
 		GEM_BUG_ON(RB_EMPTY_NODE(&node->rb));
 		node->prio = prio;
 		if (first && prio > sibling->execlists.queue_priority_hint)
-			tasklet_hi_schedule(&sibling->execlists.tasklet);
+			i915_sched_kick(&sibling->active);
 
 unlock_engine:
 		spin_unlock_irq(&sibling->active.lock);
@@ -3231,7 +3229,7 @@ static void virtual_submit_request(struct i915_request *rq)
 	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
 	list_move_tail(&rq->sched.link, virtual_queue(ve));
 
-	tasklet_hi_schedule(&ve->base.execlists.tasklet);
+	i915_sched_kick(&ve->base.active);
 
 unlock:
 	spin_unlock_irqrestore(&ve->base.active.lock, flags);
@@ -3329,7 +3327,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	INIT_LIST_HEAD(virtual_queue(ve));
 	ve->base.execlists.queue_priority_hint = INT_MIN;
-	tasklet_init(&ve->base.execlists.tasklet,
+	tasklet_init(&ve->base.active.tasklet,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
 
@@ -3359,7 +3357,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 		 * layering if we handle cloning of the requests and
 		 * submitting a copy into each backend.
 		 */
-		if (sibling->execlists.tasklet.func !=
+		if (sibling->active.tasklet.func !=
 		    execlists_submission_tasklet) {
 			err = -ENODEV;
 			goto err_put;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 9830342aa6f4..2106fb403c3e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -60,7 +60,7 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 	}
 
 	if (tasklet)
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		i915_sched_kick(&engine->active);
 }
 
 static u32
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 276743d553a9..291fb04807b9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -44,7 +44,7 @@ static int wait_for_submit(struct intel_engine_cs *engine,
 			   unsigned long timeout)
 {
 	/* Ignore our own attempts to suppress excess tasklets */
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	i915_sched_kick(&engine->active);
 
 	timeout += jiffies;
 	do {
@@ -603,9 +603,9 @@ static int live_hold_reset(void *arg)
 			err = -EBUSY;
 			goto out;
 		}
-		tasklet_disable(&engine->execlists.tasklet);
+		tasklet_disable(&engine->active.tasklet);
 
-		engine->execlists.tasklet.func(engine->execlists.tasklet.data);
+		engine->active.tasklet.func(engine->active.tasklet.data);
 		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 		i915_request_get(rq);
@@ -615,7 +615,7 @@ static int live_hold_reset(void *arg)
 		__intel_engine_reset_bh(engine, NULL);
 		GEM_BUG_ON(rq->fence.error != -EIO);
 
-		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_enable(&engine->active.tasklet);
 		clear_and_wake_up_bit(I915_RESET_ENGINE + id,
 				      &gt->reset.flags);
 		local_bh_enable();
@@ -1174,7 +1174,7 @@ static int live_timeslice_rewind(void *arg)
 		while (i915_request_is_active(rq[A2])) { /* semaphore yield! */
 			/* Wait for the timeslice to kick in */
 			del_timer(&engine->execlists.timer);
-			tasklet_hi_schedule(&engine->execlists.tasklet);
+			i915_sched_kick(&engine->active);
 			intel_engine_flush_submission(engine);
 		}
 		/* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */
@@ -4525,9 +4525,9 @@ static int reset_virtual_engine(struct intel_gt *gt,
 		err = -EBUSY;
 		goto out_heartbeat;
 	}
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->active.tasklet);
 
-	engine->execlists.tasklet.func(engine->execlists.tasklet.data);
+	engine->active.tasklet.func(engine->active.tasklet.data);
 	GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 	/* Fake a preemption event; failed of course */
@@ -4544,7 +4544,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	GEM_BUG_ON(rq->fence.error != -EIO);
 
 	/* Release our grasp on the engine, letting CS flow again */
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 	clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags);
 	local_bh_enable();
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 927d54c702f4..cc0120411d62 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1568,7 +1568,7 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 				     const struct igt_atomic_section *p,
 				     const char *mode)
 {
-	struct tasklet_struct * const t = &engine->execlists.tasklet;
+	struct tasklet_struct * const t = &engine->active.tasklet;
 	int err;
 
 	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index f449c56e0946..e26f7f957468 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -49,7 +49,7 @@ static int wait_for_submit(struct intel_engine_cs *engine,
 			   unsigned long timeout)
 {
 	/* Ignore our own attempts to suppress excess tasklets */
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	i915_sched_kick(&engine->active);
 
 	timeout += jiffies;
 	do {
@@ -1608,12 +1608,12 @@ static void garbage_reset(struct intel_engine_cs *engine,
 
 	local_bh_disable();
 	if (!test_and_set_bit(bit, lock)) {
-		tasklet_disable(&engine->execlists.tasklet);
+		tasklet_disable(&engine->active.tasklet);
 
 		if (!rq->fence.error)
 			__intel_engine_reset_bh(engine, NULL);
 
-		tasklet_enable(&engine->execlists.tasklet);
+		tasklet_enable(&engine->active.tasklet);
 		clear_and_wake_up_bit(bit, lock);
 	}
 	local_bh_enable();
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 5ec8d4e9983f..2a7059923a01 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -321,7 +321,7 @@ static int igt_atomic_engine_reset(void *arg)
 		goto out_unlock;
 
 	for_each_engine(engine, gt, id) {
-		tasklet_disable(&engine->execlists.tasklet);
+		tasklet_disable(&engine->active.tasklet);
 		intel_engine_pm_get(engine);
 
 		for (p = igt_atomic_phases; p->name; p++) {
@@ -345,8 +345,8 @@ static int igt_atomic_engine_reset(void *arg)
 		}
 
 		intel_engine_pm_put(engine);
-		tasklet_enable(&engine->execlists.tasklet);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		tasklet_enable(&engine->active.tasklet);
+		tasklet_hi_schedule(&engine->active.tasklet);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 6d97b5ad09b5..b9cb6807d101 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -372,8 +372,6 @@ static void guc_submission_tasklet(unsigned long data)
 
 static void guc_reset_prepare(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
 	ENGINE_TRACE(engine, "\n");
 
 	/*
@@ -385,7 +383,7 @@ static void guc_reset_prepare(struct intel_engine_cs *engine)
 	 * Turning off the execlists->tasklet until the reset is over
 	 * prevents the race.
 	 */
-	__tasklet_disable_sync_once(&execlists->tasklet);
+	__tasklet_disable_sync_once(&engine->active.tasklet);
 }
 
 static void
@@ -508,14 +506,12 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 
 static void guc_reset_finish(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-
-	if (__tasklet_enable(&execlists->tasklet))
+	if (__tasklet_enable(&engine->active.tasklet))
 		/* And kick in case we missed a new request submission. */
-		tasklet_hi_schedule(&execlists->tasklet);
+		tasklet_hi_schedule(&engine->active.tasklet);
 
 	ENGINE_TRACE(engine, "depth->%d\n",
-		     atomic_read(&execlists->tasklet.count));
+		     atomic_read(&engine->active.tasklet.count));
 }
 
 /*
@@ -613,7 +609,7 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	 */
 	intel_execlists_set_default_submission(engine);
 
-	engine->execlists.tasklet.func = guc_submission_tasklet;
+	engine->active.tasklet.func = guc_submission_tasklet;
 
 	/* do not use execlists park/unpark */
 	engine->park = engine->unpark = NULL;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 9d77dae93be9..99f1dd6a9719 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -125,6 +125,7 @@ void i915_sched_park_engine(struct i915_sched_engine *se)
 void i915_sched_fini_engine(struct i915_sched_engine *se)
 {
 	GEM_BUG_ON(!list_empty(&se->requests));
+	tasklet_kill(&se->tasklet); /* flush the callback */
 }
 
 static void __ipi_add(struct i915_request *rq)
@@ -339,7 +340,7 @@ static void kick_submission(struct intel_engine_cs *engine,
 
 	engine->execlists.queue_priority_hint = prio;
 	if (need_preempt(prio, rq_prio(inflight)))
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		i915_sched_kick(&engine->active);
 }
 
 static void ipi_priority(struct i915_request *rq, int prio)
@@ -619,16 +620,17 @@ static bool ancestor_on_hold(const struct intel_engine_cs *engine,
 void i915_request_enqueue(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
+	struct i915_sched_engine *se = &engine->active;
 	unsigned long flags;
 	bool kick = false;
 
 	/* Will be called from irq-context when using foreign fences. */
-	spin_lock_irqsave(&engine->active.lock, flags);
+	spin_lock_irqsave(&se->lock, flags);
 	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
 
 	if (unlikely(ancestor_on_hold(engine, rq))) {
 		RQ_TRACE(rq, "ancestor on hold\n");
-		list_add_tail(&rq->sched.link, &engine->active.hold);
+		list_add_tail(&rq->sched.link, &se->hold);
 		i915_request_set_hold(rq);
 	} else {
 		queue_request(engine, rq);
@@ -639,9 +641,9 @@ void i915_request_enqueue(struct i915_request *rq)
 	}
 
 	GEM_BUG_ON(list_empty(&rq->sched.link));
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	spin_unlock_irqrestore(&se->lock, flags);
 	if (kick)
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		i915_sched_kick(se);
 }
 
 struct i915_request *
@@ -754,7 +756,7 @@ void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 
 	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
 		engine->execlists.queue_priority_hint = rq_prio(rq);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
+		i915_sched_kick(&engine->active);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 6bb9d8c3519a..a68747d682d2 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -74,6 +74,26 @@ i915_sched_is_last_request(const struct i915_sched_engine *se,
 	return list_is_last_rcu(&rq->sched.link, &se->requests);
 }
 
+static inline void
+i915_sched_lock_bh(struct i915_sched_engine *se)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&se->tasklet);
+}
+
+static inline void
+i915_sched_unlock_bh(struct i915_sched_engine *se)
+{
+	tasklet_unlock(&se->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
+static inline void i915_sched_kick(struct i915_sched_engine *se)
+{
+	/* Kick the tasklet for some interrupt coalescing and reset handling */
+	tasklet_hi_schedule(&se->tasklet);
+}
+
 void i915_request_show_with_schedule(struct drm_printer *m,
 				     const struct i915_request *rq,
 				     const char *prefix,
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 1a4cf7e52186..92332fb71b14 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -7,6 +7,7 @@
 #ifndef _I915_SCHEDULER_TYPES_H_
 #define _I915_SCHEDULER_TYPES_H_
 
+#include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/workqueue.h>
 
@@ -101,6 +102,11 @@ struct i915_sched_engine {
 	 * @no_priolist: priority lists disabled
 	 */
 	bool no_priolist;
+
+	/**
+	 * @tasklet: softirq tasklet for bottom half
+	 */
+	struct tasklet_struct tasklet;
 };
 
 struct i915_dependency {
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index 63431b6b85dd..0756ba8e68bb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -172,12 +172,12 @@ static int __single_chain(struct intel_engine_cs *engine, unsigned long length,
 	}
 	intel_engine_flush_submission(engine);
 
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->active.tasklet);
 	local_bh_disable();
 	if (fn(rq, count, count - 1) && !check_context_order(engine))
 		err = -EINVAL;
 	local_bh_enable();
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 
 	igt_spinner_end(&spin);
 err_context:
@@ -258,12 +258,12 @@ static int __wide_chain(struct intel_engine_cs *engine, unsigned long width,
 	}
 	intel_engine_flush_submission(engine);
 
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->active.tasklet);
 	local_bh_disable();
 	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
 		err = -EINVAL;
 	local_bh_enable();
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 
 	igt_spinner_end(&spin);
 err_free:
@@ -348,12 +348,12 @@ static int __inv_chain(struct intel_engine_cs *engine, unsigned long width,
 	}
 	intel_engine_flush_submission(engine);
 
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->active.tasklet);
 	local_bh_disable();
 	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
 		err = -EINVAL;
 	local_bh_enable();
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 
 	igt_spinner_end(&spin);
 err_free:
@@ -455,12 +455,12 @@ static int __sparse_chain(struct intel_engine_cs *engine, unsigned long width,
 	}
 	intel_engine_flush_submission(engine);
 
-	tasklet_disable(&engine->execlists.tasklet);
+	tasklet_disable(&engine->active.tasklet);
 	local_bh_disable();
 	if (fn(rq[i - 1], i, count) && !check_context_order(engine))
 		err = -EINVAL;
 	local_bh_enable();
-	tasklet_enable(&engine->execlists.tasklet);
+	tasklet_enable(&engine->active.tasklet);
 
 	igt_spinner_end(&spin);
 err_free:
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 39/62] drm/i915: Replace priolist rbtree with a skiplist

[Chris Wilson]

Replace the priolist rbtree with a skiplist. The crucial difference is
that walking and removing the first element of a skiplist is O(1), but
O(lgN) for an rbtree, as we need to rebalance on remove. This is a
hindrance for submission latency as it occurs between picking a request
for the priolist and submitting it to hardware, as well effectively
trippling the number of O(lgN) operations required under the irqoff lock.
This is critical to reducing the latency jitter with multiple clients.

The downsides to skiplists are that lookup/insertion is only
probablistically O(lgN) and there is a significant memory penalty to
as each skip node is larger than the rbtree equivalent. Furthermore, we
don't use dynamic arrays for the skiplist, so the allocation is fixed,
and imposes an upper bound on the scalability wrt to the number of
inflight requests.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  |  63 ++++---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c |  30 +--
 drivers/gpu/drm/i915/i915_priolist_types.h    |  29 ++-
 drivers/gpu/drm/i915/i915_scheduler.c         | 178 ++++++++++++------
 drivers/gpu/drm/i915/i915_scheduler.h         |  11 +-
 drivers/gpu/drm/i915/i915_scheduler_types.h   |   2 +-
 .../drm/i915/selftests/i915_mock_selftests.h  |   1 +
 .../gpu/drm/i915/selftests/i915_scheduler.c   |  42 ++++-
 8 files changed, 241 insertions(+), 115 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 0a14b2d305d2..d99d682d8569 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -246,11 +246,6 @@ ring_set_paused(const struct intel_engine_cs *engine, int state)
 		wmb();
 }
 
-static inline struct i915_priolist *to_priolist(struct rb_node *rb)
-{
-	return rb_entry(rb, struct i915_priolist, node);
-}
-
 static inline int rq_prio(const struct i915_request *rq)
 {
 	return READ_ONCE(rq->sched.attr.priority);
@@ -274,15 +269,31 @@ static int effective_prio(const struct i915_request *rq)
 	return prio;
 }
 
-static int queue_prio(const struct i915_sched_engine *se)
+static struct i915_request *first_request(struct i915_sched_engine *se)
 {
-	struct rb_node *rb;
+	struct i915_priolist *pl;
+
+	for_each_priolist(pl, &se->queue) {
+		if (likely(!list_empty(&pl->requests)))
+			return list_first_entry(&pl->requests,
+						struct i915_request,
+						sched.link);
+
+		i915_priolist_advance(&se->queue, pl);
+	}
+
+	return NULL;
+}
 
-	rb = rb_first_cached(&se->queue);
-	if (!rb)
+static int queue_prio(struct i915_sched_engine *se)
+{
+	struct i915_request *rq;
+
+	rq = first_request(se);
+	if (!rq)
 		return INT_MIN;
 
-	return to_priolist(rb)->priority;
+	return rq_prio(rq);
 }
 
 static int virtual_prio(const struct intel_engine_execlists *el)
@@ -292,7 +303,7 @@ static int virtual_prio(const struct intel_engine_execlists *el)
 	return rb ? rb_entry(rb, struct ve_node, rb)->prio : INT_MIN;
 }
 
-static inline bool need_preempt(const struct intel_engine_cs *engine,
+static inline bool need_preempt(struct intel_engine_cs *engine,
 				const struct i915_request *rq)
 {
 	int last_prio;
@@ -1112,6 +1123,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct i915_request ** const last_port = port + execlists->port_mask;
 	struct i915_request *last = *execlists->active;
 	struct virtual_engine *ve;
+	struct i915_priolist *pl;
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -1317,11 +1329,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			break;
 	}
 
-	while ((rb = rb_first_cached(&engine->active.queue))) {
-		struct i915_priolist *p = to_priolist(rb);
+	for_each_priolist(pl, &engine->active.queue) {
 		struct i915_request *rq, *rn;
 
-		priolist_for_each_request_consume(rq, rn, p) {
+		priolist_for_each_request_safe(rq, rn, pl) {
 			bool merge = true;
 
 			/*
@@ -1396,8 +1407,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			}
 		}
 
-		rb_erase_cached(&p->node, &engine->active.queue);
-		i915_priolist_free(p);
+		i915_priolist_advance(&engine->active.queue, pl);
 	}
 done:
 	*port++ = i915_request_get(last);
@@ -2621,6 +2631,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
+	struct i915_priolist *pl;
 	struct rb_node *rb;
 	unsigned long flags;
 
@@ -2651,16 +2662,12 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&engine->active.queue))) {
-		struct i915_priolist *p = to_priolist(rb);
-
-		priolist_for_each_request_consume(rq, rn, p) {
+	for_each_priolist(pl, &engine->active.queue) {
+		priolist_for_each_request_safe(rq, rn, pl) {
 			mark_eio(rq);
 			__i915_request_submit(rq);
 		}
-
-		rb_erase_cached(&p->node, &engine->active.queue);
-		i915_priolist_free(p);
+		i915_priolist_advance(&engine->active.queue, pl);
 	}
 	GEM_BUG_ON(!i915_sched_is_idle(&engine->active));
 
@@ -2693,7 +2700,6 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority_hint = INT_MIN;
-	engine->active.queue = RB_ROOT_CACHED;
 
 	GEM_BUG_ON(__tasklet_is_enabled(&engine->active.tasklet));
 	engine->active.tasklet.func = nop_submission_tasklet;
@@ -3076,6 +3082,8 @@ static void virtual_context_exit(struct intel_context *ce)
 
 	for (n = 0; n < ve->num_siblings; n++)
 		intel_engine_pm_put(ve->siblings[n]);
+
+	i915_sched_park_engine(&ve->base.active);
 }
 
 static const struct intel_context_ops virtual_context_ops = {
@@ -3486,6 +3494,7 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 {
 	const struct intel_engine_execlists *execlists = &engine->execlists;
 	struct i915_request *rq, *last;
+	struct i915_priolist *pl;
 	unsigned long flags;
 	unsigned int count;
 	struct rb_node *rb;
@@ -3515,10 +3524,8 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 
 	last = NULL;
 	count = 0;
-	for (rb = rb_first_cached(&engine->active.queue); rb; rb = rb_next(rb)) {
-		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
-
-		priolist_for_each_request(rq, p) {
+	for_each_priolist(pl, &engine->active.queue) {
+		priolist_for_each_request(rq, pl) {
 			if (count++ < max - 1)
 				show_request(m, rq, "\t\t", 0);
 			else
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index b9cb6807d101..34be8dc8949e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -55,11 +55,6 @@
  *
  */
 
-static inline struct i915_priolist *to_priolist(struct rb_node *rb)
-{
-	return rb_entry(rb, struct i915_priolist, node);
-}
-
 static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id)
 {
 	struct guc_stage_desc *base = guc->stage_desc_pool_vaddr;
@@ -292,8 +287,8 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 	struct i915_request ** const last_port = first + execlists->port_mask;
 	struct i915_request *last = first[0];
 	struct i915_request **port;
+	struct i915_priolist *pl;
 	bool submit = false;
-	struct rb_node *rb;
 
 	lockdep_assert_held(&engine->active.lock);
 
@@ -310,11 +305,10 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 	 * event.
 	 */
 	port = first;
-	while ((rb = rb_first_cached(&engine->active.queue))) {
-		struct i915_priolist *p = to_priolist(rb);
+	for_each_priolist(pl, &engine->active.queue) {
 		struct i915_request *rq, *rn;
 
-		priolist_for_each_request_consume(rq, rn, p) {
+		priolist_for_each_request_safe(rq, rn, pl) {
 			if (last && rq->context != last->context) {
 				if (port == last_port)
 					goto done;
@@ -330,12 +324,11 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 			last = rq;
 		}
 
-		rb_erase_cached(&p->node, &engine->active.queue);
-		i915_priolist_free(p);
+		i915_priolist_advance(&engine->active.queue, pl);
 	}
 done:
 	execlists->queue_priority_hint =
-		rb ? to_priolist(rb)->priority : INT_MIN;
+		pl != &engine->active.queue.sentinel ? pl->priority : INT_MIN;
 	if (submit) {
 		*port = schedule_in(last, port - execlists->inflight);
 		*++port = NULL;
@@ -450,7 +443,7 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
-	struct rb_node *rb;
+	struct i915_priolist *p;
 	unsigned long flags;
 
 	ENGINE_TRACE(engine, "\n");
@@ -481,25 +474,20 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	while ((rb = rb_first_cached(&engine->active.queue))) {
-		struct i915_priolist *p = to_priolist(rb);
-
-		priolist_for_each_request_consume(rq, rn, p) {
+	for_each_priolist(p, &engine->active.queue) {
+		priolist_for_each_request_safe(rq, rn, p) {
 			list_del_init(&rq->sched.link);
 			__i915_request_submit(rq);
 			dma_fence_set_error(&rq->fence, -EIO);
 			i915_request_mark_complete(rq);
 		}
-
-		rb_erase_cached(&p->node, &engine->active.queue);
-		i915_priolist_free(p);
+		i915_priolist_advance(&engine->active.queue, p);
 	}
 	GEM_BUG_ON(!i915_sched_is_idle(&engine->active));
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority_hint = INT_MIN;
-	engine->active.queue = RB_ROOT_CACHED;
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index bc2fa84f98a8..807cd8f65481 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -38,10 +38,37 @@ enum {
 #define I915_PRIORITY_UNPREEMPTABLE INT_MAX
 #define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
 
+#ifdef CONFIG_64BIT
+#define I915_PRIOLIST_HEIGHT 12
+#else
+#define I915_PRIOLIST_HEIGHT 11
+#endif
+
 struct i915_priolist {
 	struct list_head requests;
-	struct rb_node node;
 	int priority;
+
+	int level;
+	struct i915_priolist *next[I915_PRIOLIST_HEIGHT];
+};
+
+struct i915_priolist_root {
+	struct i915_priolist sentinel;
+	u32 prng;
 };
 
+#define priolist_first(root) ((root)->sentinel.next[0])
+#define i915_priolist_is_empty(root) (priolist_first(root) == &(root)->sentinel)
+
+#define for_each_priolist(p, root) \
+	for ((p) = priolist_first(root); \
+	     (p) != &(root)->sentinel; \
+	     (p) = (p)->next[0])
+
+#define priolist_for_each_request(it, plist) \
+	list_for_each_entry(it, &(plist)->requests, sched.link)
+
+#define priolist_for_each_request_safe(it, n, plist) \
+	list_for_each_entry_safe(it, n, &(plist)->requests, sched.link)
+
 #endif /* _I915_PRIOLIST_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 99f1dd6a9719..a0e8ecd06d8d 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -4,7 +4,9 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include <linux/bitops.h>
 #include <linux/mutex.h>
+#include <linux/prandom.h>
 
 #include "gt/intel_ring.h"
 #include "gt/intel_lrc_reg.h"
@@ -91,15 +93,25 @@ static void i915_sched_init_ipi(struct i915_sched_ipi *ipi)
 	ipi->list = NULL;
 }
 
+static void init_priolist(struct i915_priolist_root *const root)
+{
+	struct i915_priolist *pl = &root->sentinel;
+
+	memset_p((void **)pl->next, pl, ARRAY_SIZE(pl->next));
+	pl->priority = INT_MIN;
+	INIT_LIST_HEAD(&pl->requests);
+	pl->level = 0;
+}
+
 void i915_sched_init_engine(struct i915_sched_engine *se,
 			    unsigned int subclass)
 {
 	spin_lock_init(&se->lock);
 	lockdep_set_subclass(&se->lock, subclass);
 
+	init_priolist(&se->queue);
 	INIT_LIST_HEAD(&se->requests);
 	INIT_LIST_HEAD(&se->hold);
-	se->queue = RB_ROOT_CACHED;
 
 	i915_sched_init_ipi(&se->ipi);
 
@@ -116,8 +128,37 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
 #endif
 }
 
+__maybe_unused static bool priolist_idle(struct i915_priolist_root *root)
+{
+	struct i915_priolist *pl = &root->sentinel;
+	int lvl;
+
+	for (lvl = 0; lvl < ARRAY_SIZE(pl->next); lvl++) {
+		if (pl->next[lvl] != pl) {
+			GEM_TRACE_ERR("root[%d] is not empty\n", lvl);
+			return false;
+		}
+	}
+
+	if (pl->level) {
+		GEM_TRACE_ERR("root is not clear: %d\n", pl->level);
+		return false;
+	}
+
+	return true;
+}
+
 void i915_sched_park_engine(struct i915_sched_engine *se)
 {
+	struct i915_priolist_root *root = &se->queue;
+	struct i915_priolist *pl, *n;
+
+	GEM_BUG_ON(!priolist_idle(root));
+
+	list_for_each_entry_safe(pl, n, &root->sentinel.requests, requests)
+		kmem_cache_free(global.slab_priorities, pl);
+	INIT_LIST_HEAD(&root->sentinel.requests);
+
 	GEM_BUG_ON(!i915_sched_is_idle(se));
 	se->no_priolist = false;
 }
@@ -183,68 +224,54 @@ static inline bool node_signaled(const struct i915_sched_node *node)
 	return i915_request_completed(node_to_request(node));
 }
 
-static inline struct i915_priolist *to_priolist(struct rb_node *rb)
+static inline unsigned int random_level(struct i915_priolist_root *root)
 {
-	return rb_entry(rb, struct i915_priolist, node);
-}
-
-static void assert_priolists(struct i915_sched_engine * const se)
-{
-	struct rb_node *rb;
-	long last_prio;
-
-	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-		return;
-
-	GEM_BUG_ON(rb_first_cached(&se->queue) !=
-		   rb_first(&se->queue.rb_root));
-
-	last_prio = INT_MAX;
-	for (rb = rb_first_cached(&se->queue); rb; rb = rb_next(rb)) {
-		const struct i915_priolist *p = to_priolist(rb);
-
-		GEM_BUG_ON(p->priority > last_prio);
-		last_prio = p->priority;
-	}
+	root->prng = next_pseudo_random32(root->prng);
+	return min_t(int, __ffs(root->prng) / 2, I915_PRIOLIST_HEIGHT - 1);
 }
 
 static struct list_head *
 lookup_priolist(struct intel_engine_cs *engine, int prio)
 {
+	struct i915_priolist *update[I915_PRIOLIST_HEIGHT];
 	struct i915_sched_engine * const se = &engine->active;
-	struct i915_priolist *p;
-	struct rb_node **parent, *rb;
-	bool first = true;
-
-	lockdep_assert_held(&engine->active.lock);
-	assert_priolists(se);
+	struct i915_priolist_root *root = &se->queue;
+	struct i915_priolist *pl, *tmp;
+	int lvl;
 
+	lockdep_assert_held(&se->lock);
 	if (unlikely(se->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
 
-find_priolist:
-	/* most positive priority is scheduled first, equal priorities fifo */
-	rb = NULL;
-	parent = &se->queue.rb_root.rb_node;
-	while (*parent) {
-		rb = *parent;
-		p = to_priolist(rb);
-		if (prio > p->priority) {
-			parent = &rb->rb_left;
-		} else if (prio < p->priority) {
-			parent = &rb->rb_right;
-			first = false;
-		} else {
-			return &p->requests;
-		}
+	for_each_priolist(pl, root) { /* recycle any empty elements before us */
+		if (pl->priority >= prio || !list_empty(&pl->requests))
+			break;
+
+		i915_priolist_advance(root, pl);
 	}
 
+find_priolist:
+	pl = &root->sentinel;
+	lvl = pl->level;
+	do {
+		while (tmp = pl->next[lvl], tmp->priority >= prio)
+			pl = tmp;
+		if (pl->priority == prio)
+			goto out;
+		update[lvl] = pl;
+	} while (--lvl >= 0);
+
 	if (prio == I915_PRIORITY_NORMAL) {
-		p = &se->default_priolist;
+		pl = &se->default_priolist;
+	} else if (!list_empty(&root->sentinel.requests)) {
+		pl = list_first_entry(&root->sentinel.requests,
+				      struct i915_priolist,
+				      requests);
+		__list_del_entry(&pl->requests);
 	} else {
-		p = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
+		pl = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
 		/* Convert an allocation failure to a priority bump */
-		if (unlikely(!p)) {
+		if (unlikely(!pl)) {
 			prio = I915_PRIORITY_NORMAL; /* recurses just once */
 
 			/* To maintain ordering with all rendering, after an
@@ -260,18 +287,61 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 		}
 	}
 
-	p->priority = prio;
-	INIT_LIST_HEAD(&p->requests);
+	pl->priority = prio;
+	INIT_LIST_HEAD(&pl->requests);
+
+	lvl = random_level(root);
+	if (lvl > root->sentinel.level) {
+		lvl = ++root->sentinel.level;
+		update[lvl] = &root->sentinel;
+	}
 
-	rb_link_node(&p->node, rb, parent);
-	rb_insert_color_cached(&p->node, &se->queue, first);
+	pl->level = lvl;
+	do {
+		tmp = update[lvl];
+		pl->next[lvl] = update[lvl]->next[lvl];
+		tmp->next[lvl] = pl;
+	} while (--lvl >= 0);
+
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) {
+		struct i915_priolist *chk;
+
+		chk = &root->sentinel;
+		lvl = chk->level;
+		do {
+			while (tmp = chk->next[lvl], tmp->priority >= prio)
+				chk = tmp;
+		} while (--lvl >= 0);
+
+		GEM_BUG_ON(chk != pl);
+	}
 
-	return &p->requests;
+out:
+	GEM_BUG_ON(pl == &root->sentinel);
+	return &pl->requests;
 }
 
-void __i915_priolist_free(struct i915_priolist *p)
+void i915_priolist_advance(struct i915_priolist_root *root,
+			   struct i915_priolist *pl)
 {
-	kmem_cache_free(global.slab_priorities, p);
+	int lvl;
+
+	GEM_BUG_ON(!list_empty(&pl->requests));
+	GEM_BUG_ON(pl == &root->sentinel);
+
+	if (pl->priority != I915_PRIORITY_NORMAL)
+		list_add(&pl->requests, &root->sentinel.requests);
+
+	for (lvl = 0; lvl <= pl->level; lvl++)
+		root->sentinel.next[lvl] = pl->next[lvl];
+
+	if (pl->level == root->sentinel.level) {
+		pl = &root->sentinel;
+		lvl = pl->level;
+		while (lvl > -0 && pl->next[lvl] == pl)
+			lvl--;
+		pl->level = lvl;
+	}
 }
 
 static struct i915_request *
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index a68747d682d2..4432aab230b6 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -16,12 +16,6 @@
 
 struct drm_printer;
 
-#define priolist_for_each_request(it, plist) \
-	list_for_each_entry(it, &(plist)->requests, sched.link)
-
-#define priolist_for_each_request_consume(it, n, plist) \
-	list_for_each_entry_safe(it, n, &(plist)->requests, sched.link)
-
 void i915_sched_node_init(struct i915_sched_node *node);
 void i915_sched_node_reinit(struct i915_sched_node *node);
 
@@ -64,7 +58,7 @@ static inline void i915_priolist_free(struct i915_priolist *p)
 
 static inline bool i915_sched_is_idle(const struct i915_sched_engine *se)
 {
-	return RB_EMPTY_ROOT(&se->queue.rb_root);
+	return i915_priolist_is_empty(&se->queue);
 }
 
 static inline bool
@@ -94,6 +88,9 @@ static inline void i915_sched_kick(struct i915_sched_engine *se)
 	tasklet_hi_schedule(&se->tasklet);
 }
 
+void i915_priolist_advance(struct i915_priolist_root *root,
+			   struct i915_priolist *old);
+
 void i915_request_show_with_schedule(struct drm_printer *m,
 				     const struct i915_request *rq,
 				     const char *prefix,
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 92332fb71b14..c155e4faa30b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -89,7 +89,7 @@ struct i915_sched_engine {
 	/**
 	 * @queue: queue of requests, in priority lists
 	 */
-	struct rb_root_cached queue;
+	struct i915_priolist_root queue;
 
 	struct i915_sched_ipi ipi;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 3db34d3eea58..946c93441c1f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -25,6 +25,7 @@ selftest(ring, intel_ring_mock_selftests)
 selftest(engine, intel_engine_cs_mock_selftests)
 selftest(timelines, intel_timeline_mock_selftests)
 selftest(requests, i915_request_mock_selftests)
+selftest(scheduler, i915_scheduler_mock_selftests)
 selftest(objects, i915_gem_object_mock_selftests)
 selftest(phys, i915_gem_phys_mock_selftests)
 selftest(dmabuf, i915_gem_dmabuf_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index 0756ba8e68bb..085a00998e95 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -12,6 +12,43 @@
 #include "selftests/igt_spinner.h"
 #include "selftests/i915_random.h"
 
+static int mock_skiplist_levels(void *dummy)
+{
+	struct i915_priolist_root root = {};
+	struct i915_priolist *pl = &root.sentinel;
+	int count, lvl;
+
+	for (count = 0; count < 16384; count++) {
+		lvl = random_level(&root);
+		if (lvl > pl->level)
+			lvl = ++pl->level;
+
+		pl->next[lvl] = ptr_inc(pl->next[lvl]);
+	}
+
+	for (lvl = 0; lvl <= pl->level; lvl++) {
+		int x = ilog2((unsigned long)pl->next[lvl]);
+		char row[80];
+
+		memset(row, '*', x);
+		row[x] = '\0';
+
+		pr_info("[%2d] %5lu %s\n",
+			lvl, (unsigned long)pl->next[lvl], row);
+	}
+
+	return 0;
+}
+
+int i915_scheduler_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(mock_skiplist_levels),
+	};
+
+	return i915_subtests(tests, NULL);
+}
+
 static void scheduling_disable(struct intel_engine_cs *engine)
 {
 	engine->props.preempt_timeout_ms = 0;
@@ -80,9 +117,9 @@ static int all_engines(struct drm_i915_private *i915,
 static bool check_context_order(struct intel_engine_cs *engine)
 {
 	u64 last_seqno, last_context;
+	struct i915_priolist *p;
 	unsigned long count;
 	bool result = false;
-	struct rb_node *rb;
 	int last_prio;
 
 	/* We expect the execution order to follow ascending fence-context */
@@ -92,8 +129,7 @@ static bool check_context_order(struct intel_engine_cs *engine)
 	last_context = 0;
 	last_seqno = 0;
 	last_prio = 0;
-	for (rb = rb_first_cached(&engine->active.queue); rb; rb = rb_next(rb)) {
-		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
+	for_each_priolist(p, &engine->active.queue) {
 		struct i915_request *rq;
 
 		priolist_for_each_request(rq, p) {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 40/62] drm/i915: Wrap cmpxchg64 with try_cmpxchg64() helper

[Chris Wilson]

Wrap cmpxchg64 with a try_cmpxchg()-esque helper. Hiding the old-value
dance in the helper allows for cleaner code.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_utils.h | 32 +++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 54773371e6bd..f8addd6d5afa 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -456,4 +456,36 @@ static inline bool timer_expired(const struct timer_list *t)
  */
 #define IS_ACTIVE(config) ((config) != 0)
 
+#ifndef try_cmpxchg64
+#if IS_ENABLED(CONFIG_64BIT)
+#define try_cmpxchg64(_ptr, _pold, _new) try_cmpxchg(_ptr, _pold, _new)
+#else
+#define try_cmpxchg64(_ptr, _pold, _new)				\
+({									\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __cur = cmpxchg64(_ptr, __old, _new);	\
+	bool success = __cur == __old;					\
+	if (unlikely(!success))						\
+		*_old = __cur;						\
+	likely(success);						\
+})
+#endif
+#endif
+
+#ifndef xchg64
+#if IS_ENABLED(CONFIG_64BIT)
+#define xchg64(_ptr, _new) xchg(_ptr, _new)
+#else
+#define xchg64(_ptr, _new)						\
+({									\
+	__typeof__(_ptr) __ptr = (_ptr);				\
+	__typeof__(*(_ptr)) __old = *__ptr;				\
+	while (!try_cmpxchg64(__ptr, &__old, (_new)))			\
+		;							\
+	__old;								\
+})
+#endif
+#endif
+
 #endif /* !__I915_UTILS_H */
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 41/62] drm/i915: Fair low-latency scheduling

[Chris Wilson]

The first "scheduler" was a topographical sorting of requests into
priority order. The execution order was deterministic, the earliest
submitted, highest priority request would be executed first. Priority
inheritance ensured that inversions were kept at bay, and allowed us to
dynamically boost priorities (e.g. for interactive pageflips).

The minimalistic timeslicing scheme was an attempt to introduce fairness
between long running requests, by evicting the active request at the end
of a timeslice and moving it to the back of its priority queue (while
ensuring that dependencies were kept in order). For short running
requests from many clients of equal priority, the scheme is still very
much FIFO submission ordering, and as unfair as before.

To impose fairness, we need an external metric that ensures that clients
are interpersed, so we don't execute one long chain from client A before
executing any of client B. This could be imposed by the clients
themselves by using fences based on an external clock, that is they only
submit work for a "frame" at frame-intervals, instead of submitting as
much work as they are able to. The standard SwapBuffers approach is akin
to double bufferring, where as one frame is being executed, the next is
being submitted, such that there is always a maximum of two frames per
client in the pipeline and so ideally maintains consistent input-output
latency. Even this scheme exhibits unfairness under load as a single
client will execute two frames back to back before the next, and with
enough clients, deadlines will be missed.

The idea introduced by BFS/MuQSS is that fairness is introduced by
metering with an external clock. Every request, when it becomes ready to
execute is assigned a virtual deadline, and execution order is then
determined by earliest deadline. Priority is used as a hint, rather than
strict ordering, where high priority requests have earlier deadlines,
but not necessarily earlier than outstanding work. Thus work is executed
in order of 'readiness', with timeslicing to demote long running work.

The Achille's heel of this scheduler is its strong preference for
low-latency and favouring of new queues. Whereas it was easy to dominate
the old scheduler by flooding it with many requests over a short period
of time, the new scheduler can be dominated by a 'synchronous' client
that waits for each of its requests to complete before submitting the
next. As such a client has no history, it is always considered
ready-to-run and receives an earlier deadline than the long running
requests. This is compensated for by refreshing the current execution's
deadline and by disallowing preemption for timeslice shuffling.

To check the impact on throughput (often the downfall of latency
sensitive schedulers), we used gem_wsim to simulate various transcode
workloads with different load balancers, and varying the number of
competing [heterogenous] clients.

+delta%------------------------------------------------------------------+
|                                a                                       |
|                                a                                       |
|                                aa                                      |
|                                aa                                      |
|                                aa                                      |
|                                aa                                      |
|                               aaa                                      |
|                              aaaa                                      |
|                           a  aaaaa                                     |
|                           a aaaaaa                                     |
|a              aa   a      aaaaaaaaaa aa               a               a|
|                                A_|                                     |
+------------------------------------------------------------------------+
   N          Min           Max        Median           Avg        Stddev
 108   -23.982194     28.421527  -0.077474828  -0.072650418    0.16179718

The impact was on average 0.1% under contention due to the change in
context execution order and number of context switches. The biggest
swings are due to the execution ordering favouring one client or another,
and maybe room for improvement.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |   2 -
 .../gpu/drm/i915/gt/intel_engine_heartbeat.c  |   1 +
 drivers/gpu/drm/i915/gt/intel_engine_pm.c     |   4 +-
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |  14 -
 .../drm/i915/gt/intel_execlists_submission.c  | 205 +++++----
 drivers/gpu/drm/i915/gt/selftest_execlists.c  |  30 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c  |   5 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c        |   1 +
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c |   4 -
 drivers/gpu/drm/i915/i915_priolist_types.h    |   7 +-
 drivers/gpu/drm/i915/i915_request.c           |  14 +-
 drivers/gpu/drm/i915/i915_scheduler.c         | 415 +++++++++++++-----
 drivers/gpu/drm/i915/i915_scheduler.h         |  19 +-
 drivers/gpu/drm/i915/i915_scheduler_types.h   |  23 +
 drivers/gpu/drm/i915/selftests/i915_request.c |   1 +
 .../gpu/drm/i915/selftests/i915_scheduler.c   | 136 ++++++
 16 files changed, 624 insertions(+), 257 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 74aa0bf8c087..f88e367d5201 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -591,8 +591,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
 	memset(execlists->pending, 0, sizeof(execlists->pending));
 	execlists->active =
 		memset(execlists->inflight, 0, sizeof(execlists->inflight));
-
-	execlists->queue_priority_hint = INT_MIN;
 }
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index bccbb932a315..495e8d5e2bf4 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -205,6 +205,7 @@ static int __intel_engine_pulse(struct intel_engine_cs *engine)
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	rq->sched.deadline = 0;
 	__set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
 
 	heartbeat_commit(rq, &attr);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 14378e3a7a50..511a379c794d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -212,6 +212,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	i915_request_add_active_barriers(rq);
 
 	/* Install ourselves as a preemption barrier */
+	rq->sched.deadline = 0;
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 	if (likely(!__i915_request_commit(rq))) { /* engine should be idle! */
 		/*
@@ -272,9 +273,6 @@ static int __engine_park(struct intel_wakeref *wf)
 	intel_engine_park_heartbeat(engine);
 	intel_breadcrumbs_park(engine->breadcrumbs);
 
-	/* Must be reset upon idling, or we may miss the busy wakeup. */
-	GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
-
 	if (engine->park)
 		engine->park(engine);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 694d2e04ba6a..824a187b2803 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -224,20 +224,6 @@ struct intel_engine_execlists {
 	 */
 	unsigned int port_mask;
 
-	/**
-	 * @queue_priority_hint: Highest pending priority.
-	 *
-	 * When we add requests into the queue, or adjust the priority of
-	 * executing requests, we compute the maximum priority of those
-	 * pending requests. We can then use this value to determine if
-	 * we need to preempt the executing requests to service the queue.
-	 * However, since the we may have recorded the priority of an inflight
-	 * request we wanted to preempt but since completed, at the time of
-	 * dequeuing the priority hint may no longer may match the highest
-	 * available request priority.
-	 */
-	int queue_priority_hint;
-
 	struct rb_root_cached virtual;
 
 	/**
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index d99d682d8569..cdd6fce1c8bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -178,7 +178,7 @@ struct virtual_engine {
 	 */
 	struct ve_node {
 		struct rb_node rb;
-		int prio;
+		u64 deadline;
 	} nodes[I915_NUM_ENGINES];
 
 	/*
@@ -248,25 +248,12 @@ ring_set_paused(const struct intel_engine_cs *engine, int state)
 
 static inline int rq_prio(const struct i915_request *rq)
 {
-	return READ_ONCE(rq->sched.attr.priority);
+	return rq->sched.attr.priority;
 }
 
-static int effective_prio(const struct i915_request *rq)
+static inline u64 rq_deadline(const struct i915_request *rq)
 {
-	int prio = rq_prio(rq);
-
-	/*
-	 * If this request is special and must not be interrupted at any
-	 * cost, so be it. Note we are only checking the most recent request
-	 * in the context and so may be masking an earlier vip request. It
-	 * is hoped that under the conditions where nopreempt is used, this
-	 * will not matter (i.e. all requests to that context will be
-	 * nopreempt for as long as desired).
-	 */
-	if (i915_request_has_nopreempt(rq))
-		prio = I915_PRIORITY_UNPREEMPTABLE;
-
-	return prio;
+	return rq->sched.deadline;
 }
 
 static struct i915_request *first_request(struct i915_sched_engine *se)
@@ -285,61 +272,61 @@ static struct i915_request *first_request(struct i915_sched_engine *se)
 	return NULL;
 }
 
-static int queue_prio(struct i915_sched_engine *se)
+static struct i915_request *first_virtual(const struct intel_engine_cs *engine)
 {
-	struct i915_request *rq;
+	struct rb_node *rb;
 
-	rq = first_request(se);
-	if (!rq)
-		return INT_MIN;
+	rb = rb_first_cached(&engine->execlists.virtual);
+	if (!rb)
+		return NULL;
 
-	return rq_prio(rq);
+	return READ_ONCE(rb_entry(rb,
+				  struct virtual_engine,
+				  nodes[engine->id].rb)->request);
 }
 
-static int virtual_prio(const struct intel_engine_execlists *el)
+static const struct i915_request *
+next_elsp_request(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
-	struct rb_node *rb = rb_first_cached(&el->virtual);
+	if (list_is_last(&rq->sched.link, &engine->active.requests))
+		return NULL;
 
-	return rb ? rb_entry(rb, struct ve_node, rb)->prio : INT_MIN;
+	return list_next_entry(rq, sched.link);
+}
+
+static inline bool
+dl_before(const struct i915_request *next, const struct i915_request *prev)
+{
+	return !prev || (next && rq_deadline(next) < rq_deadline(prev));
 }
 
 static inline bool need_preempt(struct intel_engine_cs *engine,
 				const struct i915_request *rq)
 {
-	int last_prio;
+	const struct i915_request *first = NULL;
+	const struct i915_request *next;
 
 	if (!intel_engine_has_semaphores(engine))
 		return false;
 
 	/*
-	 * Check if the current priority hint merits a preemption attempt.
-	 *
-	 * We record the highest value priority we saw during rescheduling
-	 * prior to this dequeue, therefore we know that if it is strictly
-	 * less than the current tail of ESLP[0], we do not need to force
-	 * a preempt-to-idle cycle.
-	 *
-	 * However, the priority hint is a mere hint that we may need to
-	 * preempt. If that hint is stale or we may be trying to preempt
-	 * ourselves, ignore the request.
-	 *
-	 * More naturally we would write
-	 *      prio >= max(0, last);
-	 * except that we wish to prevent triggering preemption at the same
-	 * priority level: the task that is running should remain running
-	 * to preserve FIFO ordering of dependencies.
+	 * If this request is special and must not be interrupted at any
+	 * cost, so be it. Note we are only checking the most recent request
+	 * in the context and so may be masking an earlier vip request. It
+	 * is hoped that under the conditions where nopreempt is used, this
+	 * will not matter (i.e. all requests to that context will be
+	 * nopreempt for as long as desired).
 	 */
-	last_prio = max(effective_prio(rq), I915_PRIORITY_NORMAL - 1);
-	if (engine->execlists.queue_priority_hint <= last_prio)
+	if (i915_request_has_nopreempt(rq))
 		return false;
 
 	/*
 	 * Check against the first request in ELSP[1], it will, thanks to the
 	 * power of PI, be the highest priority of that context.
 	 */
-	if (!list_is_last(&rq->sched.link, &engine->active.requests) &&
-	    rq_prio(list_next_entry(rq, sched.link)) > last_prio)
-		return true;
+	next = next_elsp_request(engine, rq);
+	if (dl_before(next, first))
+		first = next;
 
 	/*
 	 * If the inflight context did not trigger the preemption, then maybe
@@ -351,8 +338,31 @@ static inline bool need_preempt(struct intel_engine_cs *engine,
 	 * ELSP[0] or ELSP[1] as, thanks again to PI, if it was the same
 	 * context, it's priority would not exceed ELSP[0] aka last_prio.
 	 */
-	return max(virtual_prio(&engine->execlists),
-		   queue_prio(&engine->active)) > last_prio;
+	next = first_request(&engine->active);
+	if (dl_before(next, first))
+		first = next;
+
+	next = first_virtual(engine);
+	if (dl_before(next, first))
+		first = next;
+
+	if (!dl_before(first, rq))
+		return false;
+
+	/*
+	 * While a request may have been queued that has an earlier deadline
+	 * than is currently running, we only allow it to perform an urgent
+	 * preemption if it also has higher priority. The cost of frequently
+	 * switching between contexts is noticeable, so we try to keep
+	 * the deadline shuffling only to timeslice boundaries.
+	 */
+	ENGINE_TRACE(engine,
+		     "preempt for first=%llx:%llu, dl=%llu, prio=%d?\n",
+		     first->fence.context,
+		     first->fence.seqno,
+		     rq_deadline(first),
+		     rq_prio(first));
+	return rq_prio(first) > max(rq_prio(rq), I915_PRIORITY_NORMAL - 1);
 }
 
 __maybe_unused static inline bool
@@ -369,7 +379,7 @@ assert_priority_queue(const struct i915_request *prev,
 	if (i915_request_is_active(prev))
 		return true;
 
-	return rq_prio(prev) >= rq_prio(next);
+	return rq_deadline(prev) <= rq_deadline(next);
 }
 
 static inline void
@@ -551,9 +561,12 @@ static inline void __execlists_schedule_out(struct i915_request *rq)
 	 * If we have just completed this context, the engine may now be
 	 * idle and we want to re-enter powersaving.
 	 */
-	if (list_is_last_rcu(&rq->link, &ce->timeline->requests) &&
-	    __i915_request_is_complete(rq))
-		intel_engine_add_retire(engine, ce->timeline);
+	if (__i915_request_is_complete(rq)) {
+		if (!list_is_last_rcu(&rq->link, &ce->timeline->requests))
+			i915_request_update_deadline(list_next_entry(rq, link));
+		else
+			intel_engine_add_retire(engine, ce->timeline);
+	}
 
 	ccid = ce->lrc.ccid;
 	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
@@ -667,14 +680,14 @@ dump_port(char *buf, int buflen, const char *prefix, struct i915_request *rq)
 	if (!rq)
 		return "";
 
-	snprintf(buf, buflen, "%sccid:%x %llx:%lld%s prio %d",
+	snprintf(buf, buflen, "%sccid:%x %llx:%lld%s dl:%llu",
 		 prefix,
 		 rq->context->lrc.ccid,
 		 rq->fence.context, rq->fence.seqno,
 		 __i915_request_is_complete(rq) ? "!" :
 		 __i915_request_has_started(rq) ? "*" :
 		 "",
-		 rq_prio(rq));
+		 rq_deadline(rq));
 
 	return buf;
 }
@@ -1175,11 +1188,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			goto check_secondary;
 		} else if (need_preempt(engine, last)) {
 			ENGINE_TRACE(engine,
-				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
+				     "preempting last=%llx:%llu, dl=%llu, prio=%d\n",
 				     last->fence.context,
 				     last->fence.seqno,
-				     last->sched.attr.priority,
-				     execlists->queue_priority_hint);
+				     rq_deadline(last),
+				     rq_prio(last));
 			record_preemption(execlists);
 
 			/*
@@ -1201,11 +1214,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			last = NULL;
 		} else if (timeslice_expired(engine, last)) {
 			ENGINE_TRACE(engine,
-				     "expired:%s last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
+				     "expired:%s last=%llx:%llu, deadline=%llu, now=%llu, yield?=%s\n",
 				     yesno(timer_expired(&execlists->timer)),
 				     last->fence.context, last->fence.seqno,
-				     rq_prio(last),
-				     execlists->queue_priority_hint,
+				     rq_deadline(last),
+				     i915_sched_to_ticks(ktime_get()),
 				     yesno(timeslice_yield(execlists, last)));
 
 			ring_set_paused(engine, 1);
@@ -1261,7 +1274,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(rq->engine != &ve->base);
 		GEM_BUG_ON(rq->context != &ve->context);
 
-		if (unlikely(rq_prio(rq) < queue_prio(&engine->active))) {
+		if (!dl_before(rq, first_request(&engine->active))) {
 			spin_unlock(&ve->base.active.lock);
 			break;
 		}
@@ -1275,16 +1288,15 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 
 		ENGINE_TRACE(engine,
-			     "virtual rq=%llx:%lld%s, new engine? %s\n",
+			     "virtual rq=%llx:%lld%s, dl %llx, new engine? %s\n",
 			     rq->fence.context,
 			     rq->fence.seqno,
 			     __i915_request_is_complete(rq) ? "!" :
 			     __i915_request_has_started(rq) ? "*" :
 			     "",
+			     rq_deadline(rq),
 			     yesno(engine != ve->siblings[0]));
-
 		WRITE_ONCE(ve->request, NULL);
-		WRITE_ONCE(ve->base.execlists.queue_priority_hint, INT_MIN);
 
 		rb = &ve->nodes[engine->id].rb;
 		rb_erase_cached(rb, &execlists->virtual);
@@ -1375,6 +1387,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				if (rq->execution_mask != engine->mask)
 					goto done;
 
+				if (unlikely(dl_before(first_virtual(engine),
+						       rq)))
+					goto done;
+
 				/*
 				 * If GVT overrides us we only ever submit
 				 * port[0], leaving port[1] empty. Note that we
@@ -1411,24 +1427,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	}
 done:
 	*port++ = i915_request_get(last);
-
-	/*
-	 * Here be a bit of magic! Or sleight-of-hand, whichever you prefer.
-	 *
-	 * We choose the priority hint such that if we add a request of greater
-	 * priority than this, we kick the submission tasklet to decide on
-	 * the right order of submitting the requests to hardware. We must
-	 * also be prepared to reorder requests as they are in-flight on the
-	 * HW. We derive the priority hint then as the first "hole" in
-	 * the HW submission ports and if there are no available slots,
-	 * the priority of the lowest executing request, i.e. last.
-	 *
-	 * When we do receive a higher priority request ready to run from the
-	 * user, see queue_request(), the priority hint is bumped to that
-	 * request triggering preemption on the next dequeue (or subsequent
-	 * interrupt for secondary ports).
-	 */
-	execlists->queue_priority_hint = queue_prio(&engine->active);
 	spin_unlock(&engine->active.lock);
 
 	/*
@@ -2621,10 +2619,6 @@ static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 
 static void nop_submission_tasklet(unsigned long data)
 {
-	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
-
-	/* The driver is wedged; don't process any more events. */
-	WRITE_ONCE(engine->execlists.queue_priority_hint, INT_MIN);
 }
 
 static void execlists_reset_cancel(struct intel_engine_cs *engine)
@@ -2691,16 +2685,12 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 			rq->engine = engine;
 			__i915_request_submit(rq);
 			i915_request_put(rq);
-
-			ve->base.execlists.queue_priority_hint = INT_MIN;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	execlists->queue_priority_hint = INT_MIN;
-
 	GEM_BUG_ON(__tasklet_is_enabled(&engine->active.tasklet));
 	engine->active.tasklet.func = nop_submission_tasklet;
 
@@ -3100,7 +3090,8 @@ static const struct intel_context_ops virtual_context_ops = {
 	.destroy = virtual_context_destroy,
 };
 
-static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
+static intel_engine_mask_t
+virtual_submission_mask(struct virtual_engine *ve, u64 *deadline)
 {
 	struct i915_request *rq;
 	intel_engine_mask_t mask;
@@ -3117,9 +3108,11 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 		mask = ve->siblings[0]->mask;
 	}
 
-	ENGINE_TRACE(&ve->base, "rq=%llx:%lld, mask=%x, prio=%d\n",
+	*deadline = rq_deadline(rq);
+
+	ENGINE_TRACE(&ve->base, "rq=%llx:%llu, mask=%x, dl=%llu\n",
 		     rq->fence.context, rq->fence.seqno,
-		     mask, ve->base.execlists.queue_priority_hint);
+		     mask, *deadline);
 
 	return mask;
 }
@@ -3127,12 +3120,12 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 static void virtual_submission_tasklet(unsigned long data)
 {
 	struct virtual_engine * const ve = (struct virtual_engine *)data;
-	const int prio = READ_ONCE(ve->base.execlists.queue_priority_hint);
 	intel_engine_mask_t mask;
+	u64 deadline;
 	unsigned int n;
 
 	rcu_read_lock();
-	mask = virtual_submission_mask(ve);
+	mask = virtual_submission_mask(ve, &deadline);
 	rcu_read_unlock();
 	if (unlikely(!mask))
 		return;
@@ -3165,7 +3158,8 @@ static void virtual_submission_tasklet(unsigned long data)
 			 */
 			first = rb_first_cached(&sibling->execlists.virtual) ==
 				&node->rb;
-			if (prio == node->prio || (prio > node->prio && first))
+			if (deadline == node->deadline ||
+			    (deadline < node->deadline && first))
 				goto submit_engine;
 
 			rb_erase_cached(&node->rb, &sibling->execlists.virtual);
@@ -3179,7 +3173,7 @@ static void virtual_submission_tasklet(unsigned long data)
 
 			rb = *parent;
 			other = rb_entry(rb, typeof(*other), rb);
-			if (prio > other->prio) {
+			if (deadline < other->deadline) {
 				parent = &rb->rb_left;
 			} else {
 				parent = &rb->rb_right;
@@ -3194,8 +3188,8 @@ static void virtual_submission_tasklet(unsigned long data)
 
 submit_engine:
 		GEM_BUG_ON(RB_EMPTY_NODE(&node->rb));
-		node->prio = prio;
-		if (first && prio > sibling->execlists.queue_priority_hint)
+		node->deadline = deadline;
+		if (first)
 			i915_sched_kick(&sibling->active);
 
 unlock_engine:
@@ -3231,7 +3225,9 @@ static void virtual_submit_request(struct i915_request *rq)
 		i915_request_put(ve->request);
 	}
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
+	rq->sched.deadline =
+		min(rq->sched.deadline,
+		    i915_scheduler_next_virtual_deadline(rq_prio(rq)));
 	ve->request = i915_request_get(rq);
 
 	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
@@ -3334,7 +3330,6 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	ve->base.bond_execute = virtual_bond_execute;
 
 	INIT_LIST_HEAD(virtual_queue(ve));
-	ve->base.execlists.queue_priority_hint = INT_MIN;
 	tasklet_init(&ve->base.active.tasklet,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
@@ -3518,10 +3513,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 		show_request(m, last, "\t\t", 0);
 	}
 
-	if (execlists->queue_priority_hint != INT_MIN)
-		drm_printf(m, "\t\tQueue priority hint: %d\n",
-			   READ_ONCE(execlists->queue_priority_hint));
-
 	last = NULL;
 	count = 0;
 	for_each_priolist(pl, &engine->active.queue) {
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index 291fb04807b9..bd170ebc7e49 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -868,7 +868,7 @@ semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 static int
 release_queue(struct intel_engine_cs *engine,
 	      struct i915_vma *vma,
-	      int idx, int prio)
+	      int idx, u64 deadline)
 {
 	struct i915_request *rq;
 	u32 *cs;
@@ -893,10 +893,7 @@ release_queue(struct intel_engine_cs *engine,
 	i915_request_get(rq);
 	i915_request_add(rq);
 
-	local_bh_disable();
-	i915_request_set_priority(rq, prio);
-	local_bh_enable(); /* kick tasklet */
-
+	i915_request_set_deadline(rq, deadline);
 	i915_request_put(rq);
 
 	return 0;
@@ -910,6 +907,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 	struct intel_engine_cs *engine;
 	struct i915_request *head;
 	enum intel_engine_id id;
+	long timeout;
 	int err, i, n = 0;
 
 	head = semaphore_queue(outer, vma, n++);
@@ -930,12 +928,16 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 		}
 	}
 
-	err = release_queue(outer, vma, n, I915_PRIORITY_BARRIER);
+	err = release_queue(outer, vma, n, 0);
 	if (err)
 		goto out;
 
-	if (i915_request_wait(head, 0,
-			      2 * outer->gt->info.num_engines * (count + 2) * (count + 3)) < 0) {
+	/* Expected number of pessimal slices required */
+	timeout = outer->gt->info.num_engines * (count + 2) * (count + 3);
+	timeout *= 4; /* safety factor, including bucketing */
+	timeout += HZ / 2; /* and include the request completion */
+
+	if (i915_request_wait(head, 0, timeout) < 0) {
 		pr_err("Failed to slice along semaphore chain of length (%d, %d)!\n",
 		       count, n);
 		GEM_TRACE_DUMP();
@@ -1040,6 +1042,8 @@ create_rewinder(struct intel_context *ce,
 		err = i915_request_await_dma_fence(rq, &wait->fence);
 		if (err)
 			goto err;
+
+		i915_request_set_deadline(rq, rq_deadline(wait));
 	}
 
 	cs = intel_ring_begin(rq, 14);
@@ -1316,6 +1320,7 @@ static int live_timeslice_queue(void *arg)
 			goto err_heartbeat;
 		}
 		i915_request_set_priority(rq, I915_PRIORITY_MAX);
+		i915_request_set_deadline(rq, 0);
 		err = wait_for_submit(engine, rq, HZ / 2);
 		if (err) {
 			pr_err("%s: Timed out trying to submit semaphores\n",
@@ -1338,10 +1343,9 @@ static int live_timeslice_queue(void *arg)
 		}
 
 		GEM_BUG_ON(i915_request_completed(rq));
-		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 		/* Queue: semaphore signal, matching priority as semaphore */
-		err = release_queue(engine, vma, 1, effective_prio(rq));
+		err = release_queue(engine, vma, 1, rq_deadline(rq));
 		if (err)
 			goto err_rq;
 
@@ -1452,6 +1456,7 @@ static int live_timeslice_nopreempt(void *arg)
 			goto out_spin;
 		}
 
+		rq->sched.deadline = 0;
 		rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 		i915_request_get(rq);
 		i915_request_add(rq);
@@ -1824,6 +1829,7 @@ static int live_late_preempt(void *arg)
 
 	/* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */
 	ctx_lo->sched.priority = 1;
+	ctx_hi->sched.priority = I915_PRIORITY_MIN;
 
 	for_each_engine(engine, gt, id) {
 		struct igt_live_test t;
@@ -2924,6 +2930,9 @@ static int live_preempt_gang(void *arg)
 		while (rq) { /* wait for each rq from highest to lowest prio */
 			struct i915_request *n = list_next_entry(rq, mock.link);
 
+			/* With deadlines, no strict priority ordering */
+			i915_request_set_deadline(rq, 0);
+
 			if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
 					drm_info_printer(engine->i915->drm.dev);
@@ -3146,6 +3155,7 @@ static int preempt_user(struct intel_engine_cs *engine,
 	i915_request_add(rq);
 
 	i915_request_set_priority(rq, I915_PRIORITY_MAX);
+	i915_request_set_deadline(rq, 0);
 
 	if (i915_request_wait(rq, 0, HZ / 2) < 0)
 		err = -ETIME;
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index cc0120411d62..3201dc334268 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -878,7 +878,10 @@ static int __igt_reset_engines(struct intel_gt *gt,
 					break;
 				}
 
-				if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+				/* With deadlines, no strict priority */
+				i915_request_set_deadline(rq, 0);
+
+				if (i915_request_wait(rq, 0, HZ / 2) < 0) {
 					struct drm_printer p =
 						drm_info_printer(gt->i915->drm.dev);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index e26f7f957468..88a61423385d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1171,6 +1171,7 @@ static int poison_registers(struct intel_context *ce, u32 poison, u32 *sema)
 
 	intel_ring_advance(rq, cs);
 
+	rq->sched.deadline = 0;
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 err_rq:
 	i915_request_add(rq);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 34be8dc8949e..1d4045ade19c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -327,8 +327,6 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 		i915_priolist_advance(&engine->active.queue, pl);
 	}
 done:
-	execlists->queue_priority_hint =
-		pl != &engine->active.queue.sentinel ? pl->priority : INT_MIN;
 	if (submit) {
 		*port = schedule_in(last, port - execlists->inflight);
 		*++port = NULL;
@@ -487,8 +485,6 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
-	execlists->queue_priority_hint = INT_MIN;
-
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 807cd8f65481..839c48f4b0e9 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -22,6 +22,8 @@ enum {
 
 	/* Interactive workload, scheduled for immediate pageflipping */
 	I915_PRIORITY_DISPLAY,
+
+	__I915_PRIORITY_KERNEL__
 };
 
 /* Smallest priority value that cannot be bumped. */
@@ -35,8 +37,7 @@ enum {
  * i.e. nothing can have higher priority and force us to usurp the
  * active request.
  */
-#define I915_PRIORITY_UNPREEMPTABLE INT_MAX
-#define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
+#define I915_PRIORITY_BARRIER INT_MAX
 
 #ifdef CONFIG_64BIT
 #define I915_PRIOLIST_HEIGHT 12
@@ -46,7 +47,7 @@ enum {
 
 struct i915_priolist {
 	struct list_head requests;
-	int priority;
+	u64 deadline;
 
 	int level;
 	struct i915_priolist *next[I915_PRIOLIST_HEIGHT];
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8408b7317ebc..c72a8710fe98 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -518,7 +518,7 @@ bool __i915_request_submit(struct i915_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	bool result = false;
 
-	RQ_TRACE(request, "\n");
+	RQ_TRACE(request, "dl %llu\n", request->sched.deadline);
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
@@ -711,6 +711,7 @@ semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
+		i915_request_update_deadline(rq);
 		break;
 
 	case FENCE_FREE:
@@ -1871,14 +1872,15 @@ long i915_request_wait(struct i915_request *rq,
 	return timeout;
 }
 
-static int print_sched_attr(const struct i915_sched_attr *attr,
-			    char *buf, int x, int len)
+static int print_sched(const struct i915_sched_node *node,
+		       char *buf, int x, int len)
 {
-	if (attr->priority == I915_PRIORITY_INVALID)
+	if (node->attr.priority == I915_PRIORITY_INVALID)
 		return x;
 
 	x += snprintf(buf + x, len - x,
-		      " prio=%d", attr->priority);
+		      " prio=%d, dl=%llu",
+		      node->attr.priority, node->deadline);
 
 	return x;
 }
@@ -1958,7 +1960,7 @@ void i915_request_show(struct drm_printer *m,
 	 *      from the lists
 	 */
 
-	x = print_sched_attr(&rq->sched.attr, buf, x, sizeof(buf));
+	x = print_sched(&rq->sched, buf, x, sizeof(buf));
 
 	drm_printf(m, "%s%.*s%c %llx:%lld%s%s %s @ %dms: %s\n",
 		   prefix, indent, "                ",
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index a0e8ecd06d8d..238656b37d86 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -33,6 +33,11 @@ static void node_put(struct i915_sched_node *node)
 	i915_request_put(container_of(node, struct i915_request, sched));
 }
 
+static inline u64 rq_deadline(const struct i915_request *rq)
+{
+	return READ_ONCE(rq->sched.deadline);
+}
+
 static inline int rq_prio(const struct i915_request *rq)
 {
 	return READ_ONCE(rq->sched.attr.priority);
@@ -46,6 +51,14 @@ static int ipi_get_prio(struct i915_request *rq)
 	return xchg(&rq->sched.ipi_priority, I915_PRIORITY_INVALID);
 }
 
+static u64 ipi_get_deadline(struct i915_request *rq)
+{
+	if (READ_ONCE(rq->sched.ipi_deadline) == I915_DEADLINE_NEVER)
+		return I915_DEADLINE_NEVER;
+
+	return xchg64(&rq->sched.ipi_deadline, I915_DEADLINE_NEVER);
+}
+
 static void ipi_schedule(struct work_struct *wrk)
 {
 	struct i915_sched_ipi *ipi = container_of(wrk, typeof(*ipi), work);
@@ -53,9 +66,11 @@ static void ipi_schedule(struct work_struct *wrk)
 
 	do {
 		struct i915_request *rn = xchg(&rq->sched.ipi_link, NULL);
+		u64 deadline;
 		int prio;
 
 		prio = ipi_get_prio(rq);
+		deadline = ipi_get_deadline(rq);
 
 		/*
 		 * For cross-engine scheduling to work we rely on one of two
@@ -80,6 +95,7 @@ static void ipi_schedule(struct work_struct *wrk)
 		 */
 		local_bh_disable();
 		i915_request_set_priority(rq, prio);
+		i915_request_set_deadline(rq, deadline);
 		local_bh_enable();
 
 		i915_request_put(rq);
@@ -98,7 +114,7 @@ static void init_priolist(struct i915_priolist_root *const root)
 	struct i915_priolist *pl = &root->sentinel;
 
 	memset_p((void **)pl->next, pl, ARRAY_SIZE(pl->next));
-	pl->priority = INT_MIN;
+	pl->deadline = I915_DEADLINE_NEVER;
 	INIT_LIST_HEAD(&pl->requests);
 	pl->level = 0;
 }
@@ -231,7 +247,7 @@ static inline unsigned int random_level(struct i915_priolist_root *root)
 }
 
 static struct list_head *
-lookup_priolist(struct intel_engine_cs *engine, int prio)
+lookup_priolist(struct intel_engine_cs *engine, u64 deadline)
 {
 	struct i915_priolist *update[I915_PRIOLIST_HEIGHT];
 	struct i915_sched_engine * const se = &engine->active;
@@ -239,12 +255,13 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 	struct i915_priolist *pl, *tmp;
 	int lvl;
 
+	GEM_BUG_ON(deadline == I915_DEADLINE_NEVER);
 	lockdep_assert_held(&se->lock);
 	if (unlikely(se->no_priolist))
-		prio = I915_PRIORITY_NORMAL;
+		deadline = 0;
 
 	for_each_priolist(pl, root) { /* recycle any empty elements before us */
-		if (pl->priority >= prio || !list_empty(&pl->requests))
+		if (pl->deadline >= deadline || !list_empty(&pl->requests))
 			break;
 
 		i915_priolist_advance(root, pl);
@@ -254,14 +271,14 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 	pl = &root->sentinel;
 	lvl = pl->level;
 	do {
-		while (tmp = pl->next[lvl], tmp->priority >= prio)
+		while (tmp = pl->next[lvl], tmp->deadline <= deadline)
 			pl = tmp;
-		if (pl->priority == prio)
+		if (pl->deadline == deadline)
 			goto out;
 		update[lvl] = pl;
 	} while (--lvl >= 0);
 
-	if (prio == I915_PRIORITY_NORMAL) {
+	if (!deadline) {
 		pl = &se->default_priolist;
 	} else if (!list_empty(&root->sentinel.requests)) {
 		pl = list_first_entry(&root->sentinel.requests,
@@ -272,7 +289,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 		pl = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
 		/* Convert an allocation failure to a priority bump */
 		if (unlikely(!pl)) {
-			prio = I915_PRIORITY_NORMAL; /* recurses just once */
+			deadline = 0; /* recurses just once */
 
 			/* To maintain ordering with all rendering, after an
 			 * allocation failure we have to disable all scheduling.
@@ -287,7 +304,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 		}
 	}
 
-	pl->priority = prio;
+	pl->deadline = deadline;
 	INIT_LIST_HEAD(&pl->requests);
 
 	lvl = random_level(root);
@@ -309,7 +326,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 		chk = &root->sentinel;
 		lvl = chk->level;
 		do {
-			while (tmp = chk->next[lvl], tmp->priority >= prio)
+			while (tmp = chk->next[lvl], tmp->deadline <= deadline)
 				chk = tmp;
 		} while (--lvl >= 0);
 
@@ -329,7 +346,7 @@ void i915_priolist_advance(struct i915_priolist_root *root,
 	GEM_BUG_ON(!list_empty(&pl->requests));
 	GEM_BUG_ON(pl == &root->sentinel);
 
-	if (pl->priority != I915_PRIORITY_NORMAL)
+	if (pl->deadline)
 		list_add(&pl->requests, &root->sentinel.requests);
 
 	for (lvl = 0; lvl <= pl->level; lvl++)
@@ -364,53 +381,236 @@ stack_pop(struct i915_request *rq,
 	return rq;
 }
 
-static inline bool need_preempt(int prio, int active)
+static void ipi_deadline(struct i915_request *rq, u64 deadline)
+{
+	u64 old = READ_ONCE(rq->sched.ipi_deadline);
+
+	do {
+		if (deadline >= old)
+			return;
+	} while (!try_cmpxchg64(&rq->sched.ipi_deadline, &old, deadline));
+
+	__ipi_add(rq);
+}
+
+static bool is_first_priolist(const struct intel_engine_cs *engine,
+			      const struct list_head *requests)
+{
+	return requests == &priolist_first(&engine->active.queue)->requests;
+}
+
+static bool __i915_request_set_deadline(struct i915_request *rq, u64 deadline)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	struct list_head *pos = &rq->sched.signalers_list;
+	struct list_head *plist;
+
+	/* Fifo and depth-first replacement ensure our deps execute first */
+	plist = lookup_priolist(engine, deadline);
+
+	rq->sched.dfs.next = NULL;
+	do {
+		list_for_each_continue(pos, &rq->sched.signalers_list) {
+			struct i915_dependency *p =
+				list_entry(pos, typeof(*p), signal_link);
+			struct i915_request *s =
+				container_of(p->signaler, typeof(*s), sched);
+
+			if (rq_deadline(s) <= deadline)
+				continue;
+
+			if (__i915_request_is_complete(s))
+				continue;
+
+			if (s->engine != engine) {
+				ipi_deadline(s, deadline);
+				continue;
+			}
+
+			/* Remember our position along this branch */
+			rq = stack_push(s, rq, pos);
+			pos = &rq->sched.signalers_list;
+		}
+
+		RQ_TRACE(rq, "set-deadline:%llu\n", deadline);
+		WRITE_ONCE(rq->sched.deadline, deadline);
+
+		/*
+		 * Once the request is ready, it will be placed into the
+		 * priority lists and then onto the HW runlist. Before the
+		 * request is ready, it does not contribute to our preemption
+		 * decisions and we can safely ignore it, as it will, and
+		 * any preemption required, be dealt with upon submission.
+		 * See engine->submit_request()
+		 */
+		GEM_BUG_ON(rq->engine != engine);
+		if (i915_request_in_priority_queue(rq))
+			list_move_tail(&rq->sched.link, plist);
+	} while ((rq = stack_pop(rq, &pos)));
+
+	return is_first_priolist(engine, plist);
+}
+
+void i915_request_set_deadline(struct i915_request *rq, u64 deadline)
+{
+	struct intel_engine_cs *engine;
+	unsigned long flags;
+
+	if (deadline >= rq_deadline(rq))
+		return;
+
+	engine = lock_engine_irqsave(rq, flags);
+	if (!intel_engine_has_scheduler(engine))
+		goto unlock;
+
+	if (i915_request_completed(rq))
+		goto unlock;
+
+	if (deadline >= rq_deadline(rq))
+		goto unlock;
+
+	rcu_read_lock();
+	if (__i915_request_set_deadline(rq, deadline))
+		i915_sched_kick(&engine->active);
+	rcu_read_unlock();
+	GEM_BUG_ON(rq_deadline(rq) != deadline);
+
+unlock:
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+}
+
+static u64 prio_slice(int prio)
 {
+	u64 slice;
+	int sf;
+
 	/*
-	 * Allow preemption of low -> normal -> high, but we do
-	 * not allow low priority tasks to preempt other low priority
-	 * tasks under the impression that latency for low priority
-	 * tasks does not matter (as much as background throughput),
-	 * so kiss.
+	 * This is the central heuristic to the virtual deadlines. By
+	 * imposing that each task takes an equal amount of time, we
+	 * let each client have an equal slice of the GPU time. By
+	 * bringing the virtual deadline forward, that client will then
+	 * have more GPU time, and vice versa a lower priority client will
+	 * have a later deadline and receive less GPU time.
+	 *
+	 * In BFS/MuQSS, the prio_ratios[] are based on the task nice range of
+	 * [-20, 20], with each lower priority having a ~10% longer deadline,
+	 * with the note that the proportion of CPU time between two clients
+	 * of different priority will be the square of the relative prio_slice.
+	 *
+	 * In contrast, this prio_slice() curve was chosen because it gave good
+	 * results with igt/gem_exec_schedule. It may not be the best choice!
+	 *
+	 * With a 1ms scheduling quantum:
+	 *
+	 *   MAX USER:  ~32us deadline
+	 *   0:         ~16ms deadline
+	 *   MIN_USER: 1000ms deadline
 	 */
-	return prio >= max(I915_PRIORITY_NORMAL, active);
+
+	if (prio >= __I915_PRIORITY_KERNEL__)
+		return INT_MAX - prio;
+
+	slice = __I915_PRIORITY_KERNEL__ - prio;
+	if (prio >= 0)
+		sf = 20 - 6;
+	else
+		sf = 20 - 1;
+
+	return slice << sf;
+}
+
+u64 i915_scheduler_virtual_deadline(u64 kt, int priority)
+{
+	return i915_sched_to_ticks(kt + prio_slice(priority));
+}
+
+u64 i915_scheduler_next_virtual_deadline(int priority)
+{
+	return i915_scheduler_virtual_deadline(ktime_get_mono_fast_ns(), priority);
 }
 
-static void kick_submission(struct intel_engine_cs *engine,
-			    const struct i915_request *rq,
-			    int prio)
+static u64 signal_deadline(const struct i915_request *rq)
 {
-	const struct i915_request *inflight;
+	u64 last = ktime_get_mono_fast_ns();
+	const struct i915_dependency *p;
 
 	/*
-	 * We only need to kick the tasklet once for the high priority
-	 * new context we add into the queue.
+	 * Find the earliest point at which we will become 'ready',
+	 * which we infer from the deadline of all active signalers.
+	 * We will position ourselves at the end of that chain of work.
 	 */
-	if (prio <= engine->execlists.queue_priority_hint)
-		return;
 
-	/* Nothing currently active? We're overdue for a submission! */
-	inflight = execlists_active(&engine->execlists);
-	if (!inflight)
-		return;
+	rcu_read_lock();
+	for_each_signaler(p, rq) {
+		const struct i915_request *s =
+			container_of(p->signaler, typeof(*s), sched);
+		u64 deadline;
+		int prio;
+
+		if (__i915_request_is_complete(s))
+			continue;
+
+		if (s->timeline == rq->timeline &&
+		    __i915_request_has_started(s))
+			continue;
+
+		prio = rq_prio(s);
+		if (prio < rq_prio(rq))
+			continue;
+
+		deadline = rq_deadline(s);
+		if (deadline == I915_DEADLINE_NEVER) /* retired & reused */
+			continue;
+
+		deadline = i915_sched_to_ns(deadline);
+		if (p->flags & I915_DEPENDENCY_WEAK)
+			deadline -= prio_slice(prio);
+
+		last = max(last, deadline);
+	}
+	rcu_read_unlock();
+
+	return last;
+}
+
+static int adj_prio(const struct i915_request *rq)
+{
+	int prio = rq_prio(rq);
 
 	/*
-	 * If we are already the currently executing context, don't
-	 * bother evaluating if we should preempt ourselves.
+	 * Deprioritize semaphore waiters. We only want to run these if there
+	 * is nothing ready to run first.
+	 *
+	 * Note by giving a more distant deadline (due to a lower priority)
+	 * we do not prevent them from having a slice of the GPU, and if there
+	 * is still contention at that point, we expect to immediately yield
+	 * on the semaphore.
+	 *
+	 * When all semaphores are signaled, we will update the request
+	 * to remove the semaphore penalty.
 	 */
-	if (inflight->context == rq->context)
-		return;
+	if (rq->sched.semaphores && !i915_sw_fence_signaled(&rq->semaphore))
+		prio -= 1024;
 
-	ENGINE_TRACE(engine,
-		     "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
-		     prio,
-		     rq->fence.context, rq->fence.seqno,
-		     inflight->fence.context, inflight->fence.seqno,
-		     inflight->sched.attr.priority);
+	return prio;
+}
 
-	engine->execlists.queue_priority_hint = prio;
-	if (need_preempt(prio, rq_prio(inflight)))
-		i915_sched_kick(&engine->active);
+static u64 earliest_deadline(const struct i915_request *rq)
+{
+	return i915_scheduler_virtual_deadline(signal_deadline(rq),
+					       adj_prio(rq));
+}
+
+static bool set_earliest_deadline(struct i915_request *rq, u64 old)
+{
+	u64 dl;
+
+	/* Recompute our deadlines and promote after a priority change */
+	dl = min(earliest_deadline(rq), rq_deadline(rq));
+	if (dl >= old)
+		return false;
+
+	return __i915_request_set_deadline(rq, dl);
 }
 
 static void ipi_priority(struct i915_request *rq, int prio)
@@ -425,13 +625,11 @@ static void ipi_priority(struct i915_request *rq, int prio)
 	__ipi_add(rq);
 }
 
-static void __i915_request_set_priority(struct i915_request *rq, int prio)
+static bool __i915_request_set_priority(struct i915_request *rq, int prio)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct list_head *pos = &rq->sched.signalers_list;
-	struct list_head *plist;
-
-	plist = lookup_priolist(engine, prio);
+	bool kick = false;
 
 	/*
 	 * Recursively bump all dependent priorities to match the new request.
@@ -453,6 +651,8 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 	 */
 	rq->sched.dfs.next = NULL;
 	do {
+		struct i915_request *next;
+
 		list_for_each_continue(pos, &rq->sched.signalers_list) {
 			struct i915_dependency *p =
 				list_entry(pos, typeof(*p), signal_link);
@@ -478,6 +678,8 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 		RQ_TRACE(rq, "set-priority:%d\n", prio);
 		WRITE_ONCE(rq->sched.attr.priority, prio);
 
+		next = stack_pop(rq, &pos);
+
 		/*
 		 * Once the request is ready, it will be placed into the
 		 * priority lists and then onto the HW runlist. Before the
@@ -486,16 +688,15 @@ static void __i915_request_set_priority(struct i915_request *rq, int prio)
 		 * any preemption required, be dealt with upon submission.
 		 * See engine->submit_request()
 		 */
-		if (!i915_request_is_ready(rq))
-			continue;
-
 		GEM_BUG_ON(rq->engine != engine);
-		if (i915_request_in_priority_queue(rq))
-			list_move_tail(&rq->sched.link, plist);
+		if (i915_request_is_ready(rq) &&
+		    set_earliest_deadline(rq, rq_deadline(rq)))
+			kick = true;
 
-		/* Defer (tasklet) submission until after all updates. */
-		kick_submission(engine, rq, prio);
-	} while ((rq = stack_pop(rq, &pos)));
+		rq = next;
+	} while (rq);
+
+	return kick;
 }
 
 void i915_request_set_priority(struct i915_request *rq, int prio)
@@ -548,7 +749,8 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 		goto unlock;
 
 	rcu_read_lock();
-	__i915_request_set_priority(rq, prio);
+	if (__i915_request_set_priority(rq, prio))
+		i915_sched_kick(&engine->active);
 	rcu_read_unlock();
 	GEM_BUG_ON(rq_prio(rq) != prio);
 
@@ -556,18 +758,27 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+bool __intel_engine_queue_request(struct intel_engine_cs *engine,
+				  struct i915_request *rq)
+{
+	lockdep_assert_held(&engine->active.lock);
+	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	return set_earliest_deadline(rq, I915_DEADLINE_NEVER);
+}
+
 void __intel_engine_defer_request(struct intel_engine_cs *engine,
 				  struct i915_request *rq)
 {
 	struct list_head *pos = &rq->sched.waiters_list;
 	struct i915_request *rn;
 	LIST_HEAD(dfs);
-	int prio;
+	u64 deadline;
 
 	lockdep_assert_held(&engine->active.lock);
 	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
 
-	prio = rq_prio(rq);
+	deadline = max(rq_deadline(rq),
+		       i915_scheduler_next_virtual_deadline(adj_prio(rq)));
 
 	/*
 	 * When we defer a request, we must maintain its order with respect
@@ -594,30 +805,32 @@ void __intel_engine_defer_request(struct intel_engine_cs *engine,
 				   __i915_request_has_started(w) &&
 				   !__i915_request_is_complete(rq));
 
+			/* An unready waiter imposes no deadline */
 			if (!i915_request_in_priority_queue(w))
 				continue;
 
 			/*
-			 * We also need to reorder within the same priority.
+			 * We also need to reorder within the same deadline.
 			 *
 			 * This is unlike priority-inheritance, where if the
 			 * signaler already has a higher priority [earlier
 			 * deadline] than us, we can ignore as it will be
 			 * scheduled first. If a waiter already has the
-			 * same priority, we still have to push it to the end
+			 * same deadline, we still have to push it to the end
 			 * of the list. This unfortunately means we cannot
 			 * use the rq_deadline() itself as a 'visited' bit.
 			 */
-			if (rq_prio(w) < prio)
+			if (rq_deadline(w) > deadline)
 				continue;
 
-			GEM_BUG_ON(rq_prio(w) != prio);
-
 			/* Remember our position along this branch */
 			rq = stack_push(w, rq, pos);
 			pos = &rq->sched.waiters_list;
 		}
 
+		RQ_TRACE(rq, "set-deadline:%llu\n", deadline);
+		WRITE_ONCE(rq->sched.deadline, deadline);
+
 		/* Note list is reversed for waiters wrt signal hierarchy */
 		GEM_BUG_ON(rq->engine != engine);
 		GEM_BUG_ON(!i915_request_in_priority_queue(rq));
@@ -627,33 +840,13 @@ void __intel_engine_defer_request(struct intel_engine_cs *engine,
 		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 	} while ((rq = stack_pop(rq, &pos)));
 
-	pos = lookup_priolist(engine, prio);
+	pos = lookup_priolist(engine, deadline);
 	list_for_each_entry_safe(rq, rn, &dfs, sched.link) {
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 		list_add_tail(&rq->sched.link, pos);
 	}
 }
 
-static void queue_request(struct intel_engine_cs *engine,
-			  struct i915_request *rq)
-{
-	GEM_BUG_ON(!list_empty(&rq->sched.link));
-	list_add_tail(&rq->sched.link, lookup_priolist(engine, rq_prio(rq)));
-	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-}
-
-static bool submit_queue(struct intel_engine_cs *engine,
-			 const struct i915_request *rq)
-{
-	struct intel_engine_execlists *execlists = &engine->execlists;
-
-	if (rq_prio(rq) <= execlists->queue_priority_hint)
-		return false;
-
-	execlists->queue_priority_hint = rq_prio(rq);
-	return true;
-}
-
 static bool hold_request(const struct i915_request *rq)
 {
 	struct i915_dependency *p;
@@ -691,6 +884,7 @@ void i915_request_enqueue(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct i915_sched_engine *se = &engine->active;
+	u64 dl = earliest_deadline(rq);
 	unsigned long flags;
 	bool kick = false;
 
@@ -703,11 +897,11 @@ void i915_request_enqueue(struct i915_request *rq)
 		list_add_tail(&rq->sched.link, &se->hold);
 		i915_request_set_hold(rq);
 	} else {
-		queue_request(engine, rq);
-
-		GEM_BUG_ON(i915_sched_is_idle(&engine->active));
-
-		kick = submit_queue(engine, rq);
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		kick = __i915_request_set_deadline(rq,
+						   min(dl, rq_deadline(rq)));
+		GEM_BUG_ON(rq_deadline(rq) == I915_DEADLINE_NEVER);
+		GEM_BUG_ON(i915_sched_is_idle(se));
 	}
 
 	GEM_BUG_ON(list_empty(&rq->sched.link));
@@ -720,8 +914,8 @@ struct i915_request *
 __intel_engine_rewind_requests(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq, *rn, *active = NULL;
+	u64 deadline = I915_DEADLINE_NEVER;
 	struct list_head *pl;
-	int prio = I915_PRIORITY_INVALID;
 
 	lockdep_assert_held(&engine->active.lock);
 
@@ -735,13 +929,20 @@ __intel_engine_rewind_requests(struct intel_engine_cs *engine)
 
 		__i915_request_unsubmit(rq);
 
-		GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
-		if (rq_prio(rq) != prio) {
-			prio = rq_prio(rq);
-			pl = lookup_priolist(engine, prio);
+		if (__i915_request_has_started(rq)) {
+			u64 deadline =
+				i915_scheduler_next_virtual_deadline(rq_prio(rq));
+			rq->sched.deadline = min(rq_deadline(rq), deadline);
+		}
+		GEM_BUG_ON(rq_deadline(rq) == I915_DEADLINE_NEVER);
+
+		if (rq_deadline(rq) != deadline) {
+			deadline = rq_deadline(rq);
+			pl = lookup_priolist(engine, deadline);
 		}
 		GEM_BUG_ON(i915_sched_is_idle(&engine->active));
 
+		GEM_BUG_ON(i915_request_in_priority_queue(rq));
 		list_move(&rq->sched.link, pl);
 		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
@@ -821,14 +1022,10 @@ void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 				   struct i915_request *rq)
 {
 	LIST_HEAD(list);
+	bool submit = false;
 
 	lockdep_assert_held(&engine->active.lock);
 
-	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
-		engine->execlists.queue_priority_hint = rq_prio(rq);
-		i915_sched_kick(&engine->active);
-	}
-
 	/*
 	 * Move this request back to the priority queue, and all of its
 	 * children and grandchildren that were suspended along with it.
@@ -842,9 +1039,7 @@ void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 		GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
 
 		i915_request_clear_hold(rq);
-		list_move_tail(&rq->sched.link,
-			       lookup_priolist(rq->engine, rq_prio(rq)));
-		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		submit |= __intel_engine_queue_request(rq->engine, rq);
 
 		/* Also release any children on this engine that are ready */
 		for_each_waiter(p, rq) {
@@ -874,6 +1069,18 @@ void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 
 		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
 	} while (rq);
+
+	if (submit)
+		i915_sched_kick(&engine->active);
+}
+
+void i915_request_update_deadline(struct i915_request *rq)
+{
+	if (!i915_request_in_priority_queue(rq))
+		return;
+
+	/* Recompute our deadlines and promote after a priority change */
+	i915_request_set_deadline(rq, earliest_deadline(rq));
 }
 
 void i915_sched_node_init(struct i915_sched_node *node)
@@ -892,10 +1099,12 @@ void i915_sched_node_init(struct i915_sched_node *node)
 void i915_sched_node_reinit(struct i915_sched_node *node)
 {
 	node->attr.priority = I915_PRIORITY_INVALID;
+	node->deadline = I915_DEADLINE_NEVER;
 	node->semaphores = 0;
 	node->flags = 0;
 
 	GEM_BUG_ON(node->ipi_link);
+	node->ipi_deadline = I915_DEADLINE_NEVER;
 	node->ipi_priority = I915_PRIORITY_INVALID;
 
 	GEM_BUG_ON(!list_empty(&node->signalers_list));
@@ -1022,7 +1231,7 @@ void i915_request_show_with_schedule(struct drm_printer *m,
 		if (signaler->timeline == rq->timeline)
 			continue;
 
-		if (i915_request_completed(signaler))
+		if (__i915_request_is_complete(signaler))
 			continue;
 
 		i915_request_show(m, signaler, prefix, indent + 2);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 4432aab230b6..a19c6970cc5c 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -36,9 +36,17 @@ void i915_sched_park_engine(struct i915_sched_engine *se);
 void i915_sched_fini_engine(struct i915_sched_engine *se);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
+void i915_request_set_deadline(struct i915_request *request, u64 deadline);
+
+void i915_request_update_deadline(struct i915_request *request);
+
+u64 i915_scheduler_virtual_deadline(u64 kt, int priority);
+u64 i915_scheduler_next_virtual_deadline(int priority);
 
 void i915_request_enqueue(struct i915_request *request);
 
+bool __intel_engine_queue_request(struct intel_engine_cs *engine,
+				  struct i915_request *request);
 struct i915_request *
 __intel_engine_rewind_requests(struct intel_engine_cs *engine);
 void __intel_engine_defer_request(struct intel_engine_cs *engine,
@@ -49,11 +57,14 @@ bool __intel_engine_hold_request(struct intel_engine_cs *engine,
 void __intel_engine_unhold_request(struct intel_engine_cs *engine,
 				   struct i915_request *request);
 
-void __i915_priolist_free(struct i915_priolist *p);
-static inline void i915_priolist_free(struct i915_priolist *p)
+static inline u64 i915_sched_to_ticks(ktime_t kt)
+{
+	return ktime_to_ns(kt) >> I915_SCHED_DEADLINE_SHIFT;
+}
+
+static inline u64 i915_sched_to_ns(u64 deadline)
 {
-	if (p->priority != I915_PRIORITY_NORMAL)
-		__i915_priolist_free(p);
+	return deadline << I915_SCHED_DEADLINE_SHIFT;
 }
 
 static inline bool i915_sched_is_idle(const struct i915_sched_engine *se)
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index c155e4faa30b..b8c484511185 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -72,7 +72,30 @@ struct i915_sched_node {
 #define I915_SCHED_HAS_EXTERNAL_CHAIN	BIT(0)
 	unsigned long semaphores;
 
+	/**
+	 * @deadline: [virtual] deadline
+	 *
+	 * When the request is ready for execution, it is given a quota
+	 * (the engine's timeslice) and a virtual deadline. The virtual
+	 * deadline is derived from the current time:
+	 *     ktime_get() + (prio_ratio * timeslice)
+	 *
+	 * Requests are then executed in order of deadline completion.
+	 * Requests with earlier deadlines than currently executing on
+	 * the engine will preempt the active requests.
+	 *
+	 * By treating it as a virtual deadline, we use it as a hint for
+	 * when it is appropriate for a request to start with respect to
+	 * all other requests in the system. It is not a hard deadline, as
+	 * we allow requests to miss them, and we do not account for the
+	 * request runtime.
+	 */
+	u64 deadline;
+#define I915_SCHED_DEADLINE_SHIFT 19 /* i.e. roughly 500us buckets */
+#define I915_DEADLINE_NEVER U64_MAX
+
 	struct i915_request *ipi_link;
+	u64 ipi_deadline;
 	int ipi_priority;
 };
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index d2a678a2497e..382f2d490959 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -2130,6 +2130,7 @@ static int measure_preemption(struct intel_context *ce)
 
 		intel_ring_advance(rq, cs);
 		rq->sched.attr.priority = I915_PRIORITY_BARRIER;
+		rq->sched.deadline = 0;
 
 		elapsed[i - 1] = ENGINE_READ_FW(ce->engine, RING_TIMESTAMP);
 		i915_request_add(rq);
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index 085a00998e95..80f9126aa9af 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -12,6 +12,40 @@
 #include "selftests/igt_spinner.h"
 #include "selftests/i915_random.h"
 
+static int mock_scheduler_slices(void *dummy)
+{
+	u64 min, max, normal, kernel;
+
+	min = prio_slice(I915_PRIORITY_MIN);
+	pr_info("%8s slice: %lluus\n", "min", min >> 10);
+
+	normal = prio_slice(0);
+	pr_info("%8s slice: %lluus\n", "normal", normal >> 10);
+
+	max = prio_slice(I915_PRIORITY_MAX);
+	pr_info("%8s slice: %lluus\n", "max", max >> 10);
+
+	kernel = prio_slice(I915_PRIORITY_BARRIER);
+	pr_info("%8s slice: %lluus\n", "kernel", kernel >> 10);
+
+	if (kernel != 0) {
+		pr_err("kernel prio slice should be 0\n");
+		return -EINVAL;
+	}
+
+	if (max >= normal) {
+		pr_err("maximum prio slice should be shorter than normal\n");
+		return -EINVAL;
+	}
+
+	if (min <= normal) {
+		pr_err("minimum prio slice should be longer than normal\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int mock_skiplist_levels(void *dummy)
 {
 	struct i915_priolist_root root = {};
@@ -43,6 +77,7 @@ static int mock_skiplist_levels(void *dummy)
 int i915_scheduler_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(mock_scheduler_slices),
 		SUBTEST(mock_skiplist_levels),
 	};
 
@@ -549,6 +584,53 @@ static int igt_priority_chains(void *arg)
 	return igt_schedule_chains(arg, igt_priority);
 }
 
+static bool igt_deadline(struct i915_request *rq,
+			 unsigned long v, unsigned long e)
+{
+	i915_request_set_deadline(rq, 0);
+	GEM_BUG_ON(rq_deadline(rq) != 0);
+	return true;
+}
+
+static int igt_deadline_chains(void *arg)
+{
+	return igt_schedule_chains(arg, igt_deadline);
+}
+
+static bool igt_defer(struct i915_request *rq, unsigned long v, unsigned long e)
+{
+	struct intel_engine_cs *engine = rq->engine;
+
+	/* XXX No generic means to unwind incomplete requests yet */
+	if (!i915_request_in_priority_queue(rq))
+		return false;
+
+	if (!intel_engine_has_preemption(engine))
+		return false;
+
+	spin_lock_irq(&engine->active.lock);
+
+	/* Push all the requests to the same deadline */
+	__i915_request_set_deadline(rq, 0);
+	GEM_BUG_ON(rq_deadline(rq) != 0);
+
+	/* Then the very first request must be the one everyone depends on */
+	rq = list_first_entry(lookup_priolist(engine, 0),
+			      typeof(*rq), sched.link);
+	GEM_BUG_ON(rq->engine != engine);
+
+	/* Deferring the first request will then have to defer all requests */
+	__intel_engine_defer_request(engine, rq);
+
+	spin_unlock_irq(&engine->active.lock);
+	return true;
+}
+
+static int igt_deadline_defer(void *arg)
+{
+	return igt_schedule_chains(arg, igt_defer);
+}
+
 static struct i915_request *
 __write_timestamp(struct intel_engine_cs *engine,
 		  struct drm_i915_gem_object *obj,
@@ -764,13 +846,22 @@ static int igt_priority_cycle(void *arg)
 	return __igt_schedule_cycle(arg, igt_priority);
 }
 
+static int igt_deadline_cycle(void *arg)
+{
+	return __igt_schedule_cycle(arg, igt_deadline);
+}
+
 int i915_scheduler_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_deadline_chains),
 		SUBTEST(igt_priority_chains),
 
 		SUBTEST(igt_schedule_cycle),
+		SUBTEST(igt_deadline_cycle),
 		SUBTEST(igt_priority_cycle),
+
+		SUBTEST(igt_deadline_defer),
 	};
 
 	return i915_subtests(tests, i915);
@@ -906,9 +997,54 @@ static int sparse_priority(void *arg)
 	return sparse(arg, set_priority);
 }
 
+static u64 __set_deadline(struct i915_request *rq, u64 deadline)
+{
+	u64 dt;
+
+	preempt_disable();
+	dt = ktime_get_raw_fast_ns();
+	i915_request_set_deadline(rq, deadline);
+	dt = ktime_get_raw_fast_ns() - dt;
+	preempt_enable();
+
+	return dt;
+}
+
+static bool set_deadline(struct i915_request *rq,
+			 unsigned long v, unsigned long e)
+{
+	report("set-deadline", v, e, __set_deadline(rq, 0));
+	return true;
+}
+
+static int single_deadline(void *arg)
+{
+	return single(arg, set_deadline);
+}
+
+static int wide_deadline(void *arg)
+{
+	return wide(arg, set_deadline);
+}
+
+static int inv_deadline(void *arg)
+{
+	return inv(arg, set_deadline);
+}
+
+static int sparse_deadline(void *arg)
+{
+	return sparse(arg, set_deadline);
+}
+
 int i915_scheduler_perf_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(single_deadline),
+		SUBTEST(wide_deadline),
+		SUBTEST(inv_deadline),
+		SUBTEST(sparse_deadline),
+
 		SUBTEST(single_priority),
 		SUBTEST(wide_priority),
 		SUBTEST(inv_priority),
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 42/62] drm/i915/gt: Specify a deadline for the heartbeat

[Chris Wilson]

As we know when we expect the heartbeat to be checked for completion,
pass this information along as its deadline. We still do not complain if
the deadline is missed, at least until we have tried a few times, but it
will allow for quicker hang detection on systems where deadlines are
adhered to.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 495e8d5e2bf4..0eb4a07b29b0 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -66,6 +66,16 @@ static void heartbeat_commit(struct i915_request *rq,
 	__i915_request_queue(rq, attr);
 }
 
+static void set_heartbeat_deadline(struct intel_engine_cs *engine,
+				   struct i915_request *rq)
+{
+	unsigned long interval;
+
+	interval = READ_ONCE(engine->props.heartbeat_interval_ms);
+	if (interval)
+		i915_request_set_deadline(rq, ktime_get() + (interval << 20));
+}
+
 static void show_heartbeat(const struct i915_request *rq,
 			   struct intel_engine_cs *engine)
 {
@@ -131,6 +141,8 @@ static void heartbeat(struct work_struct *wrk)
 
 			local_bh_disable();
 			i915_request_set_priority(rq, attr.priority);
+			if (attr.priority == I915_PRIORITY_BARRIER)
+				i915_request_set_deadline(rq, 0);
 			local_bh_enable();
 		} else {
 			if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
@@ -162,6 +174,7 @@ static void heartbeat(struct work_struct *wrk)
 	if (IS_ERR(rq))
 		goto unlock;
 
+	set_heartbeat_deadline(engine, rq);
 	heartbeat_commit(rq, &attr);
 
 unlock:
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 43/62] drm/i915: Extend the priority boosting for the display with a deadline

[Chris Wilson]

For a modeset/pageflip, there is a very precise deadline by which the
frame must be completed in order to hit the vblank and be shown. While
we don't pass along that exact information, we can at least inform the
scheduler that this request-chain needs to be completed asap.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c |  4 +++-
 drivers/gpu/drm/i915/gem/i915_gem_object.h   |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_wait.c     | 21 +++++++++++---------
 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index f25ab2b15ca1..22c902188c3d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15687,7 +15687,9 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 	if (ret)
 		return ret;
 
-	i915_gem_object_wait_priority(obj, 0, I915_PRIORITY_DISPLAY);
+	i915_gem_object_wait_priority(obj, 0,
+				      I915_PRIORITY_DISPLAY,
+				      ktime_get() /* next vblank? */);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB);
 
 	if (!new_plane_state->uapi.fence) { /* implicit fencing */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index b106bc81c303..88b849c6f49d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -517,7 +517,7 @@ int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 long timeout);
 int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 				  unsigned int flags,
-				  int prio);
+				  int prio, ktime_t deadline);
 
 void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
 					 enum fb_op_origin origin);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index 483139bd05c1..57fbd145d697 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -44,8 +44,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
 		unsigned int count, i;
 		int ret;
 
-		ret = dma_resv_get_fences_rcu(resv,
-							&excl, &count, &shared);
+		ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared);
 		if (ret)
 			return ret;
 
@@ -94,17 +93,20 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
 	return timeout;
 }
 
-static void __fence_set_priority(struct dma_fence *fence, int prio)
+static void
+__fence_set_prio(struct dma_fence *fence, int prio, ktime_t deadline)
 {
 	if (dma_fence_is_signaled(fence) || !dma_fence_is_i915(fence))
 		return;
 
 	local_bh_disable();
+	i915_request_set_deadline(to_request(fence),
+				  i915_sched_to_ticks(deadline));
 	i915_request_set_priority(to_request(fence), prio);
 	local_bh_enable(); /* kick the tasklets if queues were reprioritised */
 }
 
-static void fence_set_priority(struct dma_fence *fence, int prio)
+static void fence_set_prio(struct dma_fence *fence, int prio, ktime_t deadline)
 {
 	/* Recurse once into a fence-array */
 	if (dma_fence_is_array(fence)) {
@@ -112,16 +114,17 @@ static void fence_set_priority(struct dma_fence *fence, int prio)
 		int i;
 
 		for (i = 0; i < array->num_fences; i++)
-			__fence_set_priority(array->fences[i], prio);
+			__fence_set_prio(array->fences[i], prio, deadline);
 	} else {
-		__fence_set_priority(fence, prio);
+		__fence_set_prio(fence, prio, deadline);
 	}
 }
 
 int
 i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			      unsigned int flags,
-			      int prio)
+			      int prio,
+			      ktime_t deadline)
 {
 	struct dma_fence *excl;
 
@@ -136,7 +139,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 			return ret;
 
 		for (i = 0; i < count; i++) {
-			fence_set_priority(shared[i], prio);
+			fence_set_prio(shared[i], prio, deadline);
 			dma_fence_put(shared[i]);
 		}
 
@@ -146,7 +149,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 	}
 
 	if (excl) {
-		fence_set_priority(excl, prio);
+		fence_set_prio(excl, prio, deadline);
 		dma_fence_put(excl);
 	}
 	return 0;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 44/62] drm/i915/gt: Skip over completed active execlists, again

[Chris Wilson]

Now that we are careful to always force-restore contexts upon rewinding
(where necessary), we can restore our optimisation to skip over
completed active execlists when dequeuing.

Referenecs: 35f3fd8182ba ("drm/i915/execlists: Workaround switching back to a completed context")
References: 8ab3a3812aa9 ("drm/i915/gt: Incrementally check for rewinding")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 33 ++++++++++---------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index cdd6fce1c8bb..019be45b1eb4 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1129,12 +1129,20 @@ static void set_preempt_timeout(struct intel_engine_cs *engine,
 		     active_preempt_timeout(engine, rq));
 }
 
+static bool completed(const struct i915_request *rq)
+{
+	if (i915_request_has_sentinel(rq))
+		return false;
+
+	return __i915_request_is_complete(rq);
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
-	struct i915_request *last = *execlists->active;
+	struct i915_request *last, * const *active;
 	struct virtual_engine *ve;
 	struct i915_priolist *pl;
 	struct rb_node *rb;
@@ -1172,21 +1180,15 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * i.e. we will retrigger preemption following the ack in case
 	 * of trouble.
 	 *
-	 * In theory we can skip over completed contexts that have not
-	 * yet been processed by events (as those events are in flight):
-	 *
-	 * while ((last = *active) && i915_request_completed(last))
-	 *	active++;
-	 *
-	 * However, the GPU cannot handle this as it will ultimately
-	 * find itself trying to jump back into a context it has just
-	 * completed and barf.
 	 */
+	active = execlists->active;
+	while ((last = *active) && completed(last))
+		active++;
 
 	if (last) {
-		if (__i915_request_is_complete(last)) {
-			goto check_secondary;
-		} else if (need_preempt(engine, last)) {
+		GEM_BUG_ON(!i915_request_is_active(last));
+
+		if (need_preempt(engine, last)) {
 			ENGINE_TRACE(engine,
 				     "preempting last=%llx:%llu, dl=%llu, prio=%d\n",
 				     last->fence.context,
@@ -1248,7 +1250,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * we hopefully coalesce several updates into a single
 			 * submission.
 			 */
-check_secondary:
 			if (!list_is_last(&last->sched.link,
 					  &engine->active.requests)) {
 				/*
@@ -1435,7 +1436,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * of ordered contexts.
 	 */
 	if (submit &&
-	    memcmp(execlists->active,
+	    memcmp(active,
 		   execlists->pending,
 		   (port - execlists->pending) * sizeof(*port))) {
 		*port = NULL;
@@ -1443,7 +1444,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			execlists_schedule_in(*port, port - execlists->pending);
 
 		WRITE_ONCE(execlists->yield, -1);
-		set_preempt_timeout(engine, *execlists->active);
+		set_preempt_timeout(engine, *active);
 		execlists_submit_ports(engine);
 	} else {
 		ring_set_paused(engine, 0);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 45/62] drm/i915/gt: Support virtual engine queues

[Chris Wilson]

Allow multiple requests to be queued unto a virtual engine, whereas
before we only allowed a single request to be queued at a time. The
advantage of keeping just one request in the queue was to ensure that we
always decided late which engine to use. However, with the introduction
of the virtual deadline we throttle submission and still only drip one
request into the sibling at a time (unless it is truly empty, but then a
second request will have an earlier deadline than the queued virtual
engine and force itself in front). This also takes advantage that a
virtual engine will remain bound while it is active, i.e. we can not
switch to a second engine until the context is completed -- such that we
cannot be as lazy as lazy can be.

By allowing a full queue, we avoid having to synchronize via the
breadcrumb interrupt everytime, letting the virtual engine reach the
full throughput of the siblings.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 396 +++++++++---------
 drivers/gpu/drm/i915/i915_request.c           |   3 +-
 drivers/gpu/drm/i915/i915_scheduler.c         |  57 ++-
 drivers/gpu/drm/i915/i915_scheduler.h         |   2 +
 4 files changed, 256 insertions(+), 202 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 019be45b1eb4..b48ab6dab738 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -160,17 +160,6 @@ struct virtual_engine {
 	struct intel_context context;
 	struct rcu_work rcu;
 
-	/*
-	 * We allow only a single request through the virtual engine at a time
-	 * (each request in the timeline waits for the completion fence of
-	 * the previous before being submitted). By restricting ourselves to
-	 * only submitting a single request, each request is placed on to a
-	 * physical to maximise load spreading (by virtue of the late greedy
-	 * scheduling -- each real engine takes the next available request
-	 * upon idling).
-	 */
-	struct i915_request *request;
-
 	/*
 	 * We keep a rbtree of available virtual engines inside each physical
 	 * engine, sorted by priority. Here we preallocate the nodes we need
@@ -272,17 +261,27 @@ static struct i915_request *first_request(struct i915_sched_engine *se)
 	return NULL;
 }
 
-static struct i915_request *first_virtual(const struct intel_engine_cs *engine)
+static struct virtual_engine *
+first_virtual_engine(struct intel_engine_cs *engine)
 {
-	struct rb_node *rb;
+	return rb_entry_safe(rb_first_cached(&engine->execlists.virtual),
+			     struct virtual_engine,
+			     nodes[engine->id].rb);
+}
 
-	rb = rb_first_cached(&engine->execlists.virtual);
-	if (!rb)
-		return NULL;
+static const struct i915_request *first_virtual(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq = NULL;
+	struct virtual_engine *ve;
+
+	ve = first_virtual_engine(engine);
+	if (ve) {
+		spin_lock(&ve->base.active.lock);
+		rq = first_request(&ve->base.active);
+		spin_unlock(&ve->base.active.lock);
+	}
 
-	return READ_ONCE(rb_entry(rb,
-				  struct virtual_engine,
-				  nodes[engine->id].rb)->request);
+	return rq;
 }
 
 static const struct i915_request *
@@ -379,7 +378,15 @@ assert_priority_queue(const struct i915_request *prev,
 	if (i915_request_is_active(prev))
 		return true;
 
-	return rq_deadline(prev) <= rq_deadline(next);
+	if (rq_deadline(prev) <= rq_deadline(next))
+		return true;
+
+	ENGINE_TRACE(prev->engine,
+		     "next %llx:%lld dl %lld is before prev %llx:%lld dl %lld\n",
+		     next->fence.context, next->fence.seqno, rq_deadline(next),
+		     prev->fence.context, prev->fence.seqno, rq_deadline(prev));
+
+	return false;
 }
 
 static inline void
@@ -485,7 +492,7 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 	trace_i915_request_in(rq, idx);
 
 	old = ce->inflight;
-	if (!old)
+	if (!__intel_context_inflight_count(old))
 		old = __execlists_schedule_in(rq);
 	WRITE_ONCE(ce->inflight, ptr_inc(old));
 
@@ -493,9 +500,11 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx)
 }
 
 static void
-resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
+__resubmit_virtual_request(struct i915_request *rq,
+			   struct intel_engine_cs *engine,
+			   struct virtual_engine *ve)
 {
-	struct intel_engine_cs *engine = rq->engine;
+	GEM_BUG_ON(rq->engine != engine);
 
 	/* Flush concurrent rcu iterators in signal_irq_work */
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) {
@@ -512,12 +521,42 @@ resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
 			cpu_relax();
 	}
 
+	__i915_request_requeue(rq, &ve->base);
+}
+
+static void
+resubmit_virtual_request(struct i915_request *rq, struct virtual_engine *ve)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	struct i915_request *pos = rq;
+	struct intel_timeline *tl;
+
 	spin_lock_irq(&engine->active.lock);
 
-	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
-	WRITE_ONCE(rq->engine, &ve->base);
-	ve->base.submit_request(rq);
+	if (__i915_request_is_complete(rq))
+		goto unlock;
+
+	tl = i915_request_active_timeline(rq);
+
+	/* Rewind back to the start of this virtual engine queue */
+	list_for_each_entry_continue_reverse(rq, &tl->requests, link) {
+		if (__i915_request_is_complete(rq))
+			break;
 
+		pos = rq;
+	}
+
+	/* Resubmit the queue in execution order */
+	spin_lock(&ve->base.active.lock);
+	list_for_each_entry_from(pos, &tl->requests, link) {
+		if (pos->engine != engine)
+			break;
+
+		__resubmit_virtual_request(pos, engine, ve);
+	}
+	spin_unlock(&ve->base.active.lock);
+
+unlock:
 	spin_unlock_irq(&engine->active.lock);
 }
 
@@ -536,7 +575,7 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 	    rq->execution_mask != engine->mask)
 		resubmit_virtual_request(rq, ve);
 
-	if (READ_ONCE(ve->request))
+	if (!i915_sched_is_idle(&ve->base.active))
 		i915_sched_kick(&ve->base.active);
 }
 
@@ -883,10 +922,16 @@ static bool ctx_single_port_submission(const struct intel_context *ce)
 		intel_context_force_single_submission(ce));
 }
 
+static bool __can_merge_ctx(const struct intel_context *prev,
+			    const struct intel_context *next)
+{
+	return prev == next;
+}
+
 static bool can_merge_ctx(const struct intel_context *prev,
 			  const struct intel_context *next)
 {
-	if (prev != next)
+	if (!__can_merge_ctx(prev, next))
 		return false;
 
 	if (ctx_single_port_submission(prev))
@@ -935,6 +980,9 @@ static bool virtual_matches(const struct virtual_engine *ve,
 {
 	const struct intel_engine_cs *inflight;
 
+	if (!rq)
+		return false;
+
 	if (!(rq->execution_mask & engine->mask)) /* We peeked too soon! */
 		return false;
 
@@ -954,31 +1002,6 @@ static bool virtual_matches(const struct virtual_engine *ve,
 	return true;
 }
 
-static struct virtual_engine *
-first_virtual_engine(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists *el = &engine->execlists;
-	struct rb_node *rb = rb_first_cached(&el->virtual);
-
-	while (rb) {
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		struct i915_request *rq = READ_ONCE(ve->request);
-
-		/* lazily cleanup after another engine handled rq */
-		if (!rq || !virtual_matches(ve, rq, engine)) {
-			rb_erase_cached(rb, &el->virtual);
-			RB_CLEAR_NODE(rb);
-			rb = rb_first_cached(&el->virtual);
-			continue;
-		}
-
-		return ve;
-	}
-
-	return NULL;
-}
-
 static void virtual_xfer_context(struct virtual_engine *ve,
 				 struct intel_engine_cs *engine)
 {
@@ -1137,15 +1160,124 @@ static bool completed(const struct i915_request *rq)
 	return __i915_request_is_complete(rq);
 }
 
+static void __virtual_dequeue(struct virtual_engine *ve,
+			      struct intel_engine_cs *sibling)
+{
+	struct ve_node * const node = &ve->nodes[sibling->id];
+	struct rb_node **parent, *rb;
+	struct i915_request *rq;
+	u64 deadline;
+	bool first;
+
+	rb_erase_cached(&node->rb, &sibling->execlists.virtual);
+	RB_CLEAR_NODE(&node->rb);
+
+	rq = first_request(&ve->base.active);
+	if (!virtual_matches(ve, rq, sibling))
+		return;
+
+	rb = NULL;
+	first = true;
+	parent = &sibling->execlists.virtual.rb_root.rb_node;
+	deadline = rq_deadline(rq);
+	while (*parent) {
+		struct ve_node *other;
+
+		rb = *parent;
+		other = rb_entry(rb, typeof(*other), rb);
+		if (deadline <= other->deadline) {
+			parent = &rb->rb_left;
+		} else {
+			parent = &rb->rb_right;
+			first = false;
+		}
+	}
+
+	rb_link_node(&node->rb, rb, parent);
+	rb_insert_color_cached(&node->rb, &sibling->execlists.virtual, first);
+}
+
+static void virtual_requeue(struct intel_engine_cs *engine,
+			    struct i915_request *last)
+{
+	const struct i915_request * const first =
+		first_request(&engine->active);
+	struct virtual_engine *ve;
+
+	while ((ve = first_virtual_engine(engine))) {
+		struct i915_request *rq;
+
+		spin_lock(&ve->base.active.lock);
+
+		rq = first_request(&ve->base.active);
+		if (unlikely(!virtual_matches(ve, rq, engine)))
+			/* lost the race to a sibling */
+			goto unlock;
+
+		GEM_BUG_ON(rq->engine != &ve->base);
+		GEM_BUG_ON(rq->context != &ve->context);
+
+		if (!dl_before(rq, first)) {
+			spin_unlock(&ve->base.active.lock);
+			break;
+		}
+
+		if (last && !__can_merge_ctx(last->context, rq->context)) {
+			spin_unlock(&ve->base.active.lock);
+			break; /* leave this for another sibling? */
+		}
+
+		ENGINE_TRACE(engine,
+			     "virtual rq=%llx:%lld%s, dl %llx, new engine? %s\n",
+			     rq->fence.context,
+			     rq->fence.seqno,
+			     __i915_request_is_complete(rq) ? "!" :
+			     __i915_request_has_started(rq) ? "*" :
+			     "",
+			     rq_deadline(rq),
+			     yesno(engine != ve->siblings[0]));
+
+		GEM_BUG_ON(!(rq->execution_mask & engine->mask));
+		if (__i915_request_requeue(rq, engine)) {
+			/*
+			 * Only after we confirm that we will submit
+			 * this request (i.e. it has not already
+			 * completed), do we want to update the context.
+			 *
+			 * This serves two purposes. It avoids
+			 * unnecessary work if we are resubmitting an
+			 * already completed request after timeslicing.
+			 * But more importantly, it prevents us altering
+			 * ve->siblings[] on an idle context, where
+			 * we may be using ve->siblings[] in
+			 * virtual_context_enter / virtual_context_exit.
+			 */
+			virtual_xfer_context(ve, engine);
+
+			/* Bind this ve before we release the lock */
+			if (!ve->context.inflight)
+				WRITE_ONCE(ve->context.inflight, engine);
+
+			GEM_BUG_ON(rq->engine != engine);
+			GEM_BUG_ON(ve->siblings[0] != engine);
+			GEM_BUG_ON(intel_context_inflight(rq->context) != engine);
+
+			last = rq;
+		}
+
+unlock:
+		__virtual_dequeue(ve, engine);
+		spin_unlock(&ve->base.active.lock);
+	}
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
 	struct i915_request *last, * const *active;
-	struct virtual_engine *ve;
 	struct i915_priolist *pl;
-	struct rb_node *rb;
 	bool submit = false;
 
 	/*
@@ -1262,85 +1394,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 	}
 
-	/* XXX virtual is always taking precedence */
-	while ((ve = first_virtual_engine(engine))) {
-		struct i915_request *rq;
-
-		spin_lock(&ve->base.active.lock);
-
-		rq = ve->request;
-		if (unlikely(!rq)) /* lost the race to a sibling */
-			goto unlock;
-
-		GEM_BUG_ON(rq->engine != &ve->base);
-		GEM_BUG_ON(rq->context != &ve->context);
-
-		if (!dl_before(rq, first_request(&engine->active))) {
-			spin_unlock(&ve->base.active.lock);
-			break;
-		}
-
-		GEM_BUG_ON(!virtual_matches(ve, rq, engine));
-
-		if (last && !can_merge_rq(last, rq)) {
-			spin_unlock(&ve->base.active.lock);
-			spin_unlock(&engine->active.lock);
-			return; /* leave this for another sibling */
-		}
-
-		ENGINE_TRACE(engine,
-			     "virtual rq=%llx:%lld%s, dl %llx, new engine? %s\n",
-			     rq->fence.context,
-			     rq->fence.seqno,
-			     __i915_request_is_complete(rq) ? "!" :
-			     __i915_request_has_started(rq) ? "*" :
-			     "",
-			     rq_deadline(rq),
-			     yesno(engine != ve->siblings[0]));
-		WRITE_ONCE(ve->request, NULL);
-
-		rb = &ve->nodes[engine->id].rb;
-		rb_erase_cached(rb, &execlists->virtual);
-		RB_CLEAR_NODE(rb);
-
-		GEM_BUG_ON(!(rq->execution_mask & engine->mask));
-		WRITE_ONCE(rq->engine, engine);
-
-		if (__i915_request_submit(rq)) {
-			/*
-			 * Only after we confirm that we will submit
-			 * this request (i.e. it has not already
-			 * completed), do we want to update the context.
-			 *
-			 * This serves two purposes. It avoids
-			 * unnecessary work if we are resubmitting an
-			 * already completed request after timeslicing.
-			 * But more importantly, it prevents us altering
-			 * ve->siblings[] on an idle context, where
-			 * we may be using ve->siblings[] in
-			 * virtual_context_enter / virtual_context_exit.
-			 */
-			virtual_xfer_context(ve, engine);
-			GEM_BUG_ON(ve->siblings[0] != engine);
-
-			submit = true;
-			last = rq;
-		}
-
-		i915_request_put(rq);
-unlock:
-		spin_unlock(&ve->base.active.lock);
-
-		/*
-		 * Hmm, we have a bunch of virtual engine requests,
-		 * but the first one was already completed (thanks
-		 * preempt-to-busy!). Keep looking at the veng queue
-		 * until we have no more relevant requests (i.e.
-		 * the normal submit queue has higher priority).
-		 */
-		if (submit)
-			break;
-	}
+	virtual_requeue(engine, last);
 
 	for_each_priolist(pl, &engine->active.queue) {
 		struct i915_request *rq, *rn;
@@ -1348,6 +1402,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		priolist_for_each_request_safe(rq, rn, pl) {
 			bool merge = true;
 
+			GEM_BUG_ON(rq->engine != engine);
+
 			/*
 			 * Can we combine this request with the current port?
 			 * It has to be the same context/ringbuffer and not
@@ -2679,13 +2735,11 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		rq = fetch_and_zero(&ve->request);
-		if (rq) {
+		while ((rq = first_request(&ve->base.active))) {
 			mark_eio(rq);
 
 			rq->engine = engine;
 			__i915_request_submit(rq);
-			i915_request_put(rq);
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
@@ -2919,11 +2973,6 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static struct list_head *virtual_queue(struct virtual_engine *ve)
-{
-	return &ve->base.active.default_priolist.requests;
-}
-
 static void rcu_virtual_context_destroy(struct work_struct *wrk)
 {
 	struct virtual_engine *ve =
@@ -2933,17 +2982,13 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 	GEM_BUG_ON(ve->context.inflight);
 
 	/* Preempt-to-busy may leave a stale request behind. */
-	if (unlikely(ve->request)) {
+	if (unlikely(!i915_sched_is_idle(&ve->base.active))) {
 		struct i915_request *old;
 
 		spin_lock_irq(&ve->base.active.lock);
 
-		old = fetch_and_zero(&ve->request);
-		if (old) {
-			GEM_BUG_ON(!i915_request_completed(old));
+		while ((old = first_request(&ve->base.active)))
 			__i915_request_submit(old);
-			i915_request_put(old);
-		}
 
 		spin_unlock_irq(&ve->base.active.lock);
 	}
@@ -2974,7 +3019,6 @@ static void rcu_virtual_context_destroy(struct work_struct *wrk)
 		spin_unlock_irq(&sibling->active.lock);
 	}
 	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.active.tasklet));
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
 
 	lrc_fini(&ve->context);
 	intel_context_fini(&ve->context);
@@ -3097,7 +3141,9 @@ virtual_submission_mask(struct virtual_engine *ve, u64 *deadline)
 	struct i915_request *rq;
 	intel_engine_mask_t mask;
 
-	rq = READ_ONCE(ve->request);
+	spin_lock_irq(&ve->base.active.lock);
+	rq = first_request(&ve->base.active);
+	spin_unlock_irq(&ve->base.active.lock);
 	if (!rq)
 		return 0;
 
@@ -3137,9 +3183,6 @@ static void virtual_submission_tasklet(unsigned long data)
 		struct rb_node **parent, *rb;
 		bool first;
 
-		if (!READ_ONCE(ve->request))
-			break; /* already handled by a sibling's tasklet */
-
 		spin_lock_irq(&sibling->active.lock);
 
 		if (unlikely(!(mask & sibling->mask))) {
@@ -3201,45 +3244,6 @@ static void virtual_submission_tasklet(unsigned long data)
 	}
 }
 
-static void virtual_submit_request(struct i915_request *rq)
-{
-	struct virtual_engine *ve = to_virtual_engine(rq->engine);
-	unsigned long flags;
-
-	ENGINE_TRACE(&ve->base, "rq=%llx:%lld\n",
-		     rq->fence.context,
-		     rq->fence.seqno);
-
-	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
-
-	spin_lock_irqsave(&ve->base.active.lock, flags);
-
-	/* By the time we resubmit a request, it may be completed */
-	if (__i915_request_is_complete(rq)) {
-		__i915_request_submit(rq);
-		goto unlock;
-	}
-
-	if (ve->request) { /* background completion from preempt-to-busy */
-		GEM_BUG_ON(!i915_request_completed(ve->request));
-		__i915_request_submit(ve->request);
-		i915_request_put(ve->request);
-	}
-
-	rq->sched.deadline =
-		min(rq->sched.deadline,
-		    i915_scheduler_next_virtual_deadline(rq_prio(rq)));
-	ve->request = i915_request_get(rq);
-
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
-
-	i915_sched_kick(&ve->base.active);
-
-unlock:
-	spin_unlock_irqrestore(&ve->base.active.lock, flags);
-}
-
 static struct ve_bond *
 virtual_find_bond(struct virtual_engine *ve,
 		  const struct intel_engine_cs *master)
@@ -3327,10 +3331,9 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
 
-	ve->base.submit_request = virtual_submit_request;
+	ve->base.submit_request = i915_request_enqueue;
 	ve->base.bond_execute = virtual_bond_execute;
 
-	INIT_LIST_HEAD(virtual_queue(ve));
 	tasklet_init(&ve->base.active.tasklet,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
@@ -3538,14 +3541,17 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 	for (rb = rb_first_cached(&execlists->virtual); rb; rb = rb_next(rb)) {
 		struct virtual_engine *ve =
 			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		struct i915_request *rq = READ_ONCE(ve->request);
+		struct i915_request *rq;
 
+		spin_lock(&ve->base.active.lock);
+		rq = first_request(&ve->base.active);
 		if (rq) {
 			if (count++ < max - 1)
 				show_request(m, rq, "\t\t", 0);
 			else
 				last = rq;
 		}
+		spin_unlock(&ve->base.active.lock);
 	}
 	if (last) {
 		if (count > max) {
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index c72a8710fe98..e636c68d4776 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1346,6 +1346,7 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 
 	GEM_BUG_ON(to == from);
 	GEM_BUG_ON(to->timeline == from->timeline);
+	GEM_BUG_ON(to->context == from->context);
 
 	if (i915_request_completed(from)) {
 		i915_sw_fence_set_error_once(&to->submit, from->fence.error);
@@ -1531,7 +1532,7 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 			   i915_seqno_passed(prev->fence.seqno,
 					     rq->fence.seqno));
 
-		if (is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask))
+		if (prev->context == rq->context)
 			i915_sw_fence_await_sw_fence(&rq->submit,
 						     &prev->submit,
 						     &rq->submitq);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 238656b37d86..b1e9fb4cec26 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -766,20 +766,17 @@ bool __intel_engine_queue_request(struct intel_engine_cs *engine,
 	return set_earliest_deadline(rq, I915_DEADLINE_NEVER);
 }
 
-void __intel_engine_defer_request(struct intel_engine_cs *engine,
-				  struct i915_request *rq)
+static void __defer_request(struct intel_engine_cs *engine,
+			    struct i915_request *rq,
+			    u64 deadline)
 {
 	struct list_head *pos = &rq->sched.waiters_list;
 	struct i915_request *rn;
 	LIST_HEAD(dfs);
-	u64 deadline;
 
 	lockdep_assert_held(&engine->active.lock);
 	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
 
-	deadline = max(rq_deadline(rq),
-		       i915_scheduler_next_virtual_deadline(adj_prio(rq)));
-
 	/*
 	 * When we defer a request, we must maintain its order with respect
 	 * to those that are waiting upon it. So we traverse its chain of
@@ -847,6 +844,14 @@ void __intel_engine_defer_request(struct intel_engine_cs *engine,
 	}
 }
 
+void __intel_engine_defer_request(struct intel_engine_cs *engine,
+				  struct i915_request *rq)
+{
+	__defer_request(engine, rq,
+			max(rq_deadline(rq),
+			    i915_scheduler_next_virtual_deadline(adj_prio(rq))));
+}
+
 static bool hold_request(const struct i915_request *rq)
 {
 	struct i915_dependency *p;
@@ -880,6 +885,46 @@ static bool ancestor_on_hold(const struct intel_engine_cs *engine,
 	return unlikely(!list_empty(&engine->active.hold)) && hold_request(rq);
 }
 
+bool __i915_request_requeue(struct i915_request *rq,
+			    struct intel_engine_cs *engine)
+{
+	RQ_TRACE(rq, "transfer from %s to %s\n",
+		 rq->engine->name, engine->name);
+
+	lockdep_assert_held(&engine->active.lock);
+	lockdep_assert_held(&rq->engine->active.lock);
+	GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags));
+	GEM_BUG_ON(rq->engine == engine);
+
+	list_del_init(&rq->sched.link);
+	WRITE_ONCE(rq->engine, engine);
+
+	if (__i915_request_is_complete(rq)) {
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
+		return false;
+	}
+
+	if (unlikely(ancestor_on_hold(engine, rq))) {
+		RQ_TRACE(rq, "ancestor on hold\n");
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		list_add_tail(&rq->sched.link, &engine->active.hold);
+		i915_request_set_hold(rq);
+	} else {
+		u64 deadline = min(earliest_deadline(rq), rq_deadline(rq));
+
+		/* Maintain request ordering wrt to existing on target */
+		__i915_request_set_deadline(rq, deadline);
+		if (!list_empty(&rq->sched.waiters_list))
+			__defer_request(engine, rq, deadline);
+
+		GEM_BUG_ON(rq_deadline(rq) == I915_DEADLINE_NEVER);
+	}
+
+	GEM_BUG_ON(list_empty(&rq->sched.link));
+	return true;
+}
+
 void i915_request_enqueue(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index a19c6970cc5c..5df3cf385bd1 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -44,6 +44,8 @@ u64 i915_scheduler_virtual_deadline(u64 kt, int priority);
 u64 i915_scheduler_next_virtual_deadline(int priority);
 
 void i915_request_enqueue(struct i915_request *request);
+bool __i915_request_requeue(struct i915_request *rq,
+			    struct intel_engine_cs *engine);
 
 bool __intel_engine_queue_request(struct intel_engine_cs *engine,
 				  struct i915_request *request);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 46/62] drm/i915: Move saturated workload detection back to the context

[Chris Wilson]

When we introduced the saturated workload detection to tell us to back
off from semaphore usage [semaphores have a noticeable impact on
contended bus cycles with the CPU for some heavy workloads], we first
introduced it as a per-context tracker. This allows individual contexts
to try and optimise their own usage, but we found that with the local
tracking and the no-semaphore boosting, the first context to disable
semaphores got a massive priority boost and so would starve the rest and
all new contexts (as they started with semaphores enabled and lower
priority). Hence we moved the saturated workload detection to the
engine, and a consequence had to disable semaphores on virtual engines.

Now that we do not have semaphore priority boosting, and try to fairly
schedule irrespective of semaphore usage, we can move the tracking back
to the context and virtual engines can now utilise the faster inter-engine
synchronisation. If we see that any context fairs to use the semaphore,
because the system is oversubscribed and was busy doing something else
instead of spinning on the semaphore, we disable further usage of
semaphores with that context until it idles again. This should restrict
the semaphores to lightly utilised system where the latency between
requests is more noticeable, and curtail the bus-contention from checking
for signaled semaphores.

References: 44d89409a12e ("drm/i915: Make the semaphore saturation mask global")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context.c           |  3 +++
 drivers/gpu/drm/i915/gt/intel_context_types.h     |  2 ++
 drivers/gpu/drm/i915/gt/intel_engine_pm.c         |  2 --
 drivers/gpu/drm/i915/gt/intel_engine_types.h      |  2 --
 .../gpu/drm/i915/gt/intel_execlists_submission.c  | 15 ---------------
 drivers/gpu/drm/i915/i915_request.c               |  4 ++--
 6 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 349e7fa1488d..b3eb7513659b 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -345,6 +345,9 @@ static int __intel_context_active(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 
+	CE_TRACE(ce, "active\n");
+	ce->saturated = 0;
+
 	intel_context_get(ce);
 
 	/* everything should already be activated by intel_context_pre_pin() */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index f7a0fb6f3a2e..1b972b1e0047 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -102,6 +102,8 @@ struct intel_context {
 	} lrc;
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
+	intel_engine_mask_t saturated; /* submitting semaphores too late? */
+
 	/* Time on GPU as tracked by the hw. */
 	struct {
 		struct ewma_runtime avg;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 511a379c794d..64b9b857c71c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -254,8 +254,6 @@ static int __engine_park(struct intel_wakeref *wf)
 	struct intel_engine_cs *engine =
 		container_of(wf, typeof(*engine), wakeref);
 
-	engine->saturated = 0;
-
 	/*
 	 * If one and only one request is completed between pm events,
 	 * we know that we are inside the kernel context and it is
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 824a187b2803..74e55e0fbc65 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -304,8 +304,6 @@ struct intel_engine_cs {
 
 	struct intel_context *kernel_context; /* pinned */
 
-	intel_engine_mask_t saturated; /* submitting semaphores too late? */
-
 	struct {
 		struct delayed_work work;
 		struct i915_request *systole;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index b48ab6dab738..a0b01b6d475c 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3308,21 +3308,6 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
 	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
 
-	/*
-	 * The decision on whether to submit a request using semaphores
-	 * depends on the saturated state of the engine. We only compute
-	 * this during HW submission of the request, and we need for this
-	 * state to be globally applied to all requests being submitted
-	 * to this engine. Virtual engines encompass more than one physical
-	 * engine and so we cannot accurately tell in advance if one of those
-	 * engines is already saturated and so cannot afford to use a semaphore
-	 * and be pessimized in priority for doing so -- if we are the only
-	 * context using semaphores after all other clients have stopped, we
-	 * will be starved on the saturated system. Such a global switch for
-	 * semaphores is less than ideal, but alas is the current compromise.
-	 */
-	ve->base.saturated = ALL_ENGINES;
-
 	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
 
 	i915_sched_init_engine(&ve->base.active, ENGINE_VIRTUAL);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e636c68d4776..8fd69631b1b6 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -572,7 +572,7 @@ bool __i915_request_submit(struct i915_request *request)
 	 */
 	if (request->sched.semaphores &&
 	    i915_sw_fence_signaled(&request->semaphore))
-		engine->saturated |= request->sched.semaphores;
+		request->context->saturated |= request->sched.semaphores;
 
 	engine->emit_fini_breadcrumb(request,
 				     request->ring->vaddr + request->postfix);
@@ -1033,7 +1033,7 @@ already_busywaiting(struct i915_request *rq)
 	 *
 	 * See the are-we-too-late? check in __i915_request_submit().
 	 */
-	return rq->sched.semaphores | READ_ONCE(rq->engine->saturated);
+	return rq->sched.semaphores | READ_ONCE(rq->context->saturated);
 }
 
 static int
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 47/62] drm/i915: Bump default timeslicing quantum to 5ms

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig.profile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index 35bbe2b80596..3eacea42b19f 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -90,7 +90,7 @@ config DRM_I915_STOP_TIMEOUT
 
 config DRM_I915_TIMESLICE_DURATION
 	int "Scheduling quantum for userspace batches (ms, jiffy granularity)"
-	default 1 # milliseconds
+	default 5 # milliseconds
 	help
 	  When two user batches of equal priority are executing, we will
 	  alternate execution of each batch to ensure forward progress of
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 48/62] drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb

[Chris Wilson]

In preparation for removing the has_initial_breadcrumb field, add a
helper function for the existing callers.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c        | 2 +-
 drivers/gpu/drm/i915/gt/intel_ring_submission.c | 4 ++--
 drivers/gpu/drm/i915/gt/intel_timeline.c        | 6 +++---
 drivers/gpu/drm/i915/gt/intel_timeline.h        | 6 ++++++
 drivers/gpu/drm/i915/gt/selftest_timeline.c     | 5 +++--
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 1972dd5dca00..74f02d857acf 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -354,7 +354,7 @@ int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	u32 *cs;
 
 	GEM_BUG_ON(i915_request_has_initial_breadcrumb(rq));
-	if (!i915_request_timeline(rq)->has_initial_breadcrumb)
+	if (!intel_timeline_has_initial_breadcrumb(i915_request_timeline(rq)))
 		return 0;
 
 	cs = intel_ring_begin(rq, 6);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 4ea741f488a8..4bc80c50dbe9 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -979,7 +979,7 @@ static int ring_request_alloc(struct i915_request *request)
 	int ret;
 
 	GEM_BUG_ON(!intel_context_is_pinned(request->context));
-	GEM_BUG_ON(i915_request_timeline(request)->has_initial_breadcrumb);
+	GEM_BUG_ON(intel_timeline_has_initial_breadcrumb(i915_request_timeline(request)));
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -1304,7 +1304,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 		err = PTR_ERR(timeline);
 		goto err;
 	}
-	GEM_BUG_ON(timeline->has_initial_breadcrumb);
+	GEM_BUG_ON(intel_timeline_has_initial_breadcrumb(timeline));
 
 	err = intel_timeline_pin(timeline, NULL);
 	if (err)
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 7fe05918a76e..3441303d6858 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -445,14 +445,14 @@ void intel_timeline_exit(struct intel_timeline *tl)
 static u32 timeline_advance(struct intel_timeline *tl)
 {
 	GEM_BUG_ON(!atomic_read(&tl->pin_count));
-	GEM_BUG_ON(tl->seqno & tl->has_initial_breadcrumb);
+	GEM_BUG_ON(tl->seqno & intel_timeline_has_initial_breadcrumb(tl));
 
-	return tl->seqno += 1 + tl->has_initial_breadcrumb;
+	return tl->seqno += 1 + intel_timeline_has_initial_breadcrumb(tl);
 }
 
 static void timeline_rollback(struct intel_timeline *tl)
 {
-	tl->seqno -= 1 + tl->has_initial_breadcrumb;
+	tl->seqno -= 1 + intel_timeline_has_initial_breadcrumb(tl);
 }
 
 static noinline int
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index f502a619843f..0e5e9fdade5b 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -61,6 +61,12 @@ static inline void intel_timeline_put(struct intel_timeline *timeline)
 	kref_put(&timeline->kref, __intel_timeline_free);
 }
 
+static inline bool
+intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
+{
+	return tl->has_initial_breadcrumb;
+}
+
 static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
 					    u64 context, u32 seqno)
 {
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 6f3a3687ef0f..4f47a0535c91 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -666,7 +666,7 @@ static int live_hwsp_wrap(void *arg)
 	if (IS_ERR(tl))
 		return PTR_ERR(tl);
 
-	if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline)
+	if (!intel_timeline_has_initial_breadcrumb(tl) || !tl->hwsp_cacheline)
 		goto out_free;
 
 	err = intel_timeline_pin(tl, NULL);
@@ -1235,7 +1235,8 @@ static int live_hwsp_rollover_user(void *arg)
 			goto out;
 
 		tl = ce->timeline;
-		if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline)
+		if (!intel_timeline_has_initial_breadcrumb(tl) ||
+		    !tl->hwsp_cacheline)
 			goto out;
 
 		timeline_rollback(tl);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 49/62] drm/i915/gt: Track timeline GGTT offset separately from subpage offset

[Chris Wilson]

Currently we know that the timeline status page is at most a page in
size, and so we can preserve the lower 12bits of the offset when
relocating the status page in the GGTT. If we want to use a larger
object, such as the context state, we may not necessarily use a position
within the first page and so need more than 12b.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/gen6_engine_cs.c       |  4 ++--
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c       |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c      |  4 ++--
 drivers/gpu/drm/i915/gt/intel_timeline.c       | 17 +++++++----------
 drivers/gpu/drm/i915/gt/intel_timeline_types.h |  1 +
 drivers/gpu/drm/i915/gt/selftest_engine_cs.c   |  2 +-
 drivers/gpu/drm/i915/gt/selftest_rc6.c         |  2 +-
 drivers/gpu/drm/i915/gt/selftest_timeline.c    | 16 ++++++++--------
 8 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
index ce38d1bcaba3..2f59dd3bdc18 100644
--- a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
@@ -161,7 +161,7 @@ u32 *gen6_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->hwsp_offset |
+	*cs++ = i915_request_active_timeline(rq)->ggtt_offset |
 		PIPE_CONTROL_GLOBAL_GTT;
 	*cs++ = rq->fence.seqno;
 
@@ -359,7 +359,7 @@ u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_GLOBAL_GTT_IVB |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->hwsp_offset;
+	*cs++ = i915_request_active_timeline(rq)->ggtt_offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 74f02d857acf..dcd8786d796d 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -346,7 +346,7 @@ static u32 hwsp_offset(const struct i915_request *rq)
 	if (cl)
 		return cl->ggtt_offset;
 
-	return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+	return rcu_dereference_protected(rq->timeline, 1)->ggtt_offset;
 }
 
 int gen8_emit_init_breadcrumb(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index f88e367d5201..6d461c2ab671 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1324,7 +1324,7 @@ static int print_ring(char *buf, int sz, struct i915_request *rq)
 		len = scnprintf(buf, sz,
 				"ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
 				i915_ggtt_offset(rq->ring->vma),
-				tl ? tl->hwsp_offset : 0,
+				tl ? tl->ggtt_offset : 0,
 				hwsp_seqno(rq),
 				DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
 						      1000 * 1000));
@@ -1663,7 +1663,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 		if (tl) {
 			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
-				   tl->hwsp_offset);
+				   tl->ggtt_offset);
 			intel_timeline_put(tl);
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 3441303d6858..7446c4eb5c8d 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -355,13 +355,11 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww)
 	if (err)
 		return err;
 
-	tl->hwsp_offset =
-		i915_ggtt_offset(tl->hwsp_ggtt) +
-		offset_in_page(tl->hwsp_offset);
+	tl->ggtt_offset = i915_ggtt_offset(tl->hwsp_ggtt) + tl->hwsp_offset;
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
-		 tl->fence_context, tl->hwsp_offset);
+		 tl->fence_context, tl->ggtt_offset);
 
-	cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
+	cacheline_acquire(tl->hwsp_cacheline, tl->ggtt_offset);
 	if (atomic_fetch_inc(&tl->pin_count)) {
 		cacheline_release(tl->hwsp_cacheline);
 		__i915_vma_unpin(tl->hwsp_ggtt);
@@ -529,14 +527,13 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 
 	vaddr = page_mask_bits(cl->vaddr);
 	tl->hwsp_offset = cacheline * CACHELINE_BYTES;
-	tl->hwsp_seqno =
-		memset(vaddr + tl->hwsp_offset, 0, CACHELINE_BYTES);
+	tl->hwsp_seqno = memset(vaddr + tl->hwsp_offset, 0, CACHELINE_BYTES);
 
-	tl->hwsp_offset += i915_ggtt_offset(vma);
+	tl->ggtt_offset = i915_ggtt_offset(vma) + tl->hwsp_offset;
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
-		 tl->fence_context, tl->hwsp_offset);
+		 tl->fence_context, tl->ggtt_offset);
 
-	cacheline_acquire(cl, tl->hwsp_offset);
+	cacheline_acquire(cl, tl->ggtt_offset);
 	tl->hwsp_cacheline = cl;
 
 	*seqno = timeline_advance(tl);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index e360f50706bf..f187c5aac11c 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -48,6 +48,7 @@ struct intel_timeline {
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
 	u32 hwsp_offset;
+	u32 ggtt_offset;
 
 	struct intel_timeline_cacheline *hwsp_cacheline;
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 439c8984f5fa..bf4b8973b188 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -54,7 +54,7 @@ static int write_timestamp(struct i915_request *rq, int slot)
 		cmd++;
 	*cs++ = cmd;
 	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base));
-	*cs++ = i915_request_timeline(rq)->hwsp_offset + slot * sizeof(u32);
+	*cs++ = i915_request_timeline(rq)->ggtt_offset + slot * sizeof(u32);
 	*cs++ = 0;
 
 	intel_ring_advance(rq, cs);
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
index 61abc0556601..4eb4c627ec44 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rc6.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -138,7 +138,7 @@ static const u32 *__live_rc6_ctx(struct intel_context *ce)
 
 	*cs++ = cmd;
 	*cs++ = i915_mmio_reg_offset(GEN8_RC6_CTX_INFO);
-	*cs++ = ce->timeline->hwsp_offset + 8;
+	*cs++ = ce->timeline->ggtt_offset + 8;
 	*cs++ = 0;
 	intel_ring_advance(rq, cs);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 4f47a0535c91..e44bfceef413 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -469,7 +469,7 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 
 	i915_request_get(rq);
 
-	err = emit_ggtt_store_dw(rq, tl->hwsp_offset, value);
+	err = emit_ggtt_store_dw(rq, tl->ggtt_offset, value);
 	i915_request_add(rq);
 	if (err) {
 		i915_request_put(rq);
@@ -565,7 +565,7 @@ static int live_hwsp_engine(void *arg)
 
 		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
 			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
-				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
+				      n, tl->fence_context, tl->ggtt_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -637,7 +637,7 @@ static int live_hwsp_alternate(void *arg)
 
 		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
 			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
-				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
+				      n, tl->fence_context, tl->ggtt_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -697,9 +697,9 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 		pr_debug("seqno[0]:%08x, hwsp_offset:%08x\n",
-			 seqno[0], tl->hwsp_offset);
+			 seqno[0], tl->ggtt_offset);
 
-		err = emit_ggtt_store_dw(rq, tl->hwsp_offset, seqno[0]);
+		err = emit_ggtt_store_dw(rq, tl->ggtt_offset, seqno[0]);
 		if (err) {
 			i915_request_add(rq);
 			goto out;
@@ -714,9 +714,9 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 		pr_debug("seqno[1]:%08x, hwsp_offset:%08x\n",
-			 seqno[1], tl->hwsp_offset);
+			 seqno[1], tl->ggtt_offset);
 
-		err = emit_ggtt_store_dw(rq, tl->hwsp_offset, seqno[1]);
+		err = emit_ggtt_store_dw(rq, tl->ggtt_offset, seqno[1]);
 		if (err) {
 			i915_request_add(rq);
 			goto out;
@@ -1344,7 +1344,7 @@ static int live_hwsp_recycle(void *arg)
 			if (READ_ONCE(*tl->hwsp_seqno) != count) {
 				GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x found 0x%x\n",
 					      count, tl->fence_context,
-					      tl->hwsp_offset, *tl->hwsp_seqno);
+					      tl->ggtt_offset, *tl->hwsp_seqno);
 				GEM_TRACE_DUMP();
 				err = -EINVAL;
 			}
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 50/62] drm/i915/gt: Add timeline "mode"

[Chris Wilson]

Explicitly differentiate between the absolute and relative timelines,
and the global HWSP and ppHWSP relative offsets. When using a timeline
that is relative to a known status page, we can replace the absolute
addressing in the commands with indexed variants.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_timeline.c      | 21 ++++++++++++++++---
 drivers/gpu/drm/i915/gt/intel_timeline.h      |  2 +-
 .../gpu/drm/i915/gt/intel_timeline_types.h    | 10 +++++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 7446c4eb5c8d..c49d088b3541 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -227,7 +227,6 @@ static int intel_timeline_init(struct intel_timeline *timeline,
 
 	timeline->gt = gt;
 
-	timeline->has_initial_breadcrumb = !hwsp;
 	timeline->hwsp_cacheline = NULL;
 
 	if (!hwsp) {
@@ -244,13 +243,29 @@ static int intel_timeline_init(struct intel_timeline *timeline,
 			return PTR_ERR(cl);
 		}
 
+		timeline->mode = INTEL_TIMELINE_ABSOLUTE;
 		timeline->hwsp_cacheline = cl;
 		timeline->hwsp_offset = cacheline * CACHELINE_BYTES;
 
 		vaddr = page_mask_bits(cl->vaddr);
 	} else {
-		timeline->hwsp_offset = offset;
-		vaddr = i915_gem_object_pin_map(hwsp->obj, I915_MAP_WB);
+		int preferred;
+
+		if (offset & INTEL_TIMELINE_RELATIVE_CONTEXT) {
+			timeline->mode = INTEL_TIMELINE_RELATIVE_CONTEXT;
+			timeline->hwsp_offset =
+				offset & ~INTEL_TIMELINE_RELATIVE_CONTEXT;
+			preferred = i915_coherent_map_type(gt->i915);
+		} else {
+			timeline->mode = INTEL_TIMELINE_RELATIVE_ENGINE;
+			timeline->hwsp_offset = offset;
+			preferred = I915_MAP_WB;
+		}
+
+		vaddr = i915_gem_object_pin_map(hwsp->obj,
+						preferred | I915_MAP_OVERRIDE);
+		if (IS_ERR(vaddr))
+			vaddr = i915_gem_object_pin_map(hwsp->obj, I915_MAP_WC);
 		if (IS_ERR(vaddr))
 			return PTR_ERR(vaddr);
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index 0e5e9fdade5b..6e738a85beda 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -64,7 +64,7 @@ static inline void intel_timeline_put(struct intel_timeline *timeline)
 static inline bool
 intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
 {
-	return tl->has_initial_breadcrumb;
+	return tl->mode == INTEL_TIMELINE_ABSOLUTE;
 }
 
 static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index f187c5aac11c..3c1ab901b702 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -20,6 +20,12 @@ struct i915_syncmap;
 struct intel_gt;
 struct intel_timeline_hwsp;
 
+enum intel_timeline_mode {
+	INTEL_TIMELINE_ABSOLUTE = 0,
+	INTEL_TIMELINE_RELATIVE_CONTEXT = BIT(0),
+	INTEL_TIMELINE_RELATIVE_ENGINE  = BIT(1),
+};
+
 struct intel_timeline {
 	u64 fence_context;
 	u32 seqno;
@@ -45,6 +51,8 @@ struct intel_timeline {
 	atomic_t pin_count;
 	atomic_t active_count;
 
+	enum intel_timeline_mode mode;
+
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
 	u32 hwsp_offset;
@@ -52,8 +60,6 @@ struct intel_timeline {
 
 	struct intel_timeline_cacheline *hwsp_cacheline;
 
-	bool has_initial_breadcrumb;
-
 	/**
 	 * List of breadcrumbs associated with GPU requests currently
 	 * outstanding.
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 51/62] drm/i915/gt: Use indices for writing into relative timelines

[Chris Wilson]

Relative timelines are relative to either the global or per-process
HWSP, and so we can replace the absolute addressing with store-index
variants for position invariance.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 98 +++++++++++++++++-------
 drivers/gpu/drm/i915/gt/intel_timeline.h | 12 +++
 2 files changed, 82 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index dcd8786d796d..5f0485cb9e3b 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -502,7 +502,19 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 
 static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	unsigned int flags = MI_FLUSH_DW_OP_STOREDW;
+	u32 offset = hwsp_offset(rq);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= MI_FLUSH_DW_STORE_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		offset |= MI_FLUSH_DW_USE_GTT;
+
+	return __gen8_emit_flush_dw(cs, rq->fence.seqno, offset, flags);
 }
 
 u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
@@ -512,6 +524,18 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	unsigned int flags = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL;
+	u32 offset = hwsp_offset(rq);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
 	cs = gen8_emit_pipe_control(cs,
 				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
@@ -519,26 +543,33 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 				    0);
 
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
-	cs = gen8_emit_ggtt_write_rcs(cs,
-				      rq->fence.seqno,
-				      hwsp_offset(rq),
-				      PIPE_CONTROL_FLUSH_ENABLE |
-				      PIPE_CONTROL_CS_STALL);
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
 
 	return gen8_emit_fini_breadcrumb_tail(rq, cs);
 }
 
 u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write_rcs(cs,
-				      rq->fence.seqno,
-				      hwsp_offset(rq),
-				      PIPE_CONTROL_CS_STALL |
-				      PIPE_CONTROL_TILE_CACHE_FLUSH |
-				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				      PIPE_CONTROL_DC_FLUSH_ENABLE |
-				      PIPE_CONTROL_FLUSH_ENABLE);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = hwsp_offset(rq);
+	unsigned int flags;
+
+	flags = (PIPE_CONTROL_CS_STALL |
+		 PIPE_CONTROL_TILE_CACHE_FLUSH |
+		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		 PIPE_CONTROL_DC_FLUSH_ENABLE |
+		 PIPE_CONTROL_FLUSH_ENABLE);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
 
 	return gen8_emit_fini_breadcrumb_tail(rq, cs);
 }
@@ -601,19 +632,30 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	cs = gen12_emit_ggtt_write_rcs(cs,
-				       rq->fence.seqno,
-				       hwsp_offset(rq),
-				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
-				       PIPE_CONTROL_CS_STALL |
-				       PIPE_CONTROL_TILE_CACHE_FLUSH |
-				       PIPE_CONTROL_FLUSH_L3 |
-				       PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				       PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				       /* Wa_1409600907:tgl */
-				       PIPE_CONTROL_DEPTH_STALL |
-				       PIPE_CONTROL_DC_FLUSH_ENABLE |
-				       PIPE_CONTROL_FLUSH_ENABLE);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = hwsp_offset(rq);
+	unsigned int flags;
+
+	flags = (PIPE_CONTROL_CS_STALL |
+		 PIPE_CONTROL_TILE_CACHE_FLUSH |
+		 PIPE_CONTROL_FLUSH_L3 |
+		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		 /* Wa_1409600907:tgl */
+		 PIPE_CONTROL_DEPTH_STALL |
+		 PIPE_CONTROL_DC_FLUSH_ENABLE |
+		 PIPE_CONTROL_FLUSH_ENABLE);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset,
+				   PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags);
 
 	return gen12_emit_fini_breadcrumb_tail(rq, cs);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index 6e738a85beda..a58823fe7a34 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -67,6 +67,18 @@ intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
 	return tl->mode == INTEL_TIMELINE_ABSOLUTE;
 }
 
+static inline bool
+intel_timeline_is_relative(const struct intel_timeline *tl)
+{
+	return tl->mode != INTEL_TIMELINE_ABSOLUTE;
+}
+
+static inline bool
+intel_timeline_in_context(const struct intel_timeline *tl)
+{
+	return tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT;
+}
+
 static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
 					    u64 context, u32 seqno)
 {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 52/62] drm/i915/selftests: Exercise relative timeline modes

[Chris Wilson]

A quick test to verify that the backend accepts each type of timeline
and can use them to track and control request emission.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/selftest_timeline.c | 105 ++++++++++++++++++++
 1 file changed, 105 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index e44bfceef413..a0a6a5ba09d2 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -1365,9 +1365,114 @@ static int live_hwsp_recycle(void *arg)
 	return err;
 }
 
+static int live_hwsp_relative(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/*
+	 * Check backend support for different timeline modes.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		enum intel_timeline_mode mode;
+
+		if (!intel_engine_has_scheduler(engine))
+			continue;
+
+		for (mode = INTEL_TIMELINE_ABSOLUTE;
+		     mode <= INTEL_TIMELINE_RELATIVE_ENGINE;
+		     mode++) {
+			struct intel_timeline *tl;
+			struct i915_request *rq;
+			struct intel_context *ce;
+			const char *msg;
+			int err;
+
+			if (mode == INTEL_TIMELINE_RELATIVE_CONTEXT &&
+			    !HAS_EXECLISTS(gt->i915))
+				continue;
+
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce))
+				return PTR_ERR(ce);
+
+			err = intel_context_alloc_state(ce);
+			if (err) {
+				intel_context_put(ce);
+				return err;
+			}
+
+			switch (mode) {
+			case INTEL_TIMELINE_ABSOLUTE:
+				tl = intel_timeline_create(gt);
+				msg = "local";
+				break;
+
+			case INTEL_TIMELINE_RELATIVE_CONTEXT:
+				tl = __intel_timeline_create(gt,
+							     ce->state,
+							     INTEL_TIMELINE_RELATIVE_CONTEXT |
+							     0x400);
+				msg = "ppHWSP";
+				break;
+
+			case INTEL_TIMELINE_RELATIVE_ENGINE:
+				tl = __intel_timeline_create(gt,
+							     engine->status_page.vma,
+							     0x400);
+				msg = "HWSP";
+				break;
+			default:
+				continue;
+			}
+			if (IS_ERR(tl)) {
+				intel_context_put(ce);
+				return PTR_ERR(tl);
+			}
+
+			pr_info("Testing %s timeline on %s\n",
+				msg, engine->name);
+
+			intel_timeline_put(ce->timeline);
+			ce->timeline = tl;
+
+			err = intel_timeline_pin(tl, NULL);
+			if (err) {
+				intel_context_put(ce);
+				return err;
+			}
+			tl->seqno = 0xc0000000;
+			WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno);
+			intel_timeline_unpin(tl);
+
+			rq = intel_context_create_request(ce);
+			intel_context_put(ce);
+			if (IS_ERR(rq))
+				return PTR_ERR(rq);
+
+			GEM_BUG_ON(rcu_access_pointer(rq->timeline) != tl);
+
+			i915_request_get(rq);
+			i915_request_add(rq);
+
+			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+				i915_request_put(rq);
+				return -EIO;
+			}
+
+			i915_request_put(rq);
+		}
+	}
+
+	return 0;
+}
+
 int intel_timeline_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(live_hwsp_relative),
 		SUBTEST(live_hwsp_recycle),
 		SUBTEST(live_hwsp_engine),
 		SUBTEST(live_hwsp_alternate),
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 53/62] drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines

[Chris Wilson]

When we are not using semaphores with a context/engine, we can simply
reuse the same seqno location across wraps, but we still require each
timeline to have its own address. For LRC submission, each context is
prefixed by a per-process HWSP, which provides us with a unique location
for each context-local timeline. A shared timeline that is common to
multiple contexts will continue to use a separate page.

This enables us to create position invariant contexts should we feel the
need to relocate them.

Initially they are automatically used by Broadwell/Braswell as they do
not require independent timelines.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 008f50a86355..d8829f7e2d8c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -834,6 +834,14 @@ pinned_timeline(struct intel_context *ce, struct intel_engine_cs *engine)
 	return intel_timeline_create_from_engine(engine, page_unmask_bits(tl));
 }
 
+static struct intel_timeline *
+pphwsp_timeline(struct intel_context *ce, struct i915_vma *state)
+{
+	return __intel_timeline_create(ce->engine->gt, state,
+				       I915_GEM_HWS_SEQNO_ADDR |
+				       INTEL_TIMELINE_RELATIVE_CONTEXT);
+}
+
 int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 {
 	struct intel_ring *ring;
@@ -861,8 +869,10 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 		 */
 		if (unlikely(ce->timeline))
 			tl = pinned_timeline(ce, engine);
-		else
+		else if (intel_engine_has_semaphores(engine))
 			tl = intel_timeline_create(engine->gt);
+		else
+			tl = pphwsp_timeline(ce, vma);
 		if (IS_ERR(tl)) {
 			err = PTR_ERR(tl);
 			goto err_ring;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 54/62] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq"

[Chris Wilson]

This was removed in commit 478ffad6d690 ("drm/i915: drop
engine_pin/unpin_breadcrumbs_irq") as the last user had been removed,
but now there is a promise of a new user in the next patch.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 24 +++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.h |  3 +++
 2 files changed, 27 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 2eabb9ab5d47..824621fcfaa4 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -329,6 +329,30 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b)
 	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
+void intel_breadcrumbs_pin_irq(struct intel_breadcrumbs *b)
+{
+	if (GEM_DEBUG_WARN_ON(!b->irq_engine))
+		return;
+
+	spin_lock_irq(&b->irq_lock);
+	if (!b->irq_enabled++)
+		irq_enable(b->irq_engine);
+	GEM_BUG_ON(!b->irq_enabled); /* no overflow! */
+	spin_unlock_irq(&b->irq_lock);
+}
+
+void intel_breadcrumbs_unpin_irq(struct intel_breadcrumbs *b)
+{
+	if (GEM_DEBUG_WARN_ON(!b->irq_engine))
+		return;
+
+	spin_lock_irq(&b->irq_lock);
+	GEM_BUG_ON(!b->irq_enabled); /* no underflow! */
+	if (!--b->irq_enabled)
+		irq_disable(b->irq_engine);
+	spin_unlock_irq(&b->irq_lock);
+}
+
 void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 {
 	if (!READ_ONCE(b->irq_armed))
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
index 75cc9cff3ae3..d400ac17c733 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.h
@@ -18,6 +18,9 @@ struct intel_breadcrumbs *
 intel_breadcrumbs_create(struct intel_engine_cs *irq_engine);
 void intel_breadcrumbs_free(struct intel_breadcrumbs *b);
 
+void intel_breadcrumbs_pin_irq(struct intel_breadcrumbs *b);
+void intel_breadcrumbs_unpin_irq(struct intel_breadcrumbs *b);
+
 void intel_breadcrumbs_reset(struct intel_breadcrumbs *b);
 void __intel_breadcrumbs_park(struct intel_breadcrumbs *b);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 55/62] drm/i915/gt: Couple tasklet scheduling for all CS interrupts

[Chris Wilson]

If any engine asks for the tasklet to be kicked from the CS interrupt,
do so. Currently, this is used by the execlists scheduler backends to
feed in the next request to the HW, and similarly could be used by a
ring scheduler, as will be seen in the next patch.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_irq.c | 17 ++++++++++++-----
 drivers/gpu/drm/i915/gt/intel_gt_irq.h |  3 +++
 drivers/gpu/drm/i915/gt/intel_rps.c    |  2 +-
 drivers/gpu/drm/i915/i915_irq.c        |  8 ++++----
 4 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 2106fb403c3e..dfb2d66e1556 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -63,6 +63,13 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		i915_sched_kick(&engine->active);
 }
 
+void gen2_engine_cs_irq(struct intel_engine_cs *engine)
+{
+	intel_engine_signal_breadcrumbs(engine);
+	if (intel_engine_needs_breadcrumb_tasklet(engine))
+		i915_sched_kick(&engine->active);
+}
+
 static u32
 gen11_gt_engine_identity(struct intel_gt *gt,
 			 const unsigned int bank, const unsigned int bit)
@@ -276,9 +283,9 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
+		gen2_engine_cs_irq(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		gen2_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 }
 
 static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
@@ -302,11 +309,11 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
 void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
+		gen2_engine_cs_irq(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		gen2_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 	if (gt_iir & GT_BLT_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine_class[COPY_ENGINE_CLASS][0]);
+		gen2_engine_cs_irq(gt->engine_class[COPY_ENGINE_CLASS][0]);
 
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.h b/drivers/gpu/drm/i915/gt/intel_gt_irq.h
index 886c5cf408a2..6c69cd563fe1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.h
@@ -9,6 +9,7 @@
 
 #include <linux/types.h>
 
+struct intel_engine_cs;
 struct intel_gt;
 
 #define GEN8_GT_IRQS (GEN8_GT_RCS_IRQ | \
@@ -19,6 +20,8 @@ struct intel_gt;
 		      GEN8_GT_PM_IRQ | \
 		      GEN8_GT_GUC_IRQ)
 
+void gen2_engine_cs_irq(struct intel_engine_cs *engine);
+
 void gen11_gt_irq_reset(struct intel_gt *gt);
 void gen11_gt_irq_postinstall(struct intel_gt *gt);
 void gen11_gt_irq_handler(struct intel_gt *gt, const u32 master_ctl);
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index e1397b8d3586..2b443b735a98 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1771,7 +1771,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 		return;
 
 	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		intel_engine_signal_breadcrumbs(gt->engine[VECS0]);
+		gen2_engine_cs_irq(gt->engine[VECS0]);
 
 	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
 		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 491f82500d68..8c8a84a148d5 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3913,7 +3913,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			gen2_engine_cs_irq(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -4019,7 +4019,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			gen2_engine_cs_irq(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -4162,10 +4162,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]);
+			gen2_engine_cs_irq(dev_priv->gt.engine[RCS0]);
 
 		if (iir & I915_BSD_USER_INTERRUPT)
-			intel_engine_signal_breadcrumbs(dev_priv->gt.engine[VCS0]);
+			gen2_engine_cs_irq(dev_priv->gt.engine[VCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 56/62] drm/i915/gt: Support creation of 'internal' rings

[Chris Wilson]

To support legacy ring buffer scheduling, we want a virtual ringbuffer
for each client. These rings are purely for holding the requests as they
are being constructed on the CPU and never accessed by the GPU, so they
should not be bound into the GGTT, and we can use plain old WB mapped
pages.

As they are not bound, we need to nerf a few assumptions that a rq->ring
is in the GGTT.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context.c    |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c  | 17 +-----
 drivers/gpu/drm/i915/gt/intel_ring.c       | 66 ++++++++++++++--------
 drivers/gpu/drm/i915/gt/intel_ring.h       | 12 +++-
 drivers/gpu/drm/i915/gt/intel_ring_types.h |  2 +
 5 files changed, 59 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index b3eb7513659b..d01678c26a91 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -259,7 +259,7 @@ int __intel_context_do_pin_ww(struct intel_context *ce,
 		}
 
 		CE_TRACE(ce, "pin ring:{start:%08x, head:%04x, tail:%04x}\n",
-			 i915_ggtt_offset(ce->ring->vma),
+			 intel_ring_address(ce->ring),
 			 ce->ring->head, ce->ring->tail);
 
 		handoff = true;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 6d461c2ab671..916f4b8ce4c0 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1323,7 +1323,7 @@ static int print_ring(char *buf, int sz, struct i915_request *rq)
 
 		len = scnprintf(buf, sz,
 				"ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
-				i915_ggtt_offset(rq->ring->vma),
+				intel_ring_address(rq->ring),
 				tl ? tl->ggtt_offset : 0,
 				hwsp_seqno(rq),
 				DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
@@ -1651,7 +1651,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		i915_request_show(m, rq, "\t\tactive ", 0);
 
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
-			   i915_ggtt_offset(rq->ring->vma));
+			   intel_ring_address(rq->ring));
 		drm_printf(m, "\t\tring->head:   0x%08x\n",
 			   rq->ring->head);
 		drm_printf(m, "\t\tring->tail:   0x%08x\n",
@@ -1732,13 +1732,6 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
 	return total;
 }
 
-static bool match_ring(struct i915_request *rq)
-{
-	u32 ring = ENGINE_READ(rq->engine, RING_START);
-
-	return ring == i915_ggtt_offset(rq->ring->vma);
-}
-
 struct i915_request *
 intel_engine_find_active_request(struct intel_engine_cs *engine)
 {
@@ -1778,11 +1771,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
 			continue;
 
 		if (!i915_request_started(request))
-			continue;
-
-		/* More than one preemptible request may match! */
-		if (!match_ring(request))
-			continue;
+			break;
 
 		active = request;
 		break;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 06385550450c..ea873c2a7d6b 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -32,33 +32,42 @@ void __intel_ring_pin(struct intel_ring *ring)
 int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww)
 {
 	struct i915_vma *vma = ring->vma;
-	unsigned int flags;
 	void *addr;
 	int ret;
 
 	if (atomic_fetch_inc(&ring->pin_count))
 		return 0;
 
-	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
-	flags = PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
+	if (!(ring->flags & INTEL_RING_CREATE_INTERNAL)) {
+		int type = i915_coherent_map_type(vma->vm->i915);
+		unsigned int pin;
 
-	if (vma->obj->stolen)
-		flags |= PIN_MAPPABLE;
-	else
-		flags |= PIN_HIGH;
+		/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+		pin |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
 
-	ret = i915_ggtt_pin(vma, ww, 0, flags);
-	if (unlikely(ret))
-		goto err_unpin;
+		if (vma->obj->stolen)
+			pin |= PIN_MAPPABLE;
+		else
+			pin |= PIN_HIGH;
 
-	if (i915_vma_is_map_and_fenceable(vma))
-		addr = (void __force *)i915_vma_pin_iomap(vma);
-	else
-		addr = i915_gem_object_pin_map(vma->obj,
-					       i915_coherent_map_type(vma->vm->i915));
-	if (IS_ERR(addr)) {
-		ret = PTR_ERR(addr);
-		goto err_ring;
+		ret = i915_ggtt_pin(vma, ww, 0, pin);
+		if (unlikely(ret))
+			goto err_unpin;
+
+		if (i915_vma_is_map_and_fenceable(vma))
+			addr = (void __force *)i915_vma_pin_iomap(vma);
+		else
+			addr = i915_gem_object_pin_map(vma->obj, type);
+		if (IS_ERR(addr)) {
+			ret = PTR_ERR(addr);
+			goto err_ring;
+		}
+	} else {
+		addr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+		if (IS_ERR(addr)) {
+			ret = PTR_ERR(addr);
+			goto err_ring;
+		}
 	}
 
 	i915_vma_make_unshrinkable(vma);
@@ -99,10 +108,12 @@ void intel_ring_unpin(struct intel_ring *ring)
 		i915_gem_object_unpin_map(vma->obj);
 
 	i915_vma_make_purgeable(vma);
-	i915_vma_unpin(vma);
+	if (!(ring->flags & INTEL_RING_CREATE_INTERNAL))
+		i915_vma_unpin(vma);
 }
 
-static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
+static struct i915_vma *
+create_ring_vma(struct i915_ggtt *ggtt, int size, unsigned int flags)
 {
 	struct i915_address_space *vm = &ggtt->vm;
 	struct drm_i915_private *i915 = vm->i915;
@@ -110,8 +121,10 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
 	struct i915_vma *vma;
 
 	obj = ERR_PTR(-ENODEV);
-	if (i915_ggtt_has_aperture(ggtt))
-		obj = i915_gem_object_create_stolen(i915, size);
+	if (!(flags & INTEL_RING_CREATE_INTERNAL)) {
+		if (i915_ggtt_has_aperture(ggtt))
+			obj = i915_gem_object_create_stolen(i915, size);
+	}
 	if (IS_ERR(obj))
 		obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
@@ -136,12 +149,14 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
 }
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size)
+intel_engine_create_ring(struct intel_engine_cs *engine, unsigned int size)
 {
 	struct drm_i915_private *i915 = engine->i915;
+	unsigned int flags = size & GENMASK(11, 0);
 	struct intel_ring *ring;
 	struct i915_vma *vma;
 
+	size ^= flags;
 	GEM_BUG_ON(!is_power_of_2(size));
 	GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES);
 
@@ -150,8 +165,10 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 		return ERR_PTR(-ENOMEM);
 
 	kref_init(&ring->ref);
+
 	ring->size = size;
 	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
+	ring->flags = flags;
 
 	/*
 	 * Workaround an erratum on the i830 which causes a hang if
@@ -164,11 +181,12 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 
 	intel_ring_update_space(ring);
 
-	vma = create_ring_vma(engine->gt->ggtt, size);
+	vma = create_ring_vma(engine->gt->ggtt, size, flags);
 	if (IS_ERR(vma)) {
 		kfree(ring);
 		return ERR_CAST(vma);
 	}
+
 	ring->vma = vma;
 
 	return ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index 1700579bdc93..5419ac0327f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -9,12 +9,14 @@
 
 #include "i915_gem.h" /* GEM_BUG_ON */
 #include "i915_request.h"
+#include "i915_vma.h"
 #include "intel_ring_types.h"
 
 struct intel_engine_cs;
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size);
+intel_engine_create_ring(struct intel_engine_cs *engine, unsigned int size);
+#define INTEL_RING_CREATE_INTERNAL BIT(0)
 
 u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords);
 int intel_ring_cacheline_align(struct i915_request *rq);
@@ -138,4 +140,12 @@ __intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
 	return (head - tail - CACHELINE_BYTES) & (size - 1);
 }
 
+static inline u32 intel_ring_address(const struct intel_ring *ring)
+{
+	if (ring->flags & INTEL_RING_CREATE_INTERNAL)
+		return -1;
+
+	return i915_ggtt_offset(ring->vma);
+}
+
 #endif /* INTEL_RING_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h
index 1a189ea00fd8..d927deafcb33 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h
@@ -47,6 +47,8 @@ struct intel_ring {
 	u32 size;
 	u32 wrap;
 	u32 effective_size;
+
+	unsigned long flags;
 };
 
 #endif /* INTEL_RING_TYPES_H */
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 57/62] drm/i915/gt: Use client timeline address for seqno writes

[Chris Wilson]

If we allow for per-client timelines, even with legacy ring submission,
we open the door to a world full of possiblities [scheduling and
semaphores].

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/gen6_engine_cs.c | 89 +++++++++++++++++-------
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 23 ++----
 drivers/gpu/drm/i915/i915_request.h      | 13 ++++
 3 files changed, 82 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
index 2f59dd3bdc18..14cab4c726ce 100644
--- a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
@@ -141,6 +141,12 @@ int gen6_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 u32 *gen6_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = __i915_request_hwsp_offset(rq);
+	unsigned int flags;
+
+	GEM_BUG_ON(tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT);
+
 	/* First we do the gen6_emit_post_sync_nonzero_flush w/a */
 	*cs++ = GFX_OP_PIPE_CONTROL(4);
 	*cs++ = PIPE_CONTROL_CS_STALL | PIPE_CONTROL_STALL_AT_SCOREBOARD;
@@ -154,15 +160,22 @@ u32 *gen6_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		PIPE_CONTROL_GLOBAL_GTT;
 	*cs++ = 0;
 
-	/* Finally we can flush and with it emit the breadcrumb */
-	*cs++ = GFX_OP_PIPE_CONTROL(4);
-	*cs++ = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+	flags = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->ggtt_offset |
-		PIPE_CONTROL_GLOBAL_GTT;
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	if (!intel_timeline_in_context(tl))
+		offset |= PIPE_CONTROL_GLOBAL_GTT;
+
+	/* Finally we can flush and with it emit the breadcrumb */
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = flags;
+	*cs++ = offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
@@ -351,15 +364,28 @@ int gen7_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	*cs++ = GFX_OP_PIPE_CONTROL(4);
-	*cs++ = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = __i915_request_hwsp_offset(rq);
+	unsigned int flags;
+
+	GEM_BUG_ON(tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT);
+
+	flags = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_FLUSH_ENABLE |
 		 PIPE_CONTROL_QW_WRITE |
-		 PIPE_CONTROL_GLOBAL_GTT_IVB |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->ggtt_offset;
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = flags;
+	*cs++ = offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
@@ -373,11 +399,21 @@ u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen6_emit_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 {
-	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = __i915_request_hwsp_offset(rq);
+	unsigned int flags = 0;
+
+	GEM_BUG_ON(tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT);
 
-	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
-	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= MI_FLUSH_DW_STORE_INDEX;
+	}
+	if (!intel_timeline_in_context(tl))
+		offset |= MI_FLUSH_DW_USE_GTT;
+
+	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | flags;
+	*cs++ = offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
@@ -391,28 +427,31 @@ u32 *gen6_emit_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 #define GEN7_XCS_WA 32
 u32 *gen7_emit_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 {
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = __i915_request_hwsp_offset(rq);
+	u32 cmd = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW;
 	int i;
 
-	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	GEM_BUG_ON(tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT);
 
-	*cs++ = MI_FLUSH_DW | MI_INVALIDATE_TLB |
-		MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
-	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		cmd |= MI_FLUSH_DW_STORE_INDEX;
+	}
+	if (!intel_timeline_in_context(tl))
+		offset |= MI_FLUSH_DW_USE_GTT;
+
+	*cs++ = cmd;
+	*cs++ = offset;
 	*cs++ = rq->fence.seqno;
 
 	for (i = 0; i < GEN7_XCS_WA; i++) {
-		*cs++ = MI_STORE_DWORD_INDEX;
-		*cs++ = I915_GEM_HWS_SEQNO_ADDR;
+		*cs++ = cmd;
+		*cs++ = offset;
 		*cs++ = rq->fence.seqno;
 	}
 
-	*cs++ = MI_FLUSH_DW;
-	*cs++ = 0;
-	*cs++ = 0;
-
 	*cs++ = MI_USER_INTERRUPT;
-	*cs++ = MI_NOOP;
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 5f0485cb9e3b..171874589174 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -336,19 +336,6 @@ static inline u32 preempt_address(struct intel_engine_cs *engine)
 		I915_GEM_HWS_PREEMPT_ADDR);
 }
 
-static u32 hwsp_offset(const struct i915_request *rq)
-{
-	const struct intel_timeline_cacheline *cl;
-
-	/* Before the request is executed, the timeline/cachline is fixed */
-
-	cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
-	if (cl)
-		return cl->ggtt_offset;
-
-	return rcu_dereference_protected(rq->timeline, 1)->ggtt_offset;
-}
-
 int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
@@ -371,7 +358,7 @@ int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	*cs++ = MI_NOOP;
 
 	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-	*cs++ = hwsp_offset(rq);
+	*cs++ = __i915_request_hwsp_offset(rq);
 	*cs++ = 0;
 	*cs++ = rq->fence.seqno - 1;
 
@@ -504,7 +491,7 @@ static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
 {
 	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
 	unsigned int flags = MI_FLUSH_DW_OP_STOREDW;
-	u32 offset = hwsp_offset(rq);
+	u32 offset = __i915_request_hwsp_offset(rq);
 
 	if (intel_timeline_is_relative(tl)) {
 		offset = offset_in_page(offset);
@@ -526,7 +513,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
 	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
 	unsigned int flags = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL;
-	u32 offset = hwsp_offset(rq);
+	u32 offset = __i915_request_hwsp_offset(rq);
 
 	if (intel_timeline_is_relative(tl)) {
 		offset = offset_in_page(offset);
@@ -551,7 +538,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
 	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
-	u32 offset = hwsp_offset(rq);
+	u32 offset = __i915_request_hwsp_offset(rq);
 	unsigned int flags;
 
 	flags = (PIPE_CONTROL_CS_STALL |
@@ -633,7 +620,7 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
 	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
-	u32 offset = hwsp_offset(rq);
+	u32 offset = __i915_request_hwsp_offset(rq);
 	unsigned int flags;
 
 	flags = (PIPE_CONTROL_CS_STALL |
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index adfe863f778e..560a0ef0c80d 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -615,4 +615,17 @@ i915_request_active_timeline(const struct i915_request *rq)
 					 lockdep_is_held(&rq->engine->active.lock));
 }
 
+static inline u32 __i915_request_hwsp_offset(const struct i915_request *rq)
+{
+	const struct intel_timeline_cacheline *cl;
+
+	/* Before the request is executed, the timeline/cachline is fixed */
+
+	cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
+	if (cl)
+		return cl->ggtt_offset;
+
+	return rcu_dereference_protected(rq->timeline, 1)->ggtt_offset;
+}
+
 #endif /* I915_REQUEST_H */
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 58/62] drm/i915/gt: Infrastructure for ring scheduling

[Chris Wilson]

Build a bare bones scheduler to sit on top the global legacy ringbuffer
submission. This virtual execlists scheme should be applicable to all
older platforms.

A key problem we have with the legacy ring buffer submission is that it
only allows for FIFO queuing. All clients share the global request queue
and must contend for its lock when submitting. As any client may need to
wait for external events, all clients must then wait. However, if we
stage each client into their own virtual ringbuffer with their own
timelines, we can copy the client requests into the global ringbuffer
only when they are ready, reordering the submission around stalls.
Furthermore, the ability to reorder gives us rudimentarily priority
sorting -- although without preemption support, once something is on the
GPU it stays on the GPU, and so it is still possible for a hog to delay
a high priority request (such as updating the display). However, it does
means that in keeping a short submission queue, the high priority
request will be next. This design resembles the old guc submission
scheduler, for reordering requests onto a global workqueue.

The implementation uses the MI_USER_INTERRUPT at the end of every
request to track completion, so is more interrupt happy than execlists
[which has an interrupt for each context event, albeit two]. Our
interrupts on these system are relatively heavy, and in the past we have
been able to completely starve Sandybrige by the interrupt traffic. Our
interrupt handlers are being much better (in part offloading the work to
bottom halves leaving the interrupt itself only dealing with acking the
registers) but we can still see the impact of starvation in the uneven
submission latency on a saturated system.

Overall though, the short sumission queues and extra interrupts do not
appear to be affecting throughput (+-10%, some tasks even improve to the
reduced request overheads) and improve latency. [Which is a massive
improvement since the introduction of Sandybridge!]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Makefile                 |   1 +
 drivers/gpu/drm/i915/gt/intel_engine.h        |   1 +
 drivers/gpu/drm/i915/gt/intel_engine_types.h  |   1 +
 .../gpu/drm/i915/gt/intel_ring_scheduler.c    | 768 ++++++++++++++++++
 .../gpu/drm/i915/gt/intel_ring_submission.c   |  17 +-
 .../gpu/drm/i915/gt/intel_ring_submission.h   |  17 +
 6 files changed, 797 insertions(+), 8 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_ring_submission.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 3a439b1d0496..d9bbc0945695 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -111,6 +111,7 @@ gt-y += \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
 	gt/intel_ring.o \
+	gt/intel_ring_scheduler.o \
 	gt/intel_ring_submission.o \
 	gt/intel_rps.o \
 	gt/intel_sseu.o \
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 801ae54cf60d..fa257a305143 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -191,6 +191,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 int intel_engine_resume(struct intel_engine_cs *engine);
 
 int intel_ring_submission_setup(struct intel_engine_cs *engine);
+int intel_ring_scheduler_setup(struct intel_engine_cs *engine);
 
 int intel_engine_stop_cs(struct intel_engine_cs *engine);
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 74e55e0fbc65..a93bef46e455 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -319,6 +319,7 @@ struct intel_engine_cs {
 	struct {
 		struct intel_ring *ring;
 		struct intel_timeline *timeline;
+		struct intel_context *context;
 	} legacy;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
new file mode 100644
index 000000000000..338d847445ca
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
@@ -0,0 +1,768 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/log2.h>
+
+#include <drm/i915_drm.h>
+
+#include "i915_drv.h"
+#include "intel_breadcrumbs.h"
+#include "intel_context.h"
+#include "intel_engine_pm.h"
+#include "intel_gt.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
+#include "intel_reset.h"
+#include "intel_ring.h"
+#include "intel_ring_submission.h"
+#include "shmem_utils.h"
+
+/*
+ * Rough estimate of the typical request size, performing a flush,
+ * set-context and then emitting the batch.
+ */
+#define LEGACY_REQUEST_SIZE 200
+
+static inline int rq_prio(const struct i915_request *rq)
+{
+	return rq->sched.attr.priority;
+}
+
+static inline u64 rq_deadline(const struct i915_request *rq)
+{
+	return rq->sched.deadline;
+}
+
+static inline bool reset_in_progress(const struct intel_engine_cs *engine)
+{
+	return unlikely(!__tasklet_is_enabled(&engine->active.tasklet));
+}
+
+static void
+set_current_context(struct intel_context **ptr, struct intel_context *ce)
+{
+	if (ce)
+		intel_context_get(ce);
+
+	ce = xchg(ptr, ce);
+
+	if (ce)
+		intel_context_put(ce);
+}
+
+static struct intel_engine_cs *__schedule_in(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+	struct intel_engine_cs *engine = rq->engine;
+
+	intel_context_get(ce);
+
+	__intel_gt_pm_get(engine->gt);
+	if (engine->fw_domain && !engine->fw_active++)
+		intel_uncore_forcewake_get(engine->uncore, engine->fw_domain);
+
+	CE_TRACE(ce, "schedule-in\n");
+
+	return engine;
+}
+
+static void schedule_in(struct i915_request *rq)
+{
+	struct intel_context * const ce = rq->context;
+	struct intel_engine_cs *old;
+
+	GEM_BUG_ON(!intel_engine_pm_is_awake(rq->engine));
+
+	old = ce->inflight;
+	if (!old)
+		old = __schedule_in(rq);
+	WRITE_ONCE(ce->inflight, ptr_inc(old));
+
+	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
+	GEM_BUG_ON(!intel_context_inflight_count(ce));
+}
+
+static void __schedule_out(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+	struct intel_engine_cs *engine = rq->engine;
+
+	CE_TRACE(ce, "schedule-out\n");
+
+	if (list_is_last_rcu(&rq->link, &ce->timeline->requests))
+		intel_engine_add_retire(engine, ce->timeline);
+	else
+		i915_request_update_deadline(list_next_entry(rq, link));
+
+	if (engine->fw_domain && !--engine->fw_active)
+		intel_uncore_forcewake_put(engine->uncore, engine->fw_domain);
+	intel_gt_pm_put_async(engine->gt);
+}
+
+static void schedule_out(struct i915_request *rq)
+{
+	struct intel_context *ce = rq->context;
+
+	GEM_BUG_ON(!ce->inflight);
+	ce->inflight = ptr_dec(ce->inflight);
+	if (!intel_context_inflight_count(ce)) {
+		GEM_BUG_ON(ce->inflight != rq->engine);
+		__schedule_out(rq);
+		WRITE_ONCE(ce->inflight, NULL);
+		intel_context_put(ce);
+	}
+
+	i915_request_put(rq);
+}
+
+static u32 *ring_map(struct intel_ring *ring, u32 len)
+{
+	u32 *va;
+
+	if (unlikely(ring->tail + len > ring->effective_size)) {
+		memset(ring->vaddr + ring->tail, 0, ring->size - ring->tail);
+		ring->tail = 0;
+	}
+
+	va = ring->vaddr + ring->tail;
+	ring->tail = intel_ring_wrap(ring, ring->tail + len);
+
+	return va;
+}
+
+static inline u32 *ring_map_dw(struct intel_ring *ring, u32 len)
+{
+	return ring_map(ring, len * sizeof(u32));
+}
+
+static void ring_copy(struct intel_ring *dst,
+		      const struct intel_ring *src,
+		      u32 start, u32 end)
+{
+	unsigned int len;
+	void *out;
+
+	len = end - start;
+	if (end < start)
+		len += src->size;
+	out = ring_map(dst, len);
+
+	if (end < start) {
+		len = src->size - start;
+		memcpy(out, src->vaddr + start, len);
+		out += len;
+		start = 0;
+	}
+
+	memcpy(out, src->vaddr + start, end - start);
+}
+
+static void switch_context(struct intel_ring *ring, struct i915_request *rq)
+{
+}
+
+static struct i915_request *ring_submit(struct i915_request *rq)
+{
+	struct intel_ring *ring = rq->engine->legacy.ring;
+
+	__i915_request_submit(rq);
+
+	if (rq->engine->legacy.context != rq->context) {
+		switch_context(ring, rq);
+		set_current_context(&rq->engine->legacy.context, rq->context);
+	}
+
+	ring_copy(ring, rq->ring, rq->head, rq->tail);
+	return rq;
+}
+
+static struct i915_request **
+copy_active(struct i915_request **port, struct i915_request * const *active)
+{
+	while (*active)
+		*port++ = *active++;
+
+	return port;
+}
+
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
+static inline void write_tail(const struct intel_engine_cs *engine)
+{
+	ENGINE_WRITE(engine, RING_TAIL, engine->legacy.ring->tail);
+}
+
+static void dequeue(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const el = &engine->execlists;
+	struct i915_request ** const last_port = el->pending + el->port_mask;
+	struct i915_request **port, **first, *last;
+	struct i915_priolist *p;
+
+	first = copy_active(el->pending, el->active);
+	if (first > last_port)
+		return;
+
+	local_irq_disable();
+
+	last = NULL;
+	port = first;
+	spin_lock(&engine->active.lock);
+	for_each_priolist(p, &engine->active.queue) {
+		struct i915_request *rq, *rn;
+
+		priolist_for_each_request_safe(rq, rn, p) {
+			GEM_BUG_ON(rq == last);
+			if (last && rq->context != last->context) {
+				if (port == last_port)
+					goto done;
+
+				*port++ = i915_request_get(last);
+			}
+
+			last = ring_submit(rq);
+		}
+
+		i915_priolist_advance(&engine->active.queue, p);
+	}
+done:
+	spin_unlock(&engine->active.lock);
+
+	if (last) {
+		*port++ = i915_request_get(last);
+		*port = NULL;
+
+		WRITE_ONCE(el->active, el->pending);
+
+		copy_ports(el->inflight, el->pending, port - el->pending + 1);
+		while (port-- != first)
+			schedule_in(*port);
+
+		wmb(); /* paranoid flush of WCB before RING_TAIL write */
+		write_tail(engine);
+
+		WRITE_ONCE(el->active, el->inflight);
+		GEM_BUG_ON(!*el->active);
+	}
+
+	local_irq_enable(); /* flush irq_work *after* RING_TAIL write */
+}
+
+static void post_process_csb(struct i915_request **port,
+			     struct i915_request **last)
+{
+	while (port != last)
+		schedule_out(*port++);
+}
+
+static struct i915_request **
+process_csb(struct intel_engine_execlists *el, struct i915_request **inactive)
+{
+	struct i915_request *rq;
+
+	while ((rq = *el->active)) {
+		if (!__i915_request_is_complete(rq))
+			break;
+
+		*inactive++ = rq;
+		el->active++;
+	}
+
+	return inactive;
+}
+
+static void submission_tasklet(unsigned long data)
+{
+	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	struct i915_request *post[2 * EXECLIST_MAX_PORTS];
+	struct i915_request **inactive;
+
+	rcu_read_lock();
+	inactive = process_csb(&engine->execlists, post);
+	GEM_BUG_ON(inactive - post > ARRAY_SIZE(post));
+
+	if (!i915_sched_is_idle(&engine->active))
+		dequeue(engine);
+
+	post_process_csb(post, inactive);
+	rcu_read_unlock();
+}
+
+static void reset_prepare(struct intel_engine_cs *engine)
+{
+	GEM_TRACE("%s\n", engine->name);
+
+	__tasklet_disable_sync_once(&engine->active.tasklet);
+	GEM_BUG_ON(!reset_in_progress(engine));
+
+	intel_ring_submission_reset_prepare(engine);
+}
+
+static inline void clear_ports(struct i915_request **ports, int count)
+{
+	memset_p((void **)ports, NULL, count);
+}
+
+static struct i915_request **
+cancel_port_requests(struct intel_engine_execlists * const el,
+		     struct i915_request **inactive)
+{
+	struct i915_request * const *port;
+
+	clear_ports(el->pending, ARRAY_SIZE(el->pending));
+
+	/* Mark the end of active before we overwrite *active */
+	for (port = xchg(&el->active, el->pending); *port; port++)
+		*inactive++ = *port;
+	clear_ports(el->inflight, ARRAY_SIZE(el->inflight));
+
+	smp_wmb(); /* complete the seqlock for execlists_active() */
+	WRITE_ONCE(el->active, el->inflight);
+
+	return inactive;
+}
+
+static void __ring_rewind(struct intel_engine_cs *engine, bool stalled)
+{
+	struct i915_request *rq;
+	unsigned long flags;
+
+	rcu_read_lock();
+	spin_lock_irqsave(&engine->active.lock, flags);
+	rq = __intel_engine_rewind_requests(engine);
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+	if (rq && __i915_request_has_started(rq))
+		__i915_request_reset(rq, stalled);
+	rcu_read_unlock();
+}
+
+static void ring_reset_csb(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const el = &engine->execlists;
+	struct i915_request *post[2 * EXECLIST_MAX_PORTS];
+	struct i915_request **inactive;
+
+	rcu_read_lock();
+	inactive = cancel_port_requests(el, post);
+
+	/* Clear the global submission state, we will submit from scratch */
+	intel_ring_reset(engine->legacy.ring, 0);
+	set_current_context(&engine->legacy.context, NULL);
+
+	post_process_csb(post, inactive);
+	rcu_read_unlock();
+}
+
+static void ring_reset_rewind(struct intel_engine_cs *engine, bool stalled)
+{
+	ring_reset_csb(engine);
+	__ring_rewind(engine, stalled);
+}
+
+static void nop_submission_tasklet(unsigned long data)
+{
+}
+
+static void mark_eio(struct i915_request *rq)
+{
+	if (__i915_request_is_complete(rq))
+		return;
+
+	GEM_BUG_ON(i915_request_signaled(rq));
+
+	i915_request_set_error_once(rq, -EIO);
+	i915_request_mark_complete(rq);
+}
+
+static void ring_reset_cancel(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq, *rn;
+	struct i915_priolist *p;
+	unsigned long flags;
+
+	ring_reset_csb(engine);
+
+	rcu_read_lock();
+	spin_lock_irqsave(&engine->active.lock, flags);
+
+	/* Mark all submitted requests as skipped. */
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
+	intel_engine_signal_breadcrumbs(engine);
+
+	/* Flush the queued requests to the timeline list (for retiring). */
+	for_each_priolist(p, &engine->active.queue) {
+		priolist_for_each_request_safe(rq, rn, p) {
+			mark_eio(rq);
+			__i915_request_submit(rq);
+		}
+		i915_priolist_advance(&engine->active.queue, p);
+	}
+	GEM_BUG_ON(!i915_sched_is_idle(&engine->active));
+
+	/* Remaining _unready_ requests will be nop'ed when submitted */
+
+	GEM_BUG_ON(__tasklet_is_enabled(&engine->active.tasklet));
+	engine->active.tasklet.func = nop_submission_tasklet;
+
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+	rcu_read_unlock();
+}
+
+static void reset_finish(struct intel_engine_cs *engine)
+{
+	intel_ring_submission_reset_finish(engine);
+
+	if (__tasklet_enable(&engine->active.tasklet))
+		i915_sched_kick(&engine->active);
+}
+
+static void submission_park(struct intel_engine_cs *engine)
+{
+	/* drain the submit queue */
+	intel_breadcrumbs_unpin_irq(engine->breadcrumbs);
+	i915_sched_kick(&engine->active);
+}
+
+static void submission_unpark(struct intel_engine_cs *engine)
+{
+	intel_breadcrumbs_pin_irq(engine->breadcrumbs);
+}
+
+static void ring_context_destroy(struct kref *ref)
+{
+	struct intel_context *ce = container_of(ref, typeof(*ce), ref);
+
+	GEM_BUG_ON(intel_context_is_pinned(ce));
+
+	if (ce->state)
+		i915_vma_put(ce->state);
+	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
+		intel_ring_put(ce->ring);
+
+	intel_context_fini(ce);
+	intel_context_free(ce);
+}
+
+static int alloc_context_vma(struct intel_context *ce)
+
+{
+	struct intel_engine_cs *engine = ce->engine;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
+
+	obj = i915_gem_object_create_shmem(engine->i915, engine->context_size);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	/*
+	 * Try to make the context utilize L3 as well as LLC.
+	 *
+	 * On VLV we don't have L3 controls in the PTEs so we
+	 * shouldn't touch the cache level, especially as that
+	 * would make the object snooped which might have a
+	 * negative performance impact.
+	 *
+	 * Snooping is required on non-llc platforms in execlist
+	 * mode, but since all GGTT accesses use PAT entry 0 we
+	 * get snooping anyway regardless of cache_level.
+	 *
+	 * This is only applicable for Ivy Bridge devices since
+	 * later platforms don't have L3 control bits in the PTE.
+	 */
+	if (IS_IVYBRIDGE(engine->i915))
+		i915_gem_object_set_cache_coherency(obj, I915_CACHE_L3_LLC);
+
+	if (engine->default_state) {
+		void *vaddr;
+
+		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto err_obj;
+		}
+
+		shmem_read(engine->default_state, 0,
+			   vaddr, engine->context_size);
+		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
+
+		i915_gem_object_flush_map(obj);
+		i915_gem_object_unpin_map(obj);
+	}
+
+	vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	ce->state = vma;
+	return 0;
+
+err_obj:
+	i915_gem_object_put(obj);
+	return err;
+}
+
+static struct intel_timeline *pinned_timeline(struct intel_context *ce)
+{
+	struct intel_timeline *tl = fetch_and_zero(&ce->timeline);
+
+	return intel_timeline_create_from_engine(ce->engine,
+						 page_unmask_bits(tl));
+}
+
+static int alloc_timeline(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = ce->engine;
+	struct intel_timeline *tl;
+
+	if (unlikely(ce->timeline))
+		tl = pinned_timeline(ce);
+	else
+		tl = intel_timeline_create(engine->gt);
+	if (IS_ERR(tl))
+		return PTR_ERR(tl);
+
+	ce->timeline = tl;
+	return 0;
+}
+
+static int ring_context_alloc(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = ce->engine;
+	struct intel_ring *ring;
+	int err;
+
+	GEM_BUG_ON(ce->state);
+	if (engine->context_size) {
+		err = alloc_context_vma(ce);
+		if (err)
+			return err;
+	}
+
+	if (!page_mask_bits(ce->timeline)) {
+		err = alloc_timeline(ce);
+		if (err)
+			goto err_vma;
+	}
+
+	ring = intel_engine_create_ring(engine,
+					(unsigned long)ce->ring |
+					INTEL_RING_CREATE_INTERNAL);
+	if (IS_ERR(ring)) {
+		err = PTR_ERR(ring);
+		goto err_timeline;
+	}
+	ce->ring = ring;
+
+	return 0;
+
+err_timeline:
+	intel_timeline_put(ce->timeline);
+err_vma:
+	if (ce->state) {
+		i915_vma_put(ce->state);
+		ce->state = NULL;
+	}
+	return err;
+}
+
+static int ring_context_pre_pin(struct intel_context *ce,
+				struct i915_gem_ww_ctx *ww,
+				void **unused)
+{
+	return 0;
+}
+
+static int ring_context_pin(struct intel_context *ce, void *unused)
+{
+	return 0;
+}
+
+static void ring_context_unpin(struct intel_context *ce)
+{
+}
+
+static void ring_context_post_unpin(struct intel_context *ce)
+{
+}
+
+static void ring_context_reset(struct intel_context *ce)
+{
+	intel_ring_reset(ce->ring, 0);
+	clear_bit(CONTEXT_VALID_BIT, &ce->flags);
+}
+
+static const struct intel_context_ops ring_context_ops = {
+	.alloc = ring_context_alloc,
+
+	.pre_pin = ring_context_pre_pin,
+	.pin = ring_context_pin,
+	.unpin = ring_context_unpin,
+	.post_unpin = ring_context_post_unpin,
+
+	.enter = intel_context_enter_engine,
+	.exit = intel_context_exit_engine,
+
+	.reset = ring_context_reset,
+	.destroy = ring_context_destroy,
+};
+
+static int ring_request_alloc(struct i915_request *rq)
+{
+	int ret;
+
+	GEM_BUG_ON(!intel_context_is_pinned(rq->context));
+
+	/*
+	 * Flush enough space to reduce the likelihood of waiting after
+	 * we start building the request - in which case we will just
+	 * have to repeat work.
+	 */
+	rq->reserved_space += LEGACY_REQUEST_SIZE;
+
+	/* Unconditionally invalidate GPU caches and TLBs. */
+	ret = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+	if (ret)
+		return ret;
+
+	rq->reserved_space -= LEGACY_REQUEST_SIZE;
+	return 0;
+}
+
+static void set_default_submission(struct intel_engine_cs *engine)
+{
+	engine->submit_request = i915_request_enqueue;
+	engine->active.tasklet.func = submission_tasklet;
+}
+
+static void ring_release(struct intel_engine_cs *engine)
+{
+	intel_engine_cleanup_common(engine);
+
+	set_current_context(&engine->legacy.context, NULL);
+
+	intel_ring_unpin(engine->legacy.ring);
+	intel_ring_put(engine->legacy.ring);
+}
+
+static void setup_irq(struct intel_engine_cs *engine)
+{
+}
+
+static void setup_common(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *i915 = engine->i915;
+
+	/* gen8+ are only supported with execlists */
+	GEM_BUG_ON(INTEL_GEN(i915) >= 8);
+	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+
+	setup_irq(engine);
+
+	engine->park = submission_park;
+	engine->unpark = submission_unpark;
+
+	engine->resume = intel_ring_submission_resume;
+	engine->sanitize = intel_ring_submission_sanitize;
+
+	engine->reset.prepare = reset_prepare;
+	engine->reset.rewind = ring_reset_rewind;
+	engine->reset.cancel = ring_reset_cancel;
+	engine->reset.finish = reset_finish;
+
+	engine->cops = &ring_context_ops;
+	engine->request_alloc = ring_request_alloc;
+
+	engine->set_default_submission = set_default_submission;
+}
+
+static void setup_rcs(struct intel_engine_cs *engine)
+{
+}
+
+static void setup_vcs(struct intel_engine_cs *engine)
+{
+}
+
+static void setup_bcs(struct intel_engine_cs *engine)
+{
+}
+
+static void setup_vecs(struct intel_engine_cs *engine)
+{
+	GEM_BUG_ON(!IS_HASWELL(engine->i915));
+}
+
+static unsigned int global_ring_size(void)
+{
+	/* Enough space to hold 2 clients and the context switch */
+	return roundup_pow_of_two(EXECLIST_MAX_PORTS * SZ_16K + SZ_4K);
+}
+
+int intel_ring_scheduler_setup(struct intel_engine_cs *engine)
+{
+	struct intel_ring *ring;
+	int err;
+
+	GEM_BUG_ON(HAS_EXECLISTS(engine->i915));
+
+	tasklet_init(&engine->active.tasklet,
+		     submission_tasklet, (unsigned long)engine);
+
+	setup_common(engine);
+
+	switch (engine->class) {
+	case RENDER_CLASS:
+		setup_rcs(engine);
+		break;
+	case VIDEO_DECODE_CLASS:
+		setup_vcs(engine);
+		break;
+	case COPY_ENGINE_CLASS:
+		setup_bcs(engine);
+		break;
+	case VIDEO_ENHANCEMENT_CLASS:
+		setup_vecs(engine);
+		break;
+	default:
+		MISSING_CASE(engine->class);
+		return -ENODEV;
+	}
+
+	ring = intel_engine_create_ring(engine, global_ring_size());
+	if (IS_ERR(ring)) {
+		err = PTR_ERR(ring);
+		goto err;
+	}
+
+	err = intel_ring_pin(ring, NULL);
+	if (err)
+		goto err_ring;
+
+	GEM_BUG_ON(engine->legacy.ring);
+	engine->legacy.ring = ring;
+
+	engine->flags |= I915_ENGINE_HAS_SCHEDULER;
+	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
+
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = ring_release;
+	return 0;
+
+err_ring:
+	intel_ring_put(ring);
+err:
+	intel_engine_cleanup_common(engine);
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 4bc80c50dbe9..65f5b7866eec 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -37,6 +37,7 @@
 #include "intel_gt.h"
 #include "intel_reset.h"
 #include "intel_ring.h"
+#include "intel_ring_submission.h"
 #include "shmem_utils.h"
 
 /* Rough estimate of the typical request size, performing a flush,
@@ -217,7 +218,7 @@ static void set_pp_dir(struct intel_engine_cs *engine)
 	}
 }
 
-static int xcs_resume(struct intel_engine_cs *engine)
+int intel_ring_submission_resume(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_ring *ring = engine->legacy.ring;
@@ -329,7 +330,7 @@ static void sanitize_hwsp(struct intel_engine_cs *engine)
 		intel_timeline_reset_seqno(tl);
 }
 
-static void xcs_sanitize(struct intel_engine_cs *engine)
+void intel_ring_submission_sanitize(struct intel_engine_cs *engine)
 {
 	/*
 	 * Poison residual state on resume, in case the suspend didn't!
@@ -354,7 +355,7 @@ static void xcs_sanitize(struct intel_engine_cs *engine)
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
 }
 
-static void reset_prepare(struct intel_engine_cs *engine)
+void intel_ring_submission_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_uncore *uncore = engine->uncore;
 	const u32 base = engine->mmio_base;
@@ -461,7 +462,7 @@ static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
-static void reset_finish(struct intel_engine_cs *engine)
+void intel_ring_submission_reset_finish(struct intel_engine_cs *engine)
 {
 }
 
@@ -1102,13 +1103,13 @@ static void setup_common(struct intel_engine_cs *engine)
 
 	setup_irq(engine);
 
-	engine->resume = xcs_resume;
-	engine->sanitize = xcs_sanitize;
+	engine->resume = intel_ring_submission_resume;
+	engine->sanitize = intel_ring_submission_sanitize;
 
-	engine->reset.prepare = reset_prepare;
+	engine->reset.prepare = intel_ring_submission_reset_prepare;
 	engine->reset.rewind = reset_rewind;
 	engine->reset.cancel = reset_cancel;
-	engine->reset.finish = reset_finish;
+	engine->reset.finish = intel_ring_submission_reset_finish;
 
 	engine->cops = &ring_context_ops;
 	engine->request_alloc = ring_request_alloc;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.h b/drivers/gpu/drm/i915/gt/intel_ring_submission.h
new file mode 100644
index 000000000000..59a43c221748
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_RING_SUBMISSION_H__
+#define __INTEL_RING_SUBMISSION_H__
+
+struct intel_engine_cs;
+
+void intel_ring_submission_reset_prepare(struct intel_engine_cs *engine);
+void intel_ring_submission_reset_finish(struct intel_engine_cs *engine);
+
+int intel_ring_submission_resume(struct intel_engine_cs *engine);
+void intel_ring_submission_sanitize(struct intel_engine_cs *engine);
+
+#endif /* __INTEL_RING_SUBMISSION_H__ */
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 59/62] drm/i915/gt: Enable busy-stats for ring-scheduler

[Chris Wilson]

Couple up the context in/out accounting to record how long each engine
is busy handling requests. This is exposed to userspace for more accurate
measurements, and also enables our soft-rps timer.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_ring_scheduler.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
index 338d847445ca..b95f4ad4bd00 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
@@ -11,6 +11,7 @@
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
+#include "intel_engine_stats.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
@@ -63,6 +64,8 @@ static struct intel_engine_cs *__schedule_in(struct i915_request *rq)
 	if (engine->fw_domain && !engine->fw_active++)
 		intel_uncore_forcewake_get(engine->uncore, engine->fw_domain);
 
+	intel_engine_context_in(engine);
+
 	CE_TRACE(ce, "schedule-in\n");
 
 	return engine;
@@ -96,6 +99,8 @@ static void __schedule_out(struct i915_request *rq)
 	else
 		i915_request_update_deadline(list_next_entry(rq, link));
 
+	intel_engine_context_out(engine);
+
 	if (engine->fw_domain && !--engine->fw_active)
 		intel_uncore_forcewake_put(engine->uncore, engine->fw_domain);
 	intel_gt_pm_put_async(engine->gt);
@@ -755,6 +760,7 @@ int intel_ring_scheduler_setup(struct intel_engine_cs *engine)
 
 	engine->flags |= I915_ENGINE_HAS_SCHEDULER;
 	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
+	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
 
 	/* Finally, take ownership and responsibility for cleanup! */
 	engine->release = ring_release;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 60/62] drm/i915/gt: Implement ring scheduler for gen6/7

[Chris Wilson]

A key prolem with legacy ring buffer submission is that it is an inheret
FIFO queue across all clients; if one blocks, they all block. A
scheduler allows us to avoid that limitation, and ensures that all
clients can submit in parallel, removing the resource contention of the
global ringbuffer.

Having built the ring scheduler infrastructure over top of the global
ringbuffer submission, we now need to provide the HW knowledge required
to build command packets and implement context switching.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gt/intel_ring_scheduler.c    | 447 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h               |  10 +
 2 files changed, 454 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
index b95f4ad4bd00..91ac415a3f82 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_scheduler.c
@@ -7,6 +7,10 @@
 
 #include <drm/i915_drm.h>
 
+#include "gen2_engine_cs.h"
+#include "gen6_engine_cs.h"
+#include "gen6_ppgtt.h"
+#include "gen7_renderclear.h"
 #include "i915_drv.h"
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
@@ -164,8 +168,263 @@ static void ring_copy(struct intel_ring *dst,
 	memcpy(out, src->vaddr + start, end - start);
 }
 
+static void mi_set_context(struct intel_ring *ring,
+			   struct intel_engine_cs *engine,
+			   struct intel_context *ce,
+			   u32 flags)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	enum intel_engine_id id;
+	const int num_engines =
+		IS_HASWELL(i915) ? engine->gt->info.num_engines - 1 : 0;
+	int len;
+	u32 *cs;
+
+	len = 4;
+	if (IS_GEN(i915, 7))
+		len += 2 + (num_engines ? 4 * num_engines + 6 : 0);
+	else if (IS_GEN(i915, 5))
+		len += 2;
+
+	cs = ring_map_dw(ring, len);
+
+	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
+	if (IS_GEN(i915, 7)) {
+		*cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+		if (num_engines) {
+			struct intel_engine_cs *signaller;
+
+			*cs++ = MI_LOAD_REGISTER_IMM(num_engines);
+			for_each_engine(signaller, engine->gt, id) {
+				if (signaller == engine)
+					continue;
+
+				*cs++ = i915_mmio_reg_offset(
+					   RING_PSMI_CTL(signaller->mmio_base));
+				*cs++ = _MASKED_BIT_ENABLE(
+						GEN6_PSMI_SLEEP_MSG_DISABLE);
+			}
+		}
+	} else if (IS_GEN(i915, 5)) {
+		/*
+		 * This w/a is only listed for pre-production ilk a/b steppings,
+		 * but is also mentioned for programming the powerctx. To be
+		 * safe, just apply the workaround; we do not use SyncFlush so
+		 * this should never take effect and so be a no-op!
+		 */
+		*cs++ = MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN;
+	}
+
+	*cs++ = MI_NOOP;
+	*cs++ = MI_SET_CONTEXT;
+	*cs++ = i915_ggtt_offset(ce->state) | flags;
+	/*
+	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
+	 * WaMiSetContext_Hang:snb,ivb,vlv
+	 */
+	*cs++ = MI_NOOP;
+
+	if (IS_GEN(i915, 7)) {
+		if (num_engines) {
+			struct intel_engine_cs *signaller;
+			i915_reg_t last_reg = {}; /* keep gcc quiet */
+
+			*cs++ = MI_LOAD_REGISTER_IMM(num_engines);
+			for_each_engine(signaller, engine->gt, id) {
+				if (signaller == engine)
+					continue;
+
+				last_reg = RING_PSMI_CTL(signaller->mmio_base);
+				*cs++ = i915_mmio_reg_offset(last_reg);
+				*cs++ = _MASKED_BIT_DISABLE(
+						GEN6_PSMI_SLEEP_MSG_DISABLE);
+			}
+
+			/* Insert a delay before the next switch! */
+			*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+			*cs++ = i915_mmio_reg_offset(last_reg);
+			*cs++ = intel_gt_scratch_offset(engine->gt,
+							INTEL_GT_SCRATCH_FIELD_DEFAULT);
+			*cs++ = MI_NOOP;
+		}
+		*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
+	} else if (IS_GEN(i915, 5)) {
+		*cs++ = MI_SUSPEND_FLUSH;
+	}
+}
+
+static struct i915_address_space *vm_alias(struct i915_address_space *vm)
+{
+	if (i915_is_ggtt(vm))
+		vm = &i915_vm_to_ggtt(vm)->alias->vm;
+
+	return vm;
+}
+
+static u32 pp_dir(const struct i915_ppgtt *ppgtt)
+{
+	return container_of(ppgtt, const struct gen6_ppgtt, base)->pp_dir;
+}
+
+static void load_pd_dir(struct intel_ring *ring,
+			struct intel_engine_cs *engine,
+			const struct i915_ppgtt *ppgtt)
+{
+	u32 *cs = ring_map_dw(ring, 10);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine->mmio_base));
+	*cs++ = PP_DIR_DCLV_2G;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
+	*cs++ = pp_dir(ppgtt);
+
+	/* Stall until the page table load is complete? */
+	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
+	*cs++ = intel_gt_scratch_offset(engine->gt,
+					INTEL_GT_SCRATCH_FIELD_DEFAULT);
+	*cs++ = MI_NOOP;
+}
+
+static struct i915_address_space *current_vm(struct intel_engine_cs *engine)
+{
+	struct intel_context *old = engine->legacy.context;
+
+	return old ? vm_alias(old->vm) : NULL;
+}
+
+static void gen6_emit_invalidate_rcs(struct intel_ring *ring,
+				     struct intel_engine_cs *engine)
+{
+	u32 addr, flags;
+	u32 *cs;
+
+	addr = intel_gt_scratch_offset(engine->gt,
+				       INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
+
+	flags = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
+	flags |= PIPE_CONTROL_TLB_INVALIDATE;
+
+	if (INTEL_GEN(engine->i915) >= 7)
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+	else
+		addr |= PIPE_CONTROL_GLOBAL_GTT;
+
+	cs = ring_map_dw(ring, 4);
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = flags;
+	*cs++ = addr;
+	*cs++ = 0;
+}
+
+static struct i915_address_space *
+clear_residuals(struct intel_ring *ring, struct intel_engine_cs *engine)
+{
+	struct intel_context *ce = engine->kernel_context;
+	struct i915_address_space *vm = vm_alias(engine->gt->vm);
+	u32 flags;
+
+	if (vm != current_vm(engine))
+		load_pd_dir(ring, engine, i915_vm_to_ppgtt(vm));
+
+	if (ce->state)
+		mi_set_context(ring, engine, ce,
+			       MI_MM_SPACE_GTT | MI_RESTORE_INHIBIT);
+
+	if (IS_HASWELL(engine->i915))
+		flags = MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW;
+	else
+		flags = MI_BATCH_NON_SECURE_I965;
+
+	__gen6_emit_bb_start(ring_map_dw(ring, 2),
+			     engine->wa_ctx.vma->node.start, flags);
+
+	return vm;
+}
+
+static void remap_l3_slice(struct intel_ring *ring,
+			   struct intel_engine_cs *engine,
+			   int slice)
+{
+	u32 *cs, *remap_info = engine->i915->l3_parity.remap_info[slice];
+	int i;
+
+	if (!remap_info)
+		return;
+
+	/*
+	 * Note: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time.
+	 */
+	cs = ring_map_dw(ring, GEN7_L3LOG_SIZE / 4 * 2 + 2);
+	*cs++ = MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE / 4);
+	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
+		*cs++ = i915_mmio_reg_offset(GEN7_L3LOG(slice, i));
+		*cs++ = remap_info[i];
+	}
+	*cs++ = MI_NOOP;
+}
+
+static void remap_l3(struct intel_ring *ring,
+		     struct intel_engine_cs *engine,
+		     struct intel_context *ce)
+{
+	struct i915_gem_context *ctx =
+		rcu_dereference_protected(ce->gem_context, true);
+	int bit, idx = -1;
+
+	if (!ctx || !ctx->remap_slice)
+		return;
+
+	do {
+		bit = ffs(ctx->remap_slice);
+		remap_l3_slice(ring, engine, idx += bit);
+	} while (ctx->remap_slice >>= bit);
+}
+
 static void switch_context(struct intel_ring *ring, struct i915_request *rq)
 {
+	struct intel_engine_cs *engine = rq->engine;
+	struct i915_address_space *cvm = current_vm(engine);
+	struct intel_context *ce = rq->context;
+	struct i915_address_space *vm;
+
+	if (engine->wa_ctx.vma && ce != engine->kernel_context) {
+		if (engine->wa_ctx.vma->private != ce) {
+			cvm = clear_residuals(ring, engine);
+			intel_context_put(engine->wa_ctx.vma->private);
+			engine->wa_ctx.vma->private = intel_context_get(ce);
+		}
+	}
+
+	vm = vm_alias(ce->vm);
+	if (vm != cvm)
+		load_pd_dir(ring, engine, i915_vm_to_ppgtt(vm));
+
+	if (ce->state) {
+		u32 flags;
+
+		GEM_BUG_ON(engine->id != RCS0);
+
+		/* For resource streamer on HSW+ and power context elsewhere */
+		BUILD_BUG_ON(HSW_MI_RS_SAVE_STATE_EN != MI_SAVE_EXT_STATE_EN);
+		BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
+
+		flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
+		if (test_bit(CONTEXT_VALID_BIT, &ce->flags)) {
+			gen6_emit_invalidate_rcs(ring, engine);
+			flags |= MI_RESTORE_EXT_STATE_EN;
+		} else {
+			flags |= MI_RESTORE_INHIBIT;
+		}
+
+		mi_set_context(ring, engine, ce, flags);
+	}
+
+	remap_l3(ring, engine, ce);
 }
 
 static struct i915_request *ring_submit(struct i915_request *rq)
@@ -205,6 +464,36 @@ static inline void write_tail(const struct intel_engine_cs *engine)
 	ENGINE_WRITE(engine, RING_TAIL, engine->legacy.ring->tail);
 }
 
+static void wa_write_tail(const struct intel_engine_cs *engine)
+{
+	const i915_reg_t psmi = RING_PSMI_CTL(engine->mmio_base);
+	struct intel_uncore *uncore = engine->uncore;
+
+	intel_uncore_write_fw(uncore, psmi,
+			      _MASKED_BIT_ENABLE(PSMI_SLEEP_MSG_DISABLE));
+
+	/* Clear the context id. Here be magic! */
+	intel_uncore_write64_fw(uncore, RING_RNCID(engine->mmio_base), 0x0);
+
+	/* Wait for the ring not to be idle, i.e. for it to wake up. */
+	if (__intel_wait_for_register_fw(uncore, psmi,
+					 PSMI_SLEEP_INDICATOR, 0,
+					 1000, 0, NULL))
+		drm_err(&uncore->i915->drm,
+			"timed out waiting for %s to wake up\n",
+			engine->name);
+
+	/* Now that the ring is fully powered up, update the tail */
+	write_tail(engine);
+
+	/*
+	 * Let the ring send IDLE messages to the GT again,
+	 * and so let it sleep to conserve power when idle.
+	 */
+	intel_uncore_write_fw(uncore, psmi,
+			      _MASKED_BIT_DISABLE(PSMI_SLEEP_MSG_DISABLE));
+}
+
 static void dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const el = &engine->execlists;
@@ -252,7 +541,10 @@ static void dequeue(struct intel_engine_cs *engine)
 			schedule_in(*port);
 
 		wmb(); /* paranoid flush of WCB before RING_TAIL write */
-		write_tail(engine);
+		if (!engine->fw_active)
+			write_tail(engine);
+		else
+			wa_write_tail(engine);
 
 		WRITE_ONCE(el->active, el->inflight);
 		GEM_BUG_ON(!*el->active);
@@ -442,6 +734,33 @@ static void submission_unpark(struct intel_engine_cs *engine)
 	intel_breadcrumbs_pin_irq(engine->breadcrumbs);
 }
 
+static int gen6_emit_init_breadcrumb(struct i915_request *rq)
+{
+	struct intel_timeline *tl = i915_request_timeline(rq);
+	u32 *cs;
+
+	GEM_BUG_ON(i915_request_has_initial_breadcrumb(rq));
+	if (!intel_timeline_has_initial_breadcrumb(tl))
+		return 0;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = 0;
+	*cs++ = __i915_request_hwsp_offset(rq);
+	*cs++ = rq->fence.seqno - 1;
+
+	intel_ring_advance(rq, cs);
+
+	/* Record the updated position of the request's payload */
+	rq->infix = intel_ring_offset(rq, cs);
+
+	__set_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
+	return 0;
+}
+
 static void ring_context_destroy(struct kref *ref)
 {
 	struct intel_context *ce = container_of(ref, typeof(*ce), ref);
@@ -586,7 +905,14 @@ static int ring_context_pre_pin(struct intel_context *ce,
 				struct i915_gem_ww_ctx *ww,
 				void **unused)
 {
-	return 0;
+	struct i915_address_space *vm;
+	int err = 0;
+
+	vm = vm_alias(ce->vm);
+	if (vm)
+		err = gen6_ppgtt_pin(i915_vm_to_ppgtt((vm)), ww);
+
+	return err;
 }
 
 static int ring_context_pin(struct intel_context *ce, void *unused)
@@ -594,12 +920,22 @@ static int ring_context_pin(struct intel_context *ce, void *unused)
 	return 0;
 }
 
+static void __context_unpin_ppgtt(struct intel_context *ce)
+{
+	struct i915_address_space *vm;
+
+	vm = vm_alias(ce->vm);
+	if (vm)
+		gen6_ppgtt_unpin(i915_vm_to_ppgtt(vm));
+}
+
 static void ring_context_unpin(struct intel_context *ce)
 {
 }
 
 static void ring_context_post_unpin(struct intel_context *ce)
 {
+	__context_unpin_ppgtt(ce);
 }
 
 static void ring_context_reset(struct intel_context *ce)
@@ -657,12 +993,19 @@ static void ring_release(struct intel_engine_cs *engine)
 
 	set_current_context(&engine->legacy.context, NULL);
 
+	if (engine->wa_ctx.vma) {
+		intel_context_put(engine->wa_ctx.vma->private);
+		i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0);
+	}
+
 	intel_ring_unpin(engine->legacy.ring);
 	intel_ring_put(engine->legacy.ring);
 }
 
 static void setup_irq(struct intel_engine_cs *engine)
 {
+	engine->irq_enable = gen6_irq_enable;
+	engine->irq_disable = gen6_irq_disable;
 }
 
 static void setup_common(struct intel_engine_cs *engine)
@@ -671,7 +1014,7 @@ static void setup_common(struct intel_engine_cs *engine)
 
 	/* gen8+ are only supported with execlists */
 	GEM_BUG_ON(INTEL_GEN(i915) >= 8);
-	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+	GEM_BUG_ON(INTEL_GEN(i915) < 6);
 
 	setup_irq(engine);
 
@@ -689,24 +1032,62 @@ static void setup_common(struct intel_engine_cs *engine)
 	engine->cops = &ring_context_ops;
 	engine->request_alloc = ring_request_alloc;
 
+	engine->emit_init_breadcrumb = gen6_emit_init_breadcrumb;
+	if (INTEL_GEN(i915) >= 7)
+		engine->emit_fini_breadcrumb = gen7_emit_breadcrumb_xcs;
+	else if (INTEL_GEN(i915) >= 6)
+		engine->emit_fini_breadcrumb = gen6_emit_breadcrumb_xcs;
+	else
+		engine->emit_fini_breadcrumb = gen3_emit_breadcrumb;
+
 	engine->set_default_submission = set_default_submission;
+
+	engine->emit_bb_start = gen6_emit_bb_start;
 }
 
 static void setup_rcs(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
+	if (HAS_L3_DPF(i915))
+		engine->irq_keep_mask = GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+
+	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
+
+	if (INTEL_GEN(i915) >= 7) {
+		engine->emit_flush = gen7_emit_flush_rcs;
+		engine->emit_fini_breadcrumb = gen7_emit_breadcrumb_rcs;
+		if (IS_HASWELL(i915))
+			engine->emit_bb_start = hsw_emit_bb_start;
+	} else {
+		engine->emit_flush = gen6_emit_flush_rcs;
+		engine->emit_fini_breadcrumb = gen6_emit_breadcrumb_rcs;
+	}
 }
 
 static void setup_vcs(struct intel_engine_cs *engine)
 {
+	engine->emit_flush = gen6_emit_flush_vcs;
+	engine->irq_enable_mask = GT_BSD_USER_INTERRUPT;
+
+	if (IS_GEN(engine->i915, 6))
+		engine->fw_domain = FORCEWAKE_ALL;
 }
 
 static void setup_bcs(struct intel_engine_cs *engine)
 {
+	engine->emit_flush = gen6_emit_flush_xcs;
+	engine->irq_enable_mask = GT_BLT_USER_INTERRUPT;
 }
 
 static void setup_vecs(struct intel_engine_cs *engine)
 {
 	GEM_BUG_ON(!IS_HASWELL(engine->i915));
+
+	engine->emit_flush = gen6_emit_flush_xcs;
+	engine->irq_enable_mask = PM_VEBOX_USER_INTERRUPT;
+	engine->irq_enable = hsw_irq_enable_vecs;
+	engine->irq_disable = hsw_irq_disable_vecs;
 }
 
 static unsigned int global_ring_size(void)
@@ -715,6 +1096,58 @@ static unsigned int global_ring_size(void)
 	return roundup_pow_of_two(EXECLIST_MAX_PORTS * SZ_16K + SZ_4K);
 }
 
+static int gen7_ctx_switch_bb_init(struct intel_engine_cs *engine)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int size;
+	int err;
+
+	size = gen7_setup_clear_gpr_bb(engine, NULL /* probe size */);
+	if (size <= 0)
+		return size;
+
+	size = ALIGN(size, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(engine->i915, size);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	vma = i915_vma_instance(obj, engine->gt->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	vma->private = intel_context_create(engine); /* dummy residuals */
+	if (IS_ERR(vma->private)) {
+		err = PTR_ERR(vma->private);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+	if (err)
+		goto err_private;
+
+	err = i915_vma_sync(vma);
+	if (err)
+		goto err_unpin;
+
+	size = gen7_setup_clear_gpr_bb(engine, vma);
+	if (err)
+		goto err_unpin;
+
+	engine->wa_ctx.vma = vma;
+	return 0;
+
+err_unpin:
+	i915_vma_unpin(vma);
+err_private:
+	intel_context_put(vma->private);
+err_obj:
+	i915_gem_object_put(obj);
+	return err;
+}
+
 int intel_ring_scheduler_setup(struct intel_engine_cs *engine)
 {
 	struct intel_ring *ring;
@@ -758,6 +1191,12 @@ int intel_ring_scheduler_setup(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->legacy.ring);
 	engine->legacy.ring = ring;
 
+	if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) {
+		err = gen7_ctx_switch_bb_init(engine);
+		if (err)
+			goto err_ring_unpin;
+	}
+
 	engine->flags |= I915_ENGINE_HAS_SCHEDULER;
 	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
 	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
@@ -766,6 +1205,8 @@ int intel_ring_scheduler_setup(struct intel_engine_cs *engine)
 	engine->release = ring_release;
 	return 0;
 
+err_ring_unpin:
+	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_put(ring);
 err:
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0023c023f472..8d38e92d05db 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2529,7 +2529,16 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
 #define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC	INVALID_MMIO_REG
+
 #define RING_PSMI_CTL(base)	_MMIO((base) + 0x50)
+#define   PSMI_SLEEP_MSG_DISABLE		REG_BIT(0)
+#define   PSMI_SLEEP_FLUSH_DISABLE		REG_BIT(2)
+#define   PSMI_SLEEP_INDICATOR			REG_BIT(3)
+#define   PSMI_GO_INDICATOR			REG_BIT(4)
+#define   GEN12_PSMI_WAIT_FOR_EVENT_POWER_DOWN_DISABLE REG_BIT(7)
+#define   GEN8_PSMI_FF_DOP_CLOCK_GATE_DISABLE	REG_BIT(10)
+#define   GEN8_PSMI_RC_SEMA_IDLE_MSG_DISABLE	REG_BIT(12)
+
 #define RING_MAX_IDLE(base)	_MMIO((base) + 0x54)
 #define RING_HWS_PGA(base)	_MMIO((base) + 0x80)
 #define RING_ID(base)		_MMIO((base) + 0x8c)
@@ -2539,6 +2548,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RESET_CTL_READY_TO_RESET REG_BIT(1)
 #define   RESET_CTL_REQUEST_RESET  REG_BIT(0)
 
+#define RING_RNCID(base)	_MMIO((base) + 0x198)
 #define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c)
 
 #define HSW_GTT_CACHE_EN	_MMIO(0x4024)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 61/62] drm/i915/gt: Enable ring scheduling for gen6/7

[Chris Wilson]

Switch over from FIFO global submission to the priority-sorted
topographical scheduler. At the cost of more busy work on the CPU to
keep the GPU supplied with the next packet of requests, this allows us
to reorder requests around submission stalls.

This also enables the timer based RPS, with the exception of Valleyview
whose PCU doesn't take kindly to our interference.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c             | 2 ++
 drivers/gpu/drm/i915/gt/intel_rps.c                   | 6 ++----
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index d3f87dc4eda3..2246b5c308dc 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -94,7 +94,7 @@ static int live_nop_switch(void *arg)
 			rq = i915_request_get(this);
 			i915_request_add(this);
 		}
-		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		if (i915_request_wait(rq, 0, HZ) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
 			intel_gt_set_wedged(&i915->gt);
 			i915_request_put(rq);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 916f4b8ce4c0..2589c8afd847 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -881,6 +881,8 @@ int intel_engines_init(struct intel_gt *gt)
 
 	if (HAS_EXECLISTS(gt->i915))
 		setup = intel_execlists_submission_setup;
+	else if (INTEL_GEN(gt->i915) >= 6)
+		setup = intel_ring_scheduler_setup;
 	else
 		setup = intel_ring_submission_setup;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 2b443b735a98..2963ab5a86ff 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1078,9 +1078,7 @@ static bool gen6_rps_enable(struct intel_rps *rps)
 	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 50000);
 	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
 
-	rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
-			  GEN6_PM_RP_DOWN_THRESHOLD |
-			  GEN6_PM_RP_DOWN_TIMEOUT);
+	rps->pm_events = GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD;
 
 	return rps_reset(rps);
 }
@@ -1388,7 +1386,7 @@ void intel_rps_enable(struct intel_rps *rps)
 	GEM_BUG_ON(rps->efficient_freq < rps->min_freq);
 	GEM_BUG_ON(rps->efficient_freq > rps->max_freq);
 
-	if (has_busy_stats(rps))
+	if (has_busy_stats(rps) && !IS_VALLEYVIEW(i915))
 		intel_rps_set_timer(rps);
 	else if (INTEL_GEN(i915) >= 6)
 		intel_rps_set_interrupts(rps);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 62/62] drm/i915: Mark up protected uses of 'i915_request_completed'

[Chris Wilson]

When we know that we are inside the timeline mutex, or inside the
submission flow (under active.lock or the holder's rcu lock), we know
that the rq->hwsp is stable and we can use the simpler direct version.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c     |  2 +-
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c     |  4 ++--
 drivers/gpu/drm/i915/gt/intel_engine_cs.c       |  2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c           |  3 +--
 drivers/gpu/drm/i915/gt/intel_ring_submission.c |  4 +++-
 drivers/gpu/drm/i915/gt/intel_timeline.c        |  4 ++--
 drivers/gpu/drm/i915/i915_request.c             | 15 +++++++--------
 7 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 52711aaf71e1..4c1643d11d38 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -408,7 +408,7 @@ __active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 	}
 
 	if (i915_request_is_active(rq)) {
-		if (!i915_request_completed(rq))
+		if (!__i915_request_is_complete(rq))
 			*active = locked;
 		ret = true;
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 824621fcfaa4..dc76b05991e7 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -508,8 +508,8 @@ static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p)
 		list_for_each_entry_rcu(rq, &ce->signals, signal_link)
 			drm_printf(p, "\t[%llx:%llx%s] @ %dms\n",
 				   rq->fence.context, rq->fence.seqno,
-				   i915_request_completed(rq) ? "!" :
-				   i915_request_started(rq) ? "*" :
+				   __i915_request_is_complete(rq) ? "!" :
+				   __i915_request_has_started(rq) ? "*" :
 				   "",
 				   jiffies_to_msecs(jiffies - rq->emitted_jiffies));
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 2589c8afd847..baaf3e8ea70c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1758,7 +1758,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
 		struct intel_timeline *tl = request->context->timeline;
 
 		list_for_each_entry_from_reverse(request, &tl->requests, link) {
-			if (i915_request_completed(request))
+			if (__i915_request_is_complete(request))
 				break;
 
 			active = request;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b85b6f3dcd60..e0b4291393ec 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -151,8 +151,7 @@ static void mark_innocent(struct i915_request *rq)
 void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
 	RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
-
-	GEM_BUG_ON(i915_request_completed(rq));
+	GEM_BUG_ON(__i915_request_is_complete(rq));
 
 	rcu_read_lock(); /* protect the GEM context */
 	if (guilty) {
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 65f5b7866eec..19d7edda2a48 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -405,12 +405,14 @@ static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 
 	rq = NULL;
 	spin_lock_irqsave(&engine->active.lock, flags);
+	rcu_read_lock();
 	list_for_each_entry(pos, &engine->active.requests, sched.link) {
-		if (!i915_request_completed(pos)) {
+		if (!__i915_request_is_complete(pos)) {
 			rq = pos;
 			break;
 		}
 	}
+	rcu_read_unlock();
 
 	/*
 	 * The guilty request will get skipped on a hung engine.
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index c49d088b3541..882b7916bb4a 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -594,11 +594,11 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 
 	rcu_read_lock();
 	cl = rcu_dereference(from->hwsp_cacheline);
-	if (i915_request_completed(from)) /* confirm cacheline is valid */
+	if (i915_request_signaled(from)) /* confirm cacheline is valid */
 		goto unlock;
 	if (unlikely(!i915_active_acquire_if_busy(&cl->active)))
 		goto unlock; /* seqno wrapped and completed! */
-	if (unlikely(i915_request_completed(from)))
+	if (unlikely(__i915_request_is_complete(from)))
 		goto release;
 	rcu_read_unlock();
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8fd69631b1b6..7179efc58640 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -276,7 +276,7 @@ static void remove_from_engine(struct i915_request *rq)
 
 bool i915_request_retire(struct i915_request *rq)
 {
-	if (!i915_request_completed(rq))
+	if (!__i915_request_is_complete(rq))
 		return false;
 
 	RQ_TRACE(rq, "\n");
@@ -342,8 +342,7 @@ void i915_request_retire_upto(struct i915_request *rq)
 	struct i915_request *tmp;
 
 	RQ_TRACE(rq, "\n");
-
-	GEM_BUG_ON(!i915_request_completed(rq));
+	GEM_BUG_ON(!__i915_request_is_complete(rq));
 
 	do {
 		tmp = list_first_entry(&tl->requests, typeof(*tmp), link);
@@ -539,7 +538,7 @@ bool __i915_request_submit(struct i915_request *request)
 	 * dropped upon retiring. (Otherwise if resubmit a *retired*
 	 * request, this would be a horrible use-after-free.)
 	 */
-	if (i915_request_completed(request)) {
+	if (__i915_request_is_complete(request)) {
 		list_del_init(&request->sched.link);
 		goto active;
 	}
@@ -645,7 +644,7 @@ void __i915_request_unsubmit(struct i915_request *request)
 		i915_request_cancel_breadcrumb(request);
 
 	/* We've already spun, don't charge on resubmitting. */
-	if (request->sched.semaphores && i915_request_started(request))
+	if (request->sched.semaphores && __i915_request_has_started(request))
 		request->sched.semaphores = 0;
 
 	/*
@@ -858,7 +857,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	RCU_INIT_POINTER(rq->timeline, tl);
 	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
-	GEM_BUG_ON(i915_request_completed(rq));
+	GEM_BUG_ON(__i915_request_is_complete(rq));
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
@@ -979,7 +978,7 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		struct i915_request *prev;
 
 		/* Confirm signal has not been retired, the link is valid */
-		if (unlikely(i915_request_started(signal)))
+		if (unlikely(__i915_request_has_started(signal)))
 			break;
 
 		/* Is signal the earliest request on its timeline? */
@@ -1521,7 +1520,7 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	 */
 	prev = to_request(__i915_active_fence_set(&timeline->last_request,
 						  &rq->fence));
-	if (prev && !i915_request_completed(prev)) {
+	if (prev && !__i915_request_is_complete(prev)) {
 		/*
 		 * The requests are supposed to be kept in order. However,
 		 * we need to be wary in case the timeline->last_request
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Patchwork]

== Series Details ==

Series: series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet
URL   : https://patchwork.freedesktop.org/series/85184/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
11ff28d8f6d3 drm/i915/gt: Replace direct submit with direct call to tasklet
5e8040a840bc drm/i915/gt: Use virtual_engine during execlists_dequeue
2a533c166dca drm/i915/gt: Decouple inflight virtual engines
e67f6b85391f drm/i915/gt: Defer schedule_out until after the next dequeue
4cf4ad3a878b drm/i915/gt: Remove virtual breadcrumb before transfer
5fcc092512e9 drm/i915/gt: Shrink the critical section for irq signaling
535418e46847 drm/i915/gt: Resubmit the virtual engine on schedule-out
fd614fdd85e4 drm/i915/gt: Simplify virtual engine handling for execlists_hold()
f1bc3696961a drm/i915/gt: ce->inflight updates are now serialised
ec26a9257ebb drm/i915/selftests: Confirm CS_TIMESTAMP / CTX_TIMESTAMP share a clock
-:91: WARNING:MEMORY_BARRIER: memory barrier without comment
#91: FILE: drivers/gpu/drm/i915/gt/selftest_engine_pm.c:69:
+	wmb();

-:139: CHECK:USLEEP_RANGE: usleep_range is preferred over udelay; see Documentation/timers/timers-howto.rst
#139: FILE: drivers/gpu/drm/i915/gt/selftest_engine_pm.c:117:
+	udelay(100);

total: 0 errors, 1 warnings, 1 checks, 223 lines checked
9b6e9d3440df drm/i915/gt: Consolidate the CS timestamp clocks
b45af9eeb47e drm/i915: Drop i915_request.lock serialisation around await_start
9214c519cc1b drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
cad1adec9393 drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
8f7854833c40 drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
f3eb0734aa17 drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
d4ab3dd23cec drm/i915/gt: Drop atomic for engine->fw_active tracking
761f42694117 drm/i915/gt: Extract busy-stats for ring-scheduler
-:12: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#12: 
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 95 lines checked
1ad786b3dafd drm/i915/gt: Convert stats.active to plain unsigned int
3e32d2a70598 drm/i915/gt: Refactor heartbeat request construction and submission
915e2215b56c drm/i915/gt: Do not suspend bonded requests if one hangs
7f7cfa94210d drm/i915/gt: Remove timeslice suppression
43182c3b43b9 drm/i915: Strip out internal priorities
0fc466b30b40 drm/i915: Remove I915_USER_PRIORITY_SHIFT
b6680c4d807c drm/i915: Replace engine->schedule() with a known request operation
d23c18eec355 drm/i915: Teach the i915_dependency to use a double-lock
660e34df14a0 drm/i915: Restructure priority inheritance
5274e559d740 drm/i915/selftests: Measure set-priority duration
-:52: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#52: 
new file mode 100644

-:434: WARNING:LINE_SPACING: Missing a blank line after declarations
#434: FILE: drivers/gpu/drm/i915/selftests/i915_scheduler.c:378:
+	struct igt_spinner spin;
+	I915_RND_STATE(prng);

total: 0 errors, 2 warnings, 0 checks, 702 lines checked
7b37857ec9d6 drm/i915/selftests: Exercise priority inheritance around an engine loop
eabb4969d40f drm/i915: Improve DFS for priority inheritance
5593476c2a97 drm/i915: Extract request submission from execlists
f48c38d2c375 drm/i915: Extract request rewinding from execlists
26a78cab587f drm/i915: Extract request suspension from the execlists backend
1edcba02be27 drm/i915: Extract the ability to defer and rerun a request later
db66ed30fd5d drm/i915: Fix the iterative dfs for defering requests
56d3c8f1f0e2 drm/i915: Move common active lists from engine to i915_scheduler
-:198: CHECK:UNCOMMENTED_DEFINITION: spinlock_t definition without comment
#198: FILE: drivers/gpu/drm/i915/i915_scheduler_types.h:84:
+	spinlock_t lock;

total: 0 errors, 0 warnings, 1 checks, 157 lines checked
4f4afaec9d87 drm/i915: Move scheduler queue
f728914b401f drm/i915: Move tasklet from execlists to sched
0113a5e42835 drm/i915: Replace priolist rbtree with a skiplist
-:305: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'root' - possible side-effects?
#305: FILE: drivers/gpu/drm/i915/i915_priolist_types.h:61:
+#define i915_priolist_is_empty(root) (priolist_first(root) == &(root)->sentinel)

-:307: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'p' - possible side-effects?
#307: FILE: drivers/gpu/drm/i915/i915_priolist_types.h:63:
+#define for_each_priolist(p, root) \
+	for ((p) = priolist_first(root); \
+	     (p) != &(root)->sentinel; \
+	     (p) = (p)->next[0])

-:307: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'root' - possible side-effects?
#307: FILE: drivers/gpu/drm/i915/i915_priolist_types.h:63:
+#define for_each_priolist(p, root) \
+	for ((p) = priolist_first(root); \
+	     (p) != &(root)->sentinel; \
+	     (p) = (p)->next[0])

total: 0 errors, 0 warnings, 3 checks, 611 lines checked
a9fdc2e2c3bf drm/i915: Wrap cmpxchg64 with try_cmpxchg64() helper
-:23: CHECK:MACRO_ARG_REUSE: Macro argument reuse '_ptr' - possible side-effects?
#23: FILE: drivers/gpu/drm/i915/i915_utils.h:463:
+#define try_cmpxchg64(_ptr, _pold, _new)				\
+({									\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __cur = cmpxchg64(_ptr, __old, _new);	\
+	bool success = __cur == __old;					\
+	if (unlikely(!success))						\
+		*_old = __cur;						\
+	likely(success);						\
+})

-:40: CHECK:MACRO_ARG_REUSE: Macro argument reuse '_ptr' - possible side-effects?
#40: FILE: drivers/gpu/drm/i915/i915_utils.h:480:
+#define xchg64(_ptr, _new)						\
+({									\
+	__typeof__(_ptr) __ptr = (_ptr);				\
+	__typeof__(*(_ptr)) __old = *__ptr;				\
+	while (!try_cmpxchg64(__ptr, &__old, (_new)))			\
+		;							\
+	__old;								\
+})

total: 0 errors, 0 warnings, 2 checks, 36 lines checked
c1315fa192f5 drm/i915: Fair low-latency scheduling
5cef41e5cbf1 drm/i915/gt: Specify a deadline for the heartbeat
9fcbcc9f2d17 drm/i915: Extend the priority boosting for the display with a deadline
49e08f2d50fd drm/i915/gt: Skip over completed active execlists, again
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#10: 
Referenecs: 35f3fd8182ba ("drm/i915/execlists: Workaround switching back to a completed context")

-:10: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit 35f3fd8182ba ("drm/i915/execlists: Workaround switching back to a completed context")'
#10: 
Referenecs: 35f3fd8182ba ("drm/i915/execlists: Workaround switching back to a completed context")

-:11: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit 8ab3a3812aa9 ("drm/i915/gt: Incrementally check for rewinding")'
#11: 
References: 8ab3a3812aa9 ("drm/i915/gt: Incrementally check for rewinding")

total: 2 errors, 1 warnings, 0 checks, 71 lines checked
0ecd53938439 drm/i915/gt: Support virtual engine queues
9fce6e1cde33 drm/i915: Move saturated workload detection back to the context
-:29: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#29: 
References: 44d89409a12e ("drm/i915: Make the semaphore saturation mask global")

-:29: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit 44d89409a12e ("drm/i915: Make the semaphore saturation mask global")'
#29: 
References: 44d89409a12e ("drm/i915: Make the semaphore saturation mask global")

total: 1 errors, 1 warnings, 0 checks, 70 lines checked
6a525ef3a97d drm/i915: Bump default timeslicing quantum to 5ms
-:7: WARNING:COMMIT_MESSAGE: Missing commit description - Add an appropriate one

total: 0 errors, 1 warnings, 0 checks, 8 lines checked
4f5204545c50 drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb
0a1f9167779e drm/i915/gt: Track timeline GGTT offset separately from subpage offset
497d8e60daa0 drm/i915/gt: Add timeline "mode"
a80e287deb01 drm/i915/gt: Use indices for writing into relative timelines
e63e15540e94 drm/i915/selftests: Exercise relative timeline modes
1c8f8f226ec3 drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines
d1d29911e5a0 Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq"
0714dcad606d drm/i915/gt: Couple tasklet scheduling for all CS interrupts
fef880930860 drm/i915/gt: Support creation of 'internal' rings
9899406a944a drm/i915/gt: Use client timeline address for seqno writes
01ac9a884ed0 drm/i915/gt: Infrastructure for ring scheduling
-:79: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#79: 
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 862 lines checked
dc748355fd5a drm/i915/gt: Enable busy-stats for ring-scheduler
b9f7ad160192 drm/i915/gt: Implement ring scheduler for gen6/7
-:68: CHECK:OPEN_ENDED_LINE: Lines should not end with a '('
#68: FILE: drivers/gpu/drm/i915/gt/intel_ring_scheduler.c:202:
+				*cs++ = i915_mmio_reg_offset(

-:70: CHECK:OPEN_ENDED_LINE: Lines should not end with a '('
#70: FILE: drivers/gpu/drm/i915/gt/intel_ring_scheduler.c:204:
+				*cs++ = _MASKED_BIT_ENABLE(

-:105: CHECK:OPEN_ENDED_LINE: Lines should not end with a '('
#105: FILE: drivers/gpu/drm/i915/gt/intel_ring_scheduler.c:239:
+				*cs++ = _MASKED_BIT_DISABLE(

total: 0 errors, 0 warnings, 3 checks, 580 lines checked
58747522a4fc drm/i915/gt: Enable ring scheduling for gen6/7
0167812eaa7f drm/i915: Mark up protected uses of 'i915_request_completed'


_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.SPARSE: warning for series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Patchwork]

== Series Details ==

Series: series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet
URL   : https://patchwork.freedesktop.org/series/85184/
State : warning

== Summary ==

$ dim sparse --fast origin/drm-tip
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:27:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:32:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:32:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:32:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:32:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:49:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:56:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:56:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:56:9: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gt/intel_engine_stats.h:56:9: warning: trying to copy expression type 31
-./include/linux/seqlock.h:838:24: warning: trying to copy expression type 31
-./include/linux/seqlock.h:838:24: warning: trying to copy expression type 31
-./include/linux/seqlock.h:864:16: warning: trying to copy expression type 31
+drivers/gpu/drm/i915/gvt/mmio.c:295:23: warning: memcpy with byte count of 279040
+drivers/gpu/drm/i915/i915_perf.c:1450:15: warning: memset with byte count of 16777216
+drivers/gpu/drm/i915/i915_perf.c:1504:15: warning: memset with byte count of 16777216
+drivers/gpu/drm/i915/intel_wakeref.c:137:19: warning: context imbalance in 'wakeref_auto_timeout' - unexpected unlock
+drivers/gpu/drm/i915/selftests/i915_syncmap.c:80:54: warning: dubious: x | !y
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_read16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_read32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_read64' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_read8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_write16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_write32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'fwtable_write8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_read16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_read32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_read64' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_read8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_write16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_write32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen11_fwtable_write8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_read16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_read32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_read64' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_read8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_write16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_write32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen12_fwtable_write8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_read16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_read32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_read64' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_read8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_write16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_write32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen6_write8' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen8_write16' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen8_write32' - different lock contexts for basic block
+./include/linux/spinlock.h:409:9: warning: context imbalance in 'gen8_write8' - different lock contexts for basic block


_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Patchwork]

[-- Attachment #1.1: Type: text/plain, Size: 8279 bytes --]

== Series Details ==

Series: series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet
URL   : https://patchwork.freedesktop.org/series/85184/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_9515 -> Patchwork_19200
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/index.html

New tests
---------

  New tests have been introduced between CI_DRM_9515 and Patchwork_19200:

### New IGT tests (1) ###

  * igt@i915_selftest@live@scheduler:
    - Statuses : 35 pass(s)
    - Exec time: [0.59, 9.37] s

  

Known issues
------------

  Here are the changes found in Patchwork_19200 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@debugfs_test@read_all_entries:
    - fi-apl-guc:         [PASS][1] -> [DMESG-WARN][2] ([i915#62])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/fi-apl-guc/igt@debugfs_test@read_all_entries.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-apl-guc/igt@debugfs_test@read_all_entries.html

  * igt@fbdev@write:
    - fi-bdw-gvtdvm:      NOTRUN -> [SKIP][3] ([fdo#109271]) +5 similar issues
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-bdw-gvtdvm/igt@fbdev@write.html

  * igt@gem_exec_suspend@basic-s0:
    - fi-apl-guc:         [PASS][4] -> [DMESG-WARN][5] ([i915#180] / [i915#62])
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/fi-apl-guc/igt@gem_exec_suspend@basic-s0.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-apl-guc/igt@gem_exec_suspend@basic-s0.html
    - fi-bdw-gvtdvm:      NOTRUN -> [INCOMPLETE][6] ([i915#146])
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-bdw-gvtdvm/igt@gem_exec_suspend@basic-s0.html

  * igt@i915_selftest@live@gt_heartbeat:
    - fi-tgl-y:           [PASS][7] -> [DMESG-FAIL][8] ([i915#2601])
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/fi-tgl-y/igt@i915_selftest@live@gt_heartbeat.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-tgl-y/igt@i915_selftest@live@gt_heartbeat.html

  * igt@vgem_basic@setversion:
    - fi-tgl-y:           [PASS][9] -> [DMESG-WARN][10] ([i915#402]) +1 similar issue
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/fi-tgl-y/igt@vgem_basic@setversion.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-tgl-y/igt@vgem_basic@setversion.html

  
#### Possible fixes ####

  * igt@prime_vgem@basic-write:
    - fi-tgl-y:           [DMESG-WARN][11] ([i915#402]) -> [PASS][12] +1 similar issue
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/fi-tgl-y/igt@prime_vgem@basic-write.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/fi-tgl-y/igt@prime_vgem@basic-write.html

  
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [i915#146]: https://gitlab.freedesktop.org/drm/intel/issues/146
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#2601]: https://gitlab.freedesktop.org/drm/intel/issues/2601
  [i915#402]: https://gitlab.freedesktop.org/drm/intel/issues/402
  [i915#62]: https://gitlab.freedesktop.org/drm/intel/issues/62


Participating hosts (42 -> 38)
------------------------------

  Additional (1): fi-bdw-gvtdvm 
  Missing    (5): fi-ilk-m540 fi-hsw-4200u fi-bsw-cyan fi-ctg-p8600 fi-bdw-samus 


Build changes
-------------

  * Linux: CI_DRM_9515 -> Patchwork_19200

  CI-20190529: 20190529
  CI_DRM_9515: fc7c8ab3de81a7382017db8cdb35baae97c150f0 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5918: 137c8f1edd9cc769e8a62808c6dcd36b233e2d05 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_19200: 0167812eaa7f3765223f9950cf1bae4bd3c1a346 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

0167812eaa7f drm/i915: Mark up protected uses of 'i915_request_completed'
58747522a4fc drm/i915/gt: Enable ring scheduling for gen6/7
b9f7ad160192 drm/i915/gt: Implement ring scheduler for gen6/7
dc748355fd5a drm/i915/gt: Enable busy-stats for ring-scheduler
01ac9a884ed0 drm/i915/gt: Infrastructure for ring scheduling
9899406a944a drm/i915/gt: Use client timeline address for seqno writes
fef880930860 drm/i915/gt: Support creation of 'internal' rings
0714dcad606d drm/i915/gt: Couple tasklet scheduling for all CS interrupts
d1d29911e5a0 Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq"
1c8f8f226ec3 drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines
e63e15540e94 drm/i915/selftests: Exercise relative timeline modes
a80e287deb01 drm/i915/gt: Use indices for writing into relative timelines
497d8e60daa0 drm/i915/gt: Add timeline "mode"
0a1f9167779e drm/i915/gt: Track timeline GGTT offset separately from subpage offset
4f5204545c50 drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb
6a525ef3a97d drm/i915: Bump default timeslicing quantum to 5ms
9fce6e1cde33 drm/i915: Move saturated workload detection back to the context
0ecd53938439 drm/i915/gt: Support virtual engine queues
49e08f2d50fd drm/i915/gt: Skip over completed active execlists, again
9fcbcc9f2d17 drm/i915: Extend the priority boosting for the display with a deadline
5cef41e5cbf1 drm/i915/gt: Specify a deadline for the heartbeat
c1315fa192f5 drm/i915: Fair low-latency scheduling
a9fdc2e2c3bf drm/i915: Wrap cmpxchg64 with try_cmpxchg64() helper
0113a5e42835 drm/i915: Replace priolist rbtree with a skiplist
f728914b401f drm/i915: Move tasklet from execlists to sched
4f4afaec9d87 drm/i915: Move scheduler queue
56d3c8f1f0e2 drm/i915: Move common active lists from engine to i915_scheduler
db66ed30fd5d drm/i915: Fix the iterative dfs for defering requests
1edcba02be27 drm/i915: Extract the ability to defer and rerun a request later
26a78cab587f drm/i915: Extract request suspension from the execlists backend
f48c38d2c375 drm/i915: Extract request rewinding from execlists
5593476c2a97 drm/i915: Extract request submission from execlists
eabb4969d40f drm/i915: Improve DFS for priority inheritance
7b37857ec9d6 drm/i915/selftests: Exercise priority inheritance around an engine loop
5274e559d740 drm/i915/selftests: Measure set-priority duration
660e34df14a0 drm/i915: Restructure priority inheritance
d23c18eec355 drm/i915: Teach the i915_dependency to use a double-lock
b6680c4d807c drm/i915: Replace engine->schedule() with a known request operation
0fc466b30b40 drm/i915: Remove I915_USER_PRIORITY_SHIFT
43182c3b43b9 drm/i915: Strip out internal priorities
7f7cfa94210d drm/i915/gt: Remove timeslice suppression
915e2215b56c drm/i915/gt: Do not suspend bonded requests if one hangs
3e32d2a70598 drm/i915/gt: Refactor heartbeat request construction and submission
1ad786b3dafd drm/i915/gt: Convert stats.active to plain unsigned int
761f42694117 drm/i915/gt: Extract busy-stats for ring-scheduler
d4ab3dd23cec drm/i915/gt: Drop atomic for engine->fw_active tracking
f3eb0734aa17 drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit()
8f7854833c40 drm/i915/gem: Reduce ctx->engines_mutex for get_engines()
cad1adec9393 drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source
9214c519cc1b drm/i915: Drop i915_request.lock requirement for intel_rps_boost()
b45af9eeb47e drm/i915: Drop i915_request.lock serialisation around await_start
9b6e9d3440df drm/i915/gt: Consolidate the CS timestamp clocks
ec26a9257ebb drm/i915/selftests: Confirm CS_TIMESTAMP / CTX_TIMESTAMP share a clock
f1bc3696961a drm/i915/gt: ce->inflight updates are now serialised
fd614fdd85e4 drm/i915/gt: Simplify virtual engine handling for execlists_hold()
535418e46847 drm/i915/gt: Resubmit the virtual engine on schedule-out
5fcc092512e9 drm/i915/gt: Shrink the critical section for irq signaling
4cf4ad3a878b drm/i915/gt: Remove virtual breadcrumb before transfer
e67f6b85391f drm/i915/gt: Defer schedule_out until after the next dequeue
2a533c166dca drm/i915/gt: Decouple inflight virtual engines
5e8040a840bc drm/i915/gt: Use virtual_engine during execlists_dequeue
11ff28d8f6d3 drm/i915/gt: Replace direct submit with direct call to tasklet

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/index.html

[-- Attachment #1.2: Type: text/html, Size: 9588 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✓ Fi.CI.IGT: success for series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet

[Patchwork]

[-- Attachment #1.1: Type: text/plain, Size: 30314 bytes --]

== Series Details ==

Series: series starting with [01/62] drm/i915/gt: Replace direct submit with direct call to tasklet
URL   : https://patchwork.freedesktop.org/series/85184/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_9515_full -> Patchwork_19200_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

New tests
---------

  New tests have been introduced between CI_DRM_9515_full and Patchwork_19200_full:

### New IGT tests (3) ###

  * igt@i915_selftest@live@scheduler:
    - Statuses : 7 pass(s)
    - Exec time: [0.62, 9.41] s

  * igt@i915_selftest@mock@scheduler:
    - Statuses : 7 pass(s)
    - Exec time: [0.17, 1.51] s

  * igt@i915_selftest@perf@scheduler:
    - Statuses : 8 pass(s)
    - Exec time: [10.13, 18.39] s

  

Known issues
------------

  Here are the changes found in Patchwork_19200_full that come from known issues:

### CI changes ###

#### Possible fixes ####

  * boot:
    - shard-skl:          ([PASS][1], [PASS][2], [PASS][3], [PASS][4], [PASS][5], [PASS][6], [PASS][7], [PASS][8], [PASS][9], [PASS][10], [PASS][11], [PASS][12], [PASS][13], [PASS][14], [PASS][15], [PASS][16], [PASS][17], [FAIL][18], [PASS][19], [PASS][20], [PASS][21], [PASS][22], [PASS][23], [PASS][24]) -> ([PASS][25], [PASS][26], [PASS][27], [PASS][28], [PASS][29], [PASS][30], [PASS][31], [PASS][32], [PASS][33], [PASS][34], [PASS][35], [PASS][36], [PASS][37], [PASS][38], [PASS][39], [PASS][40], [PASS][41], [PASS][42], [PASS][43], [PASS][44], [PASS][45], [PASS][46], [PASS][47], [PASS][48])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl9/boot.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl9/boot.html
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl8/boot.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl8/boot.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl8/boot.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl7/boot.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl7/boot.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl7/boot.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl6/boot.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl6/boot.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl6/boot.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl5/boot.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl5/boot.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl4/boot.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl4/boot.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl4/boot.html
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl3/boot.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl3/boot.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl2/boot.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl10/boot.html
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl10/boot.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl1/boot.html
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl1/boot.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl1/boot.html
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/boot.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl9/boot.html
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl9/boot.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl8/boot.html
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl8/boot.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/boot.html
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/boot.html
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/boot.html
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/boot.html
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/boot.html
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/boot.html
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl5/boot.html
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl5/boot.html
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl4/boot.html
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl4/boot.html
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl4/boot.html
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl3/boot.html
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl3/boot.html
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl2/boot.html
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl2/boot.html
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl10/boot.html
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl10/boot.html
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl10/boot.html
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/boot.html

  

### IGT changes ###

#### Issues hit ####

  * igt@feature_discovery@display-2x:
    - shard-hsw:          [PASS][49] -> [SKIP][50] ([fdo#109271]) +1 similar issue
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-hsw2/igt@feature_discovery@display-2x.html
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-hsw4/igt@feature_discovery@display-2x.html

  * igt@gem_ctx_param@set-priority-not-supported:
    - shard-snb:          [PASS][51] -> [SKIP][52] ([fdo#109271])
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-snb4/igt@gem_ctx_param@set-priority-not-supported.html
   [52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-snb5/igt@gem_ctx_param@set-priority-not-supported.html

  * igt@gem_ctx_sseu@invalid-args:
    - shard-tglb:         NOTRUN -> [SKIP][53] ([i915#280])
   [53]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@gem_ctx_sseu@invalid-args.html

  * igt@gem_exec_params@no-vebox:
    - shard-skl:          NOTRUN -> [SKIP][54] ([fdo#109271]) +80 similar issues
   [54]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/igt@gem_exec_params@no-vebox.html

  * igt@gem_exec_reloc@basic-many-active@vcs1:
    - shard-iclb:         NOTRUN -> [FAIL][55] ([i915#2389])
   [55]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb2/igt@gem_exec_reloc@basic-many-active@vcs1.html

  * igt@gem_exec_schedule@lateslice@vcs0:
    - shard-hsw:          NOTRUN -> [SKIP][56] ([fdo#109271]) +41 similar issues
   [56]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-hsw2/igt@gem_exec_schedule@lateslice@vcs0.html

  * igt@gem_exec_schedule@thriceslice@bcs0:
    - shard-snb:          NOTRUN -> [SKIP][57] ([fdo#109271]) +20 similar issues
   [57]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-snb2/igt@gem_exec_schedule@thriceslice@bcs0.html

  * igt@gem_exec_whisper@basic-queues-forked-all:
    - shard-iclb:         [PASS][58] -> [INCOMPLETE][59] ([i915#2295])
   [58]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb4/igt@gem_exec_whisper@basic-queues-forked-all.html
   [59]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb7/igt@gem_exec_whisper@basic-queues-forked-all.html

  * igt@gem_render_copy@y-tiled-ccs-to-yf-tiled-mc-ccs:
    - shard-iclb:         NOTRUN -> [SKIP][60] ([i915#768])
   [60]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@gem_render_copy@y-tiled-ccs-to-yf-tiled-mc-ccs.html

  * igt@gen7_exec_parse@cmd-crossing-page:
    - shard-tglb:         NOTRUN -> [SKIP][61] ([fdo#109289])
   [61]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@gen7_exec_parse@cmd-crossing-page.html
    - shard-iclb:         NOTRUN -> [SKIP][62] ([fdo#109289])
   [62]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@gen7_exec_parse@cmd-crossing-page.html

  * igt@i915_pm_rpm@system-suspend:
    - shard-skl:          [PASS][63] -> [INCOMPLETE][64] ([i915#151])
   [63]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl9/igt@i915_pm_rpm@system-suspend.html
   [64]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/igt@i915_pm_rpm@system-suspend.html

  * igt@i915_selftest@live@gt_lrc:
    - shard-tglb:         NOTRUN -> [DMESG-FAIL][65] ([i915#2373])
   [65]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@i915_selftest@live@gt_lrc.html

  * igt@i915_selftest@live@gt_pm:
    - shard-tglb:         NOTRUN -> [DMESG-FAIL][66] ([i915#1759] / [i915#2291])
   [66]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@i915_selftest@live@gt_pm.html

  * igt@kms_async_flips@test-time-stamp:
    - shard-tglb:         [PASS][67] -> [FAIL][68] ([i915#2574])
   [67]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb5/igt@kms_async_flips@test-time-stamp.html
   [68]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb1/igt@kms_async_flips@test-time-stamp.html

  * igt@kms_big_fb@linear-32bpp-rotate-270:
    - shard-iclb:         NOTRUN -> [SKIP][69] ([fdo#110725] / [fdo#111614])
   [69]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_big_fb@linear-32bpp-rotate-270.html
    - shard-tglb:         NOTRUN -> [SKIP][70] ([fdo#111614])
   [70]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@kms_big_fb@linear-32bpp-rotate-270.html

  * igt@kms_ccs@pipe-c-crc-primary-basic:
    - shard-skl:          NOTRUN -> [SKIP][71] ([fdo#109271] / [fdo#111304])
   [71]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/igt@kms_ccs@pipe-c-crc-primary-basic.html

  * igt@kms_chamelium@hdmi-crc-single:
    - shard-glk:          NOTRUN -> [SKIP][72] ([fdo#109271] / [fdo#111827]) +5 similar issues
   [72]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-glk7/igt@kms_chamelium@hdmi-crc-single.html

  * igt@kms_chamelium@hdmi-hpd-storm:
    - shard-kbl:          NOTRUN -> [SKIP][73] ([fdo#109271] / [fdo#111827]) +2 similar issues
   [73]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl7/igt@kms_chamelium@hdmi-hpd-storm.html

  * igt@kms_color@pipe-c-ctm-0-75:
    - shard-skl:          [PASS][74] -> [DMESG-WARN][75] ([i915#1982])
   [74]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl7/igt@kms_color@pipe-c-ctm-0-75.html
   [75]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl10/igt@kms_color@pipe-c-ctm-0-75.html

  * igt@kms_color_chamelium@pipe-a-ctm-red-to-blue:
    - shard-iclb:         NOTRUN -> [SKIP][76] ([fdo#109284] / [fdo#111827]) +4 similar issues
   [76]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_color_chamelium@pipe-a-ctm-red-to-blue.html

  * igt@kms_color_chamelium@pipe-b-ctm-max:
    - shard-skl:          NOTRUN -> [SKIP][77] ([fdo#109271] / [fdo#111827]) +10 similar issues
   [77]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/igt@kms_color_chamelium@pipe-b-ctm-max.html

  * igt@kms_color_chamelium@pipe-c-ctm-0-25:
    - shard-tglb:         NOTRUN -> [SKIP][78] ([fdo#109284] / [fdo#111827]) +6 similar issues
   [78]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@kms_color_chamelium@pipe-c-ctm-0-25.html

  * igt@kms_color_chamelium@pipe-d-gamma:
    - shard-iclb:         NOTRUN -> [SKIP][79] ([fdo#109278] / [fdo#109284] / [fdo#111827])
   [79]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_color_chamelium@pipe-d-gamma.html

  * igt@kms_cursor_crc@pipe-b-cursor-64x64-onscreen:
    - shard-skl:          [PASS][80] -> [FAIL][81] ([i915#54]) +1 similar issue
   [80]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl9/igt@kms_cursor_crc@pipe-b-cursor-64x64-onscreen.html
   [81]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl8/igt@kms_cursor_crc@pipe-b-cursor-64x64-onscreen.html

  * igt@kms_cursor_edge_walk@pipe-d-128x128-top-edge:
    - shard-iclb:         NOTRUN -> [SKIP][82] ([fdo#109278]) +4 similar issues
   [82]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_cursor_edge_walk@pipe-d-128x128-top-edge.html

  * igt@kms_cursor_legacy@cursorb-vs-flipa-legacy:
    - shard-iclb:         NOTRUN -> [SKIP][83] ([fdo#109274] / [fdo#109278]) +1 similar issue
   [83]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_cursor_legacy@cursorb-vs-flipa-legacy.html

  * igt@kms_cursor_legacy@flip-vs-cursor-atomic:
    - shard-tglb:         [PASS][84] -> [FAIL][85] ([i915#2346])
   [84]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb5/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html
   [85]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb1/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html

  * igt@kms_cursor_legacy@flip-vs-cursor-toggle:
    - shard-tglb:         NOTRUN -> [FAIL][86] ([i915#2346])
   [86]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@kms_cursor_legacy@flip-vs-cursor-toggle.html

  * igt@kms_flip@2x-single-buffer-flip-vs-dpms-off-vs-modeset:
    - shard-iclb:         NOTRUN -> [SKIP][87] ([fdo#109274])
   [87]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_flip@2x-single-buffer-flip-vs-dpms-off-vs-modeset.html

  * igt@kms_flip@flip-vs-expired-vblank-interruptible@b-edp1:
    - shard-skl:          [PASS][88] -> [FAIL][89] ([i915#79]) +1 similar issue
   [88]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl10/igt@kms_flip@flip-vs-expired-vblank-interruptible@b-edp1.html
   [89]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@b-edp1.html

  * igt@kms_flip@flip-vs-suspend@b-dp1:
    - shard-kbl:          [PASS][90] -> [DMESG-WARN][91] ([i915#180])
   [90]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-kbl6/igt@kms_flip@flip-vs-suspend@b-dp1.html
   [91]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl4/igt@kms_flip@flip-vs-suspend@b-dp1.html

  * igt@kms_frontbuffer_tracking@fbc-2p-primscrn-shrfb-plflip-blt:
    - shard-tglb:         NOTRUN -> [SKIP][92] ([fdo#111825]) +14 similar issues
   [92]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@kms_frontbuffer_tracking@fbc-2p-primscrn-shrfb-plflip-blt.html

  * igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-onoff:
    - shard-iclb:         NOTRUN -> [SKIP][93] ([fdo#109280]) +10 similar issues
   [93]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-onoff.html

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-mmap-cpu:
    - shard-kbl:          NOTRUN -> [SKIP][94] ([fdo#109271]) +32 similar issues
   [94]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl7/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscren-pri-shrfb-draw-mmap-cpu.html

  * igt@kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-mmap-wc:
    - shard-glk:          NOTRUN -> [SKIP][95] ([fdo#109271]) +25 similar issues
   [95]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-glk7/igt@kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-draw-mmap-wc.html

  * igt@kms_hdr@bpc-switch-dpms:
    - shard-skl:          [PASS][96] -> [FAIL][97] ([i915#1188])
   [96]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl1/igt@kms_hdr@bpc-switch-dpms.html
   [97]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/igt@kms_hdr@bpc-switch-dpms.html

  * igt@kms_plane_alpha_blend@pipe-a-alpha-basic:
    - shard-glk:          NOTRUN -> [FAIL][98] ([fdo#108145] / [i915#265])
   [98]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-glk7/igt@kms_plane_alpha_blend@pipe-a-alpha-basic.html

  * igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max:
    - shard-kbl:          NOTRUN -> [FAIL][99] ([fdo#108145] / [i915#265])
   [99]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl7/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max.html

  * igt@kms_plane_alpha_blend@pipe-c-coverage-7efc:
    - shard-skl:          [PASS][100] -> [FAIL][101] ([fdo#108145] / [i915#265])
   [100]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl10/igt@kms_plane_alpha_blend@pipe-c-coverage-7efc.html
   [101]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/igt@kms_plane_alpha_blend@pipe-c-coverage-7efc.html

  * igt@kms_psr@psr2_sprite_plane_move:
    - shard-iclb:         NOTRUN -> [SKIP][102] ([fdo#109441])
   [102]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@kms_psr@psr2_sprite_plane_move.html

  * igt@kms_vblank@pipe-d-wait-idle:
    - shard-kbl:          NOTRUN -> [SKIP][103] ([fdo#109271] / [i915#533])
   [103]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl7/igt@kms_vblank@pipe-d-wait-idle.html

  * igt@kms_writeback@writeback-pixel-formats:
    - shard-skl:          NOTRUN -> [SKIP][104] ([fdo#109271] / [i915#2437]) +1 similar issue
   [104]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/igt@kms_writeback@writeback-pixel-formats.html

  * igt@nouveau_crc@pipe-c-ctx-flip-detection:
    - shard-iclb:         NOTRUN -> [SKIP][105] ([i915#2530]) +1 similar issue
   [105]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@nouveau_crc@pipe-c-ctx-flip-detection.html
    - shard-tglb:         NOTRUN -> [SKIP][106] ([i915#2530]) +1 similar issue
   [106]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@nouveau_crc@pipe-c-ctx-flip-detection.html

  * igt@perf@polling-parameterized:
    - shard-skl:          [PASS][107] -> [FAIL][108] ([i915#1542])
   [107]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl7/igt@perf@polling-parameterized.html
   [108]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl10/igt@perf@polling-parameterized.html

  * igt@prime_nv_pcopy@test3_2:
    - shard-tglb:         NOTRUN -> [SKIP][109] ([fdo#109291]) +2 similar issues
   [109]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@prime_nv_pcopy@test3_2.html
    - shard-iclb:         NOTRUN -> [SKIP][110] ([fdo#109291])
   [110]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@prime_nv_pcopy@test3_2.html

  * igt@sysfs_heartbeat_interval@mixed@bcs0:
    - shard-skl:          [PASS][111] -> [FAIL][112] ([i915#1731])
   [111]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl2/igt@sysfs_heartbeat_interval@mixed@bcs0.html
   [112]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl2/igt@sysfs_heartbeat_interval@mixed@bcs0.html

  * igt@tools_test@sysfs_l3_parity:
    - shard-iclb:         NOTRUN -> [SKIP][113] ([fdo#109307])
   [113]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@tools_test@sysfs_l3_parity.html
    - shard-tglb:         NOTRUN -> [SKIP][114] ([fdo#109307])
   [114]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@tools_test@sysfs_l3_parity.html

  
#### Possible fixes ####

  * {igt@gem_exec_balancer@fairslice}:
    - shard-tglb:         [FAIL][115] ([i915#2802]) -> [PASS][116]
   [115]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb2/igt@gem_exec_balancer@fairslice.html
   [116]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb3/igt@gem_exec_balancer@fairslice.html
    - shard-iclb:         [FAIL][117] ([i915#2802]) -> [PASS][118]
   [117]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb1/igt@gem_exec_balancer@fairslice.html
   [118]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb2/igt@gem_exec_balancer@fairslice.html

  * {igt@gem_exec_fair@basic-deadline}:
    - shard-kbl:          [FAIL][119] -> [PASS][120]
   [119]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-kbl2/igt@gem_exec_fair@basic-deadline.html
   [120]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl1/igt@gem_exec_fair@basic-deadline.html

  * {igt@gem_exec_fair@basic-none-rrul@rcs0}:
    - shard-iclb:         [FAIL][121] ([i915#2842]) -> [PASS][122] +10 similar issues
   [121]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb8/igt@gem_exec_fair@basic-none-rrul@rcs0.html
   [122]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb2/igt@gem_exec_fair@basic-none-rrul@rcs0.html

  * {igt@gem_exec_fair@basic-none-solo@rcs0}:
    - shard-kbl:          [FAIL][123] ([i915#2842]) -> [PASS][124] +3 similar issues
   [123]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-kbl2/igt@gem_exec_fair@basic-none-solo@rcs0.html
   [124]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl4/igt@gem_exec_fair@basic-none-solo@rcs0.html

  * {igt@gem_exec_fair@basic-none-vip@rcs0}:
    - shard-tglb:         [FAIL][125] ([i915#2842]) -> [PASS][126] +16 similar issues
   [125]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb7/igt@gem_exec_fair@basic-none-vip@rcs0.html
   [126]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb3/igt@gem_exec_fair@basic-none-vip@rcs0.html

  * {igt@gem_exec_fair@basic-none@vcs0}:
    - shard-apl:          [SKIP][127] ([fdo#109271]) -> [PASS][128] +2 similar issues
   [127]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-apl1/igt@gem_exec_fair@basic-none@vcs0.html
   [128]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-apl4/igt@gem_exec_fair@basic-none@vcs0.html

  * {igt@gem_exec_fair@basic-pace-solo@rcs0}:
    - shard-glk:          [FAIL][129] ([i915#2842]) -> [PASS][130] +8 similar issues
   [129]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-glk9/igt@gem_exec_fair@basic-pace-solo@rcs0.html
   [130]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-glk3/igt@gem_exec_fair@basic-pace-solo@rcs0.html
    - shard-apl:          [FAIL][131] ([i915#2842]) -> [PASS][132]
   [131]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-apl4/igt@gem_exec_fair@basic-pace-solo@rcs0.html
   [132]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-apl3/igt@gem_exec_fair@basic-pace-solo@rcs0.html

  * {igt@gem_exec_schedule@u-fairslice@vcs0}:
    - shard-glk:          [DMESG-WARN][133] ([i915#1610]) -> [PASS][134]
   [133]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-glk3/igt@gem_exec_schedule@u-fairslice@vcs0.html
   [134]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-glk7/igt@gem_exec_schedule@u-fairslice@vcs0.html

  * {igt@gem_exec_schedule@u-fairslice@vecs0}:
    - shard-tglb:         [DMESG-WARN][135] ([i915#2803]) -> [PASS][136]
   [135]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb8/igt@gem_exec_schedule@u-fairslice@vecs0.html
   [136]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb5/igt@gem_exec_schedule@u-fairslice@vecs0.html
    - shard-iclb:         [DMESG-WARN][137] ([i915#2803]) -> [PASS][138]
   [137]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb3/igt@gem_exec_schedule@u-fairslice@vecs0.html
   [138]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb1/igt@gem_exec_schedule@u-fairslice@vecs0.html

  * igt@kms_async_flips@async-flip-with-page-flip-events:
    - shard-skl:          [FAIL][139] ([i915#2715]) -> [PASS][140]
   [139]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl8/igt@kms_async_flips@async-flip-with-page-flip-events.html
   [140]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl9/igt@kms_async_flips@async-flip-with-page-flip-events.html

  * igt@kms_color@pipe-b-ctm-0-25:
    - shard-skl:          [DMESG-WARN][141] ([i915#1982]) -> [PASS][142]
   [141]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl8/igt@kms_color@pipe-b-ctm-0-25.html
   [142]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl6/igt@kms_color@pipe-b-ctm-0-25.html

  * igt@kms_cursor_crc@pipe-a-cursor-128x128-sliding:
    - shard-skl:          [FAIL][143] ([i915#54]) -> [PASS][144] +2 similar issues
   [143]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl5/igt@kms_cursor_crc@pipe-a-cursor-128x128-sliding.html
   [144]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/igt@kms_cursor_crc@pipe-a-cursor-128x128-sliding.html

  * igt@kms_cursor_crc@pipe-b-cursor-suspend:
    - shard-kbl:          [DMESG-WARN][145] ([i915#180]) -> [PASS][146]
   [145]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-kbl6/igt@kms_cursor_crc@pipe-b-cursor-suspend.html
   [146]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-kbl7/igt@kms_cursor_crc@pipe-b-cursor-suspend.html

  * igt@kms_cursor_legacy@2x-long-cursor-vs-flip-legacy:
    - shard-hsw:          [FAIL][147] ([i915#96]) -> [PASS][148] +1 similar issue
   [147]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-hsw8/igt@kms_cursor_legacy@2x-long-cursor-vs-flip-legacy.html
   [148]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-hsw2/igt@kms_cursor_legacy@2x-long-cursor-vs-flip-legacy.html

  * igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1:
    - shard-skl:          [FAIL][149] ([i915#79]) -> [PASS][150]
   [149]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl10/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html
   [150]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl1/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html

  * igt@kms_flip@flip-vs-suspend@a-edp1:
    - shard-skl:          [INCOMPLETE][151] ([i915#198]) -> [PASS][152]
   [151]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl1/igt@kms_flip@flip-vs-suspend@a-edp1.html
   [152]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl8/igt@kms_flip@flip-vs-suspend@a-edp1.html

  * igt@kms_flip@plain-flip-ts-check-interruptible@c-edp1:
    - shard-skl:          [FAIL][153] ([i915#2122]) -> [PASS][154]
   [153]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl6/igt@kms_flip@plain-flip-ts-check-interruptible@c-edp1.html
   [154]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl5/igt@kms_flip@plain-flip-ts-check-interruptible@c-edp1.html

  * igt@kms_psr@psr2_primary_mmap_cpu:
    - shard-iclb:         [SKIP][155] ([fdo#109441]) -> [PASS][156] +1 similar issue
   [155]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb8/igt@kms_psr@psr2_primary_mmap_cpu.html
   [156]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb2/igt@kms_psr@psr2_primary_mmap_cpu.html

  * igt@kms_vblank@pipe-d-ts-continuation-suspend:
    - shard-tglb:         [INCOMPLETE][157] ([i915#2841]) -> [PASS][158]
   [157]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-tglb5/igt@kms_vblank@pipe-d-ts-continuation-suspend.html
   [158]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-tglb3/igt@kms_vblank@pipe-d-ts-continuation-suspend.html

  * igt@perf_pmu@busy-accuracy-2@bcs0:
    - shard-snb:          [SKIP][159] ([fdo#109271]) -> [PASS][160] +22 similar issues
   [159]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-snb4/igt@perf_pmu@busy-accuracy-2@bcs0.html
   [160]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-snb6/igt@perf_pmu@busy-accuracy-2@bcs0.html

  * igt@perf_pmu@busy-accuracy-98@vcs0:
    - shard-hsw:          [SKIP][161] ([fdo#109271]) -> [PASS][162] +25 similar issues
   [161]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-hsw2/igt@perf_pmu@busy-accuracy-98@vcs0.html
   [162]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-hsw4/igt@perf_pmu@busy-accuracy-98@vcs0.html

  * igt@sysfs_heartbeat_interval@nopreempt@rcs0:
    - shard-skl:          [FAIL][163] ([i915#1778]) -> [PASS][164]
   [163]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-skl5/igt@sysfs_heartbeat_interval@nopreempt@rcs0.html
   [164]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-skl7/igt@sysfs_heartbeat_interval@nopreempt@rcs0.html

  
#### Warnings ####

  * igt@i915_pm_rc6_residency@rc6-fence:
    - shard-iclb:         [WARN][165] ([i915#2681] / [i915#2684]) -> [WARN][166] ([i915#2684])
   [165]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb1/igt@i915_pm_rc6_residency@rc6-fence.html
   [166]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb2/igt@i915_pm_rc6_residency@rc6-fence.html

  * igt@i915_pm_rc6_residency@rc6-idle:
    - shard-iclb:         [WARN][167] ([i915#1804] / [i915#2684]) -> [WARN][168] ([i915#2684])
   [167]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-iclb6/igt@i915_pm_rc6_residency@rc6-idle.html
   [168]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-iclb5/igt@i915_pm_rc6_residency@rc6-idle.html

  * igt@runner@aborted:
    - shard-hsw:          ([FAIL][169], [FAIL][170]) ([i915#2295]) -> ([FAIL][171], [FAIL][172]) ([i915#2295] / [i915#483])
   [169]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-hsw8/igt@runner@aborted.html
   [170]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9515/shard-hsw7/igt@runner@aborted.html
   [171]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/shard-hsw1/igt@runner@aborted.html
   [172]: https://in

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19200/index.html

[-- Attachment #1.2: Type: text/html, Size: 33593 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 02/62] drm/i915/gt: Use virtual_engine during execlists_dequeue

[Matthew Auld]

On Wed, 23 Dec 2020 at 11:11, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Rather than going back and forth between the rb_node entry and the
> virtual_engine type, store the ve local and reuse it. As the
> container_of conversion from rb_node to virtual_engine requires a
> variable offset, performing that conversion just once shaves off a bit
> of code.
>
> v2: Keep a single virtual engine lookup, for typical use.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 03/62] drm/i915/gt: Decouple inflight virtual engines

[Matthew Auld]

On Wed, 23 Dec 2020 at 11:12, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Once a virtual engine has been bound to a sibling, it will remain bound
> until we finally schedule out the last active request. We can not rebind
> the context to a new sibling while it is inflight as the context save
> will conflict, hence we wait. As we cannot then use any other sibliing
> while the context is inflight, only kick the bound sibling while it
> inflight and upon scheduling out the kick the rest (so that we can swap
> engines on timeslicing if the previously bound engine becomes
> oversubscribed).
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 04/62] drm/i915/gt: Defer schedule_out until after the next dequeue

[Matthew Auld]

On Wed, 23 Dec 2020 at 11:12, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Inside schedule_out, we do extra work upon idling the context, such as
> updating the runtime, kicking off retires, kicking virtual engines.
> However, if we are in a series of processing single requests per
> contexts, we may find ourselves scheduling out the context, only to
> immediately schedule it back in during dequeue. This is just extra work
> that we can avoid if we keep the context marked as inflight across the
> dequeue. This becomes more significant later on for minimising virtual
> engine misses.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 07/62] drm/i915/gt: Resubmit the virtual engine on schedule-out

[Matthew Auld]

On Wed, 23 Dec 2020 at 11:12, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Having recognised that we do not change the sibling until we schedule
> out, we can then defer the decision to resubmit the virtual engine from
> the unwind of the active queue to scheduling out of the virtual context.
> This improves our resilence in virtual engine scheduling, and should
> eliminate the rare cases of gem_exec_balance failing.
>
> By keeping the unwind order intact on the local engine, we can preserve
> data dependency ordering while doing a preempt-to-busy pass until we
> have determined the new ELSP. This means that if we try to timeslice
> between a virtual engine and a data-dependent ordinary request, the pair
> will maintain their relative ordering and we will avoid the
> resubmission, cancelling the timeslicing until further change.
>
> The dilemma though is that we then may end up in a situation where the
> 'demotion' of the virtual request to an ordinary request in the engine
> queue results in filling the ELSP[] with virtual requests instead of
> spreading the load across the engines. To compensate for this, we mark
> each virtual request and refuse to resubmit a virtual request in the
> secondary ELSP slots, thus forcing subsequent virtual requests to be
> scheduled out after timeslicing. By delaying the decision until we
> schedule out, we will avoid unnecessary resubmission.
>
> Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2079
> Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2098
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 08/62] drm/i915/gt: Simplify virtual engine handling for execlists_hold()

[Matthew Auld]

On Wed, 23 Dec 2020 at 11:12, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> Now that the tasklet completely controls scheduling of the requests, and
> we postpone scheduling out the old requests, we can keep a hanging
> virtual request bound to the engine on which it hung, and remove it from
> te queue. On release, it will be returned to the same engine and remain
> in its queue until it is scheduled; after which point it will become
> eligible for transfer to a sibling. Instead, we could opt to resubmit the
> request along the virtual engine on unhold, making it eligible for load
> balancing immediately -- but that seems like a pointless optimisation
> for a hanging context.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx