4 files changed, 42 insertions, 28 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8a5054f21bf8..24c99d0838af 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
+				mutex_unlock(&tl->mutex);
+
 				timeout = dma_fence_wait_timeout(fence,
 								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
+
+				/* Retirement is best effort */
+				if (!mutex_trylock(&tl->mutex)) {
+					active_count++;
+					goto out_active;
+				}
 			}
 		}
 
 		if (!retire_requests(tl) || flush_submission(gt))
 			active_count++;
+		mutex_unlock(&tl->mutex);
 
-		spin_lock(&timelines->lock);
+out_active:	spin_lock(&timelines->lock);
 
-		/* Resume iteration after dropping lock */
+		/* Resume list iteration after reacquiring spinlock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fe8a59aaa629..940e7f7df69a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1679,11 +1679,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 	if (!intel_engine_has_timeslices(engine))
 		return false;
 
-	if (list_is_last(&rq->sched.link, &engine->active.requests))
-		return false;
-
-	hint = max(rq_prio(list_next_entry(rq, sched.link)),
-		   engine->execlists.queue_priority_hint);
+	hint = engine->execlists.queue_priority_hint;
+	if (!list_is_last(&rq->sched.link, &engine->active.requests))
+		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
 
 	return hint >= effective_prio(rq);
 }
@@ -1725,6 +1723,18 @@ static void set_timeslice(struct intel_engine_cs *engine)
 	set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
 }
 
+static void start_timeslice(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *execlists = &engine->execlists;
+
+	execlists->switch_priority_hint = execlists->queue_priority_hint;
+
+	if (timer_pending(&execlists->timer))
+		return;
+
+	set_timer_ms(&execlists->timer, timeslice(engine));
+}
+
 static void record_preemption(struct intel_engine_execlists *execlists)
 {
 	(void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++);
@@ -1888,11 +1898,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				if (!execlists->timer.expires &&
-				    need_timeslice(engine, last))
-					set_timer_ms(&execlists->timer,
-						     timeslice(engine));
-
+				start_timeslice(engine);
 				return;
 			}
 		}
@@ -1927,7 +1933,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
-				return; /* leave this for another */
+				start_timeslice(engine);
+				return; /* leave this for another sibling */
 			}
 
 			ENGINE_TRACE(engine,
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 87716529cd2f..d8d9f1179c2b 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl)
 
 static void cacheline_free(struct intel_timeline_cacheline *cl)
 {
+	if (!i915_active_acquire_if_busy(&cl->active)) {
+		__idle_cacheline_free(cl);
+		return;
+	}
+
 	GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE));
 	cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE);
 
-	if (i915_active_is_idle(&cl->active))
-		__idle_cacheline_free(cl);
+	i915_active_release(&cl->active);
 }
 
 int intel_timeline_init(struct intel_timeline *timeline,
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4e292d4bf7b9..173a7f2d109f 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -575,24 +575,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	u32 val;
-
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
-	/* Wa_1604555607:tgl */
-	val = intel_uncore_read(engine->uncore, FF_MODE2);
-	val &= ~FF_MODE2_TDS_TIMER_MASK;
-	val |= FF_MODE2_TDS_TIMER_128;
 	/*
-	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
-	 * enable verification of WA from the later steppings, which enables
-	 * the read of FF_MODE2.
+	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * FF_MODE2 register will return the wrong value when read. The default
+	 * value for this register is zero for all fields and there are no bit
+	 * masks. So instead of doing a RMW we should just write the TDS timer
+	 * value for Wa_1604555607.
 	 */
-	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
-	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
-			    FF_MODE2_TDS_TIMER_MASK);
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128, 0);
 }
 
 static void