4 files changed, 76 insertions, 71 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..31455eceeb0c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1600,17 +1600,6 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 	spin_unlock(&old->breadcrumbs.irq_lock);
 }
 
-static struct i915_request *
-last_active(const struct intel_engine_execlists *execlists)
-{
-	struct i915_request * const *last = READ_ONCE(execlists->active);
-
-	while (*last && i915_request_completed(*last))
-		last++;
-
-	return *last;
-}
-
 #define for_each_waiter(p__, rq__) \
 	list_for_each_entry_lockless(p__, \
 				     &(rq__)->sched.waiters_list, \
@@ -1679,11 +1668,9 @@ 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);
 }
@@ -1725,16 +1712,26 @@ 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++);
 }
 
-static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
+static unsigned long active_preempt_timeout(struct intel_engine_cs *engine,
+					    const struct i915_request *rq)
 {
-	struct i915_request *rq;
-
-	rq = last_active(&engine->execlists);
 	if (!rq)
 		return 0;
 
@@ -1745,13 +1742,14 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.preempt_timeout_ms);
 }
 
-static void set_preempt_timeout(struct intel_engine_cs *engine)
+static void set_preempt_timeout(struct intel_engine_cs *engine,
+				const struct i915_request *rq)
 {
 	if (!intel_engine_has_preempt_reset(engine))
 		return;
 
 	set_timer_ms(&engine->execlists.preempt,
-		     active_preempt_timeout(engine));
+		     active_preempt_timeout(engine, rq));
 }
 
 static inline void clear_ports(struct i915_request **ports, int count)
@@ -1764,6 +1762,7 @@ 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 rb_node *rb;
 	bool submit = false;
@@ -1818,7 +1817,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * i.e. we will retrigger preemption following the ack in case
 	 * of trouble.
 	 */
-	last = last_active(execlists);
+	active = READ_ONCE(execlists->active);
+	while ((last = *active) && i915_request_completed(last))
+		active++;
+
 	if (last) {
 		if (need_preempt(engine, last, rb)) {
 			ENGINE_TRACE(engine,
@@ -1888,11 +1890,7 @@ 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 +1925,8 @@ 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,
@@ -2103,7 +2102,7 @@ done:
 		 * 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,
+		if (!memcmp(active, execlists->pending,
 			    (port - execlists->pending + 1) * sizeof(*port))) {
 			do
 				execlists_schedule_out(fetch_and_zero(port));
@@ -2114,7 +2113,7 @@ done:
 		clear_ports(port + 1, last_port - port);
 
 		execlists_submit_ports(engine);
-		set_preempt_timeout(engine);
+		set_preempt_timeout(engine, *active);
 	} else {
 skip_submit:
 		ring_set_paused(engine, 0);
@@ -4001,26 +4000,6 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
-
-		/*
-		 * Wa_1604544889:tgl
-		 */
-		if (IS_TGL_REVID(request->i915, TGL_REVID_A0, TGL_REVID_A0)) {
-			flags = 0;
-			flags |= PIPE_CONTROL_CS_STALL;
-			flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
-
-			flags |= PIPE_CONTROL_STORE_DATA_INDEX;
-			flags |= PIPE_CONTROL_QW_WRITE;
-
-			cs = intel_ring_begin(request, 6);
-			if (IS_ERR(cs))
-				return PTR_ERR(cs);
-
-			cs = gen8_emit_pipe_control(cs, flags,
-						    LRC_PPHWSP_SCRATCH_ADDR);
-			intel_ring_advance(request, cs);
-		}
 	}
 
 	return 0;
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..6c2f8462e0f3 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
@@ -1534,15 +1529,34 @@ err_obj:
 	return ERR_PTR(err);
 }
 
+static const struct {
+	u32 start;
+	u32 end;
+} mcr_ranges_gen8[] = {
+	{ .start = 0x5500, .end = 0x55ff },
+	{ .start = 0x7000, .end = 0x7fff },
+	{ .start = 0x9400, .end = 0x97ff },
+	{ .start = 0xb000, .end = 0xb3ff },
+	{ .start = 0xe000, .end = 0xe7ff },
+	{},
+};
+
 static bool mcr_range(struct drm_i915_private *i915, u32 offset)
 {
+	int i;
+
+	if (INTEL_GEN(i915) < 8)
+		return false;
+
 	/*
-	 * Registers in this range are affected by the MCR selector
+	 * Registers in these ranges are affected by the MCR selector
 	 * which only controls CPU initiated MMIO. Routing does not
 	 * work for CS access so we cannot verify them on this path.
 	 */
-	if (INTEL_GEN(i915) >= 8 && (offset >= 0xb000 && offset <= 0xb4ff))
-		return true;
+	for (i = 0; mcr_ranges_gen8[i].start; i++)
+		if (offset >= mcr_ranges_gen8[i].start &&
+		    offset <= mcr_ranges_gen8[i].end)
+			return true;
 
 	return false;
 }