diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9c499edb4c13..d92e7ab0005e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2871,6 +2871,14 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
+static bool match_ring(struct i915_request *rq)
+{
+	struct drm_i915_private *dev_priv = rq->i915;
+	u32 ring = I915_READ(RING_START(rq->engine->mmio_base));
+
+	return ring == i915_ggtt_offset(rq->ring->vma);
+}
+
 struct i915_request *
 i915_gem_find_active_request(struct intel_engine_cs *engine)
 {
@@ -2893,6 +2901,13 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 		if (i915_request_completed(request))
 			continue;
 
+		if (!i915_request_started(request))
+			break;
+
+		/* More than one preemptible request may match! */
+		if (!match_ring(request))
+			break;
+
 		active = request;
 		break;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f250109e1f66..8eedf7cac493 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1976,6 +1976,18 @@ static int eb_submit(struct i915_execbuffer *eb)
 			return err;
 	}
 
+	/*
+	 * After we completed waiting for other engines (using HW semaphores)
+	 * then we can signal that this request/batch is ready to run. This
+	 * allows us to determine if the batch is still waiting on the GPU
+	 * or actually running by checking the breadcrumb.
+	 */
+	if (eb->engine->emit_init_breadcrumb) {
+		err = eb->engine->emit_init_breadcrumb(eb->request);
+		if (err)
+			return err;
+	}
+
 	err = eb->engine->emit_bb_start(eb->request,
 					eb->batch->node.start +
 					eb->batch_start_offset,
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 4d58770e6a8c..7db15b7b3de8 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -333,7 +333,7 @@ void i915_request_retire_upto(struct i915_request *rq)
 
 static u32 timeline_get_seqno(struct i915_timeline *tl)
 {
-	return ++tl->seqno;
+	return tl->seqno += 1 + tl->has_initial_breadcrumb;
 }
 
 static void move_to_timeline(struct i915_request *request,
@@ -382,8 +382,8 @@ void __i915_request_submit(struct i915_request *request)
 		intel_engine_enable_signaling(request, false);
 	spin_unlock(&request->lock);
 
-	engine->emit_breadcrumb(request,
-				request->ring->vaddr + request->postfix);
+	engine->emit_fini_breadcrumb(request,
+				     request->ring->vaddr + request->postfix);
 
 	/* Transfer from per-context onto the global per-engine timeline */
 	move_to_timeline(request, &engine->timeline);
@@ -657,7 +657,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * around inside i915_request_add() there is sufficient space at
 	 * the beginning of the ring as well.
 	 */
-	rq->reserved_space = 2 * engine->emit_breadcrumb_dw * sizeof(u32);
+	rq->reserved_space = 2 * engine->emit_fini_breadcrumb_dw * sizeof(u32);
 
 	/*
 	 * Record the position of the start of the request so that
@@ -908,7 +908,7 @@ void i915_request_add(struct i915_request *request)
 	 * GPU processing the request, we never over-estimate the
 	 * position of the ring's HEAD.
 	 */
-	cs = intel_ring_begin(request, engine->emit_breadcrumb_dw);
+	cs = intel_ring_begin(request, engine->emit_fini_breadcrumb_dw);
 	GEM_BUG_ON(IS_ERR(cs));
 	request->postfix = intel_ring_offset(request, cs);
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 96c586d6ff4d..340d6216791c 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -344,6 +344,7 @@ static inline bool i915_request_started(const struct i915_request *rq)
 	if (i915_request_signaled(rq))
 		return true;
 
+	/* Remember: started but may have since been preempted! */
 	return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno - 1);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
index 79838d89bdb9..5ea3af393ffe 100644
--- a/drivers/gpu/drm/i915/i915_timeline.c
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -135,6 +135,7 @@ int i915_timeline_init(struct drm_i915_private *i915,
 	timeline->i915 = i915;
 	timeline->name = name;
 	timeline->pin_count = 0;
+	timeline->has_initial_breadcrumb = !hwsp;
 
 	timeline->hwsp_offset = I915_GEM_HWS_SEQNO_ADDR;
 	if (!hwsp) {
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index ab736e2e5707..8caeb66d1cd5 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -48,6 +48,8 @@ struct i915_timeline {
 	struct i915_vma *hwsp_ggtt;
 	u32 hwsp_offset;
 
+	bool has_initial_breadcrumb;
+
 	/**
 	 * List of breadcrumbs associated with GPU requests currently
 	 * outstanding.
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index ead9c4371fe1..8dca76f6315d 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -664,7 +664,7 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
 	if (dw < 0)
 		goto out_timeline;
 
-	dw = engine->emit_breadcrumb(&frame->rq, frame->cs) - frame->cs;
+	dw = engine->emit_fini_breadcrumb(&frame->rq, frame->cs) - frame->cs;
 
 	i915_timeline_unpin(&frame->timeline);
 
@@ -725,7 +725,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	if (ret < 0)
 		goto err_breadcrumbs;
 
-	engine->emit_breadcrumb_dw = ret;
+	engine->emit_fini_breadcrumb_dw = ret;
 
 	return 0;
 
@@ -1297,7 +1297,9 @@ static void print_request(struct drm_printer *m,
 	drm_printf(m, "%s%x%s [%llx:%llx]%s @ %dms: %s\n",
 		   prefix,
 		   rq->global_seqno,
-		   i915_request_completed(rq) ? "!" : "",
+		   i915_request_completed(rq) ? "!" :
+		   i915_request_started(rq) ? "*" :
+		   "",
 		   rq->fence.context, rq->fence.seqno,
 		   buf,
 		   jiffies_to_msecs(jiffies - rq->emitted_jiffies),
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index fdbb3fe8eac9..5db16dd8e844 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -624,7 +624,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		 * WaIdleLiteRestore:bdw,skl
 		 * Apply the wa NOOPs to prevent
 		 * ring:HEAD == rq:TAIL as we resubmit the
-		 * request. See gen8_emit_breadcrumb() for
+		 * request. See gen8_emit_fini_breadcrumb() for
 		 * where we prepare the padding after the
 		 * end of the request.
 		 */
@@ -1283,6 +1283,34 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	return __execlists_context_pin(engine, ctx, ce);
 }
 
+static int gen8_emit_init_breadcrumb(struct i915_request *rq)
+{
+	u32 *cs;
+
+	GEM_BUG_ON(!rq->timeline->has_initial_breadcrumb);
+
+	cs = intel_ring_begin(rq, 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/*
+	 * Check if we have been preempted before we even get started.
+	 *
+	 * After this point i915_request_started() reports true, even if
+	 * we get preempted and so are no longer running.
+	 */
+	*cs++ = MI_ARB_CHECK;
+	*cs++ = MI_NOOP;
+
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = rq->timeline->hwsp_offset;
+	*cs++ = 0;
+	*cs++ = rq->fence.seqno - 1;
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
 static int emit_pdps(struct i915_request *rq)
 {
 	const struct intel_engine_cs * const engine = rq->engine;
@@ -2039,7 +2067,7 @@ static u32 *gen8_emit_wa_tail(struct i915_request *request, u32 *cs)
 	return cs;
 }
 
-static u32 *gen8_emit_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
 {
 	/* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */
 	BUILD_BUG_ON(I915_GEM_HWS_INDEX_ADDR & (1 << 5));
@@ -2061,7 +2089,7 @@ static u32 *gen8_emit_breadcrumb(struct i915_request *request, u32 *cs)
 	return gen8_emit_wa_tail(request, cs);
 }
 
-static u32 *gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs)
+static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
@@ -2176,7 +2204,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->request_alloc = execlists_request_alloc;
 
 	engine->emit_flush = gen8_emit_flush;
-	engine->emit_breadcrumb = gen8_emit_breadcrumb;
+	engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb;
+	engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb;
 
 	engine->set_default_submission = intel_execlists_set_default_submission;
 
@@ -2289,7 +2318,7 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	/* Override some for render ring. */
 	engine->init_context = gen8_init_rcs_context;
 	engine->emit_flush = gen8_emit_flush_render;
-	engine->emit_breadcrumb = gen8_emit_breadcrumb_rcs;
+	engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb_rcs;
 
 	ret = logical_ring_init(engine);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ee3719324e2d..668ed67336a2 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1607,6 +1607,7 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 		err = PTR_ERR(timeline);
 		goto err;
 	}
+	GEM_BUG_ON(timeline->has_initial_breadcrumb);
 
 	ring = intel_engine_create_ring(engine, timeline, 32 * PAGE_SIZE);
 	i915_timeline_put(timeline);
@@ -1960,6 +1961,7 @@ static int ring_request_alloc(struct i915_request *request)
 	int ret;
 
 	GEM_BUG_ON(!request->hw_context->pin_count);
+	GEM_BUG_ON(request->timeline->has_initial_breadcrumb);
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -2296,9 +2298,14 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
 	engine->context_pin = intel_ring_context_pin;
 	engine->request_alloc = ring_request_alloc;
 
-	engine->emit_breadcrumb = i9xx_emit_breadcrumb;
+	/*
+	 * Using a global execution timeline; the previous final breadcrumb is
+	 * equivalent to our next initial bread so we can elide
+	 * engine->emit_init_breadcrumb().
+	 */
+	engine->emit_fini_breadcrumb = i9xx_emit_breadcrumb;
 	if (IS_GEN(dev_priv, 5))
-		engine->emit_breadcrumb = gen5_emit_breadcrumb;
+		engine->emit_fini_breadcrumb = gen5_emit_breadcrumb;
 
 	engine->set_default_submission = i9xx_set_default_submission;
 
@@ -2327,11 +2334,11 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 	if (INTEL_GEN(dev_priv) >= 7) {
 		engine->init_context = intel_rcs_ctx_init;
 		engine->emit_flush = gen7_render_ring_flush;
-		engine->emit_breadcrumb = gen7_rcs_emit_breadcrumb;
+		engine->emit_fini_breadcrumb = gen7_rcs_emit_breadcrumb;
 	} else if (IS_GEN(dev_priv, 6)) {
 		engine->init_context = intel_rcs_ctx_init;
 		engine->emit_flush = gen6_render_ring_flush;
-		engine->emit_breadcrumb = gen6_rcs_emit_breadcrumb;
+		engine->emit_fini_breadcrumb = gen6_rcs_emit_breadcrumb;
 	} else if (IS_GEN(dev_priv, 5)) {
 		engine->emit_flush = gen4_render_ring_flush;
 	} else {
@@ -2368,9 +2375,9 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine)
 		engine->irq_enable_mask = GT_BSD_USER_INTERRUPT;
 
 		if (IS_GEN(dev_priv, 6))
-			engine->emit_breadcrumb = gen6_xcs_emit_breadcrumb;
+			engine->emit_fini_breadcrumb = gen6_xcs_emit_breadcrumb;
 		else
-			engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb;
+			engine->emit_fini_breadcrumb = gen7_xcs_emit_breadcrumb;
 	} else {
 		engine->emit_flush = bsd_ring_flush;
 		if (IS_GEN(dev_priv, 5))
@@ -2394,9 +2401,9 @@ int intel_init_blt_ring_buffer(struct intel_engine_cs *engine)
 	engine->irq_enable_mask = GT_BLT_USER_INTERRUPT;
 
 	if (IS_GEN(dev_priv, 6))
-		engine->emit_breadcrumb = gen6_xcs_emit_breadcrumb;
+		engine->emit_fini_breadcrumb = gen6_xcs_emit_breadcrumb;
 	else
-		engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb;
+		engine->emit_fini_breadcrumb = gen7_xcs_emit_breadcrumb;
 
 	return intel_init_ring_buffer(engine);
 }
@@ -2414,7 +2421,7 @@ int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine)
 	engine->irq_enable = hsw_vebox_irq_enable;
 	engine->irq_disable = hsw_vebox_irq_disable;
 
-	engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb;
+	engine->emit_fini_breadcrumb = gen7_xcs_emit_breadcrumb;
 
 	return intel_init_ring_buffer(engine);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2927b712b973..1f30ffb84936 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -463,8 +463,10 @@ struct intel_engine_cs {
 					 unsigned int dispatch_flags);
 #define I915_DISPATCH_SECURE BIT(0)
 #define I915_DISPATCH_PINNED BIT(1)
-	u32		*(*emit_breadcrumb)(struct i915_request *rq, u32 *cs);
-	int		emit_breadcrumb_dw;
+	int		 (*emit_init_breadcrumb)(struct i915_request *rq);
+	u32		*(*emit_fini_breadcrumb)(struct i915_request *rq,
+						 u32 *cs);
+	unsigned int	emit_fini_breadcrumb_dw;
 
 	/* Pass the request to the hardware queue (e.g. directly into
 	 * the legacy ringbuffer or to the end of an execlist).
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 95e890d7f58b..3b226ebc6bc4 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -227,7 +227,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.context_pin = mock_context_pin;
 	engine->base.request_alloc = mock_request_alloc;
 	engine->base.emit_flush = mock_emit_flush;
-	engine->base.emit_breadcrumb = mock_emit_breadcrumb;
+	engine->base.emit_fini_breadcrumb = mock_emit_breadcrumb;
 	engine->base.submit_request = mock_submit_request;
 
 	if (i915_timeline_init(i915,