Merge tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for the 5.1 merge window.

  The big changes I'd highlight are:
   - nouveau has HMM support now, there is finally an in-tree user so we
     can quieten down the rip it out people.
   - i915 now enables fastboot by default on Skylake+
   - Displayport Multistream support has been refactored and should
     hopefully be more reliable.

  Core:
   - header cleanups aiming towards removing drmP.h
   - dma-buf fence seqnos to 64-bits
   - common helper for DP mst hotplug for radeon,i915,amdgpu + new
     refcounting scheme
   - MST i2c improvements
   - drm_syncobj_cb removal
   - ARM FB compression fourcc
   - P010 + P016 fourcc
   - allwinner tiled format modifier
   - i2c over aux I2C_M_STOP support
   - DRM_AUTH handling fixes

  TTM:
   - ref/unref renaming

  New driver:
   - ARM komeda display driver

  scheduler:
   - refactor mirror list handling
   - rework hw fence processing
   - 0 run queue entity fix

  bridge:
   - TI DS90C185 LVDS bridge
   - thc631lvdm83d bridge improvements
   - cadence + allwinner DSI ported to generic phy

  panels:
   - Sitronix ST7701 panel
   - Kingdisplay KD097D04
   - LeMaker BL035-RGB-002
   - PDA 91-00156-A0
   - Innolux EE101IA-01D

  i915:
   - Enable fastboot by default on SKL+/VLV/CHV
   - Export RPCS configuration for ICL media driver
   - Coffelake PCI ID
   - CNL clocks setup fixes
   - ACPI/PMIC support for MIPI/DSI
   - Per-engine WA init for all engines
   - Shrinker locking fixes
   - Kerneldoc updates
   - Lots of ring improvements and reset fixes
   - Coffeelake GVT Support
   - VFIO GVT EDID Region support
   - runtime PM wakeref tracking
   - ILK->IVB primary plane enable delays
   - userptr mutex locking fixes
   - DSI fixes
   - LVDS/TV cleanups
   - HW readout fixes
   - LUT robustness fixes
   - ICL display and watermark fixes
   - gem mmap race fix

  amdgpu:
   - add scheduled dependencies interface
   - DCC on scanout surfaces
   - vega10/20 BACO support
   - Multiple IH rings on soc15
   - XGMI locking fixes
   - DC i2c/aux cleanups
   - runtime SMU debug interface
   - Kexec improvmeents
   - SR-IOV fixes
   - DC freesync + ABM fixes
   - GDS fixes
   - GPUVM fixes
   - vega20 PCIE DPM switching fixes
   - Context priority handling fixes

  radeon:
   - fix missing break in evergreen parser

  nouveau:
   - SVM support via HMM

  msm:
   - QCOM Compressed modifier support

  exynos:
   - s5pv210 rotator support

  imx:
   - zpos property support
   - pending update fixes

  v3d:
   - cache flush improvments

  vc4:
   - reflection support
   - HDMI overscan support

  tegra:
   - CEC refactoring
   - HDMI audio fixes
   - Tegra186 prep work
   - SOR crossbar device tree fixes

  sun4i:
   - implicit fencing support
   - YUV and scalar support improvements
   - A23 support
   - tiling fixes

  atmel-hlcdc:
   - clipping and rotation property fixes

  qxl:
   - BO and PRIME improvements
   - generic fbdev emulation

  dw-hdmi:
   - HDMI 2.0 2160p
   - YUV420 ouput

  rockchip:
   - implicit fencing support
   - reflection proerties

  virtio-gpu:
   - use generic fbdev emulation

  tilcdc:
   - cpufreq vs crtc init fix

  rcar-du:
   - R8A774C0 support
   - D3/E3 RGB output routing fixes and DPAD0 support
   - RA87744 LVDS support

  bochs:
   - atomic and generic fbdev emulation
   - ID mismatch error on bochs load

  meson:
   - remove firmware fbs"

* tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm: (1130 commits)
  drm/amd/display: Use vrr friendly pageflip throttling in DC.
  drm/imx: only send commit done event when all state has been applied
  drm/imx: allow building under COMPILE_TEST
  drm/imx: imx-tve: depend on COMMON_CLK
  drm/imx: ipuv3-plane: add zpos property
  drm/imx: ipuv3-plane: add function to query atomic update status
  gpu: ipu-v3: prg: add function to get channel configure status
  gpu: ipu-v3: pre: add double buffer status readback
  drm/amdgpu: Bump amdgpu version for context priority override.
  drm/amdgpu/powerplay: fix typo in BACO header guards
  drm/amdgpu/powerplay: fix return codes in BACO code
  drm/amdgpu: add missing license on baco files
  drm/bochs: Fix the ID mismatch error
  drm/nouveau/dmem: use dma addresses during migration copies
  drm/nouveau/dmem: use physical vram addresses during migration copies
  drm/nouveau/dmem: extend copy function to allow direct use of physical addresses
  drm/nouveau/svm: new ioctl to migrate process memory to GPU memory
  drm/nouveau/dmem: device memory helpers for SVM
  drm/nouveau/svm: initial support for shared virtual memory
  drm/nouveau: prepare for enabling svm with existing userspace interfaces
  ...

1 files changed, 224 insertions, 206 deletions

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index af2873403009..49fa43ff02ba 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,6 +25,7 @@
 #include <drm/drm_print.h>
 
 #include "i915_drv.h"
+#include "i915_reset.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
@@ -261,6 +262,31 @@ static void __sprint_engine_name(char *name, const struct engine_info *info)
 			 info->instance) >= INTEL_ENGINE_CS_MAX_NAME);
 }
 
+void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	i915_reg_t hwstam;
+
+	/*
+	 * Though they added more rings on g4x/ilk, they did not add
+	 * per-engine HWSTAM until gen6.
+	 */
+	if (INTEL_GEN(dev_priv) < 6 && engine->class != RENDER_CLASS)
+		return;
+
+	hwstam = RING_HWSTAM(engine->mmio_base);
+	if (INTEL_GEN(dev_priv) >= 3)
+		I915_WRITE(hwstam, mask);
+	else
+		I915_WRITE16(hwstam, mask);
+}
+
+static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine)
+{
+	/* Mask off all writes into the unknown HWSP */
+	intel_engine_set_hwsp_writemask(engine, ~0u);
+}
+
 static int
 intel_engine_setup(struct drm_i915_private *dev_priv,
 		   enum intel_engine_id id)
@@ -312,6 +338,9 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
+	/* Scrub mmio state on takeover */
+	intel_engine_sanitize_mmio(engine);
+
 	dev_priv->engine_class[info->class][info->instance] = engine;
 	dev_priv->engine[id] = engine;
 	return 0;
@@ -365,7 +394,7 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv)
 		goto cleanup;
 	}
 
-	device_info->num_rings = hweight32(mask);
+	RUNTIME_INFO(dev_priv)->num_rings = hweight32(mask);
 
 	i915_check_and_clear_faults(dev_priv);
 
@@ -426,33 +455,9 @@ cleanup:
 	return err;
 }
 
-void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
+void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
-	/* Our semaphore implementation is strictly monotonic (i.e. we proceed
-	 * so long as the semaphore value in the register/page is greater
-	 * than the sync value), so whenever we reset the seqno,
-	 * so long as we reset the tracking semaphore value to 0, it will
-	 * always be before the next request's seqno. If we don't reset
-	 * the semaphore value, then when the seqno moves backwards all
-	 * future waits will complete instantly (causing rendering corruption).
-	 */
-	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
-		I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
-		I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
-		if (HAS_VEBOX(dev_priv))
-			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
-	}
-
 	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-	clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
-
-	/* After manually advancing the seqno, fake the interrupt in case
-	 * there are any waiters for that seqno.
-	 */
-	intel_engine_wakeup(engine);
-
 	GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
 }
 
@@ -469,50 +474,67 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 	GEM_BUG_ON(!is_power_of_2(execlists_num_ports(execlists)));
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
-	execlists->queue_priority = INT_MIN;
+	execlists->queue_priority_hint = INT_MIN;
 	execlists->queue = RB_ROOT_CACHED;
 }
 
-/**
- * intel_engines_setup_common - setup engine state not requiring hw access
- * @engine: Engine to setup.
- *
- * Initializes @engine@ structure members shared between legacy and execlists
- * submission modes which do not require hardware access.
- *
- * Typically done early in the submission mode specific engine setup stage.
- */
-void intel_engine_setup_common(struct intel_engine_cs *engine)
+static void cleanup_status_page(struct intel_engine_cs *engine)
 {
-	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
-	i915_timeline_set_subclass(&engine->timeline, TIMELINE_ENGINE);
+	struct i915_vma *vma;
 
-	intel_engine_init_execlist(engine);
-	intel_engine_init_hangcheck(engine);
-	intel_engine_init_batch_pool(engine);
-	intel_engine_init_cmd_parser(engine);
+	/* Prevent writes into HWSP after returning the page to the system */
+	intel_engine_set_hwsp_writemask(engine, ~0u);
+
+	vma = fetch_and_zero(&engine->status_page.vma);
+	if (!vma)
+		return;
+
+	if (!HWS_NEEDS_PHYSICAL(engine->i915))
+		i915_vma_unpin(vma);
+
+	i915_gem_object_unpin_map(vma->obj);
+	__i915_gem_object_release_unless_active(vma->obj);
 }
 
-static void cleanup_status_page(struct intel_engine_cs *engine)
+static int pin_ggtt_status_page(struct intel_engine_cs *engine,
+				struct i915_vma *vma)
 {
-	if (HWS_NEEDS_PHYSICAL(engine->i915)) {
-		void *addr = fetch_and_zero(&engine->status_page.page_addr);
+	unsigned int flags;
 
-		__free_page(virt_to_page(addr));
-	}
+	flags = PIN_GLOBAL;
+	if (!HAS_LLC(engine->i915))
+		/*
+		 * On g33, we cannot place HWS above 256MiB, so
+		 * restrict its pinning to the low mappable arena.
+		 * Though this restriction is not documented for
+		 * gen4, gen5, or byt, they also behave similarly
+		 * and hang if the HWS is placed at the top of the
+		 * GTT. To generalise, it appears that all !llc
+		 * platforms have issues with us placing the HWS
+		 * above the mappable region (even though we never
+		 * actually map it).
+		 */
+		flags |= PIN_MAPPABLE;
+	else
+		flags |= PIN_HIGH;
 
-	i915_vma_unpin_and_release(&engine->status_page.vma,
-				   I915_VMA_RELEASE_MAP);
+	return i915_vma_pin(vma, 0, 0, flags);
 }
 
 static int init_status_page(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
-	unsigned int flags;
 	void *vaddr;
 	int ret;
 
+	/*
+	 * Though the HWS register does support 36bit addresses, historically
+	 * we have had hangs and corruption reported due to wild writes if
+	 * the HWS is placed above 4G. We only allow objects to be allocated
+	 * in GFP_DMA32 for i965, and no earlier physical address users had
+	 * access to more than 4G.
+	 */
 	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Failed to allocate status page\n");
@@ -529,59 +551,67 @@ static int init_status_page(struct intel_engine_cs *engine)
 		goto err;
 	}
 
-	flags = PIN_GLOBAL;
-	if (!HAS_LLC(engine->i915))
-		/* On g33, we cannot place HWS above 256MiB, so
-		 * restrict its pinning to the low mappable arena.
-		 * Though this restriction is not documented for
-		 * gen4, gen5, or byt, they also behave similarly
-		 * and hang if the HWS is placed at the top of the
-		 * GTT. To generalise, it appears that all !llc
-		 * platforms have issues with us placing the HWS
-		 * above the mappable region (even though we never
-		 * actually map it).
-		 */
-		flags |= PIN_MAPPABLE;
-	else
-		flags |= PIN_HIGH;
-	ret = i915_vma_pin(vma, 0, 0, flags);
-	if (ret)
-		goto err;
-
 	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
-		goto err_unpin;
+		goto err;
 	}
 
+	engine->status_page.addr = memset(vaddr, 0, PAGE_SIZE);
 	engine->status_page.vma = vma;
-	engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
-	engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE);
+
+	if (!HWS_NEEDS_PHYSICAL(engine->i915)) {
+		ret = pin_ggtt_status_page(engine, vma);
+		if (ret)
+			goto err_unpin;
+	}
+
 	return 0;
 
 err_unpin:
-	i915_vma_unpin(vma);
+	i915_gem_object_unpin_map(obj);
 err:
 	i915_gem_object_put(obj);
 	return ret;
 }
 
-static int init_phys_status_page(struct intel_engine_cs *engine)
+/**
+ * intel_engines_setup_common - setup engine state not requiring hw access
+ * @engine: Engine to setup.
+ *
+ * Initializes @engine@ structure members shared between legacy and execlists
+ * submission modes which do not require hardware access.
+ *
+ * Typically done early in the submission mode specific engine setup stage.
+ */
+int intel_engine_setup_common(struct intel_engine_cs *engine)
 {
-	struct page *page;
+	int err;
 
-	/*
-	 * Though the HWS register does support 36bit addresses, historically
-	 * we have had hangs and corruption reported due to wild writes if
-	 * the HWS is placed above 4G.
-	 */
-	page = alloc_page(GFP_KERNEL | __GFP_DMA32 | __GFP_ZERO);
-	if (!page)
-		return -ENOMEM;
+	err = init_status_page(engine);
+	if (err)
+		return err;
+
+	err = i915_timeline_init(engine->i915,
+				 &engine->timeline,
+				 engine->name,
+				 engine->status_page.vma);
+	if (err)
+		goto err_hwsp;
 
-	engine->status_page.page_addr = page_address(page);
+	i915_timeline_set_subclass(&engine->timeline, TIMELINE_ENGINE);
+
+	intel_engine_init_breadcrumbs(engine);
+	intel_engine_init_execlist(engine);
+	intel_engine_init_hangcheck(engine);
+	intel_engine_init_batch_pool(engine);
+	intel_engine_init_cmd_parser(engine);
 
 	return 0;
+
+err_hwsp:
+	cleanup_status_page(engine);
+	return err;
 }
 
 static void __intel_context_unpin(struct i915_gem_context *ctx,
@@ -590,6 +620,56 @@ static void __intel_context_unpin(struct i915_gem_context *ctx,
 	intel_context_unpin(to_intel_context(ctx, engine));
 }
 
+struct measure_breadcrumb {
+	struct i915_request rq;
+	struct i915_timeline timeline;
+	struct intel_ring ring;
+	u32 cs[1024];
+};
+
+static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
+{
+	struct measure_breadcrumb *frame;
+	int dw = -ENOMEM;
+
+	GEM_BUG_ON(!engine->i915->gt.scratch);
+
+	frame = kzalloc(sizeof(*frame), GFP_KERNEL);
+	if (!frame)
+		return -ENOMEM;
+
+	if (i915_timeline_init(engine->i915,
+			       &frame->timeline, "measure",
+			       engine->status_page.vma))
+		goto out_frame;
+
+	INIT_LIST_HEAD(&frame->ring.request_list);
+	frame->ring.timeline = &frame->timeline;
+	frame->ring.vaddr = frame->cs;
+	frame->ring.size = sizeof(frame->cs);
+	frame->ring.effective_size = frame->ring.size;
+	intel_ring_update_space(&frame->ring);
+
+	frame->rq.i915 = engine->i915;
+	frame->rq.engine = engine;
+	frame->rq.ring = &frame->ring;
+	frame->rq.timeline = &frame->timeline;
+
+	dw = i915_timeline_pin(&frame->timeline);
+	if (dw < 0)
+		goto out_timeline;
+
+	dw = engine->emit_fini_breadcrumb(&frame->rq, frame->cs) - frame->cs;
+
+	i915_timeline_unpin(&frame->timeline);
+
+out_timeline:
+	i915_timeline_fini(&frame->timeline);
+out_frame:
+	kfree(frame);
+	return dw;
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -632,21 +712,14 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 		}
 	}
 
-	ret = intel_engine_init_breadcrumbs(engine);
-	if (ret)
+	ret = measure_breadcrumb_dw(engine);
+	if (ret < 0)
 		goto err_unpin_preempt;
 
-	if (HWS_NEEDS_PHYSICAL(i915))
-		ret = init_phys_status_page(engine);
-	else
-		ret = init_status_page(engine);
-	if (ret)
-		goto err_breadcrumbs;
+	engine->emit_fini_breadcrumb_dw = ret;
 
 	return 0;
 
-err_breadcrumbs:
-	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
 	if (i915->preempt_context)
 		__intel_context_unpin(i915->preempt_context, engine);
@@ -769,12 +842,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 
 u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
 {
-	const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 mcr_s_ss_select;
 	u32 slice = fls(sseu->slice_mask);
 	u32 subslice = fls(sseu->subslice_mask[slice]);
 
-	if (IS_GEN10(dev_priv))
+	if (IS_GEN(dev_priv, 10))
 		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
 				  GEN8_MCR_SUBSLICE(subslice);
 	else if (INTEL_GEN(dev_priv) >= 11)
@@ -786,15 +859,15 @@ u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
 	return mcr_s_ss_select;
 }
 
-static inline uint32_t
+static inline u32
 read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 		  int subslice, i915_reg_t reg)
 {
-	uint32_t mcr_slice_subslice_mask;
-	uint32_t mcr_slice_subslice_select;
-	uint32_t default_mcr_s_ss_select;
-	uint32_t mcr;
-	uint32_t ret;
+	u32 mcr_slice_subslice_mask;
+	u32 mcr_slice_subslice_select;
+	u32 default_mcr_s_ss_select;
+	u32 mcr;
+	u32 ret;
 	enum forcewake_domains fw_domains;
 
 	if (INTEL_GEN(dev_priv) >= 11) {
@@ -900,10 +973,15 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 static bool ring_is_idle(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	intel_wakeref_t wakeref;
 	bool idle = true;
 
+	if (I915_SELFTEST_ONLY(!engine->mmio_base))
+		return true;
+
 	/* If the whole device is asleep, the engine must be idle */
-	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (!wakeref)
 		return true;
 
 	/* First check that no commands are left in the ring */
@@ -915,7 +993,7 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
 		idle = false;
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return idle;
 }
@@ -939,9 +1017,6 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	if (!intel_engine_signaled(engine, intel_engine_last_submit(engine)))
 		return false;
 
-	if (I915_SELFTEST_ONLY(engine->breadcrumbs.mock))
-		return true;
-
 	/* Waiting to drain ELSP? */
 	if (READ_ONCE(engine->execlists.active)) {
 		struct tasklet_struct *t = &engine->execlists.tasklet;
@@ -967,10 +1042,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return false;
 
 	/* Ring stopped? */
-	if (!ring_is_idle(engine))
-		return false;
-
-	return true;
+	return ring_is_idle(engine);
 }
 
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
@@ -1014,7 +1086,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 * the last request that remains in the timeline. When idle, it is
 	 * the last executed context as tracked by retirement.
 	 */
-	rq = __i915_gem_active_peek(&engine->timeline.last_request);
+	rq = __i915_active_request_peek(&engine->timeline.last_request);
 	if (rq)
 		return rq->hw_context == kernel_context;
 	else
@@ -1030,26 +1102,36 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 		engine->set_default_submission(engine);
 }
 
+static bool reset_engines(struct drm_i915_private *i915)
+{
+	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
+		return false;
+
+	return intel_gpu_reset(i915, ALL_ENGINES) == 0;
+}
+
 /**
  * intel_engines_sanitize: called after the GPU has lost power
  * @i915: the i915 device
+ * @force: ignore a failed reset and sanitize engine state anyway
  *
  * Anytime we reset the GPU, either with an explicit GPU reset or through a
  * PCI power cycle, the GPU loses state and we must reset our state tracking
  * to match. Note that calling intel_engines_sanitize() if the GPU has not
  * been reset results in much confusion!
  */
-void intel_engines_sanitize(struct drm_i915_private *i915)
+void intel_engines_sanitize(struct drm_i915_private *i915, bool force)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
 	GEM_TRACE("\n");
 
-	for_each_engine(engine, i915, id) {
-		if (engine->reset.reset)
-			engine->reset.reset(engine, NULL);
-	}
+	if (!reset_engines(i915) && !force)
+		return;
+
+	for_each_engine(engine, i915, id)
+		intel_engine_reset(engine, false);
 }
 
 /**
@@ -1085,7 +1167,7 @@ void intel_engines_park(struct drm_i915_private *i915)
 		}
 
 		/* Must be reset upon idling, or we may miss the busy wakeup. */
-		GEM_BUG_ON(engine->execlists.queue_priority != INT_MIN);
+		GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN);
 
 		if (engine->park)
 			engine->park(engine);
@@ -1201,10 +1283,14 @@ static void print_request(struct drm_printer *m,
 
 	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
 
-	drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n",
+	drm_printf(m, "%s%x%s%s [%llx:%llx]%s @ %dms: %s\n",
 		   prefix,
 		   rq->global_seqno,
-		   i915_request_completed(rq) ? "!" : "",
+		   i915_request_completed(rq) ? "!" :
+		   i915_request_started(rq) ? "*" :
+		   "",
+		   test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
+			    &rq->fence.flags) ?  "+" : "",
 		   rq->fence.context, rq->fence.seqno,
 		   buf,
 		   jiffies_to_msecs(jiffies - rq->emitted_jiffies),
@@ -1248,7 +1334,7 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		&engine->execlists;
 	u64 addr;
 
-	if (engine->id == RCS && IS_GEN(dev_priv, 4, 7))
+	if (engine->id == RCS && IS_GEN_RANGE(dev_priv, 4, 7))
 		drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID));
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   I915_READ(RING_START(engine->mmio_base)));
@@ -1269,16 +1355,6 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		drm_printf(m, "\tRING_IMR: %08x\n", I915_READ_IMR(engine));
 	}
 
-	if (HAS_LEGACY_SEMAPHORES(dev_priv)) {
-		drm_printf(m, "\tSYNC_0: 0x%08x\n",
-			   I915_READ(RING_SYNC_0(engine->mmio_base)));
-		drm_printf(m, "\tSYNC_1: 0x%08x\n",
-			   I915_READ(RING_SYNC_1(engine->mmio_base)));
-		if (HAS_VEBOX(dev_priv))
-			drm_printf(m, "\tSYNC_2: 0x%08x\n",
-				   I915_READ(RING_SYNC_2(engine->mmio_base)));
-	}
-
 	addr = intel_engine_get_active_head(engine);
 	drm_printf(m, "\tACTHD:  0x%08x_%08x\n",
 		   upper_32_bits(addr), lower_32_bits(addr));
@@ -1305,7 +1381,8 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 	}
 
 	if (HAS_EXECLISTS(dev_priv)) {
-		const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+		const u32 *hws =
+			&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
 		unsigned int idx;
 		u8 read, write;
 
@@ -1348,9 +1425,10 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 				char hdr[80];
 
 				snprintf(hdr, sizeof(hdr),
-					 "\t\tELSP[%d] count=%d, ring->start=%08x, rq: ",
+					 "\t\tELSP[%d] count=%d, ring:{start:%08x, hwsp:%08x}, rq: ",
 					 idx, count,
-					 i915_ggtt_offset(rq->ring->vma));
+					 i915_ggtt_offset(rq->ring->vma),
+					 rq->timeline->hwsp_offset);
 				print_request(m, rq, hdr);
 			} else {
 				drm_printf(m, "\t\tELSP[%d] idle\n", idx);
@@ -1405,14 +1483,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
 {
-	const int MAX_REQUESTS_TO_SHOW = 8;
-	struct intel_breadcrumbs * const b = &engine->breadcrumbs;
-	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
-	struct i915_request *rq, *last;
-	unsigned long flags;
-	struct rb_node *rb;
-	int count;
+	struct i915_request *rq;
+	intel_wakeref_t wakeref;
 
 	if (header) {
 		va_list ap;
@@ -1462,85 +1535,30 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->ring->emit);
 		drm_printf(m, "\t\tring->space:  0x%08x\n",
 			   rq->ring->space);
+		drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
+			   rq->timeline->hwsp_offset);
 
 		print_request_ring(m, rq);
 	}
 
 	rcu_read_unlock();
 
-	if (intel_runtime_pm_get_if_in_use(engine->i915)) {
+	wakeref = intel_runtime_pm_get_if_in_use(engine->i915);
+	if (wakeref) {
 		intel_engine_print_registers(engine, m);
-		intel_runtime_pm_put(engine->i915);
+		intel_runtime_pm_put(engine->i915, wakeref);
 	} else {
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
 
-	local_irq_save(flags);
-	spin_lock(&engine->timeline.lock);
-
-	last = NULL;
-	count = 0;
-	list_for_each_entry(rq, &engine->timeline.requests, link) {
-		if (count++ < MAX_REQUESTS_TO_SHOW - 1)
-			print_request(m, rq, "\t\tE ");
-		else
-			last = rq;
-	}
-	if (last) {
-		if (count > MAX_REQUESTS_TO_SHOW) {
-			drm_printf(m,
-				   "\t\t...skipping %d executing requests...\n",
-				   count - MAX_REQUESTS_TO_SHOW);
-		}
-		print_request(m, last, "\t\tE ");
-	}
-
-	last = NULL;
-	count = 0;
-	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	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) {
-			if (count++ < MAX_REQUESTS_TO_SHOW - 1)
-				print_request(m, rq, "\t\tQ ");
-			else
-				last = rq;
-		}
-	}
-	if (last) {
-		if (count > MAX_REQUESTS_TO_SHOW) {
-			drm_printf(m,
-				   "\t\t...skipping %d queued requests...\n",
-				   count - MAX_REQUESTS_TO_SHOW);
-		}
-		print_request(m, last, "\t\tQ ");
-	}
-
-	spin_unlock(&engine->timeline.lock);
-
-	spin_lock(&b->rb_lock);
-	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
-		struct intel_wait *w = rb_entry(rb, typeof(*w), node);
-
-		drm_printf(m, "\t%s [%d:%c] waiting for %x\n",
-			   w->tsk->comm, w->tsk->pid,
-			   task_state_to_char(w->tsk),
-			   w->seqno);
-	}
-	spin_unlock(&b->rb_lock);
-	local_irq_restore(flags);
-
-	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
-		   engine->irq_posted,
-		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-				  &engine->irq_posted)));
+	intel_execlists_show_requests(engine, m, print_request, 8);
 
 	drm_printf(m, "HWSP:\n");
-	hexdump(m, engine->status_page.page_addr, PAGE_SIZE);
+	hexdump(m, engine->status_page.addr, PAGE_SIZE);
 
 	drm_printf(m, "Idle? %s\n", yesno(intel_engine_is_idle(engine)));
+
+	intel_engine_print_breadcrumbs(engine, m);
 }
 
 static u8 user_class_map[] = {