Merge tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This has two exciting community drivers for ARM Mali accelerators.
  Since ARM has never been open source friendly on the GPU side of the
  house, the community has had to create open source drivers for the
  Mali GPUs. Lima covers the older t4xx and panfrost the newer 6xx/7xx
  series. Well done to all involved and hopefully this will help ARM
  head in the right direction.

  There is also now the ability if you don't have any of the legacy
  drivers enabled (pre-KMS) to remove all the pre-KMS support code from
  the core drm, this saves 10% or so in codesize on my machine.

  i915 also enable Icelake/Elkhart Lake Gen11 GPUs by default, vboxvideo
  moves out of staging.

  There are also some rcar-du patches which crossover with media tree
  but all should be acked by Mauro.

  Summary:

  uapi changes:
   - Colorspace connector property
   - fourcc - new YUV formts
   - timeline sync objects initially merged
   - expose FB_DAMAGE_CLIPS to atomic userspace

  new drivers:
   - vboxvideo: moved out of staging
   - aspeed: ASPEED SoC BMC chip display support
   - lima: ARM Mali4xx GPU acceleration driver support
   - panfrost: ARM Mali6xx/7xx Midgard/Bitfrost acceleration driver support

  core:
   - component helper docs
   - unplugging fixes
   - devm device init
   - MIPI/DSI rate control
   - shmem backed gem objects
   - connector, display_info, edid_quirks cleanups
   - dma_buf fence chain support
   - 64-bit dma-fence seqno comparison fixes
   - move initial fb config code to core
   - gem fence array helpers for Lima
   - ability to remove legacy support code if no drivers requires it (removes 10% of drm.ko size)
   - lease fixes

  ttm:
   - unified DRM_FILE_PAGE_OFFSET handling
   - Account for kernel allocations in kernel zone only

  panel:
   - OSD070T1718-19TS panel support
   - panel-tpo-td028ttec1 backlight support
   - Ronbo RB070D30 MIPI/DSI
   - Feiyang FY07024DI26A30-D MIPI-DSI panel
   - Rocktech jh057n00900 MIPI-DSI panel

  i915:
   - Comet Lake (Gen9) PCI IDs
   - Updated Icelake PCI IDs
   - Elkhartlake (Gen11) support
   - DP MST property addtions
   - plane and watermark fixes
   - Icelake port sync and VEBOX disable fixes
   - struct_mutex usage reduction
   - Icelake gamma fix
   - GuC reset fixes
   - make mmap more asynchronous
   - sound display power well race fixes
   - DDI/MIPI-DSI clocks for Icelake
   - Icelake RPS frequency changing support
   - Icelake workarounds

  amdgpu:
   - Use HMM for userptr
   - vega20 experimental smu11 support
   - RAS support for vega20
   - BACO support for vega12 + fixes for vega20
   - reworked IH interrupt handling
   - amdkfd RAS support
   - Freesync improvements
   - initial timeline sync object support
   - DC Z ordering fixes
   - NV12 planes support
   - colorspace properties for planes=
   - eDP opts if eDP already initialized

  nouveau:
   - misc fixes

  etnaviv:
   - misc fixes

  msm:
   - GPU zap shader support expansion
   - robustness ABI addition

  exynos:
   - Logging cleanups

  tegra:
   - Shared reset fix
   - CPU cache maintenance fix

  cirrus:
   - driver rewritten using simple helpers

  meson:
   - G12A support

  vmwgfx:
   - Resource dirtying management improvements
   - Userspace logging improvements

  virtio:
   - PRIME fixes

  rockchip:
   - rk3066 hdmi support

  sun4i:
   - DSI burst mode support

  vc4:
   - load tracker to detect underflow

  v3d:
   - v3d v4.2 support

  malidp:
   - initial Mali D71 support in komeda driver

  tfp410:
   - omap related improvement

  omapdrm:
   - drm bridge/panel support
   - drop some omap specific panels

  rcar-du:
   - Display writeback support"

* tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm: (1507 commits)
  drm/msm/a6xx: No zap shader is not an error
  drm/cma-helper: Fix drm_gem_cma_free_object()
  drm: Fix timestamp docs for variable refresh properties.
  drm/komeda: Mark the local functions as static
  drm/komeda: Fixed warning: Function parameter or member not described
  drm/komeda: Expose bus_width to Komeda-CORE
  drm/komeda: Add sysfs attribute: core_id and config_id
  drm: add non-desktop quirk for Valve HMDs
  drm/panfrost: Show stored feature registers
  drm/panfrost: Don't scream about deferred probe
  drm/panfrost: Disable PM on probe failure
  drm/panfrost: Set DMA masks earlier
  drm/panfrost: Add sanity checks to submit IOCTL
  drm/etnaviv: initialize idle mask before querying the HW db
  drm: introduce a capability flag for syncobj timeline support
  drm: report consistent errors when checking syncobj capibility
  drm/nouveau/nouveau: forward error generated while resuming objects tree
  drm/nouveau/fb/ramgk104: fix spelling mistake "sucessfully" -> "successfully"
  drm/nouveau/i2c: Disable i2c bus access after ->fini()
  drm/nouveau: Remove duplicate ACPI_VIDEO_NOTIFY_PROBE definition
  ...

1 files changed, 277 insertions, 214 deletions

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 49fa43ff02ba..eea9bec04f1b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -84,7 +84,6 @@ static const struct engine_class_info intel_engine_classes[] = {
 #define MAX_MMIO_BASES 3
 struct engine_info {
 	unsigned int hw_id;
-	unsigned int uabi_id;
 	u8 class;
 	u8 instance;
 	/* mmio bases table *must* be sorted in reverse gen order */
@@ -95,27 +94,24 @@ struct engine_info {
 };
 
 static const struct engine_info intel_engines[] = {
-	[RCS] = {
-		.hw_id = RCS_HW,
-		.uabi_id = I915_EXEC_RENDER,
+	[RCS0] = {
+		.hw_id = RCS0_HW,
 		.class = RENDER_CLASS,
 		.instance = 0,
 		.mmio_bases = {
 			{ .gen = 1, .base = RENDER_RING_BASE }
 		},
 	},
-	[BCS] = {
-		.hw_id = BCS_HW,
-		.uabi_id = I915_EXEC_BLT,
+	[BCS0] = {
+		.hw_id = BCS0_HW,
 		.class = COPY_ENGINE_CLASS,
 		.instance = 0,
 		.mmio_bases = {
 			{ .gen = 6, .base = BLT_RING_BASE }
 		},
 	},
-	[VCS] = {
-		.hw_id = VCS_HW,
-		.uabi_id = I915_EXEC_BSD,
+	[VCS0] = {
+		.hw_id = VCS0_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -124,9 +120,8 @@ static const struct engine_info intel_engines[] = {
 			{ .gen = 4, .base = BSD_RING_BASE }
 		},
 	},
-	[VCS2] = {
-		.hw_id = VCS2_HW,
-		.uabi_id = I915_EXEC_BSD,
+	[VCS1] = {
+		.hw_id = VCS1_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 1,
 		.mmio_bases = {
@@ -134,27 +129,24 @@ static const struct engine_info intel_engines[] = {
 			{ .gen = 8, .base = GEN8_BSD2_RING_BASE }
 		},
 	},
-	[VCS3] = {
-		.hw_id = VCS3_HW,
-		.uabi_id = I915_EXEC_BSD,
+	[VCS2] = {
+		.hw_id = VCS2_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 2,
 		.mmio_bases = {
 			{ .gen = 11, .base = GEN11_BSD3_RING_BASE }
 		},
 	},
-	[VCS4] = {
-		.hw_id = VCS4_HW,
-		.uabi_id = I915_EXEC_BSD,
+	[VCS3] = {
+		.hw_id = VCS3_HW,
 		.class = VIDEO_DECODE_CLASS,
 		.instance = 3,
 		.mmio_bases = {
 			{ .gen = 11, .base = GEN11_BSD4_RING_BASE }
 		},
 	},
-	[VECS] = {
-		.hw_id = VECS_HW,
-		.uabi_id = I915_EXEC_VEBOX,
+	[VECS0] = {
+		.hw_id = VECS0_HW,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 0,
 		.mmio_bases = {
@@ -162,9 +154,8 @@ static const struct engine_info intel_engines[] = {
 			{ .gen = 7, .base = VEBOX_RING_BASE }
 		},
 	},
-	[VECS2] = {
-		.hw_id = VECS2_HW,
-		.uabi_id = I915_EXEC_VEBOX,
+	[VECS1] = {
+		.hw_id = VECS1_HW,
 		.class = VIDEO_ENHANCEMENT_CLASS,
 		.instance = 1,
 		.mmio_bases = {
@@ -264,21 +255,17 @@ static void __sprint_engine_name(char *name, const struct engine_info *info)
 
 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)
+	if (INTEL_GEN(engine->i915) < 6 && engine->class != RENDER_CLASS)
 		return;
 
-	hwstam = RING_HWSTAM(engine->mmio_base);
-	if (INTEL_GEN(dev_priv) >= 3)
-		I915_WRITE(hwstam, mask);
+	if (INTEL_GEN(engine->i915) >= 3)
+		ENGINE_WRITE(engine, RING_HWSTAM, mask);
 	else
-		I915_WRITE16(hwstam, mask);
+		ENGINE_WRITE16(engine, RING_HWSTAM, mask);
 }
 
 static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine)
@@ -313,15 +300,18 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	if (!engine)
 		return -ENOMEM;
 
+	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);
+
 	engine->id = id;
+	engine->mask = BIT(id);
 	engine->i915 = dev_priv;
+	engine->uncore = &dev_priv->uncore;
 	__sprint_engine_name(engine->name, info);
 	engine->hw_id = engine->guc_id = info->hw_id;
 	engine->mmio_base = __engine_mmio_base(dev_priv, info->mmio_bases);
 	engine->class = info->class;
 	engine->instance = info->instance;
 
-	engine->uabi_id = info->uabi_id;
 	engine->uabi_class = intel_engine_classes[info->class].uabi_class;
 
 	engine->context_size = __intel_engine_context_size(dev_priv,
@@ -355,15 +345,15 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 int intel_engines_init_mmio(struct drm_i915_private *dev_priv)
 {
 	struct intel_device_info *device_info = mkwrite_device_info(dev_priv);
-	const unsigned int ring_mask = INTEL_INFO(dev_priv)->ring_mask;
+	const unsigned int engine_mask = INTEL_INFO(dev_priv)->engine_mask;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	unsigned int mask = 0;
 	unsigned int i;
 	int err;
 
-	WARN_ON(ring_mask == 0);
-	WARN_ON(ring_mask &
+	WARN_ON(engine_mask == 0);
+	WARN_ON(engine_mask &
 		GENMASK(BITS_PER_TYPE(mask) - 1, I915_NUM_ENGINES));
 
 	if (i915_inject_load_failure())
@@ -377,7 +367,7 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv)
 		if (err)
 			goto cleanup;
 
-		mask |= ENGINE_MASK(i);
+		mask |= BIT(i);
 	}
 
 	/*
@@ -385,16 +375,16 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv)
 	 * are added to the driver by a warning and disabling the forgotten
 	 * engines.
 	 */
-	if (WARN_ON(mask != ring_mask))
-		device_info->ring_mask = mask;
+	if (WARN_ON(mask != engine_mask))
+		device_info->engine_mask = mask;
 
 	/* We always presume we have at least RCS available for later probing */
-	if (WARN_ON(!HAS_ENGINE(dev_priv, RCS))) {
+	if (WARN_ON(!HAS_ENGINE(dev_priv, RCS0))) {
 		err = -ENODEV;
 		goto cleanup;
 	}
 
-	RUNTIME_INFO(dev_priv)->num_rings = hweight32(mask);
+	RUNTIME_INFO(dev_priv)->num_engines = hweight32(mask);
 
 	i915_check_and_clear_faults(dev_priv);
 
@@ -455,12 +445,6 @@ cleanup:
 	return err;
 }
 
-void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-	GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
-}
-
 static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 {
 	i915_gem_batch_pool_init(&engine->batch_pool, engine);
@@ -541,9 +525,7 @@ static int init_status_page(struct intel_engine_cs *engine)
 		return PTR_ERR(obj);
 	}
 
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-	if (ret)
-		goto err;
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
 
 	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
@@ -594,7 +576,6 @@ int intel_engine_setup_common(struct intel_engine_cs *engine)
 
 	err = i915_timeline_init(engine->i915,
 				 &engine->timeline,
-				 engine->name,
 				 engine->status_page.vma);
 	if (err)
 		goto err_hwsp;
@@ -614,10 +595,44 @@ err_hwsp:
 	return err;
 }
 
-static void __intel_context_unpin(struct i915_gem_context *ctx,
-				  struct intel_engine_cs *engine)
+void intel_engines_set_scheduler_caps(struct drm_i915_private *i915)
 {
-	intel_context_unpin(to_intel_context(ctx, engine));
+	static const struct {
+		u8 engine;
+		u8 sched;
+	} map[] = {
+#define MAP(x, y) { ilog2(I915_ENGINE_HAS_##x), ilog2(I915_SCHEDULER_CAP_##y) }
+		MAP(PREEMPTION, PREEMPTION),
+		MAP(SEMAPHORES, SEMAPHORES),
+#undef MAP
+	};
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 enabled, disabled;
+
+	enabled = 0;
+	disabled = 0;
+	for_each_engine(engine, i915, id) { /* all engines must agree! */
+		int i;
+
+		if (engine->schedule)
+			enabled |= (I915_SCHEDULER_CAP_ENABLED |
+				    I915_SCHEDULER_CAP_PRIORITY);
+		else
+			disabled |= (I915_SCHEDULER_CAP_ENABLED |
+				     I915_SCHEDULER_CAP_PRIORITY);
+
+		for (i = 0; i < ARRAY_SIZE(map); i++) {
+			if (engine->flags & BIT(map[i].engine))
+				enabled |= BIT(map[i].sched);
+			else
+				disabled |= BIT(map[i].sched);
+		}
+	}
+
+	i915->caps.scheduler = enabled & ~disabled;
+	if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_ENABLED))
+		i915->caps.scheduler = 0;
 }
 
 struct measure_breadcrumb {
@@ -639,7 +654,7 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
 		return -ENOMEM;
 
 	if (i915_timeline_init(engine->i915,
-			       &frame->timeline, "measure",
+			       &frame->timeline,
 			       engine->status_page.vma))
 		goto out_frame;
 
@@ -670,6 +685,20 @@ out_frame:
 	return dw;
 }
 
+static int pin_context(struct i915_gem_context *ctx,
+		       struct intel_engine_cs *engine,
+		       struct intel_context **out)
+{
+	struct intel_context *ce;
+
+	ce = intel_context_pin(ctx, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	*out = ce;
+	return 0;
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -684,11 +713,8 @@ out_frame:
 int intel_engine_init_common(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
-	struct intel_context *ce;
 	int ret;
 
-	engine->set_default_submission(engine);
-
 	/* We may need to do things with the shrinker which
 	 * require us to immediately switch back to the default
 	 * context. This can cause a problem as pinning the
@@ -696,39 +722,61 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ce = intel_context_pin(i915->kernel_context, engine);
-	if (IS_ERR(ce))
-		return PTR_ERR(ce);
+	ret = pin_context(i915->kernel_context, engine,
+			  &engine->kernel_context);
+	if (ret)
+		return ret;
 
 	/*
 	 * Similarly the preempt context must always be available so that
-	 * we can interrupt the engine at any time.
+	 * we can interrupt the engine at any time. However, as preemption
+	 * is optional, we allow it to fail.
 	 */
-	if (i915->preempt_context) {
-		ce = intel_context_pin(i915->preempt_context, engine);
-		if (IS_ERR(ce)) {
-			ret = PTR_ERR(ce);
-			goto err_unpin_kernel;
-		}
-	}
+	if (i915->preempt_context)
+		pin_context(i915->preempt_context, engine,
+			    &engine->preempt_context);
 
 	ret = measure_breadcrumb_dw(engine);
 	if (ret < 0)
-		goto err_unpin_preempt;
+		goto err_unpin;
 
 	engine->emit_fini_breadcrumb_dw = ret;
 
-	return 0;
+	engine->set_default_submission(engine);
 
-err_unpin_preempt:
-	if (i915->preempt_context)
-		__intel_context_unpin(i915->preempt_context, engine);
+	return 0;
 
-err_unpin_kernel:
-	__intel_context_unpin(i915->kernel_context, engine);
+err_unpin:
+	if (engine->preempt_context)
+		intel_context_unpin(engine->preempt_context);
+	intel_context_unpin(engine->kernel_context);
 	return ret;
 }
 
+void intel_gt_resume(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/*
+	 * After resume, we may need to poke into the pinned kernel
+	 * contexts to paper over any damage caused by the sudden suspend.
+	 * Only the kernel contexts should remain pinned over suspend,
+	 * allowing us to fixup the user contexts on their first pin.
+	 */
+	for_each_engine(engine, i915, id) {
+		struct intel_context *ce;
+
+		ce = engine->kernel_context;
+		if (ce)
+			ce->ops->reset(ce);
+
+		ce = engine->preempt_context;
+		if (ce)
+			ce->ops->reset(ce);
+	}
+}
+
 /**
  * intel_engines_cleanup_common - cleans up the engine state created by
  *                                the common initiailizers.
@@ -738,8 +786,6 @@ err_unpin_kernel:
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = engine->i915;
-
 	cleanup_status_page(engine);
 
 	intel_engine_fini_breadcrumbs(engine);
@@ -749,9 +795,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	if (i915->preempt_context)
-		__intel_context_unpin(i915->preempt_context, engine);
-	__intel_context_unpin(i915->kernel_context, engine);
+	if (engine->preempt_context)
+		intel_context_unpin(engine->preempt_context);
+	intel_context_unpin(engine->kernel_context);
 
 	i915_timeline_fini(&engine->timeline);
 
@@ -762,50 +808,48 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	struct drm_i915_private *i915 = engine->i915;
+
 	u64 acthd;
 
-	if (INTEL_GEN(dev_priv) >= 8)
-		acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base),
-					 RING_ACTHD_UDW(engine->mmio_base));
-	else if (INTEL_GEN(dev_priv) >= 4)
-		acthd = I915_READ(RING_ACTHD(engine->mmio_base));
+	if (INTEL_GEN(i915) >= 8)
+		acthd = ENGINE_READ64(engine, RING_ACTHD, RING_ACTHD_UDW);
+	else if (INTEL_GEN(i915) >= 4)
+		acthd = ENGINE_READ(engine, RING_ACTHD);
 	else
-		acthd = I915_READ(ACTHD);
+		acthd = ENGINE_READ(engine, ACTHD);
 
 	return acthd;
 }
 
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	u64 bbaddr;
 
-	if (INTEL_GEN(dev_priv) >= 8)
-		bbaddr = I915_READ64_2x32(RING_BBADDR(engine->mmio_base),
-					  RING_BBADDR_UDW(engine->mmio_base));
+	if (INTEL_GEN(engine->i915) >= 8)
+		bbaddr = ENGINE_READ64(engine, RING_BBADDR, RING_BBADDR_UDW);
 	else
-		bbaddr = I915_READ(RING_BBADDR(engine->mmio_base));
+		bbaddr = ENGINE_READ(engine, RING_BBADDR);
 
 	return bbaddr;
 }
 
 int intel_engine_stop_cs(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
 	const u32 base = engine->mmio_base;
 	const i915_reg_t mode = RING_MI_MODE(base);
 	int err;
 
-	if (INTEL_GEN(dev_priv) < 3)
+	if (INTEL_GEN(engine->i915) < 3)
 		return -ENODEV;
 
 	GEM_TRACE("%s\n", engine->name);
 
-	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
 
 	err = 0;
-	if (__intel_wait_for_register_fw(dev_priv,
+	if (__intel_wait_for_register_fw(uncore,
 					 mode, MODE_IDLE, MODE_IDLE,
 					 1000, 0,
 					 NULL)) {
@@ -814,19 +858,16 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 	}
 
 	/* A final mmio read to let GPU writes be hopefully flushed to memory */
-	POSTING_READ_FW(mode);
+	intel_uncore_posting_read_fw(uncore, mode);
 
 	return err;
 }
 
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
 	GEM_TRACE("%s\n", engine->name);
 
-	I915_WRITE_FW(RING_MI_MODE(engine->mmio_base),
-		      _MASKED_BIT_DISABLE(STOP_RING));
+	ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
 }
 
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
@@ -863,6 +904,7 @@ static inline u32
 read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 		  int subslice, i915_reg_t reg)
 {
+	struct intel_uncore *uncore = &dev_priv->uncore;
 	u32 mcr_slice_subslice_mask;
 	u32 mcr_slice_subslice_select;
 	u32 default_mcr_s_ss_select;
@@ -884,33 +926,33 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 
 	default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
 
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
 						    FW_REG_READ);
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
+	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
 						     GEN8_MCR_SELECTOR,
 						     FW_REG_READ | FW_REG_WRITE);
 
-	spin_lock_irq(&dev_priv->uncore.lock);
-	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+	spin_lock_irq(&uncore->lock);
+	intel_uncore_forcewake_get__locked(uncore, fw_domains);
 
-	mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
+	mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
 
 	WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) !=
 		     default_mcr_s_ss_select);
 
 	mcr &= ~mcr_slice_subslice_mask;
 	mcr |= mcr_slice_subslice_select;
-	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
+	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 
-	ret = I915_READ_FW(reg);
+	ret = intel_uncore_read_fw(uncore, reg);
 
 	mcr &= ~mcr_slice_subslice_mask;
 	mcr |= default_mcr_s_ss_select;
 
-	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
+	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 
-	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
-	spin_unlock_irq(&dev_priv->uncore.lock);
+	intel_uncore_forcewake_put__locked(uncore, fw_domains);
+	spin_unlock_irq(&uncore->lock);
 
 	return ret;
 }
@@ -920,6 +962,7 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
 	u32 mmio_base = engine->mmio_base;
 	int slice;
 	int subslice;
@@ -928,12 +971,14 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 
 	switch (INTEL_GEN(dev_priv)) {
 	default:
-		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
+		instdone->instdone =
+			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
-		if (engine->id != RCS)
+		if (engine->id != RCS0)
 			break;
 
-		instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
+		instdone->slice_common =
+			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
 		for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
 			instdone->sampler[slice][subslice] =
 				read_subslice_reg(dev_priv, slice, subslice,
@@ -944,28 +989,33 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 		}
 		break;
 	case 7:
-		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
+		instdone->instdone =
+			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
-		if (engine->id != RCS)
+		if (engine->id != RCS0)
 			break;
 
-		instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
-		instdone->sampler[0][0] = I915_READ(GEN7_SAMPLER_INSTDONE);
-		instdone->row[0][0] = I915_READ(GEN7_ROW_INSTDONE);
+		instdone->slice_common =
+			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
+		instdone->sampler[0][0] =
+			intel_uncore_read(uncore, GEN7_SAMPLER_INSTDONE);
+		instdone->row[0][0] =
+			intel_uncore_read(uncore, GEN7_ROW_INSTDONE);
 
 		break;
 	case 6:
 	case 5:
 	case 4:
-		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));
-
-		if (engine->id == RCS)
+		instdone->instdone =
+			intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
+		if (engine->id == RCS0)
 			/* HACK: Using the wrong struct member */
-			instdone->slice_common = I915_READ(GEN4_INSTDONE1);
+			instdone->slice_common =
+				intel_uncore_read(uncore, GEN4_INSTDONE1);
 		break;
 	case 3:
 	case 2:
-		instdone->instdone = I915_READ(GEN2_INSTDONE);
+		instdone->instdone = intel_uncore_read(uncore, GEN2_INSTDONE);
 		break;
 	}
 }
@@ -985,12 +1035,13 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 		return true;
 
 	/* First check that no commands are left in the ring */
-	if ((I915_READ_HEAD(engine) & HEAD_ADDR) !=
-	    (I915_READ_TAIL(engine) & TAIL_ADDR))
+	if ((ENGINE_READ(engine, RING_HEAD) & HEAD_ADDR) !=
+	    (ENGINE_READ(engine, RING_TAIL) & TAIL_ADDR))
 		idle = false;
 
 	/* No bit for gen2, so assume the CS parser is idle */
-	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+	if (INTEL_GEN(dev_priv) > 2 &&
+	    !(ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE))
 		idle = false;
 
 	intel_runtime_pm_put(dev_priv, wakeref);
@@ -1007,16 +1058,10 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
  */
 bool intel_engine_is_idle(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
 	/* More white lies, if wedged, hw state is inconsistent */
-	if (i915_terminally_wedged(&dev_priv->gpu_error))
+	if (i915_reset_failed(engine->i915))
 		return true;
 
-	/* Any inflight/incomplete requests? */
-	if (!intel_engine_signaled(engine, intel_engine_last_submit(engine)))
-		return false;
-
 	/* Waiting to drain ELSP? */
 	if (READ_ONCE(engine->execlists.active)) {
 		struct tasklet_struct *t = &engine->execlists.tasklet;
@@ -1045,7 +1090,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	return ring_is_idle(engine);
 }
 
-bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
+bool intel_engines_are_idle(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1054,10 +1099,14 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
 	 * If the driver is wedged, HW state may be very inconsistent and
 	 * report that it is still busy, even though we have stopped using it.
 	 */
-	if (i915_terminally_wedged(&dev_priv->gpu_error))
+	if (i915_reset_failed(i915))
 		return true;
 
-	for_each_engine(engine, dev_priv, id) {
+	/* Already parked (and passed an idleness test); must still be idle */
+	if (!READ_ONCE(i915->gt.awake))
+		return true;
+
+	for_each_engine(engine, i915, id) {
 		if (!intel_engine_is_idle(engine))
 			return false;
 	}
@@ -1065,34 +1114,6 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
 	return true;
 }
 
-/**
- * intel_engine_has_kernel_context:
- * @engine: the engine
- *
- * Returns true if the last context to be executed on this engine, or has been
- * executed if the engine is already idle, is the kernel context
- * (#i915.kernel_context).
- */
-bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
-{
-	const struct intel_context *kernel_context =
-		to_intel_context(engine->i915->kernel_context, engine);
-	struct i915_request *rq;
-
-	lockdep_assert_held(&engine->i915->drm.struct_mutex);
-
-	/*
-	 * Check the last context seen by the engine. If active, it will be
-	 * the last request that remains in the timeline. When idle, it is
-	 * the last executed context as tracked by retirement.
-	 */
-	rq = __i915_active_request_peek(&engine->timeline.last_request);
-	if (rq)
-		return rq->hw_context == kernel_context;
-	else
-		return engine->last_retired_context == kernel_context;
-}
-
 void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
@@ -1180,6 +1201,8 @@ void intel_engines_park(struct drm_i915_private *i915)
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 		engine->execlists.no_priolist = false;
 	}
+
+	i915->gt.active_engines = 0;
 }
 
 /**
@@ -1283,15 +1306,14 @@ 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%s [%llx:%llx]%s @ %dms: %s\n",
+	drm_printf(m, "%s %llx:%llx%s%s %s @ %dms: %s\n",
 		   prefix,
-		   rq->global_seqno,
+		   rq->fence.context, rq->fence.seqno,
 		   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),
 		   name);
@@ -1334,25 +1356,26 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		&engine->execlists;
 	u64 addr;
 
-	if (engine->id == RCS && IS_GEN_RANGE(dev_priv, 4, 7))
-		drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID));
+	if (engine->id == RCS0 && IS_GEN_RANGE(dev_priv, 4, 7))
+		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
 	drm_printf(m, "\tRING_START: 0x%08x\n",
-		   I915_READ(RING_START(engine->mmio_base)));
+		   ENGINE_READ(engine, RING_START));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
-		   I915_READ(RING_HEAD(engine->mmio_base)) & HEAD_ADDR);
+		   ENGINE_READ(engine, RING_HEAD) & HEAD_ADDR);
 	drm_printf(m, "\tRING_TAIL:  0x%08x\n",
-		   I915_READ(RING_TAIL(engine->mmio_base)) & TAIL_ADDR);
+		   ENGINE_READ(engine, RING_TAIL) & TAIL_ADDR);
 	drm_printf(m, "\tRING_CTL:   0x%08x%s\n",
-		   I915_READ(RING_CTL(engine->mmio_base)),
-		   I915_READ(RING_CTL(engine->mmio_base)) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? " [waiting]" : "");
+		   ENGINE_READ(engine, RING_CTL),
+		   ENGINE_READ(engine, RING_CTL) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? " [waiting]" : "");
 	if (INTEL_GEN(engine->i915) > 2) {
 		drm_printf(m, "\tRING_MODE:  0x%08x%s\n",
-			   I915_READ(RING_MI_MODE(engine->mmio_base)),
-			   I915_READ(RING_MI_MODE(engine->mmio_base)) & (MODE_IDLE) ? " [idle]" : "");
+			   ENGINE_READ(engine, RING_MI_MODE),
+			   ENGINE_READ(engine, RING_MI_MODE) & (MODE_IDLE) ? " [idle]" : "");
 	}
 
 	if (INTEL_GEN(dev_priv) >= 6) {
-		drm_printf(m, "\tRING_IMR: %08x\n", I915_READ_IMR(engine));
+		drm_printf(m, "\tRING_IMR: %08x\n",
+			   ENGINE_READ(engine, RING_IMR));
 	}
 
 	addr = intel_engine_get_active_head(engine);
@@ -1362,57 +1385,53 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 	drm_printf(m, "\tBBADDR: 0x%08x_%08x\n",
 		   upper_32_bits(addr), lower_32_bits(addr));
 	if (INTEL_GEN(dev_priv) >= 8)
-		addr = I915_READ64_2x32(RING_DMA_FADD(engine->mmio_base),
-					RING_DMA_FADD_UDW(engine->mmio_base));
+		addr = ENGINE_READ64(engine, RING_DMA_FADD, RING_DMA_FADD_UDW);
 	else if (INTEL_GEN(dev_priv) >= 4)
-		addr = I915_READ(RING_DMA_FADD(engine->mmio_base));
+		addr = ENGINE_READ(engine, RING_DMA_FADD);
 	else
-		addr = I915_READ(DMA_FADD_I8XX);
+		addr = ENGINE_READ(engine, DMA_FADD_I8XX);
 	drm_printf(m, "\tDMA_FADDR: 0x%08x_%08x\n",
 		   upper_32_bits(addr), lower_32_bits(addr));
 	if (INTEL_GEN(dev_priv) >= 4) {
 		drm_printf(m, "\tIPEIR: 0x%08x\n",
-			   I915_READ(RING_IPEIR(engine->mmio_base)));
+			   ENGINE_READ(engine, RING_IPEIR));
 		drm_printf(m, "\tIPEHR: 0x%08x\n",
-			   I915_READ(RING_IPEHR(engine->mmio_base)));
+			   ENGINE_READ(engine, RING_IPEHR));
 	} else {
-		drm_printf(m, "\tIPEIR: 0x%08x\n", I915_READ(IPEIR));
-		drm_printf(m, "\tIPEHR: 0x%08x\n", I915_READ(IPEHR));
+		drm_printf(m, "\tIPEIR: 0x%08x\n", ENGINE_READ(engine, IPEIR));
+		drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR));
 	}
 
 	if (HAS_EXECLISTS(dev_priv)) {
 		const u32 *hws =
 			&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
+		const u8 num_entries = execlists->csb_size;
 		unsigned int idx;
 		u8 read, write;
 
-		drm_printf(m, "\tExeclist status: 0x%08x %08x\n",
-			   I915_READ(RING_EXECLIST_STATUS_LO(engine)),
-			   I915_READ(RING_EXECLIST_STATUS_HI(engine)));
+		drm_printf(m, "\tExeclist status: 0x%08x %08x, entries %u\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO),
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI),
+			   num_entries);
 
 		read = execlists->csb_head;
 		write = READ_ONCE(*execlists->csb_write);
 
-		drm_printf(m, "\tExeclist CSB read %d, write %d [mmio:%d], tasklet queued? %s (%s)\n",
+		drm_printf(m, "\tExeclist CSB read %d, write %d, tasklet queued? %s (%s)\n",
 			   read, write,
-			   GEN8_CSB_WRITE_PTR(I915_READ(RING_CONTEXT_STATUS_PTR(engine))),
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
-		if (read >= GEN8_CSB_ENTRIES)
+		if (read >= num_entries)
 			read = 0;
-		if (write >= GEN8_CSB_ENTRIES)
+		if (write >= num_entries)
 			write = 0;
 		if (read > write)
-			write += GEN8_CSB_ENTRIES;
+			write += num_entries;
 		while (read < write) {
-			idx = ++read % GEN8_CSB_ENTRIES;
-			drm_printf(m, "\tExeclist CSB[%d]: 0x%08x [mmio:0x%08x], context: %d [mmio:%d]\n",
-				   idx,
-				   hws[idx * 2],
-				   I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
-				   hws[idx * 2 + 1],
-				   I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)));
+			idx = ++read % num_entries;
+			drm_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n",
+				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
 		rcu_read_lock();
@@ -1425,10 +1444,11 @@ 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, hwsp:%08x}, rq: ",
+					 "\t\tELSP[%d] count=%d, ring:{start:%08x, hwsp:%08x, seqno:%08x}, rq: ",
 					 idx, count,
 					 i915_ggtt_offset(rq->ring->vma),
-					 rq->timeline->hwsp_offset);
+					 rq->timeline->hwsp_offset,
+					 hwsp_seqno(rq));
 				print_request(m, rq, hdr);
 			} else {
 				drm_printf(m, "\t\tELSP[%d] idle\n", idx);
@@ -1438,11 +1458,11 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		rcu_read_unlock();
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_BASE(engine)));
+			   ENGINE_READ(engine, RING_PP_DIR_BASE));
 		drm_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_BASE_READ(engine)));
+			   ENGINE_READ(engine, RING_PP_DIR_BASE_READ));
 		drm_printf(m, "\tPP_DIR_DCLV: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_DCLV(engine)));
+			   ENGINE_READ(engine, RING_PP_DIR_DCLV));
 	}
 }
 
@@ -1495,13 +1515,12 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		va_end(ap);
 	}
 
-	if (i915_terminally_wedged(&engine->i915->gpu_error))
+	if (i915_reset_failed(engine->i915))
 		drm_printf(m, "*** WEDGED ***\n");
 
-	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
-		   intel_engine_get_seqno(engine),
-		   intel_engine_last_submit(engine),
-		   engine->hangcheck.seqno,
+	drm_printf(m, "\tHangcheck %x:%x [%d ms]\n",
+		   engine->hangcheck.last_seqno,
+		   engine->hangcheck.next_seqno,
 		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
@@ -1521,7 +1540,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	if (&rq->link != &engine->timeline.requests)
 		print_request(m, rq, "\t\tlast   ");
 
-	rq = i915_gem_find_active_request(engine);
+	rq = intel_engine_find_active_request(engine);
 	if (rq) {
 		print_request(m, rq, "\t\tactive ");
 
@@ -1688,6 +1707,50 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine)
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
+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)
+{
+	struct i915_request *request, *active = NULL;
+	unsigned long flags;
+
+	/*
+	 * We are called by the error capture, reset and to dump engine
+	 * state at random points in time. In particular, note that neither is
+	 * crucially ordered with an interrupt. After a hang, the GPU is dead
+	 * and we assume that no more writes can happen (we waited long enough
+	 * for all writes that were in transaction to be flushed) - adding an
+	 * extra delay for a recent interrupt is pointless. Hence, we do
+	 * not need an engine->irq_seqno_barrier() before the seqno reads.
+	 * At all other times, we must assume the GPU is still running, but
+	 * we only care about the snapshot of this moment.
+	 */
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	list_for_each_entry(request, &engine->timeline.requests, link) {
+		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;
+	}
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+
+	return active;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #include "selftests/intel_engine_cs.c"