Merge tag 'drm-next-2018-08-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.19.

  Rob has some new hardware support for new qualcomm hw that I'll send
  along separately. This has the display part of it, the remaining pull
  is for the acceleration engine.

  This also contains a wound-wait/wait-die mutex rework, Peter has acked
  it for merging via my tree.

  Otherwise mostly the usual level of activity. Summary:

  core:
   - Wound-wait/wait-die mutex rework
   - Add writeback connector type
   - Add "content type" property for HDMI
   - Move GEM bo to drm_framebuffer
   - Initial gpu scheduler documentation
   - GPU scheduler fixes for dying processes
   - Console deferred fbcon takeover support
   - Displayport support for CEC tunneling over AUX

  panel:
   - otm8009a panel driver fixes
   - Innolux TV123WAM and G070Y2-L01 panel driver
   - Ilitek ILI9881c panel driver
   - Rocktech RK070ER9427 LCD
   - EDT ETM0700G0EDH6 and EDT ETM0700G0BDH6
   - DLC DLC0700YZG-1
   - BOE HV070WSA-100
   - newhaven, nhd-4.3-480272ef-atxl LCD
   - DataImage SCF0700C48GGU18
   - Sharp LQ035Q7DB03
   - p079zca: Refactor to support multiple panels

  tinydrm:
   - ILI9341 display panel

  New driver:
   - vkms - virtual kms driver to testing.

  i915:
   - Icelake:
        Display enablement
        DSI support
        IRQ support
        Powerwell support
   - GPU reset fixes and improvements
   - Full ppgtt support refactoring
   - PSR fixes and improvements
   - Execlist improvments
   - GuC related fixes

  amdgpu:
   - Initial amdgpu documentation
   - JPEG engine support on VCN
   - CIK uses powerplay by default
   - Move to using core PCIE functionality for gens/lanes
   - DC/Powerplay interface rework
   - Stutter mode support for RV
   - Vega12 Powerplay updates
   - GFXOFF fixes
   - GPUVM fault debugging
   - Vega12 GFXOFF
   - DC improvements
   - DC i2c/aux changes
   - UVD 7.2 fixes
   - Powerplay fixes for Polaris12, CZ/ST
   - command submission bo_list fixes

  amdkfd:
   - Raven support
   - Power management fixes

  udl:
   - Cleanups and fixes

  nouveau:
   - misc fixes and cleanups.

  msm:
   - DPU1 support display controller in sdm845
   - GPU coredump support.

  vmwgfx:
   - Atomic modesetting validation fixes
   - Support for multisample surfaces

  armada:
   - Atomic modesetting support completed.

  exynos:
   - IPPv2 fixes
   - Move g2d to component framework
   - Suspend/resume support cleanups
   - Driver cleanups

  imx:
   - CSI configuration improvements
   - Driver cleanups
   - Use atomic suspend/resume helpers
   - ipu-v3 V4L2 XRGB32/XBGR32 support

  pl111:
   - Add Nomadik LCDC variant

  v3d:
   - GPU scheduler jobs management

  sun4i:
   - R40 display engine support
   - TCON TOP driver

  mediatek:
   - MT2712 SoC support

  rockchip:
   - vop fixes

  omapdrm:
   - Workaround for DRA7 errata i932
   - Fix mm_list locking

  mali-dp:
   - Writeback implementation
        PM improvements
   - Internal error reporting debugfs

  tilcdc:
   - Single fix for deferred probing

  hdlcd:
   - Teardown fixes

  tda998x:
   - Converted to a bridge driver.

  etnaviv:
   - Misc fixes"

* tag 'drm-next-2018-08-15' of git://anongit.freedesktop.org/drm/drm: (1506 commits)
  drm/amdgpu/sriov: give 8s for recover vram under RUNTIME
  drm/scheduler: fix param documentation
  drm/i2c: tda998x: correct PLL divider calculation
  drm/i2c: tda998x: get rid of private fill_modes function
  drm/i2c: tda998x: move mode_valid() to bridge
  drm/i2c: tda998x: register bridge outside of component helper
  drm/i2c: tda998x: cleanup from previous changes
  drm/i2c: tda998x: allocate tda998x_priv inside tda998x_create()
  drm/i2c: tda998x: convert to bridge driver
  drm/scheduler: fix timeout worker setup for out of order job completions
  drm/amd/display: display connected to dp-1 does not light up
  drm/amd/display: update clk for various HDMI color depths
  drm/amd/display: program display clock on cache match
  drm/amd/display: Add NULL check for enabling dp ss
  drm/amd/display: add vbios table check for enabling dp ss
  drm/amd/display: Don't share clk source between DP and HDMI
  drm/amd/display: Fix DP HBR2 Eye Diagram Pattern on Carrizo
  drm/amd/display: Use calculated disp_clk_khz value for dce110
  drm/amd/display: Implement custom degamma lut on dcn
  drm/amd/display: Destroy aux_engines only once
  ...

1 files changed, 222 insertions, 66 deletions

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1590375f31cb..2d1952849d69 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,7 +25,6 @@
 #include <drm/drm_print.h>
 
 #include "i915_drv.h"
-#include "i915_vgpu.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
@@ -230,6 +229,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		break;
 	default:
 		MISSING_CASE(class);
+		/* fall through */
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
@@ -302,6 +302,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 							   engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
+	if (engine->context_size)
+		DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
 
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
@@ -456,28 +458,16 @@ static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 	i915_gem_batch_pool_init(&engine->batch_pool, engine);
 }
 
-static bool csb_force_mmio(struct drm_i915_private *i915)
-{
-	/* Older GVT emulation depends upon intercepting CSB mmio */
-	if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
-		return true;
-
-	return false;
-}
-
 static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	execlists->csb_use_mmio = csb_force_mmio(engine->i915);
-
 	execlists->port_mask = 1;
 	BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 }
 
 /**
@@ -492,6 +482,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
 	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
+	lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE);
 
 	intel_engine_init_execlist(engine);
 	intel_engine_init_hangcheck(engine);
@@ -499,7 +490,8 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_cmd_parser(engine);
 }
 
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size)
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -515,7 +507,7 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 		return PTR_ERR(obj);
 	}
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unref;
@@ -533,7 +525,7 @@ err_unref:
 	return ret;
 }
 
-static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->scratch);
 }
@@ -585,7 +577,7 @@ static int init_status_page(struct intel_engine_cs *engine)
 	if (ret)
 		goto err;
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
@@ -645,6 +637,12 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 	return 0;
 }
 
+static void __intel_context_unpin(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine)
+{
+	intel_context_unpin(to_intel_context(ctx, engine));
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -658,7 +656,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
  */
 int intel_engine_init_common(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
@@ -670,18 +669,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ring = intel_context_pin(engine->i915->kernel_context, engine);
-	if (IS_ERR(ring))
-		return PTR_ERR(ring);
+	ce = intel_context_pin(i915->kernel_context, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	/*
 	 * Similarly the preempt context must always be available so that
 	 * we can interrupt the engine at any time.
 	 */
-	if (engine->i915->preempt_context) {
-		ring = intel_context_pin(engine->i915->preempt_context, engine);
-		if (IS_ERR(ring)) {
-			ret = PTR_ERR(ring);
+	if (i915->preempt_context) {
+		ce = intel_context_pin(i915->preempt_context, engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
 			goto err_unpin_kernel;
 		}
 	}
@@ -690,7 +689,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	if (ret)
 		goto err_unpin_preempt;
 
-	if (HWS_NEEDS_PHYSICAL(engine->i915))
+	if (HWS_NEEDS_PHYSICAL(i915))
 		ret = init_phys_status_page(engine);
 	else
 		ret = init_status_page(engine);
@@ -702,10 +701,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+
 err_unpin_kernel:
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 	return ret;
 }
 
@@ -718,6 +718,8 @@ err_unpin_kernel:
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	intel_engine_cleanup_scratch(engine);
 
 	if (HWS_NEEDS_PHYSICAL(engine->i915))
@@ -732,9 +734,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 
 	i915_timeline_fini(&engine->timeline);
 }
@@ -769,6 +771,35 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 	return bbaddr;
 }
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	const i915_reg_t mode = RING_MI_MODE(base);
+	int err;
+
+	if (INTEL_GEN(dev_priv) < 3)
+		return -ENODEV;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+
+	err = 0;
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL)) {
+		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		err = -ETIMEDOUT;
+	}
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	POSTING_READ_FW(mode);
+
+	return err;
+}
+
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
@@ -780,12 +811,32 @@ 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);
+	u32 mcr_s_ss_select;
+	u32 slice = fls(sseu->slice_mask);
+	u32 subslice = fls(sseu->subslice_mask[slice]);
+
+	if (INTEL_GEN(dev_priv) == 10)
+		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
+				  GEN8_MCR_SUBSLICE(subslice);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		mcr_s_ss_select = GEN11_MCR_SLICE(slice) |
+				  GEN11_MCR_SUBSLICE(subslice);
+	else
+		mcr_s_ss_select = 0;
+
+	return mcr_s_ss_select;
+}
+
 static inline uint32_t
 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;
 	enum forcewake_domains fw_domains;
@@ -802,6 +853,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 					    GEN8_MCR_SUBSLICE(subslice);
 	}
 
+	default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
+
 	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
 						    FW_REG_READ);
 	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
@@ -812,11 +865,10 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
 
 	mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
-	/*
-	 * The HW expects the slice and sublice selectors to be reset to 0
-	 * after reading out the registers.
-	 */
-	WARN_ON_ONCE(mcr & mcr_slice_subslice_mask);
+
+	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);
@@ -824,6 +876,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	ret = I915_READ_FW(reg);
 
 	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= default_mcr_s_ss_select;
+
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
 
 	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
@@ -934,11 +988,24 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return true;
 
 	/* Waiting to drain ELSP? */
-	if (READ_ONCE(engine->execlists.active))
-		return false;
+	if (READ_ONCE(engine->execlists.active)) {
+		struct tasklet_struct *t = &engine->execlists.tasklet;
+
+		local_bh_disable();
+		if (tasklet_trylock(t)) {
+			/* Must wait for any GPU reset in progress. */
+			if (__tasklet_is_enabled(t))
+				t->func(t->data);
+			tasklet_unlock(t);
+		}
+		local_bh_enable();
 
-	/* ELSP is empty, but there are ready requests? */
-	if (READ_ONCE(engine->execlists.first))
+		if (READ_ONCE(engine->execlists.active))
+			return false;
+	}
+
+	/* ELSP is empty, but there are ready requests? E.g. after reset */
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
 		return false;
 
 	/* Ring stopped? */
@@ -978,8 +1045,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
  */
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 {
-	const struct i915_gem_context * const kernel_context =
-		engine->i915->kernel_context;
+	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);
@@ -991,7 +1058,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 */
 	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
-		return rq->ctx == kernel_context;
+		return rq->hw_context == kernel_context;
 	else
 		return engine->last_retired_context == kernel_context;
 }
@@ -1006,6 +1073,28 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 }
 
 /**
+ * intel_engines_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ *
+ * 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)
+{
+	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);
+	}
+}
+
+/**
  * intel_engines_park: called when the GT is transitioning from busy->idle
  * @i915: the i915 device
  *
@@ -1043,6 +1132,11 @@ void intel_engines_park(struct drm_i915_private *i915)
 		if (engine->park)
 			engine->park(engine);
 
+		if (engine->pinned_default_state) {
+			i915_gem_object_unpin_map(engine->default_state);
+			engine->pinned_default_state = NULL;
+		}
+
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 		engine->execlists.no_priolist = false;
 	}
@@ -1060,6 +1154,16 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
+		void *map;
+
+		/* Pin the default state for fast resets from atomic context. */
+		map = NULL;
+		if (engine->default_state)
+			map = i915_gem_object_pin_map(engine->default_state,
+						      I915_MAP_WB);
+		if (!IS_ERR_OR_NULL(map))
+			engine->pinned_default_state = map;
+
 		if (engine->unpark)
 			engine->unpark(engine);
 
@@ -1067,6 +1171,26 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	}
 }
 
+/**
+ * intel_engine_lost_context: called when the GPU is reset into unknown state
+ * @engine: the engine
+ *
+ * We have either reset the GPU or otherwise about to lose state tracking of
+ * the current GPU logical state (e.g. suspend). On next use, it is therefore
+ * imperative that we make no presumptions about the current state and load
+ * from scratch.
+ */
+void intel_engine_lost_context(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
+
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
+}
+
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
@@ -1151,7 +1275,7 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len)
 						rowsize, sizeof(u32),
 						line, sizeof(line),
 						false) >= sizeof(line));
-		drm_printf(m, "%08zx %s\n", pos, line);
+		drm_printf(m, "[%04zx] %s\n", pos, line);
 
 		prev = buf + pos;
 		skip = false;
@@ -1166,6 +1290,8 @@ 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))
+		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)));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
@@ -1232,12 +1358,10 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
 		read = GEN8_CSB_READ_PTR(ptr);
 		write = GEN8_CSB_WRITE_PTR(ptr);
-		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n",
+		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], tasklet queued? %s (%s)\n",
 			   read, execlists->csb_head,
 			   write,
 			   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
-			   yesno(test_bit(ENGINE_IRQ_EXECLIST,
-					  &engine->irq_posted)),
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
@@ -1287,6 +1411,39 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 	}
 }
 
+static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
+{
+	void *ring;
+	int size;
+
+	drm_printf(m,
+		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
+		   rq->head, rq->postfix, rq->tail,
+		   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
+		   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
+	size = rq->tail - rq->head;
+	if (rq->tail < rq->head)
+		size += rq->ring->size;
+
+	ring = kmalloc(size, GFP_ATOMIC);
+	if (ring) {
+		const void *vaddr = rq->ring->vaddr;
+		unsigned int head = rq->head;
+		unsigned int len = 0;
+
+		if (rq->tail < head) {
+			len = rq->ring->size - head;
+			memcpy(ring, vaddr + head, len);
+			head = 0;
+		}
+		memcpy(ring + len, vaddr + head, size - len);
+
+		hexdump(m, ring, size);
+		kfree(ring);
+	}
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1296,6 +1453,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	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;
 
@@ -1336,11 +1494,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	rq = i915_gem_find_active_request(engine);
 	if (rq) {
 		print_request(m, rq, "\t\tactive ");
-		drm_printf(m,
-			   "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
-			   rq->head, rq->postfix, rq->tail,
-			   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
-			   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
 			   i915_ggtt_offset(rq->ring->vma));
 		drm_printf(m, "\t\tring->head:   0x%08x\n",
@@ -1351,6 +1505,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->ring->emit);
 		drm_printf(m, "\t\tring->space:  0x%08x\n",
 			   rq->ring->space);
+
+		print_request_ring(m, rq);
 	}
 
 	rcu_read_unlock();
@@ -1362,7 +1518,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
 
-	spin_lock_irq(&engine->timeline.lock);
+	local_irq_save(flags);
+	spin_lock(&engine->timeline.lock);
 
 	last = NULL;
 	count = 0;
@@ -1384,7 +1541,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	last = NULL;
 	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	for (rb = execlists->first; rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
@@ -1404,22 +1561,21 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		print_request(m, last, "\t\tQ ");
 	}
 
-	spin_unlock_irq(&engine->timeline.lock);
+	spin_unlock(&engine->timeline.lock);
 
-	spin_lock_irq(&b->rb_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] waiting for %x\n",
 			   w->tsk->comm, w->tsk->pid, w->seqno);
 	}
-	spin_unlock_irq(&b->rb_lock);
+	spin_unlock(&b->rb_lock);
+	local_irq_restore(flags);
 
-	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
 		   engine->irq_posted,
 		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-				  &engine->irq_posted)),
-		   yesno(test_bit(ENGINE_IRQ_EXECLIST,
 				  &engine->irq_posted)));
 
 	drm_printf(m, "HWSP:\n");
@@ -1468,8 +1624,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	tasklet_disable(&execlists->tasklet);
-	write_seqlock_irqsave(&engine->stats.lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	write_seqlock(&engine->stats.lock);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1493,8 +1649,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-	tasklet_enable(&execlists->tasklet);
+	write_sequnlock(&engine->stats.lock);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	return err;
 }