Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Davbe Airlie:
 "This is the main pull request for graphics for 5.6. Usual selection of
  changes all over.

  I've got one outstanding vmwgfx pull that touches mm so kept it
  separate until after all of this lands. I'll try and get it to you
  soon after this, but it might be early next week (nothing wrong with
  code, just my schedule is messy)

  This also hits a lot of fbdev drivers with some cleanups.

  Other notables:
   - vulkan timeline semaphore support added to syncobjs
   - nouveau turing secureboot/graphics support
   - Displayport MST display stream compression support

  Detailed summary:

  uapi:
   - dma-buf heaps added (and fixed)
   - command line add support for panel oreientation
   - command line allow overriding penguin count

  drm:
   - mipi dsi definition updates
   - lockdep annotations for dma_resv
   - remove dma-buf kmap/kunmap support
   - constify fb_ops in all fbdev drivers
   - MST fix for daisy chained hotplug-
   - CTA-861-G modes with VIC >= 193 added
   - fix drm_panel_of_backlight export
   - LVDS decoder support
   - more device based logging support
   - scanline alighment for dumb buffers
   - MST DSC helpers

  scheduler:
   - documentation fixes
   - job distribution improvements

  panel:
   - Logic PD type 28 panel support
   - Jimax8729d MIPI-DSI
   - igenic JZ4770
   - generic DSI devicetree bindings
   - sony acx424AKP panel
   - Leadtek LTK500HD1829
   - xinpeng XPP055C272
   - AUO B116XAK01
   - GiantPlus GPM940B0
   - BOE NV140FHM-N49
   - Satoz SAT050AT40H12R2
   - Sharp LS020B1DD01D panels.

  ttm:
   - use blocking WW lock

  i915:
   - hw/uapi state separation
   - Lock annotation improvements
   - selftest improvements
   - ICL/TGL DSI VDSC support
   - VBT parsing improvments
   - Display refactoring
   - DSI updates + fixes
   - HDCP 2.2 for CFL
   - CML PCI ID fixes
   - GLK+ fbc fix
   - PSR fixes
   - GEN/GT refactor improvments
   - DP MST fixes
   - switch context id alloc to xarray
   - workaround updates
   - LMEM debugfs support
   - tiled monitor fixes
   - ICL+ clock gating programming removed
   - DP MST disable sequence fixed
   - LMEM discontiguous object maps
   - prefaulting for discontiguous objects
   - use LMEM for dumb buffers if possible
   - add LMEM mmap support

  amdgpu:
   - enable sync object timelines for vulkan
   - MST atomic routines
   - enable MST DSC support
   - add DMCUB display microengine support
   - DC OEM i2c support
   - Renoir DC fixes
   - Initial HDCP 2.x support
   - BACO support for Arcturus
   - Use BACO for runtime PM power save
   - gfxoff on navi10
   - gfx10 golden updates and fixes
   - DCN support on POWER
   - GFXOFF for raven1 refresh
   - MM engine idle handlers cleanup
   - 10bpc EDP panel fixes
   - renoir watermark fixes
   - SR-IOV fixes
   - Arcturus VCN fixes
   - GDDR6 training fixes
   - freesync fixes
   - Pollock support

  amdkfd:
   - unify more codepath with amdgpu
   - use KIQ to setup HIQ rather than MMIO

  radeon:
   - fix vma fault handler race
   - PPC DMA fix
   - register check fixes for r100/r200

  nouveau:
   - mmap_sem vs dma_resv fix
   - rewrite the ACR secure boot code for Turing
   - TU10x graphics engine support (TU11x pending)
   - Page kind mapping for turing
   - 10-bit LUT support
   - GP10B Tegra fixes
   - HD audio regression fix

  hisilicon/hibmc:
   - use generic fbdev code and helpers

  rockchip:
   - dsi/px30 support

  virtio:
   - fb damage support
   - static some functions

  vc4:
   - use dma_resv lock wrappers

  msm:
   - use dma_resv lock wrappers
   - sc7180 display + DSI support
   - a618 support
   - UBWC support improvements

  vmwgfx:
   - updates + new logging uapi

  exynos:
   - enable/disable callback cleanups

  etnaviv:
   - use dma_resv lock wrappers

  atmel-hlcdc:
   - clock fixes

  mediatek:
   - cmdq support
   - non-smooth cursor fixes
   - ctm property support

  sun4i:
   - suspend support
   - A64 mipi dsi support

  rcar-du:
   - Color management module support
   - LVDS encoder dual-link support
   - R8A77980 support

  analogic:
   - add support for an6345

  ast:
   - atomic modeset support
   - primary plane garbage fix

  arcgpu:
   - fixes for fourcc handling

  tegra:
   - minor fixes and improvments

  mcde:
   - vblank support

  meson:
   - OSD1 plane AFBC commit

  gma500:
   - add pageflip support
   - reomve global drm_dev

  komeda:
   - tweak debugfs output
   - d32 support
   - runtime PM suppotr

  udl:
   - use generic shmem helpers
   - cleanup and fixes"

* tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits)
  drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing
  drm/nouveau/acr: return error when registering LSF if ACR not supported
  drm/nouveau/disp/gv100-: not all channel types support reporting error codes
  drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
  drm/nouveau: support synchronous pushbuf submission
  drm/nouveau: signal pending fences when channel has been killed
  drm/nouveau: reject attempts to submit to dead channels
  drm/nouveau: zero vma pointer even if we only unreference it rather than free
  drm/nouveau: Add HD-audio component notifier support
  drm/nouveau: fix build error without CONFIG_IOMMU_API
  drm/nouveau/kms/nv04: remove set but not used variable 'width'
  drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector'
  drm/nouveau/mmu: fix comptag memory leak
  drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc
  drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping
  drm/exynos: Rename Exynos to lowercase
  drm/exynos: change callback names
  drm/mst: Don't do atomic checks over disabled managers
  drm/amdgpu: add the lost mutex_init back
  drm/amd/display: skip opp blank or unblank if test pattern enabled
  ...

1 files changed, 402 insertions, 235 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d925a1035c9d..0cf0f6fae675 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -133,12 +133,11 @@
  */
 #include <linux/interrupt.h>
 
-#include "gem/i915_gem_context.h"
-
 #include "i915_drv.h"
 #include "i915_perf.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
+#include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -489,17 +488,23 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	return desc;
 }
 
-static u32 *set_offsets(u32 *regs,
+static inline unsigned int dword_in_page(void *addr)
+{
+	return offset_in_page(addr) / sizeof(u32);
+}
+
+static void set_offsets(u32 *regs,
 			const u8 *data,
-			const struct intel_engine_cs *engine)
+			const struct intel_engine_cs *engine,
+			bool clear)
 #define NOP(x) (BIT(7) | (x))
-#define LRI(count, flags) ((flags) << 6 | (count))
+#define LRI(count, flags) ((flags) << 6 | (count) | BUILD_BUG_ON_ZERO(count >= BIT(6)))
 #define POSTED BIT(0)
 #define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END() 0
+#define END(x) 0, (x)
 {
 	const u32 base = engine->mmio_base;
 
@@ -507,7 +512,10 @@ static u32 *set_offsets(u32 *regs,
 		u8 count, flags;
 
 		if (*data & BIT(7)) { /* skip */
-			regs += *data++ & ~BIT(7);
+			count = *data++ & ~BIT(7);
+			if (clear)
+				memset32(regs, MI_NOOP, count);
+			regs += count;
 			continue;
 		}
 
@@ -533,12 +541,25 @@ static u32 *set_offsets(u32 *regs,
 				offset |= v & ~BIT(7);
 			} while (v & BIT(7));
 
-			*regs = base + (offset << 2);
+			regs[0] = base + (offset << 2);
+			if (clear)
+				regs[1] = 0;
 			regs += 2;
 		} while (--count);
 	}
 
-	return regs;
+	if (clear) {
+		u8 count = *++data;
+
+		/* Clear past the tail for HW access */
+		GEM_BUG_ON(dword_in_page(regs) > count);
+		memset32(regs, MI_NOOP, count - dword_in_page(regs));
+
+		/* Close the batch; used mainly by live_lrc_layout() */
+		*regs = MI_BATCH_BUFFER_END;
+		if (INTEL_GEN(engine->i915) >= 10)
+			*regs |= BIT(0);
+	}
 }
 
 static const u8 gen8_xcs_offsets[] = {
@@ -573,7 +594,7 @@ static const u8 gen8_xcs_offsets[] = {
 	REG16(0x200),
 	REG(0x028),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen9_xcs_offsets[] = {
@@ -657,7 +678,7 @@ static const u8 gen9_xcs_offsets[] = {
 	REG16(0x67c),
 	REG(0x068),
 
-	END(),
+	END(176)
 };
 
 static const u8 gen12_xcs_offsets[] = {
@@ -689,7 +710,7 @@ static const u8 gen12_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen8_rcs_offsets[] = {
@@ -726,7 +747,91 @@ static const u8 gen8_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
+};
+
+static const u8 gen9_rcs_offsets[] = {
+	NOP(1),
+	LRI(14, POSTED),
+	REG16(0x244),
+	REG(0x34),
+	REG(0x30),
+	REG(0x38),
+	REG(0x3c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+
+	NOP(3),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(1, 0),
+	REG(0xc8),
+
+	NOP(13),
+	LRI(44, POSTED),
+	REG(0x28),
+	REG(0x9c),
+	REG(0xc0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x68),
+
+	END(176)
 };
 
 static const u8 gen11_rcs_offsets[] = {
@@ -767,7 +872,7 @@ static const u8 gen11_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen12_rcs_offsets[] = {
@@ -808,7 +913,7 @@ static const u8 gen12_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 #undef END
@@ -833,6 +938,8 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 			return gen12_rcs_offsets;
 		else if (INTEL_GEN(engine->i915) >= 11)
 			return gen11_rcs_offsets;
+		else if (INTEL_GEN(engine->i915) >= 9)
+			return gen9_rcs_offsets;
 		else
 			return gen8_rcs_offsets;
 	} else {
@@ -880,7 +987,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			active = rq;
 		} else {
-			struct intel_engine_cs *owner = rq->hw_context->engine;
+			struct intel_engine_cs *owner = rq->context->engine;
 
 			/*
 			 * Decouple the virtual breadcrumb before moving it
@@ -983,6 +1090,58 @@ static void intel_engine_context_out(struct intel_engine_cs *engine)
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
+static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x60;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x54;
+	else if (engine->class == RENDER_CLASS)
+		return 0x58;
+	else
+		return -1;
+}
+
+static void
+execlists_check_context(const struct intel_context *ce,
+			const struct intel_engine_cs *engine)
+{
+	const struct intel_ring *ring = ce->ring;
+	u32 *regs = ce->lrc_reg_state;
+	bool valid = true;
+	int x;
+
+	if (regs[CTX_RING_START] != i915_ggtt_offset(ring->vma)) {
+		pr_err("%s: context submitted with incorrect RING_START [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_START],
+		       i915_ggtt_offset(ring->vma));
+		regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
+		valid = false;
+	}
+
+	if ((regs[CTX_RING_CTL] & ~(RING_WAIT | RING_WAIT_SEMAPHORE)) !=
+	    (RING_CTL_SIZE(ring->size) | RING_VALID)) {
+		pr_err("%s: context submitted with incorrect RING_CTL [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_CTL],
+		       (u32)(RING_CTL_SIZE(ring->size) | RING_VALID));
+		regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
+		valid = false;
+	}
+
+	x = lrc_ring_mi_mode(engine);
+	if (x != -1 && regs[x + 1] & (regs[x + 1] >> 16) & STOP_RING) {
+		pr_err("%s: context submitted with STOP_RING [%08x] in RING_MI_MODE\n",
+		       engine->name, regs[x + 1]);
+		regs[x + 1] &= ~STOP_RING;
+		regs[x + 1] |= STOP_RING << 16;
+		valid = false;
+	}
+
+	WARN_ONCE(!valid, "Invalid lrc state found before submission\n");
+}
+
 static void restore_default_state(struct intel_context *ce,
 				  struct intel_engine_cs *engine)
 {
@@ -999,7 +1158,7 @@ static void restore_default_state(struct intel_context *ce,
 static void reset_active(struct i915_request *rq,
 			 struct intel_engine_cs *engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	u32 head;
 
 	/*
@@ -1017,8 +1176,8 @@ static void reset_active(struct i915_request *rq,
 	 * remain correctly ordered. And we defer to __i915_request_submit()
 	 * so that all asynchronous waits are correctly handled.
 	 */
-	GEM_TRACE("%s(%s): { rq=%llx:%lld }\n",
-		  __func__, engine->name, rq->fence.context, rq->fence.seqno);
+	ENGINE_TRACE(engine, "{ rq=%llx:%lld }\n",
+		     rq->fence.context, rq->fence.seqno);
 
 	/* On resubmission of the active request, payload will be scrubbed */
 	if (i915_request_completed(rq))
@@ -1040,13 +1199,16 @@ static inline struct intel_engine_cs *
 __execlists_schedule_in(struct i915_request *rq)
 {
 	struct intel_engine_cs * const engine = rq->engine;
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	intel_context_get(ce);
 
-	if (unlikely(i915_gem_context_is_banned(ce->gem_context)))
+	if (unlikely(intel_context_is_banned(ce)))
 		reset_active(rq, engine);
 
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		execlists_check_context(ce, engine);
+
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
 		ce->lrc_desc |= (u64)ce->tag << 32;
@@ -1054,12 +1216,12 @@ __execlists_schedule_in(struct i915_request *rq)
 		/* We don't need a strict matching tag, just different values */
 		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 		ce->lrc_desc |=
-			(u64)(engine->context_tag++ % NUM_CONTEXT_TAG) <<
+			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
 			GEN11_SW_CTX_ID_SHIFT;
 		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
-	intel_gt_pm_get(engine->gt);
+	__intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
 
@@ -1069,7 +1231,7 @@ __execlists_schedule_in(struct i915_request *rq)
 static inline struct i915_request *
 execlists_schedule_in(struct i915_request *rq, int idx)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *old;
 
 	GEM_BUG_ON(!intel_engine_pm_is_awake(rq->engine));
@@ -1100,7 +1262,7 @@ static inline void
 __execlists_schedule_out(struct i915_request *rq,
 			 struct intel_engine_cs * const engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	/*
 	 * NB process_csb() is not under the engine->active.lock and hence
@@ -1138,7 +1300,7 @@ __execlists_schedule_out(struct i915_request *rq,
 static inline void
 execlists_schedule_out(struct i915_request *rq)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
@@ -1155,7 +1317,7 @@ execlists_schedule_out(struct i915_request *rq)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->hw_context;
+	struct intel_context *ce = rq->context;
 	u64 desc = ce->lrc_desc;
 	u32 tail;
 
@@ -1186,17 +1348,8 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * may not be visible to the HW prior to the completion of the UC
 	 * register write and that we may begin execution from the context
 	 * before its image is complete leading to invalid PD chasing.
-	 *
-	 * Furthermore, Braswell, at least, wants a full mb to be sure that
-	 * the writes are coherent in memory (visible to the GPU) prior to
-	 * execution, and not just visible to other CPUs (as is the result of
-	 * wmb).
 	 */
-	mb();
-
-	/* Wa_1607138340:tgl */
-	if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
-		desc |= CTX_DESC_FORCE_RESTORE;
+	wmb();
 
 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
@@ -1224,15 +1377,14 @@ trace_ports(const struct intel_engine_execlists *execlists,
 	if (!ports[0])
 		return;
 
-	GEM_TRACE("%s: %s { %llx:%lld%s, %llx:%lld }\n",
-		  engine->name, msg,
-		  ports[0]->fence.context,
-		  ports[0]->fence.seqno,
-		  i915_request_completed(ports[0]) ? "!" :
-		  i915_request_started(ports[0]) ? "*" :
-		  "",
-		  ports[1] ? ports[1]->fence.context : 0,
-		  ports[1] ? ports[1]->fence.seqno : 0);
+	ENGINE_TRACE(engine, "%s { %llx:%lld%s, %llx:%lld }\n", msg,
+		     ports[0]->fence.context,
+		     ports[0]->fence.seqno,
+		     i915_request_completed(ports[0]) ? "!" :
+		     i915_request_started(ports[0]) ? "*" :
+		     "",
+		     ports[1] ? ports[1]->fence.context : 0,
+		     ports[1] ? ports[1]->fence.seqno : 0);
 }
 
 static __maybe_unused bool
@@ -1256,33 +1408,56 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 	}
 
 	for (port = execlists->pending; (rq = *port); port++) {
-		if (ce == rq->hw_context) {
-			GEM_TRACE_ERR("Duplicate context in pending[%zd]\n",
+		unsigned long flags;
+		bool ok = true;
+
+		GEM_BUG_ON(!kref_read(&rq->fence.refcount));
+		GEM_BUG_ON(!i915_request_is_active(rq));
+
+		if (ce == rq->context) {
+			GEM_TRACE_ERR("Dup context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
 		}
+		ce = rq->context;
 
-		ce = rq->hw_context;
-		if (i915_request_completed(rq))
+		/* Hold tightly onto the lock to prevent concurrent retires! */
+		if (!spin_trylock_irqsave(&rq->lock, flags))
 			continue;
 
-		if (i915_active_is_idle(&ce->active)) {
-			GEM_TRACE_ERR("Inactive context in pending[%zd]\n",
+		if (i915_request_completed(rq))
+			goto unlock;
+
+		if (i915_active_is_idle(&ce->active) &&
+		    !intel_context_is_barrier(ce)) {
+			GEM_TRACE_ERR("Inactive context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->state)) {
-			GEM_TRACE_ERR("Unpinned context in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->ring->vma)) {
-			GEM_TRACE_ERR("Unpinned ringbuffer in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned ring:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
+
+unlock:
+		spin_unlock_irqrestore(&rq->lock, flags);
+		if (!ok)
+			return false;
 	}
 
 	return ce;
@@ -1327,7 +1502,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ce->gem_context));
+		intel_context_force_single_submission(ce));
 }
 
 static bool can_merge_ctx(const struct intel_context *prev,
@@ -1359,11 +1534,11 @@ static bool can_merge_rq(const struct i915_request *prev,
 	if (i915_request_completed(next))
 		return true;
 
-	if (unlikely((prev->flags ^ next->flags) &
-		     (I915_REQUEST_NOPREEMPT | I915_REQUEST_SENTINEL)))
+	if (unlikely((prev->fence.flags ^ next->fence.flags) &
+		     (I915_FENCE_FLAG_NOPREEMPT | I915_FENCE_FLAG_SENTINEL)))
 		return false;
 
-	if (!can_merge_ctx(prev->hw_context, next->hw_context))
+	if (!can_merge_ctx(prev->context, next->context))
 		return false;
 
 	return true;
@@ -1372,7 +1547,7 @@ static bool can_merge_rq(const struct i915_request *prev,
 static void virtual_update_register_offsets(u32 *regs,
 					    struct intel_engine_cs *engine)
 {
-	set_offsets(regs, reg_offsets(engine), engine);
+	set_offsets(regs, reg_offsets(engine), engine, false);
 }
 
 static bool virtual_matches(const struct virtual_engine *ve,
@@ -1411,7 +1586,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 	if (!list_empty(&ve->context.signal_link)) {
 		list_move_tail(&ve->context.signal_link,
 			       &engine->breadcrumbs.signalers);
-		intel_engine_queue_breadcrumbs(engine);
+		intel_engine_signal_breadcrumbs(engine);
 	}
 	spin_unlock(&old->breadcrumbs.irq_lock);
 }
@@ -1519,7 +1694,7 @@ active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct i915_request *rq = *engine->execlists.active;
 
-	if (i915_request_completed(rq))
+	if (!rq || i915_request_completed(rq))
 		return 0;
 
 	if (engine->execlists.switch_priority_hint < effective_prio(rq))
@@ -1550,7 +1725,7 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
 		return 0;
 
 	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
-	if (unlikely(i915_gem_context_is_banned(rq->gem_context)))
+	if (unlikely(intel_context_is_banned(rq->context)))
 		return 1;
 
 	return READ_ONCE(engine->props.preempt_timeout_ms);
@@ -1565,6 +1740,11 @@ static void set_preempt_timeout(struct intel_engine_cs *engine)
 		     active_preempt_timeout(engine));
 }
 
+static inline void clear_ports(struct i915_request **ports, int count)
+{
+	memset_p((void **)ports, NULL, count);
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1627,12 +1807,12 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	last = last_active(execlists);
 	if (last) {
 		if (need_preempt(engine, last, rb)) {
-			GEM_TRACE("%s: preempting last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 			record_preemption(execlists);
 
 			/*
@@ -1658,16 +1838,16 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * tendency to ignore us rewinding the TAIL to the
 			 * end of an earlier request.
 			 */
-			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+			last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {
-			GEM_TRACE("%s: expired last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -1730,7 +1910,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 		GEM_BUG_ON(rq != ve->request);
 		GEM_BUG_ON(rq->engine != &ve->base);
-		GEM_BUG_ON(rq->hw_context != &ve->context);
+		GEM_BUG_ON(rq->context != &ve->context);
 
 		if (rq_prio(rq) >= queue_prio(execlists)) {
 			if (!virtual_matches(ve, rq, engine)) {
@@ -1744,14 +1924,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				return; /* leave this for another */
 			}
 
-			GEM_TRACE("%s: virtual rq=%llx:%lld%s, new engine? %s\n",
-				  engine->name,
-				  rq->fence.context,
-				  rq->fence.seqno,
-				  i915_request_completed(rq) ? "!" :
-				  i915_request_started(rq) ? "*" :
-				  "",
-				  yesno(engine != ve->siblings[0]));
+			ENGINE_TRACE(engine,
+				     "virtual rq=%llx:%lld%s, new engine? %s\n",
+				     rq->fence.context,
+				     rq->fence.seqno,
+				     i915_request_completed(rq) ? "!" :
+				     i915_request_started(rq) ? "*" :
+				     "",
+				     yesno(engine != ve->siblings[0]));
 
 			ve->request = NULL;
 			ve->base.execlists.queue_priority_hint = INT_MIN;
@@ -1849,7 +2029,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * same LRCA, i.e. we must submit 2 different
 				 * contexts if we submit 2 ELSP.
 				 */
-				if (last->hw_context == rq->hw_context)
+				if (last->context == rq->context)
 					goto done;
 
 				if (i915_request_has_sentinel(last))
@@ -1862,8 +2042,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->hw_context) ||
-				    ctx_single_port_submission(rq->hw_context))
+				if (ctx_single_port_submission(last->context) ||
+				    ctx_single_port_submission(rq->context))
 					goto done;
 
 				merge = false;
@@ -1877,8 +2057,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				}
 
 				GEM_BUG_ON(last &&
-					   !can_merge_ctx(last->hw_context,
-							  rq->hw_context));
+					   !can_merge_ctx(last->context,
+							  rq->context));
 
 				submit = true;
 				last = rq;
@@ -1907,9 +2087,6 @@ done:
 	 * interrupt for secondary ports).
 	 */
 	execlists->queue_priority_hint = queue_prio(execlists);
-	GEM_TRACE("%s: queue_priority_hint:%d, submit:%s\n",
-		  engine->name, execlists->queue_priority_hint,
-		  yesno(submit));
 
 	if (submit) {
 		*port = execlists_schedule_in(last, port - execlists->pending);
@@ -1928,10 +2105,9 @@ done:
 
 			goto skip_submit;
 		}
+		clear_ports(port + 1, last_port - port);
 
-		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists_submit_ports(engine);
-
 		set_preempt_timeout(engine);
 	} else {
 skip_submit:
@@ -1946,13 +2122,14 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 
 	for (port = execlists->pending; *port; port++)
 		execlists_schedule_out(*port);
-	memset(execlists->pending, 0, sizeof(execlists->pending));
+	clear_ports(execlists->pending, ARRAY_SIZE(execlists->pending));
 
 	/* Mark the end of active before we overwrite *active */
 	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
 		execlists_schedule_out(*port);
-	WRITE_ONCE(execlists->active,
-		   memset(execlists->inflight, 0, sizeof(execlists->inflight)));
+	clear_ports(execlists->inflight, ARRAY_SIZE(execlists->inflight));
+
+	WRITE_ONCE(execlists->active, execlists->inflight);
 }
 
 static inline void
@@ -2058,7 +2235,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	 */
 	head = execlists->csb_head;
 	tail = READ_ONCE(*execlists->csb_write);
-	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	ENGINE_TRACE(engine, "cs-irq head=%d, tail=%d\n", head, tail);
 	if (unlikely(head == tail))
 		return;
 
@@ -2096,9 +2273,8 @@ static void process_csb(struct intel_engine_cs *engine)
 		 * status notifier.
 		 */
 
-		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x\n",
-			  engine->name, head,
-			  buf[2 * head + 0], buf[2 * head + 1]);
+		ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
+			     head, buf[2 * head + 0], buf[2 * head + 1]);
 
 		if (INTEL_GEN(engine->i915) >= 12)
 			promote = gen12_csb_parse(execlists, buf + 2 * head);
@@ -2109,7 +2285,6 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* Point active to the new ELSP; prevent overwriting */
 			WRITE_ONCE(execlists->active, execlists->pending);
-			set_timeslice(engine);
 
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
@@ -2150,6 +2325,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	} while (head != tail);
 
 	execlists->csb_head = head;
+	set_timeslice(engine);
 
 	/*
 	 * Gen11 has proven to fail wrt global observation point between
@@ -2189,10 +2365,9 @@ static noinline void preempt_reset(struct intel_engine_cs *engine)
 	/* Mark this tasklet as disabled to avoid waiting for it to complete */
 	tasklet_disable_nosync(&engine->execlists.tasklet);
 
-	GEM_TRACE("%s: preempt timeout %lu+%ums\n",
-		  engine->name,
-		  READ_ONCE(engine->props.preempt_timeout_ms),
-		  jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
+	ENGINE_TRACE(engine, "preempt timeout %lu+%ums\n",
+		     READ_ONCE(engine->props.preempt_timeout_ms),
+		     jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
 	intel_engine_reset(engine, "preemption time out");
 
 	tasklet_enable(&engine->execlists.tasklet);
@@ -2333,7 +2508,7 @@ set_redzone(void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	memset(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE);
+	memset(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE);
 }
 
 static void
@@ -2344,7 +2519,7 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	if (memchr_inv(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE))
+	if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE))
 		dev_err_once(engine->i915->drm.dev,
 			     "%s context redzone overwritten!\n",
 			     engine->name);
@@ -2369,7 +2544,7 @@ __execlists_update_reg_state(const struct intel_context *ce,
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
-	regs[CTX_RING_BUFFER_START] = i915_ggtt_offset(ring->vma);
+	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
 	regs[CTX_RING_HEAD] = ring->head;
 	regs[CTX_RING_TAIL] = ring->tail;
 
@@ -2387,33 +2562,21 @@ __execlists_context_pin(struct intel_context *ce,
 			struct intel_engine_cs *engine)
 {
 	void *vaddr;
-	int ret;
 
 	GEM_BUG_ON(!ce->state);
-
-	ret = intel_context_active_acquire(ce);
-	if (ret)
-		goto err;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	vaddr = i915_gem_object_pin_map(ce->state->obj,
 					i915_coherent_map_type(engine->i915) |
 					I915_MAP_OVERRIDE);
-	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		goto unpin_active;
-	}
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
-	ce->lrc_desc = lrc_descriptor(ce, engine);
+	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine);
 
 	return 0;
-
-unpin_active:
-	intel_context_active_release(ce);
-err:
-	return ret;
 }
 
 static int execlists_context_pin(struct intel_context *ce)
@@ -2428,6 +2591,9 @@ static int execlists_context_alloc(struct intel_context *ce)
 
 static void execlists_context_reset(struct intel_context *ce)
 {
+	CE_TRACE(ce, "reset\n");
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
+
 	/*
 	 * Because we emit WA_TAIL_DWORDS there may be a disparity
 	 * between our bookkeeping in ce->ring->head and ce->ring->tail and
@@ -2444,8 +2610,14 @@ static void execlists_context_reset(struct intel_context *ce)
 	 * So to avoid that we reset the context images upon resume. For
 	 * simplicity, we just zero everything out.
 	 */
-	intel_ring_reset(ce->ring, 0);
+	intel_ring_reset(ce->ring, ce->ring->emit);
+
+	/* Scrub away the garbage */
+	execlists_init_reg_state(ce->lrc_reg_state,
+				 ce, ce->engine, ce->ring, true);
 	__execlists_update_reg_state(ce, ce->engine);
+
+	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static const struct intel_context_ops execlists_context_ops = {
@@ -2497,7 +2669,7 @@ static int execlists_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
+	GEM_BUG_ON(!intel_context_is_pinned(request->context));
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -2867,6 +3039,8 @@ static void enable_execlists(struct intel_engine_cs *engine)
 			RING_HWS_PGA,
 			i915_ggtt_offset(engine->status_page.vma));
 	ENGINE_POSTING_READ(engine, RING_HWS_PGA);
+
+	engine->context_tag = 0;
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -2906,8 +3080,8 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
 
-	GEM_TRACE("%s: depth<-%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth<-%d\n",
+		     atomic_read(&execlists->tasklet.count));
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -2960,26 +3134,20 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 	WRITE_ONCE(*execlists->csb_write, reset_value);
 	wmb(); /* Make sure this is visible to HW (paranoia?) */
 
+	/*
+	 * Sometimes Icelake forgets to reset its pointers on a GPU reset.
+	 * Bludgeon them with a mmio update to be sure.
+	 */
+	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
+		     reset_value << 8 | reset_value);
+	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
 	invalidate_csb_entries(&execlists->csb_status[0],
 			       &execlists->csb_status[reset_value]);
 }
 
-static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
-{
-	if (INTEL_GEN(engine->i915) >= 12)
-		return 0x60;
-	else if (INTEL_GEN(engine->i915) >= 9)
-		return 0x54;
-	else if (engine->class == RENDER_CLASS)
-		return 0x58;
-	else
-		return -1;
-}
-
-static void __execlists_reset_reg_state(const struct intel_context *ce,
-					const struct intel_engine_cs *engine)
+static void __reset_stop_ring(u32 *regs, const struct intel_engine_cs *engine)
 {
-	u32 *regs = ce->lrc_reg_state;
 	int x;
 
 	x = lrc_ring_mi_mode(engine);
@@ -2989,6 +3157,14 @@ static void __execlists_reset_reg_state(const struct intel_context *ce,
 	}
 }
 
+static void __execlists_reset_reg_state(const struct intel_context *ce,
+					const struct intel_engine_cs *engine)
+{
+	u32 *regs = ce->lrc_reg_state;
+
+	__reset_stop_ring(regs, engine);
+}
+
 static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -3016,7 +3192,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	/* We still have requests in-flight; the engine should be active */
 	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 
-	ce = rq->hw_context;
+	ce = rq->context;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	if (i915_request_completed(rq)) {
@@ -3073,8 +3249,8 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	restore_default_state(ce, engine);
 
 out_replay:
-	GEM_TRACE("%s replay {head:%04x, tail:%04x}\n",
-		  engine->name, ce->ring->head, ce->ring->tail);
+	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
+		     ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
@@ -3086,11 +3262,11 @@ unwind:
 	__unwind_incomplete_requests(engine);
 }
 
-static void execlists_reset(struct intel_engine_cs *engine, bool stalled)
+static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	spin_lock_irqsave(&engine->active.lock, flags);
 
@@ -3104,14 +3280,14 @@ static void nop_submission_tasklet(unsigned long data)
 	/* The driver is wedged; don't process any more events. */
 }
 
-static void execlists_cancel_requests(struct intel_engine_cs *engine)
+static void execlists_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -3198,13 +3374,13 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	if (__tasklet_enable(&execlists->tasklet))
 		/* And kick in case we missed a new request submission. */
 		tasklet_hi_schedule(&execlists->tasklet);
-	GEM_TRACE("%s: depth->%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth->%d\n",
+		     atomic_read(&execlists->tasklet.count));
 }
 
-static int gen8_emit_bb_start(struct i915_request *rq,
-			      u64 offset, u32 len,
-			      const unsigned int flags)
+static int gen8_emit_bb_start_noarb(struct i915_request *rq,
+				    u64 offset, u32 len,
+				    const unsigned int flags)
 {
 	u32 *cs;
 
@@ -3238,7 +3414,7 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	return 0;
 }
 
-static int gen9_emit_bb_start(struct i915_request *rq,
+static int gen8_emit_bb_start(struct i915_request *rq,
 			      u64 offset, u32 len,
 			      const unsigned int flags)
 {
@@ -3693,12 +3869,12 @@ static void execlists_park(struct intel_engine_cs *engine)
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
-	engine->cancel_requests = execlists_cancel_requests;
 	engine->schedule = i915_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
+	engine->reset.rewind = execlists_reset_rewind;
+	engine->reset.cancel = execlists_reset_cancel;
 	engine->reset.finish = execlists_reset_finish;
 
 	engine->park = execlists_park;
@@ -3713,13 +3889,27 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 
 	if (INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
+
+	if (intel_engine_has_preemption(engine))
+		engine->emit_bb_start = gen8_emit_bb_start;
+	else
+		engine->emit_bb_start = gen8_emit_bb_start_noarb;
 }
 
-static void execlists_destroy(struct intel_engine_cs *engine)
+static void execlists_shutdown(struct intel_engine_cs *engine)
 {
+	/* Synchronise with residual timers and any softirq they raise */
+	del_timer_sync(&engine->execlists.timer);
+	del_timer_sync(&engine->execlists.preempt);
+	tasklet_kill(&engine->execlists.tasklet);
+}
+
+static void execlists_release(struct intel_engine_cs *engine)
+{
+	execlists_shutdown(engine);
+
 	intel_engine_cleanup_common(engine);
 	lrc_destroy_wa_ctx(engine);
-	kfree(engine);
 }
 
 static void
@@ -3727,13 +3917,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 
-	engine->destroy = execlists_destroy;
 	engine->resume = execlists_resume;
 
-	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
-	engine->reset.finish = execlists_reset_finish;
-
 	engine->cops = &execlists_context_ops;
 	engine->request_alloc = execlists_request_alloc;
 
@@ -3756,10 +3941,6 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 		 * until a more refined solution exists.
 		 */
 	}
-	if (IS_GEN(engine->i915, 8))
-		engine->emit_bb_start = gen8_emit_bb_start;
-	else
-		engine->emit_bb_start = gen9_emit_bb_start;
 }
 
 static inline void
@@ -3803,6 +3984,11 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 
 int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
+	u32 base = engine->mmio_base;
+
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
@@ -3814,21 +4000,6 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	if (engine->class == RENDER_CLASS)
 		rcs_submission_override(engine);
 
-	return 0;
-}
-
-int intel_execlists_submission_init(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct drm_i915_private *i915 = engine->i915;
-	struct intel_uncore *uncore = engine->uncore;
-	u32 base = engine->mmio_base;
-	int ret;
-
-	ret = intel_engine_init_common(engine);
-	if (ret)
-		return ret;
-
 	if (intel_init_workaround_bb(engine))
 		/*
 		 * We continue even if we fail to initialize WA batch
@@ -3860,6 +4031,9 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine)
 
 	reset_csb_pointers(engine);
 
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = execlists_release;
+
 	return 0;
 }
 
@@ -3899,18 +4073,21 @@ static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
 
 static void init_common_reg_state(u32 * const regs,
 				  const struct intel_engine_cs *engine,
-				  const struct intel_ring *ring)
+				  const struct intel_ring *ring,
+				  bool inhibit)
 {
-	regs[CTX_CONTEXT_CONTROL] =
-		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
-		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	u32 ctl;
+
+	ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	if (inhibit)
+		ctl |= CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
 	if (INTEL_GEN(engine->i915) < 11)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
-					    CTX_CTRL_RS_CTX_ENABLE);
+		ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
+					   CTX_CTRL_RS_CTX_ENABLE);
+	regs[CTX_CONTEXT_CONTROL] = ctl;
 
-	regs[CTX_RING_BUFFER_CONTROL] = RING_CTL_SIZE(ring->size) | RING_VALID;
-	regs[CTX_BB_STATE] = RING_BB_PPGTT;
+	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
 }
 
 static void init_wa_bb_reg_state(u32 * const regs,
@@ -3966,7 +4143,7 @@ static void execlists_init_reg_state(u32 *regs,
 				     const struct intel_context *ce,
 				     const struct intel_engine_cs *engine,
 				     const struct intel_ring *ring,
-				     bool close)
+				     bool inhibit)
 {
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3978,21 +4155,17 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	u32 *bbe = set_offsets(regs, reg_offsets(engine), engine);
-
-	if (close) { /* Close the batch; used mainly by live_lrc_layout() */
-		*bbe = MI_BATCH_BUFFER_END;
-		if (INTEL_GEN(engine->i915) >= 10)
-			*bbe |= BIT(0);
-	}
+	set_offsets(regs, reg_offsets(engine), engine, inhibit);
 
-	init_common_reg_state(regs, engine, ring);
+	init_common_reg_state(regs, engine, ring, inhibit);
 	init_ppgtt_reg_state(regs, vm_alias(ce->vm));
 
 	init_wa_bb_reg_state(regs, engine,
 			     INTEL_GEN(engine->i915) >= 12 ?
 			     GEN12_CTX_BB_PER_CTX_PTR :
 			     CTX_BB_PER_CTX_PTR);
+
+	__reset_stop_ring(regs, engine);
 }
 
 static int
@@ -4003,7 +4176,6 @@ populate_lr_context(struct intel_context *ce,
 {
 	bool inhibit = true;
 	void *vaddr;
-	u32 *regs;
 	int ret;
 
 	vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB);
@@ -4027,16 +4199,14 @@ populate_lr_context(struct intel_context *ce,
 
 		memcpy(vaddr, defaults, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
+		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
 
 	/* The second page of the context object contains some fields which must
 	 * be set up prior to the first execution. */
-	regs = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	execlists_init_reg_state(regs, ce, engine, ring, inhibit);
-	if (inhibit)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
+				 ce, engine, ring, inhibit);
 
 	ret = 0;
 err_unpin_ctx:
@@ -4174,6 +4344,13 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 						ve->siblings[0]);
 }
 
+static int virtual_context_alloc(struct intel_context *ce)
+{
+	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
+
+	return __execlists_context_alloc(ce, ve->siblings[0]);
+}
+
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
@@ -4211,6 +4388,8 @@ static void virtual_context_exit(struct intel_context *ce)
 }
 
 static const struct intel_context_ops virtual_context_ops = {
+	.alloc = virtual_context_alloc,
+
 	.pin = virtual_context_pin,
 	.unpin = execlists_context_unpin,
 
@@ -4237,10 +4416,9 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 		mask = ve->siblings[0]->mask;
 	}
 
-	GEM_TRACE("%s: rq=%llx:%lld, mask=%x, prio=%d\n",
-		  ve->base.name,
-		  rq->fence.context, rq->fence.seqno,
-		  mask, ve->base.execlists.queue_priority_hint);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld, mask=%x, prio=%d\n",
+		     rq->fence.context, rq->fence.seqno,
+		     mask, ve->base.execlists.queue_priority_hint);
 
 	return mask;
 }
@@ -4331,10 +4509,9 @@ static void virtual_submit_request(struct i915_request *rq)
 	struct i915_request *old;
 	unsigned long flags;
 
-	GEM_TRACE("%s: rq=%llx:%lld\n",
-		  ve->base.name,
-		  rq->fence.context,
-		  rq->fence.seqno);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld\n",
+		     rq->fence.context,
+		     rq->fence.seqno);
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
@@ -4402,8 +4579,7 @@ virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 }
 
 struct intel_context *
-intel_execlists_create_virtual(struct i915_gem_context *ctx,
-			       struct intel_engine_cs **siblings,
+intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count)
 {
 	struct virtual_engine *ve;
@@ -4414,13 +4590,13 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		return ERR_PTR(-EINVAL);
 
 	if (count == 1)
-		return intel_context_create(ctx, siblings[0]);
+		return intel_context_create(siblings[0]);
 
 	ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL);
 	if (!ve)
 		return ERR_PTR(-ENOMEM);
 
-	ve->base.i915 = ctx->i915;
+	ve->base.i915 = siblings[0]->i915;
 	ve->base.gt = siblings[0]->gt;
 	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
@@ -4449,7 +4625,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
-
 	intel_engine_init_execlists(&ve->base);
 
 	ve->base.cops = &virtual_context_ops;
@@ -4465,7 +4640,7 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
 
-	intel_context_init(&ve->context, ctx, &ve->base);
+	intel_context_init(&ve->context, &ve->base);
 
 	for (n = 0; n < count; n++) {
 		struct intel_engine_cs *sibling = siblings[n];
@@ -4532,12 +4707,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
-	err = __execlists_context_alloc(&ve->context, siblings[0]);
-	if (err)
-		goto err_put;
-
-	__set_bit(CONTEXT_ALLOC_BIT, &ve->context.flags);
-
 	return &ve->context;
 
 err_put:
@@ -4546,14 +4715,12 @@ err_put:
 }
 
 struct intel_context *
-intel_execlists_clone_virtual(struct i915_gem_context *ctx,
-			      struct intel_engine_cs *src)
+intel_execlists_clone_virtual(struct intel_engine_cs *src)
 {
 	struct virtual_engine *se = to_virtual_engine(src);
 	struct intel_context *dst;
 
-	dst = intel_execlists_create_virtual(ctx,
-					     se->siblings,
+	dst = intel_execlists_create_virtual(se->siblings,
 					     se->num_siblings);
 	if (IS_ERR(dst))
 		return dst;