Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.2.

  I've one other new driver from freescale on my radar, it's been posted
  and reviewed, I'd just like to get someone to give it a last look, so
  maybe I'll send it or maybe I'll leave it.

  There is no major nouveau changes in here, Ben was working on
  something big, and we agreed it was a bit late, there wasn't anything
  else he considered urgent to merge.

  There might be another msm pull for some bits that are waiting on
  arm-soc, I'll see how we time it.

  This touches some "of" stuff, acks are in place except for the fixes
  to the build in various configs,t hat I just applied.

  Summary:

  New drivers:
      - virtio-gpu:
                KMS only pieces of driver for virtio-gpu in qemu.
                This is just the first part of this driver, enough to run
                unaccelerated userspace on. As qemu merges more we'll start
                adding the 3D features for the virgl 3d work.
      - amdgpu:
                a new driver from AMD to driver their newer GPUs. (VI+)
                It contains a new cleaner userspace API, and is a clean
                break from radeon moving forward, that AMD are going to
                concentrate on. It also contains a set of register headers
                auto generated from AMD internal database.

  core:
      - atomic modesetting API completed, enabled by default now.
      - Add support for mode_id blob to atomic ioctl to complete interface.
      - bunch of Displayport MST fixes
      - lots of misc fixes.

  panel:
      - new simple panels
      - fix some long-standing build issues with bridge drivers

  radeon:
      - VCE1 support
      - add a GPU reset counter for userspace
      - lots of fixes.

  amdkfd:
      - H/W debugger support module
      - static user-mode queues
      - support killing all the waves when a process terminates
      - use standard DECLARE_BITMAP

  i915:
      - Add Broxton support
      - S3, rotation support for Skylake
      - RPS booting tuning
      - CPT modeset sequence fixes
      - ns2501 dither support
      - enable cmd parser on haswell
      - cdclk handling fixes
      - gen8 dynamic pte allocation
      - lots of atomic conversion work

  exynos:
      - Add atomic modesetting support
      - Add iommu support
      - Consolidate drm driver initialization
      - and MIC, DECON and MIPI-DSI support for exynos5433

  omapdrm:
      - atomic modesetting support (fixes lots of things in rewrite)

  tegra:
      - DP aux transaction fixes
      - iommu support fix

  msm:
      - adreno a306 support
      - various dsi bits
      - various 64-bit fixes
      - NV12MT support

  rcar-du:
      - atomic and misc fixes

  sti:
      - fix HDMI timing complaince

  tilcdc:
      - use drm component API to access tda998x driver
      - fix module unloading

  qxl:
      - stability fixes"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (872 commits)
  drm/nouveau: Pause between setting gpu to D3hot and cutting the power
  drm/dp/mst: close deadlock in connector destruction.
  drm: Always enable atomic API
  drm/vgem: Set unique to "vgem"
  of: fix a build error to of_graph_get_endpoint_by_regs function
  drm/dp/mst: take lock around looking up the branch device on hpd irq
  drm/dp/mst: make sure mst_primary mstb is valid in work function
  of: add EXPORT_SYMBOL for of_graph_get_endpoint_by_regs
  ARM: dts: rename the clock of MIPI DSI 'pll_clk' to 'sclk_mipi'
  drm/atomic: Don't set crtc_state->enable manually
  drm/exynos: dsi: do not set TE GPIO direction by input
  drm/exynos: dsi: add support for MIC driver as a bridge
  drm/exynos: dsi: add support for Exynos5433
  drm/exynos: dsi: make use of array for clock access
  drm/exynos: dsi: make use of driver data for static values
  drm/exynos: dsi: add macros for register access
  drm/exynos: dsi: rename pll_clk to sclk_clk
  drm/exynos: mic: add MIC driver
  of: add helper for getting endpoint node of specific identifiers
  drm/exynos: add Exynos5433 decon driver
  ...

1 files changed, 246 insertions, 277 deletions

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 424e62197787..9b74ffae5f5a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -188,6 +188,15 @@
 #define GEN8_CTX_FORCE_RESTORE (1<<2)
 #define GEN8_CTX_L3LLC_COHERENT (1<<5)
 #define GEN8_CTX_PRIVILEGE (1<<8)
+
+#define ASSIGN_CTX_PDP(ppgtt, reg_state, n) { \
+	const u64 _addr = test_bit(n, ppgtt->pdp.used_pdpes) ? \
+		ppgtt->pdp.page_directory[n]->daddr : \
+		ppgtt->scratch_pd->daddr; \
+	reg_state[CTX_PDP ## n ## _UDW+1] = upper_32_bits(_addr); \
+	reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
+}
+
 enum {
 	ADVANCED_CONTEXT = 0,
 	LEGACY_CONTEXT,
@@ -265,7 +274,8 @@ static uint64_t execlists_ctx_descriptor(struct intel_engine_cs *ring,
 
 	desc = GEN8_CTX_VALID;
 	desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
-	desc |= GEN8_CTX_L3LLC_COHERENT;
+	if (IS_GEN8(ctx_obj->base.dev))
+		desc |= GEN8_CTX_L3LLC_COHERENT;
 	desc |= GEN8_CTX_PRIVILEGE;
 	desc |= lrca;
 	desc |= (u64)intel_execlists_ctx_id(ctx_obj) << GEN8_CTX_ID_SHIFT;
@@ -305,21 +315,24 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
 	desc[3] = (u32)(temp >> 32);
 	desc[2] = (u32)temp;
 
-	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-	I915_WRITE(RING_ELSP(ring), desc[1]);
-	I915_WRITE(RING_ELSP(ring), desc[0]);
-	I915_WRITE(RING_ELSP(ring), desc[3]);
+	spin_lock(&dev_priv->uncore.lock);
+	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
+	I915_WRITE_FW(RING_ELSP(ring), desc[1]);
+	I915_WRITE_FW(RING_ELSP(ring), desc[0]);
+	I915_WRITE_FW(RING_ELSP(ring), desc[3]);
 
 	/* The context is automatically loaded after the following */
-	I915_WRITE(RING_ELSP(ring), desc[2]);
+	I915_WRITE_FW(RING_ELSP(ring), desc[2]);
 
 	/* ELSP is a wo register, so use another nearby reg for posting instead */
-	POSTING_READ(RING_EXECLIST_STATUS(ring));
-	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	POSTING_READ_FW(RING_EXECLIST_STATUS(ring));
+	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
+	spin_unlock(&dev_priv->uncore.lock);
 }
 
 static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
 				    struct drm_i915_gem_object *ring_obj,
+				    struct i915_hw_ppgtt *ppgtt,
 				    u32 tail)
 {
 	struct page *page;
@@ -331,6 +344,16 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
 	reg_state[CTX_RING_TAIL+1] = tail;
 	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
 
+	/* True PPGTT with dynamic page allocation: update PDP registers and
+	 * point the unallocated PDPs to the scratch page
+	 */
+	if (ppgtt) {
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+		ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+	}
+
 	kunmap_atomic(reg_state);
 
 	return 0;
@@ -349,7 +372,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,
 	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));
 	WARN_ON(!i915_gem_obj_is_pinned(ringbuf0->obj));
 
-	execlists_update_context(ctx_obj0, ringbuf0->obj, tail0);
+	execlists_update_context(ctx_obj0, ringbuf0->obj, to0->ppgtt, tail0);
 
 	if (to1) {
 		ringbuf1 = to1->engine[ring->id].ringbuf;
@@ -358,7 +381,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,
 		WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
 		WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));
 
-		execlists_update_context(ctx_obj1, ringbuf1->obj, tail1);
+		execlists_update_context(ctx_obj1, ringbuf1->obj, to1->ppgtt, tail1);
 	}
 
 	execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
@@ -371,6 +394,12 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
 
 	assert_spin_locked(&ring->execlist_lock);
 
+	/*
+	 * If irqs are not active generate a warning as batches that finish
+	 * without the irqs may get lost and a GPU Hang may occur.
+	 */
+	WARN_ON(!intel_irqs_enabled(ring->dev->dev_private));
+
 	if (list_empty(&ring->execlist_queue))
 		return;
 
@@ -398,7 +427,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
 		 * WaIdleLiteRestore: make sure we never cause a lite
 		 * restore with HEAD==TAIL
 		 */
-		if (req0 && req0->elsp_submitted) {
+		if (req0->elsp_submitted) {
 			/*
 			 * Apply the wa NOOPS to prevent ring:HEAD == req:TAIL
 			 * as we resubmit the request. See gen8_emit_request()
@@ -520,8 +549,6 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 				   struct drm_i915_gem_request *request)
 {
 	struct drm_i915_gem_request *cursor;
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	unsigned long flags;
 	int num_elements = 0;
 
 	if (to != ring->default_context)
@@ -538,7 +565,6 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 		request->ring = ring;
 		request->ctx = to;
 		kref_init(&request->ref);
-		request->uniq = dev_priv->request_uniq++;
 		i915_gem_context_reference(request->ctx);
 	} else {
 		i915_gem_request_reference(request);
@@ -546,9 +572,7 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 	}
 	request->tail = tail;
 
-	intel_runtime_pm_get(dev_priv);
-
-	spin_lock_irqsave(&ring->execlist_lock, flags);
+	spin_lock_irq(&ring->execlist_lock);
 
 	list_for_each_entry(cursor, &ring->execlist_queue, execlist_link)
 		if (++num_elements > 2)
@@ -574,7 +598,7 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 	if (num_elements == 0)
 		execlists_context_unqueue(ring);
 
-	spin_unlock_irqrestore(&ring->execlist_lock, flags);
+	spin_unlock_irq(&ring->execlist_lock);
 
 	return 0;
 }
@@ -604,6 +628,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
 				 struct list_head *vmas)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
+	const unsigned other_rings = ~intel_ring_flag(ring);
 	struct i915_vma *vma;
 	uint32_t flush_domains = 0;
 	bool flush_chipset = false;
@@ -612,9 +637,11 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
 	list_for_each_entry(vma, vmas, exec_list) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
-		ret = i915_gem_object_sync(obj, ring);
-		if (ret)
-			return ret;
+		if (obj->active & other_rings) {
+			ret = i915_gem_object_sync(obj, ring);
+			if (ret)
+				return ret;
+		}
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
 			flush_chipset |= i915_gem_clflush_object(obj, false);
@@ -631,6 +658,170 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
 	return logical_ring_invalidate_all_caches(ringbuf, ctx);
 }
 
+int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request,
+					    struct intel_context *ctx)
+{
+	int ret;
+
+	if (ctx != request->ring->default_context) {
+		ret = intel_lr_context_pin(request->ring, ctx);
+		if (ret)
+			return ret;
+	}
+
+	request->ringbuf = ctx->engine[request->ring->id].ringbuf;
+	request->ctx     = ctx;
+	i915_gem_context_reference(request->ctx);
+
+	return 0;
+}
+
+static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
+				       struct intel_context *ctx,
+				       int bytes)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_i915_gem_request *request;
+	unsigned space;
+	int ret;
+
+	if (intel_ring_space(ringbuf) >= bytes)
+		return 0;
+
+	list_for_each_entry(request, &ring->request_list, list) {
+		/*
+		 * The request queue is per-engine, so can contain requests
+		 * from multiple ringbuffers. Here, we must ignore any that
+		 * aren't from the ringbuffer we're considering.
+		 */
+		if (request->ringbuf != ringbuf)
+			continue;
+
+		/* Would completion of this request free enough space? */
+		space = __intel_ring_space(request->postfix, ringbuf->tail,
+					   ringbuf->size);
+		if (space >= bytes)
+			break;
+	}
+
+	if (WARN_ON(&request->list == &ring->request_list))
+		return -ENOSPC;
+
+	ret = i915_wait_request(request);
+	if (ret)
+		return ret;
+
+	ringbuf->space = space;
+	return 0;
+}
+
+/*
+ * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
+ * @ringbuf: Logical Ringbuffer to advance.
+ *
+ * The tail is updated in our logical ringbuffer struct, not in the actual context. What
+ * really happens during submission is that the context and current tail will be placed
+ * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
+ * point, the tail *inside* the context is updated and the ELSP written to.
+ */
+static void
+intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+				      struct intel_context *ctx,
+				      struct drm_i915_gem_request *request)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+
+	intel_logical_ring_advance(ringbuf);
+
+	if (intel_ring_stopped(ring))
+		return;
+
+	execlists_context_queue(ring, ctx, ringbuf->tail, request);
+}
+
+static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
+				    struct intel_context *ctx)
+{
+	uint32_t __iomem *virt;
+	int rem = ringbuf->size - ringbuf->tail;
+
+	if (ringbuf->space < rem) {
+		int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
+
+		if (ret)
+			return ret;
+	}
+
+	virt = ringbuf->virtual_start + ringbuf->tail;
+	rem /= 4;
+	while (rem--)
+		iowrite32(MI_NOOP, virt++);
+
+	ringbuf->tail = 0;
+	intel_ring_update_space(ringbuf);
+
+	return 0;
+}
+
+static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
+				struct intel_context *ctx, int bytes)
+{
+	int ret;
+
+	if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
+		ret = logical_ring_wrap_buffer(ringbuf, ctx);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	if (unlikely(ringbuf->space < bytes)) {
+		ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
+ *
+ * @ringbuf: Logical ringbuffer.
+ * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
+ *
+ * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
+ * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
+ * and also preallocates a request (every workload submission is still mediated through
+ * requests, same as it did with legacy ringbuffer submission).
+ *
+ * Return: non-zero if the ringbuffer is not ready to be written to.
+ */
+static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
+				    struct intel_context *ctx, int num_dwords)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+				   dev_priv->mm.interruptible);
+	if (ret)
+		return ret;
+
+	ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
+	if (ret)
+		return ret;
+
+	/* Preallocate the olr before touching the ring */
+	ret = i915_gem_request_alloc(ring, ctx);
+	if (ret)
+		return ret;
+
+	ringbuf->space -= num_dwords * sizeof(uint32_t);
+	return 0;
+}
+
 /**
  * execlists_submission() - submit a batchbuffer for execution, Execlists style
  * @dev: DRM device.
@@ -742,8 +933,6 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
 void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_request *req, *tmp;
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	unsigned long flags;
 	struct list_head retired_list;
 
 	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
@@ -751,9 +940,9 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 		return;
 
 	INIT_LIST_HEAD(&retired_list);
-	spin_lock_irqsave(&ring->execlist_lock, flags);
+	spin_lock_irq(&ring->execlist_lock);
 	list_replace_init(&ring->execlist_retired_req_list, &retired_list);
-	spin_unlock_irqrestore(&ring->execlist_lock, flags);
+	spin_unlock_irq(&ring->execlist_lock);
 
 	list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
 		struct intel_context *ctx = req->ctx;
@@ -762,7 +951,6 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 
 		if (ctx_obj && (ctx != ring->default_context))
 			intel_lr_context_unpin(ring, ctx);
-		intel_runtime_pm_put(dev_priv);
 		list_del(&req->execlist_link);
 		i915_gem_request_unreference(req);
 	}
@@ -807,30 +995,6 @@ int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
 	return 0;
 }
 
-/*
- * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
- * @ringbuf: Logical Ringbuffer to advance.
- *
- * The tail is updated in our logical ringbuffer struct, not in the actual context. What
- * really happens during submission is that the context and current tail will be placed
- * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
- * point, the tail *inside* the context is updated and the ELSP written to.
- */
-static void
-intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
-				      struct intel_context *ctx,
-				      struct drm_i915_gem_request *request)
-{
-	struct intel_engine_cs *ring = ringbuf->ring;
-
-	intel_logical_ring_advance(ringbuf);
-
-	if (intel_ring_stopped(ring))
-		return;
-
-	execlists_context_queue(ring, ctx, ringbuf->tail, request);
-}
-
 static int intel_lr_context_pin(struct intel_engine_cs *ring,
 		struct intel_context *ctx)
 {
@@ -875,219 +1039,6 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
 	}
 }
 
-static int logical_ring_alloc_request(struct intel_engine_cs *ring,
-				      struct intel_context *ctx)
-{
-	struct drm_i915_gem_request *request;
-	struct drm_i915_private *dev_private = ring->dev->dev_private;
-	int ret;
-
-	if (ring->outstanding_lazy_request)
-		return 0;
-
-	request = kzalloc(sizeof(*request), GFP_KERNEL);
-	if (request == NULL)
-		return -ENOMEM;
-
-	if (ctx != ring->default_context) {
-		ret = intel_lr_context_pin(ring, ctx);
-		if (ret) {
-			kfree(request);
-			return ret;
-		}
-	}
-
-	kref_init(&request->ref);
-	request->ring = ring;
-	request->uniq = dev_private->request_uniq++;
-
-	ret = i915_gem_get_seqno(ring->dev, &request->seqno);
-	if (ret) {
-		intel_lr_context_unpin(ring, ctx);
-		kfree(request);
-		return ret;
-	}
-
-	request->ctx = ctx;
-	i915_gem_context_reference(request->ctx);
-	request->ringbuf = ctx->engine[ring->id].ringbuf;
-
-	ring->outstanding_lazy_request = request;
-	return 0;
-}
-
-static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
-				     int bytes)
-{
-	struct intel_engine_cs *ring = ringbuf->ring;
-	struct drm_i915_gem_request *request;
-	int ret;
-
-	if (intel_ring_space(ringbuf) >= bytes)
-		return 0;
-
-	list_for_each_entry(request, &ring->request_list, list) {
-		/*
-		 * The request queue is per-engine, so can contain requests
-		 * from multiple ringbuffers. Here, we must ignore any that
-		 * aren't from the ringbuffer we're considering.
-		 */
-		struct intel_context *ctx = request->ctx;
-		if (ctx->engine[ring->id].ringbuf != ringbuf)
-			continue;
-
-		/* Would completion of this request free enough space? */
-		if (__intel_ring_space(request->tail, ringbuf->tail,
-				       ringbuf->size) >= bytes) {
-			break;
-		}
-	}
-
-	if (&request->list == &ring->request_list)
-		return -ENOSPC;
-
-	ret = i915_wait_request(request);
-	if (ret)
-		return ret;
-
-	i915_gem_retire_requests_ring(ring);
-
-	return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
-}
-
-static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
-				       struct intel_context *ctx,
-				       int bytes)
-{
-	struct intel_engine_cs *ring = ringbuf->ring;
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long end;
-	int ret;
-
-	ret = logical_ring_wait_request(ringbuf, bytes);
-	if (ret != -ENOSPC)
-		return ret;
-
-	/* Force the context submission in case we have been skipping it */
-	intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
-
-	/* With GEM the hangcheck timer should kick us out of the loop,
-	 * leaving it early runs the risk of corrupting GEM state (due
-	 * to running on almost untested codepaths). But on resume
-	 * timers don't work yet, so prevent a complete hang in that
-	 * case by choosing an insanely large timeout. */
-	end = jiffies + 60 * HZ;
-
-	ret = 0;
-	do {
-		if (intel_ring_space(ringbuf) >= bytes)
-			break;
-
-		msleep(1);
-
-		if (dev_priv->mm.interruptible && signal_pending(current)) {
-			ret = -ERESTARTSYS;
-			break;
-		}
-
-		ret = i915_gem_check_wedge(&dev_priv->gpu_error,
-					   dev_priv->mm.interruptible);
-		if (ret)
-			break;
-
-		if (time_after(jiffies, end)) {
-			ret = -EBUSY;
-			break;
-		}
-	} while (1);
-
-	return ret;
-}
-
-static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
-				    struct intel_context *ctx)
-{
-	uint32_t __iomem *virt;
-	int rem = ringbuf->size - ringbuf->tail;
-
-	if (ringbuf->space < rem) {
-		int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
-
-		if (ret)
-			return ret;
-	}
-
-	virt = ringbuf->virtual_start + ringbuf->tail;
-	rem /= 4;
-	while (rem--)
-		iowrite32(MI_NOOP, virt++);
-
-	ringbuf->tail = 0;
-	intel_ring_update_space(ringbuf);
-
-	return 0;
-}
-
-static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
-				struct intel_context *ctx, int bytes)
-{
-	int ret;
-
-	if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
-		ret = logical_ring_wrap_buffer(ringbuf, ctx);
-		if (unlikely(ret))
-			return ret;
-	}
-
-	if (unlikely(ringbuf->space < bytes)) {
-		ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
-		if (unlikely(ret))
-			return ret;
-	}
-
-	return 0;
-}
-
-/**
- * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
- *
- * @ringbuf: Logical ringbuffer.
- * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
- *
- * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
- * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
- * and also preallocates a request (every workload submission is still mediated through
- * requests, same as it did with legacy ringbuffer submission).
- *
- * Return: non-zero if the ringbuffer is not ready to be written to.
- */
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
-			     struct intel_context *ctx, int num_dwords)
-{
-	struct intel_engine_cs *ring = ringbuf->ring;
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-	ret = i915_gem_check_wedge(&dev_priv->gpu_error,
-				   dev_priv->mm.interruptible);
-	if (ret)
-		return ret;
-
-	ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
-	if (ret)
-		return ret;
-
-	/* Preallocate the olr before touching the ring */
-	ret = logical_ring_alloc_request(ring, ctx);
-	if (ret)
-		return ret;
-
-	ringbuf->space -= num_dwords * sizeof(uint32_t);
-	return 0;
-}
-
 static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
 					       struct intel_context *ctx)
 {
@@ -1288,6 +1239,7 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	bool vf_flush_wa;
 	u32 flags = 0;
 	int ret;
 
@@ -1309,10 +1261,26 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
 	}
 
-	ret = intel_logical_ring_begin(ringbuf, ctx, 6);
+	/*
+	 * On GEN9+ Before VF_CACHE_INVALIDATE we need to emit a NULL pipe
+	 * control.
+	 */
+	vf_flush_wa = INTEL_INFO(ring->dev)->gen >= 9 &&
+		      flags & PIPE_CONTROL_VF_CACHE_INVALIDATE;
+
+	ret = intel_logical_ring_begin(ringbuf, ctx, vf_flush_wa ? 12 : 6);
 	if (ret)
 		return ret;
 
+	if (vf_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf, flags);
 	intel_logical_ring_emit(ringbuf, scratch_addr);
@@ -1443,6 +1411,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
 		ring->cleanup(ring);
 
 	i915_cmd_parser_fini_ring(ring);
+	i915_gem_batch_pool_fini(&ring->batch_pool);
 
 	if (ring->status_page.obj) {
 		kunmap(sg_page(ring->status_page.obj->pages->sgl));
@@ -1460,6 +1429,7 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
+	i915_gem_batch_pool_init(dev, &ring->batch_pool);
 	init_waitqueue_head(&ring->irq_queue);
 
 	INIT_LIST_HEAD(&ring->execlist_queue);
@@ -1812,14 +1782,14 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 	reg_state[CTX_PDP1_LDW] = GEN8_RING_PDP_LDW(ring, 1);
 	reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
 	reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
-	reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[3]->daddr);
-	reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[3]->daddr);
-	reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[2]->daddr);
-	reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[2]->daddr);
-	reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[1]->daddr);
-	reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[1]->daddr);
-	reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pdp.page_directory[0]->daddr);
-	reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pdp.page_directory[0]->daddr);
+
+	/* With dynamic page allocation, PDPs may not be allocated at this point,
+	 * Point the unallocated PDPs to the scratch page
+	 */
+	ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+	ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+	ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+	ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
 	if (ring->id == RCS) {
 		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
 		reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE;
@@ -1936,11 +1906,10 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
 
 	context_size = round_up(get_lr_context_size(ring), 4096);
 
-	ctx_obj = i915_gem_alloc_context_obj(dev, context_size);
-	if (IS_ERR(ctx_obj)) {
-		ret = PTR_ERR(ctx_obj);
-		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed: %d\n", ret);
-		return ret;
+	ctx_obj = i915_gem_alloc_object(dev, context_size);
+	if (!ctx_obj) {
+		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n");
+		return -ENOMEM;
 	}
 
 	if (is_global_default_ctx) {