Linux-libre 4.6.2-gnu

63 files changed, 4838 insertions, 3471 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 051eab33e..20a5d0455 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -2,9 +2,7 @@ config DRM_I915
 	tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics"
 	depends on DRM
 	depends on X86 && PCI
-	depends on (AGP || AGP=n)
 	select INTEL_GTT
-	select AGP_INTEL if AGP
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
@@ -47,3 +45,14 @@ config DRM_I915_PRELIMINARY_HW_SUPPORT
 	  option changes the default for that module option.
 
 	  If in doubt, say "N".
+
+config DRM_I915_USERPTR
+	bool "Always enable userptr support"
+	depends on DRM_I915
+	select MMU_NOTIFIER
+	default y
+	help
+	  This option selects CONFIG_MMU_NOTIFIER if it isn't already
+	  selected to enabled full userptr support.
+
+	  If in doubt, say "Y".
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index cf39ed313..e3f4c725a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -117,9 +117,8 @@ static u64 i915_gem_obj_total_ggtt_size(struct drm_i915_gem_object *obj)
 	u64 size = 0;
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
-		if (i915_is_ggtt(vma->vm) &&
-		    drm_mm_node_allocated(&vma->node))
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
+		if (vma->is_ggtt && drm_mm_node_allocated(&vma->node))
 			size += vma->node.size;
 	}
 
@@ -155,7 +154,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   obj->madv == I915_MADV_DONTNEED ? " purgeable" : "");
 	if (obj->base.name)
 		seq_printf(m, " (name: %d)", obj->base.name);
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
 		if (vma->pin_count > 0)
 			pin_count++;
 	}
@@ -164,14 +163,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (display)");
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
 		seq_printf(m, " (%sgtt offset: %08llx, size: %08llx",
-			   i915_is_ggtt(vma->vm) ? "g" : "pp",
+			   vma->is_ggtt ? "g" : "pp",
 			   vma->node.start, vma->node.size);
-		if (i915_is_ggtt(vma->vm))
-			seq_printf(m, ", type: %u)", vma->ggtt_view.type);
-		else
-			seq_puts(m, ")");
+		if (vma->is_ggtt)
+			seq_printf(m, ", type: %u", vma->ggtt_view.type);
+		seq_puts(m, ")");
 	}
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
@@ -230,7 +228,7 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	}
 
 	total_obj_size = total_gtt_size = count = 0;
-	list_for_each_entry(vma, head, mm_list) {
+	list_for_each_entry(vma, head, vm_link) {
 		seq_printf(m, "   ");
 		describe_obj(m, vma->obj);
 		seq_printf(m, "\n");
@@ -342,13 +340,13 @@ static int per_file_stats(int id, void *ptr, void *data)
 		stats->shared += obj->base.size;
 
 	if (USES_FULL_PPGTT(obj->base.dev)) {
-		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		list_for_each_entry(vma, &obj->vma_list, obj_link) {
 			struct i915_hw_ppgtt *ppgtt;
 
 			if (!drm_mm_node_allocated(&vma->node))
 				continue;
 
-			if (i915_is_ggtt(vma->vm)) {
+			if (vma->is_ggtt) {
 				stats->global += obj->base.size;
 				continue;
 			}
@@ -454,12 +452,12 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   count, mappable_count, size, mappable_size);
 
 	size = count = mappable_size = mappable_count = 0;
-	count_vmas(&vm->active_list, mm_list);
+	count_vmas(&vm->active_list, vm_link);
 	seq_printf(m, "  %u [%u] active objects, %llu [%llu] bytes\n",
 		   count, mappable_count, size, mappable_size);
 
 	size = count = mappable_size = mappable_count = 0;
-	count_vmas(&vm->inactive_list, mm_list);
+	count_vmas(&vm->inactive_list, vm_link);
 	seq_printf(m, "  %u [%u] inactive objects, %llu [%llu] bytes\n",
 		   count, mappable_count, size, mappable_size);
 
@@ -1336,7 +1334,8 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	struct intel_engine_cs *ring;
 	u64 acthd[I915_NUM_RINGS];
 	u32 seqno[I915_NUM_RINGS];
-	int i;
+	u32 instdone[I915_NUM_INSTDONE_REG];
+	int i, j;
 
 	if (!i915.enable_hangcheck) {
 		seq_printf(m, "Hangcheck disabled\n");
@@ -1350,6 +1349,8 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		acthd[i] = intel_ring_get_active_head(ring);
 	}
 
+	i915_get_extra_instdone(dev, instdone);
+
 	intel_runtime_pm_put(dev_priv);
 
 	if (delayed_work_pending(&dev_priv->gpu_error.hangcheck_work)) {
@@ -1370,6 +1371,21 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 			   (long long)ring->hangcheck.max_acthd);
 		seq_printf(m, "\tscore = %d\n", ring->hangcheck.score);
 		seq_printf(m, "\taction = %d\n", ring->hangcheck.action);
+
+		if (ring->id == RCS) {
+			seq_puts(m, "\tinstdone read =");
+
+			for (j = 0; j < I915_NUM_INSTDONE_REG; j++)
+				seq_printf(m, " 0x%08x", instdone[j]);
+
+			seq_puts(m, "\n\tinstdone accu =");
+
+			for (j = 0; j < I915_NUM_INSTDONE_REG; j++)
+				seq_printf(m, " 0x%08x",
+					   ring->hangcheck.instdone[j]);
+
+			seq_puts(m, "\n");
+		}
 	}
 
 	return 0;
@@ -1947,11 +1963,8 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 		seq_puts(m, "HW context ");
 		describe_ctx(m, ctx);
-		for_each_ring(ring, dev_priv, i) {
-			if (ring->default_context == ctx)
-				seq_printf(m, "(default context %s) ",
-					   ring->name);
-		}
+		if (ctx == dev_priv->kernel_context)
+			seq_printf(m, "(kernel context) ");
 
 		if (i915.enable_execlists) {
 			seq_putc(m, '\n');
@@ -1981,12 +1994,13 @@ static int i915_context_status(struct seq_file *m, void *unused)
 }
 
 static void i915_dump_lrc_obj(struct seq_file *m,
-			      struct intel_engine_cs *ring,
-			      struct drm_i915_gem_object *ctx_obj)
+			      struct intel_context *ctx,
+			      struct intel_engine_cs *ring)
 {
 	struct page *page;
 	uint32_t *reg_state;
 	int j;
+	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
 	unsigned long ggtt_offset = 0;
 
 	if (ctx_obj == NULL) {
@@ -1996,7 +2010,7 @@ static void i915_dump_lrc_obj(struct seq_file *m,
 	}
 
 	seq_printf(m, "CONTEXT: %s %u\n", ring->name,
-		   intel_execlists_ctx_id(ctx_obj));
+		   intel_execlists_ctx_id(ctx, ring));
 
 	if (!i915_gem_obj_ggtt_bound(ctx_obj))
 		seq_puts(m, "\tNot bound in GGTT\n");
@@ -2042,13 +2056,10 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 	if (ret)
 		return ret;
 
-	list_for_each_entry(ctx, &dev_priv->context_list, link) {
-		for_each_ring(ring, dev_priv, i) {
-			if (ring->default_context != ctx)
-				i915_dump_lrc_obj(m, ring,
-						  ctx->engine[i].state);
-		}
-	}
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		if (ctx != dev_priv->kernel_context)
+			for_each_ring(ring, dev_priv, i)
+				i915_dump_lrc_obj(m, ctx, ring);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -2097,13 +2108,13 @@ static int i915_execlists(struct seq_file *m, void *data)
 		seq_printf(m, "\tStatus pointer: 0x%08X\n", status_pointer);
 
 		read_pointer = ring->next_context_status_buffer;
-		write_pointer = status_pointer & 0x07;
+		write_pointer = GEN8_CSB_WRITE_PTR(status_pointer);
 		if (read_pointer > write_pointer)
-			write_pointer += 6;
+			write_pointer += GEN8_CSB_ENTRIES;
 		seq_printf(m, "\tRead pointer: 0x%08X, write pointer 0x%08X\n",
 			   read_pointer, write_pointer);
 
-		for (i = 0; i < 6; i++) {
+		for (i = 0; i < GEN8_CSB_ENTRIES; i++) {
 			status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, i));
 			ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, i));
 
@@ -2120,11 +2131,8 @@ static int i915_execlists(struct seq_file *m, void *data)
 
 		seq_printf(m, "\t%d requests in queue\n", count);
 		if (head_req) {
-			struct drm_i915_gem_object *ctx_obj;
-
-			ctx_obj = head_req->ctx->engine[ring_id].state;
 			seq_printf(m, "\tHead request id: %u\n",
-				   intel_execlists_ctx_id(ctx_obj));
+				   intel_execlists_ctx_id(head_req->ctx, ring));
 			seq_printf(m, "\tHead request tail: %u\n",
 				   head_req->tail);
 		}
@@ -2458,9 +2466,9 @@ static void i915_guc_client_info(struct seq_file *m,
 
 	for_each_ring(ring, dev_priv, i) {
 		seq_printf(m, "\tSubmissions: %llu %s\n",
-				client->submissions[i],
+				client->submissions[ring->guc_id],
 				ring->name);
-		tot += client->submissions[i];
+		tot += client->submissions[ring->guc_id];
 	}
 	seq_printf(m, "\tTotal: %llu\n", tot);
 }
@@ -2497,10 +2505,10 @@ static int i915_guc_info(struct seq_file *m, void *data)
 
 	seq_printf(m, "\nGuC submissions:\n");
 	for_each_ring(ring, dev_priv, i) {
-		seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x %9d\n",
-			ring->name, guc.submissions[i],
-			guc.last_seqno[i], guc.last_seqno[i]);
-		total += guc.submissions[i];
+		seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x\n",
+			ring->name, guc.submissions[ring->guc_id],
+			guc.last_seqno[ring->guc_id]);
+		total += guc.submissions[ring->guc_id];
 	}
 	seq_printf(m, "\t%s: %llu\n", "Total", total);
 
@@ -2578,6 +2586,10 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 				enabled = true;
 		}
 	}
+
+	seq_printf(m, "Main link in standby mode: %s\n",
+		   yesno(dev_priv->psr.link_standby));
+
 	seq_printf(m, "HW Enabled & Active bit: %s", yesno(enabled));
 
 	if (!HAS_DDI(dev))
@@ -2860,20 +2872,6 @@ static void intel_dp_info(struct seq_file *m,
 		intel_panel_info(m, &intel_connector->panel);
 }
 
-static void intel_dp_mst_info(struct seq_file *m,
-			  struct intel_connector *intel_connector)
-{
-	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct intel_dp_mst_encoder *intel_mst =
-		enc_to_mst(&intel_encoder->base);
-	struct intel_digital_port *intel_dig_port = intel_mst->primary;
-	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	bool has_audio = drm_dp_mst_port_has_audio(&intel_dp->mst_mgr,
-					intel_connector->port);
-
-	seq_printf(m, "\taudio support: %s\n", yesno(has_audio));
-}
-
 static void intel_hdmi_info(struct seq_file *m,
 			    struct intel_connector *intel_connector)
 {
@@ -2917,8 +2915,6 @@ static void intel_connector_info(struct seq_file *m,
 			intel_hdmi_info(m, intel_connector);
 		else if (intel_encoder->type == INTEL_OUTPUT_LVDS)
 			intel_lvds_info(m, intel_connector);
-		else if (intel_encoder->type == INTEL_OUTPUT_DP_MST)
-			intel_dp_mst_info(m, intel_connector);
 	}
 
 	seq_printf(m, "\tmodes:\n");
@@ -3216,9 +3212,11 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 {
 	int i;
 	int ret;
+	struct intel_engine_cs *ring;
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_workarounds *workarounds = &dev_priv->workarounds;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
@@ -3226,15 +3224,18 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 
 	intel_runtime_pm_get(dev_priv);
 
-	seq_printf(m, "Workarounds applied: %d\n", dev_priv->workarounds.count);
-	for (i = 0; i < dev_priv->workarounds.count; ++i) {
+	seq_printf(m, "Workarounds applied: %d\n", workarounds->count);
+	for_each_ring(ring, dev_priv, i)
+		seq_printf(m, "HW whitelist count for %s: %d\n",
+			   ring->name, workarounds->hw_whitelist_count[i]);
+	for (i = 0; i < workarounds->count; ++i) {
 		i915_reg_t addr;
 		u32 mask, value, read;
 		bool ok;
 
-		addr = dev_priv->workarounds.reg[i].addr;
-		mask = dev_priv->workarounds.reg[i].mask;
-		value = dev_priv->workarounds.reg[i].value;
+		addr = workarounds->reg[i].addr;
+		mask = workarounds->reg[i].mask;
+		value = workarounds->reg[i].value;
 		read = I915_READ(addr);
 		ok = (value & mask) == (read & mask);
 		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X, read: 0x%08x, status: %s\n",
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index d70d96fe5..1c6d227aa 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -391,20 +391,13 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (ret)
 		goto cleanup_vga_client;
 
-	/* Initialise stolen first so that we may reserve preallocated
-	 * objects for the BIOS to KMS transition.
-	 */
-	ret = i915_gem_init_stolen(dev);
-	if (ret)
-		goto cleanup_vga_switcheroo;
-
 	intel_power_domains_init_hw(dev_priv, false);
 
 	intel_csr_ucode_init(dev_priv);
 
 	ret = intel_irq_install(dev_priv);
 	if (ret)
-		goto cleanup_gem_stolen;
+		goto cleanup_csr;
 
 	intel_setup_gmbus(dev);
 
@@ -458,9 +451,8 @@ cleanup_irq:
 	intel_guc_ucode_fini(dev);
 	drm_irq_uninstall(dev);
 	intel_teardown_gmbus(dev);
-cleanup_gem_stolen:
-	i915_gem_cleanup_stolen(dev);
-cleanup_vga_switcheroo:
+cleanup_csr:
+	intel_csr_ucode_fini(dev_priv);
 	vga_switcheroo_unregister_client(dev->pdev);
 cleanup_vga_client:
 	vga_client_register(dev->pdev, NULL, NULL, NULL);
@@ -816,7 +808,41 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
 			DRM_INFO("Display fused off, disabling\n");
 			info->num_pipes = 0;
+		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
+			DRM_INFO("PipeC fused off\n");
+			info->num_pipes -= 1;
 		}
+	} else if (info->num_pipes > 0 && INTEL_INFO(dev)->gen == 9) {
+		u32 dfsm = I915_READ(SKL_DFSM);
+		u8 disabled_mask = 0;
+		bool invalid;
+		int num_bits;
+
+		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
+			disabled_mask |= BIT(PIPE_A);
+		if (dfsm & SKL_DFSM_PIPE_B_DISABLE)
+			disabled_mask |= BIT(PIPE_B);
+		if (dfsm & SKL_DFSM_PIPE_C_DISABLE)
+			disabled_mask |= BIT(PIPE_C);
+
+		num_bits = hweight8(disabled_mask);
+
+		switch (disabled_mask) {
+		case BIT(PIPE_A):
+		case BIT(PIPE_B):
+		case BIT(PIPE_A) | BIT(PIPE_B):
+		case BIT(PIPE_A) | BIT(PIPE_C):
+			invalid = true;
+			break;
+		default:
+			invalid = false;
+		}
+
+		if (num_bits > info->num_pipes || invalid)
+			DRM_ERROR("invalid pipe fuse configuration: 0x%x\n",
+				  disabled_mask);
+		else
+			info->num_pipes -= num_bits;
 	}
 
 	/* Initialize slice/subslice/EU info */
@@ -855,6 +881,94 @@ static void intel_init_dpio(struct drm_i915_private *dev_priv)
 	}
 }
 
+static int i915_workqueues_init(struct drm_i915_private *dev_priv)
+{
+	/*
+	 * The i915 workqueue is primarily used for batched retirement of
+	 * requests (and thus managing bo) once the task has been completed
+	 * by the GPU. i915_gem_retire_requests() is called directly when we
+	 * need high-priority retirement, such as waiting for an explicit
+	 * bo.
+	 *
+	 * It is also used for periodic low-priority events, such as
+	 * idle-timers and recording error state.
+	 *
+	 * All tasks on the workqueue are expected to acquire the dev mutex
+	 * so there is no point in running more than one instance of the
+	 * workqueue at any time.  Use an ordered one.
+	 */
+	dev_priv->wq = alloc_ordered_workqueue("i915", 0);
+	if (dev_priv->wq == NULL)
+		goto out_err;
+
+	dev_priv->hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0);
+	if (dev_priv->hotplug.dp_wq == NULL)
+		goto out_free_wq;
+
+	dev_priv->gpu_error.hangcheck_wq =
+		alloc_ordered_workqueue("i915-hangcheck", 0);
+	if (dev_priv->gpu_error.hangcheck_wq == NULL)
+		goto out_free_dp_wq;
+
+	return 0;
+
+out_free_dp_wq:
+	destroy_workqueue(dev_priv->hotplug.dp_wq);
+out_free_wq:
+	destroy_workqueue(dev_priv->wq);
+out_err:
+	DRM_ERROR("Failed to allocate workqueues.\n");
+
+	return -ENOMEM;
+}
+
+static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv)
+{
+	destroy_workqueue(dev_priv->gpu_error.hangcheck_wq);
+	destroy_workqueue(dev_priv->hotplug.dp_wq);
+	destroy_workqueue(dev_priv->wq);
+}
+
+static int i915_mmio_setup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int mmio_bar;
+	int mmio_size;
+
+	mmio_bar = IS_GEN2(dev) ? 1 : 0;
+	/*
+	 * Before gen4, the registers and the GTT are behind different BARs.
+	 * However, from gen4 onwards, the registers and the GTT are shared
+	 * in the same BAR, so we want to restrict this ioremap from
+	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
+	 * the register BAR remains the same size for all the earlier
+	 * generations up to Ironlake.
+	 */
+	if (INTEL_INFO(dev)->gen < 5)
+		mmio_size = 512 * 1024;
+	else
+		mmio_size = 2 * 1024 * 1024;
+	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
+	if (dev_priv->regs == NULL) {
+		DRM_ERROR("failed to map registers\n");
+
+		return -EIO;
+	}
+
+	/* Try to make sure MCHBAR is enabled before poking at it */
+	intel_setup_mchbar(dev);
+
+	return 0;
+}
+
+static void i915_mmio_cleanup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	intel_teardown_mchbar(dev);
+	pci_iounmap(dev->pdev, dev_priv->regs);
+}
+
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -870,7 +984,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 {
 	struct drm_i915_private *dev_priv;
 	struct intel_device_info *info, *device_info;
-	int ret = 0, mmio_bar, mmio_size;
+	int ret = 0;
 	uint32_t aperture_size;
 
 	info = (struct intel_device_info *) flags;
@@ -897,6 +1011,10 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	mutex_init(&dev_priv->modeset_restore_lock);
 	mutex_init(&dev_priv->av_mutex);
 
+	ret = i915_workqueues_init(dev_priv);
+	if (ret < 0)
+		goto out_free_priv;
+
 	intel_pm_setup(dev);
 
 	intel_runtime_pm_get(dev_priv);
@@ -915,28 +1033,12 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	if (i915_get_bridge_dev(dev)) {
 		ret = -EIO;
-		goto free_priv;
+		goto out_runtime_pm_put;
 	}
 
-	mmio_bar = IS_GEN2(dev) ? 1 : 0;
-	/* Before gen4, the registers and the GTT are behind different BARs.
-	 * However, from gen4 onwards, the registers and the GTT are shared
-	 * in the same BAR, so we want to restrict this ioremap from
-	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
-	 * the register BAR remains the same size for all the earlier
-	 * generations up to Ironlake.
-	 */
-	if (info->gen < 5)
-		mmio_size = 512*1024;
-	else
-		mmio_size = 2*1024*1024;
-
-	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
-	if (!dev_priv->regs) {
-		DRM_ERROR("failed to map registers\n");
-		ret = -EIO;
+	ret = i915_mmio_setup(dev);
+	if (ret < 0)
 		goto put_bridge;
-	}
 
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(dev);
@@ -945,7 +1047,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	ret = i915_gem_gtt_init(dev);
 	if (ret)
-		goto out_freecsr;
+		goto out_uncore_fini;
 
 	/* WARNING: Apparently we must kick fbdev drivers before vgacon,
 	 * otherwise the vga fbdev driver falls over. */
@@ -991,49 +1093,13 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	dev_priv->gtt.mtrr = arch_phys_wc_add(dev_priv->gtt.mappable_base,
 					      aperture_size);
 
-	/* The i915 workqueue is primarily used for batched retirement of
-	 * requests (and thus managing bo) once the task has been completed
-	 * by the GPU. i915_gem_retire_requests() is called directly when we
-	 * need high-priority retirement, such as waiting for an explicit
-	 * bo.
-	 *
-	 * It is also used for periodic low-priority events, such as
-	 * idle-timers and recording error state.
-	 *
-	 * All tasks on the workqueue are expected to acquire the dev mutex
-	 * so there is no point in running more than one instance of the
-	 * workqueue at any time.  Use an ordered one.
-	 */
-	dev_priv->wq = alloc_ordered_workqueue("i915", 0);
-	if (dev_priv->wq == NULL) {
-		DRM_ERROR("Failed to create our workqueue.\n");
-		ret = -ENOMEM;
-		goto out_mtrrfree;
-	}
-
-	dev_priv->hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0);
-	if (dev_priv->hotplug.dp_wq == NULL) {
-		DRM_ERROR("Failed to create our dp workqueue.\n");
-		ret = -ENOMEM;
-		goto out_freewq;
-	}
-
-	dev_priv->gpu_error.hangcheck_wq =
-		alloc_ordered_workqueue("i915-hangcheck", 0);
-	if (dev_priv->gpu_error.hangcheck_wq == NULL) {
-		DRM_ERROR("Failed to create our hangcheck workqueue.\n");
-		ret = -ENOMEM;
-		goto out_freedpwq;
-	}
-
 	intel_irq_init(dev_priv);
 	intel_uncore_sanitize(dev);
 
-	/* Try to make sure MCHBAR is enabled before poking at it */
-	intel_setup_mchbar(dev);
 	intel_opregion_setup(dev);
 
-	i915_gem_load(dev);
+	i915_gem_load_init(dev);
+	i915_gem_shrinker_init(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
 	 * integrated graphics even though the support isn't actually there
@@ -1046,8 +1112,10 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	 * be lost or delayed, but we use them anyways to avoid
 	 * stuck interrupts on some machines.
 	 */
-	if (!IS_I945G(dev) && !IS_I945GM(dev))
-		pci_enable_msi(dev->pdev);
+	if (!IS_I945G(dev) && !IS_I945GM(dev)) {
+		if (pci_enable_msi(dev->pdev) < 0)
+			DRM_DEBUG_DRIVER("can't enable MSI");
+	}
 
 	intel_device_info_runtime_init(dev);
 
@@ -1097,38 +1165,29 @@ out_power_well:
 	intel_power_domains_fini(dev_priv);
 	drm_vblank_cleanup(dev);
 out_gem_unload:
-	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
-	unregister_shrinker(&dev_priv->mm.shrinker);
+	i915_gem_shrinker_cleanup(dev_priv);
 
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
 
 	intel_teardown_mchbar(dev);
 	pm_qos_remove_request(&dev_priv->pm_qos);
-	destroy_workqueue(dev_priv->gpu_error.hangcheck_wq);
-out_freedpwq:
-	destroy_workqueue(dev_priv->hotplug.dp_wq);
-out_freewq:
-	destroy_workqueue(dev_priv->wq);
-out_mtrrfree:
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
 	io_mapping_free(dev_priv->gtt.mappable);
 out_gtt:
 	i915_global_gtt_cleanup(dev);
-out_freecsr:
-	intel_csr_ucode_fini(dev_priv);
+out_uncore_fini:
 	intel_uncore_fini(dev);
-	pci_iounmap(dev->pdev, dev_priv->regs);
+	i915_mmio_cleanup(dev);
 put_bridge:
 	pci_dev_put(dev_priv->bridge_dev);
-free_priv:
-	kmem_cache_destroy(dev_priv->requests);
-	kmem_cache_destroy(dev_priv->vmas);
-	kmem_cache_destroy(dev_priv->objects);
-
+	i915_gem_load_cleanup(dev);
+out_runtime_pm_put:
 	intel_runtime_pm_put(dev_priv);
-
+	i915_workqueues_cleanup(dev_priv);
+out_free_priv:
 	kfree(dev_priv);
+
 	return ret;
 }
 
@@ -1153,8 +1212,7 @@ int i915_driver_unload(struct drm_device *dev)
 
 	i915_teardown_sysfs(dev);
 
-	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
-	unregister_shrinker(&dev_priv->mm.shrinker);
+	i915_gem_shrinker_cleanup(dev_priv);
 
 	io_mapping_free(dev_priv->gtt.mappable);
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
@@ -1182,6 +1240,8 @@ int i915_driver_unload(struct drm_device *dev)
 	vga_switcheroo_unregister_client(dev->pdev);
 	vga_client_register(dev->pdev, NULL, NULL, NULL);
 
+	intel_csr_ucode_fini(dev_priv);
+
 	/* Free error state after interrupts are fully disabled. */
 	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
 	i915_destroy_error_state(dev);
@@ -1200,27 +1260,17 @@ int i915_driver_unload(struct drm_device *dev)
 	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
 	intel_fbc_cleanup_cfb(dev_priv);
-	i915_gem_cleanup_stolen(dev);
 
-	intel_csr_ucode_fini(dev_priv);
-
-	intel_teardown_mchbar(dev);
-
-	destroy_workqueue(dev_priv->hotplug.dp_wq);
-	destroy_workqueue(dev_priv->wq);
-	destroy_workqueue(dev_priv->gpu_error.hangcheck_wq);
 	pm_qos_remove_request(&dev_priv->pm_qos);
 
 	i915_global_gtt_cleanup(dev);
 
 	intel_uncore_fini(dev);
-	if (dev_priv->regs != NULL)
-		pci_iounmap(dev->pdev, dev_priv->regs);
+	i915_mmio_cleanup(dev);
 
-	kmem_cache_destroy(dev_priv->requests);
-	kmem_cache_destroy(dev_priv->vmas);
-	kmem_cache_destroy(dev_priv->objects);
+	i915_gem_load_cleanup(dev);
 	pci_dev_put(dev_priv->bridge_dev);
+	i915_workqueues_cleanup(dev_priv);
 	kfree(dev_priv);
 
 	return 0;
@@ -1261,8 +1311,6 @@ void i915_driver_preclose(struct drm_device *dev, struct drm_file *file)
 	i915_gem_context_close(dev, file);
 	i915_gem_release(dev, file);
 	mutex_unlock(&dev->struct_mutex);
-
-	intel_modeset_preclose(dev, file);
 }
 
 void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index da9a471fc..6d2fb3f4a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -35,9 +35,12 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+#include <linux/apple-gmux.h>
 #include <linux/console.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
+#include <linux/vgaarb.h>
+#include <linux/vga_switcheroo.h>
 #include <drm/drm_crtc_helper.h>
 
 static struct drm_driver driver;
@@ -600,13 +603,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_suspend_gt_powersave(dev);
 
-	/*
-	 * Disable CRTCs directly since we want to preserve sw state
-	 * for _thaw. Also, power gate the CRTC power wells.
-	 */
-	drm_modeset_lock_all(dev);
 	intel_display_suspend(dev);
-	drm_modeset_unlock_all(dev);
 
 	intel_dp_mst_suspend(dev);
 
@@ -763,9 +760,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_dp_mst_resume(dev);
 
-	drm_modeset_lock_all(dev);
 	intel_display_resume(dev);
-	drm_modeset_unlock_all(dev);
 
 	/*
 	 * ... but also need to make sure that hotplug processing
@@ -999,6 +994,15 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (PCI_FUNC(pdev->devfn))
 		return -ENODEV;
 
+	/*
+	 * apple-gmux is needed on dual GPU MacBook Pro
+	 * to probe the panel if we're the inactive GPU.
+	 */
+	if (IS_ENABLED(CONFIG_VGA_ARB) && IS_ENABLED(CONFIG_VGA_SWITCHEROO) &&
+	    apple_gmux_present() && pdev != vga_default_device() &&
+	    !vga_switcheroo_handler_flags())
+		return -EPROBE_DEFER;
+
 	return drm_get_pci_dev(pdev, ent, &driver);
 }
 
@@ -1109,7 +1113,6 @@ static int bxt_resume_prepare(struct drm_i915_private *dev_priv)
 	 */
 	broxton_init_cdclk(dev);
 	broxton_ddi_phy_init(dev);
-	intel_prepare_ddi(dev);
 
 	return 0;
 }
@@ -1368,8 +1371,8 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
 		return 0;
 
 	DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n",
-			wait_for_on ? "on" : "off",
-			I915_READ(VLV_GTLC_PW_STATUS));
+		      onoff(wait_for_on),
+		      I915_READ(VLV_GTLC_PW_STATUS));
 
 	/*
 	 * RC6 transitioning can be delayed up to 2 msec (see
@@ -1378,7 +1381,7 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
 	err = wait_for(COND, 3);
 	if (err)
 		DRM_ERROR("timeout waiting for GT wells to go %s\n",
-			  wait_for_on ? "on" : "off");
+			  onoff(wait_for_on));
 
 	return err;
 #undef COND
@@ -1389,7 +1392,7 @@ static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv)
 	if (!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEERR))
 		return;
 
-	DRM_ERROR("GT register access while GT waking disabled\n");
+	DRM_DEBUG_DRIVER("GT register access while GT waking disabled\n");
 	I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR);
 }
 
@@ -1533,6 +1536,10 @@ static int intel_runtime_suspend(struct device *device)
 
 	enable_rpm_wakeref_asserts(dev_priv);
 	WARN_ON_ONCE(atomic_read(&dev_priv->pm.wakeref_count));
+
+	if (intel_uncore_arm_unclaimed_mmio_detection(dev_priv))
+		DRM_ERROR("Unclaimed access detected prior to suspending\n");
+
 	dev_priv->pm.suspended = true;
 
 	/*
@@ -1581,6 +1588,8 @@ static int intel_runtime_resume(struct device *device)
 
 	intel_opregion_notify_adapter(dev, PCI_D0);
 	dev_priv->pm.suspended = false;
+	if (intel_uncore_unclaimed_mmio(dev_priv))
+		DRM_DEBUG_DRIVER("Unclaimed access during suspend, bios?\n");
 
 	intel_guc_resume(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b0847b915..daba7ebb9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -34,6 +34,7 @@
 #include <uapi/drm/drm_fourcc.h>
 
 #include <drm/drmP.h>
+#include "i915_params.h"
 #include "i915_reg.h"
 #include "intel_bios.h"
 #include "intel_ringbuffer.h"
@@ -58,7 +59,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20151218"
+#define DRIVER_DATE		"20160229"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -69,11 +70,11 @@
 		BUILD_BUG_ON(__i915_warn_cond); \
 	WARN(__i915_warn_cond, "WARN_ON(" #x ")"); })
 #else
-#define WARN_ON(x) WARN((x), "WARN_ON(%s)", #x )
+#define WARN_ON(x) WARN((x), "%s", "WARN_ON(" __stringify(x) ")")
 #endif
 
 #undef WARN_ON_ONCE
-#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(%s)", #x )
+#define WARN_ON_ONCE(x) WARN_ONCE((x), "%s", "WARN_ON_ONCE(" __stringify(x) ")")
 
 #define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \
 			     (long) (x), __func__);
@@ -87,31 +88,25 @@
  */
 #define I915_STATE_WARN(condition, format...) ({			\
 	int __ret_warn_on = !!(condition);				\
-	if (unlikely(__ret_warn_on)) {					\
-		if (i915.verbose_state_checks)				\
-			WARN(1, format);				\
-		else 							\
+	if (unlikely(__ret_warn_on))					\
+		if (!WARN(i915.verbose_state_checks, format))		\
 			DRM_ERROR(format);				\
-	}								\
 	unlikely(__ret_warn_on);					\
 })
 
-#define I915_STATE_WARN_ON(condition) ({				\
-	int __ret_warn_on = !!(condition);				\
-	if (unlikely(__ret_warn_on)) {					\
-		if (i915.verbose_state_checks)				\
-			WARN(1, "WARN_ON(" #condition ")\n");		\
-		else 							\
-			DRM_ERROR("WARN_ON(" #condition ")\n");		\
-	}								\
-	unlikely(__ret_warn_on);					\
-})
+#define I915_STATE_WARN_ON(x)						\
+	I915_STATE_WARN((x), "%s", "WARN_ON(" __stringify(x) ")")
 
 static inline const char *yesno(bool v)
 {
 	return v ? "yes" : "no";
 }
 
+static inline const char *onoff(bool v)
+{
+	return v ? "on" : "off";
+}
+
 enum pipe {
 	INVALID_PIPE = -1,
 	PIPE_A = 0,
@@ -266,6 +261,9 @@ struct i915_hotplug {
 
 #define for_each_pipe(__dev_priv, __p) \
 	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++)
+#define for_each_pipe_masked(__dev_priv, __p, __mask) \
+	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++) \
+		for_each_if ((__mask) & (1 << (__p)))
 #define for_each_plane(__dev_priv, __pipe, __p)				\
 	for ((__p) = 0;							\
 	     (__p) < INTEL_INFO(__dev_priv)->num_sprites[(__pipe)] + 1;	\
@@ -339,7 +337,7 @@ struct drm_i915_file_private {
 		unsigned boosts;
 	} rps;
 
-	struct intel_engine_cs *bsd_ring;
+	unsigned int bsd_ring;
 };
 
 enum intel_dpll_id {
@@ -633,6 +631,7 @@ struct drm_i915_display_funcs {
 			  struct dpll *best_clock);
 	int (*compute_pipe_wm)(struct intel_crtc *crtc,
 			       struct drm_atomic_state *state);
+	void (*program_watermarks)(struct intel_crtc_state *cstate);
 	void (*update_wm)(struct drm_crtc *crtc);
 	int (*modeset_calc_cdclk)(struct drm_atomic_state *state);
 	void (*modeset_commit_cdclk)(struct drm_atomic_state *state);
@@ -657,9 +656,6 @@ struct drm_i915_display_funcs {
 			  struct drm_i915_gem_object *obj,
 			  struct drm_i915_gem_request *req,
 			  uint32_t flags);
-	void (*update_primary_plane)(struct drm_crtc *crtc,
-				     struct drm_framebuffer *fb,
-				     int x, int y);
 	void (*hpd_irq_setup)(struct drm_device *dev);
 	/* clock updates for mode set */
 	/* cursor updates */
@@ -726,6 +722,8 @@ struct intel_uncore {
 		i915_reg_t reg_post;
 		u32 val_reset;
 	} fw_domain[FW_DOMAIN_ID_COUNT];
+
+	int unclaimed_mmio_check;
 };
 
 /* Iterate over initialised fw domains */
@@ -890,6 +888,9 @@ struct intel_context {
 		struct drm_i915_gem_object *state;
 		struct intel_ringbuffer *ringbuf;
 		int pin_count;
+		struct i915_vma *lrc_vma;
+		u64 lrc_desc;
+		uint32_t *lrc_reg_state;
 	} engine[I915_NUM_RINGS];
 
 	struct list_head link;
@@ -903,16 +904,15 @@ enum fb_op_origin {
 	ORIGIN_DIRTYFB,
 };
 
-struct i915_fbc {
+struct intel_fbc {
 	/* This is always the inner lock when overlapping with struct_mutex and
 	 * it's the outer lock when overlapping with stolen_lock. */
 	struct mutex lock;
 	unsigned threshold;
-	unsigned int fb_id;
 	unsigned int possible_framebuffer_bits;
 	unsigned int busy_bits;
+	unsigned int visible_pipes_mask;
 	struct intel_crtc *crtc;
-	int y;
 
 	struct drm_mm_node compressed_fb;
 	struct drm_mm_node *compressed_llb;
@@ -922,18 +922,52 @@ struct i915_fbc {
 	bool enabled;
 	bool active;
 
+	struct intel_fbc_state_cache {
+		struct {
+			unsigned int mode_flags;
+			uint32_t hsw_bdw_pixel_rate;
+		} crtc;
+
+		struct {
+			unsigned int rotation;
+			int src_w;
+			int src_h;
+			bool visible;
+		} plane;
+
+		struct {
+			u64 ilk_ggtt_offset;
+			uint32_t pixel_format;
+			unsigned int stride;
+			int fence_reg;
+			unsigned int tiling_mode;
+		} fb;
+	} state_cache;
+
+	struct intel_fbc_reg_params {
+		struct {
+			enum pipe pipe;
+			enum plane plane;
+			unsigned int fence_y_offset;
+		} crtc;
+
+		struct {
+			u64 ggtt_offset;
+			uint32_t pixel_format;
+			unsigned int stride;
+			int fence_reg;
+		} fb;
+
+		int cfb_size;
+	} params;
+
 	struct intel_fbc_work {
 		bool scheduled;
+		u32 scheduled_vblank;
 		struct work_struct work;
-		struct drm_framebuffer *fb;
-		unsigned long enable_jiffies;
 	} work;
 
 	const char *no_fbc_reason;
-
-	bool (*is_active)(struct drm_i915_private *dev_priv);
-	void (*activate)(struct intel_crtc *crtc);
-	void (*deactivate)(struct drm_i915_private *dev_priv);
 };
 
 /**
@@ -973,6 +1007,7 @@ struct i915_psr {
 	unsigned busy_frontbuffer_bits;
 	bool psr2_support;
 	bool aux_frame_sync;
+	bool link_standby;
 };
 
 enum intel_pch {
@@ -1302,7 +1337,7 @@ struct i915_gem_mm {
 	bool busy;
 
 	/* the indicator for dispatch video commands on two BSD rings */
-	int bsd_ring_dispatch_index;
+	unsigned int bsd_ring_dispatch_index;
 
 	/** Bit 6 swizzling required for X tiling */
 	uint32_t bit_6_swizzle_x;
@@ -1488,7 +1523,7 @@ struct intel_vbt_data {
 		u8 seq_version;
 		u32 size;
 		u8 *data;
-		u8 *sequence[MIPI_SEQ_MAX];
+		const u8 *sequence[MIPI_SEQ_MAX];
 	} dsi;
 
 	int crt_ddc_pin;
@@ -1660,11 +1695,18 @@ struct i915_wa_reg {
 	u32 mask;
 };
 
-#define I915_MAX_WA_REGS 16
+/*
+ * RING_MAX_NONPRIV_SLOTS is per-engine but at this point we are only
+ * allowing it for RCS as we don't foresee any requirement of having
+ * a whitelist for other engines. When it is really required for
+ * other engines then the limit need to be increased.
+ */
+#define I915_MAX_WA_REGS (16 + RING_MAX_NONPRIV_SLOTS)
 
 struct i915_workarounds {
 	struct i915_wa_reg reg[I915_MAX_WA_REGS];
 	u32 count;
+	u32 hw_whitelist_count[I915_NUM_RINGS];
 };
 
 struct i915_virtual_gpu {
@@ -1761,7 +1803,7 @@ struct drm_i915_private {
 	u32 pipestat_irq_mask[I915_MAX_PIPES];
 
 	struct i915_hotplug hotplug;
-	struct i915_fbc fbc;
+	struct intel_fbc fbc;
 	struct i915_drrs drrs;
 	struct intel_opregion opregion;
 	struct intel_vbt_data vbt;
@@ -1785,7 +1827,7 @@ struct drm_i915_private {
 
 	unsigned int fsb_freq, mem_freq, is_ddr3;
 	unsigned int skl_boot_cdclk;
-	unsigned int cdclk_freq, max_cdclk_freq;
+	unsigned int cdclk_freq, max_cdclk_freq, atomic_cdclk_freq;
 	unsigned int max_dotclk_freq;
 	unsigned int hpll_freq;
 	unsigned int czclk_freq;
@@ -1810,6 +1852,7 @@ struct drm_i915_private {
 
 	enum modeset_restore modeset_restore;
 	struct mutex modeset_restore_lock;
+	struct drm_atomic_state *modeset_restore_state;
 
 	struct list_head vm_list; /* Global list of all address spaces */
 	struct i915_gtt gtt; /* VM representing the global address space */
@@ -1830,8 +1873,13 @@ struct drm_i915_private {
 	struct intel_pipe_crc pipe_crc[I915_MAX_PIPES];
 #endif
 
+	/* dpll and cdclk state is protected by connection_mutex */
 	int num_shared_dpll;
 	struct intel_shared_dpll shared_dplls[I915_NUM_PLLS];
+
+	unsigned int active_crtcs;
+	unsigned int min_pixclk[I915_MAX_PIPES];
+
 	int dpio_phy_iosf_port[I915_NUM_PHYS_VLV];
 
 	struct i915_workarounds workarounds;
@@ -1946,6 +1994,8 @@ struct drm_i915_private {
 		void (*stop_ring)(struct intel_engine_cs *ring);
 	} gt;
 
+	struct intel_context *kernel_context;
+
 	bool edp_low_vswing;
 
 	/* perform PHY state sanity checks? */
@@ -2270,9 +2320,9 @@ struct drm_i915_gem_request {
 
 };
 
-int i915_gem_request_alloc(struct intel_engine_cs *ring,
-			   struct intel_context *ctx,
-			   struct drm_i915_gem_request **req_out);
+struct drm_i915_gem_request * __must_check
+i915_gem_request_alloc(struct intel_engine_cs *engine,
+		       struct intel_context *ctx);
 void i915_gem_request_cancel(struct drm_i915_gem_request *req);
 void i915_gem_request_free(struct kref *req_ref);
 int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
@@ -2581,6 +2631,12 @@ struct drm_i915_cmd_table {
 
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
+
+/* WaRsDisableCoarsePowerGating:skl,bxt */
+#define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \
+						 IS_SKL_GT3(dev) || \
+						 IS_SKL_GT4(dev))
+
 /*
  * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
  * even when in MSI mode. This results in spurious interrupt warnings if the
@@ -2670,44 +2726,7 @@ extern int i915_max_ioctl;
 extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state);
 extern int i915_resume_switcheroo(struct drm_device *dev);
 
-/* i915_params.c */
-struct i915_params {
-	int modeset;
-	int panel_ignore_lid;
-	int semaphores;
-	int lvds_channel_mode;
-	int panel_use_ssc;
-	int vbt_sdvo_panel_type;
-	int enable_rc6;
-	int enable_dc;
-	int enable_fbc;
-	int enable_ppgtt;
-	int enable_execlists;
-	int enable_psr;
-	unsigned int preliminary_hw_support;
-	int disable_power_well;
-	int enable_ips;
-	int invert_brightness;
-	int enable_cmd_parser;
-	/* leave bools at the end to not create holes */
-	bool enable_hangcheck;
-	bool fastboot;
-	bool prefault_disable;
-	bool load_detect_test;
-	bool reset;
-	bool disable_display;
-	bool disable_vtd_wa;
-	bool enable_guc_submission;
-	int guc_log_level;
-	int use_mmio_flip;
-	int mmio_debug;
-	bool verbose_state_checks;
-	bool nuclear_pageflip;
-	int edp_vswing;
-};
-extern struct i915_params i915 __read_mostly;
-
-				/* i915_dma.c */
+/* i915_dma.c */
 extern int i915_driver_load(struct drm_device *, unsigned long flags);
 extern int i915_driver_unload(struct drm_device *);
 extern int i915_driver_open(struct drm_device *dev, struct drm_file *file);
@@ -2750,7 +2769,8 @@ extern void intel_uncore_sanitize(struct drm_device *dev);
 extern void intel_uncore_early_sanitize(struct drm_device *dev,
 					bool restore_forcewake);
 extern void intel_uncore_init(struct drm_device *dev);
-extern void intel_uncore_check_errors(struct drm_device *dev);
+extern bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv);
+extern bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv);
 extern void intel_uncore_fini(struct drm_device *dev);
 extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore);
 const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id);
@@ -2872,7 +2892,8 @@ int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
-void i915_gem_load(struct drm_device *dev);
+void i915_gem_load_init(struct drm_device *dev);
+void i915_gem_load_cleanup(struct drm_device *dev);
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
@@ -3136,18 +3157,11 @@ bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj);
 /* Some GGTT VM helpers */
 #define i915_obj_to_ggtt(obj) \
 	(&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base)
-static inline bool i915_is_ggtt(struct i915_address_space *vm)
-{
-	struct i915_address_space *ggtt =
-		&((struct drm_i915_private *)(vm)->dev->dev_private)->gtt.base;
-	return vm == ggtt;
-}
 
 static inline struct i915_hw_ppgtt *
 i915_vm_to_ppgtt(struct i915_address_space *vm)
 {
 	WARN_ON(i915_is_ggtt(vm));
-
 	return container_of(vm, struct i915_hw_ppgtt, base);
 }
 
@@ -3285,6 +3299,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
 #define I915_SHRINK_ACTIVE 0x8
 unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
+void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv);
 
 
 /* i915_gem_tiling.c */
@@ -3455,16 +3470,14 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val
 u32 vlv_punit_read(struct drm_i915_private *dev_priv, u32 addr);
 void vlv_punit_write(struct drm_i915_private *dev_priv, u32 addr, u32 val);
 u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr);
-u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg);
-void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
+u32 vlv_iosf_sb_read(struct drm_i915_private *dev_priv, u8 port, u32 reg);
+void vlv_iosf_sb_write(struct drm_i915_private *dev_priv, u8 port, u32 reg, u32 val);
 u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
-u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg);
-void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg);
 void vlv_dpio_write(struct drm_i915_private *dev_priv, enum pipe pipe, int reg, u32 val);
 u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index bb44bad15..dabc08987 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -138,10 +138,10 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 
 	pinned = 0;
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(vma, &ggtt->base.active_list, mm_list)
+	list_for_each_entry(vma, &ggtt->base.active_list, vm_link)
 		if (vma->pin_count)
 			pinned += vma->node.size;
-	list_for_each_entry(vma, &ggtt->base.inactive_list, mm_list)
+	list_for_each_entry(vma, &ggtt->base.inactive_list, vm_link)
 		if (vma->pin_count)
 			pinned += vma->node.size;
 	mutex_unlock(&dev->struct_mutex);
@@ -177,7 +177,7 @@ i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 		drm_clflush_virt_range(vaddr, PAGE_SIZE);
 		kunmap_atomic(src);
 
-		page_cache_release(page);
+		put_page(page);
 		vaddr += PAGE_SIZE;
 	}
 
@@ -243,7 +243,7 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj)
 			set_page_dirty(page);
 			if (obj->madv == I915_MADV_WILLNEED)
 				mark_page_accessed(page);
-			page_cache_release(page);
+			put_page(page);
 			vaddr += PAGE_SIZE;
 		}
 		obj->dirty = 0;
@@ -272,7 +272,7 @@ drop_pages(struct drm_i915_gem_object *obj)
 	int ret;
 
 	drm_gem_object_reference(&obj->base);
-	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link)
+	list_for_each_entry_safe(vma, next, &obj->vma_list, obj_link)
 		if (i915_vma_unbind(vma))
 			break;
 
@@ -489,7 +489,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
 
 	*needs_clflush = 0;
 
-	if (!obj->base.filp)
+	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
 		return -EINVAL;
 
 	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
@@ -1251,7 +1251,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
 	DEFINE_WAIT(wait);
 	unsigned long timeout_expire;
-	s64 before, now;
+	s64 before = 0; /* Only to silence a compiler warning. */
 	int ret;
 
 	WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled");
@@ -1271,14 +1271,17 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 			return -ETIME;
 
 		timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+
+		/*
+		 * Record current time in case interrupted by signal, or wedged.
+		 */
+		before = ktime_get_raw_ns();
 	}
 
 	if (INTEL_INFO(dev_priv)->gen >= 6)
 		gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
 
-	/* Record current time in case interrupted by signal, or wedged */
 	trace_i915_gem_request_wait_begin(req);
-	before = ktime_get_raw_ns();
 
 	/* Optimistic spin for the next jiffie before touching IRQs */
 	ret = __i915_spin_request(req, state);
@@ -1343,11 +1346,10 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	finish_wait(&ring->irq_queue, &wait);
 
 out:
-	now = ktime_get_raw_ns();
 	trace_i915_gem_request_wait_end(req);
 
 	if (timeout) {
-		s64 tres = *timeout - (now - before);
+		s64 tres = *timeout - (ktime_get_raw_ns() - before);
 
 		*timeout = tres < 0 ? 0 : tres;
 
@@ -2204,7 +2206,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 		if (obj->madv == I915_MADV_WILLNEED)
 			mark_page_accessed(page);
 
-		page_cache_release(page);
+		put_page(page);
 	}
 	obj->dirty = 0;
 
@@ -2344,7 +2346,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 err_pages:
 	sg_mark_end(sg);
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0)
-		page_cache_release(sg_page_iter_page(&sg_iter));
+		put_page(sg_page_iter_page(&sg_iter));
 	sg_free_table(st);
 	kfree(st);
 
@@ -2414,7 +2416,7 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 	list_move_tail(&obj->ring_list[ring->id], &ring->active_list);
 	i915_gem_request_assign(&obj->last_read_req[ring->id], req);
 
-	list_move_tail(&vma->mm_list, &vma->vm->active_list);
+	list_move_tail(&vma->vm_link, &vma->vm->active_list);
 }
 
 static void
@@ -2452,9 +2454,9 @@ i915_gem_object_retire__read(struct drm_i915_gem_object *obj, int ring)
 	list_move_tail(&obj->global_list,
 		       &to_i915(obj->base.dev)->mm.bound_list);
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
-		if (!list_empty(&vma->mm_list))
-			list_move_tail(&vma->mm_list, &vma->vm->inactive_list);
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
+		if (!list_empty(&vma->vm_link))
+			list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
 	}
 
 	i915_gem_request_assign(&obj->last_fenced_req, NULL);
@@ -2677,10 +2679,8 @@ void i915_gem_request_free(struct kref *req_ref)
 		i915_gem_request_remove_from_client(req);
 
 	if (ctx) {
-		if (i915.enable_execlists) {
-			if (ctx != req->ring->default_context)
-				intel_lr_context_unpin(req);
-		}
+		if (i915.enable_execlists && ctx != req->i915->kernel_context)
+			intel_lr_context_unpin(ctx, req->ring);
 
 		i915_gem_context_unreference(ctx);
 	}
@@ -2688,9 +2688,10 @@ void i915_gem_request_free(struct kref *req_ref)
 	kmem_cache_free(req->i915->requests, req);
 }
 
-int i915_gem_request_alloc(struct intel_engine_cs *ring,
-			   struct intel_context *ctx,
-			   struct drm_i915_gem_request **req_out)
+static inline int
+__i915_gem_request_alloc(struct intel_engine_cs *ring,
+			 struct intel_context *ctx,
+			 struct drm_i915_gem_request **req_out)
 {
 	struct drm_i915_private *dev_priv = to_i915(ring->dev);
 	struct drm_i915_gem_request *req;
@@ -2753,6 +2754,31 @@ err:
 	return ret;
 }
 
+/**
+ * i915_gem_request_alloc - allocate a request structure
+ *
+ * @engine: engine that we wish to issue the request on.
+ * @ctx: context that the request will be associated with.
+ *       This can be NULL if the request is not directly related to
+ *       any specific user context, in which case this function will
+ *       choose an appropriate context to use.
+ *
+ * Returns a pointer to the allocated request if successful,
+ * or an error code if not.
+ */
+struct drm_i915_gem_request *
+i915_gem_request_alloc(struct intel_engine_cs *engine,
+		       struct intel_context *ctx)
+{
+	struct drm_i915_gem_request *req;
+	int err;
+
+	if (ctx == NULL)
+		ctx = to_i915(engine->dev)->kernel_context;
+	err = __i915_gem_request_alloc(engine, ctx, &req);
+	return err ? ERR_PTR(err) : req;
+}
+
 void i915_gem_request_cancel(struct drm_i915_gem_request *req)
 {
 	intel_ring_reserved_space_cancel(req->ringbuf);
@@ -2944,11 +2970,9 @@ i915_gem_retire_requests(struct drm_device *dev)
 		i915_gem_retire_requests_ring(ring);
 		idle &= list_empty(&ring->request_list);
 		if (i915.enable_execlists) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&ring->execlist_lock, flags);
+			spin_lock_irq(&ring->execlist_lock);
 			idle &= list_empty(&ring->execlist_queue);
-			spin_unlock_irqrestore(&ring->execlist_lock, flags);
+			spin_unlock_irq(&ring->execlist_lock);
 
 			intel_execlists_retire_requests(ring);
 		}
@@ -3170,9 +3194,13 @@ __i915_gem_object_sync(struct drm_i915_gem_object *obj,
 			return 0;
 
 		if (*to_req == NULL) {
-			ret = i915_gem_request_alloc(to, to->default_context, to_req);
-			if (ret)
-				return ret;
+			struct drm_i915_gem_request *req;
+
+			req = i915_gem_request_alloc(to, NULL);
+			if (IS_ERR(req))
+				return PTR_ERR(req);
+
+			*to_req = req;
 		}
 
 		trace_i915_gem_ring_sync_to(*to_req, from, from_req);
@@ -3289,7 +3317,7 @@ static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 	int ret;
 
-	if (list_empty(&vma->vma_link))
+	if (list_empty(&vma->obj_link))
 		return 0;
 
 	if (!drm_mm_node_allocated(&vma->node)) {
@@ -3308,8 +3336,7 @@ static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 			return ret;
 	}
 
-	if (i915_is_ggtt(vma->vm) &&
-	    vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
+	if (vma->is_ggtt && vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
 		i915_gem_object_finish_gtt(obj);
 
 		/* release the fence reg _after_ flushing */
@@ -3323,8 +3350,8 @@ static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 	vma->vm->unbind_vma(vma);
 	vma->bound = 0;
 
-	list_del_init(&vma->mm_list);
-	if (i915_is_ggtt(vma->vm)) {
+	list_del_init(&vma->vm_link);
+	if (vma->is_ggtt) {
 		if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
 			obj->map_and_fenceable = false;
 		} else if (vma->ggtt_view.pages) {
@@ -3372,9 +3399,9 @@ int i915_gpu_idle(struct drm_device *dev)
 		if (!i915.enable_execlists) {
 			struct drm_i915_gem_request *req;
 
-			ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-			if (ret)
-				return ret;
+			req = i915_gem_request_alloc(ring, NULL);
+			if (IS_ERR(req))
+				return PTR_ERR(req);
 
 			ret = i915_switch_context(req);
 			if (ret) {
@@ -3581,7 +3608,7 @@ search_free:
 		goto err_remove_node;
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
-	list_add_tail(&vma->mm_list, &vm->inactive_list);
+	list_add_tail(&vma->vm_link, &vm->inactive_list);
 
 	return vma;
 
@@ -3746,7 +3773,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	/* And bump the LRU for this access */
 	vma = i915_gem_obj_to_ggtt(obj);
 	if (vma && drm_mm_node_allocated(&vma->node) && !obj->active)
-		list_move_tail(&vma->mm_list,
+		list_move_tail(&vma->vm_link,
 			       &to_i915(obj->base.dev)->gtt.base.inactive_list);
 
 	return 0;
@@ -3781,7 +3808,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 	 * catch the issue of the CS prefetch crossing page boundaries and
 	 * reading an invalid PTE on older architectures.
 	 */
-	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
+	list_for_each_entry_safe(vma, next, &obj->vma_list, obj_link) {
 		if (!drm_mm_node_allocated(&vma->node))
 			continue;
 
@@ -3844,7 +3871,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 			 */
 		}
 
-		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		list_for_each_entry(vma, &obj->vma_list, obj_link) {
 			if (!drm_mm_node_allocated(&vma->node))
 				continue;
 
@@ -3854,7 +3881,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		}
 	}
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
+	list_for_each_entry(vma, &obj->vma_list, obj_link)
 		vma->node.color = cache_level;
 	obj->cache_level = cache_level;
 
@@ -4328,10 +4355,20 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto unref;
 
-	BUILD_BUG_ON(I915_NUM_RINGS > 16);
-	args->busy = obj->active << 16;
-	if (obj->last_write_req)
-		args->busy |= obj->last_write_req->ring->id;
+	args->busy = 0;
+	if (obj->active) {
+		int i;
+
+		for (i = 0; i < I915_NUM_RINGS; i++) {
+			struct drm_i915_gem_request *req;
+
+			req = obj->last_read_req[i];
+			if (req)
+				args->busy |= 1 << (16 + req->ring->exec_id);
+		}
+		if (obj->last_write_req)
+			args->busy |= obj->last_write_req->ring->exec_id;
+	}
 
 unref:
 	drm_gem_object_unreference(&obj->base);
@@ -4518,7 +4555,7 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 
 	trace_i915_gem_object_destroy(obj);
 
-	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
+	list_for_each_entry_safe(vma, next, &obj->vma_list, obj_link) {
 		int ret;
 
 		vma->pin_count = 0;
@@ -4575,7 +4612,7 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 				     struct i915_address_space *vm)
 {
 	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
 		if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL &&
 		    vma->vm == vm)
 			return vma;
@@ -4592,7 +4629,7 @@ struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
 	if (WARN_ONCE(!view, "no view specified"))
 		return ERR_PTR(-EINVAL);
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
+	list_for_each_entry(vma, &obj->vma_list, obj_link)
 		if (vma->vm == ggtt &&
 		    i915_ggtt_view_equal(&vma->ggtt_view, view))
 			return vma;
@@ -4601,19 +4638,16 @@ struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
 
 void i915_gem_vma_destroy(struct i915_vma *vma)
 {
-	struct i915_address_space *vm = NULL;
 	WARN_ON(vma->node.allocated);
 
 	/* Keep the vma as a placeholder in the execbuffer reservation lists */
 	if (!list_empty(&vma->exec_list))
 		return;
 
-	vm = vma->vm;
-
-	if (!i915_is_ggtt(vm))
-		i915_ppgtt_put(i915_vm_to_ppgtt(vm));
+	if (!vma->is_ggtt)
+		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
 
-	list_del(&vma->vma_link);
+	list_del(&vma->obj_link);
 
 	kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
 }
@@ -4833,7 +4867,7 @@ i915_gem_init_hw(struct drm_device *dev)
 	 */
 	init_unused_rings(dev);
 
-	BUG_ON(!dev_priv->ring[RCS].default_context);
+	BUG_ON(!dev_priv->kernel_context);
 
 	ret = i915_ppgtt_init_hw(dev);
 	if (ret) {
@@ -4870,10 +4904,9 @@ i915_gem_init_hw(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i) {
 		struct drm_i915_gem_request *req;
 
-		WARN_ON(!ring->default_context);
-
-		ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-		if (ret) {
+		req = i915_gem_request_alloc(ring, NULL);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
 			i915_gem_cleanup_ringbuffer(dev);
 			goto out;
 		}
@@ -4996,7 +5029,7 @@ init_ring_lists(struct intel_engine_cs *ring)
 }
 
 void
-i915_gem_load(struct drm_device *dev)
+i915_gem_load_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
@@ -5062,11 +5095,18 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.interruptible = true;
 
-	i915_gem_shrinker_init(dev_priv);
-
 	mutex_init(&dev_priv->fb_tracking.lock);
 }
 
+void i915_gem_load_cleanup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	kmem_cache_destroy(dev_priv->requests);
+	kmem_cache_destroy(dev_priv->vmas);
+	kmem_cache_destroy(dev_priv->objects);
+}
+
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -5113,6 +5153,8 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file)
 	spin_lock_init(&file_priv->mm.lock);
 	INIT_LIST_HEAD(&file_priv->mm.request_list);
 
+	file_priv->bsd_ring = -1;
+
 	ret = i915_gem_context_open(dev, file);
 	if (ret)
 		kfree(file_priv);
@@ -5155,8 +5197,8 @@ u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
 
 	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
 
-	list_for_each_entry(vma, &o->vma_list, vma_link) {
-		if (i915_is_ggtt(vma->vm) &&
+	list_for_each_entry(vma, &o->vma_list, obj_link) {
+		if (vma->is_ggtt &&
 		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
 			continue;
 		if (vma->vm == vm)
@@ -5174,7 +5216,7 @@ u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
 	struct i915_address_space *ggtt = i915_obj_to_ggtt(o);
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &o->vma_list, vma_link)
+	list_for_each_entry(vma, &o->vma_list, obj_link)
 		if (vma->vm == ggtt &&
 		    i915_ggtt_view_equal(&vma->ggtt_view, view))
 			return vma->node.start;
@@ -5188,8 +5230,8 @@ bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
 {
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &o->vma_list, vma_link) {
-		if (i915_is_ggtt(vma->vm) &&
+	list_for_each_entry(vma, &o->vma_list, obj_link) {
+		if (vma->is_ggtt &&
 		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
 			continue;
 		if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
@@ -5205,7 +5247,7 @@ bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
 	struct i915_address_space *ggtt = i915_obj_to_ggtt(o);
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &o->vma_list, vma_link)
+	list_for_each_entry(vma, &o->vma_list, obj_link)
 		if (vma->vm == ggtt &&
 		    i915_ggtt_view_equal(&vma->ggtt_view, view) &&
 		    drm_mm_node_allocated(&vma->node))
@@ -5218,7 +5260,7 @@ bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o)
 {
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &o->vma_list, vma_link)
+	list_for_each_entry(vma, &o->vma_list, obj_link)
 		if (drm_mm_node_allocated(&vma->node))
 			return true;
 
@@ -5235,8 +5277,8 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 
 	BUG_ON(list_empty(&o->vma_list));
 
-	list_for_each_entry(vma, &o->vma_list, vma_link) {
-		if (i915_is_ggtt(vma->vm) &&
+	list_for_each_entry(vma, &o->vma_list, obj_link) {
+		if (vma->is_ggtt &&
 		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
 			continue;
 		if (vma->vm == vm)
@@ -5248,7 +5290,7 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
+	list_for_each_entry(vma, &obj->vma_list, obj_link)
 		if (vma->pin_count > 0)
 			return true;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index c25083c78..5dd84e148 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -142,7 +142,7 @@ static void i915_gem_context_clean(struct intel_context *ctx)
 		return;
 
 	list_for_each_entry_safe(vma, next, &ppgtt->base.inactive_list,
-				 mm_list) {
+				 vm_link) {
 		if (WARN_ON(__i915_vma_unbind_no_wait(vma)))
 			break;
 	}
@@ -321,6 +321,18 @@ err_destroy:
 	return ERR_PTR(ret);
 }
 
+static void i915_gem_context_unpin(struct intel_context *ctx,
+				   struct intel_engine_cs *engine)
+{
+	if (i915.enable_execlists) {
+		intel_lr_context_unpin(ctx, engine);
+	} else {
+		if (engine->id == RCS && ctx->legacy_hw_ctx.rcs_state)
+			i915_gem_object_ggtt_unpin(ctx->legacy_hw_ctx.rcs_state);
+		i915_gem_context_unreference(ctx);
+	}
+}
+
 void i915_gem_context_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -329,40 +341,31 @@ void i915_gem_context_reset(struct drm_device *dev)
 	if (i915.enable_execlists) {
 		struct intel_context *ctx;
 
-		list_for_each_entry(ctx, &dev_priv->context_list, link) {
+		list_for_each_entry(ctx, &dev_priv->context_list, link)
 			intel_lr_context_reset(dev, ctx);
-		}
-
-		return;
 	}
 
 	for (i = 0; i < I915_NUM_RINGS; i++) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
-		struct intel_context *lctx = ring->last_context;
-
-		if (lctx) {
-			if (lctx->legacy_hw_ctx.rcs_state && i == RCS)
-				i915_gem_object_ggtt_unpin(lctx->legacy_hw_ctx.rcs_state);
 
-			i915_gem_context_unreference(lctx);
+		if (ring->last_context) {
+			i915_gem_context_unpin(ring->last_context, ring);
 			ring->last_context = NULL;
 		}
-
-		/* Force the GPU state to be reinitialised on enabling */
-		if (ring->default_context)
-			ring->default_context->legacy_hw_ctx.initialized = false;
 	}
+
+	/* Force the GPU state to be reinitialised on enabling */
+	dev_priv->kernel_context->legacy_hw_ctx.initialized = false;
 }
 
 int i915_gem_context_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_context *ctx;
-	int i;
 
 	/* Init should only be called once per module load. Eventually the
 	 * restriction on the context_disabled check can be loosened. */
-	if (WARN_ON(dev_priv->ring[RCS].default_context))
+	if (WARN_ON(dev_priv->kernel_context))
 		return 0;
 
 	if (intel_vgpu_active(dev) && HAS_LOGICAL_RING_CONTEXTS(dev)) {
@@ -392,12 +395,7 @@ int i915_gem_context_init(struct drm_device *dev)
 		return PTR_ERR(ctx);
 	}
 
-	for (i = 0; i < I915_NUM_RINGS; i++) {
-		struct intel_engine_cs *ring = &dev_priv->ring[i];
-
-		/* NB: RCS will hold a ref for all rings */
-		ring->default_context = ctx;
-	}
+	dev_priv->kernel_context = ctx;
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
 			i915.enable_execlists ? "LR" :
@@ -408,7 +406,7 @@ int i915_gem_context_init(struct drm_device *dev)
 void i915_gem_context_fini(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_context *dctx = dev_priv->ring[RCS].default_context;
+	struct intel_context *dctx = dev_priv->kernel_context;
 	int i;
 
 	if (dctx->legacy_hw_ctx.rcs_state) {
@@ -424,28 +422,21 @@ void i915_gem_context_fini(struct drm_device *dev)
 		 * to offset the do_switch part, so that i915_gem_context_unreference()
 		 * can then free the base object correctly. */
 		WARN_ON(!dev_priv->ring[RCS].last_context);
-		if (dev_priv->ring[RCS].last_context == dctx) {
-			/* Fake switch to NULL context */
-			WARN_ON(dctx->legacy_hw_ctx.rcs_state->active);
-			i915_gem_object_ggtt_unpin(dctx->legacy_hw_ctx.rcs_state);
-			i915_gem_context_unreference(dctx);
-			dev_priv->ring[RCS].last_context = NULL;
-		}
 
 		i915_gem_object_ggtt_unpin(dctx->legacy_hw_ctx.rcs_state);
 	}
 
-	for (i = 0; i < I915_NUM_RINGS; i++) {
+	for (i = I915_NUM_RINGS; --i >= 0;) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
 
-		if (ring->last_context)
-			i915_gem_context_unreference(ring->last_context);
-
-		ring->default_context = NULL;
-		ring->last_context = NULL;
+		if (ring->last_context) {
+			i915_gem_context_unpin(ring->last_context, ring);
+			ring->last_context = NULL;
+		}
 	}
 
 	i915_gem_context_unreference(dctx);
+	dev_priv->kernel_context = NULL;
 }
 
 int i915_gem_context_enable(struct drm_i915_gem_request *req)
@@ -864,6 +855,9 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	if (!contexts_enabled(dev))
 		return -ENODEV;
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
@@ -887,6 +881,9 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	struct intel_context *ctx;
 	int ret;
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	if (args->ctx_id == DEFAULT_CONTEXT_HANDLE)
 		return -ENOENT;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index e9c2bfd85..0506016e1 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -193,10 +193,26 @@ static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_n
 
 static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
-	return -EINVAL;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
+	int ret;
+
+	if (obj->base.size < vma->vm_end - vma->vm_start)
+		return -EINVAL;
+
+	if (!obj->base.filp)
+		return -ENODEV;
+
+	ret = obj->base.filp->f_op->mmap(obj->base.filp, vma);
+	if (ret)
+		return ret;
+
+	fput(vma->vm_file);
+	vma->vm_file = get_file(obj->base.filp);
+
+	return 0;
 }
 
-static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t length, enum dma_data_direction direction)
+static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction direction)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
@@ -212,6 +228,22 @@ static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size
 	return ret;
 }
 
+static int i915_gem_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction direction)
+{
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
+	struct drm_device *dev = obj->base.dev;
+	int ret;
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, false);
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
 static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.map_dma_buf = i915_gem_map_dma_buf,
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
@@ -224,6 +256,7 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.vmap = i915_gem_dmabuf_vmap,
 	.vunmap = i915_gem_dmabuf_vunmap,
 	.begin_cpu_access = i915_gem_begin_cpu_access,
+	.end_cpu_access = i915_gem_end_cpu_access,
 };
 
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 07c6e4d32..ea1f8d1bd 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -116,7 +116,7 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 
 search_again:
 	/* First see if there is a large enough contiguous idle region... */
-	list_for_each_entry(vma, &vm->inactive_list, mm_list) {
+	list_for_each_entry(vma, &vm->inactive_list, vm_link) {
 		if (mark_free(vma, &unwind_list))
 			goto found;
 	}
@@ -125,7 +125,7 @@ search_again:
 		goto none;
 
 	/* Now merge in the soon-to-be-expired objects... */
-	list_for_each_entry(vma, &vm->active_list, mm_list) {
+	list_for_each_entry(vma, &vm->active_list, vm_link) {
 		if (mark_free(vma, &unwind_list))
 			goto found;
 	}
@@ -270,7 +270,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle)
 		WARN_ON(!list_empty(&vm->active_list));
 	}
 
-	list_for_each_entry_safe(vma, next, &vm->inactive_list, mm_list)
+	list_for_each_entry_safe(vma, next, &vm->inactive_list, vm_link)
 		if (vma->pin_count == 0)
 			WARN_ON(i915_vma_unbind(vma));
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index dccb51736..1328bc502 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -193,13 +193,10 @@ static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle)
 		return eb->lut[handle];
 	} else {
 		struct hlist_head *head;
-		struct hlist_node *node;
+		struct i915_vma *vma;
 
 		head = &eb->buckets[handle & eb->and];
-		hlist_for_each(node, head) {
-			struct i915_vma *vma;
-
-			vma = hlist_entry(node, struct i915_vma, exec_node);
+		hlist_for_each_entry(vma, head, exec_node) {
 			if (vma->exec_handle == handle)
 				return vma;
 		}
@@ -671,7 +668,7 @@ need_reloc_mappable(struct i915_vma *vma)
 	if (entry->relocation_count == 0)
 		return false;
 
-	if (!i915_is_ggtt(vma->vm))
+	if (!vma->is_ggtt)
 		return false;
 
 	/* See also use_cpu_reloc() */
@@ -690,8 +687,7 @@ eb_vma_misplaced(struct i915_vma *vma)
 	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	WARN_ON(entry->flags & __EXEC_OBJECT_NEEDS_MAP &&
-	       !i915_is_ggtt(vma->vm));
+	WARN_ON(entry->flags & __EXEC_OBJECT_NEEDS_MAP && !vma->is_ggtt);
 
 	if (entry->alignment &&
 	    vma->node.start & (entry->alignment - 1))
@@ -1309,6 +1305,9 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 	exec_start = params->batch_obj_vm_offset +
 		     params->args_batch_start_offset;
 
+	if (exec_len == 0)
+		exec_len = params->batch_obj->base.size;
+
 	ret = ring->dispatch_execbuffer(params->request,
 					exec_start, exec_len,
 					params->dispatch_flags);
@@ -1325,33 +1324,23 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 
 /**
  * Find one BSD ring to dispatch the corresponding BSD command.
- * The Ring ID is returned.
+ * The ring index is returned.
  */
-static int gen8_dispatch_bsd_ring(struct drm_device *dev,
-				  struct drm_file *file)
+static unsigned int
+gen8_dispatch_bsd_ring(struct drm_i915_private *dev_priv, struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
-	/* Check whether the file_priv is using one ring */
-	if (file_priv->bsd_ring)
-		return file_priv->bsd_ring->id;
-	else {
-		/* If no, use the ping-pong mechanism to select one ring */
-		int ring_id;
-
-		mutex_lock(&dev->struct_mutex);
-		if (dev_priv->mm.bsd_ring_dispatch_index == 0) {
-			ring_id = VCS;
-			dev_priv->mm.bsd_ring_dispatch_index = 1;
-		} else {
-			ring_id = VCS2;
-			dev_priv->mm.bsd_ring_dispatch_index = 0;
-		}
-		file_priv->bsd_ring = &dev_priv->ring[ring_id];
-		mutex_unlock(&dev->struct_mutex);
-		return ring_id;
+	/* Check whether the file_priv has already selected one ring. */
+	if ((int)file_priv->bsd_ring < 0) {
+		/* If not, use the ping-pong mechanism to select one. */
+		mutex_lock(&dev_priv->dev->struct_mutex);
+		file_priv->bsd_ring = dev_priv->mm.bsd_ring_dispatch_index;
+		dev_priv->mm.bsd_ring_dispatch_index ^= 1;
+		mutex_unlock(&dev_priv->dev->struct_mutex);
 	}
+
+	return file_priv->bsd_ring;
 }
 
 static struct drm_i915_gem_object *
@@ -1374,6 +1363,64 @@ eb_get_batch(struct eb_vmas *eb)
 	return vma->obj;
 }
 
+#define I915_USER_RINGS (4)
+
+static const enum intel_ring_id user_ring_map[I915_USER_RINGS + 1] = {
+	[I915_EXEC_DEFAULT]	= RCS,
+	[I915_EXEC_RENDER]	= RCS,
+	[I915_EXEC_BLT]		= BCS,
+	[I915_EXEC_BSD]		= VCS,
+	[I915_EXEC_VEBOX]	= VECS
+};
+
+static int
+eb_select_ring(struct drm_i915_private *dev_priv,
+	       struct drm_file *file,
+	       struct drm_i915_gem_execbuffer2 *args,
+	       struct intel_engine_cs **ring)
+{
+	unsigned int user_ring_id = args->flags & I915_EXEC_RING_MASK;
+
+	if (user_ring_id > I915_USER_RINGS) {
+		DRM_DEBUG("execbuf with unknown ring: %u\n", user_ring_id);
+		return -EINVAL;
+	}
+
+	if ((user_ring_id != I915_EXEC_BSD) &&
+	    ((args->flags & I915_EXEC_BSD_MASK) != 0)) {
+		DRM_DEBUG("execbuf with non bsd ring but with invalid "
+			  "bsd dispatch flags: %d\n", (int)(args->flags));
+		return -EINVAL;
+	}
+
+	if (user_ring_id == I915_EXEC_BSD && HAS_BSD2(dev_priv)) {
+		unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK;
+
+		if (bsd_idx == I915_EXEC_BSD_DEFAULT) {
+			bsd_idx = gen8_dispatch_bsd_ring(dev_priv, file);
+		} else if (bsd_idx >= I915_EXEC_BSD_RING1 &&
+			   bsd_idx <= I915_EXEC_BSD_RING2) {
+			bsd_idx >>= I915_EXEC_BSD_SHIFT;
+			bsd_idx--;
+		} else {
+			DRM_DEBUG("execbuf with unknown bsd ring: %u\n",
+				  bsd_idx);
+			return -EINVAL;
+		}
+
+		*ring = &dev_priv->ring[_VCS(bsd_idx)];
+	} else {
+		*ring = &dev_priv->ring[user_ring_map[user_ring_id]];
+	}
+
+	if (!intel_ring_initialized(*ring)) {
+		DRM_DEBUG("execbuf with invalid ring: %u\n", user_ring_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
@@ -1381,6 +1428,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_request *req = NULL;
 	struct eb_vmas *eb;
 	struct drm_i915_gem_object *batch_obj;
 	struct drm_i915_gem_exec_object2 shadow_exec_entry;
@@ -1411,51 +1459,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		dispatch_flags |= I915_DISPATCH_PINNED;
 
-	if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
-		DRM_DEBUG("execbuf with unknown ring: %d\n",
-			  (int)(args->flags & I915_EXEC_RING_MASK));
-		return -EINVAL;
-	}
-
-	if (((args->flags & I915_EXEC_RING_MASK) != I915_EXEC_BSD) &&
-	    ((args->flags & I915_EXEC_BSD_MASK) != 0)) {
-		DRM_DEBUG("execbuf with non bsd ring but with invalid "
-			"bsd dispatch flags: %d\n", (int)(args->flags));
-		return -EINVAL;
-	} 
-
-	if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT)
-		ring = &dev_priv->ring[RCS];
-	else if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_BSD) {
-		if (HAS_BSD2(dev)) {
-			int ring_id;
-
-			switch (args->flags & I915_EXEC_BSD_MASK) {
-			case I915_EXEC_BSD_DEFAULT:
-				ring_id = gen8_dispatch_bsd_ring(dev, file);
-				ring = &dev_priv->ring[ring_id];
-				break;
-			case I915_EXEC_BSD_RING1:
-				ring = &dev_priv->ring[VCS];
-				break;
-			case I915_EXEC_BSD_RING2:
-				ring = &dev_priv->ring[VCS2];
-				break;
-			default:
-				DRM_DEBUG("execbuf with unknown bsd ring: %d\n",
-					  (int)(args->flags & I915_EXEC_BSD_MASK));
-				return -EINVAL;
-			}
-		} else
-			ring = &dev_priv->ring[VCS];
-	} else
-		ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1];
-
-	if (!intel_ring_initialized(ring)) {
-		DRM_DEBUG("execbuf with invalid ring: %d\n",
-			  (int)(args->flags & I915_EXEC_RING_MASK));
-		return -EINVAL;
-	}
+	ret = eb_select_ring(dev_priv, file, args, &ring);
+	if (ret)
+		return ret;
 
 	if (args->buffer_count < 1) {
 		DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count);
@@ -1602,11 +1608,13 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
 
 	/* Allocate a request for this batch buffer nice and early. */
-	ret = i915_gem_request_alloc(ring, ctx, &params->request);
-	if (ret)
+	req = i915_gem_request_alloc(ring, ctx);
+	if (IS_ERR(req)) {
+		ret = PTR_ERR(req);
 		goto err_batch_unpin;
+	}
 
-	ret = i915_gem_request_add_to_client(params->request, file);
+	ret = i915_gem_request_add_to_client(req, file);
 	if (ret)
 		goto err_batch_unpin;
 
@@ -1622,6 +1630,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	params->dispatch_flags          = dispatch_flags;
 	params->batch_obj               = batch_obj;
 	params->ctx                     = ctx;
+	params->request                 = req;
 
 	ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
 
@@ -1645,8 +1654,8 @@ err:
 	 * must be freed again. If it was submitted then it is being tracked
 	 * on the active request list and no clean up is required here.
 	 */
-	if (ret && params->request)
-		i915_gem_request_cancel(params->request);
+	if (ret && !IS_ERR_OR_NULL(req))
+		i915_gem_request_cancel(req);
 
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 598198543..a2b938ec0 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -34,8 +34,8 @@
  * set of these objects.
  *
  * Fences are used to detile GTT memory mappings. They're also connected to the
- * hardware frontbuffer render tracking and hence interract with frontbuffer
- * conmpression. Furthermore on older platforms fences are required for tiled
+ * hardware frontbuffer render tracking and hence interact with frontbuffer
+ * compression. Furthermore on older platforms fences are required for tiled
  * objects used by the display engine. They can also be used by the render
  * engine - they're required for blitter commands and are optional for render
  * commands. But on gen4+ both display (with the exception of fbc) and rendering
@@ -46,8 +46,8 @@
  *
  * Finally note that because fences are such a restricted resource they're
  * dynamically associated with objects. Furthermore fence state is committed to
- * the hardware lazily to avoid unecessary stalls on gen2/3. Therefore code must
- * explictly call i915_gem_object_get_fence() to synchronize fencing status
+ * the hardware lazily to avoid unnecessary stalls on gen2/3. Therefore code must
+ * explicitly call i915_gem_object_get_fence() to synchronize fencing status
  * for cpu access. Also note that some code wants an unfenced view, for those
  * cases the fence can be removed forcefully with i915_gem_object_put_fence().
  *
@@ -527,7 +527,7 @@ void i915_gem_restore_fences(struct drm_device *dev)
  * required.
  *
  * When bit 17 is XORed in, we simply refuse to tile at all.  Bit
- * 17 is not just a page offset, so as we page an objet out and back in,
+ * 17 is not just a page offset, so as we page an object out and back in,
  * individual pages in it will have different bit 17 addresses, resulting in
  * each 64 bytes being swapped with its neighbor!
  *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 56f4f2e58..49e4f26b7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -96,9 +96,11 @@
 static int
 i915_get_ggtt_vma_pages(struct i915_vma *vma);
 
-const struct i915_ggtt_view i915_ggtt_view_normal;
+const struct i915_ggtt_view i915_ggtt_view_normal = {
+	.type = I915_GGTT_VIEW_NORMAL,
+};
 const struct i915_ggtt_view i915_ggtt_view_rotated = {
-        .type = I915_GGTT_VIEW_ROTATED
+	.type = I915_GGTT_VIEW_ROTATED,
 };
 
 static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
@@ -2130,6 +2132,25 @@ static void i915_address_space_init(struct i915_address_space *vm,
 	list_add_tail(&vm->global_link, &dev_priv->vm_list);
 }
 
+static void gtt_write_workarounds(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* This function is for gtt related workarounds. This function is
+	 * called on driver load and after a GPU reset, so you can place
+	 * workarounds here even if they get overwritten by GPU reset.
+	 */
+	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt */
+	if (IS_BROADWELL(dev))
+		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
+	else if (IS_CHERRYVIEW(dev))
+		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
+	else if (IS_SKYLAKE(dev))
+		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
+	else if (IS_BROXTON(dev))
+		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
+}
+
 int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2146,6 +2167,8 @@ int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 
 int i915_ppgtt_init_hw(struct drm_device *dev)
 {
+	gtt_write_workarounds(dev);
+
 	/* In the case of execlists, PPGTT is enabled by the context descriptor
 	 * and the PDPs are contained within the context itself.  We don't
 	 * need to do anything here. */
@@ -2735,7 +2758,7 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev,
 		}
 		vma->bound |= GLOBAL_BIND;
 		__i915_vma_set_map_and_fenceable(vma);
-		list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list);
+		list_add_tail(&vma->vm_link, &ggtt_vm->inactive_list);
 	}
 
 	/* Clear any non-preallocated blocks */
@@ -2807,6 +2830,8 @@ void i915_global_gtt_cleanup(struct drm_device *dev)
 		ppgtt->base.cleanup(&ppgtt->base);
 	}
 
+	i915_gem_cleanup_stolen(dev);
+
 	if (drm_mm_initialized(&vm->mm)) {
 		if (intel_vgpu_active(dev))
 			intel_vgt_deballoon();
@@ -3173,12 +3198,21 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	}
 
 	gtt->base.dev = dev;
+	gtt->base.is_ggtt = true;
 
 	ret = gtt->gtt_probe(dev, &gtt->base.total, &gtt->stolen_size,
 			     &gtt->mappable_base, &gtt->mappable_end);
 	if (ret)
 		return ret;
 
+	/*
+	 * Initialise stolen early so that we may reserve preallocated
+	 * objects for the BIOS to KMS transition.
+	 */
+	ret = i915_gem_init_stolen(dev);
+	if (ret)
+		goto out_gtt_cleanup;
+
 	/* GMADR is the PCI mmio aperture into the global GTT. */
 	DRM_INFO("Memory usable by graphics device = %lluM\n",
 		 gtt->base.total >> 20);
@@ -3198,6 +3232,11 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt);
 
 	return 0;
+
+out_gtt_cleanup:
+	gtt->base.cleanup(&dev_priv->gtt.base);
+
+	return ret;
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
@@ -3220,7 +3259,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	vm = &dev_priv->gtt.base;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		flush = false;
-		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		list_for_each_entry(vma, &obj->vma_list, obj_link) {
 			if (vma->vm != vm)
 				continue;
 
@@ -3276,19 +3315,20 @@ __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->vma_link);
-	INIT_LIST_HEAD(&vma->mm_list);
+	INIT_LIST_HEAD(&vma->vm_link);
+	INIT_LIST_HEAD(&vma->obj_link);
 	INIT_LIST_HEAD(&vma->exec_list);
 	vma->vm = vm;
 	vma->obj = obj;
+	vma->is_ggtt = i915_is_ggtt(vm);
 
 	if (i915_is_ggtt(vm))
 		vma->ggtt_view = *ggtt_view;
-
-	list_add_tail(&vma->vma_link, &obj->vma_list);
-	if (!i915_is_ggtt(vm))
+	else
 		i915_ppgtt_get(i915_vm_to_ppgtt(vm));
 
+	list_add_tail(&vma->obj_link, &obj->vma_list);
+
 	return vma;
 }
 
@@ -3329,8 +3369,9 @@ i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
 }
 
 static struct scatterlist *
-rotate_pages(dma_addr_t *in, unsigned int offset,
+rotate_pages(const dma_addr_t *in, unsigned int offset,
 	     unsigned int width, unsigned int height,
+	     unsigned int stride,
 	     struct sg_table *st, struct scatterlist *sg)
 {
 	unsigned int column, row;
@@ -3342,7 +3383,7 @@ rotate_pages(dma_addr_t *in, unsigned int offset,
 	}
 
 	for (column = 0; column < width; column++) {
-		src_idx = width * (height - 1) + column;
+		src_idx = stride * (height - 1) + column;
 		for (row = 0; row < height; row++) {
 			st->nents++;
 			/* We don't need the pages, but need to initialize
@@ -3353,7 +3394,7 @@ rotate_pages(dma_addr_t *in, unsigned int offset,
 			sg_dma_address(sg) = in[offset + src_idx];
 			sg_dma_len(sg) = PAGE_SIZE;
 			sg = sg_next(sg);
-			src_idx -= width;
+			src_idx -= stride;
 		}
 	}
 
@@ -3361,10 +3402,9 @@ rotate_pages(dma_addr_t *in, unsigned int offset,
 }
 
 static struct sg_table *
-intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
+intel_rotate_fb_obj_pages(struct intel_rotation_info *rot_info,
 			  struct drm_i915_gem_object *obj)
 {
-	struct intel_rotation_info *rot_info = &ggtt_view->params.rotation_info;
 	unsigned int size_pages = rot_info->size >> PAGE_SHIFT;
 	unsigned int size_pages_uv;
 	struct sg_page_iter sg_iter;
@@ -3406,6 +3446,7 @@ intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
 	/* Rotate the pages. */
 	sg = rotate_pages(page_addr_list, 0,
 		     rot_info->width_pages, rot_info->height_pages,
+		     rot_info->width_pages,
 		     st, NULL);
 
 	/* Append the UV plane if NV12. */
@@ -3421,6 +3462,7 @@ intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
 		rotate_pages(page_addr_list, uv_start_page,
 			     rot_info->width_pages_uv,
 			     rot_info->height_pages_uv,
+			     rot_info->width_pages_uv,
 			     st, sg);
 	}
 
@@ -3502,7 +3544,7 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma)
 		vma->ggtt_view.pages = vma->obj->pages;
 	else if (vma->ggtt_view.type == I915_GGTT_VIEW_ROTATED)
 		vma->ggtt_view.pages =
-			intel_rotate_fb_obj_pages(&vma->ggtt_view, vma->obj);
+			intel_rotate_fb_obj_pages(&vma->ggtt_view.params.rotated, vma->obj);
 	else if (vma->ggtt_view.type == I915_GGTT_VIEW_PARTIAL)
 		vma->ggtt_view.pages =
 			intel_partial_pages(&vma->ggtt_view, vma->obj);
@@ -3558,13 +3600,9 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		return 0;
 
 	if (vma->bound == 0 && vma->vm->allocate_va_range) {
-		trace_i915_va_alloc(vma->vm,
-				    vma->node.start,
-				    vma->node.size,
-				    VM_TO_TRACE_NAME(vma->vm));
-
 		/* XXX: i915_vma_pin() will fix this +- hack */
 		vma->pin_count++;
+		trace_i915_va_alloc(vma);
 		ret = vma->vm->allocate_va_range(vma->vm,
 						 vma->node.start,
 						 vma->node.size);
@@ -3596,7 +3634,7 @@ i915_ggtt_view_size(struct drm_i915_gem_object *obj,
 	if (view->type == I915_GGTT_VIEW_NORMAL) {
 		return obj->base.size;
 	} else if (view->type == I915_GGTT_VIEW_ROTATED) {
-		return view->params.rotation_info.size;
+		return view->params.rotated.size;
 	} else if (view->type == I915_GGTT_VIEW_PARTIAL) {
 		return view->params.partial.size << PAGE_SHIFT;
 	} else {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index b448ad832..8774f1ba4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -44,7 +44,6 @@ typedef uint64_t gen8_ppgtt_pml4e_t;
 
 #define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
 
-
 /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
 #define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
@@ -156,7 +155,7 @@ struct i915_ggtt_view {
 			u64 offset;
 			unsigned int size;
 		} partial;
-		struct intel_rotation_info rotation_info;
+		struct intel_rotation_info rotated;
 	} params;
 
 	struct sg_table *pages;
@@ -184,6 +183,7 @@ struct i915_vma {
 #define GLOBAL_BIND	(1<<0)
 #define LOCAL_BIND	(1<<1)
 	unsigned int bound : 4;
+	bool is_ggtt : 1;
 
 	/**
 	 * Support different GGTT views into the same object.
@@ -195,9 +195,9 @@ struct i915_vma {
 	struct i915_ggtt_view ggtt_view;
 
 	/** This object's place on the active/inactive lists */
-	struct list_head mm_list;
+	struct list_head vm_link;
 
-	struct list_head vma_link; /* Link in the object's VMA list */
+	struct list_head obj_link; /* Link in the object's VMA list */
 
 	/** This vma's place in the batchbuffer or on the eviction list */
 	struct list_head exec_list;
@@ -276,6 +276,8 @@ struct i915_address_space {
 	u64 start;		/* Start offset always 0 for dri2 */
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 
+	bool is_ggtt;
+
 	struct i915_page_scratch *scratch_page;
 	struct i915_page_table *scratch_pt;
 	struct i915_page_directory *scratch_pd;
@@ -331,6 +333,8 @@ struct i915_address_space {
 			u32 flags);
 };
 
+#define i915_is_ggtt(V) ((V)->is_ggtt)
+
 /* The Graphics Translation Table is the way in which GEN hardware translates a
  * Graphics Virtual Address into a Physical Address. In addition to the normal
  * collateral associated with any va->pa translations GEN hardware also has a
@@ -343,6 +347,8 @@ struct i915_gtt {
 
 	size_t stolen_size;		/* Total size of stolen memory */
 	size_t stolen_usable_size;	/* Total size minus BIOS reserved */
+	size_t stolen_reserved_base;
+	size_t stolen_reserved_size;
 	u64 mappable_end;		/* End offset that we can CPU map */
 	struct io_mapping *mappable;	/* Mapping to our CPU mappable region */
 	phys_addr_t mappable_base;	/* PA of our GMADR */
@@ -417,7 +423,7 @@ static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift)
 static inline uint32_t i915_pte_count(uint64_t addr, size_t length,
 				      uint32_t pde_shift)
 {
-	const uint64_t mask = ~((1 << pde_shift) - 1);
+	const uint64_t mask = ~((1ULL << pde_shift) - 1);
 	uint64_t end;
 
 	WARN_ON(length == 0);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index f7df54a8e..d3c473ffb 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -47,6 +47,46 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 #endif
 }
 
+static int num_vma_bound(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	int count = 0;
+
+	list_for_each_entry(vma, &obj->vma_list, obj_link) {
+		if (drm_mm_node_allocated(&vma->node))
+			count++;
+		if (vma->pin_count)
+			count++;
+	}
+
+	return count;
+}
+
+static bool swap_available(void)
+{
+	return get_nr_swap_pages() > 0;
+}
+
+static bool can_release_pages(struct drm_i915_gem_object *obj)
+{
+	/* Only report true if by unbinding the object and putting its pages
+	 * we can actually make forward progress towards freeing physical
+	 * pages.
+	 *
+	 * If the pages are pinned for any other reason than being bound
+	 * to the GPU, simply unbinding from the GPU is not going to succeed
+	 * in releasing our pin count on the pages themselves.
+	 */
+	if (obj->pages_pin_count != num_vma_bound(obj))
+		return false;
+
+	/* We can only return physical pages to the system if we can either
+	 * discard the contents (because the user has marked them as being
+	 * purgeable) or if we can move their contents out to swap.
+	 */
+	return swap_available() || obj->madv == I915_MADV_DONTNEED;
+}
+
 /**
  * i915_gem_shrink - Shrink buffer object caches
  * @dev_priv: i915 device
@@ -129,11 +169,14 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active)
 				continue;
 
+			if (!can_release_pages(obj))
+				continue;
+
 			drm_gem_object_reference(&obj->base);
 
 			/* For the unbound phase, this should be a no-op! */
 			list_for_each_entry_safe(vma, v,
-						 &obj->vma_list, vma_link)
+						 &obj->vma_list, obj_link)
 				if (i915_vma_unbind(vma))
 					break;
 
@@ -188,21 +231,6 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 	return true;
 }
 
-static int num_vma_bound(struct drm_i915_gem_object *obj)
-{
-	struct i915_vma *vma;
-	int count = 0;
-
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
-		if (drm_mm_node_allocated(&vma->node))
-			count++;
-		if (vma->pin_count)
-			count++;
-	}
-
-	return count;
-}
-
 static unsigned long
 i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
@@ -222,7 +250,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (!obj->active && obj->pages_pin_count == num_vma_bound(obj))
+		if (!obj->active && can_release_pages(obj))
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 
@@ -339,8 +367,20 @@ void i915_gem_shrinker_init(struct drm_i915_private *dev_priv)
 	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
 	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
 	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
-	register_shrinker(&dev_priv->mm.shrinker);
+	WARN_ON(register_shrinker(&dev_priv->mm.shrinker));
 
 	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
-	register_oom_notifier(&dev_priv->mm.oom_notifier);
+	WARN_ON(register_oom_notifier(&dev_priv->mm.oom_notifier));
+}
+
+/**
+ * i915_gem_shrinker_cleanup - Clean up i915 shrinker
+ * @dev_priv: i915 device
+ *
+ * This function unregisters the i915 shrinker and OOM handler.
+ */
+void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
+	unregister_shrinker(&dev_priv->mm.shrinker);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 3476877fc..2e6e9fb6f 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -458,6 +458,9 @@ int i915_gem_init_stolen(struct drm_device *dev)
 		return 0;
 	}
 
+	dev_priv->gtt.stolen_reserved_base = reserved_base;
+	dev_priv->gtt.stolen_reserved_size = reserved_size;
+
 	/* It is possible for the reserved area to end before the end of stolen
 	 * memory, so just consider the start. */
 	reserved_total = stolen_top - reserved_base;
@@ -569,6 +572,9 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 	if (obj->pages == NULL)
 		goto cleanup;
 
+	obj->get_page.sg = obj->pages->sgl;
+	obj->get_page.last = 0;
+
 	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
@@ -632,6 +638,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
 
+	lockdep_assert_held(&dev->struct_mutex);
+
 	DRM_DEBUG_KMS("creating preallocated stolen object: stolen_offset=%x, gtt_offset=%x, size=%x\n",
 			stolen_offset, gtt_offset, size);
 
@@ -689,7 +697,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 		vma->bound |= GLOBAL_BIND;
 		__i915_vma_set_map_and_fenceable(vma);
-		list_add_tail(&vma->mm_list, &ggtt->inactive_list);
+		list_add_tail(&vma->vm_link, &ggtt->inactive_list);
 	}
 
 	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 59e45b3a6..4d30b60de 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -49,21 +49,18 @@ struct i915_mmu_notifier {
 	struct hlist_node node;
 	struct mmu_notifier mn;
 	struct rb_root objects;
-	struct list_head linear;
-	bool has_linear;
 };
 
 struct i915_mmu_object {
 	struct i915_mmu_notifier *mn;
+	struct drm_i915_gem_object *obj;
 	struct interval_tree_node it;
 	struct list_head link;
-	struct drm_i915_gem_object *obj;
 	struct work_struct work;
-	bool active;
-	bool is_linear;
+	bool attached;
 };
 
-static void __cancel_userptr__worker(struct work_struct *work)
+static void cancel_userptr(struct work_struct *work)
 {
 	struct i915_mmu_object *mo = container_of(work, typeof(*mo), work);
 	struct drm_i915_gem_object *obj = mo->obj;
@@ -81,7 +78,7 @@ static void __cancel_userptr__worker(struct work_struct *work)
 		was_interruptible = dev_priv->mm.interruptible;
 		dev_priv->mm.interruptible = false;
 
-		list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) {
+		list_for_each_entry_safe(vma, tmp, &obj->vma_list, obj_link) {
 			int ret = i915_vma_unbind(vma);
 			WARN_ON(ret && ret != -EIO);
 		}
@@ -94,24 +91,22 @@ static void __cancel_userptr__worker(struct work_struct *work)
 	mutex_unlock(&dev->struct_mutex);
 }
 
-static unsigned long cancel_userptr(struct i915_mmu_object *mo)
+static void add_object(struct i915_mmu_object *mo)
 {
-	unsigned long end = mo->obj->userptr.ptr + mo->obj->base.size;
-
-	/* The mmu_object is released late when destroying the
-	 * GEM object so it is entirely possible to gain a
-	 * reference on an object in the process of being freed
-	 * since our serialisation is via the spinlock and not
-	 * the struct_mutex - and consequently use it after it
-	 * is freed and then double free it.
-	 */
-	if (mo->active && kref_get_unless_zero(&mo->obj->base.refcount)) {
-		schedule_work(&mo->work);
-		/* only schedule one work packet to avoid the refleak */
-		mo->active = false;
-	}
+	if (mo->attached)
+		return;
+
+	interval_tree_insert(&mo->it, &mo->mn->objects);
+	mo->attached = true;
+}
 
-	return end;
+static void del_object(struct i915_mmu_object *mo)
+{
+	if (!mo->attached)
+		return;
+
+	interval_tree_remove(&mo->it, &mo->mn->objects);
+	mo->attached = false;
 }
 
 static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
@@ -122,28 +117,36 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	struct i915_mmu_notifier *mn =
 		container_of(_mn, struct i915_mmu_notifier, mn);
 	struct i915_mmu_object *mo;
+	struct interval_tree_node *it;
+	LIST_HEAD(cancelled);
+
+	if (RB_EMPTY_ROOT(&mn->objects))
+		return;
 
 	/* interval ranges are inclusive, but invalidate range is exclusive */
 	end--;
 
 	spin_lock(&mn->lock);
-	if (mn->has_linear) {
-		list_for_each_entry(mo, &mn->linear, link) {
-			if (mo->it.last < start || mo->it.start > end)
-				continue;
-
-			cancel_userptr(mo);
-		}
-	} else {
-		struct interval_tree_node *it;
+	it = interval_tree_iter_first(&mn->objects, start, end);
+	while (it) {
+		/* The mmu_object is released late when destroying the
+		 * GEM object so it is entirely possible to gain a
+		 * reference on an object in the process of being freed
+		 * since our serialisation is via the spinlock and not
+		 * the struct_mutex - and consequently use it after it
+		 * is freed and then double free it. To prevent that
+		 * use-after-free we only acquire a reference on the
+		 * object if it is not in the process of being destroyed.
+		 */
+		mo = container_of(it, struct i915_mmu_object, it);
+		if (kref_get_unless_zero(&mo->obj->base.refcount))
+			schedule_work(&mo->work);
 
-		it = interval_tree_iter_first(&mn->objects, start, end);
-		while (it) {
-			mo = container_of(it, struct i915_mmu_object, it);
-			start = cancel_userptr(mo);
-			it = interval_tree_iter_next(it, start, end);
-		}
+		list_add(&mo->link, &cancelled);
+		it = interval_tree_iter_next(it, start, end);
 	}
+	list_for_each_entry(mo, &cancelled, link)
+		del_object(mo);
 	spin_unlock(&mn->lock);
 }
 
@@ -164,8 +167,6 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 	spin_lock_init(&mn->lock);
 	mn->mn.ops = &i915_gem_userptr_notifier;
 	mn->objects = RB_ROOT;
-	INIT_LIST_HEAD(&mn->linear);
-	mn->has_linear = false;
 
 	 /* Protected by mmap_sem (write-lock) */
 	ret = __mmu_notifier_register(&mn->mn, mm);
@@ -177,85 +178,6 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 	return mn;
 }
 
-static int
-i915_mmu_notifier_add(struct drm_device *dev,
-		      struct i915_mmu_notifier *mn,
-		      struct i915_mmu_object *mo)
-{
-	struct interval_tree_node *it;
-	int ret = 0;
-
-	/* By this point we have already done a lot of expensive setup that
-	 * we do not want to repeat just because the caller (e.g. X) has a
-	 * signal pending (and partly because of that expensive setup, X
-	 * using an interrupt timer is likely to get stuck in an EINTR loop).
-	 */
-	mutex_lock(&dev->struct_mutex);
-
-	/* Make sure we drop the final active reference (and thereby
-	 * remove the objects from the interval tree) before we do
-	 * the check for overlapping objects.
-	 */
-	i915_gem_retire_requests(dev);
-
-	spin_lock(&mn->lock);
-	it = interval_tree_iter_first(&mn->objects,
-				      mo->it.start, mo->it.last);
-	if (it) {
-		struct drm_i915_gem_object *obj;
-
-		/* We only need to check the first object in the range as it
-		 * either has cancelled gup work queued and we need to
-		 * return back to the user to give time for the gup-workers
-		 * to flush their object references upon which the object will
-		 * be removed from the interval-tree, or the the range is
-		 * still in use by another client and the overlap is invalid.
-		 *
-		 * If we do have an overlap, we cannot use the interval tree
-		 * for fast range invalidation.
-		 */
-
-		obj = container_of(it, struct i915_mmu_object, it)->obj;
-		if (!obj->userptr.workers)
-			mn->has_linear = mo->is_linear = true;
-		else
-			ret = -EAGAIN;
-	} else
-		interval_tree_insert(&mo->it, &mn->objects);
-
-	if (ret == 0)
-		list_add(&mo->link, &mn->linear);
-
-	spin_unlock(&mn->lock);
-	mutex_unlock(&dev->struct_mutex);
-
-	return ret;
-}
-
-static bool i915_mmu_notifier_has_linear(struct i915_mmu_notifier *mn)
-{
-	struct i915_mmu_object *mo;
-
-	list_for_each_entry(mo, &mn->linear, link)
-		if (mo->is_linear)
-			return true;
-
-	return false;
-}
-
-static void
-i915_mmu_notifier_del(struct i915_mmu_notifier *mn,
-		      struct i915_mmu_object *mo)
-{
-	spin_lock(&mn->lock);
-	list_del(&mo->link);
-	if (mo->is_linear)
-		mn->has_linear = i915_mmu_notifier_has_linear(mn);
-	else
-		interval_tree_remove(&mo->it, &mn->objects);
-	spin_unlock(&mn->lock);
-}
-
 static void
 i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 {
@@ -265,7 +187,9 @@ i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 	if (mo == NULL)
 		return;
 
-	i915_mmu_notifier_del(mo->mn, mo);
+	spin_lock(&mo->mn->lock);
+	del_object(mo);
+	spin_unlock(&mo->mn->lock);
 	kfree(mo);
 
 	obj->userptr.mmu_object = NULL;
@@ -299,7 +223,6 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
 {
 	struct i915_mmu_notifier *mn;
 	struct i915_mmu_object *mo;
-	int ret;
 
 	if (flags & I915_USERPTR_UNSYNCHRONIZED)
 		return capable(CAP_SYS_ADMIN) ? 0 : -EPERM;
@@ -316,16 +239,10 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
 		return -ENOMEM;
 
 	mo->mn = mn;
-	mo->it.start = obj->userptr.ptr;
-	mo->it.last = mo->it.start + obj->base.size - 1;
 	mo->obj = obj;
-	INIT_WORK(&mo->work, __cancel_userptr__worker);
-
-	ret = i915_mmu_notifier_add(obj->base.dev, mn, mo);
-	if (ret) {
-		kfree(mo);
-		return ret;
-	}
+	mo->it.start = obj->userptr.ptr;
+	mo->it.last = obj->userptr.ptr + obj->base.size - 1;
+	INIT_WORK(&mo->work, cancel_userptr);
 
 	obj->userptr.mmu_object = mo;
 	return 0;
@@ -552,8 +469,10 @@ __i915_gem_userptr_set_active(struct drm_i915_gem_object *obj,
 	/* In order to serialise get_pages with an outstanding
 	 * cancel_userptr, we must drop the struct_mutex and try again.
 	 */
-	if (!value || !work_pending(&obj->userptr.mmu_object->work))
-		obj->userptr.mmu_object->active = value;
+	if (!value)
+		del_object(obj->userptr.mmu_object);
+	else if (!work_pending(&obj->userptr.mmu_object->work))
+		add_object(obj->userptr.mmu_object);
 	else
 		ret = -EAGAIN;
 	spin_unlock(&obj->userptr.mmu_object->mn->lock);
@@ -582,19 +501,24 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
-		down_read(&mm->mmap_sem);
-		while (pinned < npages) {
-			ret = get_user_pages(work->task, mm,
-					     obj->userptr.ptr + pinned * PAGE_SIZE,
-					     npages - pinned,
-					     !obj->userptr.read_only, 0,
-					     pvec + pinned, NULL);
-			if (ret < 0)
-				break;
-
-			pinned += ret;
+		ret = -EFAULT;
+		if (atomic_inc_not_zero(&mm->mm_users)) {
+			down_read(&mm->mmap_sem);
+			while (pinned < npages) {
+				ret = get_user_pages_remote
+					(work->task, mm,
+					 obj->userptr.ptr + pinned * PAGE_SIZE,
+					 npages - pinned,
+					 !obj->userptr.read_only, 0,
+					 pvec + pinned, NULL);
+				if (ret < 0)
+					break;
+
+				pinned += ret;
+			}
+			up_read(&mm->mmap_sem);
+			mmput(mm);
 		}
-		up_read(&mm->mmap_sem);
 	}
 
 	mutex_lock(&dev->struct_mutex);
@@ -764,7 +688,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 			set_page_dirty(page);
 
 		mark_page_accessed(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	obj->dirty = 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 06ca40827..831895b8c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -365,6 +365,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Reset count: %u\n", error->reset_count);
 	err_printf(m, "Suspend count: %u\n", error->suspend_count);
 	err_printf(m, "PCI ID: 0x%04x\n", dev->pdev->device);
+	err_printf(m, "PCI Revision: 0x%02x\n", dev->pdev->revision);
+	err_printf(m, "PCI Subsystem: %04x:%04x\n",
+		   dev->pdev->subsystem_vendor,
+		   dev->pdev->subsystem_device);
 	err_printf(m, "IOMMU enabled?: %d\n", error->iommu);
 
 	if (HAS_CSR(dev)) {
@@ -732,7 +736,7 @@ static u32 capture_active_bo(struct drm_i915_error_buffer *err,
 	struct i915_vma *vma;
 	int i = 0;
 
-	list_for_each_entry(vma, head, mm_list) {
+	list_for_each_entry(vma, head, vm_link) {
 		capture_bo(err++, vma);
 		if (++i == count)
 			break;
@@ -755,7 +759,7 @@ static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
 		if (err == last)
 			break;
 
-		list_for_each_entry(vma, &obj->vma_list, vma_link)
+		list_for_each_entry(vma, &obj->vma_list, obj_link)
 			if (vma->vm == vm && vma->pin_count > 0)
 				capture_bo(err++, vma);
 	}
@@ -1050,7 +1054,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 			if (request)
 				rbuf = request->ctx->engine[ring->id].ringbuf;
 			else
-				rbuf = ring->default_context->engine[ring->id].ringbuf;
+				rbuf = dev_priv->kernel_context->engine[ring->id].ringbuf;
 		} else
 			rbuf = ring->buffer;
 
@@ -1123,12 +1127,12 @@ static void i915_gem_capture_vm(struct drm_i915_private *dev_priv,
 	int i;
 
 	i = 0;
-	list_for_each_entry(vma, &vm->active_list, mm_list)
+	list_for_each_entry(vma, &vm->active_list, vm_link)
 		i++;
 	error->active_bo_count[ndx] = i;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		list_for_each_entry(vma, &obj->vma_list, vma_link)
+		list_for_each_entry(vma, &obj->vma_list, obj_link)
 			if (vma->vm == vm && vma->pin_count > 0)
 				i++;
 	}
diff --git a/drivers/gpu/drm/i915/i915_guc_reg.h b/drivers/gpu/drm/i915/i915_guc_reg.h
index 685c7991e..e4ba58222 100644
--- a/drivers/gpu/drm/i915/i915_guc_reg.h
+++ b/drivers/gpu/drm/i915/i915_guc_reg.h
@@ -40,6 +40,7 @@
 #define   GS_MIA_CORE_STATE		  (1 << GS_MIA_SHIFT)
 
 #define SOFT_SCRATCH(n)			_MMIO(0xc180 + (n) * 4)
+#define SOFT_SCRATCH_COUNT		16
 
 #define UOS_RSA_SCRATCH(i)		_MMIO(0xc200 + (i) * 4)
 #define   UOS_RSA_SCRATCH_MAX_COUNT	  64
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 05aa7e61c..d7543efc8 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -158,10 +158,8 @@ static int host2guc_sample_forcewake(struct intel_guc *guc,
 
 	data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
 	/* WaRsDisableCoarsePowerGating:skl,bxt */
-	if (!intel_enable_rc6(dev_priv->dev) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1) ||
-	    (IS_SKL_GT3(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0)) ||
-	    (IS_SKL_GT4(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0)))
+	if (!intel_enable_rc6(dev) ||
+	    NEEDS_WaRsDisableCoarsePowerGating(dev))
 		data[1] = 0;
 	else
 		/* bit 0 and 1 are for Render and Media domain separately */
@@ -246,6 +244,9 @@ static int guc_ring_doorbell(struct i915_guc_client *gc)
 			db_exc.cookie = 1;
 	}
 
+	/* Finally, update the cached copy of the GuC's WQ head */
+	gc->wq_head = desc->head;
+
 	kunmap_atomic(base);
 	return ret;
 }
@@ -375,6 +376,8 @@ static void guc_init_proc_desc(struct intel_guc *guc,
 static void guc_init_ctx_desc(struct intel_guc *guc,
 			      struct i915_guc_client *client)
 {
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct intel_engine_cs *ring;
 	struct intel_context *ctx = client->owner;
 	struct guc_context_desc desc;
 	struct sg_table *sg;
@@ -387,10 +390,8 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	desc.priority = client->priority;
 	desc.db_id = client->doorbell_id;
 
-	for (i = 0; i < I915_NUM_RINGS; i++) {
-		struct guc_execlist_context *lrc = &desc.lrc[i];
-		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
-		struct intel_engine_cs *ring;
+	for_each_ring(ring, dev_priv, i) {
+		struct guc_execlist_context *lrc = &desc.lrc[ring->guc_id];
 		struct drm_i915_gem_object *obj;
 		uint64_t ctx_desc;
 
@@ -405,7 +406,6 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		if (!obj)
 			break;	/* XXX: continue? */
 
-		ring = ringbuf->ring;
 		ctx_desc = intel_lr_context_descriptor(ctx, ring);
 		lrc->context_desc = (u32)ctx_desc;
 
@@ -413,16 +413,16 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		lrc->ring_lcra = i915_gem_obj_ggtt_offset(obj) +
 				LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
-				(ring->id << GUC_ELC_ENGINE_OFFSET);
+				(ring->guc_id << GUC_ELC_ENGINE_OFFSET);
 
-		obj = ringbuf->obj;
+		obj = ctx->engine[i].ringbuf->obj;
 
 		lrc->ring_begin = i915_gem_obj_ggtt_offset(obj);
 		lrc->ring_end = lrc->ring_begin + obj->base.size - 1;
 		lrc->ring_next_free_location = lrc->ring_begin;
 		lrc->ring_current_tail_pointer_value = 0;
 
-		desc.engines_used |= (1 << ring->id);
+		desc.engines_used |= (1 << ring->guc_id);
 	}
 
 	WARN_ON(desc.engines_used == 0);
@@ -471,28 +471,30 @@ static void guc_fini_ctx_desc(struct intel_guc *guc,
 			     sizeof(desc) * client->ctx_index);
 }
 
-/* Get valid workqueue item and return it back to offset */
-static int guc_get_workqueue_space(struct i915_guc_client *gc, u32 *offset)
+int i915_guc_wq_check_space(struct i915_guc_client *gc)
 {
 	struct guc_process_desc *desc;
 	void *base;
 	u32 size = sizeof(struct guc_wq_item);
 	int ret = -ETIMEDOUT, timeout_counter = 200;
 
+	if (!gc)
+		return 0;
+
+	/* Quickly return if wq space is available since last time we cache the
+	 * head position. */
+	if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size)
+		return 0;
+
 	base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0));
 	desc = base + gc->proc_desc_offset;
 
 	while (timeout_counter-- > 0) {
-		if (CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size) >= size) {
-			*offset = gc->wq_tail;
+		gc->wq_head = desc->head;
 
-			/* advance the tail for next workqueue item */
-			gc->wq_tail += size;
-			gc->wq_tail &= gc->wq_size - 1;
-
-			/* this will break the loop */
-			timeout_counter = 0;
+		if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size) {
 			ret = 0;
+			break;
 		}
 
 		if (timeout_counter)
@@ -507,15 +509,18 @@ static int guc_get_workqueue_space(struct i915_guc_client *gc, u32 *offset)
 static int guc_add_workqueue_item(struct i915_guc_client *gc,
 				  struct drm_i915_gem_request *rq)
 {
-	enum intel_ring_id ring_id = rq->ring->id;
 	struct guc_wq_item *wqi;
 	void *base;
-	u32 tail, wq_len, wq_off = 0;
-	int ret;
+	u32 tail, wq_len, wq_off, space;
+
+	space = CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size);
+	if (WARN_ON(space < sizeof(struct guc_wq_item)))
+		return -ENOSPC; /* shouldn't happen */
 
-	ret = guc_get_workqueue_space(gc, &wq_off);
-	if (ret)
-		return ret;
+	/* postincrement WQ tail for next time */
+	wq_off = gc->wq_tail;
+	gc->wq_tail += sizeof(struct guc_wq_item);
+	gc->wq_tail &= gc->wq_size - 1;
 
 	/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
 	 * should not have the case where structure wqi is across page, neither
@@ -537,7 +542,7 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc,
 	wq_len = sizeof(struct guc_wq_item) / sizeof(u32) - 1;
 	wqi->header = WQ_TYPE_INORDER |
 			(wq_len << WQ_LEN_SHIFT) |
-			(ring_id << WQ_TARGET_SHIFT) |
+			(rq->ring->guc_id << WQ_TARGET_SHIFT) |
 			WQ_NO_WCFLUSH_WAIT;
 
 	/* The GuC wants only the low-order word of the context descriptor */
@@ -553,29 +558,6 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc,
 	return 0;
 }
 
-#define CTX_RING_BUFFER_START		0x08
-
-/* Update the ringbuffer pointer in a saved context image */
-static void lr_context_update(struct drm_i915_gem_request *rq)
-{
-	enum intel_ring_id ring_id = rq->ring->id;
-	struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring_id].state;
-	struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj;
-	struct page *page;
-	uint32_t *reg_state;
-
-	BUG_ON(!ctx_obj);
-	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
-	WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
-
-	page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN);
-	reg_state = kmap_atomic(page);
-
-	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
-
-	kunmap_atomic(reg_state);
-}
-
 /**
  * i915_guc_submit() - Submit commands through GuC
  * @client:	the guc client where commands will go through
@@ -587,18 +569,14 @@ int i915_guc_submit(struct i915_guc_client *client,
 		    struct drm_i915_gem_request *rq)
 {
 	struct intel_guc *guc = client->guc;
-	enum intel_ring_id ring_id = rq->ring->id;
+	unsigned int engine_id = rq->ring->guc_id;
 	int q_ret, b_ret;
 
-	/* Need this because of the deferred pin ctx and ring */
-	/* Shall we move this right after ring is pinned? */
-	lr_context_update(rq);
-
 	q_ret = guc_add_workqueue_item(client, rq);
 	if (q_ret == 0)
 		b_ret = guc_ring_doorbell(client);
 
-	client->submissions[ring_id] += 1;
+	client->submissions[engine_id] += 1;
 	if (q_ret) {
 		client->q_fail += 1;
 		client->retcode = q_ret;
@@ -608,8 +586,8 @@ int i915_guc_submit(struct i915_guc_client *client,
 	} else {
 		client->retcode = 0;
 	}
-	guc->submissions[ring_id] += 1;
-	guc->last_seqno[ring_id] = rq->seqno;
+	guc->submissions[engine_id] += 1;
+	guc->last_seqno[engine_id] = rq->seqno;
 
 	return q_ret;
 }
@@ -832,6 +810,96 @@ static void guc_create_log(struct intel_guc *guc)
 	guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
 }
 
+static void init_guc_policies(struct guc_policies *policies)
+{
+	struct guc_policy *policy;
+	u32 p, i;
+
+	policies->dpc_promote_time = 500000;
+	policies->max_num_work_items = POLICY_MAX_NUM_WI;
+
+	for (p = 0; p < GUC_CTX_PRIORITY_NUM; p++) {
+		for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
+			policy = &policies->policy[p][i];
+
+			policy->execution_quantum = 1000000;
+			policy->preemption_time = 500000;
+			policy->fault_time = 250000;
+			policy->policy_flags = 0;
+		}
+	}
+
+	policies->is_valid = 1;
+}
+
+static void guc_create_ads(struct intel_guc *guc)
+{
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_i915_gem_object *obj;
+	struct guc_ads *ads;
+	struct guc_policies *policies;
+	struct guc_mmio_reg_state *reg_state;
+	struct intel_engine_cs *ring;
+	struct page *page;
+	u32 size, i;
+
+	/* The ads obj includes the struct itself and buffers passed to GuC */
+	size = sizeof(struct guc_ads) + sizeof(struct guc_policies) +
+			sizeof(struct guc_mmio_reg_state) +
+			GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE;
+
+	obj = guc->ads_obj;
+	if (!obj) {
+		obj = gem_allocate_guc_obj(dev_priv->dev, PAGE_ALIGN(size));
+		if (!obj)
+			return;
+
+		guc->ads_obj = obj;
+	}
+
+	page = i915_gem_object_get_page(obj, 0);
+	ads = kmap(page);
+
+	/*
+	 * The GuC requires a "Golden Context" when it reinitialises
+	 * engines after a reset. Here we use the Render ring default
+	 * context, which must already exist and be pinned in the GGTT,
+	 * so its address won't change after we've told the GuC where
+	 * to find it.
+	 */
+	ring = &dev_priv->ring[RCS];
+	ads->golden_context_lrca = ring->status_page.gfx_addr;
+
+	for_each_ring(ring, dev_priv, i)
+		ads->eng_state_size[ring->guc_id] = intel_lr_context_size(ring);
+
+	/* GuC scheduling policies */
+	policies = (void *)ads + sizeof(struct guc_ads);
+	init_guc_policies(policies);
+
+	ads->scheduler_policies = i915_gem_obj_ggtt_offset(obj) +
+			sizeof(struct guc_ads);
+
+	/* MMIO reg state */
+	reg_state = (void *)policies + sizeof(struct guc_policies);
+
+	for_each_ring(ring, dev_priv, i) {
+		reg_state->mmio_white_list[ring->guc_id].mmio_start =
+			ring->mmio_base + GUC_MMIO_WHITE_LIST_START;
+
+		/* Nothing to be saved or restored for now. */
+		reg_state->mmio_white_list[ring->guc_id].count = 0;
+	}
+
+	ads->reg_state_addr = ads->scheduler_policies +
+			sizeof(struct guc_policies);
+
+	ads->reg_state_buffer = ads->reg_state_addr +
+			sizeof(struct guc_mmio_reg_state);
+
+	kunmap(page);
+}
+
 /*
  * Set up the memory resources to be shared with the GuC.  At this point,
  * we require just one object that can be mapped through the GGTT.
@@ -858,6 +926,8 @@ int i915_guc_submission_init(struct drm_device *dev)
 
 	guc_create_log(guc);
 
+	guc_create_ads(guc);
+
 	return 0;
 }
 
@@ -865,7 +935,7 @@ int i915_guc_submission_enable(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_context *ctx = dev_priv->ring[RCS].default_context;
+	struct intel_context *ctx = dev_priv->kernel_context;
 	struct i915_guc_client *client;
 
 	/* client for execbuf submission */
@@ -896,6 +966,9 @@ void i915_guc_submission_fini(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
 
+	gem_release_guc_obj(dev_priv->guc.ads_obj);
+	guc->ads_obj = NULL;
+
 	gem_release_guc_obj(dev_priv->guc.log_obj);
 	guc->log_obj = NULL;
 
@@ -919,7 +992,7 @@ int intel_guc_suspend(struct drm_device *dev)
 	if (!i915.enable_guc_submission)
 		return 0;
 
-	ctx = dev_priv->ring[RCS].default_context;
+	ctx = dev_priv->kernel_context;
 
 	data[0] = HOST2GUC_ACTION_ENTER_S_STATE;
 	/* any value greater than GUC_POWER_D0 */
@@ -945,7 +1018,7 @@ int intel_guc_resume(struct drm_device *dev)
 	if (!i915.enable_guc_submission)
 		return 0;
 
-	ctx = dev_priv->ring[RCS].default_context;
+	ctx = dev_priv->kernel_context;
 
 	data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
 	data[1] = GUC_POWER_D0;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index fa8afa786..1c212205d 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1651,6 +1651,12 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 	int pipe;
 
 	spin_lock(&dev_priv->irq_lock);
+
+	if (!dev_priv->display_irqs_enabled) {
+		spin_unlock(&dev_priv->irq_lock);
+		return;
+	}
+
 	for_each_pipe(dev_priv, pipe) {
 		i915_reg_t reg;
 		u32 mask, iir_bit = 0;
@@ -1823,7 +1829,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	disable_rpm_wakeref_asserts(dev_priv);
 
-	for (;;) {
+	do {
 		master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL;
 		iir = I915_READ(VLV_IIR);
 
@@ -1851,7 +1857,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(GEN8_MASTER_IRQ, DE_MASTER_IRQ_CONTROL);
 		POSTING_READ(GEN8_MASTER_IRQ);
-	}
+	} while (0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 
@@ -2188,10 +2194,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	disable_rpm_wakeref_asserts(dev_priv);
 
-	/* We get interrupts on unclaimed registers, so check for this before we
-	 * do any I915_{READ,WRITE}. */
-	intel_uncore_check_errors(dev);
-
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
 	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
@@ -2268,43 +2270,20 @@ static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
 	intel_hpd_irq_handler(dev, pin_mask, long_mask);
 }
 
-static irqreturn_t gen8_irq_handler(int irq, void *arg)
+static irqreturn_t
+gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 {
-	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 master_ctl;
+	struct drm_device *dev = dev_priv->dev;
 	irqreturn_t ret = IRQ_NONE;
-	uint32_t tmp = 0;
+	u32 iir;
 	enum pipe pipe;
-	u32 aux_mask = GEN8_AUX_CHANNEL_A;
-
-	if (!intel_irqs_enabled(dev_priv))
-		return IRQ_NONE;
-
-	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
-	disable_rpm_wakeref_asserts(dev_priv);
-
-	if (INTEL_INFO(dev_priv)->gen >= 9)
-		aux_mask |=  GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
-			GEN9_AUX_CHANNEL_D;
-
-	master_ctl = I915_READ_FW(GEN8_MASTER_IRQ);
-	master_ctl &= ~GEN8_MASTER_IRQ_CONTROL;
-	if (!master_ctl)
-		goto out;
-
-	I915_WRITE_FW(GEN8_MASTER_IRQ, 0);
-
-	/* Find, clear, then process each source of interrupt */
-
-	ret = gen8_gt_irq_handler(dev_priv, master_ctl);
 
 	if (master_ctl & GEN8_DE_MISC_IRQ) {
-		tmp = I915_READ(GEN8_DE_MISC_IIR);
-		if (tmp) {
-			I915_WRITE(GEN8_DE_MISC_IIR, tmp);
+		iir = I915_READ(GEN8_DE_MISC_IIR);
+		if (iir) {
+			I915_WRITE(GEN8_DE_MISC_IIR, iir);
 			ret = IRQ_HANDLED;
-			if (tmp & GEN8_DE_MISC_GSE)
+			if (iir & GEN8_DE_MISC_GSE)
 				intel_opregion_asle_intr(dev);
 			else
 				DRM_ERROR("Unexpected DE Misc interrupt\n");
@@ -2314,33 +2293,40 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	}
 
 	if (master_ctl & GEN8_DE_PORT_IRQ) {
-		tmp = I915_READ(GEN8_DE_PORT_IIR);
-		if (tmp) {
+		iir = I915_READ(GEN8_DE_PORT_IIR);
+		if (iir) {
+			u32 tmp_mask;
 			bool found = false;
-			u32 hotplug_trigger = 0;
-
-			if (IS_BROXTON(dev_priv))
-				hotplug_trigger = tmp & BXT_DE_PORT_HOTPLUG_MASK;
-			else if (IS_BROADWELL(dev_priv))
-				hotplug_trigger = tmp & GEN8_PORT_DP_A_HOTPLUG;
 
-			I915_WRITE(GEN8_DE_PORT_IIR, tmp);
+			I915_WRITE(GEN8_DE_PORT_IIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (tmp & aux_mask) {
+			tmp_mask = GEN8_AUX_CHANNEL_A;
+			if (INTEL_INFO(dev_priv)->gen >= 9)
+				tmp_mask |= GEN9_AUX_CHANNEL_B |
+					    GEN9_AUX_CHANNEL_C |
+					    GEN9_AUX_CHANNEL_D;
+
+			if (iir & tmp_mask) {
 				dp_aux_irq_handler(dev);
 				found = true;
 			}
 
-			if (hotplug_trigger) {
-				if (IS_BROXTON(dev))
-					bxt_hpd_irq_handler(dev, hotplug_trigger, hpd_bxt);
-				else
-					ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_bdw);
-				found = true;
+			if (IS_BROXTON(dev_priv)) {
+				tmp_mask = iir & BXT_DE_PORT_HOTPLUG_MASK;
+				if (tmp_mask) {
+					bxt_hpd_irq_handler(dev, tmp_mask, hpd_bxt);
+					found = true;
+				}
+			} else if (IS_BROADWELL(dev_priv)) {
+				tmp_mask = iir & GEN8_PORT_DP_A_HOTPLUG;
+				if (tmp_mask) {
+					ilk_hpd_irq_handler(dev, tmp_mask, hpd_bdw);
+					found = true;
+				}
 			}
 
-			if (IS_BROXTON(dev) && (tmp & BXT_DE_PORT_GMBUS)) {
+			if (IS_BROXTON(dev) && (iir & BXT_DE_PORT_GMBUS)) {
 				gmbus_irq_handler(dev);
 				found = true;
 			}
@@ -2353,49 +2339,51 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	}
 
 	for_each_pipe(dev_priv, pipe) {
-		uint32_t pipe_iir, flip_done = 0, fault_errors = 0;
+		u32 flip_done, fault_errors;
 
 		if (!(master_ctl & GEN8_DE_PIPE_IRQ(pipe)))
 			continue;
 
-		pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe));
-		if (pipe_iir) {
-			ret = IRQ_HANDLED;
-			I915_WRITE(GEN8_DE_PIPE_IIR(pipe), pipe_iir);
+		iir = I915_READ(GEN8_DE_PIPE_IIR(pipe));
+		if (!iir) {
+			DRM_ERROR("The master control interrupt lied (DE PIPE)!\n");
+			continue;
+		}
 
-			if (pipe_iir & GEN8_PIPE_VBLANK &&
-			    intel_pipe_handle_vblank(dev, pipe))
-				intel_check_page_flip(dev, pipe);
+		ret = IRQ_HANDLED;
+		I915_WRITE(GEN8_DE_PIPE_IIR(pipe), iir);
 
-			if (INTEL_INFO(dev_priv)->gen >= 9)
-				flip_done = pipe_iir & GEN9_PIPE_PLANE1_FLIP_DONE;
-			else
-				flip_done = pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE;
+		if (iir & GEN8_PIPE_VBLANK &&
+		    intel_pipe_handle_vblank(dev, pipe))
+			intel_check_page_flip(dev, pipe);
 
-			if (flip_done) {
-				intel_prepare_page_flip(dev, pipe);
-				intel_finish_page_flip_plane(dev, pipe);
-			}
+		flip_done = iir;
+		if (INTEL_INFO(dev_priv)->gen >= 9)
+			flip_done &= GEN9_PIPE_PLANE1_FLIP_DONE;
+		else
+			flip_done &= GEN8_PIPE_PRIMARY_FLIP_DONE;
 
-			if (pipe_iir & GEN8_PIPE_CDCLK_CRC_DONE)
-				hsw_pipe_crc_irq_handler(dev, pipe);
+		if (flip_done) {
+			intel_prepare_page_flip(dev, pipe);
+			intel_finish_page_flip_plane(dev, pipe);
+		}
 
-			if (pipe_iir & GEN8_PIPE_FIFO_UNDERRUN)
-				intel_cpu_fifo_underrun_irq_handler(dev_priv,
-								    pipe);
+		if (iir & GEN8_PIPE_CDCLK_CRC_DONE)
+			hsw_pipe_crc_irq_handler(dev, pipe);
 
+		if (iir & GEN8_PIPE_FIFO_UNDERRUN)
+			intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
 
-			if (INTEL_INFO(dev_priv)->gen >= 9)
-				fault_errors = pipe_iir & GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
-			else
-				fault_errors = pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
+		fault_errors = iir;
+		if (INTEL_INFO(dev_priv)->gen >= 9)
+			fault_errors &= GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
+		else
+			fault_errors &= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 
-			if (fault_errors)
-				DRM_ERROR("Fault errors on pipe %c\n: 0x%08x",
-					  pipe_name(pipe),
-					  pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS);
-		} else
-			DRM_ERROR("The master control interrupt lied (DE PIPE)!\n");
+		if (fault_errors)
+			DRM_ERROR("Fault errors on pipe %c\n: 0x%08x",
+				  pipe_name(pipe),
+				  fault_errors);
 	}
 
 	if (HAS_PCH_SPLIT(dev) && !HAS_PCH_NOP(dev) &&
@@ -2405,15 +2393,15 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 		 * scheme also closed the SDE interrupt handling race we've seen
 		 * on older pch-split platforms. But this needs testing.
 		 */
-		u32 pch_iir = I915_READ(SDEIIR);
-		if (pch_iir) {
-			I915_WRITE(SDEIIR, pch_iir);
+		iir = I915_READ(SDEIIR);
+		if (iir) {
+			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
 			if (HAS_PCH_SPT(dev_priv))
-				spt_irq_handler(dev, pch_iir);
+				spt_irq_handler(dev, iir);
 			else
-				cpt_irq_handler(dev, pch_iir);
+				cpt_irq_handler(dev, iir);
 		} else {
 			/*
 			 * Like on previous PCH there seems to be something
@@ -2423,10 +2411,36 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 		}
 	}
 
+	return ret;
+}
+
+static irqreturn_t gen8_irq_handler(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 master_ctl;
+	irqreturn_t ret;
+
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
+	master_ctl = I915_READ_FW(GEN8_MASTER_IRQ);
+	master_ctl &= ~GEN8_MASTER_IRQ_CONTROL;
+	if (!master_ctl)
+		return IRQ_NONE;
+
+	I915_WRITE_FW(GEN8_MASTER_IRQ, 0);
+
+	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
+	disable_rpm_wakeref_asserts(dev_priv);
+
+	/* Find, clear, then process each source of interrupt */
+	ret = gen8_gt_irq_handler(dev_priv, master_ctl);
+	ret |= gen8_de_irq_handler(dev_priv, master_ctl);
+
 	I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
 	POSTING_READ_FW(GEN8_MASTER_IRQ);
 
-out:
 	enable_rpm_wakeref_asserts(dev_priv);
 
 	return ret;
@@ -2949,14 +2963,44 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 		ring->hangcheck.deadlock = 0;
 }
 
-static enum intel_ring_hangcheck_action
-ring_stuck(struct intel_engine_cs *ring, u64 acthd)
+static bool subunits_stuck(struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 tmp;
+	u32 instdone[I915_NUM_INSTDONE_REG];
+	bool stuck;
+	int i;
+
+	if (ring->id != RCS)
+		return true;
+
+	i915_get_extra_instdone(ring->dev, instdone);
+
+	/* There might be unstable subunit states even when
+	 * actual head is not moving. Filter out the unstable ones by
+	 * accumulating the undone -> done transitions and only
+	 * consider those as progress.
+	 */
+	stuck = true;
+	for (i = 0; i < I915_NUM_INSTDONE_REG; i++) {
+		const u32 tmp = instdone[i] | ring->hangcheck.instdone[i];
+
+		if (tmp != ring->hangcheck.instdone[i])
+			stuck = false;
 
+		ring->hangcheck.instdone[i] |= tmp;
+	}
+
+	return stuck;
+}
+
+static enum intel_ring_hangcheck_action
+head_stuck(struct intel_engine_cs *ring, u64 acthd)
+{
 	if (acthd != ring->hangcheck.acthd) {
+
+		/* Clear subunit states on head movement */
+		memset(ring->hangcheck.instdone, 0,
+		       sizeof(ring->hangcheck.instdone));
+
 		if (acthd > ring->hangcheck.max_acthd) {
 			ring->hangcheck.max_acthd = acthd;
 			return HANGCHECK_ACTIVE;
@@ -2965,6 +3009,24 @@ ring_stuck(struct intel_engine_cs *ring, u64 acthd)
 		return HANGCHECK_ACTIVE_LOOP;
 	}
 
+	if (!subunits_stuck(ring))
+		return HANGCHECK_ACTIVE;
+
+	return HANGCHECK_HUNG;
+}
+
+static enum intel_ring_hangcheck_action
+ring_stuck(struct intel_engine_cs *ring, u64 acthd)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_ring_hangcheck_action ha;
+	u32 tmp;
+
+	ha = head_stuck(ring, acthd);
+	if (ha != HANGCHECK_HUNG)
+		return ha;
+
 	if (IS_GEN2(dev))
 		return HANGCHECK_HUNG;
 
@@ -3032,6 +3094,12 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	 */
 	DISABLE_RPM_WAKEREF_ASSERTS(dev_priv);
 
+	/* As enabling the GPU requires fairly extensive mmio access,
+	 * periodically arm the mmio checker to see if we are triggering
+	 * any invalid access.
+	 */
+	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+
 	for_each_ring(ring, dev_priv, i) {
 		u64 acthd;
 		u32 seqno;
@@ -3106,7 +3174,11 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			if (ring->hangcheck.score > 0)
 				ring->hangcheck.score--;
 
+			/* Clear head and subunit states on seqno movement */
 			ring->hangcheck.acthd = ring->hangcheck.max_acthd = 0;
+
+			memset(ring->hangcheck.instdone, 0,
+			       sizeof(ring->hangcheck.instdone));
 		}
 
 		ring->hangcheck.seqno = seqno;
@@ -3277,23 +3349,30 @@ void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
 				     unsigned int pipe_mask)
 {
 	uint32_t extra_ier = GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN;
+	enum pipe pipe;
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	if (pipe_mask & 1 << PIPE_A)
-		GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_A,
-				  dev_priv->de_irq_mask[PIPE_A],
-				  ~dev_priv->de_irq_mask[PIPE_A] | extra_ier);
-	if (pipe_mask & 1 << PIPE_B)
-		GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_B,
-				  dev_priv->de_irq_mask[PIPE_B],
-				  ~dev_priv->de_irq_mask[PIPE_B] | extra_ier);
-	if (pipe_mask & 1 << PIPE_C)
-		GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_C,
-				  dev_priv->de_irq_mask[PIPE_C],
-				  ~dev_priv->de_irq_mask[PIPE_C] | extra_ier);
+	for_each_pipe_masked(dev_priv, pipe, pipe_mask)
+		GEN8_IRQ_INIT_NDX(DE_PIPE, pipe,
+				  dev_priv->de_irq_mask[pipe],
+				  ~dev_priv->de_irq_mask[pipe] | extra_ier);
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
+void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv,
+				     unsigned int pipe_mask)
+{
+	enum pipe pipe;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	for_each_pipe_masked(dev_priv, pipe, pipe_mask)
+		GEN8_IRQ_RESET_NDX(DE_PIPE, pipe);
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/* make sure we're done processing display irqs */
+	synchronize_irq(dev_priv->dev->irq);
+}
+
 static void cherryview_irq_preinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 835d6099c..278c9c40c 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -22,6 +22,7 @@
  * IN THE SOFTWARE.
  */
 
+#include "i915_params.h"
 #include "i915_drv.h"
 
 struct i915_params i915 __read_mostly = {
@@ -37,7 +38,7 @@ struct i915_params i915 __read_mostly = {
 	.enable_execlists = -1,
 	.enable_hangcheck = true,
 	.enable_ppgtt = -1,
-	.enable_psr = 0,
+	.enable_psr = -1,
 	.preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT),
 	.disable_power_well = -1,
 	.enable_ips = 1,
@@ -48,7 +49,6 @@ struct i915_params i915 __read_mostly = {
 	.invert_brightness = 0,
 	.disable_display = 0,
 	.enable_cmd_parser = 1,
-	.disable_vtd_wa = 0,
 	.use_mmio_flip = 0,
 	.mmio_debug = 0,
 	.verbose_state_checks = 1,
@@ -91,7 +91,7 @@ MODULE_PARM_DESC(enable_fbc,
 	"Enable frame buffer compression for power savings "
 	"(default: -1 (use per-chip default))");
 
-module_param_named_unsafe(lvds_channel_mode, i915.lvds_channel_mode, int, 0600);
+module_param_named_unsafe(lvds_channel_mode, i915.lvds_channel_mode, int, 0400);
 MODULE_PARM_DESC(lvds_channel_mode,
 	 "Specify LVDS channel mode "
 	 "(0=probe BIOS [default], 1=single-channel, 2=dual-channel)");
@@ -101,7 +101,7 @@ MODULE_PARM_DESC(lvds_use_ssc,
 	"Use Spread Spectrum Clock with panels [LVDS/eDP] "
 	"(default: auto from VBT)");
 
-module_param_named_unsafe(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0600);
+module_param_named_unsafe(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0400);
 MODULE_PARM_DESC(vbt_sdvo_panel_type,
 	"Override/Ignore selection of SDVO panel mode in the VBT "
 	"(-2=ignore, -1=auto [default], index in VBT BIOS table)");
@@ -126,9 +126,11 @@ MODULE_PARM_DESC(enable_execlists,
 	"(-1=auto [default], 0=disabled, 1=enabled)");
 
 module_param_named_unsafe(enable_psr, i915.enable_psr, int, 0600);
-MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)");
+MODULE_PARM_DESC(enable_psr, "Enable PSR "
+		 "(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) "
+		 "Default: -1 (use per-chip default)");
 
-module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, int, 0600);
+module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, int, 0400);
 MODULE_PARM_DESC(preliminary_hw_support,
 	"Enable preliminary hardware support.");
 
@@ -162,12 +164,9 @@ MODULE_PARM_DESC(invert_brightness,
 	"to dri-devel@lists.freedesktop.org, if your machine needs it. "
 	"It will then be included in an upcoming module version.");
 
-module_param_named(disable_display, i915.disable_display, bool, 0600);
+module_param_named(disable_display, i915.disable_display, bool, 0400);
 MODULE_PARM_DESC(disable_display, "Disable display (default: false)");
 
-module_param_named_unsafe(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600);
-MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)");
-
 module_param_named_unsafe(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
 MODULE_PARM_DESC(enable_cmd_parser,
 		 "Enable command parsing (1=enabled [default], 0=disabled)");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
new file mode 100644
index 000000000..bd5026b15
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright © 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _I915_PARAMS_H_
+#define _I915_PARAMS_H_
+
+#include <linux/cache.h> /* for __read_mostly */
+
+struct i915_params {
+	int modeset;
+	int panel_ignore_lid;
+	int semaphores;
+	int lvds_channel_mode;
+	int panel_use_ssc;
+	int vbt_sdvo_panel_type;
+	int enable_rc6;
+	int enable_dc;
+	int enable_fbc;
+	int enable_ppgtt;
+	int enable_execlists;
+	int enable_psr;
+	unsigned int preliminary_hw_support;
+	int disable_power_well;
+	int enable_ips;
+	int invert_brightness;
+	int enable_cmd_parser;
+	int guc_log_level;
+	int use_mmio_flip;
+	int mmio_debug;
+	int edp_vswing;
+	/* leave bools at the end to not create holes */
+	bool enable_hangcheck;
+	bool fastboot;
+	bool prefault_disable;
+	bool load_detect_test;
+	bool reset;
+	bool disable_display;
+	bool enable_guc_submission;
+	bool verbose_state_checks;
+	bool nuclear_pageflip;
+};
+
+extern struct i915_params i915 __read_mostly;
+
+#endif
+
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9b6737c85..363bd79de 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -610,16 +610,17 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   IOSF_BYTE_ENABLES_SHIFT		4
 #define   IOSF_BAR_SHIFT			1
 #define   IOSF_SB_BUSY				(1<<0)
-#define   IOSF_PORT_BUNIT			0x3
-#define   IOSF_PORT_PUNIT			0x4
+#define   IOSF_PORT_BUNIT			0x03
+#define   IOSF_PORT_PUNIT			0x04
 #define   IOSF_PORT_NC				0x11
 #define   IOSF_PORT_DPIO			0x12
-#define   IOSF_PORT_DPIO_2			0x1a
 #define   IOSF_PORT_GPIO_NC			0x13
 #define   IOSF_PORT_CCK				0x14
-#define   IOSF_PORT_CCU				0xA9
-#define   IOSF_PORT_GPS_CORE			0x48
-#define   IOSF_PORT_FLISDSI			0x1B
+#define   IOSF_PORT_DPIO_2			0x1a
+#define   IOSF_PORT_FLISDSI			0x1b
+#define   IOSF_PORT_GPIO_SC			0x48
+#define   IOSF_PORT_GPIO_SUS			0xa8
+#define   IOSF_PORT_CCU				0xa9
 #define VLV_IOSF_DATA				_MMIO(VLV_DISPLAY_BASE + 0x2104)
 #define VLV_IOSF_ADDR				_MMIO(VLV_DISPLAY_BASE + 0x2108)
 
@@ -1635,6 +1636,9 @@ enum skl_disp_power_wells {
 #define   RING_WAIT		(1<<11) /* gen3+, PRBx_CTL */
 #define   RING_WAIT_SEMAPHORE	(1<<10) /* gen6+ */
 
+#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base)+0x4D0) + (i)*4)
+#define   RING_MAX_NONPRIV_SLOTS  12
+
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
 #if 0
@@ -1711,6 +1715,11 @@ enum skl_disp_power_wells {
 #define FPGA_DBG		_MMIO(0x42300)
 #define   FPGA_DBG_RM_NOCLAIM	(1<<31)
 
+#define CLAIM_ER		_MMIO(VLV_DISPLAY_BASE + 0x2028)
+#define   CLAIM_ER_CLR		(1 << 31)
+#define   CLAIM_ER_OVERFLOW	(1 << 16)
+#define   CLAIM_ER_CTR_MASK	0xffff
+
 #define DERRMR		_MMIO(0x44050)
 /* Note that HBLANK events are reserved on bdw+ */
 #define   DERRMR_PIPEA_SCANLINE		(1<<0)
@@ -5948,6 +5957,7 @@ enum skl_disp_power_wells {
 #define  ILK_INTERNAL_GRAPHICS_DISABLE	(1 << 31)
 #define  ILK_INTERNAL_DISPLAY_DISABLE	(1 << 30)
 #define  ILK_DISPLAY_DEBUG_DISABLE	(1 << 29)
+#define  IVB_PIPE_C_DISABLE		(1 << 28)
 #define  ILK_HDCP_DISABLE		(1 << 25)
 #define  ILK_eDP_A_DISABLE		(1 << 24)
 #define  HSW_CDCLK_LIMIT		(1 << 24)
@@ -5994,10 +6004,19 @@ enum skl_disp_power_wells {
 #define SKL_DFSM_CDCLK_LIMIT_540	(1 << 23)
 #define SKL_DFSM_CDCLK_LIMIT_450	(2 << 23)
 #define SKL_DFSM_CDCLK_LIMIT_337_5	(3 << 23)
+#define SKL_DFSM_PIPE_A_DISABLE		(1 << 30)
+#define SKL_DFSM_PIPE_B_DISABLE		(1 << 21)
+#define SKL_DFSM_PIPE_C_DISABLE		(1 << 28)
+
+#define GEN7_FF_SLICE_CS_CHICKEN1	_MMIO(0x20e0)
+#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1<<14)
 
 #define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
 #define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
 
+#define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
+#define GEN8_CS_CHICKEN1		_MMIO(0x2580)
+
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
@@ -6043,6 +6062,8 @@ enum skl_disp_power_wells {
 #define  HDC_FORCE_NON_COHERENT			(1<<4)
 #define  HDC_BARRIER_PERFORMANCE_DISABLE	(1<<10)
 
+#define GEN8_HDC_CHICKEN1			_MMIO(0x7304)
+
 /* GEN9 chicken */
 #define SLICE_ECO_CHICKEN0			_MMIO(0x7308)
 #define   PIXEL_MASK_CAMMING_DISABLE		(1 << 14)
@@ -6773,6 +6794,16 @@ enum skl_disp_power_wells {
 
 #define  VLV_PMWGICZ				_MMIO(0x1300a4)
 
+#define  RC6_LOCATION				_MMIO(0xD40)
+#define	   RC6_CTX_IN_DRAM			(1 << 0)
+#define  RC6_CTX_BASE				_MMIO(0xD48)
+#define    RC6_CTX_BASE_MASK			0xFFFFFFF0
+#define  PWRCTX_MAXCNT_RCSUNIT			_MMIO(0x2054)
+#define  PWRCTX_MAXCNT_VCSUNIT0			_MMIO(0x12054)
+#define  PWRCTX_MAXCNT_BCSUNIT			_MMIO(0x22054)
+#define  PWRCTX_MAXCNT_VECSUNIT			_MMIO(0x1A054)
+#define  PWRCTX_MAXCNT_VCSUNIT1			_MMIO(0x1C054)
+#define    IDLE_TIME_MASK			0xFFFFF
 #define  FORCEWAKE				_MMIO(0xA18C)
 #define  FORCEWAKE_VLV				_MMIO(0x1300b0)
 #define  FORCEWAKE_ACK_VLV			_MMIO(0x1300b4)
@@ -6911,6 +6942,7 @@ enum skl_disp_power_wells {
 #define GEN6_RPDEUC				_MMIO(0xA084)
 #define GEN6_RPDEUCSW				_MMIO(0xA088)
 #define GEN6_RC_STATE				_MMIO(0xA094)
+#define   RC6_STATE				(1 << 18)
 #define GEN6_RC1_WAKE_RATE_LIMIT		_MMIO(0xA098)
 #define GEN6_RC6_WAKE_RATE_LIMIT		_MMIO(0xA09C)
 #define GEN6_RC6pp_WAKE_RATE_LIMIT		_MMIO(0xA0A0)
@@ -7412,6 +7444,8 @@ enum skl_disp_power_wells {
 #define  TRANS_CLK_SEL_DISABLED		(0x0<<29)
 #define  TRANS_CLK_SEL_PORT(x)		(((x)+1)<<29)
 
+#define CDCLK_FREQ			_MMIO(0x46200)
+
 #define _TRANSA_MSA_MISC		0x60410
 #define _TRANSB_MSA_MISC		0x61410
 #define _TRANSC_MSA_MISC		0x62410
@@ -7543,6 +7577,7 @@ enum skl_disp_power_wells {
 #define  DC_STATE_EN_UPTO_DC5_DC6_MASK   0x3
 
 #define  DC_STATE_DEBUG                  _MMIO(0x45520)
+#define  DC_STATE_DEBUG_MASK_CORES	(1<<0)
 #define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1<<1)
 
 /* Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
@@ -8162,4 +8197,11 @@ enum skl_disp_power_wells {
 #define GEN9_VEBOX_MOCS(i)	_MMIO(0xcb00 + (i) * 4)	/* Video MOCS registers */
 #define GEN9_BLT_MOCS(i)	_MMIO(0xcc00 + (i) * 4)	/* Blitter MOCS registers */
 
+/* gamt regs */
+#define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4)
+#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW  0x67F1427F /* max/min for LRA1/2 */
+#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV  0x5FF101FF /* max/min for LRA1/2 */
+#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL  0x67F1427F /*    "        " */
+#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT  0x5FF101FF /*    "        " */
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index a8af594fb..34e061a9e 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -92,7 +92,7 @@ static void i915_restore_display(struct drm_device *dev)
 	}
 
 	/* only restore FBC info on the platform that supports FBC*/
-	intel_fbc_disable(dev_priv);
+	intel_fbc_global_disable(dev_priv);
 
 	/* restore FBC interval */
 	if (HAS_FBC(dev) && INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev))
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 37e3f0ddf..c6188dddb 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -164,7 +164,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	     struct bin_attribute *attr, char *buf,
 	     loff_t offset, size_t count)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct drm_minor *dminor = dev_to_drm_minor(dev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
@@ -200,7 +200,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	      struct bin_attribute *attr, char *buf,
 	      loff_t offset, size_t count)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct drm_minor *dminor = dev_to_drm_minor(dev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
@@ -521,7 +521,7 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 				loff_t off, size_t count)
 {
 
-	struct device *kdev = container_of(kobj, struct device, kobj);
+	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
 	struct i915_error_state_file_priv error_priv;
@@ -556,7 +556,7 @@ static ssize_t error_state_write(struct file *file, struct kobject *kobj,
 				 struct bin_attribute *attr, char *buf,
 				 loff_t off, size_t count)
 {
-	struct device *kdev = container_of(kobj, struct device, kobj);
+	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
 	int ret;
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 52b2d4099..fa09e5581 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -175,35 +175,24 @@ TRACE_EVENT(i915_vma_unbind,
 		      __entry->obj, __entry->offset, __entry->size, __entry->vm)
 );
 
-#define VM_TO_TRACE_NAME(vm) \
-	(i915_is_ggtt(vm) ? "G" : \
-		      "P")
-
-DECLARE_EVENT_CLASS(i915_va,
-	TP_PROTO(struct i915_address_space *vm, u64 start, u64 length, const char *name),
-	TP_ARGS(vm, start, length, name),
+TRACE_EVENT(i915_va_alloc,
+	TP_PROTO(struct i915_vma *vma),
+	TP_ARGS(vma),
 
 	TP_STRUCT__entry(
 		__field(struct i915_address_space *, vm)
 		__field(u64, start)
 		__field(u64, end)
-		__string(name, name)
 	),
 
 	TP_fast_assign(
-		__entry->vm = vm;
-		__entry->start = start;
-		__entry->end = start + length - 1;
-		__assign_str(name, name);
+		__entry->vm = vma->vm;
+		__entry->start = vma->node.start;
+		__entry->end = vma->node.start + vma->node.size - 1;
 	),
 
-	TP_printk("vm=%p (%s), 0x%llx-0x%llx",
-		  __entry->vm, __get_str(name),  __entry->start, __entry->end)
-);
-
-DEFINE_EVENT(i915_va, i915_va_alloc,
-	     TP_PROTO(struct i915_address_space *vm, u64 start, u64 length, const char *name),
-	     TP_ARGS(vm, start, length, name)
+	TP_printk("vm=%p (%c), 0x%llx-0x%llx",
+		  __entry->vm, i915_is_ggtt(__entry->vm) ? 'G' : 'P',  __entry->start, __entry->end)
 );
 
 DECLARE_EVENT_CLASS(i915_px_entry,
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index d0b1c9afa..e7c1686e4 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -96,7 +96,9 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->update_pipe = false;
 	crtc_state->disable_lp_wm = false;
 	crtc_state->disable_cxsr = false;
-	crtc_state->wm_changed = false;
+	crtc_state->update_wm_pre = false;
+	crtc_state->update_wm_post = false;
+	crtc_state->fb_changed = false;
 
 	return &crtc_state->base;
 }
@@ -308,5 +310,5 @@ void intel_atomic_state_clear(struct drm_atomic_state *s)
 {
 	struct intel_atomic_state *state = to_intel_atomic_state(s);
 	drm_atomic_state_default_clear(&state->base);
-	state->dpll_set = false;
+	state->dpll_set = state->modeset = false;
 }
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index c6bb0fc1e..7de7721f6 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -152,9 +152,9 @@ static int intel_plane_atomic_check(struct drm_plane *plane,
 	intel_state->clip.x1 = 0;
 	intel_state->clip.y1 = 0;
 	intel_state->clip.x2 =
-		crtc_state->base.active ? crtc_state->pipe_src_w : 0;
+		crtc_state->base.enable ? crtc_state->pipe_src_w : 0;
 	intel_state->clip.y2 =
-		crtc_state->base.active ? crtc_state->pipe_src_h : 0;
+		crtc_state->base.enable ? crtc_state->pipe_src_h : 0;
 
 	if (state->fb && intel_rotation_90_or_270(state->rotation)) {
 		if (!(state->fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
@@ -194,8 +194,14 @@ static void intel_plane_atomic_update(struct drm_plane *plane,
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_plane_state *intel_state =
 		to_intel_plane_state(plane->state);
-
-	intel_plane->commit_plane(plane, intel_state);
+	struct drm_crtc *crtc = plane->state->crtc ?: old_state->crtc;
+
+	if (intel_state->visible)
+		intel_plane->update_plane(plane,
+					  to_intel_crtc_state(crtc->state),
+					  intel_state);
+	else
+		intel_plane->disable_plane(plane, crtc);
 }
 
 const struct drm_plane_helper_funcs intel_plane_helper_funcs = {
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 30f921421..7d281b400 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -262,8 +262,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder)
 	tmp |= AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_UPPER_N_MASK;
 	tmp &= ~AUD_CONFIG_LOWER_N_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT) ||
-	    intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DP_MST))
+	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	I915_WRITE(HSW_AUD_CFG(pipe), tmp);
 
@@ -476,8 +475,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector,
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
 	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT) ||
-	    intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DP_MST))
+	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	else
 		tmp |= audio_config_hdmi_pixel_clock(adjusted_mode);
@@ -515,8 +513,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 
 	/* ELD Conn_Type */
 	connector->eld[5] &= ~(3 << 2);
-	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_DP_MST))
+	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT))
 		connector->eld[5] |= (1 << 2);
 
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index eba3e0f87..bf62a19c8 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -31,11 +31,49 @@
 #include "i915_drv.h"
 #include "intel_bios.h"
 
+/**
+ * DOC: Video BIOS Table (VBT)
+ *
+ * The Video BIOS Table, or VBT, provides platform and board specific
+ * configuration information to the driver that is not discoverable or available
+ * through other means. The configuration is mostly related to display
+ * hardware. The VBT is available via the ACPI OpRegion or, on older systems, in
+ * the PCI ROM.
+ *
+ * The VBT consists of a VBT Header (defined as &struct vbt_header), a BDB
+ * Header (&struct bdb_header), and a number of BIOS Data Blocks (BDB) that
+ * contain the actual configuration information. The VBT Header, and thus the
+ * VBT, begins with "$VBT" signature. The VBT Header contains the offset of the
+ * BDB Header. The data blocks are concatenated after the BDB Header. The data
+ * blocks have a 1-byte Block ID, 2-byte Block Size, and Block Size bytes of
+ * data. (Block 53, the MIPI Sequence Block is an exception.)
+ *
+ * The driver parses the VBT during load. The relevant information is stored in
+ * driver private data for ease of use, and the actual VBT is not read after
+ * that.
+ */
+
 #define	SLAVE_ADDR1	0x70
 #define	SLAVE_ADDR2	0x72
 
 static int panel_type;
 
+/* Get BDB block size given a pointer to Block ID. */
+static u32 _get_blocksize(const u8 *block_base)
+{
+	/* The MIPI Sequence Block v3+ has a separate size field. */
+	if (*block_base == BDB_MIPI_SEQUENCE && *(block_base + 3) >= 3)
+		return *((const u32 *)(block_base + 4));
+	else
+		return *((const u16 *)(block_base + 1));
+}
+
+/* Get BDB block size give a pointer to data after Block ID and Block Size. */
+static u32 get_blocksize(const void *block_data)
+{
+	return _get_blocksize(block_data - 3);
+}
+
 static const void *
 find_section(const void *_bdb, int section_id)
 {
@@ -52,14 +90,8 @@ find_section(const void *_bdb, int section_id)
 	/* walk the sections looking for section_id */
 	while (index + 3 < total) {
 		current_id = *(base + index);
-		index++;
-
-		current_size = *((const u16 *)(base + index));
-		index += 2;
-
-		/* The MIPI Sequence Block v3+ has a separate size field. */
-		if (current_id == BDB_MIPI_SEQUENCE && *(base + index) >= 3)
-			current_size = *((const u32 *)(base + index + 1));
+		current_size = _get_blocksize(base + index);
+		index += 3;
 
 		if (index + current_size > total)
 			return NULL;
@@ -73,16 +105,6 @@ find_section(const void *_bdb, int section_id)
 	return NULL;
 }
 
-static u16
-get_blocksize(const void *p)
-{
-	u16 *block_ptr, block_size;
-
-	block_ptr = (u16 *)((char *)p - 2);
-	block_size = *block_ptr;
-	return block_size;
-}
-
 static void
 fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode,
 			const struct lvds_dvo_timing *dvo_timing)
@@ -675,84 +697,13 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	dev_priv->vbt.psr.tp2_tp3_wakeup_time = psr_table->tp2_tp3_wakeup_time;
 }
 
-static u8 *goto_next_sequence(u8 *data, int *size)
-{
-	u16 len;
-	int tmp = *size;
-
-	if (--tmp < 0)
-		return NULL;
-
-	/* goto first element */
-	data++;
-	while (1) {
-		switch (*data) {
-		case MIPI_SEQ_ELEM_SEND_PKT:
-			/*
-			 * skip by this element payload size
-			 * skip elem id, command flag and data type
-			 */
-			tmp -= 5;
-			if (tmp < 0)
-				return NULL;
-
-			data += 3;
-			len = *((u16 *)data);
-
-			tmp -= len;
-			if (tmp < 0)
-				return NULL;
-
-			/* skip by len */
-			data = data + 2 + len;
-			break;
-		case MIPI_SEQ_ELEM_DELAY:
-			/* skip by elem id, and delay is 4 bytes */
-			tmp -= 5;
-			if (tmp < 0)
-				return NULL;
-
-			data += 5;
-			break;
-		case MIPI_SEQ_ELEM_GPIO:
-			tmp -= 3;
-			if (tmp < 0)
-				return NULL;
-
-			data += 3;
-			break;
-		default:
-			DRM_ERROR("Unknown element\n");
-			return NULL;
-		}
-
-		/* end of sequence ? */
-		if (*data == 0)
-			break;
-	}
-
-	/* goto next sequence or end of block byte */
-	if (--tmp < 0)
-		return NULL;
-
-	data++;
-
-	/* update amount of data left for the sequence block to be parsed */
-	*size = tmp;
-	return data;
-}
-
 static void
-parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
+parse_mipi_config(struct drm_i915_private *dev_priv,
+		  const struct bdb_header *bdb)
 {
 	const struct bdb_mipi_config *start;
-	const struct bdb_mipi_sequence *sequence;
 	const struct mipi_config *config;
 	const struct mipi_pps_data *pps;
-	u8 *data;
-	const u8 *seq_data;
-	int i, panel_id, seq_size;
-	u16 block_size;
 
 	/* parse MIPI blocks only if LFP type is MIPI */
 	if (!dev_priv->vbt.has_mipi)
@@ -798,104 +749,233 @@ parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 
 	/* We have mandatory mipi config blocks. Initialize as generic panel */
 	dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID;
+}
 
-	/* Check if we have sequence block as well */
-	sequence = find_section(bdb, BDB_MIPI_SEQUENCE);
-	if (!sequence) {
-		DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n");
-		return;
+/* Find the sequence block and size for the given panel. */
+static const u8 *
+find_panel_sequence_block(const struct bdb_mipi_sequence *sequence,
+			  u16 panel_id, u32 *seq_size)
+{
+	u32 total = get_blocksize(sequence);
+	const u8 *data = &sequence->data[0];
+	u8 current_id;
+	u32 current_size;
+	int header_size = sequence->version >= 3 ? 5 : 3;
+	int index = 0;
+	int i;
+
+	/* skip new block size */
+	if (sequence->version >= 3)
+		data += 4;
+
+	for (i = 0; i < MAX_MIPI_CONFIGURATIONS && index < total; i++) {
+		if (index + header_size > total) {
+			DRM_ERROR("Invalid sequence block (header)\n");
+			return NULL;
+		}
+
+		current_id = *(data + index);
+		if (sequence->version >= 3)
+			current_size = *((const u32 *)(data + index + 1));
+		else
+			current_size = *((const u16 *)(data + index + 1));
+
+		index += header_size;
+
+		if (index + current_size > total) {
+			DRM_ERROR("Invalid sequence block\n");
+			return NULL;
+		}
+
+		if (current_id == panel_id) {
+			*seq_size = current_size;
+			return data + index;
+		}
+
+		index += current_size;
 	}
 
-	/* Fail gracefully for forward incompatible sequence block. */
-	if (sequence->version >= 3) {
-		DRM_ERROR("Unable to parse MIPI Sequence Block v3+\n");
-		return;
+	DRM_ERROR("Sequence block detected but no valid configuration\n");
+
+	return NULL;
+}
+
+static int goto_next_sequence(const u8 *data, int index, int total)
+{
+	u16 len;
+
+	/* Skip Sequence Byte. */
+	for (index = index + 1; index < total; index += len) {
+		u8 operation_byte = *(data + index);
+		index++;
+
+		switch (operation_byte) {
+		case MIPI_SEQ_ELEM_END:
+			return index;
+		case MIPI_SEQ_ELEM_SEND_PKT:
+			if (index + 4 > total)
+				return 0;
+
+			len = *((const u16 *)(data + index + 2)) + 4;
+			break;
+		case MIPI_SEQ_ELEM_DELAY:
+			len = 4;
+			break;
+		case MIPI_SEQ_ELEM_GPIO:
+			len = 2;
+			break;
+		case MIPI_SEQ_ELEM_I2C:
+			if (index + 7 > total)
+				return 0;
+			len = *(data + index + 6) + 7;
+			break;
+		default:
+			DRM_ERROR("Unknown operation byte\n");
+			return 0;
+		}
 	}
 
-	DRM_DEBUG_DRIVER("Found MIPI sequence block\n");
+	return 0;
+}
 
-	block_size = get_blocksize(sequence);
+static int goto_next_sequence_v3(const u8 *data, int index, int total)
+{
+	int seq_end;
+	u16 len;
+	u32 size_of_sequence;
 
 	/*
-	 * parse the sequence block for individual sequences
+	 * Could skip sequence based on Size of Sequence alone, but also do some
+	 * checking on the structure.
 	 */
-	dev_priv->vbt.dsi.seq_version = sequence->version;
+	if (total < 5) {
+		DRM_ERROR("Too small sequence size\n");
+		return 0;
+	}
 
-	seq_data = &sequence->data[0];
+	/* Skip Sequence Byte. */
+	index++;
 
 	/*
-	 * sequence block is variable length and hence we need to parse and
-	 * get the sequence data for specific panel id
+	 * Size of Sequence. Excludes the Sequence Byte and the size itself,
+	 * includes MIPI_SEQ_ELEM_END byte, excludes the final MIPI_SEQ_END
+	 * byte.
 	 */
-	for (i = 0; i < MAX_MIPI_CONFIGURATIONS; i++) {
-		panel_id = *seq_data;
-		seq_size = *((u16 *) (seq_data + 1));
-		if (panel_id == panel_type)
-			break;
+	size_of_sequence = *((const uint32_t *)(data + index));
+	index += 4;
 
-		/* skip the sequence including seq header of 3 bytes */
-		seq_data = seq_data + 3 + seq_size;
-		if ((seq_data - &sequence->data[0]) > block_size) {
-			DRM_ERROR("Sequence start is beyond sequence block size, corrupted sequence block\n");
-			return;
+	seq_end = index + size_of_sequence;
+	if (seq_end > total) {
+		DRM_ERROR("Invalid sequence size\n");
+		return 0;
+	}
+
+	for (; index < total; index += len) {
+		u8 operation_byte = *(data + index);
+		index++;
+
+		if (operation_byte == MIPI_SEQ_ELEM_END) {
+			if (index != seq_end) {
+				DRM_ERROR("Invalid element structure\n");
+				return 0;
+			}
+			return index;
+		}
+
+		len = *(data + index);
+		index++;
+
+		/*
+		 * FIXME: Would be nice to check elements like for v1/v2 in
+		 * goto_next_sequence() above.
+		 */
+		switch (operation_byte) {
+		case MIPI_SEQ_ELEM_SEND_PKT:
+		case MIPI_SEQ_ELEM_DELAY:
+		case MIPI_SEQ_ELEM_GPIO:
+		case MIPI_SEQ_ELEM_I2C:
+		case MIPI_SEQ_ELEM_SPI:
+		case MIPI_SEQ_ELEM_PMIC:
+			break;
+		default:
+			DRM_ERROR("Unknown operation byte %u\n",
+				  operation_byte);
+			break;
 		}
 	}
 
-	if (i == MAX_MIPI_CONFIGURATIONS) {
-		DRM_ERROR("Sequence block detected but no valid configuration\n");
+	return 0;
+}
+
+static void
+parse_mipi_sequence(struct drm_i915_private *dev_priv,
+		    const struct bdb_header *bdb)
+{
+	const struct bdb_mipi_sequence *sequence;
+	const u8 *seq_data;
+	u32 seq_size;
+	u8 *data;
+	int index = 0;
+
+	/* Only our generic panel driver uses the sequence block. */
+	if (dev_priv->vbt.dsi.panel_id != MIPI_DSI_GENERIC_PANEL_ID)
+		return;
+
+	sequence = find_section(bdb, BDB_MIPI_SEQUENCE);
+	if (!sequence) {
+		DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n");
 		return;
 	}
 
-	/* check if found sequence is completely within the sequence block
-	 * just being paranoid */
-	if (seq_size > block_size) {
-		DRM_ERROR("Corrupted sequence/size, bailing out\n");
+	/* Fail gracefully for forward incompatible sequence block. */
+	if (sequence->version >= 4) {
+		DRM_ERROR("Unable to parse MIPI Sequence Block v%u\n",
+			  sequence->version);
 		return;
 	}
 
-	/* skip the panel id(1 byte) and seq size(2 bytes) */
-	dev_priv->vbt.dsi.data = kmemdup(seq_data + 3, seq_size, GFP_KERNEL);
-	if (!dev_priv->vbt.dsi.data)
+	DRM_DEBUG_DRIVER("Found MIPI sequence block v%u\n", sequence->version);
+
+	seq_data = find_panel_sequence_block(sequence, panel_type, &seq_size);
+	if (!seq_data)
 		return;
 
-	/*
-	 * loop into the sequence data and split into multiple sequneces
-	 * There are only 5 types of sequences as of now
-	 */
-	data = dev_priv->vbt.dsi.data;
-	dev_priv->vbt.dsi.size = seq_size;
+	data = kmemdup(seq_data, seq_size, GFP_KERNEL);
+	if (!data)
+		return;
 
-	/* two consecutive 0x00 indicate end of all sequences */
-	while (1) {
-		int seq_id = *data;
-		if (MIPI_SEQ_MAX > seq_id && seq_id > MIPI_SEQ_UNDEFINED) {
-			dev_priv->vbt.dsi.sequence[seq_id] = data;
-			DRM_DEBUG_DRIVER("Found mipi sequence - %d\n", seq_id);
-		} else {
-			DRM_ERROR("undefined sequence\n");
+	/* Parse the sequences, store pointers to each sequence. */
+	for (;;) {
+		u8 seq_id = *(data + index);
+		if (seq_id == MIPI_SEQ_END)
+			break;
+
+		if (seq_id >= MIPI_SEQ_MAX) {
+			DRM_ERROR("Unknown sequence %u\n", seq_id);
 			goto err;
 		}
 
-		/* partial parsing to skip elements */
-		data = goto_next_sequence(data, &seq_size);
+		dev_priv->vbt.dsi.sequence[seq_id] = data + index;
 
-		if (data == NULL) {
-			DRM_ERROR("Sequence elements going beyond block itself. Sequence block parsing failed\n");
+		if (sequence->version >= 3)
+			index = goto_next_sequence_v3(data, index, seq_size);
+		else
+			index = goto_next_sequence(data, index, seq_size);
+		if (!index) {
+			DRM_ERROR("Invalid sequence %u\n", seq_id);
 			goto err;
 		}
-
-		if (*data == 0)
-			break; /* end of sequence reached */
 	}
 
-	DRM_DEBUG_DRIVER("MIPI related vbt parsing complete\n");
+	dev_priv->vbt.dsi.data = data;
+	dev_priv->vbt.dsi.size = seq_size;
+	dev_priv->vbt.dsi.seq_version = sequence->version;
+
+	DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n");
 	return;
-err:
-	kfree(dev_priv->vbt.dsi.data);
-	dev_priv->vbt.dsi.data = NULL;
 
-	/* error during parsing so set all pointers to null
-	 * because of partial parsing */
+err:
+	kfree(data);
 	memset(dev_priv->vbt.dsi.sequence, 0, sizeof(dev_priv->vbt.dsi.sequence));
 }
 
@@ -1088,7 +1168,12 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("No general definition block is found, no devices defined.\n");
 		return;
 	}
-	if (bdb->version < 195) {
+	if (bdb->version < 106) {
+		expected_size = 22;
+	} else if (bdb->version < 109) {
+		expected_size = 27;
+	} else if (bdb->version < 195) {
+		BUILD_BUG_ON(sizeof(struct old_child_dev_config) != 33);
 		expected_size = sizeof(struct old_child_dev_config);
 	} else if (bdb->version == 195) {
 		expected_size = 37;
@@ -1101,18 +1186,18 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 				 bdb->version, expected_size);
 	}
 
-	/* The legacy sized child device config is the minimum we need. */
-	if (p_defs->child_dev_size < sizeof(struct old_child_dev_config)) {
-		DRM_ERROR("Child device config size %u is too small.\n",
-			  p_defs->child_dev_size);
-		return;
-	}
-
 	/* Flag an error for unexpected size, but continue anyway. */
 	if (p_defs->child_dev_size != expected_size)
 		DRM_ERROR("Unexpected child device config size %u (expected %u for VBT version %u)\n",
 			  p_defs->child_dev_size, expected_size, bdb->version);
 
+	/* The legacy sized child device config is the minimum we need. */
+	if (p_defs->child_dev_size < sizeof(struct old_child_dev_config)) {
+		DRM_DEBUG_KMS("Child device config size %u is too small.\n",
+			      p_defs->child_dev_size);
+		return;
+	}
+
 	/* get the block size of general definitions */
 	block_size = get_blocksize(p_defs);
 	/* get the number of child device */
@@ -1285,7 +1370,7 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
 
 /**
  * intel_bios_init - find VBT and initialize settings from the BIOS
- * @dev: DRM device
+ * @dev_priv: i915 device instance
  *
  * Loads the Video BIOS and checks that the VBT exists.  Sets scratch registers
  * to appropriate values.
@@ -1337,7 +1422,8 @@ intel_bios_init(struct drm_i915_private *dev_priv)
 	parse_driver_features(dev_priv, bdb);
 	parse_edp(dev_priv, bdb);
 	parse_psr(dev_priv, bdb);
-	parse_mipi(dev_priv, bdb);
+	parse_mipi_config(dev_priv, bdb);
+	parse_mipi_sequence(dev_priv, bdb);
 	parse_ddi_ports(dev_priv, bdb);
 
 	if (bios)
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index 54eac1003..350d4e0f7 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -25,25 +25,43 @@
  *
  */
 
-#ifndef _I830_BIOS_H_
-#define _I830_BIOS_H_
-
+#ifndef _INTEL_BIOS_H_
+#define _INTEL_BIOS_H_
+
+/**
+ * struct vbt_header - VBT Header structure
+ * @signature:		VBT signature, always starts with "$VBT"
+ * @version:		Version of this structure
+ * @header_size:	Size of this structure
+ * @vbt_size:		Size of VBT (VBT Header, BDB Header and data blocks)
+ * @vbt_checksum:	Checksum
+ * @reserved0:		Reserved
+ * @bdb_offset:		Offset of &struct bdb_header from beginning of VBT
+ * @aim_offset:		Offsets of add-in data blocks from beginning of VBT
+ */
 struct vbt_header {
-	u8 signature[20];		/**< Always starts with 'VBT$' */
-	u16 version;			/**< decimal */
-	u16 header_size;		/**< in bytes */
-	u16 vbt_size;			/**< in bytes */
+	u8 signature[20];
+	u16 version;
+	u16 header_size;
+	u16 vbt_size;
 	u8 vbt_checksum;
 	u8 reserved0;
-	u32 bdb_offset;			/**< from beginning of VBT */
-	u32 aim_offset[4];		/**< from beginning of VBT */
+	u32 bdb_offset;
+	u32 aim_offset[4];
 } __packed;
 
+/**
+ * struct bdb_header - BDB Header structure
+ * @signature:		BDB signature "BIOS_DATA_BLOCK"
+ * @version:		Version of the data block definitions
+ * @header_size:	Size of this structure
+ * @bdb_size:		Size of BDB (BDB Header and data blocks)
+ */
 struct bdb_header {
-	u8 signature[16];		/**< Always 'BIOS_DATA_BLOCK' */
-	u16 version;			/**< decimal */
-	u16 header_size;		/**< in bytes */
-	u16 bdb_size;			/**< in bytes */
+	u8 signature[16];
+	u16 version;
+	u16 header_size;
+	u16 bdb_size;
 } __packed;
 
 /* strictly speaking, this is a "skip" block, but it has interesting info */
@@ -936,21 +954,29 @@ struct bdb_mipi_sequence {
 
 /* MIPI Sequnece Block definitions */
 enum mipi_seq {
-	MIPI_SEQ_UNDEFINED = 0,
+	MIPI_SEQ_END = 0,
 	MIPI_SEQ_ASSERT_RESET,
 	MIPI_SEQ_INIT_OTP,
 	MIPI_SEQ_DISPLAY_ON,
 	MIPI_SEQ_DISPLAY_OFF,
 	MIPI_SEQ_DEASSERT_RESET,
+	MIPI_SEQ_BACKLIGHT_ON,		/* sequence block v2+ */
+	MIPI_SEQ_BACKLIGHT_OFF,		/* sequence block v2+ */
+	MIPI_SEQ_TEAR_ON,		/* sequence block v2+ */
+	MIPI_SEQ_TEAR_OFF,		/* sequence block v3+ */
+	MIPI_SEQ_POWER_ON,		/* sequence block v3+ */
+	MIPI_SEQ_POWER_OFF,		/* sequence block v3+ */
 	MIPI_SEQ_MAX
 };
 
 enum mipi_seq_element {
-	MIPI_SEQ_ELEM_UNDEFINED = 0,
+	MIPI_SEQ_ELEM_END = 0,
 	MIPI_SEQ_ELEM_SEND_PKT,
 	MIPI_SEQ_ELEM_DELAY,
 	MIPI_SEQ_ELEM_GPIO,
-	MIPI_SEQ_ELEM_STATUS,
+	MIPI_SEQ_ELEM_I2C,		/* sequence block v2+ */
+	MIPI_SEQ_ELEM_SPI,		/* sequence block v3+ */
+	MIPI_SEQ_ELEM_PMIC,		/* sequence block v3+ */
 	MIPI_SEQ_ELEM_MAX
 };
 
@@ -965,4 +991,4 @@ enum mipi_gpio_pin_index {
 	MIPI_GPIO_MAX
 };
 
-#endif /* _I830_BIOS_H_ */
+#endif /* _INTEL_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index a7b4a524f..036429236 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -213,9 +213,7 @@ static void pch_post_disable_crt(struct intel_encoder *encoder)
 
 static void intel_enable_crt(struct intel_encoder *encoder)
 {
-	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-
-	intel_crt_set_dpms(encoder, crt->connector->base.dpms);
+	intel_crt_set_dpms(encoder, DRM_MODE_DPMS_ON);
 }
 
 static enum drm_mode_status
@@ -223,6 +221,7 @@ intel_crt_mode_valid(struct drm_connector *connector,
 		     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
+	int max_dotclk = to_i915(dev)->max_dotclk_freq;
 
 	int max_clock = 0;
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
@@ -238,6 +237,9 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	if (mode->clock > max_clock)
 		return MODE_CLOCK_HIGH;
 
+	if (mode->clock > max_dotclk)
+		return MODE_CLOCK_HIGH;
+
 	/* The FDI receiver on LPT only supports 8bpc and only has 2 lanes. */
 	if (HAS_PCH_LPT(dev) &&
 	    (ironlake_get_lanes_required(mode->clock, 270000, 24) > 2))
@@ -255,8 +257,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	/* LPT FDI RX only supports 8bpc. */
-	if (HAS_PCH_LPT(dev))
+	if (HAS_PCH_LPT(dev)) {
+		if (pipe_config->bw_constrained && pipe_config->pipe_bpp < 24) {
+			DRM_DEBUG_KMS("LPT only supports 24bpp\n");
+			return false;
+		}
+
 		pipe_config->pipe_bpp = 24;
+	}
 
 	/* FDI must always be 2.7 GHz */
 	if (HAS_DDI(dev)) {
@@ -476,11 +484,10 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 }
 
 static enum drm_connector_status
-intel_crt_load_detect(struct intel_crt *crt)
+intel_crt_load_detect(struct intel_crt *crt, uint32_t pipe)
 {
 	struct drm_device *dev = crt->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t pipe = to_intel_crtc(crt->base.base.crtc)->pipe;
 	uint32_t save_bclrpat;
 	uint32_t save_vtotal;
 	uint32_t vtotal, vactive;
@@ -649,7 +656,8 @@ intel_crt_detect(struct drm_connector *connector, bool force)
 		if (intel_crt_detect_ddc(connector))
 			status = connector_status_connected;
 		else if (INTEL_INFO(dev)->gen < 4)
-			status = intel_crt_load_detect(crt);
+			status = intel_crt_load_detect(crt,
+				to_intel_crtc(connector->state->crtc)->pipe);
 		else
 			status = connector_status_unknown;
 		intel_release_load_detect_pipe(connector, &tmp, &ctx);
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 9eb96b197..b1a547378 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -44,6 +44,8 @@
 #define I915_CSR_SKL "/*(DEBLOBBED)*/"
 #define I915_CSR_BXT "/*(DEBLOBBED)*/"
 
+#define FIRMWARE_URL  "/*(DEBLOBBED)*/"
+
 /*(DEBLOBBED)*/
 
 #define SKL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 23)
@@ -217,19 +219,19 @@ static const struct stepping_info *intel_get_stepping_info(struct drm_device *de
  * Everytime display comes back from low power state this function is called to
  * copy the firmware from internal memory to registers.
  */
-void intel_csr_load_program(struct drm_i915_private *dev_priv)
+bool intel_csr_load_program(struct drm_i915_private *dev_priv)
 {
 	u32 *payload = dev_priv->csr.dmc_payload;
 	uint32_t i, fw_size;
 
 	if (!IS_GEN9(dev_priv)) {
 		DRM_ERROR("No CSR support available for this platform\n");
-		return;
+		return false;
 	}
 
 	if (!dev_priv->csr.dmc_payload) {
 		DRM_ERROR("Tried to program CSR with empty payload\n");
-		return;
+		return false;
 	}
 
 	fw_size = dev_priv->csr.dmc_fw_size;
@@ -242,6 +244,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv)
 	}
 
 	dev_priv->csr.dc_state = 0;
+
+	return true;
 }
 
 static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
@@ -280,10 +284,11 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 
 	csr->version = css_header->version;
 
-	if (IS_SKYLAKE(dev) && csr->version < SKL_CSR_VERSION_REQUIRED) {
+	if ((IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) &&
+	    csr->version < SKL_CSR_VERSION_REQUIRED) {
 		DRM_INFO("Refusing to load old Skylake DMC firmware v%u.%u,"
 			 " please upgrade to v%u.%u or later"
-			 " [https://01.org/linuxgraphics/intel-linux-graphics-firmwares].\n",
+			   " [" FIRMWARE_URL "].\n",
 			 CSR_VERSION_MAJOR(csr->version),
 			 CSR_VERSION_MINOR(csr->version),
 			 CSR_VERSION_MAJOR(SKL_CSR_VERSION_REQUIRED),
@@ -401,7 +406,10 @@ out:
 			 CSR_VERSION_MAJOR(csr->version),
 			 CSR_VERSION_MINOR(csr->version));
 	} else {
-		DRM_ERROR("Failed to load DMC firmware, disabling rpm\n");
+		dev_notice(dev_priv->dev->dev,
+			   "Failed to load DMC firmware"
+			   " [" FIRMWARE_URL "],"
+			   " disabling runtime power management.\n");
 	}
 
 	release_firmware(fw);
@@ -423,7 +431,7 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv)
 	if (!HAS_CSR(dev_priv))
 		return;
 
-	if (IS_SKYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
 		csr->fw_path = I915_CSR_SKL;
 	else if (IS_BROXTON(dev_priv))
 		csr->fw_path = I915_CSR_BXT;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 33b8e0a2b..50f5b0c97 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -133,38 +133,38 @@ static const struct ddi_buf_trans skl_ddi_translations_dp[] = {
 	{ 0x00002016, 0x000000A0, 0x0 },
 	{ 0x00005012, 0x0000009B, 0x0 },
 	{ 0x00007011, 0x00000088, 0x0 },
-	{ 0x80009010, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80009010, 0x000000C0, 0x1 },
 	{ 0x00002016, 0x0000009B, 0x0 },
 	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x80007011, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80007011, 0x000000C0, 0x1 },
 	{ 0x00002016, 0x000000DF, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80005012, 0x000000C0, 0x1 },
 };
 
 /* Skylake U */
 static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = {
 	{ 0x0000201B, 0x000000A2, 0x0 },
 	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x00007011, 0x00000087, 0x0 },
-	{ 0x80009010, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80007011, 0x000000CD, 0x0 },
+	{ 0x80009010, 0x000000C0, 0x1 },
 	{ 0x0000201B, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
-	{ 0x80007011, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80005012, 0x000000C0, 0x1 },
+	{ 0x80007011, 0x000000C0, 0x1 },
 	{ 0x00002016, 0x00000088, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x1 },	/* Uses I_boost level 0x1 */
+	{ 0x80005012, 0x000000C0, 0x1 },
 };
 
 /* Skylake Y */
 static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = {
 	{ 0x00000018, 0x000000A2, 0x0 },
 	{ 0x00005012, 0x00000088, 0x0 },
-	{ 0x00007011, 0x00000087, 0x0 },
-	{ 0x80009010, 0x000000C0, 0x3 },	/* Uses I_boost level 0x3 */
+	{ 0x80007011, 0x000000CD, 0x0 },
+	{ 0x80009010, 0x000000C0, 0x3 },
 	{ 0x00000018, 0x0000009D, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },	/* Uses I_boost level 0x3 */
-	{ 0x80007011, 0x000000C0, 0x3 },	/* Uses I_boost level 0x3 */
+	{ 0x80005012, 0x000000C0, 0x3 },
+	{ 0x80007011, 0x000000C0, 0x3 },
 	{ 0x00000018, 0x00000088, 0x0 },
-	{ 0x80005012, 0x000000C0, 0x3 },	/* Uses I_boost level 0x3 */
+	{ 0x80005012, 0x000000C0, 0x3 },
 };
 
 /*
@@ -226,26 +226,26 @@ static const struct ddi_buf_trans skl_ddi_translations_hdmi[] = {
 	{ 0x00000018, 0x000000A1, 0x0 },
 	{ 0x00000018, 0x00000098, 0x0 },
 	{ 0x00004013, 0x00000088, 0x0 },
-	{ 0x00006012, 0x00000087, 0x0 },
+	{ 0x80006012, 0x000000CD, 0x1 },
 	{ 0x00000018, 0x000000DF, 0x0 },
-	{ 0x00003015, 0x00000087, 0x0 },	/* Default */
-	{ 0x00003015, 0x000000C7, 0x0 },
-	{ 0x00000018, 0x000000C7, 0x0 },
+	{ 0x80003015, 0x000000CD, 0x1 },	/* Default */
+	{ 0x80003015, 0x000000C0, 0x1 },
+	{ 0x80000018, 0x000000C0, 0x1 },
 };
 
 /* Skylake Y */
 static const struct ddi_buf_trans skl_y_ddi_translations_hdmi[] = {
 	{ 0x00000018, 0x000000A1, 0x0 },
 	{ 0x00005012, 0x000000DF, 0x0 },
-	{ 0x00007011, 0x00000084, 0x0 },
+	{ 0x80007011, 0x000000CB, 0x3 },
 	{ 0x00000018, 0x000000A4, 0x0 },
 	{ 0x00000018, 0x0000009D, 0x0 },
 	{ 0x00004013, 0x00000080, 0x0 },
-	{ 0x00006013, 0x000000C7, 0x0 },
+	{ 0x80006013, 0x000000C0, 0x3 },
 	{ 0x00000018, 0x0000008A, 0x0 },
-	{ 0x00003015, 0x000000C7, 0x0 },	/* Default */
-	{ 0x80003015, 0x000000C7, 0x7 },	/* Uses I_boost level 0x7 */
-	{ 0x00000018, 0x000000C7, 0x0 },
+	{ 0x80003015, 0x000000C0, 0x3 },	/* Default */
+	{ 0x80003015, 0x000000C0, 0x3 },
+	{ 0x80000018, 0x000000C0, 0x3 },
 };
 
 struct bxt_ddi_buf_trans {
@@ -301,8 +301,8 @@ static const struct bxt_ddi_buf_trans bxt_ddi_translations_hdmi[] = {
 	{ 154, 0x9A, 1, 128, true },	/* 9:	1200		0   */
 };
 
-static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level,
-				    enum port port, int type);
+static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv,
+				    u32 level, enum port port, int type);
 
 static void ddi_get_encoder_port(struct intel_encoder *intel_encoder,
 				 struct intel_digital_port **dig_port,
@@ -342,81 +342,50 @@ enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder)
 	return port;
 }
 
-static bool
-intel_dig_port_supports_hdmi(const struct intel_digital_port *intel_dig_port)
-{
-	return i915_mmio_reg_valid(intel_dig_port->hdmi.hdmi_reg);
-}
-
-static const struct ddi_buf_trans *skl_get_buf_trans_dp(struct drm_device *dev,
-							int *n_entries)
+static const struct ddi_buf_trans *
+skl_get_buf_trans_dp(struct drm_i915_private *dev_priv, int *n_entries)
 {
-	const struct ddi_buf_trans *ddi_translations;
-
-	if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) {
-		ddi_translations = skl_y_ddi_translations_dp;
+	if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) {
 		*n_entries = ARRAY_SIZE(skl_y_ddi_translations_dp);
-	} else if (IS_SKL_ULT(dev) || IS_KBL_ULT(dev)) {
-		ddi_translations = skl_u_ddi_translations_dp;
+		return skl_y_ddi_translations_dp;
+	} else if (IS_SKL_ULT(dev_priv) || IS_KBL_ULT(dev_priv)) {
 		*n_entries = ARRAY_SIZE(skl_u_ddi_translations_dp);
+		return skl_u_ddi_translations_dp;
 	} else {
-		ddi_translations = skl_ddi_translations_dp;
 		*n_entries = ARRAY_SIZE(skl_ddi_translations_dp);
+		return skl_ddi_translations_dp;
 	}
-
-	return ddi_translations;
 }
 
-static const struct ddi_buf_trans *skl_get_buf_trans_edp(struct drm_device *dev,
-							 int *n_entries)
+static const struct ddi_buf_trans *
+skl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const struct ddi_buf_trans *ddi_translations;
-
-	if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) {
-		if (dev_priv->edp_low_vswing) {
-			ddi_translations = skl_y_ddi_translations_edp;
+	if (dev_priv->edp_low_vswing) {
+		if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) {
 			*n_entries = ARRAY_SIZE(skl_y_ddi_translations_edp);
-		} else {
-			ddi_translations = skl_y_ddi_translations_dp;
-			*n_entries = ARRAY_SIZE(skl_y_ddi_translations_dp);
-		}
-	} else if (IS_SKL_ULT(dev) || IS_KBL_ULT(dev)) {
-		if (dev_priv->edp_low_vswing) {
-			ddi_translations = skl_u_ddi_translations_edp;
+			return skl_y_ddi_translations_edp;
+		} else if (IS_SKL_ULT(dev_priv) || IS_KBL_ULT(dev_priv)) {
 			*n_entries = ARRAY_SIZE(skl_u_ddi_translations_edp);
+			return skl_u_ddi_translations_edp;
 		} else {
-			ddi_translations = skl_u_ddi_translations_dp;
-			*n_entries = ARRAY_SIZE(skl_u_ddi_translations_dp);
-		}
-	} else {
-		if (dev_priv->edp_low_vswing) {
-			ddi_translations = skl_ddi_translations_edp;
 			*n_entries = ARRAY_SIZE(skl_ddi_translations_edp);
-		} else {
-			ddi_translations = skl_ddi_translations_dp;
-			*n_entries = ARRAY_SIZE(skl_ddi_translations_dp);
+			return skl_ddi_translations_edp;
 		}
 	}
 
-	return ddi_translations;
+	return skl_get_buf_trans_dp(dev_priv, n_entries);
 }
 
 static const struct ddi_buf_trans *
-skl_get_buf_trans_hdmi(struct drm_device *dev,
-		       int *n_entries)
+skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries)
 {
-	const struct ddi_buf_trans *ddi_translations;
-
-	if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) {
-		ddi_translations = skl_y_ddi_translations_hdmi;
+	if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) {
 		*n_entries = ARRAY_SIZE(skl_y_ddi_translations_hdmi);
+		return skl_y_ddi_translations_hdmi;
 	} else {
-		ddi_translations = skl_ddi_translations_hdmi;
 		*n_entries = ARRAY_SIZE(skl_ddi_translations_hdmi);
+		return skl_ddi_translations_hdmi;
 	}
-
-	return ddi_translations;
 }
 
 /*
@@ -426,42 +395,52 @@ skl_get_buf_trans_hdmi(struct drm_device *dev,
  * in either FDI or DP modes only, as HDMI connections will work with both
  * of those
  */
-static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
-				      bool supports_hdmi)
+void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 iboost_bit = 0;
 	int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry,
 	    size;
-	int hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+	int hdmi_level;
+	enum port port;
 	const struct ddi_buf_trans *ddi_translations_fdi;
 	const struct ddi_buf_trans *ddi_translations_dp;
 	const struct ddi_buf_trans *ddi_translations_edp;
 	const struct ddi_buf_trans *ddi_translations_hdmi;
 	const struct ddi_buf_trans *ddi_translations;
 
-	if (IS_BROXTON(dev)) {
-		if (!supports_hdmi)
+	port = intel_ddi_get_encoder_port(encoder);
+	hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+
+	if (IS_BROXTON(dev_priv)) {
+		if (encoder->type != INTEL_OUTPUT_HDMI)
 			return;
 
 		/* Vswing programming for HDMI */
-		bxt_ddi_vswing_sequence(dev, hdmi_level, port,
+		bxt_ddi_vswing_sequence(dev_priv, hdmi_level, port,
 					INTEL_OUTPUT_HDMI);
 		return;
-	} else if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+	}
+
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		ddi_translations_fdi = NULL;
 		ddi_translations_dp =
-				skl_get_buf_trans_dp(dev, &n_dp_entries);
+				skl_get_buf_trans_dp(dev_priv, &n_dp_entries);
 		ddi_translations_edp =
-				skl_get_buf_trans_edp(dev, &n_edp_entries);
+				skl_get_buf_trans_edp(dev_priv, &n_edp_entries);
 		ddi_translations_hdmi =
-				skl_get_buf_trans_hdmi(dev, &n_hdmi_entries);
+				skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries);
 		hdmi_default_entry = 8;
 		/* If we're boosting the current, set bit 31 of trans1 */
 		if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level ||
 		    dev_priv->vbt.ddi_port_info[port].dp_boost_level)
 			iboost_bit = 1<<31;
-	} else if (IS_BROADWELL(dev)) {
+
+		if (WARN_ON(encoder->type == INTEL_OUTPUT_EDP &&
+			    port != PORT_A && port != PORT_E &&
+			    n_edp_entries > 9))
+			n_edp_entries = 9;
+	} else if (IS_BROADWELL(dev_priv)) {
 		ddi_translations_fdi = bdw_ddi_translations_fdi;
 		ddi_translations_dp = bdw_ddi_translations_dp;
 
@@ -478,7 +457,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
 		n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
 		n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
 		hdmi_default_entry = 7;
-	} else if (IS_HASWELL(dev)) {
+	} else if (IS_HASWELL(dev_priv)) {
 		ddi_translations_fdi = hsw_ddi_translations_fdi;
 		ddi_translations_dp = hsw_ddi_translations_dp;
 		ddi_translations_edp = hsw_ddi_translations_dp;
@@ -498,30 +477,18 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
 		hdmi_default_entry = 7;
 	}
 
-	switch (port) {
-	case PORT_A:
+	switch (encoder->type) {
+	case INTEL_OUTPUT_EDP:
 		ddi_translations = ddi_translations_edp;
 		size = n_edp_entries;
 		break;
-	case PORT_B:
-	case PORT_C:
+	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_HDMI:
 		ddi_translations = ddi_translations_dp;
 		size = n_dp_entries;
 		break;
-	case PORT_D:
-		if (intel_dp_is_edp(dev, PORT_D)) {
-			ddi_translations = ddi_translations_edp;
-			size = n_edp_entries;
-		} else {
-			ddi_translations = ddi_translations_dp;
-			size = n_dp_entries;
-		}
-		break;
-	case PORT_E:
-		if (ddi_translations_fdi)
-			ddi_translations = ddi_translations_fdi;
-		else
-			ddi_translations = ddi_translations_dp;
+	case INTEL_OUTPUT_ANALOG:
+		ddi_translations = ddi_translations_fdi;
 		size = n_dp_entries;
 		break;
 	default:
@@ -535,7 +502,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
 			   ddi_translations[i].trans2);
 	}
 
-	if (!supports_hdmi)
+	if (encoder->type != INTEL_OUTPUT_HDMI)
 		return;
 
 	/* Choose a good default if VBT is badly populated */
@@ -550,37 +517,6 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
 		   ddi_translations_hdmi[hdmi_level].trans2);
 }
 
-/* Program DDI buffers translations for DP. By default, program ports A-D in DP
- * mode and port E for FDI.
- */
-void intel_prepare_ddi(struct drm_device *dev)
-{
-	struct intel_encoder *intel_encoder;
-	bool visited[I915_MAX_PORTS] = { 0, };
-
-	if (!HAS_DDI(dev))
-		return;
-
-	for_each_intel_encoder(dev, intel_encoder) {
-		struct intel_digital_port *intel_dig_port;
-		enum port port;
-		bool supports_hdmi;
-
-		if (intel_encoder->type == INTEL_OUTPUT_DSI)
-			continue;
-
-		ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port);
-		if (visited[port])
-			continue;
-
-		supports_hdmi = intel_dig_port &&
-				intel_dig_port_supports_hdmi(intel_dig_port);
-
-		intel_prepare_ddi_buffers(dev, port, supports_hdmi);
-		visited[port] = true;
-	}
-}
-
 static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 				    enum port port)
 {
@@ -609,8 +545,14 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_encoder *encoder;
 	u32 temp, i, rx_ctl_val;
 
+	for_each_encoder_on_crtc(dev, crtc, encoder) {
+		WARN_ON(encoder->type != INTEL_OUTPUT_ANALOG);
+		intel_prepare_ddi_buffer(encoder);
+	}
+
 	/* Set the FDI_RX_MISC pwrdn lanes and the 2 workarounds listed at the
 	 * mode set "sequence for CRT port" document:
 	 * - TP1 to TP2 time with the default value
@@ -1612,8 +1554,10 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc,
 		}
 
 		cfgcr1 = cfgcr2 = 0;
-	} else /* eDP */
+	} else if (intel_encoder->type == INTEL_OUTPUT_EDP) {
 		return true;
+	} else
+		return false;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
@@ -2117,10 +2061,9 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc)
 			   TRANS_CLK_SEL_DISABLED);
 }
 
-static void skl_ddi_set_iboost(struct drm_device *dev, u32 level,
-			       enum port port, int type)
+static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
+			       u32 level, enum port port, int type)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	const struct ddi_buf_trans *ddi_translations;
 	uint8_t iboost;
 	uint8_t dp_iboost, hdmi_iboost;
@@ -2135,21 +2078,26 @@ static void skl_ddi_set_iboost(struct drm_device *dev, u32 level,
 		if (dp_iboost) {
 			iboost = dp_iboost;
 		} else {
-			ddi_translations = skl_get_buf_trans_dp(dev, &n_entries);
+			ddi_translations = skl_get_buf_trans_dp(dev_priv, &n_entries);
 			iboost = ddi_translations[level].i_boost;
 		}
 	} else if (type == INTEL_OUTPUT_EDP) {
 		if (dp_iboost) {
 			iboost = dp_iboost;
 		} else {
-			ddi_translations = skl_get_buf_trans_edp(dev, &n_entries);
+			ddi_translations = skl_get_buf_trans_edp(dev_priv, &n_entries);
+
+			if (WARN_ON(port != PORT_A &&
+				    port != PORT_E && n_entries > 9))
+				n_entries = 9;
+
 			iboost = ddi_translations[level].i_boost;
 		}
 	} else if (type == INTEL_OUTPUT_HDMI) {
 		if (hdmi_iboost) {
 			iboost = hdmi_iboost;
 		} else {
-			ddi_translations = skl_get_buf_trans_hdmi(dev, &n_entries);
+			ddi_translations = skl_get_buf_trans_hdmi(dev_priv, &n_entries);
 			iboost = ddi_translations[level].i_boost;
 		}
 	} else {
@@ -2174,10 +2122,9 @@ static void skl_ddi_set_iboost(struct drm_device *dev, u32 level,
 	I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg);
 }
 
-static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level,
-				    enum port port, int type)
+static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv,
+				    u32 level, enum port port, int type)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	const struct bxt_ddi_buf_trans *ddi_translations;
 	u32 n_entries, i;
 	uint32_t val;
@@ -2292,7 +2239,7 @@ static uint32_t translate_signal_level(int signal_levels)
 uint32_t ddi_signal_levels(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dport->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
 	struct intel_encoder *encoder = &dport->base;
 	uint8_t train_set = intel_dp->train_set[0];
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
@@ -2302,10 +2249,10 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp)
 
 	level = translate_signal_level(signal_levels);
 
-	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev))
-		skl_ddi_set_iboost(dev, level, port, encoder->type);
-	else if (IS_BROXTON(dev))
-		bxt_ddi_vswing_sequence(dev, level, port, encoder->type);
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+		skl_ddi_set_iboost(dev_priv, level, port, encoder->type);
+	else if (IS_BROXTON(dev_priv))
+		bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type);
 
 	return DDI_BUF_TRANS_SELECT(level);
 }
@@ -2357,12 +2304,18 @@ void intel_ddi_clk_select(struct intel_encoder *encoder,
 static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
-	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	int type = intel_encoder->type;
-	int hdmi_level;
+
+	if (type == INTEL_OUTPUT_HDMI) {
+		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+		intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
+	}
+
+	intel_prepare_ddi_buffer(intel_encoder);
 
 	if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
@@ -2380,17 +2333,11 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 		intel_dp_start_link_train(intel_dp);
-		if (port != PORT_A || INTEL_INFO(dev)->gen >= 9)
+		if (port != PORT_A || INTEL_INFO(dev_priv)->gen >= 9)
 			intel_dp_stop_link_train(intel_dp);
 	} else if (type == INTEL_OUTPUT_HDMI) {
 		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 
-		if (IS_BROXTON(dev)) {
-			hdmi_level = dev_priv->vbt.
-				ddi_port_info[port].hdmi_level_shift;
-			bxt_ddi_vswing_sequence(dev, hdmi_level, port,
-					INTEL_OUTPUT_HDMI);
-		}
 		intel_hdmi->set_infoframes(encoder,
 					   crtc->config->has_hdmi_sink,
 					   &crtc->config->base.adjusted_mode);
@@ -2434,6 +2381,12 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
 					DPLL_CTRL2_DDI_CLK_OFF(port)));
 	else if (INTEL_INFO(dev)->gen < 9)
 		I915_WRITE(PORT_CLK_SEL(port), PORT_CLK_SEL_NONE);
+
+	if (type == INTEL_OUTPUT_HDMI) {
+		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+		intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
+	}
 }
 
 static void intel_enable_ddi(struct intel_encoder *intel_encoder)
@@ -3165,23 +3118,6 @@ void intel_ddi_fdi_disable(struct drm_crtc *crtc)
 	I915_WRITE(FDI_RX_CTL(PIPE_A), val);
 }
 
-bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
-				 struct intel_crtc *intel_crtc)
-{
-	u32 temp;
-
-	if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
-		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
-
-		intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
-
-		if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe))
-			return true;
-	}
-
-	return false;
-}
-
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config)
 {
@@ -3242,8 +3178,11 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		break;
 	}
 
-	pipe_config->has_audio =
-		intel_ddi_is_audio_enabled(dev_priv, intel_crtc);
+	if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
+		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
+		if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe))
+			pipe_config->has_audio = true;
+	}
 
 	if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp &&
 	    pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) {
@@ -3332,6 +3271,33 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	struct intel_encoder *intel_encoder;
 	struct drm_encoder *encoder;
 	bool init_hdmi, init_dp;
+	int max_lanes;
+
+	if (I915_READ(DDI_BUF_CTL(PORT_A)) & DDI_A_4_LANES) {
+		switch (port) {
+		case PORT_A:
+			max_lanes = 4;
+			break;
+		case PORT_E:
+			max_lanes = 0;
+			break;
+		default:
+			max_lanes = 4;
+			break;
+		}
+	} else {
+		switch (port) {
+		case PORT_A:
+			max_lanes = 2;
+			break;
+		case PORT_E:
+			max_lanes = 2;
+			break;
+		default:
+			max_lanes = 4;
+			break;
+		}
+	}
 
 	init_hdmi = (dev_priv->vbt.ddi_port_info[port].supports_dvi ||
 		     dev_priv->vbt.ddi_port_info[port].supports_hdmi);
@@ -3377,9 +3343,12 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 		if (!(intel_dig_port->saved_port_bits & DDI_A_4_LANES)) {
 			DRM_DEBUG_KMS("BXT BIOS forgot to set DDI_A_4_LANES for port A; fixing\n");
 			intel_dig_port->saved_port_bits |= DDI_A_4_LANES;
+			max_lanes = 4;
 		}
 	}
 
+	intel_dig_port->max_lanes = max_lanes;
+
 	intel_encoder->type = INTEL_OUTPUT_UNKNOWN;
 	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
 	intel_encoder->cloneable = 0;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c023a04c4..7741efbd5 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -85,8 +85,6 @@ static const uint32_t intel_cursor_formats[] = {
 	DRM_FORMAT_ARGB8888,
 };
 
-static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
-
 static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config);
 static void ironlake_pch_clock_get(struct intel_crtc *crtc,
@@ -1152,11 +1150,6 @@ static void intel_wait_for_pipe_off(struct intel_crtc *crtc)
 	}
 }
 
-static const char *state_string(bool enabled)
-{
-	return enabled ? "on" : "off";
-}
-
 /* Only for pre-ILK configs */
 void assert_pll(struct drm_i915_private *dev_priv,
 		enum pipe pipe, bool state)
@@ -1168,7 +1161,7 @@ void assert_pll(struct drm_i915_private *dev_priv,
 	cur_state = !!(val & DPLL_VCO_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "PLL state assertion failure (expected %s, current %s)\n",
-	     state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 
 /* XXX: the dsi pll is shared between MIPI DSI ports */
@@ -1184,7 +1177,7 @@ static void assert_dsi_pll(struct drm_i915_private *dev_priv, bool state)
 	cur_state = val & DSI_PLL_VCO_EN;
 	I915_STATE_WARN(cur_state != state,
 	     "DSI PLL state assertion failure (expected %s, current %s)\n",
-	     state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 #define assert_dsi_pll_enabled(d) assert_dsi_pll(d, true)
 #define assert_dsi_pll_disabled(d) assert_dsi_pll(d, false)
@@ -1208,14 +1201,13 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
 	bool cur_state;
 	struct intel_dpll_hw_state hw_state;
 
-	if (WARN (!pll,
-		  "asserting DPLL %s with no DPLL\n", state_string(state)))
+	if (WARN(!pll, "asserting DPLL %s with no DPLL\n", onoff(state)))
 		return;
 
 	cur_state = pll->get_hw_state(dev_priv, pll, &hw_state);
 	I915_STATE_WARN(cur_state != state,
 	     "%s assertion failure (expected %s, current %s)\n",
-	     pll->name, state_string(state), state_string(cur_state));
+			pll->name, onoff(state), onoff(cur_state));
 }
 
 static void assert_fdi_tx(struct drm_i915_private *dev_priv,
@@ -1235,7 +1227,7 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 	}
 	I915_STATE_WARN(cur_state != state,
 	     "FDI TX state assertion failure (expected %s, current %s)\n",
-	     state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 #define assert_fdi_tx_enabled(d, p) assert_fdi_tx(d, p, true)
 #define assert_fdi_tx_disabled(d, p) assert_fdi_tx(d, p, false)
@@ -1250,7 +1242,7 @@ static void assert_fdi_rx(struct drm_i915_private *dev_priv,
 	cur_state = !!(val & FDI_RX_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "FDI RX state assertion failure (expected %s, current %s)\n",
-	     state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 #define assert_fdi_rx_enabled(d, p) assert_fdi_rx(d, p, true)
 #define assert_fdi_rx_disabled(d, p) assert_fdi_rx(d, p, false)
@@ -1282,7 +1274,7 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 	cur_state = !!(val & FDI_RX_PLL_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "FDI RX PLL assertion failure (expected %s, current %s)\n",
-	     state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 
 void assert_panel_unlocked(struct drm_i915_private *dev_priv,
@@ -1340,7 +1332,7 @@ static void assert_cursor(struct drm_i915_private *dev_priv,
 
 	I915_STATE_WARN(cur_state != state,
 	     "cursor on pipe %c assertion failure (expected %s, current %s)\n",
-	     pipe_name(pipe), state_string(state), state_string(cur_state));
+			pipe_name(pipe), onoff(state), onoff(cur_state));
 }
 #define assert_cursor_enabled(d, p) assert_cursor(d, p, true)
 #define assert_cursor_disabled(d, p) assert_cursor(d, p, false)
@@ -1370,7 +1362,7 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 
 	I915_STATE_WARN(cur_state != state,
 	     "pipe %c assertion failure (expected %s, current %s)\n",
-	     pipe_name(pipe), state_string(state), state_string(cur_state));
+			pipe_name(pipe), onoff(state), onoff(cur_state));
 }
 
 static void assert_plane(struct drm_i915_private *dev_priv,
@@ -1383,7 +1375,7 @@ static void assert_plane(struct drm_i915_private *dev_priv,
 	cur_state = !!(val & DISPLAY_PLANE_ENABLE);
 	I915_STATE_WARN(cur_state != state,
 	     "plane %c assertion failure (expected %s, current %s)\n",
-	     plane_name(plane), state_string(state), state_string(cur_state));
+			plane_name(plane), onoff(state), onoff(cur_state));
 }
 
 #define assert_plane_enabled(d, p) assert_plane(d, p, true)
@@ -2156,6 +2148,17 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
 
 	I915_WRITE(reg, val | PIPECONF_ENABLE);
 	POSTING_READ(reg);
+
+	/*
+	 * Until the pipe starts DSL will read as 0, which would cause
+	 * an apparent vblank timestamp jump, which messes up also the
+	 * frame count when it's derived from the timestamps. So let's
+	 * wait for the pipe to start properly before we call
+	 * drm_crtc_vblank_on()
+	 */
+	if (dev->max_vblank_count == 0 &&
+	    wait_for(intel_get_crtc_scanline(crtc) != crtc->scanline_offset, 50))
+		DRM_ERROR("pipe %c didn't start\n", pipe_name(pipe));
 }
 
 /**
@@ -2217,67 +2220,75 @@ static bool need_vtd_wa(struct drm_device *dev)
 	return false;
 }
 
-unsigned int
-intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
-		  uint64_t fb_format_modifier, unsigned int plane)
+static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv)
 {
-	unsigned int tile_height;
-	uint32_t pixel_bytes;
+	return IS_GEN2(dev_priv) ? 2048 : 4096;
+}
 
-	switch (fb_format_modifier) {
+static unsigned int intel_tile_width(const struct drm_i915_private *dev_priv,
+				     uint64_t fb_modifier, unsigned int cpp)
+{
+	switch (fb_modifier) {
 	case DRM_FORMAT_MOD_NONE:
-		tile_height = 1;
-		break;
+		return cpp;
 	case I915_FORMAT_MOD_X_TILED:
-		tile_height = IS_GEN2(dev) ? 16 : 8;
-		break;
+		if (IS_GEN2(dev_priv))
+			return 128;
+		else
+			return 512;
 	case I915_FORMAT_MOD_Y_TILED:
-		tile_height = 32;
-		break;
+		if (IS_GEN2(dev_priv) || HAS_128_BYTE_Y_TILING(dev_priv))
+			return 128;
+		else
+			return 512;
 	case I915_FORMAT_MOD_Yf_TILED:
-		pixel_bytes = drm_format_plane_cpp(pixel_format, plane);
-		switch (pixel_bytes) {
-		default:
+		switch (cpp) {
 		case 1:
-			tile_height = 64;
-			break;
+			return 64;
 		case 2:
 		case 4:
-			tile_height = 32;
-			break;
+			return 128;
 		case 8:
-			tile_height = 16;
-			break;
 		case 16:
-			WARN_ONCE(1,
-				  "128-bit pixels are not supported for display!");
-			tile_height = 16;
-			break;
+			return 256;
+		default:
+			MISSING_CASE(cpp);
+			return cpp;
 		}
 		break;
 	default:
-		MISSING_CASE(fb_format_modifier);
-		tile_height = 1;
-		break;
+		MISSING_CASE(fb_modifier);
+		return cpp;
 	}
+}
 
-	return tile_height;
+unsigned int intel_tile_height(const struct drm_i915_private *dev_priv,
+			       uint64_t fb_modifier, unsigned int cpp)
+{
+	if (fb_modifier == DRM_FORMAT_MOD_NONE)
+		return 1;
+	else
+		return intel_tile_size(dev_priv) /
+			intel_tile_width(dev_priv, fb_modifier, cpp);
 }
 
 unsigned int
 intel_fb_align_height(struct drm_device *dev, unsigned int height,
-		      uint32_t pixel_format, uint64_t fb_format_modifier)
+		      uint32_t pixel_format, uint64_t fb_modifier)
 {
-	return ALIGN(height, intel_tile_height(dev, pixel_format,
-					       fb_format_modifier, 0));
+	unsigned int cpp = drm_format_plane_cpp(pixel_format, 0);
+	unsigned int tile_height = intel_tile_height(to_i915(dev), fb_modifier, cpp);
+
+	return ALIGN(height, tile_height);
 }
 
 static void
 intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb,
 			const struct drm_plane_state *plane_state)
 {
-	struct intel_rotation_info *info = &view->params.rotation_info;
-	unsigned int tile_height, tile_pitch;
+	struct drm_i915_private *dev_priv = to_i915(fb->dev);
+	struct intel_rotation_info *info = &view->params.rotated;
+	unsigned int tile_size, tile_width, tile_height, cpp;
 
 	*view = i915_ggtt_view_normal;
 
@@ -2295,26 +2306,28 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb,
 	info->uv_offset = fb->offsets[1];
 	info->fb_modifier = fb->modifier[0];
 
-	tile_height = intel_tile_height(fb->dev, fb->pixel_format,
-					fb->modifier[0], 0);
-	tile_pitch = PAGE_SIZE / tile_height;
-	info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_pitch);
+	tile_size = intel_tile_size(dev_priv);
+
+	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	tile_width = intel_tile_width(dev_priv, fb->modifier[0], cpp);
+	tile_height = tile_size / tile_width;
+
+	info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_width);
 	info->height_pages = DIV_ROUND_UP(fb->height, tile_height);
-	info->size = info->width_pages * info->height_pages * PAGE_SIZE;
+	info->size = info->width_pages * info->height_pages * tile_size;
 
 	if (info->pixel_format == DRM_FORMAT_NV12) {
-		tile_height = intel_tile_height(fb->dev, fb->pixel_format,
-						fb->modifier[0], 1);
-		tile_pitch = PAGE_SIZE / tile_height;
-		info->width_pages_uv = DIV_ROUND_UP(fb->pitches[0], tile_pitch);
-		info->height_pages_uv = DIV_ROUND_UP(fb->height / 2,
-						     tile_height);
-		info->size_uv = info->width_pages_uv * info->height_pages_uv *
-				PAGE_SIZE;
+		cpp = drm_format_plane_cpp(fb->pixel_format, 1);
+		tile_width = intel_tile_width(dev_priv, fb->modifier[1], cpp);
+		tile_height = tile_size / tile_width;
+
+		info->width_pages_uv = DIV_ROUND_UP(fb->pitches[1], tile_width);
+		info->height_pages_uv = DIV_ROUND_UP(fb->height / 2, tile_height);
+		info->size_uv = info->width_pages_uv * info->height_pages_uv * tile_size;
 	}
 }
 
-static unsigned int intel_linear_alignment(struct drm_i915_private *dev_priv)
+static unsigned int intel_linear_alignment(const struct drm_i915_private *dev_priv)
 {
 	if (INTEL_INFO(dev_priv)->gen >= 9)
 		return 256 * 1024;
@@ -2327,6 +2340,25 @@ static unsigned int intel_linear_alignment(struct drm_i915_private *dev_priv)
 		return 0;
 }
 
+static unsigned int intel_surf_alignment(const struct drm_i915_private *dev_priv,
+					 uint64_t fb_modifier)
+{
+	switch (fb_modifier) {
+	case DRM_FORMAT_MOD_NONE:
+		return intel_linear_alignment(dev_priv);
+	case I915_FORMAT_MOD_X_TILED:
+		if (INTEL_INFO(dev_priv)->gen >= 9)
+			return 256 * 1024;
+		return 0;
+	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Yf_TILED:
+		return 1 * 1024 * 1024;
+	default:
+		MISSING_CASE(fb_modifier);
+		return 0;
+	}
+}
+
 int
 intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 			   struct drm_framebuffer *fb,
@@ -2341,29 +2373,7 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	switch (fb->modifier[0]) {
-	case DRM_FORMAT_MOD_NONE:
-		alignment = intel_linear_alignment(dev_priv);
-		break;
-	case I915_FORMAT_MOD_X_TILED:
-		if (INTEL_INFO(dev)->gen >= 9)
-			alignment = 256 * 1024;
-		else {
-			/* pin() will align the object as required by fence */
-			alignment = 0;
-		}
-		break;
-	case I915_FORMAT_MOD_Y_TILED:
-	case I915_FORMAT_MOD_Yf_TILED:
-		if (WARN_ONCE(INTEL_INFO(dev)->gen < 9,
-			  "Y tiling bo slipped through, driver bug!\n"))
-			return -EINVAL;
-		alignment = 1 * 1024 * 1024;
-		break;
-	default:
-		MISSING_CASE(fb->modifier[0]);
-		return -EINVAL;
-	}
+	alignment = intel_surf_alignment(dev_priv, fb->modifier[0]);
 
 	intel_fill_fb_ggtt_view(&view, fb, plane_state);
 
@@ -2441,22 +2451,27 @@ static void intel_unpin_fb_obj(struct drm_framebuffer *fb,
 
 /* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel
  * is assumed to be a power-of-two. */
-unsigned long intel_gen4_compute_page_offset(struct drm_i915_private *dev_priv,
-					     int *x, int *y,
-					     unsigned int tiling_mode,
-					     unsigned int cpp,
-					     unsigned int pitch)
-{
-	if (tiling_mode != I915_TILING_NONE) {
+u32 intel_compute_tile_offset(struct drm_i915_private *dev_priv,
+			      int *x, int *y,
+			      uint64_t fb_modifier,
+			      unsigned int cpp,
+			      unsigned int pitch)
+{
+	if (fb_modifier != DRM_FORMAT_MOD_NONE) {
+		unsigned int tile_size, tile_width, tile_height;
 		unsigned int tile_rows, tiles;
 
-		tile_rows = *y / 8;
-		*y %= 8;
+		tile_size = intel_tile_size(dev_priv);
+		tile_width = intel_tile_width(dev_priv, fb_modifier, cpp);
+		tile_height = tile_size / tile_width;
+
+		tile_rows = *y / tile_height;
+		*y %= tile_height;
 
-		tiles = *x / (512/cpp);
-		*x %= 512/cpp;
+		tiles = *x / (tile_width/cpp);
+		*x %= tile_width/cpp;
 
-		return tile_rows * pitch * 8 + tiles * 4096;
+		return tile_rows * pitch * tile_height + tiles * tile_size;
 	} else {
 		unsigned int alignment = intel_linear_alignment(dev_priv) - 1;
 		unsigned int offset;
@@ -2539,12 +2554,16 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 	if (size_aligned * 2 > dev_priv->gtt.stolen_usable_size)
 		return false;
 
+	mutex_lock(&dev->struct_mutex);
+
 	obj = i915_gem_object_create_stolen_for_preallocated(dev,
 							     base_aligned,
 							     base_aligned,
 							     size_aligned);
-	if (!obj)
+	if (!obj) {
+		mutex_unlock(&dev->struct_mutex);
 		return false;
+	}
 
 	obj->tiling_mode = plane_config->tiling;
 	if (obj->tiling_mode == I915_TILING_X)
@@ -2557,12 +2576,12 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 	mode_cmd.modifier[0] = fb->modifier[0];
 	mode_cmd.flags = DRM_MODE_FB_MODIFIERS;
 
-	mutex_lock(&dev->struct_mutex);
 	if (intel_framebuffer_init(dev, to_intel_framebuffer(fb),
 				   &mode_cmd, obj)) {
 		DRM_DEBUG_KMS("intel fb init failed\n");
 		goto out_unref_obj;
 	}
+
 	mutex_unlock(&dev->struct_mutex);
 
 	DRM_DEBUG_KMS("initial plane fb obj %p\n", obj);
@@ -2601,6 +2620,8 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	struct drm_plane_state *plane_state = primary->state;
 	struct drm_crtc_state *crtc_state = intel_crtc->base.state;
 	struct intel_plane *intel_plane = to_intel_plane(primary);
+	struct intel_plane_state *intel_state =
+		to_intel_plane_state(plane_state);
 	struct drm_framebuffer *fb;
 
 	if (!plane_config->fb)
@@ -2662,6 +2683,15 @@ valid_fb:
 	plane_state->crtc_w = fb->width;
 	plane_state->crtc_h = fb->height;
 
+	intel_state->src.x1 = plane_state->src_x;
+	intel_state->src.y1 = plane_state->src_y;
+	intel_state->src.x2 = plane_state->src_x + plane_state->src_w;
+	intel_state->src.y2 = plane_state->src_y + plane_state->src_h;
+	intel_state->dst.x1 = plane_state->crtc_x;
+	intel_state->dst.y1 = plane_state->crtc_y;
+	intel_state->dst.x2 = plane_state->crtc_x + plane_state->crtc_w;
+	intel_state->dst.y2 = plane_state->crtc_y + plane_state->crtc_h;
+
 	obj = intel_fb_obj(fb);
 	if (obj->tiling_mode != I915_TILING_NONE)
 		dev_priv->preserve_bios_swizzle = true;
@@ -2673,37 +2703,22 @@ valid_fb:
 	obj->frontbuffer_bits |= to_intel_plane(primary)->frontbuffer_bit;
 }
 
-static void i9xx_update_primary_plane(struct drm_crtc *crtc,
-				      struct drm_framebuffer *fb,
-				      int x, int y)
+static void i9xx_update_primary_plane(struct drm_plane *primary,
+				      const struct intel_crtc_state *crtc_state,
+				      const struct intel_plane_state *plane_state)
 {
-	struct drm_device *dev = crtc->dev;
+	struct drm_device *dev = primary->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_plane *primary = crtc->primary;
-	bool visible = to_intel_plane_state(primary->state)->visible;
-	struct drm_i915_gem_object *obj;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int plane = intel_crtc->plane;
-	unsigned long linear_offset;
+	u32 linear_offset;
 	u32 dspcntr;
 	i915_reg_t reg = DSPCNTR(plane);
-	int pixel_size;
-
-	if (!visible || !fb) {
-		I915_WRITE(reg, 0);
-		if (INTEL_INFO(dev)->gen >= 4)
-			I915_WRITE(DSPSURF(plane), 0);
-		else
-			I915_WRITE(DSPADDR(plane), 0);
-		POSTING_READ(reg);
-		return;
-	}
-
-	obj = intel_fb_obj(fb);
-	if (WARN_ON(obj == NULL))
-		return;
-
-	pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	int x = plane_state->src.x1 >> 16;
+	int y = plane_state->src.y1 >> 16;
 
 	dspcntr = DISPPLANE_GAMMA_ENABLE;
 
@@ -2717,13 +2732,13 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc,
 		 * which should always be the user's requested size.
 		 */
 		I915_WRITE(DSPSIZE(plane),
-			   ((intel_crtc->config->pipe_src_h - 1) << 16) |
-			   (intel_crtc->config->pipe_src_w - 1));
+			   ((crtc_state->pipe_src_h - 1) << 16) |
+			   (crtc_state->pipe_src_w - 1));
 		I915_WRITE(DSPPOS(plane), 0);
 	} else if (IS_CHERRYVIEW(dev) && plane == PLANE_B) {
 		I915_WRITE(PRIMSIZE(plane),
-			   ((intel_crtc->config->pipe_src_h - 1) << 16) |
-			   (intel_crtc->config->pipe_src_w - 1));
+			   ((crtc_state->pipe_src_h - 1) << 16) |
+			   (crtc_state->pipe_src_w - 1));
 		I915_WRITE(PRIMPOS(plane), 0);
 		I915_WRITE(PRIMCNSTALPHA(plane), 0);
 	}
@@ -2761,30 +2776,29 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc,
 	if (IS_G4X(dev))
 		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
+	linear_offset = y * fb->pitches[0] + x * cpp;
 
 	if (INTEL_INFO(dev)->gen >= 4) {
 		intel_crtc->dspaddr_offset =
-			intel_gen4_compute_page_offset(dev_priv,
-						       &x, &y, obj->tiling_mode,
-						       pixel_size,
-						       fb->pitches[0]);
+			intel_compute_tile_offset(dev_priv, &x, &y,
+						  fb->modifier[0], cpp,
+						  fb->pitches[0]);
 		linear_offset -= intel_crtc->dspaddr_offset;
 	} else {
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
-	if (crtc->primary->state->rotation == BIT(DRM_ROTATE_180)) {
+	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
 		dspcntr |= DISPPLANE_ROTATE_180;
 
-		x += (intel_crtc->config->pipe_src_w - 1);
-		y += (intel_crtc->config->pipe_src_h - 1);
+		x += (crtc_state->pipe_src_w - 1);
+		y += (crtc_state->pipe_src_h - 1);
 
 		/* Finding the last pixel of the last line of the display
 		data and adding to linear_offset*/
 		linear_offset +=
-			(intel_crtc->config->pipe_src_h - 1) * fb->pitches[0] +
-			(intel_crtc->config->pipe_src_w - 1) * pixel_size;
+			(crtc_state->pipe_src_h - 1) * fb->pitches[0] +
+			(crtc_state->pipe_src_w - 1) * cpp;
 	}
 
 	intel_crtc->adjusted_x = x;
@@ -2803,37 +2817,40 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc,
 	POSTING_READ(reg);
 }
 
-static void ironlake_update_primary_plane(struct drm_crtc *crtc,
-					  struct drm_framebuffer *fb,
-					  int x, int y)
+static void i9xx_disable_primary_plane(struct drm_plane *primary,
+				       struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_plane *primary = crtc->primary;
-	bool visible = to_intel_plane_state(primary->state)->visible;
-	struct drm_i915_gem_object *obj;
 	int plane = intel_crtc->plane;
-	unsigned long linear_offset;
-	u32 dspcntr;
-	i915_reg_t reg = DSPCNTR(plane);
-	int pixel_size;
 
-	if (!visible || !fb) {
-		I915_WRITE(reg, 0);
+	I915_WRITE(DSPCNTR(plane), 0);
+	if (INTEL_INFO(dev_priv)->gen >= 4)
 		I915_WRITE(DSPSURF(plane), 0);
-		POSTING_READ(reg);
-		return;
-	}
-
-	obj = intel_fb_obj(fb);
-	if (WARN_ON(obj == NULL))
-		return;
+	else
+		I915_WRITE(DSPADDR(plane), 0);
+	POSTING_READ(DSPCNTR(plane));
+}
 
-	pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+static void ironlake_update_primary_plane(struct drm_plane *primary,
+					  const struct intel_crtc_state *crtc_state,
+					  const struct intel_plane_state *plane_state)
+{
+	struct drm_device *dev = primary->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	int plane = intel_crtc->plane;
+	u32 linear_offset;
+	u32 dspcntr;
+	i915_reg_t reg = DSPCNTR(plane);
+	int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	int x = plane_state->src.x1 >> 16;
+	int y = plane_state->src.y1 >> 16;
 
 	dspcntr = DISPPLANE_GAMMA_ENABLE;
-
 	dspcntr |= DISPLAY_PLANE_ENABLE;
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
@@ -2868,25 +2885,24 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc,
 	if (!IS_HASWELL(dev) && !IS_BROADWELL(dev))
 		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
+	linear_offset = y * fb->pitches[0] + x * cpp;
 	intel_crtc->dspaddr_offset =
-		intel_gen4_compute_page_offset(dev_priv,
-					       &x, &y, obj->tiling_mode,
-					       pixel_size,
-					       fb->pitches[0]);
+		intel_compute_tile_offset(dev_priv, &x, &y,
+					  fb->modifier[0], cpp,
+					  fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
-	if (crtc->primary->state->rotation == BIT(DRM_ROTATE_180)) {
+	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
 		dspcntr |= DISPPLANE_ROTATE_180;
 
 		if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
-			x += (intel_crtc->config->pipe_src_w - 1);
-			y += (intel_crtc->config->pipe_src_h - 1);
+			x += (crtc_state->pipe_src_w - 1);
+			y += (crtc_state->pipe_src_h - 1);
 
 			/* Finding the last pixel of the last line of the display
 			data and adding to linear_offset*/
 			linear_offset +=
-				(intel_crtc->config->pipe_src_h - 1) * fb->pitches[0] +
-				(intel_crtc->config->pipe_src_w - 1) * pixel_size;
+				(crtc_state->pipe_src_h - 1) * fb->pitches[0] +
+				(crtc_state->pipe_src_w - 1) * cpp;
 		}
 	}
 
@@ -2907,37 +2923,15 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc,
 	POSTING_READ(reg);
 }
 
-u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier,
-			      uint32_t pixel_format)
+u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv,
+			      uint64_t fb_modifier, uint32_t pixel_format)
 {
-	u32 bits_per_pixel = drm_format_plane_cpp(pixel_format, 0) * 8;
-
-	/*
-	 * The stride is either expressed as a multiple of 64 bytes
-	 * chunks for linear buffers or in number of tiles for tiled
-	 * buffers.
-	 */
-	switch (fb_modifier) {
-	case DRM_FORMAT_MOD_NONE:
-		return 64;
-	case I915_FORMAT_MOD_X_TILED:
-		if (INTEL_INFO(dev)->gen == 2)
-			return 128;
-		return 512;
-	case I915_FORMAT_MOD_Y_TILED:
-		/* No need to check for old gens and Y tiling since this is
-		 * about the display engine and those will be blocked before
-		 * we get here.
-		 */
-		return 128;
-	case I915_FORMAT_MOD_Yf_TILED:
-		if (bits_per_pixel == 8)
-			return 64;
-		else
-			return 128;
-	default:
-		MISSING_CASE(fb_modifier);
+	if (fb_modifier == DRM_FORMAT_MOD_NONE) {
 		return 64;
+	} else {
+		int cpp = drm_format_plane_cpp(pixel_format, 0);
+
+		return intel_tile_width(dev_priv, fb_modifier, cpp);
 	}
 }
 
@@ -2960,7 +2954,7 @@ u32 intel_plane_obj_offset(struct intel_plane *intel_plane,
 	offset = vma->node.start;
 
 	if (plane == 1) {
-		offset += vma->ggtt_view.params.rotation_info.uv_start_page *
+		offset += vma->ggtt_view.params.rotated.uv_start_page *
 			  PAGE_SIZE;
 	}
 
@@ -3077,36 +3071,30 @@ u32 skl_plane_ctl_rotation(unsigned int rotation)
 	return 0;
 }
 
-static void skylake_update_primary_plane(struct drm_crtc *crtc,
-					 struct drm_framebuffer *fb,
-					 int x, int y)
+static void skylake_update_primary_plane(struct drm_plane *plane,
+					 const struct intel_crtc_state *crtc_state,
+					 const struct intel_plane_state *plane_state)
 {
-	struct drm_device *dev = crtc->dev;
+	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_plane *plane = crtc->primary;
-	bool visible = to_intel_plane_state(plane->state)->visible;
-	struct drm_i915_gem_object *obj;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int pipe = intel_crtc->pipe;
 	u32 plane_ctl, stride_div, stride;
 	u32 tile_height, plane_offset, plane_size;
-	unsigned int rotation;
+	unsigned int rotation = plane_state->base.rotation;
 	int x_offset, y_offset;
 	u32 surf_addr;
-	struct intel_crtc_state *crtc_state = intel_crtc->config;
-	struct intel_plane_state *plane_state;
-	int src_x = 0, src_y = 0, src_w = 0, src_h = 0;
-	int dst_x = 0, dst_y = 0, dst_w = 0, dst_h = 0;
-	int scaler_id = -1;
-
-	plane_state = to_intel_plane_state(plane->state);
-
-	if (!visible || !fb) {
-		I915_WRITE(PLANE_CTL(pipe, 0), 0);
-		I915_WRITE(PLANE_SURF(pipe, 0), 0);
-		POSTING_READ(PLANE_CTL(pipe, 0));
-		return;
-	}
+	int scaler_id = plane_state->scaler_id;
+	int src_x = plane_state->src.x1 >> 16;
+	int src_y = plane_state->src.y1 >> 16;
+	int src_w = drm_rect_width(&plane_state->src) >> 16;
+	int src_h = drm_rect_height(&plane_state->src) >> 16;
+	int dst_x = plane_state->dst.x1;
+	int dst_y = plane_state->dst.y1;
+	int dst_w = drm_rect_width(&plane_state->dst);
+	int dst_h = drm_rect_height(&plane_state->dst);
 
 	plane_ctl = PLANE_CTL_ENABLE |
 		    PLANE_CTL_PIPE_GAMMA_ENABLE |
@@ -3115,41 +3103,27 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc,
 	plane_ctl |= skl_plane_ctl_format(fb->pixel_format);
 	plane_ctl |= skl_plane_ctl_tiling(fb->modifier[0]);
 	plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE;
-
-	rotation = plane->state->rotation;
 	plane_ctl |= skl_plane_ctl_rotation(rotation);
 
-	obj = intel_fb_obj(fb);
-	stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
+	stride_div = intel_fb_stride_alignment(dev_priv, fb->modifier[0],
 					       fb->pixel_format);
 	surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj, 0);
 
 	WARN_ON(drm_rect_width(&plane_state->src) == 0);
 
-	scaler_id = plane_state->scaler_id;
-	src_x = plane_state->src.x1 >> 16;
-	src_y = plane_state->src.y1 >> 16;
-	src_w = drm_rect_width(&plane_state->src) >> 16;
-	src_h = drm_rect_height(&plane_state->src) >> 16;
-	dst_x = plane_state->dst.x1;
-	dst_y = plane_state->dst.y1;
-	dst_w = drm_rect_width(&plane_state->dst);
-	dst_h = drm_rect_height(&plane_state->dst);
-
-	WARN_ON(x != src_x || y != src_y);
-
 	if (intel_rotation_90_or_270(rotation)) {
+		int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+
 		/* stride = Surface height in tiles */
-		tile_height = intel_tile_height(dev, fb->pixel_format,
-						fb->modifier[0], 0);
+		tile_height = intel_tile_height(dev_priv, fb->modifier[0], cpp);
 		stride = DIV_ROUND_UP(fb->height, tile_height);
-		x_offset = stride * tile_height - y - src_h;
-		y_offset = x;
+		x_offset = stride * tile_height - src_y - src_h;
+		y_offset = src_x;
 		plane_size = (src_w - 1) << 16 | (src_h - 1);
 	} else {
 		stride = fb->pitches[0] / stride_div;
-		x_offset = x;
-		y_offset = y;
+		x_offset = src_x;
+		y_offset = src_y;
 		plane_size = (src_h - 1) << 16 | (src_w - 1);
 	}
 	plane_offset = y_offset << 16 | x_offset;
@@ -3182,20 +3156,27 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc,
 	POSTING_READ(PLANE_SURF(pipe, 0));
 }
 
-/* Assume fb object is pinned & idle & fenced and just update base pointers */
-static int
-intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			   int x, int y, enum mode_set_atomic state)
+static void skylake_disable_primary_plane(struct drm_plane *primary,
+					  struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = to_intel_crtc(crtc)->pipe;
 
-	if (dev_priv->fbc.deactivate)
-		dev_priv->fbc.deactivate(dev_priv);
+	I915_WRITE(PLANE_CTL(pipe, 0), 0);
+	I915_WRITE(PLANE_SURF(pipe, 0), 0);
+	POSTING_READ(PLANE_SURF(pipe, 0));
+}
 
-	dev_priv->display.update_primary_plane(crtc, fb, x, y);
+/* Assume fb object is pinned & idle & fenced and just update base pointers */
+static int
+intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
+			   int x, int y, enum mode_set_atomic state)
+{
+	/* Support for kgdboc is disabled, this needs a major rework. */
+	DRM_ERROR("legacy panic handler not supported any more.\n");
 
-	return 0;
+	return -ENODEV;
 }
 
 static void intel_complete_page_flips(struct drm_device *dev)
@@ -3222,8 +3203,10 @@ static void intel_update_primary_planes(struct drm_device *dev)
 		drm_modeset_lock_crtc(crtc, &plane->base);
 		plane_state = to_intel_plane_state(plane->base.state);
 
-		if (crtc->state->active && plane_state->base.fb)
-			plane->commit_plane(&plane->base, plane_state);
+		if (plane_state->visible)
+			plane->update_plane(&plane->base,
+					    to_intel_crtc_state(crtc->state),
+					    plane_state);
 
 		drm_modeset_unlock_crtc(crtc);
 	}
@@ -4809,18 +4792,15 @@ static void intel_post_plane_update(struct intel_crtc *crtc)
 		to_intel_crtc_state(crtc->base.state);
 	struct drm_device *dev = crtc->base.dev;
 
-	if (atomic->wait_vblank)
-		intel_wait_for_vblank(dev, crtc->pipe);
-
 	intel_frontbuffer_flip(dev, atomic->fb_bits);
 
 	crtc->wm.cxsr_allowed = true;
 
-	if (pipe_config->wm_changed && pipe_config->base.active)
+	if (pipe_config->update_wm_post && pipe_config->base.active)
 		intel_update_watermarks(&crtc->base);
 
 	if (atomic->update_fbc)
-		intel_fbc_update(crtc);
+		intel_fbc_post_update(crtc);
 
 	if (atomic->post_enable_primary)
 		intel_post_enable_primary(&crtc->base);
@@ -4828,29 +4808,42 @@ static void intel_post_plane_update(struct intel_crtc *crtc)
 	memset(atomic, 0, sizeof(*atomic));
 }
 
-static void intel_pre_plane_update(struct intel_crtc *crtc)
+static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc_atomic_commit *atomic = &crtc->atomic;
 	struct intel_crtc_state *pipe_config =
 		to_intel_crtc_state(crtc->base.state);
+	struct drm_atomic_state *old_state = old_crtc_state->base.state;
+	struct drm_plane *primary = crtc->base.primary;
+	struct drm_plane_state *old_pri_state =
+		drm_atomic_get_existing_plane_state(old_state, primary);
+	bool modeset = needs_modeset(&pipe_config->base);
 
-	if (atomic->disable_fbc)
-		intel_fbc_deactivate(crtc);
+	if (atomic->update_fbc)
+		intel_fbc_pre_update(crtc);
 
-	if (crtc->atomic.disable_ips)
-		hsw_disable_ips(crtc);
+	if (old_pri_state) {
+		struct intel_plane_state *primary_state =
+			to_intel_plane_state(primary->state);
+		struct intel_plane_state *old_primary_state =
+			to_intel_plane_state(old_pri_state);
 
-	if (atomic->pre_disable_primary)
-		intel_pre_disable_primary(&crtc->base);
+		if (old_primary_state->visible &&
+		    (modeset || !primary_state->visible))
+			intel_pre_disable_primary(&crtc->base);
+	}
 
 	if (pipe_config->disable_cxsr) {
 		crtc->wm.cxsr_allowed = false;
-		intel_set_memory_cxsr(dev_priv, false);
+
+		if (old_crtc_state->base.active)
+			intel_set_memory_cxsr(dev_priv, false);
 	}
 
-	if (!needs_modeset(&pipe_config->base) && pipe_config->wm_changed)
+	if (!needs_modeset(&pipe_config->base) && pipe_config->update_wm_pre)
 		intel_update_watermarks(&crtc->base);
 }
 
@@ -4948,8 +4941,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	if (intel_crtc->config->has_pch_encoder)
 		intel_wait_for_vblank(dev, pipe);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
-
-	intel_fbc_enable(intel_crtc);
 }
 
 /* IPS only exists on ULT machines and is tied to pipe A. */
@@ -5062,8 +5053,6 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 		intel_wait_for_vblank(dev, hsw_workaround_pipe);
 		intel_wait_for_vblank(dev, hsw_workaround_pipe);
 	}
-
-	intel_fbc_enable(intel_crtc);
 }
 
 static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force)
@@ -5144,8 +5133,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 	}
 
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
-
-	intel_fbc_disable_crtc(intel_crtc);
 }
 
 static void haswell_crtc_disable(struct drm_crtc *crtc)
@@ -5196,8 +5183,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 		intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A,
 						      true);
 	}
-
-	intel_fbc_disable_crtc(intel_crtc);
 }
 
 static void i9xx_pfit_enable(struct intel_crtc *crtc)
@@ -5320,31 +5305,37 @@ intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder)
 	}
 }
 
-static unsigned long get_crtc_power_domains(struct drm_crtc *crtc)
+static unsigned long get_crtc_power_domains(struct drm_crtc *crtc,
+					    struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct intel_encoder *intel_encoder;
+	struct drm_encoder *encoder;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	unsigned long mask;
-	enum transcoder transcoder = intel_crtc->config->cpu_transcoder;
+	enum transcoder transcoder = crtc_state->cpu_transcoder;
 
-	if (!crtc->state->active)
+	if (!crtc_state->base.active)
 		return 0;
 
 	mask = BIT(POWER_DOMAIN_PIPE(pipe));
 	mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
-	if (intel_crtc->config->pch_pfit.enabled ||
-	    intel_crtc->config->pch_pfit.force_thru)
+	if (crtc_state->pch_pfit.enabled ||
+	    crtc_state->pch_pfit.force_thru)
 		mask |= BIT(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
 
-	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
+	drm_for_each_encoder_mask(encoder, dev, crtc_state->base.encoder_mask) {
+		struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+
 		mask |= BIT(intel_display_port_power_domain(intel_encoder));
+	}
 
 	return mask;
 }
 
-static unsigned long modeset_get_crtc_power_domains(struct drm_crtc *crtc)
+static unsigned long
+modeset_get_crtc_power_domains(struct drm_crtc *crtc,
+			       struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -5352,7 +5343,8 @@ static unsigned long modeset_get_crtc_power_domains(struct drm_crtc *crtc)
 	unsigned long domains, new_domains, old_domains;
 
 	old_domains = intel_crtc->enabled_power_domains;
-	intel_crtc->enabled_power_domains = new_domains = get_crtc_power_domains(crtc);
+	intel_crtc->enabled_power_domains = new_domains =
+		get_crtc_power_domains(crtc, crtc_state);
 
 	domains = new_domains & ~old_domains;
 
@@ -5371,34 +5363,6 @@ static void modeset_put_power_domains(struct drm_i915_private *dev_priv,
 		intel_display_power_put(dev_priv, domain);
 }
 
-static void modeset_update_crtc_power_domains(struct drm_atomic_state *state)
-{
-	struct drm_device *dev = state->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long put_domains[I915_MAX_PIPES] = {};
-	struct drm_crtc_state *crtc_state;
-	struct drm_crtc *crtc;
-	int i;
-
-	for_each_crtc_in_state(state, crtc, crtc_state, i) {
-		if (needs_modeset(crtc->state))
-			put_domains[to_intel_crtc(crtc)->pipe] =
-				modeset_get_crtc_power_domains(crtc);
-	}
-
-	if (dev_priv->display.modeset_commit_cdclk) {
-		unsigned int cdclk = to_intel_atomic_state(state)->cdclk;
-
-		if (cdclk != dev_priv->cdclk_freq &&
-		    !WARN_ON(!state->allow_modeset))
-			dev_priv->display.modeset_commit_cdclk(state);
-	}
-
-	for (i = 0; i < I915_MAX_PIPES; i++)
-		if (put_domains[i])
-			modeset_put_power_domains(dev_priv, put_domains[i]);
-}
-
 static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv)
 {
 	int max_cdclk_freq = dev_priv->max_cdclk_freq;
@@ -6061,27 +6025,32 @@ static int broxton_calc_cdclk(struct drm_i915_private *dev_priv,
 		return 144000;
 }
 
-/* Compute the max pixel clock for new configuration. Uses atomic state if
- * that's non-NULL, look at current state otherwise. */
+/* Compute the max pixel clock for new configuration. */
 static int intel_mode_max_pixclk(struct drm_device *dev,
 				 struct drm_atomic_state *state)
 {
-	struct intel_crtc *intel_crtc;
-	struct intel_crtc_state *crtc_state;
-	int max_pixclk = 0;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	unsigned max_pixclk = 0, i;
+	enum pipe pipe;
 
-	for_each_intel_crtc(dev, intel_crtc) {
-		crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
+	memcpy(intel_state->min_pixclk, dev_priv->min_pixclk,
+	       sizeof(intel_state->min_pixclk));
 
-		if (!crtc_state->base.enable)
-			continue;
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		int pixclk = 0;
+
+		if (crtc_state->enable)
+			pixclk = crtc_state->adjusted_mode.crtc_clock;
 
-		max_pixclk = max(max_pixclk,
-				 crtc_state->base.adjusted_mode.crtc_clock);
+		intel_state->min_pixclk[i] = pixclk;
 	}
 
+	for_each_pipe(dev_priv, pipe)
+		max_pixclk = max(intel_state->min_pixclk[pipe], max_pixclk);
+
 	return max_pixclk;
 }
 
@@ -6090,13 +6059,18 @@ static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state)
 	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int max_pixclk = intel_mode_max_pixclk(dev, state);
+	struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(state);
 
 	if (max_pixclk < 0)
 		return max_pixclk;
 
-	to_intel_atomic_state(state)->cdclk =
+	intel_state->cdclk = intel_state->dev_cdclk =
 		valleyview_calc_cdclk(dev_priv, max_pixclk);
 
+	if (!intel_state->active_crtcs)
+		intel_state->dev_cdclk = valleyview_calc_cdclk(dev_priv, 0);
+
 	return 0;
 }
 
@@ -6105,13 +6079,18 @@ static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state)
 	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int max_pixclk = intel_mode_max_pixclk(dev, state);
+	struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(state);
 
 	if (max_pixclk < 0)
 		return max_pixclk;
 
-	to_intel_atomic_state(state)->cdclk =
+	intel_state->cdclk = intel_state->dev_cdclk =
 		broxton_calc_cdclk(dev_priv, max_pixclk);
 
+	if (!intel_state->active_crtcs)
+		intel_state->dev_cdclk = broxton_calc_cdclk(dev_priv, 0);
+
 	return 0;
 }
 
@@ -6154,8 +6133,10 @@ static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv)
 static void valleyview_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
-	unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_atomic_state *old_intel_state =
+		to_intel_atomic_state(old_state);
+	unsigned req_cdclk = old_intel_state->dev_cdclk;
 
 	/*
 	 * FIXME: We can end up here with all power domains off, yet
@@ -6229,6 +6210,7 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 
 	intel_crtc_load_lut(crtc);
 
+	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
 
 	assert_vblank_disabled(crtc);
@@ -6290,8 +6272,6 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		encoder->enable(encoder);
-
-	intel_fbc_enable(intel_crtc);
 }
 
 static void i9xx_pfit_disable(struct intel_crtc *crtc)
@@ -6354,8 +6334,6 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 
 	if (!IS_GEN2(dev))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-
-	intel_fbc_disable_crtc(intel_crtc);
 }
 
 static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
@@ -6379,6 +6357,7 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 
 	dev_priv->display.crtc_disable(crtc);
 	intel_crtc->active = false;
+	intel_fbc_disable(intel_crtc);
 	intel_update_watermarks(crtc);
 	intel_disable_shared_dpll(intel_crtc);
 
@@ -6386,6 +6365,9 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 	for_each_power_domain(domain, domains)
 		intel_display_power_put(dev_priv, domain);
 	intel_crtc->enabled_power_domains = 0;
+
+	dev_priv->active_crtcs &= ~(1 << intel_crtc->pipe);
+	dev_priv->min_pixclk[intel_crtc->pipe] = 0;
 }
 
 /*
@@ -6394,55 +6376,16 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
  */
 int intel_display_suspend(struct drm_device *dev)
 {
-	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_atomic_state *state;
-	struct drm_crtc *crtc;
-	unsigned crtc_mask = 0;
-	int ret = 0;
-
-	if (WARN_ON(!ctx))
-		return 0;
-
-	lockdep_assert_held(&ctx->ww_ctx);
-	state = drm_atomic_state_alloc(dev);
-	if (WARN_ON(!state))
-		return -ENOMEM;
-
-	state->acquire_ctx = ctx;
-	state->allow_modeset = true;
-
-	for_each_crtc(dev, crtc) {
-		struct drm_crtc_state *crtc_state =
-			drm_atomic_get_crtc_state(state, crtc);
-
-		ret = PTR_ERR_OR_ZERO(crtc_state);
-		if (ret)
-			goto free;
-
-		if (!crtc_state->active)
-			continue;
-
-		crtc_state->active = false;
-		crtc_mask |= 1 << drm_crtc_index(crtc);
-	}
-
-	if (crtc_mask) {
-		ret = drm_atomic_commit(state);
-
-		if (!ret) {
-			for_each_crtc(dev, crtc)
-				if (crtc_mask & (1 << drm_crtc_index(crtc)))
-					crtc->state->active = true;
-
-			return ret;
-		}
-	}
+	int ret;
 
-free:
+	state = drm_atomic_helper_suspend(dev);
+	ret = PTR_ERR_OR_ZERO(state);
 	if (ret)
 		DRM_ERROR("Suspending crtc's failed with %i\n", ret);
-	drm_atomic_state_free(state);
+	else
+		dev_priv->modeset_restore_state = state;
 	return ret;
 }
 
@@ -7596,26 +7539,34 @@ static void chv_prepare_pll(struct intel_crtc *crtc,
  * in cases where we need the PLL enabled even when @pipe is not going to
  * be enabled.
  */
-void vlv_force_pll_on(struct drm_device *dev, enum pipe pipe,
-		      const struct dpll *dpll)
+int vlv_force_pll_on(struct drm_device *dev, enum pipe pipe,
+		     const struct dpll *dpll)
 {
 	struct intel_crtc *crtc =
 		to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
-	struct intel_crtc_state pipe_config = {
-		.base.crtc = &crtc->base,
-		.pixel_multiplier = 1,
-		.dpll = *dpll,
-	};
+	struct intel_crtc_state *pipe_config;
+
+	pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL);
+	if (!pipe_config)
+		return -ENOMEM;
+
+	pipe_config->base.crtc = &crtc->base;
+	pipe_config->pixel_multiplier = 1;
+	pipe_config->dpll = *dpll;
 
 	if (IS_CHERRYVIEW(dev)) {
-		chv_compute_dpll(crtc, &pipe_config);
-		chv_prepare_pll(crtc, &pipe_config);
-		chv_enable_pll(crtc, &pipe_config);
+		chv_compute_dpll(crtc, pipe_config);
+		chv_prepare_pll(crtc, pipe_config);
+		chv_enable_pll(crtc, pipe_config);
 	} else {
-		vlv_compute_dpll(crtc, &pipe_config);
-		vlv_prepare_pll(crtc, &pipe_config);
-		vlv_enable_pll(crtc, &pipe_config);
+		vlv_compute_dpll(crtc, pipe_config);
+		vlv_prepare_pll(crtc, pipe_config);
+		vlv_enable_pll(crtc, pipe_config);
 	}
+
+	kfree(pipe_config);
+
+	return 0;
 }
 
 /**
@@ -8038,9 +7989,6 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc,
 
 	pipe_config->gmch_pfit.control = tmp;
 	pipe_config->gmch_pfit.pgm_ratios = I915_READ(PFIT_PGM_RATIOS);
-	if (INTEL_INFO(dev)->gen < 5)
-		pipe_config->gmch_pfit.lvds_border_bits =
-			I915_READ(LVDS) & LVDS_BORDER_ENABLE;
 }
 
 static void vlv_crtc_clock_get(struct intel_crtc *crtc,
@@ -9258,7 +9206,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	fb->width = ((val >> 0) & 0x1fff) + 1;
 
 	val = I915_READ(PLANE_STRIDE(pipe, 0));
-	stride_mult = intel_fb_stride_alignment(dev, fb->modifier[0],
+	stride_mult = intel_fb_stride_alignment(dev_priv, fb->modifier[0],
 						fb->pixel_format);
 	fb->pitches[0] = (val & 0x3ff) * stride_mult;
 
@@ -9682,14 +9630,14 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 		val |= PCH_LP_PARTITION_LEVEL_DISABLE;
 		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
 	}
-
-	intel_prepare_ddi(dev);
 }
 
 static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
-	unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
+	struct intel_atomic_state *old_intel_state =
+		to_intel_atomic_state(old_state);
+	unsigned int req_cdclk = old_intel_state->dev_cdclk;
 
 	broxton_set_cdclk(dev, req_cdclk);
 }
@@ -9697,29 +9645,38 @@ static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 /* compute the max rate for new configuration */
 static int ilk_max_pixel_rate(struct drm_atomic_state *state)
 {
-	struct intel_crtc *intel_crtc;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = state->dev->dev_private;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *cstate;
 	struct intel_crtc_state *crtc_state;
-	int max_pixel_rate = 0;
+	unsigned max_pixel_rate = 0, i;
+	enum pipe pipe;
 
-	for_each_intel_crtc(state->dev, intel_crtc) {
-		int pixel_rate;
+	memcpy(intel_state->min_pixclk, dev_priv->min_pixclk,
+	       sizeof(intel_state->min_pixclk));
 
-		crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
+	for_each_crtc_in_state(state, crtc, cstate, i) {
+		int pixel_rate;
 
-		if (!crtc_state->base.enable)
+		crtc_state = to_intel_crtc_state(cstate);
+		if (!crtc_state->base.enable) {
+			intel_state->min_pixclk[i] = 0;
 			continue;
+		}
 
 		pixel_rate = ilk_pipe_pixel_rate(crtc_state);
 
 		/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
-		if (IS_BROADWELL(state->dev) && crtc_state->ips_enabled)
+		if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
 			pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95);
 
-		max_pixel_rate = max(max_pixel_rate, pixel_rate);
+		intel_state->min_pixclk[i] = pixel_rate;
 	}
 
+	for_each_pipe(dev_priv, pipe)
+		max_pixel_rate = max(intel_state->min_pixclk[pipe], max_pixel_rate);
+
 	return max_pixel_rate;
 }
 
@@ -9793,6 +9750,8 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
 	sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
+	I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1);
+
 	intel_update_cdclk(dev);
 
 	WARN(cdclk != dev_priv->cdclk_freq,
@@ -9803,6 +9762,7 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
 static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->dev);
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	int max_pixclk = ilk_max_pixel_rate(state);
 	int cdclk;
 
@@ -9825,7 +9785,9 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 		return -EINVAL;
 	}
 
-	to_intel_atomic_state(state)->cdclk = cdclk;
+	intel_state->cdclk = intel_state->dev_cdclk = cdclk;
+	if (!intel_state->active_crtcs)
+		intel_state->dev_cdclk = 337500;
 
 	return 0;
 }
@@ -9833,7 +9795,9 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 static void broadwell_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
-	unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk;
+	struct intel_atomic_state *old_intel_state =
+		to_intel_atomic_state(old_state);
+	unsigned req_cdclk = old_intel_state->dev_cdclk;
 
 	broadwell_set_cdclk(dev, req_cdclk);
 }
@@ -9841,8 +9805,13 @@ static void broadwell_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 				      struct intel_crtc_state *crtc_state)
 {
-	if (!intel_ddi_pll_select(crtc, crtc_state))
-		return -EINVAL;
+	struct intel_encoder *intel_encoder =
+		intel_ddi_get_crtc_new_encoder(crtc_state);
+
+	if (intel_encoder->type != INTEL_OUTPUT_DSI) {
+		if (!intel_ddi_pll_select(crtc, crtc_state))
+			return -EINVAL;
+	}
 
 	crtc->lowfreq_avail = false;
 
@@ -10058,16 +10027,17 @@ out:
 	return ret;
 }
 
-static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
+static void i845_update_cursor(struct drm_crtc *crtc, u32 base,
+			       const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t cntl = 0, size = 0;
 
-	if (on) {
-		unsigned int width = intel_crtc->base.cursor->state->crtc_w;
-		unsigned int height = intel_crtc->base.cursor->state->crtc_h;
+	if (plane_state && plane_state->visible) {
+		unsigned int width = plane_state->base.crtc_w;
+		unsigned int height = plane_state->base.crtc_h;
 		unsigned int stride = roundup_pow_of_two(width) * 4;
 
 		switch (stride) {
@@ -10120,7 +10090,8 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 	}
 }
 
-static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
+static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base,
+			       const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -10128,9 +10099,9 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 	int pipe = intel_crtc->pipe;
 	uint32_t cntl = 0;
 
-	if (on) {
+	if (plane_state && plane_state->visible) {
 		cntl = MCURSOR_GAMMA_ENABLE;
-		switch (intel_crtc->base.cursor->state->crtc_w) {
+		switch (plane_state->base.crtc_w) {
 			case 64:
 				cntl |= CURSOR_MODE_64_ARGB_AX;
 				break;
@@ -10141,17 +10112,17 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 				cntl |= CURSOR_MODE_256_ARGB_AX;
 				break;
 			default:
-				MISSING_CASE(intel_crtc->base.cursor->state->crtc_w);
+				MISSING_CASE(plane_state->base.crtc_w);
 				return;
 		}
 		cntl |= pipe << 28; /* Connect to correct pipe */
 
 		if (HAS_DDI(dev))
 			cntl |= CURSOR_PIPE_CSC_ENABLE;
-	}
 
-	if (crtc->cursor->state->rotation == BIT(DRM_ROTATE_180))
-		cntl |= CURSOR_ROTATE_180;
+		if (plane_state->base.rotation == BIT(DRM_ROTATE_180))
+			cntl |= CURSOR_ROTATE_180;
+	}
 
 	if (intel_crtc->cursor_cntl != cntl) {
 		I915_WRITE(CURCNTR(pipe), cntl);
@@ -10168,56 +10139,45 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 
 /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
 static void intel_crtc_update_cursor(struct drm_crtc *crtc,
-				     bool on)
+				     const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	struct drm_plane_state *cursor_state = crtc->cursor->state;
-	int x = cursor_state->crtc_x;
-	int y = cursor_state->crtc_y;
-	u32 base = 0, pos = 0;
-
-	base = intel_crtc->cursor_addr;
-
-	if (x >= intel_crtc->config->pipe_src_w)
-		on = false;
-
-	if (y >= intel_crtc->config->pipe_src_h)
-		on = false;
+	u32 base = intel_crtc->cursor_addr;
+	u32 pos = 0;
 
-	if (x < 0) {
-		if (x + cursor_state->crtc_w <= 0)
-			on = false;
+	if (plane_state) {
+		int x = plane_state->base.crtc_x;
+		int y = plane_state->base.crtc_y;
 
-		pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT;
-		x = -x;
-	}
-	pos |= x << CURSOR_X_SHIFT;
+		if (x < 0) {
+			pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT;
+			x = -x;
+		}
+		pos |= x << CURSOR_X_SHIFT;
 
-	if (y < 0) {
-		if (y + cursor_state->crtc_h <= 0)
-			on = false;
+		if (y < 0) {
+			pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT;
+			y = -y;
+		}
+		pos |= y << CURSOR_Y_SHIFT;
 
-		pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT;
-		y = -y;
+		/* ILK+ do this automagically */
+		if (HAS_GMCH_DISPLAY(dev) &&
+		    plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
+			base += (plane_state->base.crtc_h *
+				 plane_state->base.crtc_w - 1) * 4;
+		}
 	}
-	pos |= y << CURSOR_Y_SHIFT;
 
 	I915_WRITE(CURPOS(pipe), pos);
 
-	/* ILK+ do this automagically */
-	if (HAS_GMCH_DISPLAY(dev) &&
-	    crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) {
-		base += (cursor_state->crtc_h *
-			 cursor_state->crtc_w - 1) * 4;
-	}
-
 	if (IS_845G(dev) || IS_I865G(dev))
-		i845_update_cursor(crtc, base, on);
+		i845_update_cursor(crtc, base, plane_state);
 	else
-		i9xx_update_cursor(crtc, base, on);
+		i9xx_update_cursor(crtc, base, plane_state);
 }
 
 static bool cursor_size_ok(struct drm_device *dev,
@@ -10385,6 +10345,7 @@ mode_fits_in_fbdev(struct drm_device *dev,
 	if (obj->base.size < mode->vdisplay * fb->pitches[0])
 		return NULL;
 
+	drm_framebuffer_reference(fb);
 	return fb;
 #else
 	return NULL;
@@ -10440,7 +10401,7 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
 	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_atomic_state *state = NULL;
+	struct drm_atomic_state *state = NULL, *restore_state = NULL;
 	struct drm_connector_state *connector_state;
 	struct intel_crtc_state *crtc_state;
 	int ret, i = -1;
@@ -10449,6 +10410,8 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 		      connector->base.id, connector->name,
 		      encoder->base.id, encoder->name);
 
+	old->restore_state = NULL;
+
 retry:
 	ret = drm_modeset_lock(&config->connection_mutex, ctx);
 	if (ret)
@@ -10465,24 +10428,15 @@ retry:
 	 */
 
 	/* See if we already have a CRTC for this connector */
-	if (encoder->crtc) {
-		crtc = encoder->crtc;
+	if (connector->state->crtc) {
+		crtc = connector->state->crtc;
 
 		ret = drm_modeset_lock(&crtc->mutex, ctx);
 		if (ret)
 			goto fail;
-		ret = drm_modeset_lock(&crtc->primary->mutex, ctx);
-		if (ret)
-			goto fail;
-
-		old->dpms_mode = connector->dpms;
-		old->load_detect_temp = false;
 
 		/* Make sure the crtc and connector are running */
-		if (connector->dpms != DRM_MODE_DPMS_ON)
-			connector->funcs->dpms(connector, DRM_MODE_DPMS_ON);
-
-		return true;
+		goto found;
 	}
 
 	/* Find an unused one (if possible) */
@@ -10490,8 +10444,15 @@ retry:
 		i++;
 		if (!(encoder->possible_crtcs & (1 << i)))
 			continue;
-		if (possible_crtc->state->enable)
+
+		ret = drm_modeset_lock(&possible_crtc->mutex, ctx);
+		if (ret)
+			goto fail;
+
+		if (possible_crtc->state->enable) {
+			drm_modeset_unlock(&possible_crtc->mutex);
 			continue;
+		}
 
 		crtc = possible_crtc;
 		break;
@@ -10505,23 +10466,22 @@ retry:
 		goto fail;
 	}
 
-	ret = drm_modeset_lock(&crtc->mutex, ctx);
-	if (ret)
-		goto fail;
+found:
+	intel_crtc = to_intel_crtc(crtc);
+
 	ret = drm_modeset_lock(&crtc->primary->mutex, ctx);
 	if (ret)
 		goto fail;
 
-	intel_crtc = to_intel_crtc(crtc);
-	old->dpms_mode = connector->dpms;
-	old->load_detect_temp = true;
-	old->release_fb = NULL;
-
 	state = drm_atomic_state_alloc(dev);
-	if (!state)
-		return false;
+	restore_state = drm_atomic_state_alloc(dev);
+	if (!state || !restore_state) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
 	state->acquire_ctx = ctx;
+	restore_state->acquire_ctx = ctx;
 
 	connector_state = drm_atomic_get_connector_state(state, connector);
 	if (IS_ERR(connector_state)) {
@@ -10529,8 +10489,9 @@ retry:
 		goto fail;
 	}
 
-	connector_state->crtc = crtc;
-	connector_state->best_encoder = &intel_encoder->base;
+	ret = drm_atomic_set_crtc_for_connector(connector_state, crtc);
+	if (ret)
+		goto fail;
 
 	crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
 	if (IS_ERR(crtc_state)) {
@@ -10554,7 +10515,6 @@ retry:
 	if (fb == NULL) {
 		DRM_DEBUG_KMS("creating tmp fb for load-detection\n");
 		fb = intel_framebuffer_create_for_mode(dev, mode, 24, 32);
-		old->release_fb = fb;
 	} else
 		DRM_DEBUG_KMS("reusing fbdev for load-detection framebuffer\n");
 	if (IS_ERR(fb)) {
@@ -10566,15 +10526,29 @@ retry:
 	if (ret)
 		goto fail;
 
-	drm_mode_copy(&crtc_state->base.mode, mode);
+	drm_framebuffer_unreference(fb);
+
+	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base, mode);
+	if (ret)
+		goto fail;
+
+	ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(restore_state, connector));
+	if (!ret)
+		ret = PTR_ERR_OR_ZERO(drm_atomic_get_crtc_state(restore_state, crtc));
+	if (!ret)
+		ret = PTR_ERR_OR_ZERO(drm_atomic_get_plane_state(restore_state, crtc->primary));
+	if (ret) {
+		DRM_DEBUG_KMS("Failed to create a copy of old state to restore: %i\n", ret);
+		goto fail;
+	}
 
-	if (drm_atomic_commit(state)) {
+	ret = drm_atomic_commit(state);
+	if (ret) {
 		DRM_DEBUG_KMS("failed to set mode on load-detect pipe\n");
-		if (old->release_fb)
-			old->release_fb->funcs->destroy(old->release_fb);
 		goto fail;
 	}
-	crtc->primary->crtc = crtc;
+
+	old->restore_state = restore_state;
 
 	/* let the connector get through one full cycle before testing */
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
@@ -10582,7 +10556,8 @@ retry:
 
 fail:
 	drm_atomic_state_free(state);
-	state = NULL;
+	drm_atomic_state_free(restore_state);
+	restore_state = state = NULL;
 
 	if (ret == -EDEADLK) {
 		drm_modeset_backoff(ctx);
@@ -10596,66 +10571,24 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct intel_load_detect_pipe *old,
 				    struct drm_modeset_acquire_ctx *ctx)
 {
-	struct drm_device *dev = connector->dev;
 	struct intel_encoder *intel_encoder =
 		intel_attached_encoder(connector);
 	struct drm_encoder *encoder = &intel_encoder->base;
-	struct drm_crtc *crtc = encoder->crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_atomic_state *state;
-	struct drm_connector_state *connector_state;
-	struct intel_crtc_state *crtc_state;
+	struct drm_atomic_state *state = old->restore_state;
 	int ret;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 		      connector->base.id, connector->name,
 		      encoder->base.id, encoder->name);
 
-	if (old->load_detect_temp) {
-		state = drm_atomic_state_alloc(dev);
-		if (!state)
-			goto fail;
-
-		state->acquire_ctx = ctx;
-
-		connector_state = drm_atomic_get_connector_state(state, connector);
-		if (IS_ERR(connector_state))
-			goto fail;
-
-		crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
-		if (IS_ERR(crtc_state))
-			goto fail;
-
-		connector_state->best_encoder = NULL;
-		connector_state->crtc = NULL;
-
-		crtc_state->base.enable = crtc_state->base.active = false;
-
-		ret = intel_modeset_setup_plane_state(state, crtc, NULL, NULL,
-						      0, 0);
-		if (ret)
-			goto fail;
-
-		ret = drm_atomic_commit(state);
-		if (ret)
-			goto fail;
-
-		if (old->release_fb) {
-			drm_framebuffer_unregister_private(old->release_fb);
-			drm_framebuffer_unreference(old->release_fb);
-		}
-
+	if (!state)
 		return;
-	}
 
-	/* Switch crtc and encoder back off if necessary */
-	if (old->dpms_mode != DRM_MODE_DPMS_ON)
-		connector->funcs->dpms(connector, old->dpms_mode);
-
-	return;
-fail:
-	DRM_DEBUG_KMS("Couldn't release load detect pipe.\n");
-	drm_atomic_state_free(state);
+	ret = drm_atomic_commit(state);
+	if (ret) {
+		DRM_DEBUG_KMS("Couldn't release load detect pipe: %i\n", ret);
+		drm_atomic_state_free(state);
+	}
 }
 
 static int i9xx_pll_refclk(struct drm_device *dev,
@@ -10810,7 +10743,7 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	struct drm_display_mode *mode;
-	struct intel_crtc_state pipe_config;
+	struct intel_crtc_state *pipe_config;
 	int htot = I915_READ(HTOTAL(cpu_transcoder));
 	int hsync = I915_READ(HSYNC(cpu_transcoder));
 	int vtot = I915_READ(VTOTAL(cpu_transcoder));
@@ -10821,6 +10754,12 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	if (!mode)
 		return NULL;
 
+	pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL);
+	if (!pipe_config) {
+		kfree(mode);
+		return NULL;
+	}
+
 	/*
 	 * Construct a pipe_config sufficient for getting the clock info
 	 * back out of crtc_clock_get.
@@ -10828,14 +10767,14 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	 * Note, if LVDS ever uses a non-1 pixel multiplier, we'll need
 	 * to use a real value here instead.
 	 */
-	pipe_config.cpu_transcoder = (enum transcoder) pipe;
-	pipe_config.pixel_multiplier = 1;
-	pipe_config.dpll_hw_state.dpll = I915_READ(DPLL(pipe));
-	pipe_config.dpll_hw_state.fp0 = I915_READ(FP0(pipe));
-	pipe_config.dpll_hw_state.fp1 = I915_READ(FP1(pipe));
-	i9xx_crtc_clock_get(intel_crtc, &pipe_config);
-
-	mode->clock = pipe_config.port_clock / pipe_config.pixel_multiplier;
+	pipe_config->cpu_transcoder = (enum transcoder) pipe;
+	pipe_config->pixel_multiplier = 1;
+	pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(pipe));
+	pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(pipe));
+	pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(pipe));
+	i9xx_crtc_clock_get(intel_crtc, pipe_config);
+
+	mode->clock = pipe_config->port_clock / pipe_config->pixel_multiplier;
 	mode->hdisplay = (htot & 0xffff) + 1;
 	mode->htotal = ((htot & 0xffff0000) >> 16) + 1;
 	mode->hsync_start = (hsync & 0xffff) + 1;
@@ -10847,6 +10786,8 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 
 	drm_mode_set_name(mode);
 
+	kfree(pipe_config);
+
 	return mode;
 }
 
@@ -10917,6 +10858,7 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 	mutex_unlock(&dev->struct_mutex);
 
 	intel_frontbuffer_flip_complete(dev, to_intel_plane(primary)->frontbuffer_bit);
+	intel_fbc_post_update(crtc);
 	drm_framebuffer_unreference(work->old_fb);
 
 	BUG_ON(atomic_read(&crtc->unpin_work_count) == 0);
@@ -10998,6 +10940,12 @@ static bool page_flip_finished(struct intel_crtc *crtc)
 		return true;
 
 	/*
+	 * BDW signals flip done immediately if the plane
+	 * is disabled, even if the plane enable is already
+	 * armed to occur at the next vblank :(
+	 */
+
+	/*
 	 * A DSPSURFLIVE check isn't enough in case the mmio and CS flips
 	 * used the same base address. In that case the mmio flip might
 	 * have completed, but the CS hasn't even executed the flip yet.
@@ -11351,13 +11299,12 @@ static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
 	 */
 	if (intel_rotation_90_or_270(rotation)) {
 		/* stride = Surface height in tiles */
-		tile_height = intel_tile_height(dev, fb->pixel_format,
-						fb->modifier[0], 0);
+		tile_height = intel_tile_height(dev_priv, fb->modifier[0], 0);
 		stride = DIV_ROUND_UP(fb->height, tile_height);
 	} else {
 		stride = fb->pitches[0] /
-				intel_fb_stride_alignment(dev, fb->modifier[0],
-							  fb->pixel_format);
+			intel_fb_stride_alignment(dev_priv, fb->modifier[0],
+						  fb->pixel_format);
 	}
 
 	/*
@@ -11633,6 +11580,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	crtc->primary->fb = fb;
 	update_state_fb(crtc->primary);
+	intel_fbc_pre_update(intel_crtc);
 
 	work->pending_flip_obj = obj;
 
@@ -11692,9 +11640,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 					obj->last_write_req);
 	} else {
 		if (!request) {
-			ret = i915_gem_request_alloc(ring, ring->default_context, &request);
-			if (ret)
+			request = i915_gem_request_alloc(ring, NULL);
+			if (IS_ERR(request)) {
+				ret = PTR_ERR(request);
 				goto cleanup_unpin;
+			}
 		}
 
 		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
@@ -11715,7 +11665,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 			  to_intel_plane(primary)->frontbuffer_bit);
 	mutex_unlock(&dev->struct_mutex);
 
-	intel_fbc_deactivate(intel_crtc);
 	intel_frontbuffer_flip_prepare(dev,
 				       to_intel_plane(primary)->frontbuffer_bit);
 
@@ -11726,7 +11675,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 cleanup_unpin:
 	intel_unpin_fb_obj(fb, crtc->primary->state);
 cleanup_pending:
-	if (request)
+	if (!IS_ERR_OR_NULL(request))
 		i915_gem_request_cancel(request);
 	atomic_dec(&intel_crtc->unpin_work_count);
 	mutex_unlock(&dev->struct_mutex);
@@ -11837,11 +11786,9 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_plane *plane = plane_state->plane;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane_state *old_plane_state =
 		to_intel_plane_state(plane->state);
 	int idx = intel_crtc->base.base.id, ret;
-	int i = drm_plane_index(plane);
 	bool mode_changed = needs_modeset(crtc_state);
 	bool was_crtc_enabled = crtc->state->active;
 	bool is_crtc_enabled = crtc_state->active;
@@ -11863,12 +11810,20 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	if (!was_crtc_enabled && WARN_ON(was_visible))
 		was_visible = false;
 
-	if (!is_crtc_enabled && WARN_ON(visible))
-		visible = false;
+	/*
+	 * Visibility is calculated as if the crtc was on, but
+	 * after scaler setup everything depends on it being off
+	 * when the crtc isn't active.
+	 */
+	if (!is_crtc_enabled)
+		to_intel_plane_state(plane_state)->visible = visible = false;
 
 	if (!was_visible && !visible)
 		return 0;
 
+	if (fb != old_plane_state->base.fb)
+		pipe_config->fb_changed = true;
+
 	turn_off = was_visible && (!visible || mode_changed);
 	turn_on = visible && (!was_visible || mode_changed);
 
@@ -11879,17 +11834,22 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 			 plane->base.id, was_visible, visible,
 			 turn_off, turn_on, mode_changed);
 
-	if (turn_on || turn_off) {
-		pipe_config->wm_changed = true;
+	if (turn_on) {
+		pipe_config->update_wm_pre = true;
 
 		/* must disable cxsr around plane enable/disable */
-		if (plane->type != DRM_PLANE_TYPE_CURSOR) {
-			if (is_crtc_enabled)
-				intel_crtc->atomic.wait_vblank = true;
+		if (plane->type != DRM_PLANE_TYPE_CURSOR)
+			pipe_config->disable_cxsr = true;
+	} else if (turn_off) {
+		pipe_config->update_wm_post = true;
+
+		/* must disable cxsr around plane enable/disable */
+		if (plane->type != DRM_PLANE_TYPE_CURSOR)
 			pipe_config->disable_cxsr = true;
-		}
 	} else if (intel_wm_need_update(plane, plane_state)) {
-		pipe_config->wm_changed = true;
+		/* FIXME bollocks */
+		pipe_config->update_wm_pre = true;
+		pipe_config->update_wm_post = true;
 	}
 
 	if (visible || was_visible)
@@ -11898,49 +11858,9 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 
 	switch (plane->type) {
 	case DRM_PLANE_TYPE_PRIMARY:
-		intel_crtc->atomic.pre_disable_primary = turn_off;
 		intel_crtc->atomic.post_enable_primary = turn_on;
+		intel_crtc->atomic.update_fbc = true;
 
-		if (turn_off) {
-			/*
-			 * FIXME: Actually if we will still have any other
-			 * plane enabled on the pipe we could let IPS enabled
-			 * still, but for now lets consider that when we make
-			 * primary invisible by setting DSPCNTR to 0 on
-			 * update_primary_plane function IPS needs to be
-			 * disable.
-			 */
-			intel_crtc->atomic.disable_ips = true;
-
-			intel_crtc->atomic.disable_fbc = true;
-		}
-
-		/*
-		 * FBC does not work on some platforms for rotated
-		 * planes, so disable it when rotation is not 0 and
-		 * update it when rotation is set back to 0.
-		 *
-		 * FIXME: This is redundant with the fbc update done in
-		 * the primary plane enable function except that that
-		 * one is done too late. We eventually need to unify
-		 * this.
-		 */
-
-		if (visible &&
-		    INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
-		    dev_priv->fbc.crtc == intel_crtc &&
-		    plane_state->rotation != BIT(DRM_ROTATE_0))
-			intel_crtc->atomic.disable_fbc = true;
-
-		/*
-		 * BDW signals flip done immediately if the plane
-		 * is disabled, even if the plane enable is already
-		 * armed to occur at the next vblank :(
-		 */
-		if (turn_on && IS_BROADWELL(dev))
-			intel_crtc->atomic.wait_vblank = true;
-
-		intel_crtc->atomic.update_fbc |= visible || mode_changed;
 		break;
 	case DRM_PLANE_TYPE_CURSOR:
 		break;
@@ -11953,13 +11873,8 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 		 */
 		if (IS_IVYBRIDGE(dev) &&
 		    needs_scaling(to_intel_plane_state(plane_state)) &&
-		    !needs_scaling(old_plane_state)) {
-			to_intel_crtc_state(crtc_state)->disable_lp_wm = true;
-		} else if (turn_off && !mode_changed) {
-			intel_crtc->atomic.wait_vblank = true;
-			intel_crtc->atomic.update_sprite_watermarks |=
-				1 << i;
-		}
+		    !needs_scaling(old_plane_state))
+			pipe_config->disable_lp_wm = true;
 
 		break;
 	}
@@ -12034,7 +11949,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 	}
 
 	if (mode_changed && !crtc_state->active)
-		pipe_config->wm_changed = true;
+		pipe_config->update_wm_post = true;
 
 	if (mode_changed && crtc_state->enable &&
 	    dev_priv->display.crtc_compute_clock &&
@@ -12561,19 +12476,22 @@ intel_compare_m_n(unsigned int m, unsigned int n,
 
 	BUILD_BUG_ON(DATA_LINK_M_N_MASK > INT_MAX);
 
-	if (m > m2) {
-		while (m > m2) {
+	if (n > n2) {
+		while (n > n2) {
 			m2 <<= 1;
 			n2 <<= 1;
 		}
-	} else if (m < m2) {
-		while (m < m2) {
+	} else if (n < n2) {
+		while (n < n2) {
 			m <<= 1;
 			n <<= 1;
 		}
 	}
 
-	return m == m2 && n == n2;
+	if (n != n2)
+		return false;
+
+	return intel_fuzzy_clock_check(m, m2);
 }
 
 static bool
@@ -13124,8 +13042,6 @@ static void intel_modeset_clear_plls(struct drm_atomic_state *state)
 	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll_config *shared_dpll = NULL;
-	struct intel_crtc *intel_crtc;
-	struct intel_crtc_state *intel_crtc_state;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	int i;
@@ -13134,21 +13050,21 @@ static void intel_modeset_clear_plls(struct drm_atomic_state *state)
 		return;
 
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
-		int dpll;
-
-		intel_crtc = to_intel_crtc(crtc);
-		intel_crtc_state = to_intel_crtc_state(crtc_state);
-		dpll = intel_crtc_state->shared_dpll;
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+		int old_dpll = to_intel_crtc_state(crtc->state)->shared_dpll;
 
-		if (!needs_modeset(crtc_state) || dpll == DPLL_ID_PRIVATE)
+		if (!needs_modeset(crtc_state))
 			continue;
 
-		intel_crtc_state->shared_dpll = DPLL_ID_PRIVATE;
+		to_intel_crtc_state(crtc_state)->shared_dpll = DPLL_ID_PRIVATE;
+
+		if (old_dpll == DPLL_ID_PRIVATE)
+			continue;
 
 		if (!shared_dpll)
 			shared_dpll = intel_atomic_get_shared_dpll_state(state);
 
-		shared_dpll[dpll].crtc_mask &= ~(1 << intel_crtc->pipe);
+		shared_dpll[old_dpll].crtc_mask &= ~(1 << intel_crtc->pipe);
 	}
 }
 
@@ -13248,15 +13164,27 @@ static int intel_modeset_all_pipes(struct drm_atomic_state *state)
 
 static int intel_modeset_checks(struct drm_atomic_state *state)
 {
-	struct drm_device *dev = state->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = state->dev->dev_private;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	int ret = 0, i;
 
 	if (!check_digital_port_conflicts(state)) {
 		DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
 		return -EINVAL;
 	}
 
+	intel_state->modeset = true;
+	intel_state->active_crtcs = dev_priv->active_crtcs;
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		if (crtc_state->active)
+			intel_state->active_crtcs |= 1 << i;
+		else
+			intel_state->active_crtcs &= ~(1 << i);
+	}
+
 	/*
 	 * See if the config requires any additional preparation, e.g.
 	 * to adjust global state with pipes off.  We need to do this
@@ -13265,22 +13193,22 @@ static int intel_modeset_checks(struct drm_atomic_state *state)
 	 * adjusted_mode bits in the crtc directly.
 	 */
 	if (dev_priv->display.modeset_calc_cdclk) {
-		unsigned int cdclk;
-
 		ret = dev_priv->display.modeset_calc_cdclk(state);
 
-		cdclk = to_intel_atomic_state(state)->cdclk;
-		if (!ret && cdclk != dev_priv->cdclk_freq)
+		if (!ret && intel_state->dev_cdclk != dev_priv->cdclk_freq)
 			ret = intel_modeset_all_pipes(state);
 
 		if (ret < 0)
 			return ret;
+
+		DRM_DEBUG_KMS("New cdclk calculated to be atomic %u, actual %u\n",
+			      intel_state->cdclk, intel_state->dev_cdclk);
 	} else
-		to_intel_atomic_state(state)->cdclk = dev_priv->cdclk_freq;
+		to_intel_atomic_state(state)->cdclk = dev_priv->atomic_cdclk_freq;
 
 	intel_modeset_clear_plls(state);
 
-	if (IS_HASWELL(dev))
+	if (IS_HASWELL(dev_priv))
 		return haswell_mode_set_planes_workaround(state);
 
 	return 0;
@@ -13333,6 +13261,7 @@ static void calc_watermark_data(struct drm_atomic_state *state)
 static int intel_atomic_check(struct drm_device *dev,
 			      struct drm_atomic_state *state)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -13375,7 +13304,7 @@ static int intel_atomic_check(struct drm_device *dev,
 			return ret;
 
 		if (i915.fastboot &&
-		    intel_pipe_config_compare(state->dev,
+		    intel_pipe_config_compare(dev,
 					to_intel_crtc_state(crtc->state),
 					pipe_config, true)) {
 			crtc_state->mode_changed = false;
@@ -13401,12 +13330,13 @@ static int intel_atomic_check(struct drm_device *dev,
 		if (ret)
 			return ret;
 	} else
-		intel_state->cdclk = to_i915(state->dev)->cdclk_freq;
+		intel_state->cdclk = dev_priv->cdclk_freq;
 
-	ret = drm_atomic_helper_check_planes(state->dev, state);
+	ret = drm_atomic_helper_check_planes(dev, state);
 	if (ret)
 		return ret;
 
+	intel_fbc_choose_crtc(dev_priv, state);
 	calc_watermark_data(state);
 
 	return 0;
@@ -13481,6 +13411,71 @@ static int intel_atomic_prepare_commit(struct drm_device *dev,
 	return ret;
 }
 
+static void intel_atomic_wait_for_vblanks(struct drm_device *dev,
+					  struct drm_i915_private *dev_priv,
+					  unsigned crtc_mask)
+{
+	unsigned last_vblank_count[I915_MAX_PIPES];
+	enum pipe pipe;
+	int ret;
+
+	if (!crtc_mask)
+		return;
+
+	for_each_pipe(dev_priv, pipe) {
+		struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+		if (!((1 << pipe) & crtc_mask))
+			continue;
+
+		ret = drm_crtc_vblank_get(crtc);
+		if (WARN_ON(ret != 0)) {
+			crtc_mask &= ~(1 << pipe);
+			continue;
+		}
+
+		last_vblank_count[pipe] = drm_crtc_vblank_count(crtc);
+	}
+
+	for_each_pipe(dev_priv, pipe) {
+		struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+		long lret;
+
+		if (!((1 << pipe) & crtc_mask))
+			continue;
+
+		lret = wait_event_timeout(dev->vblank[pipe].queue,
+				last_vblank_count[pipe] !=
+					drm_crtc_vblank_count(crtc),
+				msecs_to_jiffies(50));
+
+		WARN_ON(!lret);
+
+		drm_crtc_vblank_put(crtc);
+	}
+}
+
+static bool needs_vblank_wait(struct intel_crtc_state *crtc_state)
+{
+	/* fb updated, need to unpin old fb */
+	if (crtc_state->fb_changed)
+		return true;
+
+	/* wm changes, need vblank before final wm's */
+	if (crtc_state->update_wm_post)
+		return true;
+
+	/*
+	 * cxsr is re-enabled after vblank.
+	 * This is already handled by crtc_state->update_wm_post,
+	 * but added for clarity.
+	 */
+	if (crtc_state->disable_cxsr)
+		return true;
+
+	return false;
+}
+
 /**
  * intel_atomic_commit - commit validated state object
  * @dev: DRM device
@@ -13501,12 +13496,14 @@ static int intel_atomic_commit(struct drm_device *dev,
 			       struct drm_atomic_state *state,
 			       bool async)
 {
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	int ret = 0;
-	int i;
-	bool any_ms = false;
+	int ret = 0, i;
+	bool hw_check = intel_state->modeset;
+	unsigned long put_domains[I915_MAX_PIPES] = {};
+	unsigned crtc_vblank_mask = 0;
 
 	ret = intel_atomic_prepare_commit(dev, state, async);
 	if (ret) {
@@ -13517,19 +13514,37 @@ static int intel_atomic_commit(struct drm_device *dev,
 	drm_atomic_helper_swap_state(dev, state);
 	dev_priv->wm.config = to_intel_atomic_state(state)->wm_config;
 
+	if (intel_state->modeset) {
+		memcpy(dev_priv->min_pixclk, intel_state->min_pixclk,
+		       sizeof(intel_state->min_pixclk));
+		dev_priv->active_crtcs = intel_state->active_crtcs;
+		dev_priv->atomic_cdclk_freq = intel_state->cdclk;
+
+		intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
+	}
+
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
+		if (needs_modeset(crtc->state) ||
+		    to_intel_crtc_state(crtc->state)->update_pipe) {
+			hw_check = true;
+
+			put_domains[to_intel_crtc(crtc)->pipe] =
+				modeset_get_crtc_power_domains(crtc,
+					to_intel_crtc_state(crtc->state));
+		}
+
 		if (!needs_modeset(crtc->state))
 			continue;
 
-		any_ms = true;
-		intel_pre_plane_update(intel_crtc);
+		intel_pre_plane_update(to_intel_crtc_state(crtc_state));
 
 		if (crtc_state->active) {
 			intel_crtc_disable_planes(crtc, crtc_state->plane_mask);
 			dev_priv->display.crtc_disable(crtc);
 			intel_crtc->active = false;
+			intel_fbc_disable(intel_crtc);
 			intel_disable_shared_dpll(intel_crtc);
 
 			/*
@@ -13548,65 +13563,80 @@ static int intel_atomic_commit(struct drm_device *dev,
 	 * update the the output configuration. */
 	intel_modeset_update_crtc_state(state);
 
-	if (any_ms) {
+	if (intel_state->modeset) {
 		intel_shared_dpll_commit(state);
 
 		drm_atomic_helper_update_legacy_modeset_state(state->dev, state);
-		modeset_update_crtc_power_domains(state);
+
+		if (dev_priv->display.modeset_commit_cdclk &&
+		    intel_state->dev_cdclk != dev_priv->cdclk_freq)
+			dev_priv->display.modeset_commit_cdclk(state);
 	}
 
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 		bool modeset = needs_modeset(crtc->state);
-		bool update_pipe = !modeset &&
-			to_intel_crtc_state(crtc->state)->update_pipe;
-		unsigned long put_domains = 0;
-
-		if (modeset)
-			intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
+		struct intel_crtc_state *pipe_config =
+			to_intel_crtc_state(crtc->state);
+		bool update_pipe = !modeset && pipe_config->update_pipe;
 
 		if (modeset && crtc->state->active) {
 			update_scanline_offset(to_intel_crtc(crtc));
 			dev_priv->display.crtc_enable(crtc);
 		}
 
-		if (update_pipe) {
-			put_domains = modeset_get_crtc_power_domains(crtc);
-
-			/* make sure intel_modeset_check_state runs */
-			any_ms = true;
-		}
-
 		if (!modeset)
-			intel_pre_plane_update(intel_crtc);
+			intel_pre_plane_update(to_intel_crtc_state(crtc_state));
+
+		if (crtc->state->active && intel_crtc->atomic.update_fbc)
+			intel_fbc_enable(intel_crtc);
 
 		if (crtc->state->active &&
 		    (crtc->state->planes_changed || update_pipe))
 			drm_atomic_helper_commit_planes_on_crtc(crtc_state);
 
-		if (put_domains)
-			modeset_put_power_domains(dev_priv, put_domains);
-
-		intel_post_plane_update(intel_crtc);
-
-		if (modeset)
-			intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
+		if (pipe_config->base.active && needs_vblank_wait(pipe_config))
+			crtc_vblank_mask |= 1 << i;
 	}
 
 	/* FIXME: add subpixel order */
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
+	if (!state->legacy_cursor_update)
+		intel_atomic_wait_for_vblanks(dev, dev_priv, crtc_vblank_mask);
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		intel_post_plane_update(to_intel_crtc(crtc));
+
+		if (put_domains[i])
+			modeset_put_power_domains(dev_priv, put_domains[i]);
+	}
+
+	if (intel_state->modeset)
+		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
 
 	mutex_lock(&dev->struct_mutex);
 	drm_atomic_helper_cleanup_planes(dev, state);
 	mutex_unlock(&dev->struct_mutex);
 
-	if (any_ms)
+	if (hw_check)
 		intel_modeset_check_state(dev, state);
 
 	drm_atomic_state_free(state);
 
+	/* As one of the primary mmio accessors, KMS has a high likelihood
+	 * of triggering bugs in unclaimed access. After we finish
+	 * modesetting, see if an error has been flagged, and if so
+	 * enable debugging for the next modeset - and hope we catch
+	 * the culprit.
+	 *
+	 * XXX note that we assume display power is on at this point.
+	 * This might hold true now but we need to add pm helper to check
+	 * unclaimed only when the hardware is on, as atomic commits
+	 * can happen also when the device is completely off.
+	 */
+	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+
 	return 0;
 }
 
@@ -13897,7 +13927,7 @@ skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state
 	struct drm_i915_private *dev_priv;
 	int crtc_clock, cdclk;
 
-	if (!intel_crtc || !crtc_state)
+	if (!intel_crtc || !crtc_state->base.enable)
 		return DRM_PLANE_HELPER_NO_SCALING;
 
 	dev = intel_crtc->base.dev;
@@ -13946,32 +13976,6 @@ intel_check_primary_plane(struct drm_plane *plane,
 					     &state->visible);
 }
 
-static void
-intel_commit_primary_plane(struct drm_plane *plane,
-			   struct intel_plane_state *state)
-{
-	struct drm_crtc *crtc = state->base.crtc;
-	struct drm_framebuffer *fb = state->base.fb;
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	crtc = crtc ? crtc : plane->crtc;
-
-	dev_priv->display.update_primary_plane(crtc, fb,
-					       state->src.x1 >> 16,
-					       state->src.y1 >> 16);
-}
-
-static void
-intel_disable_primary_plane(struct drm_plane *plane,
-			    struct drm_crtc *crtc)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	dev_priv->display.update_primary_plane(crtc, NULL, 0, 0);
-}
-
 static void intel_begin_crtc_commit(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_crtc_state)
 {
@@ -14056,20 +14060,33 @@ static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
 	primary->plane = pipe;
 	primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe);
 	primary->check_plane = intel_check_primary_plane;
-	primary->commit_plane = intel_commit_primary_plane;
-	primary->disable_plane = intel_disable_primary_plane;
 	if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4)
 		primary->plane = !pipe;
 
 	if (INTEL_INFO(dev)->gen >= 9) {
 		intel_primary_formats = skl_primary_formats;
 		num_formats = ARRAY_SIZE(skl_primary_formats);
+
+		primary->update_plane = skylake_update_primary_plane;
+		primary->disable_plane = skylake_disable_primary_plane;
+	} else if (HAS_PCH_SPLIT(dev)) {
+		intel_primary_formats = i965_primary_formats;
+		num_formats = ARRAY_SIZE(i965_primary_formats);
+
+		primary->update_plane = ironlake_update_primary_plane;
+		primary->disable_plane = i9xx_disable_primary_plane;
 	} else if (INTEL_INFO(dev)->gen >= 4) {
 		intel_primary_formats = i965_primary_formats;
 		num_formats = ARRAY_SIZE(i965_primary_formats);
+
+		primary->update_plane = i9xx_update_primary_plane;
+		primary->disable_plane = i9xx_disable_primary_plane;
 	} else {
 		intel_primary_formats = i8xx_primary_formats;
 		num_formats = ARRAY_SIZE(i8xx_primary_formats);
+
+		primary->update_plane = i9xx_update_primary_plane;
+		primary->disable_plane = i9xx_disable_primary_plane;
 	}
 
 	drm_universal_plane_init(dev, &primary->base, 0,
@@ -14168,22 +14185,23 @@ static void
 intel_disable_cursor_plane(struct drm_plane *plane,
 			   struct drm_crtc *crtc)
 {
-	intel_crtc_update_cursor(crtc, false);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+
+	intel_crtc->cursor_addr = 0;
+	intel_crtc_update_cursor(crtc, NULL);
 }
 
 static void
-intel_commit_cursor_plane(struct drm_plane *plane,
-			  struct intel_plane_state *state)
+intel_update_cursor_plane(struct drm_plane *plane,
+			  const struct intel_crtc_state *crtc_state,
+			  const struct intel_plane_state *state)
 {
-	struct drm_crtc *crtc = state->base.crtc;
+	struct drm_crtc *crtc = crtc_state->base.crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = plane->dev;
-	struct intel_crtc *intel_crtc;
 	struct drm_i915_gem_object *obj = intel_fb_obj(state->base.fb);
 	uint32_t addr;
 
-	crtc = crtc ? crtc : plane->crtc;
-	intel_crtc = to_intel_crtc(crtc);
-
 	if (!obj)
 		addr = 0;
 	else if (!INTEL_INFO(dev)->cursor_needs_physical)
@@ -14192,9 +14210,7 @@ intel_commit_cursor_plane(struct drm_plane *plane,
 		addr = obj->phys_handle->busaddr;
 
 	intel_crtc->cursor_addr = addr;
-
-	if (crtc->state->active)
-		intel_crtc_update_cursor(crtc, state->visible);
+	intel_crtc_update_cursor(crtc, state);
 }
 
 static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev,
@@ -14220,7 +14236,7 @@ static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev,
 	cursor->plane = pipe;
 	cursor->frontbuffer_bit = INTEL_FRONTBUFFER_CURSOR(pipe);
 	cursor->check_plane = intel_check_cursor_plane;
-	cursor->commit_plane = intel_commit_cursor_plane;
+	cursor->update_plane = intel_update_cursor_plane;
 	cursor->disable_plane = intel_disable_cursor_plane;
 
 	drm_universal_plane_init(dev, &cursor->base, 0,
@@ -14667,10 +14683,12 @@ u32 intel_fb_pitch_limit(struct drm_device *dev, uint64_t fb_modifier,
 	u32 gen = INTEL_INFO(dev)->gen;
 
 	if (gen >= 9) {
+		int cpp = drm_format_plane_cpp(pixel_format, 0);
+
 		/* "The stride in bytes must not exceed the of the size of 8K
 		 *  pixels and 32K bytes."
 		 */
-		 return min(8192*drm_format_plane_cpp(pixel_format, 0), 32768);
+		return min(8192 * cpp, 32768);
 	} else if (gen >= 5 && !IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
 		return 32*1024;
 	} else if (gen >= 4) {
@@ -14694,6 +14712,7 @@ static int intel_framebuffer_init(struct drm_device *dev,
 				  struct drm_mode_fb_cmd2 *mode_cmd,
 				  struct drm_i915_gem_object *obj)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned int aligned_height;
 	int ret;
 	u32 pitch_limit, stride_alignment;
@@ -14735,7 +14754,8 @@ static int intel_framebuffer_init(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	stride_alignment = intel_fb_stride_alignment(dev, mode_cmd->modifier[0],
+	stride_alignment = intel_fb_stride_alignment(dev_priv,
+						     mode_cmd->modifier[0],
 						     mode_cmd->pixel_format);
 	if (mode_cmd->pitches[0] & (stride_alignment - 1)) {
 		DRM_DEBUG("pitch (%d) must be at least %u byte aligned\n",
@@ -14827,7 +14847,6 @@ static int intel_framebuffer_init(struct drm_device *dev,
 
 	drm_helper_mode_fill_fb_struct(&intel_fb->base, mode_cmd);
 	intel_fb->obj = obj;
-	intel_fb->obj->framebuffer_references++;
 
 	ret = drm_framebuffer_init(dev, &intel_fb->base, &intel_fb_funcs);
 	if (ret) {
@@ -14835,6 +14854,8 @@ static int intel_framebuffer_init(struct drm_device *dev,
 		return ret;
 	}
 
+	intel_fb->obj->framebuffer_references++;
+
 	return 0;
 }
 
@@ -14898,8 +14919,6 @@ static void intel_init_display(struct drm_device *dev)
 			haswell_crtc_compute_clock;
 		dev_priv->display.crtc_enable = haswell_crtc_enable;
 		dev_priv->display.crtc_disable = haswell_crtc_disable;
-		dev_priv->display.update_primary_plane =
-			skylake_update_primary_plane;
 	} else if (HAS_DDI(dev)) {
 		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -14908,8 +14927,6 @@ static void intel_init_display(struct drm_device *dev)
 			haswell_crtc_compute_clock;
 		dev_priv->display.crtc_enable = haswell_crtc_enable;
 		dev_priv->display.crtc_disable = haswell_crtc_disable;
-		dev_priv->display.update_primary_plane =
-			ironlake_update_primary_plane;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		dev_priv->display.get_pipe_config = ironlake_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -14918,8 +14935,6 @@ static void intel_init_display(struct drm_device *dev)
 			ironlake_crtc_compute_clock;
 		dev_priv->display.crtc_enable = ironlake_crtc_enable;
 		dev_priv->display.crtc_disable = ironlake_crtc_disable;
-		dev_priv->display.update_primary_plane =
-			ironlake_update_primary_plane;
 	} else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -14927,8 +14942,6 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock;
 		dev_priv->display.crtc_enable = valleyview_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
-		dev_priv->display.update_primary_plane =
-			i9xx_update_primary_plane;
 	} else {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -14936,8 +14949,6 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock;
 		dev_priv->display.crtc_enable = i9xx_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
-		dev_priv->display.update_primary_plane =
-			i9xx_update_primary_plane;
 	}
 
 	/* Returns the core display clock speed */
@@ -15243,12 +15254,89 @@ static void i915_disable_vga(struct drm_device *dev)
 
 void intel_modeset_init_hw(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	intel_update_cdclk(dev);
-	intel_prepare_ddi(dev);
+
+	dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq;
+
 	intel_init_clock_gating(dev);
 	intel_enable_gt_powersave(dev);
 }
 
+/*
+ * Calculate what we think the watermarks should be for the state we've read
+ * out of the hardware and then immediately program those watermarks so that
+ * we ensure the hardware settings match our internal state.
+ *
+ * We can calculate what we think WM's should be by creating a duplicate of the
+ * current state (which was constructed during hardware readout) and running it
+ * through the atomic check code to calculate new watermark values in the
+ * state object.
+ */
+static void sanitize_watermarks(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_atomic_state *state;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *cstate;
+	struct drm_modeset_acquire_ctx ctx;
+	int ret;
+	int i;
+
+	/* Only supported on platforms that use atomic watermark design */
+	if (!dev_priv->display.program_watermarks)
+		return;
+
+	/*
+	 * We need to hold connection_mutex before calling duplicate_state so
+	 * that the connector loop is protected.
+	 */
+	drm_modeset_acquire_init(&ctx, 0);
+retry:
+	ret = drm_modeset_lock_all_ctx(dev, &ctx);
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(&ctx);
+		goto retry;
+	} else if (WARN_ON(ret)) {
+		goto fail;
+	}
+
+	state = drm_atomic_helper_duplicate_state(dev, &ctx);
+	if (WARN_ON(IS_ERR(state)))
+		goto fail;
+
+	ret = intel_atomic_check(dev, state);
+	if (ret) {
+		/*
+		 * If we fail here, it means that the hardware appears to be
+		 * programmed in a way that shouldn't be possible, given our
+		 * understanding of watermark requirements.  This might mean a
+		 * mistake in the hardware readout code or a mistake in the
+		 * watermark calculations for a given platform.  Raise a WARN
+		 * so that this is noticeable.
+		 *
+		 * If this actually happens, we'll have to just leave the
+		 * BIOS-programmed watermarks untouched and hope for the best.
+		 */
+		WARN(true, "Could not determine valid watermarks for inherited state\n");
+		goto fail;
+	}
+
+	/* Write calculated watermark values back */
+	to_i915(dev)->wm.config = to_intel_atomic_state(state)->wm_config;
+	for_each_crtc_in_state(state, crtc, cstate, i) {
+		struct intel_crtc_state *cs = to_intel_crtc_state(cstate);
+
+		dev_priv->display.program_watermarks(cs);
+	}
+
+	drm_atomic_state_free(state);
+fail:
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+}
+
 void intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -15369,6 +15457,13 @@ void intel_modeset_init(struct drm_device *dev)
 		 */
 		intel_find_initial_plane_obj(crtc, &plane_config);
 	}
+
+	/*
+	 * Make sure hardware watermarks really match the state we read out.
+	 * Note that we need to do this after reconstructing the BIOS fb's
+	 * since the watermark calculation done here will use pstate->fb.
+	 */
+	sanitize_watermarks(dev);
 }
 
 static void intel_enable_pipe_a(struct drm_device *dev)
@@ -15425,6 +15520,17 @@ static bool intel_crtc_has_encoders(struct intel_crtc *crtc)
 	return false;
 }
 
+static bool intel_encoder_has_connectors(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct intel_connector *connector;
+
+	for_each_connector_on_encoder(dev, &encoder->base, connector)
+		return true;
+
+	return false;
+}
+
 static void intel_sanitize_crtc(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -15499,6 +15605,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 		crtc->base.state->active = crtc->active;
 		crtc->base.enabled = crtc->active;
 		crtc->base.state->connector_mask = 0;
+		crtc->base.state->encoder_mask = 0;
 
 		/* Because we only establish the connector -> encoder ->
 		 * crtc links if something is active, this means the
@@ -15534,7 +15641,6 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 {
 	struct intel_connector *connector;
 	struct drm_device *dev = encoder->base.dev;
-	bool active = false;
 
 	/* We need to check both for a crtc link (meaning that the
 	 * encoder is active and trying to read from a pipe) and the
@@ -15542,15 +15648,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 	bool has_active_crtc = encoder->base.crtc &&
 		to_intel_crtc(encoder->base.crtc)->active;
 
-	for_each_intel_connector(dev, connector) {
-		if (connector->base.encoder != &encoder->base)
-			continue;
-
-		active = true;
-		break;
-	}
-
-	if (active && !has_active_crtc) {
+	if (intel_encoder_has_connectors(encoder) && !has_active_crtc) {
 		DRM_DEBUG_KMS("[ENCODER:%d:%s] has active connectors but no active pipe!\n",
 			      encoder->base.base.id,
 			      encoder->base.name);
@@ -15643,16 +15741,40 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	struct intel_connector *connector;
 	int i;
 
+	dev_priv->active_crtcs = 0;
+
 	for_each_intel_crtc(dev, crtc) {
-		__drm_atomic_helper_crtc_destroy_state(&crtc->base, crtc->base.state);
-		memset(crtc->config, 0, sizeof(*crtc->config));
-		crtc->config->base.crtc = &crtc->base;
+		struct intel_crtc_state *crtc_state = crtc->config;
+		int pixclk = 0;
 
-		crtc->active = dev_priv->display.get_pipe_config(crtc,
-								 crtc->config);
+		__drm_atomic_helper_crtc_destroy_state(&crtc->base, &crtc_state->base);
+		memset(crtc_state, 0, sizeof(*crtc_state));
+		crtc_state->base.crtc = &crtc->base;
 
-		crtc->base.state->active = crtc->active;
-		crtc->base.enabled = crtc->active;
+		crtc_state->base.active = crtc_state->base.enable =
+			dev_priv->display.get_pipe_config(crtc, crtc_state);
+
+		crtc->base.enabled = crtc_state->base.enable;
+		crtc->active = crtc_state->base.active;
+
+		if (crtc_state->base.active) {
+			dev_priv->active_crtcs |= 1 << crtc->pipe;
+
+			if (IS_BROADWELL(dev_priv)) {
+				pixclk = ilk_pipe_pixel_rate(crtc_state);
+
+				/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+				if (crtc_state->ips_enabled)
+					pixclk = DIV_ROUND_UP(pixclk * 100, 95);
+			} else if (IS_VALLEYVIEW(dev_priv) ||
+				   IS_CHERRYVIEW(dev_priv) ||
+				   IS_BROXTON(dev_priv))
+				pixclk = crtc_state->base.adjusted_mode.crtc_clock;
+			else
+				WARN_ON(dev_priv->display.modeset_calc_cdclk);
+		}
+
+		dev_priv->min_pixclk[crtc->pipe] = pixclk;
 
 		readout_plane_state(crtc);
 
@@ -15716,6 +15838,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 				 */
 				encoder->base.crtc->state->connector_mask |=
 					1 << drm_connector_index(&connector->base);
+				encoder->base.crtc->state->encoder_mask |=
+					1 << drm_encoder_index(&encoder->base);
 			}
 
 		} else {
@@ -15812,63 +15936,88 @@ intel_modeset_setup_hw_state(struct drm_device *dev)
 	for_each_intel_crtc(dev, crtc) {
 		unsigned long put_domains;
 
-		put_domains = modeset_get_crtc_power_domains(&crtc->base);
+		put_domains = modeset_get_crtc_power_domains(&crtc->base, crtc->config);
 		if (WARN_ON(put_domains))
 			modeset_put_power_domains(dev_priv, put_domains);
 	}
 	intel_display_set_init_power(dev_priv, false);
+
+	intel_fbc_init_pipe_state(dev_priv);
 }
 
 void intel_display_resume(struct drm_device *dev)
 {
-	struct drm_atomic_state *state = drm_atomic_state_alloc(dev);
-	struct intel_connector *conn;
-	struct intel_plane *plane;
-	struct drm_crtc *crtc;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_atomic_state *state = dev_priv->modeset_restore_state;
+	struct drm_modeset_acquire_ctx ctx;
 	int ret;
+	bool setup = false;
 
-	if (!state)
-		return;
+	dev_priv->modeset_restore_state = NULL;
 
-	state->acquire_ctx = dev->mode_config.acquire_ctx;
+	/*
+	 * This is a cludge because with real atomic modeset mode_config.mutex
+	 * won't be taken. Unfortunately some probed state like
+	 * audio_codec_enable is still protected by mode_config.mutex, so lock
+	 * it here for now.
+	 */
+	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_acquire_init(&ctx, 0);
 
-	/* preserve complete old state, including dpll */
-	intel_atomic_get_shared_dpll_state(state);
+retry:
+	ret = drm_modeset_lock_all_ctx(dev, &ctx);
 
-	for_each_crtc(dev, crtc) {
-		struct drm_crtc_state *crtc_state =
-			drm_atomic_get_crtc_state(state, crtc);
+	/*
+	 * With MST, the number of connectors can change between suspend and
+	 * resume, which means that the state we want to restore might now be
+	 * impossible to use since it'll be pointing to non-existant
+	 * connectors.
+	 */
+	if (ret == 0 && state &&
+	    state->num_connector != dev->mode_config.num_connector) {
+		drm_atomic_state_free(state);
+		state = NULL;
+	}
 
-		ret = PTR_ERR_OR_ZERO(crtc_state);
-		if (ret)
-			goto err;
+	if (ret == 0 && !setup) {
+		setup = true;
 
-		/* force a restore */
-		crtc_state->mode_changed = true;
+		intel_modeset_setup_hw_state(dev);
+		i915_redisable_vga(dev);
 	}
 
-	for_each_intel_plane(dev, plane) {
-		ret = PTR_ERR_OR_ZERO(drm_atomic_get_plane_state(state, &plane->base));
-		if (ret)
-			goto err;
-	}
+	if (ret == 0 && state) {
+		struct drm_crtc_state *crtc_state;
+		struct drm_crtc *crtc;
+		int i;
 
-	for_each_intel_connector(dev, conn) {
-		ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(state, &conn->base));
-		if (ret)
-			goto err;
+		state->acquire_ctx = &ctx;
+
+		for_each_crtc_in_state(state, crtc, crtc_state, i) {
+			/*
+			 * Force recalculation even if we restore
+			 * current state. With fast modeset this may not result
+			 * in a modeset when the state is compatible.
+			 */
+			crtc_state->mode_changed = true;
+		}
+
+		ret = drm_atomic_commit(state);
 	}
 
-	intel_modeset_setup_hw_state(dev);
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(&ctx);
+		goto retry;
+	}
 
-	i915_redisable_vga(dev);
-	ret = drm_atomic_commit(state);
-	if (!ret)
-		return;
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+	mutex_unlock(&dev->mode_config.mutex);
 
-err:
-	DRM_ERROR("Restoring old state failed with %i\n", ret);
-	drm_atomic_state_free(state);
+	if (ret) {
+		DRM_ERROR("Restoring old state failed with %i\n", ret);
+		drm_atomic_state_free(state);
+	}
 }
 
 void intel_modeset_gem_init(struct drm_device *dev)
@@ -15877,9 +16026,7 @@ void intel_modeset_gem_init(struct drm_device *dev)
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	mutex_lock(&dev->struct_mutex);
 	intel_init_gt_powersave(dev);
-	mutex_unlock(&dev->struct_mutex);
 
 	intel_modeset_init_hw(dev);
 
@@ -15946,7 +16093,7 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_unregister_dsm_handler();
 
-	intel_fbc_disable(dev_priv);
+	intel_fbc_global_disable(dev_priv);
 
 	/* flush any delayed tasks or pending work */
 	flush_scheduled_work();
@@ -15959,9 +16106,7 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_cleanup_overlay(dev);
 
-	mutex_lock(&dev->struct_mutex);
 	intel_cleanup_gt_powersave(dev);
-	mutex_unlock(&dev->struct_mutex);
 
 	intel_teardown_gmbus(dev);
 }
@@ -16156,7 +16301,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 	for_each_pipe(dev_priv, i) {
 		err_printf(m, "Pipe [%d]:\n", i);
 		err_printf(m, "  Power: %s\n",
-			   error->pipe[i].power_domain_on ? "on" : "off");
+			   onoff(error->pipe[i].power_domain_on));
 		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
 		err_printf(m, "  STAT: %08x\n", error->pipe[i].stat);
 
@@ -16184,7 +16329,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "CPU transcoder: %c\n",
 			   transcoder_name(error->transcoder[i].cpu_transcoder));
 		err_printf(m, "  Power: %s\n",
-			   error->transcoder[i].power_domain_on ? "on" : "off");
+			   onoff(error->transcoder[i].power_domain_on));
 		err_printf(m, "  CONF: %08x\n", error->transcoder[i].conf);
 		err_printf(m, "  HTOTAL: %08x\n", error->transcoder[i].htotal);
 		err_printf(m, "  HBLANK: %08x\n", error->transcoder[i].hblank);
@@ -16194,24 +16339,3 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  VSYNC: %08x\n", error->transcoder[i].vsync);
 	}
 }
-
-void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file)
-{
-	struct intel_crtc *crtc;
-
-	for_each_intel_crtc(dev, crtc) {
-		struct intel_unpin_work *work;
-
-		spin_lock_irq(&dev->event_lock);
-
-		work = crtc->unpin_work;
-
-		if (work && work->event &&
-		    work->event->base.file_priv == file) {
-			kfree(work->event);
-			work->event = NULL;
-		}
-
-		spin_unlock_irq(&dev->event_lock);
-	}
-}
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 60ee2375a..412a34c39 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -157,14 +157,9 @@ intel_dp_max_link_bw(struct intel_dp  *intel_dp)
 static u8 intel_dp_max_lane_count(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = intel_dig_port->base.base.dev;
 	u8 source_max, sink_max;
 
-	source_max = 4;
-	if (HAS_DDI(dev) && intel_dig_port->port == PORT_A &&
-	    (intel_dig_port->saved_port_bits & DDI_A_4_LANES) == 0)
-		source_max = 2;
-
+	source_max = intel_dig_port->max_lanes;
 	sink_max = drm_dp_max_lane_count(intel_dp->dpcd);
 
 	return min(source_max, sink_max);
@@ -208,6 +203,7 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	int target_clock = mode->clock;
 	int max_rate, mode_rate, max_lanes, max_link_clock;
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
 	if (is_edp(intel_dp) && fixed_mode) {
 		if (mode->hdisplay > fixed_mode->hdisplay)
@@ -225,7 +221,7 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
 	mode_rate = intel_dp_link_required(target_clock, 18);
 
-	if (mode_rate > max_rate)
+	if (mode_rate > max_rate || target_clock > max_dotclk)
 		return MODE_CLOCK_HIGH;
 
 	if (mode->clock < 10000)
@@ -340,8 +336,12 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 		release_cl_override = IS_CHERRYVIEW(dev) &&
 			!chv_phy_powergate_ch(dev_priv, phy, ch, true);
 
-		vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ?
-				 &chv_dpll[0].dpll : &vlv_dpll[0].dpll);
+		if (vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ?
+				     &chv_dpll[0].dpll : &vlv_dpll[0].dpll)) {
+			DRM_ERROR("Failed to force on pll for pipe %c!\n",
+				  pipe_name(pipe));
+			return;
+		}
 	}
 
 	/*
@@ -980,7 +980,10 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 		if (WARN_ON(txsize > 20))
 			return -E2BIG;
 
-		memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size);
+		if (msg->buffer)
+			memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size);
+		else
+			WARN_ON(msg->size);
 
 		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize);
 		if (ret > 0) {
@@ -1189,7 +1192,6 @@ intel_dp_aux_fini(struct intel_dp *intel_dp)
 static int
 intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	enum port port = intel_dig_port->port;
 	int ret;
@@ -1200,7 +1202,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 	if (!intel_dp->aux.name)
 		return -ENOMEM;
 
-	intel_dp->aux.dev = dev->dev;
+	intel_dp->aux.dev = connector->base.kdev;
 	intel_dp->aux.transfer = intel_dp_aux_transfer;
 
 	DRM_DEBUG_KMS("registering %s bus for %s\n",
@@ -1215,16 +1217,6 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 		return ret;
 	}
 
-	ret = sysfs_create_link(&connector->base.kdev->kobj,
-				&intel_dp->aux.ddc.dev.kobj,
-				intel_dp->aux.ddc.dev.kobj.name);
-	if (ret < 0) {
-		DRM_ERROR("sysfs_create_link() for %s failed (%d)\n",
-			  intel_dp->aux.name, ret);
-		intel_dp_aux_fini(intel_dp);
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -1233,9 +1225,7 @@ intel_dp_connector_unregister(struct intel_connector *intel_connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base);
 
-	if (!intel_connector->mst_port)
-		sysfs_remove_link(&intel_connector->base.kdev->kobj,
-				  intel_dp->aux.ddc.dev.kobj.name);
+	intel_dp_aux_fini(intel_dp);
 	intel_connector_unregister(intel_connector);
 }
 
@@ -1812,12 +1802,21 @@ static void wait_panel_off(struct intel_dp *intel_dp)
 
 static void wait_panel_power_cycle(struct intel_dp *intel_dp)
 {
+	ktime_t panel_power_on_time;
+	s64 panel_power_off_duration;
+
 	DRM_DEBUG_KMS("Wait for panel power cycle\n");
 
+	/* take the difference of currrent time and panel power off time
+	 * and then make panel wait for t11_t12 if needed. */
+	panel_power_on_time = ktime_get_boottime();
+	panel_power_off_duration = ktime_ms_delta(panel_power_on_time, intel_dp->panel_power_off_time);
+
 	/* When we disable the VDD override bit last we have to do the manual
 	 * wait. */
-	wait_remaining_ms_from_jiffies(intel_dp->last_power_cycle,
-				       intel_dp->panel_power_cycle_delay);
+	if (panel_power_off_duration < (s64)intel_dp->panel_power_cycle_delay)
+		wait_remaining_ms_from_jiffies(jiffies,
+				       intel_dp->panel_power_cycle_delay - panel_power_off_duration);
 
 	wait_panel_status(intel_dp, IDLE_CYCLE_MASK, IDLE_CYCLE_VALUE);
 }
@@ -1969,7 +1968,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	I915_READ(pp_stat_reg), I915_READ(pp_ctrl_reg));
 
 	if ((pp & POWER_TARGET_ON) == 0)
-		intel_dp->last_power_cycle = jiffies;
+		intel_dp->panel_power_off_time = ktime_get_boottime();
 
 	power_domain = intel_display_port_aux_power_domain(intel_encoder);
 	intel_display_power_put(dev_priv, power_domain);
@@ -2118,7 +2117,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
-	intel_dp->last_power_cycle = jiffies;
+	intel_dp->panel_power_off_time = ktime_get_boottime();
 	wait_panel_off(intel_dp);
 
 	/* We got a reference when we enabled the VDD. */
@@ -2243,11 +2242,6 @@ static void intel_edp_backlight_power(struct intel_connector *connector,
 		_intel_edp_backlight_off(intel_dp);
 }
 
-static const char *state_string(bool enabled)
-{
-	return enabled ? "on" : "off";
-}
-
 static void assert_dp_port(struct intel_dp *intel_dp, bool state)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -2257,7 +2251,7 @@ static void assert_dp_port(struct intel_dp *intel_dp, bool state)
 	I915_STATE_WARN(cur_state != state,
 			"DP port %c state assertion failure (expected %s, current %s)\n",
 			port_name(dig_port->port),
-			state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 #define assert_dp_port_disabled(d) assert_dp_port((d), false)
 
@@ -2267,7 +2261,7 @@ static void assert_edp_pll(struct drm_i915_private *dev_priv, bool state)
 
 	I915_STATE_WARN(cur_state != state,
 			"eDP PLL state assertion failure (expected %s, current %s)\n",
-			state_string(state), state_string(cur_state));
+			onoff(state), onoff(cur_state));
 }
 #define assert_edp_pll_enabled(d) assert_edp_pll((d), true)
 #define assert_edp_pll_disabled(d) assert_edp_pll((d), false)
@@ -4024,7 +4018,7 @@ static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp)
 	} while (--attempts && count);
 
 	if (attempts == 0) {
-		DRM_ERROR("TIMEOUT: Sink CRC counter is not zeroed\n");
+		DRM_DEBUG_KMS("TIMEOUT: Sink CRC counter is not zeroed after calculation is stopped\n");
 		ret = -ETIMEDOUT;
 	}
 
@@ -4564,7 +4558,7 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 {
 	if (HAS_PCH_IBX(dev_priv))
 		return ibx_digital_port_connected(dev_priv, port);
-	if (HAS_PCH_SPLIT(dev_priv))
+	else if (HAS_PCH_SPLIT(dev_priv))
 		return cpt_digital_port_connected(dev_priv, port);
 	else if (IS_BROXTON(dev_priv))
 		return bxt_digital_port_connected(dev_priv, port);
@@ -4884,7 +4878,6 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
-	intel_dp_aux_fini(intel_dp);
 	intel_dp_mst_encoder_cleanup(intel_dig_port);
 	if (is_edp(intel_dp)) {
 		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
@@ -5132,7 +5125,7 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 
 static void intel_dp_init_panel_power_timestamps(struct intel_dp *intel_dp)
 {
-	intel_dp->last_power_cycle = jiffies;
+	intel_dp->panel_power_off_time = ktime_get_boottime();
 	intel_dp->last_power_on = jiffies;
 	intel_dp->last_backlight_off = jiffies;
 }
@@ -5849,6 +5842,11 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	enum port port = intel_dig_port->port;
 	int type, ret;
 
+	if (WARN(intel_dig_port->max_lanes < 1,
+		 "Not enough lanes (%d) for DP on port %c\n",
+		 intel_dig_port->max_lanes, port_name(port)))
+		return false;
+
 	intel_dp->pps_pipe = INVALID_PIPE;
 
 	/* intel_dp vfuncs */
@@ -6046,6 +6044,7 @@ intel_dp_init(struct drm_device *dev,
 
 	intel_dig_port->port = port;
 	intel_dig_port->dp.output_reg = output_reg;
+	intel_dig_port->max_lanes = 4;
 
 	intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
 	if (IS_CHERRYVIEW(dev)) {
@@ -6113,19 +6112,6 @@ void intel_dp_mst_resume(struct drm_device *dev)
 
 			ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
 			if (ret != 0) {
-				/*
-				 * For some reason, some laptops can't bring
-				 * their MST docks back up immediately after
-				 * resume and need to wait a short period of
-				 * time before aux transactions with the dock
-				 * become functional again. Until we find a
-				 * proper fix for this, this workaround should
-				 * suffice
-				 */
-				msleep(30);
-				ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
-			}
-			if (ret != 0) {
 				intel_dp_check_mst_status(&intel_dig_port->dp);
 			}
 		}
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index db6361b5a..2c999725b 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -78,8 +78,6 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 		return false;
 	}
 
-	if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, found->port))
-		pipe_config->has_audio = true;
 	mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp);
 
 	pipe_config->pbn = mst_pbn;
@@ -104,11 +102,6 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder)
 	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = encoder->base.crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
 	int ret;
 
 	DRM_DEBUG_KMS("%d\n", intel_dp->active_mst_links);
@@ -119,10 +112,6 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder)
 	if (ret) {
 		DRM_ERROR("failed to update payload %d\n", ret);
 	}
-	if (intel_crtc->config->has_audio) {
-		intel_audio_codec_disable(encoder);
-		intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
-	}
 }
 
 static void intel_mst_post_disable_dp(struct intel_encoder *encoder)
@@ -184,6 +173,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder)
 	intel_mst->port = found->port;
 
 	if (intel_dp->active_mst_links == 0) {
+		intel_prepare_ddi_buffer(&intel_dig_port->base);
+
 		intel_ddi_clk_select(&intel_dig_port->base, intel_crtc->config);
 
 		intel_dp_set_link_params(intel_dp, intel_crtc->config);
@@ -219,7 +210,6 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder)
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	enum port port = intel_dig_port->port;
 	int ret;
 
@@ -232,13 +222,6 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder)
 	ret = drm_dp_check_act_status(&intel_dp->mst_mgr);
 
 	ret = drm_dp_update_payload_part2(&intel_dp->mst_mgr);
-
-	if (crtc->config->has_audio) {
-		DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n",
-				 pipe_name(crtc->pipe));
-		intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
-		intel_audio_codec_enable(encoder);
-	}
 }
 
 static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder,
@@ -264,9 +247,6 @@ static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder,
 
 	pipe_config->has_dp_encoder = true;
 
-	pipe_config->has_audio =
-		intel_ddi_is_audio_enabled(dev_priv, crtc);
-
 	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 	if (temp & TRANS_DDI_PHSYNC)
 		flags |= DRM_MODE_FLAG_PHSYNC;
@@ -369,6 +349,8 @@ static enum drm_mode_status
 intel_dp_mst_mode_valid(struct drm_connector *connector,
 			struct drm_display_mode *mode)
 {
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+
 	/* TODO - validate mode against available PBN for link */
 	if (mode->clock < 10000)
 		return MODE_CLOCK_LOW;
@@ -376,6 +358,9 @@ intel_dp_mst_mode_valid(struct drm_connector *connector,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return MODE_H_ILLEGAL;
 
+	if (mode->clock > max_dotclk)
+		return MODE_CLOCK_HIGH;
+
 	return MODE_OK;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 3ce3bee36..3a30b37d6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -33,6 +33,7 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_dp_dual_mode_helper.h>
 #include <drm/drm_dp_mst_helper.h>
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic.h>
@@ -246,7 +247,18 @@ struct intel_atomic_state {
 	struct drm_atomic_state base;
 
 	unsigned int cdclk;
-	bool dpll_set;
+
+	/*
+	 * Calculated device cdclk, can be different from cdclk
+	 * only when all crtc's are DPMS off.
+	 */
+	unsigned int dev_cdclk;
+
+	bool dpll_set, modeset;
+
+	unsigned int active_crtcs;
+	unsigned int min_pixclk[I915_MAX_PIPES];
+
 	struct intel_shared_dpll_config shared_dpll[I915_NUM_PLLS];
 	struct intel_wm_config wm_config;
 };
@@ -367,7 +379,8 @@ struct intel_crtc_state {
 
 	bool update_pipe; /* can a fast modeset be performed? */
 	bool disable_cxsr;
-	bool wm_changed; /* watermarks are updated */
+	bool update_wm_pre, update_wm_post; /* watermarks are updated */
+	bool fb_changed; /* fb on any of the planes is changed */
 
 	/* Pipe source size (ie. panel fitter input size)
 	 * All planes will be positioned inside this space,
@@ -481,6 +494,8 @@ struct intel_crtc_state {
 
 	bool ips_enabled;
 
+	bool enable_fbc;
+
 	bool double_wide;
 
 	bool dp_encoder_is_mst;
@@ -531,16 +546,13 @@ struct intel_mmio_flip {
  */
 struct intel_crtc_atomic_commit {
 	/* Sleepable operations to perform before commit */
-	bool disable_fbc;
-	bool disable_ips;
-	bool pre_disable_primary;
 
 	/* Sleepable operations to perform after commit */
 	unsigned fb_bits;
-	bool wait_vblank;
-	bool update_fbc;
 	bool post_enable_primary;
-	unsigned update_sprite_watermarks;
+
+	/* Sleepable operations to perform before and after commit */
+	bool update_fbc;
 };
 
 struct intel_crtc {
@@ -564,7 +576,7 @@ struct intel_crtc {
 	/* Display surface base address adjustement for pageflips. Note that on
 	 * gen4+ this only adjusts up to a tile, offsets within a tile are
 	 * handled in the hw itself (with the TILEOFF register). */
-	unsigned long dspaddr_offset;
+	u32 dspaddr_offset;
 	int adjusted_x;
 	int adjusted_y;
 
@@ -647,23 +659,17 @@ struct intel_plane {
 	/*
 	 * NOTE: Do not place new plane state fields here (e.g., when adding
 	 * new plane properties).  New runtime state should now be placed in
-	 * the intel_plane_state structure and accessed via drm_plane->state.
+	 * the intel_plane_state structure and accessed via plane_state.
 	 */
 
 	void (*update_plane)(struct drm_plane *plane,
-			     struct drm_crtc *crtc,
-			     struct drm_framebuffer *fb,
-			     int crtc_x, int crtc_y,
-			     unsigned int crtc_w, unsigned int crtc_h,
-			     uint32_t x, uint32_t y,
-			     uint32_t src_w, uint32_t src_h);
+			     const struct intel_crtc_state *crtc_state,
+			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct drm_plane *plane,
 			      struct drm_crtc *crtc);
 	int (*check_plane)(struct drm_plane *plane,
 			   struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *state);
-	void (*commit_plane)(struct drm_plane *plane,
-			     struct intel_plane_state *state);
 };
 
 struct intel_watermark_params {
@@ -698,6 +704,10 @@ struct cxsr_latency {
 struct intel_hdmi {
 	i915_reg_t hdmi_reg;
 	int ddc_bus;
+	struct {
+		enum drm_dp_dual_mode_type type;
+		int max_tmds_clock;
+	} dp_dual_mode;
 	bool limited_color_range;
 	bool color_range_auto;
 	bool has_hdmi_sink;
@@ -765,9 +775,9 @@ struct intel_dp {
 	int backlight_off_delay;
 	struct delayed_work panel_vdd_work;
 	bool want_panel_vdd;
-	unsigned long last_power_cycle;
 	unsigned long last_power_on;
 	unsigned long last_backlight_off;
+	ktime_t panel_power_off_time;
 
 	struct notifier_block edp_notifier;
 
@@ -817,6 +827,7 @@ struct intel_digital_port {
 	struct intel_hdmi hdmi;
 	enum irqreturn (*hpd_pulse)(struct intel_digital_port *, bool);
 	bool release_cl2_override;
+	uint8_t max_lanes;
 	/* for communication with audio component; protected by av_mutex */
 	const struct drm_connector *audio_connector;
 };
@@ -903,9 +914,7 @@ struct intel_unpin_work {
 };
 
 struct intel_load_detect_pipe {
-	struct drm_framebuffer *release_fb;
-	bool load_detect_temp;
-	int dpms_mode;
+	struct drm_atomic_state *restore_state;
 };
 
 static inline struct intel_encoder *
@@ -988,6 +997,8 @@ static inline bool intel_irqs_enabled(struct drm_i915_private *dev_priv)
 int intel_get_crtc_scanline(struct intel_crtc *crtc);
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
 				     unsigned int pipe_mask);
+void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv,
+				     unsigned int pipe_mask);
 
 /* intel_crt.c */
 void intel_crt_init(struct drm_device *dev);
@@ -996,7 +1007,7 @@ void intel_crt_init(struct drm_device *dev);
 /* intel_ddi.c */
 void intel_ddi_clk_select(struct intel_encoder *encoder,
 			  const struct intel_crtc_state *pipe_config);
-void intel_prepare_ddi(struct drm_device *dev);
+void intel_prepare_ddi_buffer(struct intel_encoder *encoder);
 void hsw_fdi_link_train(struct drm_crtc *crtc);
 void intel_ddi_init(struct drm_device *dev, enum port port);
 enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder);
@@ -1013,8 +1024,6 @@ void intel_ddi_set_pipe_settings(struct drm_crtc *crtc);
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp);
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
 void intel_ddi_fdi_disable(struct drm_crtc *crtc);
-bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
-				 struct intel_crtc *intel_crtc);
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config);
 struct intel_encoder *
@@ -1041,8 +1050,8 @@ unsigned int intel_fb_align_height(struct drm_device *dev,
 				   uint64_t fb_format_modifier);
 void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire,
 			enum fb_op_origin origin);
-u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier,
-			      uint32_t pixel_format);
+u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv,
+			      uint64_t fb_modifier, uint32_t pixel_format);
 
 /* intel_audio.c */
 void intel_init_audio(struct drm_device *dev);
@@ -1126,9 +1135,8 @@ int intel_plane_atomic_set_property(struct drm_plane *plane,
 int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 				    struct drm_plane_state *plane_state);
 
-unsigned int
-intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
-		  uint64_t fb_format_modifier, unsigned int plane);
+unsigned int intel_tile_height(const struct drm_i915_private *dev_priv,
+			       uint64_t fb_modifier, unsigned int cpp);
 
 static inline bool
 intel_rotation_90_or_270(unsigned int rotation)
@@ -1149,8 +1157,8 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
 struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
 						struct intel_crtc_state *state);
 
-void vlv_force_pll_on(struct drm_device *dev, enum pipe pipe,
-		      const struct dpll *dpll);
+int vlv_force_pll_on(struct drm_device *dev, enum pipe pipe,
+		     const struct dpll *dpll);
 void vlv_force_pll_off(struct drm_device *dev, enum pipe pipe);
 
 /* modesetting asserts */
@@ -1167,11 +1175,11 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state);
 #define assert_pipe_enabled(d, p) assert_pipe(d, p, true)
 #define assert_pipe_disabled(d, p) assert_pipe(d, p, false)
-unsigned long intel_gen4_compute_page_offset(struct drm_i915_private *dev_priv,
-					     int *x, int *y,
-					     unsigned int tiling_mode,
-					     unsigned int bpp,
-					     unsigned int pitch);
+u32 intel_compute_tile_offset(struct drm_i915_private *dev_priv,
+			      int *x, int *y,
+			      uint64_t fb_modifier,
+			      unsigned int cpp,
+			      unsigned int pitch);
 void intel_prepare_reset(struct drm_device *dev);
 void intel_finish_reset(struct drm_device *dev);
 void hsw_enable_pc8(struct drm_i915_private *dev_priv);
@@ -1207,7 +1215,6 @@ enum intel_display_power_domain
 intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config);
-void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file);
 
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
@@ -1222,7 +1229,7 @@ u32 skl_plane_ctl_rotation(unsigned int rotation);
 
 /* intel_csr.c */
 void intel_csr_ucode_init(struct drm_i915_private *);
-void intel_csr_load_program(struct drm_i915_private *);
+bool intel_csr_load_program(struct drm_i915_private *);
 void intel_csr_ucode_fini(struct drm_i915_private *);
 
 /* intel_dp.c */
@@ -1325,13 +1332,16 @@ static inline void intel_fbdev_restore_mode(struct drm_device *dev)
 #endif
 
 /* intel_fbc.c */
+void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
+			   struct drm_atomic_state *state);
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv);
-void intel_fbc_deactivate(struct intel_crtc *crtc);
-void intel_fbc_update(struct intel_crtc *crtc);
+void intel_fbc_pre_update(struct intel_crtc *crtc);
+void intel_fbc_post_update(struct intel_crtc *crtc);
 void intel_fbc_init(struct drm_i915_private *dev_priv);
+void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv);
 void intel_fbc_enable(struct intel_crtc *crtc);
-void intel_fbc_disable(struct drm_i915_private *dev_priv);
-void intel_fbc_disable_crtc(struct intel_crtc *crtc);
+void intel_fbc_disable(struct intel_crtc *crtc);
+void intel_fbc_global_disable(struct drm_i915_private *dev_priv);
 void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 			  unsigned int frontbuffer_bits,
 			  enum fb_op_origin origin);
@@ -1346,6 +1356,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
 bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 			       struct intel_crtc_state *pipe_config);
+void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable);
 
 
 /* intel_lvds.c */
@@ -1560,6 +1571,7 @@ void skl_wm_get_hw_state(struct drm_device *dev);
 void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 			  struct skl_ddb_allocation *ddb /* out */);
 uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config);
+int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6);
 
 /* intel_sdvo.c */
 bool intel_sdvo_init(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 0193c62a5..01b8e9f4c 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -478,8 +478,8 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("\n");
 
-	intel_dsi_prepare(encoder);
 	intel_enable_dsi_pll(encoder);
+	intel_dsi_prepare(encoder);
 
 	/* Panel Enable over CRC PMIC */
 	if (intel_dsi->gpio_panel)
@@ -634,7 +634,6 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	u32 val;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -642,9 +641,13 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder)
 
 	intel_dsi_clear_device_ready(encoder);
 
-	val = I915_READ(DSPCLK_GATE_D);
-	val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
-	I915_WRITE(DSPCLK_GATE_D, val);
+	if (!IS_BROXTON(dev_priv)) {
+		u32 val;
+
+		val = I915_READ(DSPCLK_GATE_D);
+		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
+		I915_WRITE(DSPCLK_GATE_D, val);
+	}
 
 	drm_panel_unprepare(intel_dsi->panel);
 
@@ -709,7 +712,7 @@ out:
 static void intel_dsi_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
-	u32 pclk = 0;
+	u32 pclk;
 	DRM_DEBUG_KMS("\n");
 
 	pipe_config->has_dsi_encoder = true;
@@ -720,12 +723,7 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	 */
 	pipe_config->dpll_hw_state.dpll_md = 0;
 
-	if (IS_BROXTON(encoder->base.dev))
-		pclk = bxt_get_dsi_pclk(encoder, pipe_config->pipe_bpp);
-	else if (IS_VALLEYVIEW(encoder->base.dev) ||
-		 IS_CHERRYVIEW(encoder->base.dev))
-		pclk = vlv_get_dsi_pclk(encoder, pipe_config->pipe_bpp);
-
+	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp);
 	if (!pclk)
 		return;
 
@@ -787,10 +785,9 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
-	unsigned int bpp = intel_crtc->config->pipe_bpp;
+	unsigned int bpp = dsi_pixel_format_bpp(intel_dsi->pixel_format);
 	unsigned int lane_count = intel_dsi->lane_count;
 
 	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
@@ -861,7 +858,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
 	enum port port;
-	unsigned int bpp = intel_crtc->config->pipe_bpp;
+	unsigned int bpp = dsi_pixel_format_bpp(intel_dsi->pixel_format);
 	u32 val, tmp;
 	u16 mode_hdisplay;
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index 02551ff22..92f39227b 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -34,6 +34,8 @@
 #define DSI_DUAL_LINK_FRONT_BACK	1
 #define DSI_DUAL_LINK_PIXEL_ALT		2
 
+int dsi_pixel_format_bpp(int pixel_format);
+
 struct intel_dsi_host;
 
 struct intel_dsi {
@@ -126,8 +128,7 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 
 extern void intel_enable_dsi_pll(struct intel_encoder *encoder);
 extern void intel_disable_dsi_pll(struct intel_encoder *encoder);
-extern u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp);
-extern u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp);
+extern u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp);
 extern void intel_dsi_reset_clocks(struct intel_encoder *encoder,
 							enum port port);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index e8113ad65..7f145b4fe 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -234,28 +234,33 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	if (!gtable[gpio].init) {
 		/* program the function */
 		/* FIXME: remove constant below */
-		vlv_gpio_nc_write(dev_priv, function, 0x2000CC00);
+		vlv_iosf_sb_write(dev_priv, IOSF_PORT_GPIO_NC, function,
+				  0x2000CC00);
 		gtable[gpio].init = 1;
 	}
 
 	val = 0x4 | action;
 
 	/* pull up/down */
-	vlv_gpio_nc_write(dev_priv, pad, val);
+	vlv_iosf_sb_write(dev_priv, IOSF_PORT_GPIO_NC, pad, val);
 	mutex_unlock(&dev_priv->sb_lock);
 
 out:
 	return data;
 }
 
+static const u8 *mipi_exec_i2c_skip(struct intel_dsi *intel_dsi, const u8 *data)
+{
+	return data + *(data + 6) + 7;
+}
+
 typedef const u8 * (*fn_mipi_elem_exec)(struct intel_dsi *intel_dsi,
 					const u8 *data);
 static const fn_mipi_elem_exec exec_elem[] = {
-	NULL, /* reserved */
-	mipi_exec_send_packet,
-	mipi_exec_delay,
-	mipi_exec_gpio,
-	NULL, /* status read; later */
+	[MIPI_SEQ_ELEM_SEND_PKT] = mipi_exec_send_packet,
+	[MIPI_SEQ_ELEM_DELAY] = mipi_exec_delay,
+	[MIPI_SEQ_ELEM_GPIO] = mipi_exec_gpio,
+	[MIPI_SEQ_ELEM_I2C] = mipi_exec_i2c_skip,
 };
 
 /*
@@ -265,107 +270,114 @@ static const fn_mipi_elem_exec exec_elem[] = {
  */
 
 static const char * const seq_name[] = {
-	"UNDEFINED",
-	"MIPI_SEQ_ASSERT_RESET",
-	"MIPI_SEQ_INIT_OTP",
-	"MIPI_SEQ_DISPLAY_ON",
-	"MIPI_SEQ_DISPLAY_OFF",
-	"MIPI_SEQ_DEASSERT_RESET"
+	[MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET",
+	[MIPI_SEQ_INIT_OTP] = "MIPI_SEQ_INIT_OTP",
+	[MIPI_SEQ_DISPLAY_ON] = "MIPI_SEQ_DISPLAY_ON",
+	[MIPI_SEQ_DISPLAY_OFF]  = "MIPI_SEQ_DISPLAY_OFF",
+	[MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET",
+	[MIPI_SEQ_BACKLIGHT_ON] = "MIPI_SEQ_BACKLIGHT_ON",
+	[MIPI_SEQ_BACKLIGHT_OFF] = "MIPI_SEQ_BACKLIGHT_OFF",
+	[MIPI_SEQ_TEAR_ON] = "MIPI_SEQ_TEAR_ON",
+	[MIPI_SEQ_TEAR_OFF] = "MIPI_SEQ_TEAR_OFF",
+	[MIPI_SEQ_POWER_ON] = "MIPI_SEQ_POWER_ON",
+	[MIPI_SEQ_POWER_OFF] = "MIPI_SEQ_POWER_OFF",
 };
 
-static void generic_exec_sequence(struct intel_dsi *intel_dsi, const u8 *data)
+static const char *sequence_name(enum mipi_seq seq_id)
+{
+	if (seq_id < ARRAY_SIZE(seq_name) && seq_name[seq_id])
+		return seq_name[seq_id];
+	else
+		return "(unknown)";
+}
+
+static void generic_exec_sequence(struct drm_panel *panel, enum mipi_seq seq_id)
 {
+	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
+	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
+	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
+	const u8 *data;
 	fn_mipi_elem_exec mipi_elem_exec;
-	int index;
 
-	if (!data)
+	if (WARN_ON(seq_id >= ARRAY_SIZE(dev_priv->vbt.dsi.sequence)))
 		return;
 
-	DRM_DEBUG_DRIVER("Starting MIPI sequence - %s\n", seq_name[*data]);
+	data = dev_priv->vbt.dsi.sequence[seq_id];
+	if (!data) {
+		DRM_DEBUG_KMS("MIPI sequence %d - %s not available\n",
+			      seq_id, sequence_name(seq_id));
+		return;
+	}
 
-	/* go to the first element of the sequence */
-	data++;
+	WARN_ON(*data != seq_id);
 
-	/* parse each byte till we reach end of sequence byte - 0x00 */
-	while (1) {
-		index = *data;
-		mipi_elem_exec = exec_elem[index];
-		if (!mipi_elem_exec) {
-			DRM_ERROR("Unsupported MIPI element, skipping sequence execution\n");
-			return;
-		}
+	DRM_DEBUG_KMS("Starting MIPI sequence %d - %s\n",
+		      seq_id, sequence_name(seq_id));
 
-		/* goto element payload */
-		data++;
+	/* Skip Sequence Byte. */
+	data++;
 
-		/* execute the element specific rotines */
-		data = mipi_elem_exec(intel_dsi, data);
+	/* Skip Size of Sequence. */
+	if (dev_priv->vbt.dsi.seq_version >= 3)
+		data += 4;
 
-		/*
-		 * After processing the element, data should point to
-		 * next element or end of sequence
-		 * check if have we reached end of sequence
-		 */
-		if (*data == 0x00)
+	while (1) {
+		u8 operation_byte = *data++;
+		u8 operation_size = 0;
+
+		if (operation_byte == MIPI_SEQ_ELEM_END)
 			break;
+
+		if (operation_byte < ARRAY_SIZE(exec_elem))
+			mipi_elem_exec = exec_elem[operation_byte];
+		else
+			mipi_elem_exec = NULL;
+
+		/* Size of Operation. */
+		if (dev_priv->vbt.dsi.seq_version >= 3)
+			operation_size = *data++;
+
+		if (mipi_elem_exec) {
+			data = mipi_elem_exec(intel_dsi, data);
+		} else if (operation_size) {
+			/* We have size, skip. */
+			DRM_DEBUG_KMS("Unsupported MIPI operation byte %u\n",
+				      operation_byte);
+			data += operation_size;
+		} else {
+			/* No size, can't skip without parsing. */
+			DRM_ERROR("Unsupported MIPI operation byte %u\n",
+				  operation_byte);
+			return;
+		}
 	}
 }
 
 static int vbt_panel_prepare(struct drm_panel *panel)
 {
-	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
-	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const u8 *sequence;
-
-	sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET];
-	generic_exec_sequence(intel_dsi, sequence);
-
-	sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
-	generic_exec_sequence(intel_dsi, sequence);
+	generic_exec_sequence(panel, MIPI_SEQ_ASSERT_RESET);
+	generic_exec_sequence(panel, MIPI_SEQ_INIT_OTP);
 
 	return 0;
 }
 
 static int vbt_panel_unprepare(struct drm_panel *panel)
 {
-	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
-	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const u8 *sequence;
-
-	sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET];
-	generic_exec_sequence(intel_dsi, sequence);
+	generic_exec_sequence(panel, MIPI_SEQ_DEASSERT_RESET);
 
 	return 0;
 }
 
 static int vbt_panel_enable(struct drm_panel *panel)
 {
-	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
-	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const u8 *sequence;
-
-	sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON];
-	generic_exec_sequence(intel_dsi, sequence);
+	generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_ON);
 
 	return 0;
 }
 
 static int vbt_panel_disable(struct drm_panel *panel)
 {
-	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
-	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const u8 *sequence;
-
-	sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_OFF];
-	generic_exec_sequence(intel_dsi, sequence);
+	generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_OFF);
 
 	return 0;
 }
@@ -428,10 +440,7 @@ struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	intel_dsi->dual_link = mipi_config->dual_link;
 	intel_dsi->pixel_overlap = mipi_config->pixel_overlap;
 
-	if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB666)
-		bits_per_pixel = 18;
-	else if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB565)
-		bits_per_pixel = 16;
+	bits_per_pixel = dsi_pixel_format_bpp(intel_dsi->pixel_format);
 
 	intel_dsi->operation_mode = mipi_config->is_cmd_mode;
 	intel_dsi->video_mode_format = mipi_config->video_transfer_mode;
@@ -685,6 +694,8 @@ struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id)
 
 	/* This is cheating a bit with the cleanup. */
 	vbt_panel = devm_kzalloc(dev->dev, sizeof(*vbt_panel), GFP_KERNEL);
+	if (!vbt_panel)
+		return NULL;
 
 	vbt_panel->intel_dsi = intel_dsi;
 	drm_panel_init(&vbt_panel->panel);
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
index fbd2b5181..70883c54c 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/intel_dsi_pll.c
@@ -30,15 +30,7 @@
 #include "i915_drv.h"
 #include "intel_dsi.h"
 
-#define DSI_HSS_PACKET_SIZE		4
-#define DSI_HSE_PACKET_SIZE		4
-#define DSI_HSA_PACKET_EXTRA_SIZE	6
-#define DSI_HBP_PACKET_EXTRA_SIZE	6
-#define DSI_HACTIVE_PACKET_EXTRA_SIZE	6
-#define DSI_HFP_PACKET_EXTRA_SIZE	6
-#define DSI_EOTP_PACKET_SIZE		4
-
-static int dsi_pixel_format_bpp(int pixel_format)
+int dsi_pixel_format_bpp(int pixel_format)
 {
 	int bpp;
 
@@ -71,77 +63,6 @@ static const u32 lfsr_converts[] = {
 	71, 35, 273, 136, 324, 418, 465, 488, 500, 506		/* 91 - 100 */
 };
 
-#ifdef DSI_CLK_FROM_RR
-
-static u32 dsi_rr_formula(const struct drm_display_mode *mode,
-			  int pixel_format, int video_mode_format,
-			  int lane_count, bool eotp)
-{
-	u32 bpp;
-	u32 hactive, vactive, hfp, hsync, hbp, vfp, vsync, vbp;
-	u32 hsync_bytes, hbp_bytes, hactive_bytes, hfp_bytes;
-	u32 bytes_per_line, bytes_per_frame;
-	u32 num_frames;
-	u32 bytes_per_x_frames, bytes_per_x_frames_x_lanes;
-	u32 dsi_bit_clock_hz;
-	u32 dsi_clk;
-
-	bpp = dsi_pixel_format_bpp(pixel_format);
-
-	hactive = mode->hdisplay;
-	vactive = mode->vdisplay;
-	hfp = mode->hsync_start - mode->hdisplay;
-	hsync = mode->hsync_end - mode->hsync_start;
-	hbp = mode->htotal - mode->hsync_end;
-
-	vfp = mode->vsync_start - mode->vdisplay;
-	vsync = mode->vsync_end - mode->vsync_start;
-	vbp = mode->vtotal - mode->vsync_end;
-
-	hsync_bytes = DIV_ROUND_UP(hsync * bpp, 8);
-	hbp_bytes = DIV_ROUND_UP(hbp * bpp, 8);
-	hactive_bytes = DIV_ROUND_UP(hactive * bpp, 8);
-	hfp_bytes = DIV_ROUND_UP(hfp * bpp, 8);
-
-	bytes_per_line = DSI_HSS_PACKET_SIZE + hsync_bytes +
-		DSI_HSA_PACKET_EXTRA_SIZE + DSI_HSE_PACKET_SIZE +
-		hbp_bytes + DSI_HBP_PACKET_EXTRA_SIZE +
-		hactive_bytes + DSI_HACTIVE_PACKET_EXTRA_SIZE +
-		hfp_bytes + DSI_HFP_PACKET_EXTRA_SIZE;
-
-	/*
-	 * XXX: Need to accurately calculate LP to HS transition timeout and add
-	 * it to bytes_per_line/bytes_per_frame.
-	 */
-
-	if (eotp && video_mode_format == VIDEO_MODE_BURST)
-		bytes_per_line += DSI_EOTP_PACKET_SIZE;
-
-	bytes_per_frame = vsync * bytes_per_line + vbp * bytes_per_line +
-		vactive * bytes_per_line + vfp * bytes_per_line;
-
-	if (eotp &&
-	    (video_mode_format == VIDEO_MODE_NON_BURST_WITH_SYNC_PULSE ||
-	     video_mode_format == VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS))
-		bytes_per_frame += DSI_EOTP_PACKET_SIZE;
-
-	num_frames = drm_mode_vrefresh(mode);
-	bytes_per_x_frames = num_frames * bytes_per_frame;
-
-	bytes_per_x_frames_x_lanes = bytes_per_x_frames / lane_count;
-
-	/* the dsi clock is divided by 2 in the hardware to get dsi ddr clock */
-	dsi_bit_clock_hz = bytes_per_x_frames_x_lanes * 8;
-	dsi_clk = dsi_bit_clock_hz / 1000;
-
-	if (eotp && video_mode_format == VIDEO_MODE_BURST)
-		dsi_clk *= 2;
-
-	return dsi_clk;
-}
-
-#else
-
 /* Get DSI clock from pixel clock */
 static u32 dsi_clk_from_pclk(u32 pclk, int pixel_format, int lane_count)
 {
@@ -155,8 +76,6 @@ static u32 dsi_clk_from_pclk(u32 pclk, int pixel_format, int lane_count)
 	return dsi_clk_khz;
 }
 
-#endif
-
 static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
 			struct dsi_mnp *dsi_mnp, int target_dsi_clk)
 {
@@ -322,7 +241,7 @@ static void assert_bpp_mismatch(int pixel_format, int pipe_bpp)
 	     bpp, pipe_bpp);
 }
 
-u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
+static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -384,7 +303,7 @@ u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
 	return pclk;
 }
 
-u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
+static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp)
 {
 	u32 pclk;
 	u32 dsi_clk;
@@ -419,6 +338,14 @@ u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
 	return pclk;
 }
 
+u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp)
+{
+	if (IS_BROXTON(encoder->base.dev))
+		return bxt_dsi_get_pclk(encoder, pipe_bpp);
+	else
+		return vlv_dsi_get_pclk(encoder, pipe_bpp);
+}
+
 static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index a1988a486..0f0492f4a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -43,7 +43,7 @@
 
 static inline bool fbc_supported(struct drm_i915_private *dev_priv)
 {
-	return dev_priv->fbc.activate != NULL;
+	return HAS_FBC(dev_priv);
 }
 
 static inline bool fbc_on_pipe_a_only(struct drm_i915_private *dev_priv)
@@ -56,6 +56,11 @@ static inline bool fbc_on_plane_a_only(struct drm_i915_private *dev_priv)
 	return INTEL_INFO(dev_priv)->gen < 4;
 }
 
+static inline bool no_fbc_on_multiple_pipes(struct drm_i915_private *dev_priv)
+{
+	return INTEL_INFO(dev_priv)->gen <= 3;
+}
+
 /*
  * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
  * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
@@ -74,19 +79,17 @@ static unsigned int get_crtc_fence_y_offset(struct intel_crtc *crtc)
  * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
  * we wrote to PIPESRC.
  */
-static void intel_fbc_get_plane_source_size(struct intel_crtc *crtc,
+static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
-	struct intel_plane_state *plane_state =
-			to_intel_plane_state(crtc->base.primary->state);
 	int w, h;
 
-	if (intel_rotation_90_or_270(plane_state->base.rotation)) {
-		w = drm_rect_height(&plane_state->src) >> 16;
-		h = drm_rect_width(&plane_state->src) >> 16;
+	if (intel_rotation_90_or_270(cache->plane.rotation)) {
+		w = cache->plane.src_h;
+		h = cache->plane.src_w;
 	} else {
-		w = drm_rect_width(&plane_state->src) >> 16;
-		h = drm_rect_height(&plane_state->src) >> 16;
+		w = cache->plane.src_w;
+		h = cache->plane.src_h;
 	}
 
 	if (width)
@@ -95,26 +98,23 @@ static void intel_fbc_get_plane_source_size(struct intel_crtc *crtc,
 		*height = h;
 }
 
-static int intel_fbc_calculate_cfb_size(struct intel_crtc *crtc,
-					struct drm_framebuffer *fb)
+static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
+					struct intel_fbc_state_cache *cache)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
 	int lines;
 
-	intel_fbc_get_plane_source_size(crtc, NULL, &lines);
+	intel_fbc_get_plane_source_size(cache, NULL, &lines);
 	if (INTEL_INFO(dev_priv)->gen >= 7)
 		lines = min(lines, 2048);
 
 	/* Hardware needs the full buffer stride, not just the active area. */
-	return lines * fb->pitches[0];
+	return lines * cache->fb.stride;
 }
 
 static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv)
 {
 	u32 fbc_ctl;
 
-	dev_priv->fbc.active = false;
-
 	/* Disable compression */
 	fbc_ctl = I915_READ(FBC_CONTROL);
 	if ((fbc_ctl & FBC_CTL_EN) == 0)
@@ -130,21 +130,17 @@ static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void i8xx_fbc_activate(struct intel_crtc *crtc)
+static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb = crtc->base.primary->fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	int cfb_pitch;
 	int i;
 	u32 fbc_ctl;
 
-	dev_priv->fbc.active = true;
-
 	/* Note: fbc.threshold == 1 for i8xx */
-	cfb_pitch = intel_fbc_calculate_cfb_size(crtc, fb) / FBC_LL_SIZE;
-	if (fb->pitches[0] < cfb_pitch)
-		cfb_pitch = fb->pitches[0];
+	cfb_pitch = params->cfb_size / FBC_LL_SIZE;
+	if (params->fb.stride < cfb_pitch)
+		cfb_pitch = params->fb.stride;
 
 	/* FBC_CTL wants 32B or 64B units */
 	if (IS_GEN2(dev_priv))
@@ -161,9 +157,9 @@ static void i8xx_fbc_activate(struct intel_crtc *crtc)
 
 		/* Set it up... */
 		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
-		fbc_ctl2 |= FBC_CTL_PLANE(crtc->plane);
+		fbc_ctl2 |= FBC_CTL_PLANE(params->crtc.plane);
 		I915_WRITE(FBC_CONTROL2, fbc_ctl2);
-		I915_WRITE(FBC_FENCE_OFF, get_crtc_fence_y_offset(crtc));
+		I915_WRITE(FBC_FENCE_OFF, params->crtc.fence_y_offset);
 	}
 
 	/* enable it... */
@@ -173,7 +169,7 @@ static void i8xx_fbc_activate(struct intel_crtc *crtc)
 	if (IS_I945GM(dev_priv))
 		fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
 	fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
-	fbc_ctl |= obj->fence_reg;
+	fbc_ctl |= params->fb.fence_reg;
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 }
 
@@ -182,23 +178,19 @@ static bool i8xx_fbc_is_active(struct drm_i915_private *dev_priv)
 	return I915_READ(FBC_CONTROL) & FBC_CTL_EN;
 }
 
-static void g4x_fbc_activate(struct intel_crtc *crtc)
+static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb = crtc->base.primary->fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
 
-	dev_priv->fbc.active = true;
-
-	dpfc_ctl = DPFC_CTL_PLANE(crtc->plane) | DPFC_SR_EN;
-	if (drm_format_plane_cpp(fb->pixel_format, 0) == 2)
+	dpfc_ctl = DPFC_CTL_PLANE(params->crtc.plane) | DPFC_SR_EN;
+	if (drm_format_plane_cpp(params->fb.pixel_format, 0) == 2)
 		dpfc_ctl |= DPFC_CTL_LIMIT_2X;
 	else
 		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
-	dpfc_ctl |= DPFC_CTL_FENCE_EN | obj->fence_reg;
+	dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fb.fence_reg;
 
-	I915_WRITE(DPFC_FENCE_YOFF, get_crtc_fence_y_offset(crtc));
+	I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
 
 	/* enable it... */
 	I915_WRITE(DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
@@ -208,8 +200,6 @@ static void g4x_fbc_deactivate(struct drm_i915_private *dev_priv)
 {
 	u32 dpfc_ctl;
 
-	dev_priv->fbc.active = false;
-
 	/* Disable compression */
 	dpfc_ctl = I915_READ(DPFC_CONTROL);
 	if (dpfc_ctl & DPFC_CTL_EN) {
@@ -230,19 +220,14 @@ static void intel_fbc_recompress(struct drm_i915_private *dev_priv)
 	POSTING_READ(MSG_FBC_REND_STATE);
 }
 
-static void ilk_fbc_activate(struct intel_crtc *crtc)
+static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb = crtc->base.primary->fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
 	int threshold = dev_priv->fbc.threshold;
-	unsigned int y_offset;
 
-	dev_priv->fbc.active = true;
-
-	dpfc_ctl = DPFC_CTL_PLANE(crtc->plane);
-	if (drm_format_plane_cpp(fb->pixel_format, 0) == 2)
+	dpfc_ctl = DPFC_CTL_PLANE(params->crtc.plane);
+	if (drm_format_plane_cpp(params->fb.pixel_format, 0) == 2)
 		threshold++;
 
 	switch (threshold) {
@@ -259,18 +244,17 @@ static void ilk_fbc_activate(struct intel_crtc *crtc)
 	}
 	dpfc_ctl |= DPFC_CTL_FENCE_EN;
 	if (IS_GEN5(dev_priv))
-		dpfc_ctl |= obj->fence_reg;
+		dpfc_ctl |= params->fb.fence_reg;
 
-	y_offset = get_crtc_fence_y_offset(crtc);
-	I915_WRITE(ILK_DPFC_FENCE_YOFF, y_offset);
-	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
+	I915_WRITE(ILK_FBC_RT_BASE, params->fb.ggtt_offset | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
 	if (IS_GEN6(dev_priv)) {
 		I915_WRITE(SNB_DPFC_CTL_SA,
-			   SNB_CPU_FENCE_ENABLE | obj->fence_reg);
-		I915_WRITE(DPFC_CPU_FENCE_OFFSET, y_offset);
+			   SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+		I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
 	}
 
 	intel_fbc_recompress(dev_priv);
@@ -280,8 +264,6 @@ static void ilk_fbc_deactivate(struct drm_i915_private *dev_priv)
 {
 	u32 dpfc_ctl;
 
-	dev_priv->fbc.active = false;
-
 	/* Disable compression */
 	dpfc_ctl = I915_READ(ILK_DPFC_CONTROL);
 	if (dpfc_ctl & DPFC_CTL_EN) {
@@ -295,21 +277,17 @@ static bool ilk_fbc_is_active(struct drm_i915_private *dev_priv)
 	return I915_READ(ILK_DPFC_CONTROL) & DPFC_CTL_EN;
 }
 
-static void gen7_fbc_activate(struct intel_crtc *crtc)
+static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb = crtc->base.primary->fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct intel_fbc_reg_params *params = &dev_priv->fbc.params;
 	u32 dpfc_ctl;
 	int threshold = dev_priv->fbc.threshold;
 
-	dev_priv->fbc.active = true;
-
 	dpfc_ctl = 0;
 	if (IS_IVYBRIDGE(dev_priv))
-		dpfc_ctl |= IVB_DPFC_CTL_PLANE(crtc->plane);
+		dpfc_ctl |= IVB_DPFC_CTL_PLANE(params->crtc.plane);
 
-	if (drm_format_plane_cpp(fb->pixel_format, 0) == 2)
+	if (drm_format_plane_cpp(params->fb.pixel_format, 0) == 2)
 		threshold++;
 
 	switch (threshold) {
@@ -337,20 +315,60 @@ static void gen7_fbc_activate(struct intel_crtc *crtc)
 			   ILK_FBCQ_DIS);
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
-		I915_WRITE(CHICKEN_PIPESL_1(crtc->pipe),
-			   I915_READ(CHICKEN_PIPESL_1(crtc->pipe)) |
+		I915_WRITE(CHICKEN_PIPESL_1(params->crtc.pipe),
+			   I915_READ(CHICKEN_PIPESL_1(params->crtc.pipe)) |
 			   HSW_FBCQ_DIS);
 	}
 
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
 	I915_WRITE(SNB_DPFC_CTL_SA,
-		   SNB_CPU_FENCE_ENABLE | obj->fence_reg);
-	I915_WRITE(DPFC_CPU_FENCE_OFFSET, get_crtc_fence_y_offset(crtc));
+		   SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+	I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
 
 	intel_fbc_recompress(dev_priv);
 }
 
+static bool intel_fbc_hw_is_active(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_INFO(dev_priv)->gen >= 5)
+		return ilk_fbc_is_active(dev_priv);
+	else if (IS_GM45(dev_priv))
+		return g4x_fbc_is_active(dev_priv);
+	else
+		return i8xx_fbc_is_active(dev_priv);
+}
+
+static void intel_fbc_hw_activate(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	fbc->active = true;
+
+	if (INTEL_INFO(dev_priv)->gen >= 7)
+		gen7_fbc_activate(dev_priv);
+	else if (INTEL_INFO(dev_priv)->gen >= 5)
+		ilk_fbc_activate(dev_priv);
+	else if (IS_GM45(dev_priv))
+		g4x_fbc_activate(dev_priv);
+	else
+		i8xx_fbc_activate(dev_priv);
+}
+
+static void intel_fbc_hw_deactivate(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	fbc->active = false;
+
+	if (INTEL_INFO(dev_priv)->gen >= 5)
+		ilk_fbc_deactivate(dev_priv);
+	else if (IS_GM45(dev_priv))
+		g4x_fbc_deactivate(dev_priv);
+	else
+		i8xx_fbc_deactivate(dev_priv);
+}
+
 /**
  * intel_fbc_is_active - Is FBC active?
  * @dev_priv: i915 device instance
@@ -364,24 +382,24 @@ bool intel_fbc_is_active(struct drm_i915_private *dev_priv)
 	return dev_priv->fbc.active;
 }
 
-static void intel_fbc_activate(const struct drm_framebuffer *fb)
-{
-	struct drm_i915_private *dev_priv = fb->dev->dev_private;
-	struct intel_crtc *crtc = dev_priv->fbc.crtc;
-
-	dev_priv->fbc.activate(crtc);
-
-	dev_priv->fbc.fb_id = fb->base.id;
-	dev_priv->fbc.y = crtc->base.y;
-}
-
 static void intel_fbc_work_fn(struct work_struct *__work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(__work, struct drm_i915_private, fbc.work.work);
-	struct intel_fbc_work *work = &dev_priv->fbc.work;
-	struct intel_crtc *crtc = dev_priv->fbc.crtc;
-	int delay_ms = 50;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_work *work = &fbc->work;
+	struct intel_crtc *crtc = fbc->crtc;
+	struct drm_vblank_crtc *vblank = &dev_priv->dev->vblank[crtc->pipe];
+
+	if (drm_crtc_vblank_get(&crtc->base)) {
+		DRM_ERROR("vblank not available for FBC on pipe %c\n",
+			  pipe_name(crtc->pipe));
+
+		mutex_lock(&fbc->lock);
+		work->scheduled = false;
+		mutex_unlock(&fbc->lock);
+		return;
+	}
 
 retry:
 	/* Delay the actual enabling to let pageflipping cease and the
@@ -390,142 +408,97 @@ retry:
 	 * vblank to pass after disabling the FBC before we attempt
 	 * to modify the control registers.
 	 *
-	 * A more complicated solution would involve tracking vblanks
-	 * following the termination of the page-flipping sequence
-	 * and indeed performing the enable as a co-routine and not
-	 * waiting synchronously upon the vblank.
-	 *
 	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
+	 *
+	 * It is also worth mentioning that since work->scheduled_vblank can be
+	 * updated multiple times by the other threads, hitting the timeout is
+	 * not an error condition. We'll just end up hitting the "goto retry"
+	 * case below.
 	 */
-	wait_remaining_ms_from_jiffies(work->enable_jiffies, delay_ms);
+	wait_event_timeout(vblank->queue,
+		drm_crtc_vblank_count(&crtc->base) != work->scheduled_vblank,
+		msecs_to_jiffies(50));
 
-	mutex_lock(&dev_priv->fbc.lock);
+	mutex_lock(&fbc->lock);
 
 	/* Were we cancelled? */
 	if (!work->scheduled)
 		goto out;
 
 	/* Were we delayed again while this function was sleeping? */
-	if (time_after(work->enable_jiffies + msecs_to_jiffies(delay_ms),
-		       jiffies)) {
-		mutex_unlock(&dev_priv->fbc.lock);
+	if (drm_crtc_vblank_count(&crtc->base) == work->scheduled_vblank) {
+		mutex_unlock(&fbc->lock);
 		goto retry;
 	}
 
-	if (crtc->base.primary->fb == work->fb)
-		intel_fbc_activate(work->fb);
+	intel_fbc_hw_activate(dev_priv);
 
 	work->scheduled = false;
 
 out:
-	mutex_unlock(&dev_priv->fbc.lock);
-}
-
-static void intel_fbc_cancel_work(struct drm_i915_private *dev_priv)
-{
-	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
-	dev_priv->fbc.work.scheduled = false;
+	mutex_unlock(&fbc->lock);
+	drm_crtc_vblank_put(&crtc->base);
 }
 
 static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct intel_fbc_work *work = &dev_priv->fbc.work;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_work *work = &fbc->work;
+
+	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
+	if (drm_crtc_vblank_get(&crtc->base)) {
+		DRM_ERROR("vblank not available for FBC on pipe %c\n",
+			  pipe_name(crtc->pipe));
+		return;
+	}
 
-	/* It is useless to call intel_fbc_cancel_work() in this function since
-	 * we're not releasing fbc.lock, so it won't have an opportunity to grab
-	 * it to discover that it was cancelled. So we just update the expected
-	 * jiffy count. */
-	work->fb = crtc->base.primary->fb;
+	/* It is useless to call intel_fbc_cancel_work() or cancel_work() in
+	 * this function since we're not releasing fbc.lock, so it won't have an
+	 * opportunity to grab it to discover that it was cancelled. So we just
+	 * update the expected jiffy count. */
 	work->scheduled = true;
-	work->enable_jiffies = jiffies;
+	work->scheduled_vblank = drm_crtc_vblank_count(&crtc->base);
+	drm_crtc_vblank_put(&crtc->base);
 
 	schedule_work(&work->work);
 }
 
-static void __intel_fbc_deactivate(struct drm_i915_private *dev_priv)
+static void intel_fbc_deactivate(struct drm_i915_private *dev_priv)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
-
-	intel_fbc_cancel_work(dev_priv);
-
-	if (dev_priv->fbc.active)
-		dev_priv->fbc.deactivate(dev_priv);
-}
-
-/*
- * intel_fbc_deactivate - deactivate FBC if it's associated with crtc
- * @crtc: the CRTC
- *
- * This function deactivates FBC if it's associated with the provided CRTC.
- */
-void intel_fbc_deactivate(struct intel_crtc *crtc)
-{
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-
-	if (!fbc_supported(dev_priv))
-		return;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
-	mutex_lock(&dev_priv->fbc.lock);
-	if (dev_priv->fbc.crtc == crtc)
-		__intel_fbc_deactivate(dev_priv);
-	mutex_unlock(&dev_priv->fbc.lock);
-}
+	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-static void set_no_fbc_reason(struct drm_i915_private *dev_priv,
-			      const char *reason)
-{
-	if (dev_priv->fbc.no_fbc_reason == reason)
-		return;
+	/* Calling cancel_work() here won't help due to the fact that the work
+	 * function grabs fbc->lock. Just set scheduled to false so the work
+	 * function can know it was cancelled. */
+	fbc->work.scheduled = false;
 
-	dev_priv->fbc.no_fbc_reason = reason;
-	DRM_DEBUG_KMS("Disabling FBC: %s\n", reason);
+	if (fbc->active)
+		intel_fbc_hw_deactivate(dev_priv);
 }
 
-static bool crtc_can_fbc(struct intel_crtc *crtc)
+static bool multiple_pipes_ok(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_plane *primary = crtc->base.primary;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	enum pipe pipe = crtc->pipe;
 
-	if (fbc_on_pipe_a_only(dev_priv) && crtc->pipe != PIPE_A)
-		return false;
-
-	if (fbc_on_plane_a_only(dev_priv) && crtc->plane != PLANE_A)
-		return false;
-
-	return true;
-}
-
-static bool crtc_is_valid(struct intel_crtc *crtc)
-{
-	if (!intel_crtc_active(&crtc->base))
-		return false;
-
-	if (!to_intel_plane_state(crtc->base.primary->state)->visible)
-		return false;
-
-	return true;
-}
-
-static bool multiple_pipes_ok(struct drm_i915_private *dev_priv)
-{
-	enum pipe pipe;
-	int n_pipes = 0;
-	struct drm_crtc *crtc;
-
-	if (INTEL_INFO(dev_priv)->gen > 4)
+	/* Don't even bother tracking anything we don't need. */
+	if (!no_fbc_on_multiple_pipes(dev_priv))
 		return true;
 
-	for_each_pipe(dev_priv, pipe) {
-		crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+	WARN_ON(!drm_modeset_is_locked(&primary->mutex));
 
-		if (intel_crtc_active(crtc) &&
-		    to_intel_plane_state(crtc->primary->state)->visible)
-			n_pipes++;
-	}
+	if (to_intel_plane_state(primary->state)->visible)
+		fbc->visible_pipes_mask |= (1 << pipe);
+	else
+		fbc->visible_pipes_mask &= ~(1 << pipe);
 
-	return (n_pipes < 2);
+	return (fbc->visible_pipes_mask & ~(1 << pipe)) != 0;
 }
 
 static int find_compression_threshold(struct drm_i915_private *dev_priv,
@@ -581,16 +554,16 @@ again:
 static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb = crtc->base.primary->state->fb;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct drm_mm_node *uninitialized_var(compressed_llb);
 	int size, fb_cpp, ret;
 
-	WARN_ON(drm_mm_node_allocated(&dev_priv->fbc.compressed_fb));
+	WARN_ON(drm_mm_node_allocated(&fbc->compressed_fb));
 
-	size = intel_fbc_calculate_cfb_size(crtc, fb);
-	fb_cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	size = intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache);
+	fb_cpp = drm_format_plane_cpp(fbc->state_cache.fb.pixel_format, 0);
 
-	ret = find_compression_threshold(dev_priv, &dev_priv->fbc.compressed_fb,
+	ret = find_compression_threshold(dev_priv, &fbc->compressed_fb,
 					 size, fb_cpp);
 	if (!ret)
 		goto err_llb;
@@ -599,12 +572,12 @@ static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
 
 	}
 
-	dev_priv->fbc.threshold = ret;
+	fbc->threshold = ret;
 
 	if (INTEL_INFO(dev_priv)->gen >= 5)
-		I915_WRITE(ILK_DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
+		I915_WRITE(ILK_DPFC_CB_BASE, fbc->compressed_fb.start);
 	else if (IS_GM45(dev_priv)) {
-		I915_WRITE(DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
+		I915_WRITE(DPFC_CB_BASE, fbc->compressed_fb.start);
 	} else {
 		compressed_llb = kzalloc(sizeof(*compressed_llb), GFP_KERNEL);
 		if (!compressed_llb)
@@ -615,23 +588,22 @@ static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
 		if (ret)
 			goto err_fb;
 
-		dev_priv->fbc.compressed_llb = compressed_llb;
+		fbc->compressed_llb = compressed_llb;
 
 		I915_WRITE(FBC_CFB_BASE,
-			   dev_priv->mm.stolen_base + dev_priv->fbc.compressed_fb.start);
+			   dev_priv->mm.stolen_base + fbc->compressed_fb.start);
 		I915_WRITE(FBC_LL_BASE,
 			   dev_priv->mm.stolen_base + compressed_llb->start);
 	}
 
 	DRM_DEBUG_KMS("reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n",
-		      dev_priv->fbc.compressed_fb.size,
-		      dev_priv->fbc.threshold);
+		      fbc->compressed_fb.size, fbc->threshold);
 
 	return 0;
 
 err_fb:
 	kfree(compressed_llb);
-	i915_gem_stolen_remove_node(dev_priv, &dev_priv->fbc.compressed_fb);
+	i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
 err_llb:
 	pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
 	return -ENOSPC;
@@ -639,25 +611,27 @@ err_llb:
 
 static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 {
-	if (drm_mm_node_allocated(&dev_priv->fbc.compressed_fb))
-		i915_gem_stolen_remove_node(dev_priv,
-					    &dev_priv->fbc.compressed_fb);
-
-	if (dev_priv->fbc.compressed_llb) {
-		i915_gem_stolen_remove_node(dev_priv,
-					    dev_priv->fbc.compressed_llb);
-		kfree(dev_priv->fbc.compressed_llb);
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	if (drm_mm_node_allocated(&fbc->compressed_fb))
+		i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb);
+
+	if (fbc->compressed_llb) {
+		i915_gem_stolen_remove_node(dev_priv, fbc->compressed_llb);
+		kfree(fbc->compressed_llb);
 	}
 }
 
 void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 {
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
 	if (!fbc_supported(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
+	mutex_lock(&fbc->lock);
 	__intel_fbc_cleanup_cfb(dev_priv);
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_unlock(&fbc->lock);
 }
 
 static bool stride_is_valid(struct drm_i915_private *dev_priv,
@@ -681,19 +655,17 @@ static bool stride_is_valid(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static bool pixel_format_is_valid(struct drm_framebuffer *fb)
+static bool pixel_format_is_valid(struct drm_i915_private *dev_priv,
+				  uint32_t pixel_format)
 {
-	struct drm_device *dev = fb->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	switch (fb->pixel_format) {
+	switch (pixel_format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
 		return true;
 	case DRM_FORMAT_XRGB1555:
 	case DRM_FORMAT_RGB565:
 		/* 16bpp not supported on gen2 */
-		if (IS_GEN2(dev))
+		if (IS_GEN2(dev_priv))
 			return false;
 		/* WaFbcOnly1to1Ratio:ctg */
 		if (IS_G4X(dev_priv))
@@ -713,6 +685,7 @@ static bool pixel_format_is_valid(struct drm_framebuffer *fb)
 static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 	unsigned int effective_w, effective_h, max_w, max_h;
 
 	if (INTEL_INFO(dev_priv)->gen >= 8 || IS_HASWELL(dev_priv)) {
@@ -726,87 +699,105 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 		max_h = 1536;
 	}
 
-	intel_fbc_get_plane_source_size(crtc, &effective_w, &effective_h);
+	intel_fbc_get_plane_source_size(&fbc->state_cache, &effective_w,
+					&effective_h);
 	effective_w += crtc->adjusted_x;
 	effective_h += crtc->adjusted_y;
 
 	return effective_w <= max_w && effective_h <= max_h;
 }
 
-/**
- * __intel_fbc_update - activate/deactivate FBC as needed, unlocked
- * @crtc: the CRTC that triggered the update
- *
- * This function completely reevaluates the status of FBC, then activates,
- * deactivates or maintains it on the same state.
- */
-static void __intel_fbc_update(struct intel_crtc *crtc)
+static void intel_fbc_update_state_cache(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_framebuffer *fb;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+	struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
+	struct intel_plane_state *plane_state =
+		to_intel_plane_state(crtc->base.primary->state);
+	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj;
-	const struct drm_display_mode *adjusted_mode;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
+	WARN_ON(!drm_modeset_is_locked(&crtc->base.mutex));
+	WARN_ON(!drm_modeset_is_locked(&crtc->base.primary->mutex));
 
-	if (!multiple_pipes_ok(dev_priv)) {
-		set_no_fbc_reason(dev_priv, "more than one pipe active");
-		goto out_disable;
-	}
+	cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		cache->crtc.hsw_bdw_pixel_rate =
+			ilk_pipe_pixel_rate(crtc_state);
 
-	if (!dev_priv->fbc.enabled || dev_priv->fbc.crtc != crtc)
-		return;
+	cache->plane.rotation = plane_state->base.rotation;
+	cache->plane.src_w = drm_rect_width(&plane_state->src) >> 16;
+	cache->plane.src_h = drm_rect_height(&plane_state->src) >> 16;
+	cache->plane.visible = plane_state->visible;
 
-	if (!crtc_is_valid(crtc)) {
-		set_no_fbc_reason(dev_priv, "no output");
-		goto out_disable;
-	}
+	if (!cache->plane.visible)
+		return;
 
-	fb = crtc->base.primary->fb;
 	obj = intel_fb_obj(fb);
-	adjusted_mode = &crtc->config->base.adjusted_mode;
 
-	if ((adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) ||
-	    (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)) {
-		set_no_fbc_reason(dev_priv, "incompatible mode");
-		goto out_disable;
+	/* FIXME: We lack the proper locking here, so only run this on the
+	 * platforms that need. */
+	if (INTEL_INFO(dev_priv)->gen >= 5 && INTEL_INFO(dev_priv)->gen < 7)
+		cache->fb.ilk_ggtt_offset = i915_gem_obj_ggtt_offset(obj);
+	cache->fb.pixel_format = fb->pixel_format;
+	cache->fb.stride = fb->pitches[0];
+	cache->fb.fence_reg = obj->fence_reg;
+	cache->fb.tiling_mode = obj->tiling_mode;
+}
+
+static bool intel_fbc_can_activate(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+	if (!cache->plane.visible) {
+		fbc->no_fbc_reason = "primary plane not visible";
+		return false;
+	}
+
+	if ((cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) ||
+	    (cache->crtc.mode_flags & DRM_MODE_FLAG_DBLSCAN)) {
+		fbc->no_fbc_reason = "incompatible mode";
+		return false;
 	}
 
 	if (!intel_fbc_hw_tracking_covers_screen(crtc)) {
-		set_no_fbc_reason(dev_priv, "mode too large for compression");
-		goto out_disable;
+		fbc->no_fbc_reason = "mode too large for compression";
+		return false;
 	}
 
 	/* The use of a CPU fence is mandatory in order to detect writes
 	 * by the CPU to the scanout and trigger updates to the FBC.
 	 */
-	if (obj->tiling_mode != I915_TILING_X ||
-	    obj->fence_reg == I915_FENCE_REG_NONE) {
-		set_no_fbc_reason(dev_priv, "framebuffer not tiled or fenced");
-		goto out_disable;
+	if (cache->fb.tiling_mode != I915_TILING_X ||
+	    cache->fb.fence_reg == I915_FENCE_REG_NONE) {
+		fbc->no_fbc_reason = "framebuffer not tiled or fenced";
+		return false;
 	}
 	if (INTEL_INFO(dev_priv)->gen <= 4 && !IS_G4X(dev_priv) &&
-	    crtc->base.primary->state->rotation != BIT(DRM_ROTATE_0)) {
-		set_no_fbc_reason(dev_priv, "rotation unsupported");
-		goto out_disable;
+	    cache->plane.rotation != BIT(DRM_ROTATE_0)) {
+		fbc->no_fbc_reason = "rotation unsupported";
+		return false;
 	}
 
-	if (!stride_is_valid(dev_priv, fb->pitches[0])) {
-		set_no_fbc_reason(dev_priv, "framebuffer stride not supported");
-		goto out_disable;
+	if (!stride_is_valid(dev_priv, cache->fb.stride)) {
+		fbc->no_fbc_reason = "framebuffer stride not supported";
+		return false;
 	}
 
-	if (!pixel_format_is_valid(fb)) {
-		set_no_fbc_reason(dev_priv, "pixel format is invalid");
-		goto out_disable;
+	if (!pixel_format_is_valid(dev_priv, cache->fb.pixel_format)) {
+		fbc->no_fbc_reason = "pixel format is invalid";
+		return false;
 	}
 
 	/* WaFbcExceedCdClockThreshold:hsw,bdw */
 	if ((IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) &&
-	    ilk_pipe_pixel_rate(crtc->config) >=
-	    dev_priv->cdclk_freq * 95 / 100) {
-		set_no_fbc_reason(dev_priv, "pixel rate is too big");
-		goto out_disable;
+	    cache->crtc.hsw_bdw_pixel_rate >= dev_priv->cdclk_freq * 95 / 100) {
+		fbc->no_fbc_reason = "pixel rate is too big";
+		return false;
 	}
 
 	/* It is possible for the required CFB size change without a
@@ -819,189 +810,322 @@ static void __intel_fbc_update(struct intel_crtc *crtc)
 	 * we didn't get any invalidate/deactivate calls, but this would require
 	 * a lot of tracking just for a specific case. If we conclude it's an
 	 * important case, we can implement it later. */
-	if (intel_fbc_calculate_cfb_size(crtc, fb) >
-	    dev_priv->fbc.compressed_fb.size * dev_priv->fbc.threshold) {
-		set_no_fbc_reason(dev_priv, "CFB requirements changed");
-		goto out_disable;
+	if (intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
+	    fbc->compressed_fb.size * fbc->threshold) {
+		fbc->no_fbc_reason = "CFB requirements changed";
+		return false;
 	}
 
+	return true;
+}
+
+static bool intel_fbc_can_choose(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	bool enable_by_default = IS_HASWELL(dev_priv) ||
+				 IS_BROADWELL(dev_priv);
+
+	if (intel_vgpu_active(dev_priv->dev)) {
+		fbc->no_fbc_reason = "VGPU is active";
+		return false;
+	}
+
+	if (i915.enable_fbc < 0 && !enable_by_default) {
+		fbc->no_fbc_reason = "disabled per chip default";
+		return false;
+	}
+
+	if (!i915.enable_fbc) {
+		fbc->no_fbc_reason = "disabled per module param";
+		return false;
+	}
+
+	if (fbc_on_pipe_a_only(dev_priv) && crtc->pipe != PIPE_A) {
+		fbc->no_fbc_reason = "no enabled pipes can have FBC";
+		return false;
+	}
+
+	if (fbc_on_plane_a_only(dev_priv) && crtc->plane != PLANE_A) {
+		fbc->no_fbc_reason = "no enabled planes can have FBC";
+		return false;
+	}
+
+	return true;
+}
+
+static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
+				     struct intel_fbc_reg_params *params)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+	/* Since all our fields are integer types, use memset here so the
+	 * comparison function can rely on memcmp because the padding will be
+	 * zero. */
+	memset(params, 0, sizeof(*params));
+
+	params->crtc.pipe = crtc->pipe;
+	params->crtc.plane = crtc->plane;
+	params->crtc.fence_y_offset = get_crtc_fence_y_offset(crtc);
+
+	params->fb.pixel_format = cache->fb.pixel_format;
+	params->fb.stride = cache->fb.stride;
+	params->fb.fence_reg = cache->fb.fence_reg;
+
+	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
+
+	params->fb.ggtt_offset = cache->fb.ilk_ggtt_offset;
+}
+
+static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
+				       struct intel_fbc_reg_params *params2)
+{
+	/* We can use this since intel_fbc_get_reg_params() does a memset. */
+	return memcmp(params1, params2, sizeof(*params1)) == 0;
+}
+
+void intel_fbc_pre_update(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	if (!fbc_supported(dev_priv))
+		return;
+
+	mutex_lock(&fbc->lock);
+
+	if (!multiple_pipes_ok(crtc)) {
+		fbc->no_fbc_reason = "more than one pipe active";
+		goto deactivate;
+	}
+
+	if (!fbc->enabled || fbc->crtc != crtc)
+		goto unlock;
+
+	intel_fbc_update_state_cache(crtc);
+
+deactivate:
+	intel_fbc_deactivate(dev_priv);
+unlock:
+	mutex_unlock(&fbc->lock);
+}
+
+static void __intel_fbc_post_update(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_reg_params old_params;
+
+	WARN_ON(!mutex_is_locked(&fbc->lock));
+
+	if (!fbc->enabled || fbc->crtc != crtc)
+		return;
+
+	if (!intel_fbc_can_activate(crtc)) {
+		WARN_ON(fbc->active);
+		return;
+	}
+
+	old_params = fbc->params;
+	intel_fbc_get_reg_params(crtc, &fbc->params);
+
 	/* If the scanout has not changed, don't modify the FBC settings.
 	 * Note that we make the fundamental assumption that the fb->obj
 	 * cannot be unpinned (and have its GTT offset and fence revoked)
 	 * without first being decoupled from the scanout and FBC disabled.
 	 */
-	if (dev_priv->fbc.crtc == crtc &&
-	    dev_priv->fbc.fb_id == fb->base.id &&
-	    dev_priv->fbc.y == crtc->base.y &&
-	    dev_priv->fbc.active)
+	if (fbc->active &&
+	    intel_fbc_reg_params_equal(&old_params, &fbc->params))
 		return;
 
-	if (intel_fbc_is_active(dev_priv)) {
-		/* We update FBC along two paths, after changing fb/crtc
-		 * configuration (modeswitching) and after page-flipping
-		 * finishes. For the latter, we know that not only did
-		 * we disable the FBC at the start of the page-flip
-		 * sequence, but also more than one vblank has passed.
-		 *
-		 * For the former case of modeswitching, it is possible
-		 * to switch between two FBC valid configurations
-		 * instantaneously so we do need to disable the FBC
-		 * before we can modify its control registers. We also
-		 * have to wait for the next vblank for that to take
-		 * effect. However, since we delay enabling FBC we can
-		 * assume that a vblank has passed since disabling and
-		 * that we can safely alter the registers in the deferred
-		 * callback.
-		 *
-		 * In the scenario that we go from a valid to invalid
-		 * and then back to valid FBC configuration we have
-		 * no strict enforcement that a vblank occurred since
-		 * disabling the FBC. However, along all current pipe
-		 * disabling paths we do need to wait for a vblank at
-		 * some point. And we wait before enabling FBC anyway.
-		 */
-		DRM_DEBUG_KMS("deactivating FBC for update\n");
-		__intel_fbc_deactivate(dev_priv);
-	}
-
+	intel_fbc_deactivate(dev_priv);
 	intel_fbc_schedule_activation(crtc);
-	dev_priv->fbc.no_fbc_reason = "FBC enabled (not necessarily active)";
-	return;
-
-out_disable:
-	/* Multiple disables should be harmless */
-	if (intel_fbc_is_active(dev_priv)) {
-		DRM_DEBUG_KMS("unsupported config, deactivating FBC\n");
-		__intel_fbc_deactivate(dev_priv);
-	}
+	fbc->no_fbc_reason = "FBC enabled (active or scheduled)";
 }
 
-/*
- * intel_fbc_update - activate/deactivate FBC as needed
- * @crtc: the CRTC that triggered the update
- *
- * This function reevaluates the overall state and activates or deactivates FBC.
- */
-void intel_fbc_update(struct intel_crtc *crtc)
+void intel_fbc_post_update(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
-	__intel_fbc_update(crtc);
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_lock(&fbc->lock);
+	__intel_fbc_post_update(crtc);
+	mutex_unlock(&fbc->lock);
+}
+
+static unsigned int intel_fbc_get_frontbuffer_bit(struct intel_fbc *fbc)
+{
+	if (fbc->enabled)
+		return to_intel_plane(fbc->crtc->base.primary)->frontbuffer_bit;
+	else
+		return fbc->possible_framebuffer_bits;
 }
 
 void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 			  unsigned int frontbuffer_bits,
 			  enum fb_op_origin origin)
 {
-	unsigned int fbc_bits;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
-	if (origin == ORIGIN_GTT)
+	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
+	mutex_lock(&fbc->lock);
 
-	if (dev_priv->fbc.enabled)
-		fbc_bits = INTEL_FRONTBUFFER_PRIMARY(dev_priv->fbc.crtc->pipe);
-	else
-		fbc_bits = dev_priv->fbc.possible_framebuffer_bits;
-
-	dev_priv->fbc.busy_bits |= (fbc_bits & frontbuffer_bits);
+	fbc->busy_bits |= intel_fbc_get_frontbuffer_bit(fbc) & frontbuffer_bits;
 
-	if (dev_priv->fbc.busy_bits)
-		__intel_fbc_deactivate(dev_priv);
+	if (fbc->enabled && fbc->busy_bits)
+		intel_fbc_deactivate(dev_priv);
 
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_unlock(&fbc->lock);
 }
 
 void intel_fbc_flush(struct drm_i915_private *dev_priv,
 		     unsigned int frontbuffer_bits, enum fb_op_origin origin)
 {
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
 	if (!fbc_supported(dev_priv))
 		return;
 
-	if (origin == ORIGIN_GTT)
+	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
+	mutex_lock(&fbc->lock);
 
-	dev_priv->fbc.busy_bits &= ~frontbuffer_bits;
+	fbc->busy_bits &= ~frontbuffer_bits;
 
-	if (!dev_priv->fbc.busy_bits && dev_priv->fbc.enabled) {
-		if (origin != ORIGIN_FLIP && dev_priv->fbc.active) {
+	if (!fbc->busy_bits && fbc->enabled &&
+	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
+		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
-		} else {
-			__intel_fbc_deactivate(dev_priv);
-			__intel_fbc_update(dev_priv->fbc.crtc);
+		else
+			__intel_fbc_post_update(fbc->crtc);
+	}
+
+	mutex_unlock(&fbc->lock);
+}
+
+/**
+ * intel_fbc_choose_crtc - select a CRTC to enable FBC on
+ * @dev_priv: i915 device instance
+ * @state: the atomic state structure
+ *
+ * This function looks at the proposed state for CRTCs and planes, then chooses
+ * which pipe is going to have FBC by setting intel_crtc_state->enable_fbc to
+ * true.
+ *
+ * Later, intel_fbc_enable is going to look for state->enable_fbc and then maybe
+ * enable FBC for the chosen CRTC. If it does, it will set dev_priv->fbc.crtc.
+ */
+void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
+			   struct drm_atomic_state *state)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
+	bool fbc_crtc_present = false;
+	int i, j;
+
+	mutex_lock(&fbc->lock);
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		if (fbc->crtc == to_intel_crtc(crtc)) {
+			fbc_crtc_present = true;
+			break;
+		}
+	}
+	/* This atomic commit doesn't involve the CRTC currently tied to FBC. */
+	if (!fbc_crtc_present && fbc->crtc != NULL)
+		goto out;
+
+	/* Simply choose the first CRTC that is compatible and has a visible
+	 * plane. We could go for fancier schemes such as checking the plane
+	 * size, but this would just affect the few platforms that don't tie FBC
+	 * to pipe or plane A. */
+	for_each_plane_in_state(state, plane, plane_state, i) {
+		struct intel_plane_state *intel_plane_state =
+			to_intel_plane_state(plane_state);
+
+		if (!intel_plane_state->visible)
+			continue;
+
+		for_each_crtc_in_state(state, crtc, crtc_state, j) {
+			struct intel_crtc_state *intel_crtc_state =
+				to_intel_crtc_state(crtc_state);
+
+			if (plane_state->crtc != crtc)
+				continue;
+
+			if (!intel_fbc_can_choose(to_intel_crtc(crtc)))
+				break;
+
+			intel_crtc_state->enable_fbc = true;
+			goto out;
 		}
 	}
 
-	mutex_unlock(&dev_priv->fbc.lock);
+out:
+	mutex_unlock(&fbc->lock);
 }
 
 /**
  * intel_fbc_enable: tries to enable FBC on the CRTC
  * @crtc: the CRTC
  *
- * This function checks if it's possible to enable FBC on the following CRTC,
- * then enables it. Notice that it doesn't activate FBC.
+ * This function checks if the given CRTC was chosen for FBC, then enables it if
+ * possible. Notice that it doesn't activate FBC. It is valid to call
+ * intel_fbc_enable multiple times for the same pipe without an
+ * intel_fbc_disable in the middle, as long as it is deactivated.
  */
 void intel_fbc_enable(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
-
-	if (dev_priv->fbc.enabled) {
-		WARN_ON(dev_priv->fbc.crtc == crtc);
-		goto out;
-	}
-
-	WARN_ON(dev_priv->fbc.active);
-	WARN_ON(dev_priv->fbc.crtc != NULL);
+	mutex_lock(&fbc->lock);
 
-	if (intel_vgpu_active(dev_priv->dev)) {
-		set_no_fbc_reason(dev_priv, "VGPU is active");
-		goto out;
-	}
-
-	if (i915.enable_fbc < 0) {
-		set_no_fbc_reason(dev_priv, "disabled per chip default");
+	if (fbc->enabled) {
+		WARN_ON(fbc->crtc == NULL);
+		if (fbc->crtc == crtc) {
+			WARN_ON(!crtc->config->enable_fbc);
+			WARN_ON(fbc->active);
+		}
 		goto out;
 	}
 
-	if (!i915.enable_fbc) {
-		set_no_fbc_reason(dev_priv, "disabled per module param");
+	if (!crtc->config->enable_fbc)
 		goto out;
-	}
 
-	if (!crtc_can_fbc(crtc)) {
-		set_no_fbc_reason(dev_priv, "no enabled pipes can have FBC");
-		goto out;
-	}
+	WARN_ON(fbc->active);
+	WARN_ON(fbc->crtc != NULL);
 
+	intel_fbc_update_state_cache(crtc);
 	if (intel_fbc_alloc_cfb(crtc)) {
-		set_no_fbc_reason(dev_priv, "not enough stolen memory");
+		fbc->no_fbc_reason = "not enough stolen memory";
 		goto out;
 	}
 
 	DRM_DEBUG_KMS("Enabling FBC on pipe %c\n", pipe_name(crtc->pipe));
-	dev_priv->fbc.no_fbc_reason = "FBC enabled but not active yet\n";
+	fbc->no_fbc_reason = "FBC enabled but not active yet\n";
 
-	dev_priv->fbc.enabled = true;
-	dev_priv->fbc.crtc = crtc;
+	fbc->enabled = true;
+	fbc->crtc = crtc;
 out:
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_unlock(&fbc->lock);
 }
 
 /**
@@ -1013,58 +1137,88 @@ out:
  */
 static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
 {
-	struct intel_crtc *crtc = dev_priv->fbc.crtc;
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_crtc *crtc = fbc->crtc;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock));
-	WARN_ON(!dev_priv->fbc.enabled);
-	WARN_ON(dev_priv->fbc.active);
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	WARN_ON(!mutex_is_locked(&fbc->lock));
+	WARN_ON(!fbc->enabled);
+	WARN_ON(fbc->active);
+	WARN_ON(crtc->active);
 
 	DRM_DEBUG_KMS("Disabling FBC on pipe %c\n", pipe_name(crtc->pipe));
 
 	__intel_fbc_cleanup_cfb(dev_priv);
 
-	dev_priv->fbc.enabled = false;
-	dev_priv->fbc.crtc = NULL;
+	fbc->enabled = false;
+	fbc->crtc = NULL;
 }
 
 /**
- * intel_fbc_disable_crtc - disable FBC if it's associated with crtc
+ * intel_fbc_disable - disable FBC if it's associated with crtc
  * @crtc: the CRTC
  *
  * This function disables FBC if it's associated with the provided CRTC.
  */
-void intel_fbc_disable_crtc(struct intel_crtc *crtc)
+void intel_fbc_disable(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
-	if (dev_priv->fbc.crtc == crtc) {
-		WARN_ON(!dev_priv->fbc.enabled);
-		WARN_ON(dev_priv->fbc.active);
+	mutex_lock(&fbc->lock);
+	if (fbc->crtc == crtc) {
+		WARN_ON(!fbc->enabled);
+		WARN_ON(fbc->active);
 		__intel_fbc_disable(dev_priv);
 	}
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_unlock(&fbc->lock);
+
+	cancel_work_sync(&fbc->work.work);
 }
 
 /**
- * intel_fbc_disable - globally disable FBC
+ * intel_fbc_global_disable - globally disable FBC
  * @dev_priv: i915 device instance
  *
  * This function disables FBC regardless of which CRTC is associated with it.
  */
-void intel_fbc_disable(struct drm_i915_private *dev_priv)
+void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 {
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
 	if (!fbc_supported(dev_priv))
 		return;
 
-	mutex_lock(&dev_priv->fbc.lock);
-	if (dev_priv->fbc.enabled)
+	mutex_lock(&fbc->lock);
+	if (fbc->enabled)
 		__intel_fbc_disable(dev_priv);
-	mutex_unlock(&dev_priv->fbc.lock);
+	mutex_unlock(&fbc->lock);
+
+	cancel_work_sync(&fbc->work.work);
+}
+
+/**
+ * intel_fbc_init_pipe_state - initialize FBC's CRTC visibility tracking
+ * @dev_priv: i915 device instance
+ *
+ * The FBC code needs to track CRTC visibility since the older platforms can't
+ * have FBC enabled while multiple pipes are used. This function does the
+ * initial setup at driver load to make sure FBC is matching the real hardware.
+ */
+void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv)
+{
+	struct intel_crtc *crtc;
+
+	/* Don't even bother tracking anything if we don't need. */
+	if (!no_fbc_on_multiple_pipes(dev_priv))
+		return;
+
+	for_each_intel_crtc(dev_priv->dev, crtc)
+		if (intel_crtc_active(&crtc->base) &&
+		    to_intel_plane_state(crtc->base.primary->state)->visible)
+			dev_priv->fbc.visible_pipes_mask |= (1 << crtc->pipe);
 }
 
 /**
@@ -1075,51 +1229,35 @@ void intel_fbc_disable(struct drm_i915_private *dev_priv)
  */
 void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
+	struct intel_fbc *fbc = &dev_priv->fbc;
 	enum pipe pipe;
 
-	INIT_WORK(&dev_priv->fbc.work.work, intel_fbc_work_fn);
-	mutex_init(&dev_priv->fbc.lock);
-	dev_priv->fbc.enabled = false;
-	dev_priv->fbc.active = false;
-	dev_priv->fbc.work.scheduled = false;
+	INIT_WORK(&fbc->work.work, intel_fbc_work_fn);
+	mutex_init(&fbc->lock);
+	fbc->enabled = false;
+	fbc->active = false;
+	fbc->work.scheduled = false;
 
 	if (!HAS_FBC(dev_priv)) {
-		dev_priv->fbc.no_fbc_reason = "unsupported by this chipset";
+		fbc->no_fbc_reason = "unsupported by this chipset";
 		return;
 	}
 
 	for_each_pipe(dev_priv, pipe) {
-		dev_priv->fbc.possible_framebuffer_bits |=
+		fbc->possible_framebuffer_bits |=
 				INTEL_FRONTBUFFER_PRIMARY(pipe);
 
 		if (fbc_on_pipe_a_only(dev_priv))
 			break;
 	}
 
-	if (INTEL_INFO(dev_priv)->gen >= 7) {
-		dev_priv->fbc.is_active = ilk_fbc_is_active;
-		dev_priv->fbc.activate = gen7_fbc_activate;
-		dev_priv->fbc.deactivate = ilk_fbc_deactivate;
-	} else if (INTEL_INFO(dev_priv)->gen >= 5) {
-		dev_priv->fbc.is_active = ilk_fbc_is_active;
-		dev_priv->fbc.activate = ilk_fbc_activate;
-		dev_priv->fbc.deactivate = ilk_fbc_deactivate;
-	} else if (IS_GM45(dev_priv)) {
-		dev_priv->fbc.is_active = g4x_fbc_is_active;
-		dev_priv->fbc.activate = g4x_fbc_activate;
-		dev_priv->fbc.deactivate = g4x_fbc_deactivate;
-	} else {
-		dev_priv->fbc.is_active = i8xx_fbc_is_active;
-		dev_priv->fbc.activate = i8xx_fbc_activate;
-		dev_priv->fbc.deactivate = i8xx_fbc_deactivate;
-
-		/* This value was pulled out of someone's hat */
+	/* This value was pulled out of someone's hat */
+	if (INTEL_INFO(dev_priv)->gen <= 4 && !IS_GM45(dev_priv))
 		I915_WRITE(FBC_CONTROL, 500 << FBC_CTL_INTERVAL_SHIFT);
-	}
 
 	/* We still don't have any sort of hardware state readout for FBC, so
 	 * deactivate it in case the BIOS activated it to make sure software
 	 * matches the hardware state. */
-	if (dev_priv->fbc.is_active(dev_priv))
-		dev_priv->fbc.deactivate(dev_priv);
+	if (intel_fbc_hw_is_active(dev_priv))
+		intel_fbc_hw_deactivate(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index bea75cafc..c607217c1 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -119,7 +119,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 {
 	struct intel_fbdev *ifbdev =
 		container_of(helper, struct intel_fbdev, helper);
-	struct drm_framebuffer *fb = NULL;
+	struct drm_framebuffer *fb;
 	struct drm_device *dev = helper->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_mode_fb_cmd2 mode_cmd = {};
@@ -171,8 +171,6 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 
 out:
 	mutex_unlock(&dev->struct_mutex);
-	if (!IS_ERR_OR_NULL(fb))
-		drm_framebuffer_unreference(fb);
 	return ret;
 }
 
@@ -368,12 +366,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	uint64_t conn_configured = 0, mask;
 	int pass = 0;
 
-	save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool),
+	save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool),
 			       GFP_KERNEL);
 	if (!save_enabled)
 		return false;
 
-	memcpy(save_enabled, enabled, dev->mode_config.num_connector);
+	memcpy(save_enabled, enabled, fb_helper->connector_count);
 	mask = (1 << fb_helper->connector_count) - 1;
 retry:
 	for (i = 0; i < fb_helper->connector_count; i++) {
@@ -408,8 +406,8 @@ retry:
 			continue;
 		}
 
-		encoder = connector->encoder;
-		if (!encoder || WARN_ON(!encoder->crtc)) {
+		encoder = connector->state->best_encoder;
+		if (!encoder || WARN_ON(!connector->state->crtc)) {
 			if (connector->force > DRM_FORCE_OFF)
 				goto bail;
 
@@ -422,7 +420,7 @@ retry:
 
 		num_connectors_enabled++;
 
-		new_crtc = intel_fb_helper_crtc(fb_helper, encoder->crtc);
+		new_crtc = intel_fb_helper_crtc(fb_helper, connector->state->crtc);
 
 		/*
 		 * Make sure we're not trying to drive multiple connectors
@@ -468,17 +466,22 @@ retry:
 			 * usually contains. But since our current
 			 * code puts a mode derived from the post-pfit timings
 			 * into crtc->mode this works out correctly.
+			 *
+			 * This is crtc->mode and not crtc->state->mode for the
+			 * fastboot check to work correctly. crtc_state->mode has
+			 * I915_MODE_FLAG_INHERITED, which we clear to force check
+			 * state.
 			 */
 			DRM_DEBUG_KMS("looking for current mode on connector %s\n",
 				      connector->name);
-			modes[i] = &encoder->crtc->mode;
+			modes[i] = &connector->state->crtc->mode;
 		}
 		crtcs[i] = new_crtc;
 
 		DRM_DEBUG_KMS("connector %s on pipe %c [CRTC:%d]: %dx%d%s\n",
 			      connector->name,
-			      pipe_name(to_intel_crtc(encoder->crtc)->pipe),
-			      encoder->crtc->base.id,
+			      pipe_name(to_intel_crtc(connector->state->crtc)->pipe),
+			      connector->state->crtc->base.id,
 			      modes[i]->hdisplay, modes[i]->vdisplay,
 			      modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :"");
 
@@ -507,7 +510,7 @@ retry:
 	if (fallback) {
 bail:
 		DRM_DEBUG_KMS("Not using firmware configuration\n");
-		memcpy(enabled, save_enabled, dev->mode_config.num_connector);
+		memcpy(enabled, save_enabled, fb_helper->connector_count);
 		kfree(save_enabled);
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 822952235..73002e901 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -43,9 +43,10 @@ struct i915_guc_client {
 	uint32_t wq_offset;
 	uint32_t wq_size;
 	uint32_t wq_tail;
+	uint32_t wq_head;
 
 	/* GuC submission statistics & status */
-	uint64_t submissions[I915_NUM_RINGS];
+	uint64_t submissions[GUC_MAX_ENGINES_NUM];
 	uint32_t q_fail;
 	uint32_t b_fail;
 	int retcode;
@@ -88,6 +89,8 @@ struct intel_guc {
 	uint32_t log_flags;
 	struct drm_i915_gem_object *log_obj;
 
+	struct drm_i915_gem_object *ads_obj;
+
 	struct drm_i915_gem_object *ctx_pool_obj;
 	struct ida ctx_ids;
 
@@ -103,8 +106,8 @@ struct intel_guc {
 	uint32_t action_fail;		/* Total number of failures	*/
 	int32_t action_err;		/* Last error code		*/
 
-	uint64_t submissions[I915_NUM_RINGS];
-	uint32_t last_seqno[I915_NUM_RINGS];
+	uint64_t submissions[GUC_MAX_ENGINES_NUM];
+	uint32_t last_seqno[GUC_MAX_ENGINES_NUM];
 };
 
 /* intel_guc_loader.c */
@@ -122,5 +125,6 @@ int i915_guc_submit(struct i915_guc_client *client,
 		    struct drm_i915_gem_request *rq);
 void i915_guc_submission_disable(struct drm_device *dev);
 void i915_guc_submission_fini(struct drm_device *dev);
+int i915_guc_wq_check_space(struct i915_guc_client *client);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 40b2ea572..2de57ffe5 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -39,10 +39,18 @@
 #define GUC_CTX_PRIORITY_HIGH		1
 #define GUC_CTX_PRIORITY_KMD_NORMAL	2
 #define GUC_CTX_PRIORITY_NORMAL		3
+#define GUC_CTX_PRIORITY_NUM		4
 
 #define GUC_MAX_GPU_CONTEXTS		1024
 #define	GUC_INVALID_CTX_ID		GUC_MAX_GPU_CONTEXTS
 
+#define GUC_RENDER_ENGINE		0
+#define GUC_VIDEO_ENGINE		1
+#define GUC_BLITTER_ENGINE		2
+#define GUC_VIDEOENHANCE_ENGINE		3
+#define GUC_VIDEO_ENGINE2		4
+#define GUC_MAX_ENGINES_NUM		(GUC_VIDEO_ENGINE2 + 1)
+
 /* Work queue item header definitions */
 #define WQ_STATUS_ACTIVE		1
 #define WQ_STATUS_SUSPENDED		2
@@ -81,11 +89,14 @@
 #define GUC_CTL_CTXINFO			0
 #define   GUC_CTL_CTXNUM_IN16_SHIFT	0
 #define   GUC_CTL_BASE_ADDR_SHIFT	12
+
 #define GUC_CTL_ARAT_HIGH		1
 #define GUC_CTL_ARAT_LOW		2
+
 #define GUC_CTL_DEVICE_INFO		3
 #define   GUC_CTL_GTTYPE_SHIFT		0
 #define   GUC_CTL_COREFAMILY_SHIFT	7
+
 #define GUC_CTL_LOG_PARAMS		4
 #define   GUC_LOG_VALID			(1 << 0)
 #define   GUC_LOG_NOTIFY_ON_HALF_FULL	(1 << 1)
@@ -97,9 +108,12 @@
 #define   GUC_LOG_ISR_PAGES		3
 #define   GUC_LOG_ISR_SHIFT		9
 #define   GUC_LOG_BUF_ADDR_SHIFT	12
+
 #define GUC_CTL_PAGE_FAULT_CONTROL	5
+
 #define GUC_CTL_WA			6
 #define   GUC_CTL_WA_UK_BY_DRIVER	(1 << 3)
+
 #define GUC_CTL_FEATURE			7
 #define   GUC_CTL_VCS2_ENABLED		(1 << 0)
 #define   GUC_CTL_KERNEL_SUBMISSIONS	(1 << 1)
@@ -109,6 +123,7 @@
 #define   GUC_CTL_PREEMPTION_LOG	(1 << 5)
 #define   GUC_CTL_ENABLE_SLPC		(1 << 7)
 #define   GUC_CTL_RESET_ON_PREMPT_FAILURE	(1 << 8)
+
 #define GUC_CTL_DEBUG			8
 #define   GUC_LOG_VERBOSITY_SHIFT	0
 #define   GUC_LOG_VERBOSITY_LOW		(0 << GUC_LOG_VERBOSITY_SHIFT)
@@ -118,9 +133,19 @@
 /* Verbosity range-check limits, without the shift */
 #define	  GUC_LOG_VERBOSITY_MIN		0
 #define	  GUC_LOG_VERBOSITY_MAX		3
+#define	  GUC_LOG_VERBOSITY_MASK	0x0000000f
+#define	  GUC_LOG_DESTINATION_MASK	(3 << 4)
+#define   GUC_LOG_DISABLED		(1 << 6)
+#define   GUC_PROFILE_ENABLED		(1 << 7)
+#define   GUC_WQ_TRACK_ENABLED		(1 << 8)
+#define   GUC_ADS_ENABLED		(1 << 9)
+#define   GUC_DEBUG_RESERVED		(1 << 10)
+#define   GUC_ADS_ADDR_SHIFT		11
+#define   GUC_ADS_ADDR_MASK		0xfffff800
+
 #define GUC_CTL_RSRVD			9
 
-#define GUC_CTL_MAX_DWORDS		(GUC_CTL_RSRVD + 1)
+#define GUC_CTL_MAX_DWORDS		(SOFT_SCRATCH_COUNT - 2) /* [1..14] */
 
 /**
  * DOC: GuC Firmware Layout
@@ -267,7 +292,7 @@ struct guc_context_desc {
 	u64 db_trigger_phy;
 	u16 db_id;
 
-	struct guc_execlist_context lrc[I915_NUM_RINGS];
+	struct guc_execlist_context lrc[GUC_MAX_ENGINES_NUM];
 
 	u8 attribute;
 
@@ -299,6 +324,99 @@ struct guc_context_desc {
 #define GUC_POWER_D2		3
 #define GUC_POWER_D3		4
 
+/* Scheduling policy settings */
+
+/* Reset engine upon preempt failure */
+#define POLICY_RESET_ENGINE		(1<<0)
+/* Preempt to idle on quantum expiry */
+#define POLICY_PREEMPT_TO_IDLE		(1<<1)
+
+#define POLICY_MAX_NUM_WI		15
+
+struct guc_policy {
+	/* Time for one workload to execute. (in micro seconds) */
+	u32 execution_quantum;
+	u32 reserved1;
+
+	/* Time to wait for a preemption request to completed before issuing a
+	 * reset. (in micro seconds). */
+	u32 preemption_time;
+
+	/* How much time to allow to run after the first fault is observed.
+	 * Then preempt afterwards. (in micro seconds) */
+	u32 fault_time;
+
+	u32 policy_flags;
+	u32 reserved[2];
+} __packed;
+
+struct guc_policies {
+	struct guc_policy policy[GUC_CTX_PRIORITY_NUM][GUC_MAX_ENGINES_NUM];
+
+	/* In micro seconds. How much time to allow before DPC processing is
+	 * called back via interrupt (to prevent DPC queue drain starving).
+	 * Typically 1000s of micro seconds (example only, not granularity). */
+	u32 dpc_promote_time;
+
+	/* Must be set to take these new values. */
+	u32 is_valid;
+
+	/* Max number of WIs to process per call. A large value may keep CS
+	 * idle. */
+	u32 max_num_work_items;
+
+	u32 reserved[19];
+} __packed;
+
+/* GuC MMIO reg state struct */
+
+#define GUC_REGSET_FLAGS_NONE		0x0
+#define GUC_REGSET_POWERCYCLE		0x1
+#define GUC_REGSET_MASKED		0x2
+#define GUC_REGSET_ENGINERESET		0x4
+#define GUC_REGSET_SAVE_DEFAULT_VALUE	0x8
+#define GUC_REGSET_SAVE_CURRENT_VALUE	0x10
+
+#define GUC_REGSET_MAX_REGISTERS	25
+#define GUC_MMIO_WHITE_LIST_START	0x24d0
+#define GUC_MMIO_WHITE_LIST_MAX		12
+#define GUC_S3_SAVE_SPACE_PAGES		10
+
+struct guc_mmio_regset {
+	struct __packed {
+		u32 offset;
+		u32 value;
+		u32 flags;
+	} registers[GUC_REGSET_MAX_REGISTERS];
+
+	u32 values_valid;
+	u32 number_of_registers;
+} __packed;
+
+struct guc_mmio_reg_state {
+	struct guc_mmio_regset global_reg;
+	struct guc_mmio_regset engine_reg[GUC_MAX_ENGINES_NUM];
+
+	/* MMIO registers that are set as non privileged */
+	struct __packed {
+		u32 mmio_start;
+		u32 offsets[GUC_MMIO_WHITE_LIST_MAX];
+		u32 count;
+	} mmio_white_list[GUC_MAX_ENGINES_NUM];
+} __packed;
+
+/* GuC Additional Data Struct */
+
+struct guc_ads {
+	u32 reg_state_addr;
+	u32 reg_state_buffer;
+	u32 golden_context_lrca;
+	u32 scheduler_policies;
+	u32 reserved0[3];
+	u32 eng_state_size[GUC_MAX_ENGINES_NUM];
+	u32 reserved2[4];
+} __packed;
+
 /* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */
 enum host2guc_action {
 	HOST2GUC_ACTION_DEFAULT = 0x0,
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index e27f82382..ef46f976f 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -165,6 +165,13 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv)
 			i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT;
 	}
 
+	if (guc->ads_obj) {
+		u32 ads = (u32)i915_gem_obj_ggtt_offset(guc->ads_obj)
+				>> PAGE_SHIFT;
+		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
+		params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
+	}
+
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (i915.enable_guc_submission) {
 		u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj);
@@ -192,7 +199,7 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv)
  * the value matches either of two values representing completion
  * of the GuC boot process.
  *
- * This is used for polling the GuC status in a wait_for_atomic()
+ * This is used for polling the GuC status in a wait_for()
  * loop below.
  */
 static inline bool guc_ucode_response(struct drm_i915_private *dev_priv,
@@ -252,14 +259,14 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
 	I915_WRITE(DMA_CTRL, _MASKED_BIT_ENABLE(UOS_MOVE | START_DMA));
 
 	/*
-	 * Spin-wait for the DMA to complete & the GuC to start up.
+	 * Wait for the DMA to complete & the GuC to start up.
 	 * NB: Docs recommend not using the interrupt for completion.
 	 * Measurements indicate this should take no more than 20ms, so a
 	 * timeout here indicates that the GuC has failed and is unusable.
 	 * (Higher levels of the driver will attempt to fall back to
 	 * execlist mode if this happens.)
 	 */
-	ret = wait_for_atomic(guc_ucode_response(dev_priv, &status), 100);
+	ret = wait_for(guc_ucode_response(dev_priv, &status), 100);
 
 	DRM_DEBUG_DRIVER("DMA status 0x%x, GuC status 0x%x\n",
 			I915_READ(DMA_CTRL), status);
@@ -438,6 +445,7 @@ fail:
 
 	direct_interrupts_to_host(dev_priv);
 	i915_guc_submission_disable(dev);
+	i915_guc_submission_fini(dev);
 
 	return err;
 }
@@ -554,10 +562,12 @@ fail:
 	DRM_ERROR("Failed to fetch GuC firmware from %s (error %d)\n",
 		  guc_fw->guc_fw_path, err);
 
+	mutex_lock(&dev->struct_mutex);
 	obj = guc_fw->guc_fw_obj;
 	if (obj)
 		drm_gem_object_unreference(&obj->base);
 	guc_fw->guc_fw_obj = NULL;
+	mutex_unlock(&dev->struct_mutex);
 
 	release_firmware(fw);		/* OK even if fw is NULL */
 	guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
@@ -624,10 +634,11 @@ void intel_guc_ucode_fini(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 
+	mutex_lock(&dev->struct_mutex);
 	direct_interrupts_to_host(dev_priv);
+	i915_guc_submission_disable(dev);
 	i915_guc_submission_fini(dev);
 
-	mutex_lock(&dev->struct_mutex);
 	if (guc_fw->guc_fw_obj)
 		drm_gem_object_unreference(&guc_fw->guc_fw_obj->base);
 	guc_fw->guc_fw_obj = NULL;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 43fdae8ff..3ddb4fac5 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -836,6 +836,22 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
+void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
+{
+	struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi));
+	struct i2c_adapter *adapter =
+		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+
+	if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI)
+		return;
+
+	DRM_DEBUG_KMS("%s DP dual mode adaptor TMDS output\n",
+		      enable ? "Enabling" : "Disabling");
+
+	drm_dp_dual_mode_set_tmds_output(hdmi->dp_dual_mode.type,
+					 adapter, enable);
+}
+
 static void intel_hdmi_prepare(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
@@ -845,6 +861,8 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder)
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	u32 hdmi_val;
 
+	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
+
 	hdmi_val = SDVO_ENCODING_HDMI;
 	if (!HAS_PCH_SPLIT(dev) && crtc->config->limited_color_range)
 		hdmi_val |= HDMI_COLOR_RANGE_16_235;
@@ -1143,6 +1161,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
 	}
 
 	intel_hdmi->set_infoframes(&encoder->base, false, NULL);
+
+	intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
 }
 
 static void g4x_disable_hdmi(struct intel_encoder *encoder)
@@ -1168,27 +1188,42 @@ static void pch_post_disable_hdmi(struct intel_encoder *encoder)
 	intel_disable_hdmi(encoder);
 }
 
-static int hdmi_port_clock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit)
+static int intel_hdmi_source_max_tmds_clock(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
-
-	if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev))
+	if (IS_G4X(dev_priv))
 		return 165000;
-	else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
+	else if (IS_HASWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 8)
 		return 300000;
 	else
 		return 225000;
 }
 
+static int hdmi_port_clock_limit(struct intel_hdmi *hdmi,
+				 bool respect_downstream_limits)
+{
+	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
+	int max_tmds_clock = intel_hdmi_source_max_tmds_clock(to_i915(dev));
+
+	if (respect_downstream_limits) {
+		if (hdmi->dp_dual_mode.max_tmds_clock)
+			max_tmds_clock = min(max_tmds_clock,
+					     hdmi->dp_dual_mode.max_tmds_clock);
+		if (!hdmi->has_hdmi_sink)
+			max_tmds_clock = min(max_tmds_clock, 165000);
+	}
+
+	return max_tmds_clock;
+}
+
 static enum drm_mode_status
 hdmi_port_clock_valid(struct intel_hdmi *hdmi,
-		      int clock, bool respect_dvi_limit)
+		      int clock, bool respect_downstream_limits)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 
 	if (clock < 25000)
 		return MODE_CLOCK_LOW;
-	if (clock > hdmi_port_clock_limit(hdmi, respect_dvi_limit))
+	if (clock > hdmi_port_clock_limit(hdmi, respect_downstream_limits))
 		return MODE_CLOCK_HIGH;
 
 	/* BXT DPLL can't generate 223-240 MHz */
@@ -1210,11 +1245,19 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 	enum drm_mode_status status;
 	int clock;
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
 	clock = mode->clock;
+
+	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+		clock *= 2;
+
+	if (clock > max_dotclk)
+		return MODE_CLOCK_HIGH;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		clock *= 2;
 
@@ -1304,7 +1347,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	 * within limits.
 	 */
 	if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink &&
-	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc, false) == MODE_OK &&
+	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true) == MODE_OK &&
 	    hdmi_12bpc_possible(pipe_config)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
@@ -1344,10 +1387,35 @@ intel_hdmi_unset_edid(struct drm_connector *connector)
 	intel_hdmi->has_audio = false;
 	intel_hdmi->rgb_quant_range_selectable = false;
 
+	intel_hdmi->dp_dual_mode.type = DRM_DP_DUAL_MODE_NONE;
+	intel_hdmi->dp_dual_mode.max_tmds_clock = 0;
+
 	kfree(to_intel_connector(connector)->detect_edid);
 	to_intel_connector(connector)->detect_edid = NULL;
 }
 
+static void
+intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+	struct i2c_adapter *adapter =
+		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
+	enum drm_dp_dual_mode_type type = drm_dp_dual_mode_detect(adapter);
+
+	if (type == DRM_DP_DUAL_MODE_NONE ||
+	    type == DRM_DP_DUAL_MODE_UNKNOWN)
+		return;
+
+	hdmi->dp_dual_mode.type = type;
+	hdmi->dp_dual_mode.max_tmds_clock =
+		drm_dp_dual_mode_max_tmds_clock(type, adapter);
+
+	DRM_DEBUG_KMS("DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n",
+		      drm_dp_get_dual_mode_type_name(type),
+		      hdmi->dp_dual_mode.max_tmds_clock);
+}
+
 static bool
 intel_hdmi_set_edid(struct drm_connector *connector, bool force)
 {
@@ -1363,6 +1431,8 @@ intel_hdmi_set_edid(struct drm_connector *connector, bool force)
 				    intel_gmbus_get_adapter(dev_priv,
 				    intel_hdmi->ddc_bus));
 
+		intel_hdmi_dp_dual_mode_detect(connector);
+
 		intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
 	}
 
@@ -2049,6 +2119,11 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	enum port port = intel_dig_port->port;
 	uint8_t alternate_ddc_pin;
 
+	if (WARN(intel_dig_port->max_lanes < 4,
+		 "Not enough lanes (%d) for HDMI on port %c\n",
+		 intel_dig_port->max_lanes, port_name(port)))
+		return;
+
 	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
@@ -2232,6 +2307,7 @@ void intel_hdmi_init(struct drm_device *dev,
 	intel_dig_port->port = port;
 	intel_dig_port->hdmi.hdmi_reg = hdmi_reg;
 	intel_dig_port->dp.output_reg = INVALID_MMIO_REG;
+	intel_dig_port->max_lanes = 4;
 
 	intel_hdmi_init_connector(intel_dig_port, intel_connector);
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index cfd5f9fff..5c6080fd0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -223,9 +223,11 @@ enum {
 	FAULT_AND_CONTINUE /* Unsupported */
 };
 #define GEN8_CTX_ID_SHIFT 32
-#define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT  0x17
+#define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
+#define GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x26
 
-static int intel_lr_context_pin(struct drm_i915_gem_request *rq);
+static int intel_lr_context_pin(struct intel_context *ctx,
+				struct intel_engine_cs *engine);
 static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
 		struct drm_i915_gem_object *default_ctx_obj);
 
@@ -263,65 +265,92 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists
 	return 0;
 }
 
+static void
+logical_ring_init_platform_invariants(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+
+	ring->disable_lite_restore_wa = (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
+					IS_BXT_REVID(dev, 0, BXT_REVID_A1)) &&
+					(ring->id == VCS || ring->id == VCS2);
+
+	ring->ctx_desc_template = GEN8_CTX_VALID;
+	ring->ctx_desc_template |= GEN8_CTX_ADDRESSING_MODE(dev) <<
+				   GEN8_CTX_ADDRESSING_MODE_SHIFT;
+	if (IS_GEN8(dev))
+		ring->ctx_desc_template |= GEN8_CTX_L3LLC_COHERENT;
+	ring->ctx_desc_template |= GEN8_CTX_PRIVILEGE;
+
+	/* TODO: WaDisableLiteRestore when we start using semaphore
+	 * signalling between Command Streamers */
+	/* ring->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE; */
+
+	/* WaEnableForceRestoreInCtxtDescForVCS:skl */
+	/* WaEnableForceRestoreInCtxtDescForVCS:bxt */
+	if (ring->disable_lite_restore_wa)
+		ring->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE;
+}
+
 /**
- * intel_execlists_ctx_id() - get the Execlists Context ID
- * @ctx_obj: Logical Ring Context backing object.
+ * intel_lr_context_descriptor_update() - calculate & cache the descriptor
+ * 					  descriptor for a pinned context
  *
- * Do not confuse with ctx->id! Unfortunately we have a name overload
- * here: the old context ID we pass to userspace as a handler so that
- * they can refer to a context, and the new context ID we pass to the
- * ELSP so that the GPU can inform us of the context status via
- * interrupts.
+ * @ctx: Context to work on
+ * @ring: Engine the descriptor will be used with
  *
- * Return: 20-bits globally unique context ID.
+ * The context descriptor encodes various attributes of a context,
+ * including its GTT address and some flags. Because it's fairly
+ * expensive to calculate, we'll just do it once and cache the result,
+ * which remains valid until the context is unpinned.
+ *
+ * This is what a descriptor looks like, from LSB to MSB:
+ *    bits 0-11:    flags, GEN8_CTX_* (cached in ctx_desc_template)
+ *    bits 12-31:    LRCA, GTT address of (the HWSP of) this context
+ *    bits 32-51:    ctx ID, a globally unique tag (the LRCA again!)
+ *    bits 52-63:    reserved, may encode the engine ID (for GuC)
  */
-u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)
+static void
+intel_lr_context_descriptor_update(struct intel_context *ctx,
+				   struct intel_engine_cs *ring)
 {
-	u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
-			LRC_PPHWSP_PN * PAGE_SIZE;
+	uint64_t lrca, desc;
 
-	/* LRCA is required to be 4K aligned so the more significant 20 bits
-	 * are globally unique */
-	return lrca >> 12;
-}
+	lrca = ctx->engine[ring->id].lrc_vma->node.start +
+	       LRC_PPHWSP_PN * PAGE_SIZE;
 
-static bool disable_lite_restore_wa(struct intel_engine_cs *ring)
-{
-	struct drm_device *dev = ring->dev;
+	desc = ring->ctx_desc_template;			   /* bits  0-11 */
+	desc |= lrca;					   /* bits 12-31 */
+	desc |= (lrca >> PAGE_SHIFT) << GEN8_CTX_ID_SHIFT; /* bits 32-51 */
 
-	return (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
-		IS_BXT_REVID(dev, 0, BXT_REVID_A1)) &&
-	       (ring->id == VCS || ring->id == VCS2);
+	ctx->engine[ring->id].lrc_desc = desc;
 }
 
 uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
 				     struct intel_engine_cs *ring)
 {
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
-	uint64_t desc;
-	uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
-			LRC_PPHWSP_PN * PAGE_SIZE;
-
-	WARN_ON(lrca & 0xFFFFFFFF00000FFFULL);
-
-	desc = GEN8_CTX_VALID;
-	desc |= GEN8_CTX_ADDRESSING_MODE(dev) << GEN8_CTX_ADDRESSING_MODE_SHIFT;
-	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;
-
-	/* TODO: WaDisableLiteRestore when we start using semaphore
-	 * signalling between Command Streamers */
-	/* desc |= GEN8_CTX_FORCE_RESTORE; */
-
-	/* WaEnableForceRestoreInCtxtDescForVCS:skl */
-	/* WaEnableForceRestoreInCtxtDescForVCS:bxt */
-	if (disable_lite_restore_wa(ring))
-		desc |= GEN8_CTX_FORCE_RESTORE;
+	return ctx->engine[ring->id].lrc_desc;
+}
 
-	return desc;
+/**
+ * intel_execlists_ctx_id() - get the Execlists Context ID
+ * @ctx: Context to get the ID for
+ * @ring: Engine to get the ID for
+ *
+ * Do not confuse with ctx->id! Unfortunately we have a name overload
+ * here: the old context ID we pass to userspace as a handler so that
+ * they can refer to a context, and the new context ID we pass to the
+ * ELSP so that the GPU can inform us of the context status via
+ * interrupts.
+ *
+ * The context ID is a portion of the context descriptor, so we can
+ * just extract the required part from the cached descriptor.
+ *
+ * Return: 20-bits globally unique context ID.
+ */
+u32 intel_execlists_ctx_id(struct intel_context *ctx,
+			   struct intel_engine_cs *ring)
+{
+	return intel_lr_context_descriptor(ctx, ring) >> GEN8_CTX_ID_SHIFT;
 }
 
 static void execlists_elsp_write(struct drm_i915_gem_request *rq0,
@@ -363,20 +392,9 @@ static int execlists_update_context(struct drm_i915_gem_request *rq)
 {
 	struct intel_engine_cs *ring = rq->ring;
 	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
-	struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
-	struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj;
-	struct page *page;
-	uint32_t *reg_state;
-
-	BUG_ON(!ctx_obj);
-	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
-	WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
-
-	page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN);
-	reg_state = kmap_atomic(page);
+	uint32_t *reg_state = rq->ctx->engine[ring->id].lrc_reg_state;
 
 	reg_state[CTX_RING_TAIL+1] = rq->tail;
-	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
 
 	if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
 		/* True 32b PPGTT with dynamic page allocation: update PDP
@@ -390,8 +408,6 @@ static int execlists_update_context(struct drm_i915_gem_request *rq)
 		ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
 	}
 
-	kunmap_atomic(reg_state);
-
 	return 0;
 }
 
@@ -431,9 +447,8 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
 			/* Same ctx: ignore first request, as second request
 			 * will update tail past first request's workload */
 			cursor->elsp_submitted = req0->elsp_submitted;
-			list_del(&req0->execlist_link);
-			list_add_tail(&req0->execlist_link,
-				&ring->execlist_retired_req_list);
+			list_move_tail(&req0->execlist_link,
+				       &ring->execlist_retired_req_list);
 			req0 = cursor;
 		} else {
 			req1 = cursor;
@@ -478,16 +493,13 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring,
 					    execlist_link);
 
 	if (head_req != NULL) {
-		struct drm_i915_gem_object *ctx_obj =
-				head_req->ctx->engine[ring->id].state;
-		if (intel_execlists_ctx_id(ctx_obj) == request_id) {
+		if (intel_execlists_ctx_id(head_req->ctx, ring) == request_id) {
 			WARN(head_req->elsp_submitted == 0,
 			     "Never submitted head request\n");
 
 			if (--head_req->elsp_submitted <= 0) {
-				list_del(&head_req->execlist_link);
-				list_add_tail(&head_req->execlist_link,
-					&ring->execlist_retired_req_list);
+				list_move_tail(&head_req->execlist_link,
+					       &ring->execlist_retired_req_list);
 				return true;
 			}
 		}
@@ -496,6 +508,19 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring,
 	return false;
 }
 
+static void get_context_status(struct intel_engine_cs *ring,
+			       u8 read_pointer,
+			       u32 *status, u32 *context_id)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (WARN_ON(read_pointer >= GEN8_CSB_ENTRIES))
+		return;
+
+	*status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer));
+	*context_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer));
+}
+
 /**
  * intel_lrc_irq_handler() - handle Context Switch interrupts
  * @ring: Engine Command Streamer to handle.
@@ -516,16 +541,16 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring)
 	status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring));
 
 	read_pointer = ring->next_context_status_buffer;
-	write_pointer = status_pointer & GEN8_CSB_PTR_MASK;
+	write_pointer = GEN8_CSB_WRITE_PTR(status_pointer);
 	if (read_pointer > write_pointer)
 		write_pointer += GEN8_CSB_ENTRIES;
 
 	spin_lock(&ring->execlist_lock);
 
 	while (read_pointer < write_pointer) {
-		read_pointer++;
-		status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer % GEN8_CSB_ENTRIES));
-		status_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer % GEN8_CSB_ENTRIES));
+
+		get_context_status(ring, ++read_pointer % GEN8_CSB_ENTRIES,
+				   &status, &status_id);
 
 		if (status & GEN8_CTX_STATUS_IDLE_ACTIVE)
 			continue;
@@ -538,14 +563,14 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring)
 				WARN(1, "Preemption without Lite Restore\n");
 		}
 
-		 if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) ||
-		     (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) {
+		if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) ||
+		    (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) {
 			if (execlists_check_remove_request(ring, status_id))
 				submit_contexts++;
 		}
 	}
 
-	if (disable_lite_restore_wa(ring)) {
+	if (ring->disable_lite_restore_wa) {
 		/* Prevent a ctx to preempt itself */
 		if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) &&
 		    (submit_contexts != 0))
@@ -556,13 +581,16 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring)
 
 	spin_unlock(&ring->execlist_lock);
 
-	WARN(submit_contexts > 2, "More than two context complete events?\n");
+	if (unlikely(submit_contexts > 2))
+		DRM_ERROR("More than two context complete events?\n");
+
 	ring->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES;
 
+	/* Update the read pointer to the old write pointer. Manual ringbuffer
+	 * management ftw </sarcasm> */
 	I915_WRITE(RING_CONTEXT_STATUS_PTR(ring),
-		   _MASKED_FIELD(GEN8_CSB_PTR_MASK << 8,
-				 ((u32)ring->next_context_status_buffer &
-				  GEN8_CSB_PTR_MASK) << 8));
+		   _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
+				 ring->next_context_status_buffer << 8));
 }
 
 static int execlists_context_queue(struct drm_i915_gem_request *request)
@@ -571,8 +599,8 @@ static int execlists_context_queue(struct drm_i915_gem_request *request)
 	struct drm_i915_gem_request *cursor;
 	int num_elements = 0;
 
-	if (request->ctx != ring->default_context)
-		intel_lr_context_pin(request);
+	if (request->ctx != request->i915->kernel_context)
+		intel_lr_context_pin(request->ctx, ring);
 
 	i915_gem_request_reference(request);
 
@@ -592,9 +620,8 @@ static int execlists_context_queue(struct drm_i915_gem_request *request)
 		if (request->ctx == tail_req->ctx) {
 			WARN(tail_req->elsp_submitted != 0,
 				"More than 2 already-submitted reqs queued\n");
-			list_del(&tail_req->execlist_link);
-			list_add_tail(&tail_req->execlist_link,
-				&ring->execlist_retired_req_list);
+			list_move_tail(&tail_req->execlist_link,
+				       &ring->execlist_retired_req_list);
 		}
 	}
 
@@ -660,17 +687,27 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
 
 int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request)
 {
-	int ret;
+	int ret = 0;
 
 	request->ringbuf = request->ctx->engine[request->ring->id].ringbuf;
 
-	if (request->ctx != request->ring->default_context) {
-		ret = intel_lr_context_pin(request);
+	if (i915.enable_guc_submission) {
+		/*
+		 * Check that the GuC has space for the request before
+		 * going any further, as the i915_add_request() call
+		 * later on mustn't fail ...
+		 */
+		struct intel_guc *guc = &request->i915->guc;
+
+		ret = i915_guc_wq_check_space(guc->execbuf_client);
 		if (ret)
 			return ret;
 	}
 
-	return 0;
+	if (request->ctx != request->i915->kernel_context)
+		ret = intel_lr_context_pin(request->ctx, request->ring);
+
+	return ret;
 }
 
 static int logical_ring_wait_for_space(struct drm_i915_gem_request *req,
@@ -724,23 +761,46 @@ static int logical_ring_wait_for_space(struct drm_i915_gem_request *req,
  * 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
+static int
 intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 {
-	struct intel_engine_cs *ring = request->ring;
+	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct drm_i915_private *dev_priv = request->i915;
+	struct intel_engine_cs *engine = request->ring;
+
+	intel_logical_ring_advance(ringbuf);
+	request->tail = ringbuf->tail;
 
-	intel_logical_ring_advance(request->ringbuf);
+	/*
+	 * Here we add two extra NOOPs as padding to avoid
+	 * lite restore of a context with HEAD==TAIL.
+	 *
+	 * Caller must reserve WA_TAIL_DWORDS for us!
+	 */
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_advance(ringbuf);
 
-	request->tail = request->ringbuf->tail;
+	if (intel_ring_stopped(engine))
+		return 0;
 
-	if (intel_ring_stopped(ring))
-		return;
+	if (engine->last_context != request->ctx) {
+		if (engine->last_context)
+			intel_lr_context_unpin(engine->last_context, engine);
+		if (request->ctx != request->i915->kernel_context) {
+			intel_lr_context_pin(request->ctx, engine);
+			engine->last_context = request->ctx;
+		} else {
+			engine->last_context = NULL;
+		}
+	}
 
 	if (dev_priv->guc.execbuf_client)
 		i915_guc_submit(dev_priv->guc.execbuf_client, request);
 	else
 		execlists_context_queue(request);
+
+	return 0;
 }
 
 static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
@@ -967,8 +1027,9 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 		struct drm_i915_gem_object *ctx_obj =
 				ctx->engine[ring->id].state;
 
-		if (ctx_obj && (ctx != ring->default_context))
-			intel_lr_context_unpin(req);
+		if (ctx_obj && (ctx != req->i915->kernel_context))
+			intel_lr_context_unpin(ctx, ring);
+
 		list_del(&req->execlist_link);
 		i915_gem_request_unreference(req);
 	}
@@ -1012,24 +1073,39 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
 	return 0;
 }
 
-static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
-		struct drm_i915_gem_object *ctx_obj,
-		struct intel_ringbuffer *ringbuf)
+static int intel_lr_context_do_pin(struct intel_context *ctx,
+				   struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret = 0;
+	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
+	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+	struct page *lrc_state_page;
+	uint32_t *lrc_reg_state;
+	int ret;
 
 	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+
 	ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN,
 			PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
 	if (ret)
 		return ret;
 
+	lrc_state_page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN);
+	if (WARN_ON(!lrc_state_page)) {
+		ret = -ENODEV;
+		goto unpin_ctx_obj;
+	}
+
 	ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);
 	if (ret)
 		goto unpin_ctx_obj;
 
+	ctx->engine[ring->id].lrc_vma = i915_gem_obj_to_ggtt(ctx_obj);
+	intel_lr_context_descriptor_update(ctx, ring);
+	lrc_reg_state = kmap(lrc_state_page);
+	lrc_reg_state[CTX_RING_BUFFER_START+1] = ringbuf->vma->node.start;
+	ctx->engine[ring->id].lrc_reg_state = lrc_reg_state;
 	ctx_obj->dirty = true;
 
 	/* Invalidate GuC TLB. */
@@ -1044,37 +1120,40 @@ unpin_ctx_obj:
 	return ret;
 }
 
-static int intel_lr_context_pin(struct drm_i915_gem_request *rq)
+static int intel_lr_context_pin(struct intel_context *ctx,
+				struct intel_engine_cs *engine)
 {
 	int ret = 0;
-	struct intel_engine_cs *ring = rq->ring;
-	struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
-	struct intel_ringbuffer *ringbuf = rq->ringbuf;
 
-	if (rq->ctx->engine[ring->id].pin_count++ == 0) {
-		ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf);
+	if (ctx->engine[engine->id].pin_count++ == 0) {
+		ret = intel_lr_context_do_pin(ctx, engine);
 		if (ret)
 			goto reset_pin_count;
+
+		i915_gem_context_reference(ctx);
 	}
 	return ret;
 
 reset_pin_count:
-	rq->ctx->engine[ring->id].pin_count = 0;
+	ctx->engine[engine->id].pin_count = 0;
 	return ret;
 }
 
-void intel_lr_context_unpin(struct drm_i915_gem_request *rq)
+void intel_lr_context_unpin(struct intel_context *ctx,
+			    struct intel_engine_cs *engine)
 {
-	struct intel_engine_cs *ring = rq->ring;
-	struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
-	struct intel_ringbuffer *ringbuf = rq->ringbuf;
+	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
 
-	if (ctx_obj) {
-		WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
-		if (--rq->ctx->engine[ring->id].pin_count == 0) {
-			intel_unpin_ringbuffer_obj(ringbuf);
-			i915_gem_object_ggtt_unpin(ctx_obj);
-		}
+	WARN_ON(!mutex_is_locked(&ctx->i915->dev->struct_mutex));
+	if (--ctx->engine[engine->id].pin_count == 0) {
+		kunmap(kmap_to_page(ctx->engine[engine->id].lrc_reg_state));
+		intel_unpin_ringbuffer_obj(ctx->engine[engine->id].ringbuf);
+		i915_gem_object_ggtt_unpin(ctx_obj);
+		ctx->engine[engine->id].lrc_vma = NULL;
+		ctx->engine[engine->id].lrc_desc = 0;
+		ctx->engine[engine->id].lrc_reg_state = NULL;
+
+		i915_gem_context_unreference(ctx);
 	}
 }
 
@@ -1087,7 +1166,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_workarounds *w = &dev_priv->workarounds;
 
-	if (WARN_ON_ONCE(w->count == 0))
+	if (w->count == 0)
 		return 0;
 
 	ring->gpu_caches_dirty = true;
@@ -1474,7 +1553,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring)
 	u8 next_context_status_buffer_hw;
 
 	lrc_setup_hardware_status_page(ring,
-				ring->default_context->engine[ring->id].state);
+				dev_priv->kernel_context->engine[ring->id].state);
 
 	I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
 	I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
@@ -1493,9 +1572,11 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring)
 	 *      | Suspend-to-idle (freeze) | Suspend-to-RAM (mem) |
 	 * BDW  | CSB regs not reset       | CSB regs reset       |
 	 * CHT  | CSB regs not reset       | CSB regs not reset   |
+	 * SKL  |         ?                |         ?            |
+	 * BXT  |         ?                |         ?            |
 	 */
-	next_context_status_buffer_hw = (I915_READ(RING_CONTEXT_STATUS_PTR(ring))
-						   & GEN8_CSB_PTR_MASK);
+	next_context_status_buffer_hw =
+		GEN8_CSB_WRITE_PTR(I915_READ(RING_CONTEXT_STATUS_PTR(ring)));
 
 	/*
 	 * When the CSB registers are reset (also after power-up / gpu reset),
@@ -1698,7 +1779,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct intel_engine_cs *ring = ringbuf->ring;
 	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
-	bool vf_flush_wa;
+	bool vf_flush_wa = false;
 	u32 flags = 0;
 	int ret;
 
@@ -1720,14 +1801,14 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
-	}
 
-	/*
-	 * 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;
+		/*
+		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
+		 * pipe control.
+		 */
+		if (IS_GEN9(ring->dev))
+			vf_flush_wa = true;
+	}
 
 	ret = intel_logical_ring_begin(request, vf_flush_wa ? 12 : 6);
 	if (ret)
@@ -1791,44 +1872,71 @@ static void bxt_a_set_seqno(struct intel_engine_cs *ring, u32 seqno)
 	intel_flush_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
+/*
+ * Reserve space for 2 NOOPs at the end of each request to be
+ * used as a workaround for not being allowed to do lite
+ * restore with HEAD==TAIL (WaIdleLiteRestore).
+ */
+#define WA_TAIL_DWORDS 2
+
+static inline u32 hws_seqno_address(struct intel_engine_cs *engine)
+{
+	return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR;
+}
+
 static int gen8_emit_request(struct drm_i915_gem_request *request)
 {
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
-	struct intel_engine_cs *ring = ringbuf->ring;
-	u32 cmd;
 	int ret;
 
-	/*
-	 * Reserve space for 2 NOOPs at the end of each request to be
-	 * used as a workaround for not being allowed to do lite
-	 * restore with HEAD==TAIL (WaIdleLiteRestore).
-	 */
-	ret = intel_logical_ring_begin(request, 8);
+	ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS);
 	if (ret)
 		return ret;
 
-	cmd = MI_STORE_DWORD_IMM_GEN4;
-	cmd |= MI_GLOBAL_GTT;
+	/* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */
+	BUILD_BUG_ON(I915_GEM_HWS_INDEX_ADDR & (1 << 5));
 
-	intel_logical_ring_emit(ringbuf, cmd);
 	intel_logical_ring_emit(ringbuf,
-				(ring->status_page.gfx_addr +
-				(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
+				(MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW);
+	intel_logical_ring_emit(ringbuf,
+				hws_seqno_address(request->ring) |
+				MI_FLUSH_DW_USE_GTT);
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
-	intel_logical_ring_advance_and_submit(request);
+	return intel_logical_ring_advance_and_submit(request);
+}
 
-	/*
-	 * Here we add two extra NOOPs as padding to avoid
-	 * lite restore of a context with HEAD==TAIL.
+static int gen8_emit_request_render(struct drm_i915_gem_request *request)
+{
+	struct intel_ringbuffer *ringbuf = request->ringbuf;
+	int ret;
+
+	ret = intel_logical_ring_begin(request, 8 + WA_TAIL_DWORDS);
+	if (ret)
+		return ret;
+
+	/* We're using qword write, seqno should be aligned to 8 bytes. */
+	BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1);
+
+	/* w/a for post sync ops following a GPGPU operation we
+	 * need a prior CS_STALL, which is emitted by the flush
+	 * following the batch.
 	 */
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+	intel_logical_ring_emit(ringbuf,
+				(PIPE_CONTROL_GLOBAL_GTT_IVB |
+				 PIPE_CONTROL_CS_STALL |
+				 PIPE_CONTROL_QW_WRITE));
+	intel_logical_ring_emit(ringbuf, hws_seqno_address(request->ring));
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	/* We're thrashing one dword of HWS. */
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
-	intel_logical_ring_emit(ringbuf, MI_NOOP);
-	intel_logical_ring_advance(ringbuf);
-
-	return 0;
+	return intel_logical_ring_advance_and_submit(request);
 }
 
 static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
@@ -1911,12 +2019,44 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
 		ring->status_page.obj = NULL;
 	}
 
+	ring->disable_lite_restore_wa = false;
+	ring->ctx_desc_template = 0;
+
 	lrc_destroy_wa_ctx_obj(ring);
 	ring->dev = NULL;
 }
 
-static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
+static void
+logical_ring_default_vfuncs(struct drm_device *dev,
+			    struct intel_engine_cs *ring)
+{
+	/* Default vfuncs which can be overriden by each engine. */
+	ring->init_hw = gen8_init_common_ring;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+		ring->get_seqno = bxt_a_get_seqno;
+		ring->set_seqno = bxt_a_set_seqno;
+	} else {
+		ring->get_seqno = gen8_get_seqno;
+		ring->set_seqno = gen8_set_seqno;
+	}
+}
+
+static inline void
+logical_ring_default_irqs(struct intel_engine_cs *ring, unsigned shift)
+{
+	ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
+	ring->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
+}
+
+static int
+logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
 {
+	struct intel_context *dctx = to_i915(dev)->kernel_context;
 	int ret;
 
 	/* Intentionally left blank. */
@@ -1933,19 +2073,18 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin
 	INIT_LIST_HEAD(&ring->execlist_retired_req_list);
 	spin_lock_init(&ring->execlist_lock);
 
+	logical_ring_init_platform_invariants(ring);
+
 	ret = i915_cmd_parser_init_ring(ring);
 	if (ret)
 		goto error;
 
-	ret = intel_lr_context_deferred_alloc(ring->default_context, ring);
+	ret = intel_lr_context_deferred_alloc(dctx, ring);
 	if (ret)
 		goto error;
 
 	/* As this is the default context, always pin it */
-	ret = intel_lr_context_do_pin(
-			ring,
-			ring->default_context->engine[ring->id].state,
-			ring->default_context->engine[ring->id].ringbuf);
+	ret = intel_lr_context_do_pin(dctx, ring);
 	if (ret) {
 		DRM_ERROR(
 			"Failed to pin and map ringbuffer %s: %d\n",
@@ -1968,32 +2107,25 @@ static int logical_render_ring_init(struct drm_device *dev)
 
 	ring->name = "render ring";
 	ring->id = RCS;
+	ring->exec_id = I915_EXEC_RENDER;
+	ring->guc_id = GUC_RENDER_ENGINE;
 	ring->mmio_base = RENDER_RING_BASE;
-	ring->irq_enable_mask =
-		GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT;
-	ring->irq_keep_mask =
-		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT;
+
+	logical_ring_default_irqs(ring, GEN8_RCS_IRQ_SHIFT);
 	if (HAS_L3_DPF(dev))
 		ring->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 
+	logical_ring_default_vfuncs(dev, ring);
+
+	/* Override some for render ring. */
 	if (INTEL_INFO(dev)->gen >= 9)
 		ring->init_hw = gen9_init_render_ring;
 	else
 		ring->init_hw = gen8_init_render_ring;
 	ring->init_context = gen8_init_rcs_context;
 	ring->cleanup = intel_fini_pipe_control;
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
-		ring->get_seqno = bxt_a_get_seqno;
-		ring->set_seqno = bxt_a_set_seqno;
-	} else {
-		ring->get_seqno = gen8_get_seqno;
-		ring->set_seqno = gen8_set_seqno;
-	}
-	ring->emit_request = gen8_emit_request;
 	ring->emit_flush = gen8_emit_flush_render;
-	ring->irq_get = gen8_logical_ring_get_irq;
-	ring->irq_put = gen8_logical_ring_put_irq;
-	ring->emit_bb_start = gen8_emit_bb_start;
+	ring->emit_request = gen8_emit_request_render;
 
 	ring->dev = dev;
 
@@ -2027,25 +2159,12 @@ static int logical_bsd_ring_init(struct drm_device *dev)
 
 	ring->name = "bsd ring";
 	ring->id = VCS;
+	ring->exec_id = I915_EXEC_BSD;
+	ring->guc_id = GUC_VIDEO_ENGINE;
 	ring->mmio_base = GEN6_BSD_RING_BASE;
-	ring->irq_enable_mask =
-		GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
-	ring->irq_keep_mask =
-		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
 
-	ring->init_hw = gen8_init_common_ring;
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
-		ring->get_seqno = bxt_a_get_seqno;
-		ring->set_seqno = bxt_a_set_seqno;
-	} else {
-		ring->get_seqno = gen8_get_seqno;
-		ring->set_seqno = gen8_set_seqno;
-	}
-	ring->emit_request = gen8_emit_request;
-	ring->emit_flush = gen8_emit_flush;
-	ring->irq_get = gen8_logical_ring_get_irq;
-	ring->irq_put = gen8_logical_ring_put_irq;
-	ring->emit_bb_start = gen8_emit_bb_start;
+	logical_ring_default_irqs(ring, GEN8_VCS1_IRQ_SHIFT);
+	logical_ring_default_vfuncs(dev, ring);
 
 	return logical_ring_init(dev, ring);
 }
@@ -2055,22 +2174,14 @@ static int logical_bsd2_ring_init(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring = &dev_priv->ring[VCS2];
 
-	ring->name = "bds2 ring";
+	ring->name = "bsd2 ring";
 	ring->id = VCS2;
+	ring->exec_id = I915_EXEC_BSD;
+	ring->guc_id = GUC_VIDEO_ENGINE2;
 	ring->mmio_base = GEN8_BSD2_RING_BASE;
-	ring->irq_enable_mask =
-		GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
-	ring->irq_keep_mask =
-		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
 
-	ring->init_hw = gen8_init_common_ring;
-	ring->get_seqno = gen8_get_seqno;
-	ring->set_seqno = gen8_set_seqno;
-	ring->emit_request = gen8_emit_request;
-	ring->emit_flush = gen8_emit_flush;
-	ring->irq_get = gen8_logical_ring_get_irq;
-	ring->irq_put = gen8_logical_ring_put_irq;
-	ring->emit_bb_start = gen8_emit_bb_start;
+	logical_ring_default_irqs(ring, GEN8_VCS2_IRQ_SHIFT);
+	logical_ring_default_vfuncs(dev, ring);
 
 	return logical_ring_init(dev, ring);
 }
@@ -2082,25 +2193,12 @@ static int logical_blt_ring_init(struct drm_device *dev)
 
 	ring->name = "blitter ring";
 	ring->id = BCS;
+	ring->exec_id = I915_EXEC_BLT;
+	ring->guc_id = GUC_BLITTER_ENGINE;
 	ring->mmio_base = BLT_RING_BASE;
-	ring->irq_enable_mask =
-		GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
-	ring->irq_keep_mask =
-		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
 
-	ring->init_hw = gen8_init_common_ring;
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
-		ring->get_seqno = bxt_a_get_seqno;
-		ring->set_seqno = bxt_a_set_seqno;
-	} else {
-		ring->get_seqno = gen8_get_seqno;
-		ring->set_seqno = gen8_set_seqno;
-	}
-	ring->emit_request = gen8_emit_request;
-	ring->emit_flush = gen8_emit_flush;
-	ring->irq_get = gen8_logical_ring_get_irq;
-	ring->irq_put = gen8_logical_ring_put_irq;
-	ring->emit_bb_start = gen8_emit_bb_start;
+	logical_ring_default_irqs(ring, GEN8_BCS_IRQ_SHIFT);
+	logical_ring_default_vfuncs(dev, ring);
 
 	return logical_ring_init(dev, ring);
 }
@@ -2112,25 +2210,12 @@ static int logical_vebox_ring_init(struct drm_device *dev)
 
 	ring->name = "video enhancement ring";
 	ring->id = VECS;
+	ring->exec_id = I915_EXEC_VEBOX;
+	ring->guc_id = GUC_VIDEOENHANCE_ENGINE;
 	ring->mmio_base = VEBOX_RING_BASE;
-	ring->irq_enable_mask =
-		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
-	ring->irq_keep_mask =
-		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
 
-	ring->init_hw = gen8_init_common_ring;
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
-		ring->get_seqno = bxt_a_get_seqno;
-		ring->set_seqno = bxt_a_set_seqno;
-	} else {
-		ring->get_seqno = gen8_get_seqno;
-		ring->set_seqno = gen8_set_seqno;
-	}
-	ring->emit_request = gen8_emit_request;
-	ring->emit_flush = gen8_emit_flush;
-	ring->irq_get = gen8_logical_ring_get_irq;
-	ring->irq_put = gen8_logical_ring_put_irq;
-	ring->emit_bb_start = gen8_emit_bb_start;
+	logical_ring_default_irqs(ring, GEN8_VECS_IRQ_SHIFT);
+	logical_ring_default_vfuncs(dev, ring);
 
 	return logical_ring_init(dev, ring);
 }
@@ -2235,6 +2320,27 @@ make_rpcs(struct drm_device *dev)
 	return rpcs;
 }
 
+static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *ring)
+{
+	u32 indirect_ctx_offset;
+
+	switch (INTEL_INFO(ring->dev)->gen) {
+	default:
+		MISSING_CASE(INTEL_INFO(ring->dev)->gen);
+		/* fall through */
+	case 9:
+		indirect_ctx_offset =
+			GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+		break;
+	case 8:
+		indirect_ctx_offset =
+			GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT;
+		break;
+	}
+
+	return indirect_ctx_offset;
+}
+
 static int
 populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_obj,
 		    struct intel_engine_cs *ring, struct intel_ringbuffer *ringbuf)
@@ -2278,7 +2384,8 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 	ASSIGN_CTX_REG(reg_state, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(ring),
 		       _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
 					  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
-					  CTX_CTRL_RS_CTX_ENABLE));
+					  (HAS_RESOURCE_STREAMER(dev) ?
+					    CTX_CTRL_RS_CTX_ENABLE : 0)));
 	ASSIGN_CTX_REG(reg_state, CTX_RING_HEAD, RING_HEAD(ring->mmio_base), 0);
 	ASSIGN_CTX_REG(reg_state, CTX_RING_TAIL, RING_TAIL(ring->mmio_base), 0);
 	/* Ring buffer start address is not known until the buffer is pinned.
@@ -2307,7 +2414,7 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 				(wa_ctx->indirect_ctx.size / CACHELINE_DWORDS);
 
 			reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] =
-				CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT << 6;
+				intel_lr_indirect_ctx_offset(ring) << 6;
 
 			reg_state[CTX_BB_PER_CTX_PTR+1] =
 				(ggtt_offset + wa_ctx->per_ctx.offset * sizeof(uint32_t)) |
@@ -2368,26 +2475,39 @@ void intel_lr_context_free(struct intel_context *ctx)
 {
 	int i;
 
-	for (i = 0; i < I915_NUM_RINGS; i++) {
+	for (i = I915_NUM_RINGS; --i >= 0; ) {
+		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
 		struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
 
-		if (ctx_obj) {
-			struct intel_ringbuffer *ringbuf =
-					ctx->engine[i].ringbuf;
-			struct intel_engine_cs *ring = ringbuf->ring;
+		if (!ctx_obj)
+			continue;
 
-			if (ctx == ring->default_context) {
-				intel_unpin_ringbuffer_obj(ringbuf);
-				i915_gem_object_ggtt_unpin(ctx_obj);
-			}
-			WARN_ON(ctx->engine[ring->id].pin_count);
-			intel_ringbuffer_free(ringbuf);
-			drm_gem_object_unreference(&ctx_obj->base);
+		if (ctx == ctx->i915->kernel_context) {
+			intel_unpin_ringbuffer_obj(ringbuf);
+			i915_gem_object_ggtt_unpin(ctx_obj);
 		}
+
+		WARN_ON(ctx->engine[i].pin_count);
+		intel_ringbuffer_free(ringbuf);
+		drm_gem_object_unreference(&ctx_obj->base);
 	}
 }
 
-static uint32_t get_lr_context_size(struct intel_engine_cs *ring)
+/**
+ * intel_lr_context_size() - return the size of the context for an engine
+ * @ring: which engine to find the context size for
+ *
+ * Each engine may require a different amount of space for a context image,
+ * so when allocating (or copying) an image, this function can be used to
+ * find the right size for the specific engine.
+ *
+ * Return: size (in bytes) of an engine-specific context image
+ *
+ * Note: this size includes the HWSP, which is part of the context image
+ * in LRC mode, but does not include the "shared data page" used with
+ * GuC submission. The caller should account for this if using the GuC.
+ */
+uint32_t intel_lr_context_size(struct intel_engine_cs *ring)
 {
 	int ret = 0;
 
@@ -2444,7 +2564,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
  */
 
 int intel_lr_context_deferred_alloc(struct intel_context *ctx,
-				     struct intel_engine_cs *ring)
+				    struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_gem_object *ctx_obj;
@@ -2455,7 +2575,7 @@ int intel_lr_context_deferred_alloc(struct intel_context *ctx,
 	WARN_ON(ctx->legacy_hw_ctx.rcs_state != NULL);
 	WARN_ON(ctx->engine[ring->id].state);
 
-	context_size = round_up(get_lr_context_size(ring), 4096);
+	context_size = round_up(intel_lr_context_size(ring), 4096);
 
 	/* One extra page as the sharing data between driver and GuC */
 	context_size += PAGE_SIZE * LRC_PPHWSP_PN;
@@ -2481,14 +2601,13 @@ int intel_lr_context_deferred_alloc(struct intel_context *ctx,
 	ctx->engine[ring->id].ringbuf = ringbuf;
 	ctx->engine[ring->id].state = ctx_obj;
 
-	if (ctx != ring->default_context && ring->init_context) {
+	if (ctx != ctx->i915->kernel_context && ring->init_context) {
 		struct drm_i915_gem_request *req;
 
-		ret = i915_gem_request_alloc(ring,
-			ctx, &req);
-		if (ret) {
-			DRM_ERROR("ring create req: %d\n",
-				ret);
+		req = i915_gem_request_alloc(ring, ctx);
+		if (IS_ERR(req)) {
+			ret = PTR_ERR(req);
+			DRM_ERROR("ring create req: %d\n", ret);
 			goto error_ringbuf;
 		}
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 0b821b917..e6cda3e22 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -25,8 +25,6 @@
 #define _INTEL_LRC_H_
 
 #define GEN8_LR_CONTEXT_ALIGN 4096
-#define GEN8_CSB_ENTRIES 6
-#define GEN8_CSB_PTR_MASK 0x07
 
 /* Execlists regs */
 #define RING_ELSP(ring)				_MMIO((ring)->mmio_base + 0x230)
@@ -40,6 +38,22 @@
 #define RING_CONTEXT_STATUS_BUF_HI(ring, i)	_MMIO((ring)->mmio_base + 0x370 + (i) * 8 + 4)
 #define RING_CONTEXT_STATUS_PTR(ring)		_MMIO((ring)->mmio_base + 0x3a0)
 
+/* The docs specify that the write pointer wraps around after 5h, "After status
+ * is written out to the last available status QW at offset 5h, this pointer
+ * wraps to 0."
+ *
+ * Therefore, one must infer than even though there are 3 bits available, 6 and
+ * 7 appear to be * reserved.
+ */
+#define GEN8_CSB_ENTRIES 6
+#define GEN8_CSB_PTR_MASK 0x7
+#define GEN8_CSB_READ_PTR_MASK (GEN8_CSB_PTR_MASK << 8)
+#define GEN8_CSB_WRITE_PTR_MASK (GEN8_CSB_PTR_MASK << 0)
+#define GEN8_CSB_WRITE_PTR(csb_status) \
+	(((csb_status) & GEN8_CSB_WRITE_PTR_MASK) >> 0)
+#define GEN8_CSB_READ_PTR(csb_status) \
+	(((csb_status) & GEN8_CSB_READ_PTR_MASK) >> 8)
+
 /* Logical Rings */
 int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request);
 int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request);
@@ -84,21 +98,25 @@ static inline void intel_logical_ring_emit_reg(struct intel_ringbuffer *ringbuf,
 #define LRC_STATE_PN	(LRC_PPHWSP_PN + 1)
 
 void intel_lr_context_free(struct intel_context *ctx);
+uint32_t intel_lr_context_size(struct intel_engine_cs *ring);
 int intel_lr_context_deferred_alloc(struct intel_context *ctx,
 				    struct intel_engine_cs *ring);
-void intel_lr_context_unpin(struct drm_i915_gem_request *req);
+void intel_lr_context_unpin(struct intel_context *ctx,
+			    struct intel_engine_cs *engine);
 void intel_lr_context_reset(struct drm_device *dev,
 			struct intel_context *ctx);
 uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
 				     struct intel_engine_cs *ring);
 
+u32 intel_execlists_ctx_id(struct intel_context *ctx,
+			   struct intel_engine_cs *ring);
+
 /* Execlists */
 int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
 struct i915_execbuffer_params;
 int intel_execlists_submission(struct i915_execbuffer_params *params,
 			       struct drm_i915_gem_execbuffer2 *args,
 			       struct list_head *vmas);
-u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
 
 void intel_lrc_irq_handler(struct intel_engine_cs *ring);
 void intel_execlists_retire_requests(struct intel_engine_cs *ring);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bc04d8d29..10dc3517b 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -31,6 +31,7 @@
 #include <linux/dmi.h>
 #include <linux/i2c.h>
 #include <linux/slab.h>
+#include <linux/vga_switcheroo.h>
 #include <drm/drmP.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
@@ -122,6 +123,10 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 
 	pipe_config->base.adjusted_mode.flags |= flags;
 
+	if (INTEL_INFO(dev)->gen < 5)
+		pipe_config->gmch_pfit.lvds_border_bits =
+			tmp & LVDS_BORDER_ENABLE;
+
 	/* gen2/3 store dither state in pfit control, needs to match */
 	if (INTEL_INFO(dev)->gen < 4) {
 		tmp = I915_READ(PFIT_CONTROL);
@@ -477,11 +482,8 @@ static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
 	 * and as part of the cleanup in the hw state restore we also redisable
 	 * the vga plane.
 	 */
-	if (!HAS_PCH_SPLIT(dev)) {
-		drm_modeset_lock_all(dev);
+	if (!HAS_PCH_SPLIT(dev))
 		intel_display_resume(dev);
-		drm_modeset_unlock_all(dev);
-	}
 
 	dev_priv->modeset_restore = MODESET_DONE;
 
@@ -1088,7 +1090,12 @@ void intel_lvds_init(struct drm_device *dev)
 	 * preferred mode is the right one.
 	 */
 	mutex_lock(&dev->mode_config.mutex);
-	edid = drm_get_edid(connector, intel_gmbus_get_adapter(dev_priv, pin));
+	if (vga_switcheroo_handler_flags() & VGA_SWITCHEROO_CAN_SWITCH_DDC)
+		edid = drm_get_edid_switcheroo(connector,
+				    intel_gmbus_get_adapter(dev_priv, pin));
+	else
+		edid = drm_get_edid(connector,
+				    intel_gmbus_get_adapter(dev_priv, pin));
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
 			drm_mode_connector_update_edid_property(connector,
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 76f1980a7..9168413fe 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -240,9 +240,9 @@ static int intel_overlay_on(struct intel_overlay *overlay)
 	WARN_ON(overlay->active);
 	WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
 
-	ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-	if (ret)
-		return ret;
+	req = i915_gem_request_alloc(ring, NULL);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	ret = intel_ring_begin(req, 4);
 	if (ret) {
@@ -283,9 +283,9 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 	if (tmp & (1 << 17))
 		DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
 
-	ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-	if (ret)
-		return ret;
+	req = i915_gem_request_alloc(ring, NULL);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	ret = intel_ring_begin(req, 2);
 	if (ret) {
@@ -349,9 +349,9 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	 * of the hw. Do it in both cases */
 	flip_addr |= OFC_UPDATE;
 
-	ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-	if (ret)
-		return ret;
+	req = i915_gem_request_alloc(ring, NULL);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	ret = intel_ring_begin(req, 6);
 	if (ret) {
@@ -423,9 +423,9 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 		/* synchronous slowpath */
 		struct drm_i915_gem_request *req;
 
-		ret = i915_gem_request_alloc(ring, ring->default_context, &req);
-		if (ret)
-			return ret;
+		req = i915_gem_request_alloc(ring, NULL);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
 
 		ret = intel_ring_begin(req, 2);
 		if (ret) {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7e4a9842b..54ab02342 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -32,6 +32,8 @@
 #include <linux/module.h>
 
 /**
+ * DOC: RC6
+ *
  * RC6 is a special power stage which allows the GPU to enter an very
  * low-voltage mode when idle, using down to 0V while at this stage.  This
  * stage is entered automatically when the GPU is idle when RC6 support is
@@ -546,7 +548,7 @@ static const struct intel_watermark_params i845_wm_info = {
  * intel_calculate_wm - calculate watermark level
  * @clock_in_khz: pixel clock
  * @wm: chip FIFO params
- * @pixel_size: display pixel size
+ * @cpp: bytes per pixel
  * @latency_ns: memory latency for the platform
  *
  * Calculate the watermark level (the level at which the display plane will
@@ -562,8 +564,7 @@ static const struct intel_watermark_params i845_wm_info = {
  */
 static unsigned long intel_calculate_wm(unsigned long clock_in_khz,
 					const struct intel_watermark_params *wm,
-					int fifo_size,
-					int pixel_size,
+					int fifo_size, int cpp,
 					unsigned long latency_ns)
 {
 	long entries_required, wm_size;
@@ -574,7 +575,7 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz,
 	 * clocks go from a few thousand to several hundred thousand.
 	 * latency is usually a few thousand
 	 */
-	entries_required = ((clock_in_khz / 1000) * pixel_size * latency_ns) /
+	entries_required = ((clock_in_khz / 1000) * cpp * latency_ns) /
 		1000;
 	entries_required = DIV_ROUND_UP(entries_required, wm->cacheline_size);
 
@@ -638,13 +639,13 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc)
 	crtc = single_enabled_crtc(dev);
 	if (crtc) {
 		const struct drm_display_mode *adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode;
-		int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8;
+		int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 		int clock = adjusted_mode->crtc_clock;
 
 		/* Display SR */
 		wm = intel_calculate_wm(clock, &pineview_display_wm,
 					pineview_display_wm.fifo_size,
-					pixel_size, latency->display_sr);
+					cpp, latency->display_sr);
 		reg = I915_READ(DSPFW1);
 		reg &= ~DSPFW_SR_MASK;
 		reg |= FW_WM(wm, SR);
@@ -654,7 +655,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc)
 		/* cursor SR */
 		wm = intel_calculate_wm(clock, &pineview_cursor_wm,
 					pineview_display_wm.fifo_size,
-					pixel_size, latency->cursor_sr);
+					cpp, latency->cursor_sr);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_CURSOR_SR_MASK;
 		reg |= FW_WM(wm, CURSOR_SR);
@@ -663,7 +664,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc)
 		/* Display HPLL off SR */
 		wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm,
 					pineview_display_hplloff_wm.fifo_size,
-					pixel_size, latency->display_hpll_disable);
+					cpp, latency->display_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_SR_MASK;
 		reg |= FW_WM(wm, HPLL_SR);
@@ -672,7 +673,7 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc)
 		/* cursor HPLL off SR */
 		wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm,
 					pineview_display_hplloff_wm.fifo_size,
-					pixel_size, latency->cursor_hpll_disable);
+					cpp, latency->cursor_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_CURSOR_MASK;
 		reg |= FW_WM(wm, HPLL_CURSOR);
@@ -696,7 +697,7 @@ static bool g4x_compute_wm0(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	const struct drm_display_mode *adjusted_mode;
-	int htotal, hdisplay, clock, pixel_size;
+	int htotal, hdisplay, clock, cpp;
 	int line_time_us, line_count;
 	int entries, tlb_miss;
 
@@ -711,10 +712,10 @@ static bool g4x_compute_wm0(struct drm_device *dev,
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 	hdisplay = to_intel_crtc(crtc)->config->pipe_src_w;
-	pixel_size = crtc->primary->state->fb->bits_per_pixel / 8;
+	cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 
 	/* Use the small buffer method to calculate plane watermark */
-	entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000;
+	entries = ((clock * cpp / 1000) * display_latency_ns) / 1000;
 	tlb_miss = display->fifo_size*display->cacheline_size - hdisplay * 8;
 	if (tlb_miss > 0)
 		entries += tlb_miss;
@@ -726,7 +727,7 @@ static bool g4x_compute_wm0(struct drm_device *dev,
 	/* Use the large buffer method to calculate cursor watermark */
 	line_time_us = max(htotal * 1000 / clock, 1);
 	line_count = (cursor_latency_ns / line_time_us + 1000) / 1000;
-	entries = line_count * crtc->cursor->state->crtc_w * pixel_size;
+	entries = line_count * crtc->cursor->state->crtc_w * cpp;
 	tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8;
 	if (tlb_miss > 0)
 		entries += tlb_miss;
@@ -782,7 +783,7 @@ static bool g4x_compute_srwm(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	const struct drm_display_mode *adjusted_mode;
-	int hdisplay, htotal, pixel_size, clock;
+	int hdisplay, htotal, cpp, clock;
 	unsigned long line_time_us;
 	int line_count, line_size;
 	int small, large;
@@ -798,21 +799,21 @@ static bool g4x_compute_srwm(struct drm_device *dev,
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 	hdisplay = to_intel_crtc(crtc)->config->pipe_src_w;
-	pixel_size = crtc->primary->state->fb->bits_per_pixel / 8;
+	cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 
 	line_time_us = max(htotal * 1000 / clock, 1);
 	line_count = (latency_ns / line_time_us + 1000) / 1000;
-	line_size = hdisplay * pixel_size;
+	line_size = hdisplay * cpp;
 
 	/* Use the minimum of the small and large buffer method for primary */
-	small = ((clock * pixel_size / 1000) * latency_ns) / 1000;
+	small = ((clock * cpp / 1000) * latency_ns) / 1000;
 	large = line_count * line_size;
 
 	entries = DIV_ROUND_UP(min(small, large), display->cacheline_size);
 	*display_wm = entries + display->guard_size;
 
 	/* calculate the self-refresh watermark for display cursor */
-	entries = line_count * pixel_size * crtc->cursor->state->crtc_w;
+	entries = line_count * cpp * crtc->cursor->state->crtc_w;
 	entries = DIV_ROUND_UP(entries, cursor->cacheline_size);
 	*cursor_wm = entries + cursor->guard_size;
 
@@ -904,13 +905,13 @@ enum vlv_wm_level {
 static unsigned int vlv_wm_method2(unsigned int pixel_rate,
 				   unsigned int pipe_htotal,
 				   unsigned int horiz_pixels,
-				   unsigned int bytes_per_pixel,
+				   unsigned int cpp,
 				   unsigned int latency)
 {
 	unsigned int ret;
 
 	ret = (latency * pixel_rate) / (pipe_htotal * 10000);
-	ret = (ret + 1) * horiz_pixels * bytes_per_pixel;
+	ret = (ret + 1) * horiz_pixels * cpp;
 	ret = DIV_ROUND_UP(ret, 64);
 
 	return ret;
@@ -939,7 +940,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane,
 				     int level)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	int clock, htotal, pixel_size, width, wm;
+	int clock, htotal, cpp, width, wm;
 
 	if (dev_priv->wm.pri_latency[level] == 0)
 		return USHRT_MAX;
@@ -947,7 +948,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane,
 	if (!state->visible)
 		return 0;
 
-	pixel_size = drm_format_plane_cpp(state->base.fb->pixel_format, 0);
+	cpp = drm_format_plane_cpp(state->base.fb->pixel_format, 0);
 	clock = crtc->config->base.adjusted_mode.crtc_clock;
 	htotal = crtc->config->base.adjusted_mode.crtc_htotal;
 	width = crtc->config->pipe_src_w;
@@ -963,7 +964,7 @@ static uint16_t vlv_compute_wm_level(struct intel_plane *plane,
 		 */
 		wm = 63;
 	} else {
-		wm = vlv_wm_method2(clock, htotal, width, pixel_size,
+		wm = vlv_wm_method2(clock, htotal, width, cpp,
 				    dev_priv->wm.pri_latency[level] * 10);
 	}
 
@@ -1437,7 +1438,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 		int clock = adjusted_mode->crtc_clock;
 		int htotal = adjusted_mode->crtc_htotal;
 		int hdisplay = to_intel_crtc(crtc)->config->pipe_src_w;
-		int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8;
+		int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 		unsigned long line_time_us;
 		int entries;
 
@@ -1445,7 +1446,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 
 		/* Use ns/us then divide to preserve precision */
 		entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) *
-			pixel_size * hdisplay;
+			cpp * hdisplay;
 		entries = DIV_ROUND_UP(entries, I915_FIFO_LINE_SIZE);
 		srwm = I965_FIFO_SIZE - entries;
 		if (srwm < 0)
@@ -1455,7 +1456,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 			      entries, srwm);
 
 		entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) *
-			pixel_size * crtc->cursor->state->crtc_w;
+			cpp * crtc->cursor->state->crtc_w;
 		entries = DIV_ROUND_UP(entries,
 					  i965_cursor_wm_info.cacheline_size);
 		cursor_sr = i965_cursor_wm_info.fifo_size -
@@ -1516,7 +1517,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev, 0);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode;
-		int cpp = crtc->primary->state->fb->bits_per_pixel / 8;
+		int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 		if (IS_GEN2(dev))
 			cpp = 4;
 
@@ -1538,7 +1539,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev, 1);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode;
-		int cpp = crtc->primary->state->fb->bits_per_pixel / 8;
+		int cpp = drm_format_plane_cpp(crtc->primary->state->fb->pixel_format, 0);
 		if (IS_GEN2(dev))
 			cpp = 4;
 
@@ -1584,7 +1585,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 		int clock = adjusted_mode->crtc_clock;
 		int htotal = adjusted_mode->crtc_htotal;
 		int hdisplay = to_intel_crtc(enabled)->config->pipe_src_w;
-		int pixel_size = enabled->primary->state->fb->bits_per_pixel / 8;
+		int cpp = drm_format_plane_cpp(enabled->primary->state->fb->pixel_format, 0);
 		unsigned long line_time_us;
 		int entries;
 
@@ -1592,7 +1593,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 
 		/* Use ns/us then divide to preserve precision */
 		entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) *
-			pixel_size * hdisplay;
+			cpp * hdisplay;
 		entries = DIV_ROUND_UP(entries, wm_info->cacheline_size);
 		DRM_DEBUG_KMS("self-refresh entries: %d\n", entries);
 		srwm = wm_info->fifo_size - entries;
@@ -1672,6 +1673,9 @@ uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 		if (pipe_h < pfit_h)
 			pipe_h = pfit_h;
 
+		if (WARN_ON(!pfit_w || !pfit_h))
+			return pixel_rate;
+
 		pixel_rate = div_u64((uint64_t) pixel_rate * pipe_w * pipe_h,
 				     pfit_w * pfit_h);
 	}
@@ -1680,15 +1684,14 @@ uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 }
 
 /* latency must be in 0.1us units. */
-static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
-			       uint32_t latency)
+static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latency)
 {
 	uint64_t ret;
 
 	if (WARN(latency == 0, "Latency value missing\n"))
 		return UINT_MAX;
 
-	ret = (uint64_t) pixel_rate * bytes_per_pixel * latency;
+	ret = (uint64_t) pixel_rate * cpp * latency;
 	ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2;
 
 	return ret;
@@ -1696,24 +1699,37 @@ static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 
 /* latency must be in 0.1us units. */
 static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
-			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
+			       uint32_t horiz_pixels, uint8_t cpp,
 			       uint32_t latency)
 {
 	uint32_t ret;
 
 	if (WARN(latency == 0, "Latency value missing\n"))
 		return UINT_MAX;
+	if (WARN_ON(!pipe_htotal))
+		return UINT_MAX;
 
 	ret = (latency * pixel_rate) / (pipe_htotal * 10000);
-	ret = (ret + 1) * horiz_pixels * bytes_per_pixel;
+	ret = (ret + 1) * horiz_pixels * cpp;
 	ret = DIV_ROUND_UP(ret, 64) + 2;
 	return ret;
 }
 
 static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
-			   uint8_t bytes_per_pixel)
+			   uint8_t cpp)
 {
-	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
+	/*
+	 * Neither of these should be possible since this function shouldn't be
+	 * called if the CRTC is off or the plane is invisible.  But let's be
+	 * extra paranoid to avoid a potential divide-by-zero if we screw up
+	 * elsewhere in the driver.
+	 */
+	if (WARN_ON(!cpp))
+		return 0;
+	if (WARN_ON(!horiz_pixels))
+		return 0;
+
+	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * cpp) + 2;
 }
 
 struct ilk_wm_maximums {
@@ -1732,13 +1748,14 @@ static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate,
 				   uint32_t mem_value,
 				   bool is_lp)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	int cpp = pstate->base.fb ?
+		drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0;
 	uint32_t method1, method2;
 
 	if (!cstate->base.active || !pstate->visible)
 		return 0;
 
-	method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value);
+	method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), cpp, mem_value);
 
 	if (!is_lp)
 		return method1;
@@ -1746,8 +1763,7 @@ static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate,
 	method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 drm_rect_width(&pstate->dst),
-				 bpp,
-				 mem_value);
+				 cpp, mem_value);
 
 	return min(method1, method2);
 }
@@ -1760,18 +1776,18 @@ static uint32_t ilk_compute_spr_wm(const struct intel_crtc_state *cstate,
 				   const struct intel_plane_state *pstate,
 				   uint32_t mem_value)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	int cpp = pstate->base.fb ?
+		drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0;
 	uint32_t method1, method2;
 
 	if (!cstate->base.active || !pstate->visible)
 		return 0;
 
-	method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value);
+	method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), cpp, mem_value);
 	method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 drm_rect_width(&pstate->dst),
-				 bpp,
-				 mem_value);
+				 cpp, mem_value);
 	return min(method1, method2);
 }
 
@@ -1804,12 +1820,13 @@ static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate,
 				   const struct intel_plane_state *pstate,
 				   uint32_t pri_val)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	int cpp = pstate->base.fb ?
+		drm_format_plane_cpp(pstate->base.fb->pixel_format, 0) : 0;
 
 	if (!cstate->base.active || !pstate->visible)
 		return 0;
 
-	return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->dst), bpp);
+	return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->dst), cpp);
 }
 
 static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
@@ -2002,14 +2019,19 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
 }
 
 static uint32_t
-hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
+hsw_compute_linetime_wm(struct drm_device *dev,
+			struct intel_crtc_state *cstate)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode =
+		&cstate->base.adjusted_mode;
 	u32 linetime, ips_linetime;
 
-	if (!intel_crtc->active)
+	if (!cstate->base.active)
+		return 0;
+	if (WARN_ON(adjusted_mode->crtc_clock == 0))
+		return 0;
+	if (WARN_ON(dev_priv->cdclk_freq == 0))
 		return 0;
 
 	/* The WM are computed with base on how long it takes to fill a single
@@ -2318,8 +2340,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc,
 			     pristate, sprstate, curstate, &pipe_wm->wm[0]);
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
-		pipe_wm->linetime = hsw_compute_linetime_wm(dev,
-							    &intel_crtc->base);
+		pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate);
 
 	/* LP0 watermarks always use 1/2 DDB partitioning */
 	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
@@ -2855,25 +2876,28 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
 			     int y)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	struct drm_framebuffer *fb = pstate->fb;
+	uint32_t width = 0, height = 0;
+
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(pstate->rotation))
+		swap(width, height);
 
 	/* for planar format */
 	if (fb->pixel_format == DRM_FORMAT_NV12) {
 		if (y)  /* y-plane data rate */
-			return intel_crtc->config->pipe_src_w *
-				intel_crtc->config->pipe_src_h *
+			return width * height *
 				drm_format_plane_cpp(fb->pixel_format, 0);
 		else    /* uv-plane data rate */
-			return (intel_crtc->config->pipe_src_w/2) *
-				(intel_crtc->config->pipe_src_h/2) *
+			return (width / 2) * (height / 2) *
 				drm_format_plane_cpp(fb->pixel_format, 1);
 	}
 
 	/* for packed formats */
-	return intel_crtc->config->pipe_src_w *
-		intel_crtc->config->pipe_src_h *
-		drm_format_plane_cpp(fb->pixel_format, 0);
+	return width * height * drm_format_plane_cpp(fb->pixel_format, 0);
 }
 
 /*
@@ -2952,8 +2976,9 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		struct drm_framebuffer *fb = plane->state->fb;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (fb == NULL)
+		if (!to_intel_plane_state(plane->state)->visible)
 			continue;
+
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
 
@@ -2979,7 +3004,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		uint16_t plane_blocks, y_plane_blocks = 0;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (pstate->fb == NULL)
+		if (!to_intel_plane_state(pstate)->visible)
 			continue;
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
@@ -3029,26 +3054,25 @@ static uint32_t skl_pipe_pixel_rate(const struct intel_crtc_state *config)
 
 /*
  * The max latency should be 257 (max the punit can code is 255 and we add 2us
- * for the read latency) and bytes_per_pixel should always be <= 8, so that
+ * for the read latency) and cpp should always be <= 8, so that
  * should allow pixel_rate up to ~2 GHz which seems sufficient since max
  * 2xcdclk is 1350 MHz and the pixel rate should never exceed that.
 */
-static uint32_t skl_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
-			       uint32_t latency)
+static uint32_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp, uint32_t latency)
 {
 	uint32_t wm_intermediate_val, ret;
 
 	if (latency == 0)
 		return UINT_MAX;
 
-	wm_intermediate_val = latency * pixel_rate * bytes_per_pixel / 512;
+	wm_intermediate_val = latency * pixel_rate * cpp / 512;
 	ret = DIV_ROUND_UP(wm_intermediate_val, 1000);
 
 	return ret;
 }
 
 static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
-			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
+			       uint32_t horiz_pixels, uint8_t cpp,
 			       uint64_t tiling, uint32_t latency)
 {
 	uint32_t ret;
@@ -3058,7 +3082,7 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 	if (latency == 0)
 		return UINT_MAX;
 
-	plane_bytes_per_line = horiz_pixels * bytes_per_pixel;
+	plane_bytes_per_line = horiz_pixels * cpp;
 
 	if (tiling == I915_FORMAT_MOD_Y_TILED ||
 	    tiling == I915_FORMAT_MOD_Yf_TILED) {
@@ -3103,28 +3127,36 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 {
 	struct drm_plane *plane = &intel_plane->base;
 	struct drm_framebuffer *fb = plane->state->fb;
+	struct intel_plane_state *intel_pstate =
+					to_intel_plane_state(plane->state);
 	uint32_t latency = dev_priv->wm.skl_latency[level];
 	uint32_t method1, method2;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
 	uint32_t res_blocks, res_lines;
 	uint32_t selected_result;
-	uint8_t bytes_per_pixel;
+	uint8_t cpp;
+	uint32_t width = 0, height = 0;
 
-	if (latency == 0 || !cstate->base.active || !fb)
+	if (latency == 0 || !cstate->base.active || !intel_pstate->visible)
 		return false;
 
-	bytes_per_pixel = drm_format_plane_cpp(fb->pixel_format, 0);
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(plane->state->rotation))
+		swap(width, height);
+
+	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 	method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate),
-				 bytes_per_pixel,
-				 latency);
+				 cpp, latency);
 	method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate),
 				 cstate->base.adjusted_mode.crtc_htotal,
-				 cstate->pipe_src_w,
-				 bytes_per_pixel,
+				 width,
+				 cpp,
 				 fb->modifier[0],
 				 latency);
 
-	plane_bytes_per_line = cstate->pipe_src_w * bytes_per_pixel;
+	plane_bytes_per_line = width * cpp;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
@@ -3132,11 +3164,11 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		uint32_t min_scanlines = 4;
 		uint32_t y_tile_minimum;
 		if (intel_rotation_90_or_270(plane->state->rotation)) {
-			int bpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
+			int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
 				drm_format_plane_cpp(fb->pixel_format, 1) :
 				drm_format_plane_cpp(fb->pixel_format, 0);
 
-			switch (bpp) {
+			switch (cpp) {
 			case 1:
 				min_scanlines = 16;
 				break;
@@ -3625,9 +3657,11 @@ static void ilk_compute_wm_config(struct drm_device *dev,
 	}
 }
 
-static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
+static void ilk_program_watermarks(struct intel_crtc_state *cstate)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_crtc *crtc = cstate->base.crtc;
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
 	struct ilk_wm_maximums max;
 	struct intel_wm_config config = {};
@@ -3660,7 +3694,6 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
 
 static void ilk_update_wm(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
 
@@ -3680,7 +3713,7 @@ static void ilk_update_wm(struct drm_crtc *crtc)
 
 	intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk;
 
-	ilk_program_watermarks(dev_priv);
+	ilk_program_watermarks(cstate);
 }
 
 static void skl_pipe_wm_active_state(uint32_t val,
@@ -3812,6 +3845,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
 
+	memset(active, 0, sizeof(*active));
+
 	active->pipe_enabled = intel_crtc->active;
 
 	if (active->pipe_enabled) {
@@ -4066,7 +4101,7 @@ void intel_update_watermarks(struct drm_crtc *crtc)
 		dev_priv->display.update_wm(crtc);
 }
 
-/**
+/*
  * Lock protecting IPS related data structures
  */
 DEFINE_SPINLOCK(mchdev_lock);
@@ -4102,11 +4137,13 @@ bool ironlake_set_drps(struct drm_device *dev, u8 val)
 static void ironlake_enable_drps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 rgvmodectl = I915_READ(MEMMODECTL);
+	u32 rgvmodectl;
 	u8 fmax, fmin, fstart, vstart;
 
 	spin_lock_irq(&mchdev_lock);
 
+	rgvmodectl = I915_READ(MEMMODECTL);
+
 	/* Enable temp reporting */
 	I915_WRITE16(PMMISC, I915_READ(PMMISC) | MCPPCE_EN);
 	I915_WRITE16(TSC1, I915_READ(TSC1) | TSE);
@@ -4539,21 +4576,71 @@ static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
 	}
 	if (HAS_RC6p(dev))
 		DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s RC6p %s RC6pp %s\n",
-			      (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
-			      (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
-			      (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
+			      onoff(mode & GEN6_RC_CTL_RC6_ENABLE),
+			      onoff(mode & GEN6_RC_CTL_RC6p_ENABLE),
+			      onoff(mode & GEN6_RC_CTL_RC6pp_ENABLE));
 
 	else
 		DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s\n",
-			      (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off");
+			      onoff(mode & GEN6_RC_CTL_RC6_ENABLE));
+}
+
+static bool bxt_check_bios_rc6_setup(const struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool enable_rc6 = true;
+	unsigned long rc6_ctx_base;
+
+	if (!(I915_READ(RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
+		DRM_DEBUG_KMS("RC6 Base location not set properly.\n");
+		enable_rc6 = false;
+	}
+
+	/*
+	 * The exact context size is not known for BXT, so assume a page size
+	 * for this check.
+	 */
+	rc6_ctx_base = I915_READ(RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
+	if (!((rc6_ctx_base >= dev_priv->gtt.stolen_reserved_base) &&
+	      (rc6_ctx_base + PAGE_SIZE <= dev_priv->gtt.stolen_reserved_base +
+					dev_priv->gtt.stolen_reserved_size))) {
+		DRM_DEBUG_KMS("RC6 Base address not as expected.\n");
+		enable_rc6 = false;
+	}
+
+	if (!(((I915_READ(PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1) &&
+	      ((I915_READ(PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1) &&
+	      ((I915_READ(PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1) &&
+	      ((I915_READ(PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1))) {
+		DRM_DEBUG_KMS("Engine Idle wait time not set properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!(I915_READ(GEN6_RC_CONTROL) & (GEN6_RC_CTL_RC6_ENABLE |
+					    GEN6_RC_CTL_HW_ENABLE)) &&
+	    ((I915_READ(GEN6_RC_CONTROL) & GEN6_RC_CTL_HW_ENABLE) ||
+	     !(I915_READ(GEN6_RC_STATE) & RC6_STATE))) {
+		DRM_DEBUG_KMS("HW/SW RC6 is not enabled by BIOS.\n");
+		enable_rc6 = false;
+	}
+
+	return enable_rc6;
 }
 
-static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
+int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
 {
 	/* No RC6 before Ironlake and code is gone for ilk. */
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
 
+	if (!enable_rc6)
+		return 0;
+
+	if (IS_BROXTON(dev) && !bxt_check_bios_rc6_setup(dev)) {
+		DRM_INFO("RC6 disabled by BIOS\n");
+		return 0;
+	}
+
 	/* Respect the kernel parameter if it is set */
 	if (enable_rc6 >= 0) {
 		int mask;
@@ -4723,8 +4810,7 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	/* 3a: Enable RC6 */
 	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
-	DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
-			"on" : "off");
+	DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE));
 	/* WaRsUseTimeoutMode */
 	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) ||
 	    IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
@@ -4743,8 +4829,7 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	 * 3b: Enable Coarse Power Gating only when RC6 is enabled.
 	 * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6.
 	 */
-	if ((IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) ||
-	    ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_F0)))
+	if (NEEDS_WaRsDisableCoarsePowerGating(dev))
 		I915_WRITE(GEN9_PG_ENABLE, 0);
 	else
 		I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
@@ -5167,8 +5252,6 @@ static void cherryview_setup_pctx(struct drm_device *dev)
 	u32 pcbr;
 	int pctx_size = 32*1024;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	pcbr = I915_READ(VLV_PCBR);
 	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
 		DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
@@ -5190,7 +5273,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 	u32 pcbr;
 	int pctx_size = 24*1024;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	mutex_lock(&dev->struct_mutex);
 
 	pcbr = I915_READ(VLV_PCBR);
 	if (pcbr) {
@@ -5218,7 +5301,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 	pctx = i915_gem_object_create_stolen(dev, pctx_size);
 	if (!pctx) {
 		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
-		return;
+		goto out;
 	}
 
 	pctx_paddr = dev_priv->mm.stolen_base + pctx->stolen->start;
@@ -5227,6 +5310,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 out:
 	DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
 	dev_priv->vlv_pctx = pctx;
+	mutex_unlock(&dev->struct_mutex);
 }
 
 static void valleyview_cleanup_pctx(struct drm_device *dev)
@@ -5236,7 +5320,7 @@ static void valleyview_cleanup_pctx(struct drm_device *dev)
 	if (WARN_ON(!dev_priv->vlv_pctx))
 		return;
 
-	drm_gem_object_unreference(&dev_priv->vlv_pctx->base);
+	drm_gem_object_unreference_unlocked(&dev_priv->vlv_pctx->base);
 	dev_priv->vlv_pctx = NULL;
 }
 
@@ -6045,7 +6129,6 @@ void intel_init_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
 	/*
 	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
 	 * requirement.
@@ -6180,8 +6263,8 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 		return;
 
 	if (IS_IRONLAKE_M(dev)) {
-		mutex_lock(&dev->struct_mutex);
 		ironlake_enable_drps(dev);
+		mutex_lock(&dev->struct_mutex);
 		intel_init_emon(dev);
 		mutex_unlock(&dev->struct_mutex);
 	} else if (INTEL_INFO(dev)->gen >= 6) {
@@ -6565,6 +6648,12 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 	I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT);
+	/*
+	 * Wait at least 100 clocks before re-enabling clock gating. See
+	 * the definition of L3SQCREG1 in BSpec.
+	 */
+	POSTING_READ(GEN8_L3SQCREG1);
+	udelay(1);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	/*
@@ -7011,6 +7100,7 @@ void intel_init_pm(struct drm_device *dev)
 		     dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) {
 			dev_priv->display.update_wm = ilk_update_wm;
 			dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm;
+			dev_priv->display.program_watermarks = ilk_program_watermarks;
 		} else {
 			DRM_DEBUG_KMS("Failed to read display plane latency. "
 				      "Disable CxSR\n");
@@ -7176,9 +7266,10 @@ static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
 	int div, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000);
 
-	div = vlv_gpu_freq_div(czclk_freq) / 2;
+	div = vlv_gpu_freq_div(czclk_freq);
 	if (div < 0)
 		return div;
+	div /= 2;
 
 	return DIV_ROUND_CLOSEST(czclk_freq * val, 2 * div) / 2;
 }
@@ -7187,9 +7278,10 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
 	int mul, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000);
 
-	mul = vlv_gpu_freq_div(czclk_freq) / 2;
+	mul = vlv_gpu_freq_div(czclk_freq);
 	if (mul < 0)
 		return mul;
+	mul /= 2;
 
 	/* CHV needs even values */
 	return DIV_ROUND_CLOSEST(val * 2 * mul, czclk_freq) * 2;
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 9ccff3011..bd322d8fb 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -225,7 +225,12 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 		   (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT));
 	}
 
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, DP_PSR_ENABLE);
+	if (dev_priv->psr.link_standby)
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
+	else
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE);
 }
 
 static void vlv_psr_enable_source(struct intel_dp *intel_dp)
@@ -275,19 +280,61 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp)
 	 * with the 5 or 6 idle patterns.
 	 */
 	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	uint32_t val = 0x0;
+	uint32_t val = EDP_PSR_ENABLE;
+
+	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
+	val |= idle_frames << EDP_PSR_IDLE_FRAME_SHIFT;
 
 	if (IS_HASWELL(dev))
 		val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
 
-	I915_WRITE(EDP_PSR_CTL, val |
-		   max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
-		   idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
-		   EDP_PSR_ENABLE);
+	if (dev_priv->psr.link_standby)
+		val |= EDP_PSR_LINK_STANDBY;
+
+	if (dev_priv->vbt.psr.tp1_wakeup_time > 5)
+		val |= EDP_PSR_TP1_TIME_2500us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time > 1)
+		val |= EDP_PSR_TP1_TIME_500us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time > 0)
+		val |= EDP_PSR_TP1_TIME_100us;
+	else
+		val |= EDP_PSR_TP1_TIME_0us;
+
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
+		val |= EDP_PSR_TP2_TP3_TIME_2500us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
+		val |= EDP_PSR_TP2_TP3_TIME_500us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+		val |= EDP_PSR_TP2_TP3_TIME_100us;
+	else
+		val |= EDP_PSR_TP2_TP3_TIME_0us;
+
+	if (intel_dp_source_supports_hbr2(intel_dp) &&
+	    drm_dp_tps3_supported(intel_dp->dpcd))
+		val |= EDP_PSR_TP1_TP3_SEL;
+	else
+		val |= EDP_PSR_TP1_TP2_SEL;
+
+	I915_WRITE(EDP_PSR_CTL, val);
+
+	if (!dev_priv->psr.psr2_support)
+		return;
 
-	if (dev_priv->psr.psr2_support)
-		I915_WRITE(EDP_PSR2_CTL, EDP_PSR2_ENABLE |
-				EDP_SU_TRACK_ENABLE | EDP_PSR2_TP2_TIME_100);
+	/* FIXME: selective update is probably totally broken because it doesn't
+	 * mesh at all with our frontbuffer tracking. And the hw alone isn't
+	 * good enough. */
+	val = EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE;
+
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
+		val |= EDP_PSR2_TP2_TIME_2500;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
+		val |= EDP_PSR2_TP2_TIME_500;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+		val |= EDP_PSR2_TP2_TIME_100;
+	else
+		val |= EDP_PSR2_TP2_TIME_50;
+
+	I915_WRITE(EDP_PSR2_CTL, val);
 }
 
 static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
@@ -304,8 +351,15 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 
 	dev_priv->psr.source_ok = false;
 
-	if (IS_HASWELL(dev) && dig_port->port != PORT_A) {
-		DRM_DEBUG_KMS("HSW ties PSR to DDI A (eDP)\n");
+	/*
+	 * HSW spec explicitly says PSR is tied to port A.
+	 * BDW+ platforms with DDI implementation of PSR have different
+	 * PSR registers per transcoder and we only implement transcoder EDP
+	 * ones. Since by Display design transcoder EDP is tied to port A
+	 * we can safely escape based on the port A.
+	 */
+	if (HAS_DDI(dev) && dig_port->port != PORT_A) {
+		DRM_DEBUG_KMS("PSR condition failed: Port not supported\n");
 		return false;
 	}
 
@@ -314,6 +368,12 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 		return false;
 	}
 
+	if ((IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) &&
+	    !dev_priv->psr.link_standby) {
+		DRM_ERROR("PSR condition failed: Link off requested but not supported on this platform\n");
+		return false;
+	}
+
 	if (IS_HASWELL(dev) &&
 	    I915_READ(HSW_STEREO_3D_CTL(intel_crtc->config->cpu_transcoder)) &
 		      S3D_ENABLE) {
@@ -327,12 +387,6 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 		return false;
 	}
 
-	if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) &&
-	    ((dev_priv->vbt.psr.full_link) || (dig_port->port != PORT_A))) {
-		DRM_DEBUG_KMS("PSR condition failed: Link Standby requested/needed but not supported on this platform\n");
-		return false;
-	}
-
 	dev_priv->psr.source_ok = true;
 	return true;
 }
@@ -763,6 +817,36 @@ void intel_psr_init(struct drm_device *dev)
 	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
 		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
 
+	/* Per platform default */
+	if (i915.enable_psr == -1) {
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev) ||
+		    IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
+			i915.enable_psr = 1;
+		else
+			i915.enable_psr = 0;
+	}
+
+	/* Set link_standby x link_off defaults */
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		/* HSW and BDW require workarounds that we don't implement. */
+		dev_priv->psr.link_standby = false;
+	else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
+		/* On VLV and CHV only standby mode is supported. */
+		dev_priv->psr.link_standby = true;
+	else
+		/* For new platforms let's respect VBT back again */
+		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
+
+	/* Override link_standby x link_off defaults */
+	if (i915.enable_psr == 2 && !dev_priv->psr.link_standby) {
+		DRM_DEBUG_KMS("PSR: Forcing link standby\n");
+		dev_priv->psr.link_standby = true;
+	}
+	if (i915.enable_psr == 3 && dev_priv->psr.link_standby) {
+		DRM_DEBUG_KMS("PSR: Forcing main link off\n");
+		dev_priv->psr.link_standby = false;
+	}
+
 	INIT_DELAYED_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 549afa7bc..9121646d7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -746,9 +746,9 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
 
 	ret = i915_gem_render_state_init(req);
 	if (ret)
-		DRM_ERROR("init render state: %d\n", ret);
+		return ret;
 
-	return ret;
+	return 0;
 }
 
 static int wa_add(struct drm_i915_private *dev_priv,
@@ -789,6 +789,22 @@ static int wa_add(struct drm_i915_private *dev_priv,
 
 #define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val)
 
+static int wa_ring_whitelist_reg(struct intel_engine_cs *ring, i915_reg_t reg)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct i915_workarounds *wa = &dev_priv->workarounds;
+	const uint32_t index = wa->hw_whitelist_count[ring->id];
+
+	if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS))
+		return -EINVAL;
+
+	WA_WRITE(RING_FORCE_TO_NONPRIV(ring->mmio_base, index),
+		 i915_mmio_reg_offset(reg));
+	wa->hw_whitelist_count[ring->id]++;
+
+	return 0;
+}
+
 static int gen8_init_workarounds(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -894,6 +910,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
+	int ret;
 
 	/* WaEnableLbsSlaRetryTimerDecrement:skl */
 	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
@@ -964,6 +981,20 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	/* WaDisableSTUnitPowerOptimization:skl,bxt */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
+	/* WaOCLCoherentLineFlush:skl,bxt */
+	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
+				    GEN8_LQSC_FLUSH_COHERENT_LINES));
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt */
+	ret= wa_ring_whitelist_reg(ring, GEN8_CS_CHICKEN1);
+	if (ret)
+		return ret;
+
+	/* WaAllowUMDToModifyHDCChicken1:skl,bxt */
+	ret = wa_ring_whitelist_reg(ring, GEN8_HDC_CHICKEN1);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1019,6 +1050,16 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
+	/*
+	 * Actual WA is to disable percontext preemption granularity control
+	 * until D0 which is the default case so this is equivalent to
+	 * !WaDisablePerCtxtPreemptionGranularityControl:skl
+	 */
+	if (IS_SKL_REVID(dev, SKL_REVID_E0, REVID_FOREVER)) {
+		I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
+			   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
+	}
+
 	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0)) {
 		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
 		I915_WRITE(FF_SLICE_CS_CHICKEN2,
@@ -1072,6 +1113,11 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 
+	/* WaDisableLSQCROPERFforOCL:skl */
+	ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+	if (ret)
+		return ret;
+
 	return skl_tune_iz_hashing(ring);
 }
 
@@ -1107,6 +1153,20 @@ static int bxt_init_workarounds(struct intel_engine_cs *ring)
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 	}
 
+	/* WaDisableObjectLevelPreemptionForTrifanOrPolygon:bxt */
+	/* WaDisableObjectLevelPreemptionForInstancedDraw:bxt */
+	/* WaDisableObjectLevelPreemtionForInstanceId:bxt */
+	/* WaDisableLSQCROPERFforOCL:bxt */
+	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+		ret = wa_ring_whitelist_reg(ring, GEN9_CS_DEBUG_MODE1);
+		if (ret)
+			return ret;
+
+		ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -1118,6 +1178,7 @@ int init_workarounds_ring(struct intel_engine_cs *ring)
 	WARN_ON(ring->id != RCS);
 
 	dev_priv->workarounds.count = 0;
+	dev_priv->workarounds.hw_whitelist_count[RCS] = 0;
 
 	if (IS_BROADWELL(dev))
 		return bdw_init_workarounds(ring);
@@ -1868,15 +1929,13 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
 		offset = cs_offset;
 	}
 
-	ret = intel_ring_begin(req, 4);
+	ret = intel_ring_begin(req, 2);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring, MI_BATCH_BUFFER);
+	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
 	intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
 					0 : MI_BATCH_NON_SECURE));
-	intel_ring_emit(ring, offset + len - 8);
-	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
 
 	return 0;
@@ -2002,6 +2061,7 @@ void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 	else
 		iounmap(ringbuf->virtual_start);
 	ringbuf->virtual_start = NULL;
+	ringbuf->vma = NULL;
 	i915_gem_object_ggtt_unpin(ringbuf->obj);
 }
 
@@ -2063,6 +2123,9 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return ret;
 		}
 
+		/* Access through the GTT requires the device to be awake. */
+		assert_rpm_wakelock_held(dev_priv);
+
 		ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +
 						    i915_gem_obj_ggtt_offset(obj), ringbuf->size);
 		if (ringbuf->virtual_start == NULL) {
@@ -2071,6 +2134,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 		}
 	}
 
+	ringbuf->vma = i915_gem_obj_to_ggtt(obj);
+
 	return 0;
 }
 
@@ -2686,6 +2751,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 	ring->name = "render ring";
 	ring->id = RCS;
+	ring->exec_id = I915_EXEC_RENDER;
 	ring->mmio_base = RENDER_RING_BASE;
 
 	if (INTEL_INFO(dev)->gen >= 8) {
@@ -2834,6 +2900,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 
 	ring->name = "bsd ring";
 	ring->id = VCS;
+	ring->exec_id = I915_EXEC_BSD;
 
 	ring->write_tail = ring_write_tail;
 	if (INTEL_INFO(dev)->gen >= 6) {
@@ -2910,6 +2977,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev)
 
 	ring->name = "bsd2 ring";
 	ring->id = VCS2;
+	ring->exec_id = I915_EXEC_BSD;
 
 	ring->write_tail = ring_write_tail;
 	ring->mmio_base = GEN8_BSD2_RING_BASE;
@@ -2940,6 +3008,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 
 	ring->name = "blitter ring";
 	ring->id = BCS;
+	ring->exec_id = I915_EXEC_BLT;
 
 	ring->mmio_base = BLT_RING_BASE;
 	ring->write_tail = ring_write_tail;
@@ -2997,6 +3066,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 
 	ring->name = "video enhancement ring";
 	ring->id = VECS;
+	ring->exec_id = I915_EXEC_VEBOX;
 
 	ring->mmio_base = VEBOX_RING_BASE;
 	ring->write_tail = ring_write_tail;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 49574ffe5..566b0ae10 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -93,11 +93,13 @@ struct intel_ring_hangcheck {
 	int score;
 	enum intel_ring_hangcheck_action action;
 	int deadlock;
+	u32 instdone[I915_NUM_INSTDONE_REG];
 };
 
 struct intel_ringbuffer {
 	struct drm_i915_gem_object *obj;
 	void __iomem *virtual_start;
+	struct i915_vma *vma;
 
 	struct intel_engine_cs *ring;
 	struct list_head link;
@@ -147,14 +149,16 @@ struct  i915_ctx_workarounds {
 struct  intel_engine_cs {
 	const char	*name;
 	enum intel_ring_id {
-		RCS = 0x0,
-		VCS,
+		RCS = 0,
 		BCS,
-		VECS,
-		VCS2
+		VCS,
+		VCS2,	/* Keep instances of the same type engine together. */
+		VECS
 	} id;
 #define I915_NUM_RINGS 5
-#define LAST_USER_RING (VECS + 1)
+#define _VCS(n) (VCS + (n))
+	unsigned int exec_id;
+	unsigned int guc_id;
 	u32		mmio_base;
 	struct		drm_device *dev;
 	struct intel_ringbuffer *buffer;
@@ -268,6 +272,8 @@ struct  intel_engine_cs {
 	struct list_head execlist_queue;
 	struct list_head execlist_retired_req_list;
 	u8 next_context_status_buffer;
+	bool disable_lite_restore_wa;
+	u32 ctx_desc_template;
 	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
 	int		(*emit_request)(struct drm_i915_gem_request *request);
 	int		(*emit_flush)(struct drm_i915_gem_request *request,
@@ -305,7 +311,6 @@ struct  intel_engine_cs {
 
 	wait_queue_head_t irq_queue;
 
-	struct intel_context *default_context;
 	struct intel_context *last_context;
 
 	struct intel_ring_hangcheck hangcheck;
@@ -406,7 +411,7 @@ intel_write_status_page(struct intel_engine_cs *ring,
 	ring->status_page.page_addr[reg] = value;
 }
 
-/**
+/*
  * Reads a dword out of the status page, which is written to from the command
  * queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or
  * MI_STORE_DATA_IMM.
@@ -423,6 +428,7 @@ intel_write_status_page(struct intel_engine_cs *ring,
  * The area from dword 0x30 to 0x3ff is available for driver usage.
  */
 #define I915_GEM_HWS_INDEX		0x30
+#define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 #define I915_GEM_HWS_SCRATCH_INDEX	0x40
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 4f43d9b32..6e54d978d 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -284,6 +284,13 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv)
 						1 << PIPE_C | 1 << PIPE_B);
 }
 
+static void hsw_power_well_pre_disable(struct drm_i915_private *dev_priv)
+{
+	if (IS_BROADWELL(dev_priv))
+		gen8_irq_power_well_pre_disable(dev_priv,
+						1 << PIPE_C | 1 << PIPE_B);
+}
+
 static void skl_power_well_post_enable(struct drm_i915_private *dev_priv,
 				       struct i915_power_well *power_well)
 {
@@ -309,6 +316,14 @@ static void skl_power_well_post_enable(struct drm_i915_private *dev_priv,
 	}
 }
 
+static void skl_power_well_pre_disable(struct drm_i915_private *dev_priv,
+				       struct i915_power_well *power_well)
+{
+	if (power_well->data == SKL_DISP_PW_2)
+		gen8_irq_power_well_pre_disable(dev_priv,
+						1 << PIPE_C | 1 << PIPE_B);
+}
+
 static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 			       struct i915_power_well *power_well, bool enable)
 {
@@ -334,6 +349,7 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 
 	} else {
 		if (enable_requested) {
+			hsw_power_well_pre_disable(dev_priv);
 			I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
 			POSTING_READ(HSW_PWR_WELL_DRIVER);
 			DRM_DEBUG_KMS("Requesting to disable the power well\n");
@@ -456,15 +472,19 @@ static void assert_can_disable_dc9(struct drm_i915_private *dev_priv)
 	  */
 }
 
-static void gen9_set_dc_state_debugmask_memory_up(
-			struct drm_i915_private *dev_priv)
+static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv)
 {
-	uint32_t val;
+	uint32_t val, mask;
+
+	mask = DC_STATE_DEBUG_MASK_MEMORY_UP;
+
+	if (IS_BROXTON(dev_priv))
+		mask |= DC_STATE_DEBUG_MASK_CORES;
 
 	/* The below bit doesn't need to be cleared ever afterwards */
 	val = I915_READ(DC_STATE_DEBUG);
-	if (!(val & DC_STATE_DEBUG_MASK_MEMORY_UP)) {
-		val |= DC_STATE_DEBUG_MASK_MEMORY_UP;
+	if ((val & mask) != mask) {
+		val |= mask;
 		I915_WRITE(DC_STATE_DEBUG, val);
 		POSTING_READ(DC_STATE_DEBUG);
 	}
@@ -525,9 +545,6 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 	else if (i915.enable_dc == 1 && state > DC_STATE_EN_UPTO_DC5)
 		state = DC_STATE_EN_UPTO_DC5;
 
-	if (state & DC_STATE_EN_UPTO_DC5_DC6_MASK)
-		gen9_set_dc_state_debugmask_memory_up(dev_priv);
-
 	val = I915_READ(DC_STATE_EN);
 	DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n",
 		      val & mask, state);
@@ -577,7 +594,8 @@ static void assert_can_enable_dc5(struct drm_i915_private *dev_priv)
 	bool pg2_enabled = intel_display_power_well_is_enabled(dev_priv,
 					SKL_DISP_PW_2);
 
-	WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n");
+	WARN_ONCE(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev),
+		  "Platform doesn't support DC5.\n");
 	WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
 	WARN_ONCE(pg2_enabled, "PG2 not disabled to enable DC5.\n");
 
@@ -613,7 +631,8 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
 
-	WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n");
+	WARN_ONCE(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev),
+		  "Platform doesn't support DC6.\n");
 	WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
 	WARN_ONCE(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE,
 		  "Backlight is not disabled.\n");
@@ -640,7 +659,8 @@ static void gen9_disable_dc5_dc6(struct drm_i915_private *dev_priv)
 {
 	assert_can_disable_dc5(dev_priv);
 
-	if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 && i915.enable_dc != 1)
+	if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) &&
+	    i915.enable_dc != 0 && i915.enable_dc != 1)
 		assert_can_disable_dc6(dev_priv);
 
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
@@ -668,7 +688,6 @@ void skl_disable_dc6(struct drm_i915_private *dev_priv)
 static void skl_set_power_well(struct drm_i915_private *dev_priv,
 			struct i915_power_well *power_well, bool enable)
 {
-	struct drm_device *dev = dev_priv->dev;
 	uint32_t tmp, fuse_status;
 	uint32_t req_mask, state_mask;
 	bool is_enabled, enable_requested, check_fuse_status = false;
@@ -706,23 +725,15 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv,
 	state_mask = SKL_POWER_WELL_STATE(power_well->data);
 	is_enabled = tmp & state_mask;
 
+	if (!enable && enable_requested)
+		skl_power_well_pre_disable(dev_priv, power_well);
+
 	if (enable) {
 		if (!enable_requested) {
 			WARN((tmp & state_mask) &&
 				!I915_READ(HSW_PWR_WELL_BIOS),
 				"Invalid for power well status to be enabled, unless done by the BIOS, \
 				when request is to disable!\n");
-			if (power_well->data == SKL_DISP_PW_2) {
-				/*
-				 * DDI buffer programming unnecessary during
-				 * driver-load/resume as it's already done
-				 * during modeset initialization then. It's
-				 * also invalid here as encoder list is still
-				 * uninitialized.
-				 */
-				if (!dev_priv->power_domains.initializing)
-					intel_prepare_ddi(dev);
-			}
 			I915_WRITE(HSW_PWR_WELL_DRIVER, tmp | req_mask);
 		}
 
@@ -828,7 +839,8 @@ static void gen9_dc_off_power_well_enable(struct drm_i915_private *dev_priv,
 static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv,
 					   struct i915_power_well *power_well)
 {
-	if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 && i915.enable_dc != 1)
+	if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) &&
+	    i915.enable_dc != 0 && i915.enable_dc != 1)
 		skl_enable_dc6(dev_priv);
 	else
 		gen9_enable_dc5(dev_priv);
@@ -840,7 +852,8 @@ static void gen9_dc_off_power_well_sync_hw(struct drm_i915_private *dev_priv,
 	if (power_well->count > 0) {
 		gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 	} else {
-		if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 &&
+		if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) &&
+		    i915.enable_dc != 0 &&
 		    i915.enable_dc != 1)
 			gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
 		else
@@ -993,6 +1006,9 @@ static void vlv_display_power_well_deinit(struct drm_i915_private *dev_priv)
 	valleyview_disable_display_irqs(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
+	/* make sure we're done processing display irqs */
+	synchronize_irq(dev_priv->dev->irq);
+
 	vlv_power_sequencer_reset(dev_priv);
 }
 
@@ -1941,7 +1957,7 @@ void skl_pw1_misc_io_init(struct drm_i915_private *dev_priv)
 {
 	struct i915_power_well *well;
 
-	if (!IS_SKYLAKE(dev_priv))
+	if (!(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)))
 		return;
 
 	well = lookup_power_well(dev_priv, SKL_DISP_PW_1);
@@ -1955,7 +1971,7 @@ void skl_pw1_misc_io_fini(struct drm_i915_private *dev_priv)
 {
 	struct i915_power_well *well;
 
-	if (!IS_SKYLAKE(dev_priv))
+	if (!(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)))
 		return;
 
 	well = lookup_power_well(dev_priv, SKL_DISP_PW_1);
@@ -2125,8 +2141,8 @@ static void skl_display_core_init(struct drm_i915_private *dev_priv,
 
 	skl_init_cdclk(dev_priv);
 
-	if (dev_priv->csr.dmc_payload)
-		intel_csr_load_program(dev_priv);
+	if (dev_priv->csr.dmc_payload && intel_csr_load_program(dev_priv))
+		gen9_set_dc_state_debugmask(dev_priv);
 }
 
 static void skl_display_core_uninit(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 2e1da060b..4ecc076c4 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1527,6 +1527,7 @@ intel_sdvo_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
@@ -1537,6 +1538,9 @@ intel_sdvo_mode_valid(struct drm_connector *connector,
 	if (intel_sdvo->pixel_clock_max < mode->clock)
 		return MODE_CLOCK_HIGH;
 
+	if (mode->clock > max_dotclk)
+		return MODE_CLOCK_HIGH;
+
 	if (intel_sdvo->is_lvds) {
 		if (mode->hdisplay > intel_sdvo->sdvo_lvds_fixed_mode->hdisplay)
 			return MODE_PANEL;
diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h
index 2e2d4eb4a..db0ed4992 100644
--- a/drivers/gpu/drm/i915/intel_sdvo_regs.h
+++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h
@@ -24,8 +24,8 @@
  *	Eric Anholt <eric@anholt.net>
  */
 
-/**
- * @file SDVO command definitions and structures.
+/*
+ * SDVO command definitions and structures.
  */
 
 #define SDVO_OUTPUT_FIRST   (0)
@@ -66,39 +66,39 @@ struct intel_sdvo_caps {
 #define DTD_FLAG_VSYNC_POSITIVE (1 << 2)
 #define DTD_FLAG_INTERLACE	(1 << 7)
 
-/** This matches the EDID DTD structure, more or less */
+/* This matches the EDID DTD structure, more or less */
 struct intel_sdvo_dtd {
 	struct {
-		u16 clock;	/**< pixel clock, in 10kHz units */
-		u8 h_active;	/**< lower 8 bits (pixels) */
-		u8 h_blank;	/**< lower 8 bits (pixels) */
-		u8 h_high;	/**< upper 4 bits each h_active, h_blank */
-		u8 v_active;	/**< lower 8 bits (lines) */
-		u8 v_blank;	/**< lower 8 bits (lines) */
-		u8 v_high;	/**< upper 4 bits each v_active, v_blank */
+		u16 clock;	/* pixel clock, in 10kHz units */
+		u8 h_active;	/* lower 8 bits (pixels) */
+		u8 h_blank;	/* lower 8 bits (pixels) */
+		u8 h_high;	/* upper 4 bits each h_active, h_blank */
+		u8 v_active;	/* lower 8 bits (lines) */
+		u8 v_blank;	/* lower 8 bits (lines) */
+		u8 v_high;	/* upper 4 bits each v_active, v_blank */
 	} part1;
 
 	struct {
-		u8 h_sync_off;	/**< lower 8 bits, from hblank start */
-		u8 h_sync_width;	/**< lower 8 bits (pixels) */
-		/** lower 4 bits each vsync offset, vsync width */
+		u8 h_sync_off;	/* lower 8 bits, from hblank start */
+		u8 h_sync_width;	/* lower 8 bits (pixels) */
+		/* lower 4 bits each vsync offset, vsync width */
 		u8 v_sync_off_width;
-		/**
+		/*
 		* 2 high bits of hsync offset, 2 high bits of hsync width,
 		* bits 4-5 of vsync offset, and 2 high bits of vsync width.
 		*/
 		u8 sync_off_width_high;
 		u8 dtd_flags;
 		u8 sdvo_flags;
-		/** bits 6-7 of vsync offset at bits 6-7 */
+		/* bits 6-7 of vsync offset at bits 6-7 */
 		u8 v_sync_off_high;
 		u8 reserved;
 	} part2;
 } __packed;
 
 struct intel_sdvo_pixel_clock_range {
-	u16 min;	/**< pixel clock, in 10kHz units */
-	u16 max;	/**< pixel clock, in 10kHz units */
+	u16 min;	/* pixel clock, in 10kHz units */
+	u16 max;	/* pixel clock, in 10kHz units */
 } __packed;
 
 struct intel_sdvo_preferred_input_timing_args {
@@ -144,7 +144,7 @@ struct intel_sdvo_preferred_input_timing_args {
 
 #define SDVO_CMD_RESET					0x01
 
-/** Returns a struct intel_sdvo_caps */
+/* Returns a struct intel_sdvo_caps */
 #define SDVO_CMD_GET_DEVICE_CAPS			0x02
 
 #define SDVO_CMD_GET_FIRMWARE_REV			0x86
@@ -152,7 +152,7 @@ struct intel_sdvo_preferred_input_timing_args {
 # define SDVO_DEVICE_FIRMWARE_MAJOR			SDVO_I2C_RETURN_1
 # define SDVO_DEVICE_FIRMWARE_PATCH			SDVO_I2C_RETURN_2
 
-/**
+/*
  * Reports which inputs are trained (managed to sync).
  *
  * Devices must have trained within 2 vsyncs of a mode change.
@@ -164,10 +164,10 @@ struct intel_sdvo_get_trained_inputs_response {
 	unsigned int pad:6;
 } __packed;
 
-/** Returns a struct intel_sdvo_output_flags of active outputs. */
+/* Returns a struct intel_sdvo_output_flags of active outputs. */
 #define SDVO_CMD_GET_ACTIVE_OUTPUTS			0x04
 
-/**
+/*
  * Sets the current set of active outputs.
  *
  * Takes a struct intel_sdvo_output_flags.  Must be preceded by a SET_IN_OUT_MAP
@@ -175,7 +175,7 @@ struct intel_sdvo_get_trained_inputs_response {
  */
 #define SDVO_CMD_SET_ACTIVE_OUTPUTS			0x05
 
-/**
+/*
  * Returns the current mapping of SDVO inputs to outputs on the device.
  *
  * Returns two struct intel_sdvo_output_flags structures.
@@ -185,29 +185,29 @@ struct intel_sdvo_in_out_map {
 	u16 in0, in1;
 };
 
-/**
+/*
  * Sets the current mapping of SDVO inputs to outputs on the device.
  *
  * Takes two struct i380_sdvo_output_flags structures.
  */
 #define SDVO_CMD_SET_IN_OUT_MAP				0x07
 
-/**
+/*
  * Returns a struct intel_sdvo_output_flags of attached displays.
  */
 #define SDVO_CMD_GET_ATTACHED_DISPLAYS			0x0b
 
-/**
+/*
  * Returns a struct intel_sdvo_ouptut_flags of displays supporting hot plugging.
  */
 #define SDVO_CMD_GET_HOT_PLUG_SUPPORT			0x0c
 
-/**
+/*
  * Takes a struct intel_sdvo_output_flags.
  */
 #define SDVO_CMD_SET_ACTIVE_HOT_PLUG			0x0d
 
-/**
+/*
  * Returns a struct intel_sdvo_output_flags of displays with hot plug
  * interrupts enabled.
  */
@@ -221,7 +221,7 @@ struct intel_sdvo_get_interrupt_event_source_response {
 	unsigned int pad:6;
 } __packed;
 
-/**
+/*
  * Selects which input is affected by future input commands.
  *
  * Commands affected include SET_INPUT_TIMINGS_PART[12],
@@ -234,7 +234,7 @@ struct intel_sdvo_set_target_input_args {
 	unsigned int pad:7;
 } __packed;
 
-/**
+/*
  * Takes a struct intel_sdvo_output_flags of which outputs are targeted by
  * future output commands.
  *
@@ -280,7 +280,7 @@ struct intel_sdvo_set_target_input_args {
 # define SDVO_DTD_SDVO_FLAG_SCALING_SMOOTH			(2 << 4)
 # define SDVO_DTD_VSYNC_OFF_HIGH			SDVO_I2C_ARG_6
 
-/**
+/*
  * Generates a DTD based on the given width, height, and flags.
  *
  * This will be supported by any device supporting scaling or interlaced
@@ -300,24 +300,24 @@ struct intel_sdvo_set_target_input_args {
 #define SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART1	0x1b
 #define SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART2	0x1c
 
-/** Returns a struct intel_sdvo_pixel_clock_range */
+/* Returns a struct intel_sdvo_pixel_clock_range */
 #define SDVO_CMD_GET_INPUT_PIXEL_CLOCK_RANGE		0x1d
-/** Returns a struct intel_sdvo_pixel_clock_range */
+/* Returns a struct intel_sdvo_pixel_clock_range */
 #define SDVO_CMD_GET_OUTPUT_PIXEL_CLOCK_RANGE		0x1e
 
-/** Returns a byte bitfield containing SDVO_CLOCK_RATE_MULT_* flags */
+/* Returns a byte bitfield containing SDVO_CLOCK_RATE_MULT_* flags */
 #define SDVO_CMD_GET_SUPPORTED_CLOCK_RATE_MULTS		0x1f
 
-/** Returns a byte containing a SDVO_CLOCK_RATE_MULT_* flag */
+/* Returns a byte containing a SDVO_CLOCK_RATE_MULT_* flag */
 #define SDVO_CMD_GET_CLOCK_RATE_MULT			0x20
-/** Takes a byte containing a SDVO_CLOCK_RATE_MULT_* flag */
+/* Takes a byte containing a SDVO_CLOCK_RATE_MULT_* flag */
 #define SDVO_CMD_SET_CLOCK_RATE_MULT			0x21
 # define SDVO_CLOCK_RATE_MULT_1X				(1 << 0)
 # define SDVO_CLOCK_RATE_MULT_2X				(1 << 1)
 # define SDVO_CLOCK_RATE_MULT_4X				(1 << 3)
 
 #define SDVO_CMD_GET_SUPPORTED_TV_FORMATS		0x27
-/** 6 bytes of bit flags for TV formats shared by all TV format functions */
+/* 6 bytes of bit flags for TV formats shared by all TV format functions */
 struct intel_sdvo_tv_format {
 	unsigned int ntsc_m:1;
 	unsigned int ntsc_j:1;
@@ -376,7 +376,7 @@ struct intel_sdvo_tv_format {
 
 #define SDVO_CMD_SET_TV_FORMAT				0x29
 
-/** Returns the resolutiosn that can be used with the given TV format */
+/* Returns the resolutiosn that can be used with the given TV format */
 #define SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT		0x83
 struct intel_sdvo_sdtv_resolution_request {
 	unsigned int ntsc_m:1;
@@ -539,7 +539,7 @@ struct intel_sdvo_hdtv_resolution_reply {
 #define SDVO_CMD_GET_MAX_PANEL_POWER_SEQUENCING		0x2d
 #define SDVO_CMD_GET_PANEL_POWER_SEQUENCING		0x2e
 #define SDVO_CMD_SET_PANEL_POWER_SEQUENCING		0x2f
-/**
+/*
  * The panel power sequencing parameters are in units of milliseconds.
  * The high fields are bits 8:9 of the 10-bit values.
  */
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 8831fc579..c3998188c 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -129,17 +129,18 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 	return val;
 }
 
-u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg)
+u32 vlv_iosf_sb_read(struct drm_i915_private *dev_priv, u8 port, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), port,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
-void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
+void vlv_iosf_sb_write(struct drm_i915_private *dev_priv,
+		       u8 port, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), port,
 			SB_CRWRDA_NP, reg, &val);
 }
 
@@ -171,20 +172,6 @@ void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 			SB_CRWRDA_NP, reg, &val);
 }
 
-u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg)
-{
-	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
-			SB_CRRDDA_NP, reg, &val);
-	return val;
-}
-
-void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
-{
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
-			SB_CRWRDA_NP, reg, &val);
-}
-
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg)
 {
 	u32 val = 0;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 4ff7a1f41..a2582c455 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -178,28 +178,33 @@ void intel_pipe_update_end(struct intel_crtc *crtc)
 }
 
 static void
-skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t x, uint32_t y,
-		 uint32_t src_w, uint32_t src_h)
+skl_update_plane(struct drm_plane *drm_plane,
+		 const struct intel_crtc_state *crtc_state,
+		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = drm_plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(drm_plane);
+	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	const int pipe = intel_plane->pipe;
 	const int plane = intel_plane->plane + 1;
 	u32 plane_ctl, stride_div, stride;
-	const struct drm_intel_sprite_colorkey *key =
-		&to_intel_plane_state(drm_plane->state)->ckey;
+	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 surf_addr;
 	u32 tile_height, plane_offset, plane_size;
 	unsigned int rotation;
 	int x_offset, y_offset;
-	struct intel_crtc_state *crtc_state = to_intel_crtc(crtc)->config;
-	int scaler_id;
+	int crtc_x = plane_state->dst.x1;
+	int crtc_y = plane_state->dst.y1;
+	uint32_t crtc_w = drm_rect_width(&plane_state->dst);
+	uint32_t crtc_h = drm_rect_height(&plane_state->dst);
+	uint32_t x = plane_state->src.x1 >> 16;
+	uint32_t y = plane_state->src.y1 >> 16;
+	uint32_t src_w = drm_rect_width(&plane_state->src) >> 16;
+	uint32_t src_h = drm_rect_height(&plane_state->src) >> 16;
+	const struct intel_scaler *scaler =
+		&crtc_state->scaler_state.scalers[plane_state->scaler_id];
 
 	plane_ctl = PLANE_CTL_ENABLE |
 		PLANE_CTL_PIPE_GAMMA_ENABLE |
@@ -208,14 +213,12 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	plane_ctl |= skl_plane_ctl_format(fb->pixel_format);
 	plane_ctl |= skl_plane_ctl_tiling(fb->modifier[0]);
 
-	rotation = drm_plane->state->rotation;
+	rotation = plane_state->base.rotation;
 	plane_ctl |= skl_plane_ctl_rotation(rotation);
 
-	stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
+	stride_div = intel_fb_stride_alignment(dev_priv, fb->modifier[0],
 					       fb->pixel_format);
 
-	scaler_id = to_intel_plane_state(drm_plane->state)->scaler_id;
-
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
@@ -236,9 +239,10 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	surf_addr = intel_plane_obj_offset(intel_plane, obj, 0);
 
 	if (intel_rotation_90_or_270(rotation)) {
+		int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+
 		/* stride: Surface height in tiles */
-		tile_height = intel_tile_height(dev, fb->pixel_format,
-						fb->modifier[0], 0);
+		tile_height = intel_tile_height(dev_priv, fb->modifier[0], cpp);
 		stride = DIV_ROUND_UP(fb->height, tile_height);
 		plane_size = (src_w << 16) | src_h;
 		x_offset = stride * tile_height - y - (src_h + 1);
@@ -256,13 +260,13 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	I915_WRITE(PLANE_SIZE(pipe, plane), plane_size);
 
 	/* program plane scaler */
-	if (scaler_id >= 0) {
+	if (plane_state->scaler_id >= 0) {
 		uint32_t ps_ctrl = 0;
+		int scaler_id = plane_state->scaler_id;
 
 		DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n", plane,
 			PS_PLANE_SEL(plane));
-		ps_ctrl = PS_SCALER_EN | PS_PLANE_SEL(plane) |
-			crtc_state->scaler_state.scalers[scaler_id].mode;
+		ps_ctrl = PS_SCALER_EN | PS_PLANE_SEL(plane) | scaler->mode;
 		I915_WRITE(SKL_PS_CTRL(pipe, scaler_id), ps_ctrl);
 		I915_WRITE(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
 		I915_WRITE(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
@@ -334,24 +338,29 @@ chv_update_csc(struct intel_plane *intel_plane, uint32_t format)
 }
 
 static void
-vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t x, uint32_t y,
-		 uint32_t src_w, uint32_t src_h)
+vlv_update_plane(struct drm_plane *dplane,
+		 const struct intel_crtc_state *crtc_state,
+		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
+	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
 	u32 sprctl;
-	unsigned long sprsurf_offset, linear_offset;
-	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
-	const struct drm_intel_sprite_colorkey *key =
-		&to_intel_plane_state(dplane->state)->ckey;
+	u32 sprsurf_offset, linear_offset;
+	int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
+	int crtc_x = plane_state->dst.x1;
+	int crtc_y = plane_state->dst.y1;
+	uint32_t crtc_w = drm_rect_width(&plane_state->dst);
+	uint32_t crtc_h = drm_rect_height(&plane_state->dst);
+	uint32_t x = plane_state->src.x1 >> 16;
+	uint32_t y = plane_state->src.y1 >> 16;
+	uint32_t src_w = drm_rect_width(&plane_state->src) >> 16;
+	uint32_t src_h = drm_rect_height(&plane_state->src) >> 16;
 
 	sprctl = SP_ENABLE;
 
@@ -413,20 +422,18 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	crtc_w--;
 	crtc_h--;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
-	sprsurf_offset = intel_gen4_compute_page_offset(dev_priv,
-							&x, &y,
-							obj->tiling_mode,
-							pixel_size,
-							fb->pitches[0]);
+	linear_offset = y * fb->pitches[0] + x * cpp;
+	sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
+						   fb->modifier[0], cpp,
+						   fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
-	if (dplane->state->rotation == BIT(DRM_ROTATE_180)) {
+	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
 		sprctl |= SP_ROTATE_180;
 
 		x += src_w;
 		y += src_h;
-		linear_offset += src_h * fb->pitches[0] + src_w * pixel_size;
+		linear_offset += src_h * fb->pitches[0] + src_w * cpp;
 	}
 
 	if (key->flags) {
@@ -474,23 +481,28 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 }
 
 static void
-ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t x, uint32_t y,
-		 uint32_t src_w, uint32_t src_h)
+ivb_update_plane(struct drm_plane *plane,
+		 const struct intel_crtc_state *crtc_state,
+		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	enum pipe pipe = intel_plane->pipe;
 	u32 sprctl, sprscale = 0;
-	unsigned long sprsurf_offset, linear_offset;
-	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
-	const struct drm_intel_sprite_colorkey *key =
-		&to_intel_plane_state(plane->state)->ckey;
+	u32 sprsurf_offset, linear_offset;
+	int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
+	int crtc_x = plane_state->dst.x1;
+	int crtc_y = plane_state->dst.y1;
+	uint32_t crtc_w = drm_rect_width(&plane_state->dst);
+	uint32_t crtc_h = drm_rect_height(&plane_state->dst);
+	uint32_t x = plane_state->src.x1 >> 16;
+	uint32_t y = plane_state->src.y1 >> 16;
+	uint32_t src_w = drm_rect_width(&plane_state->src) >> 16;
+	uint32_t src_h = drm_rect_height(&plane_state->src) >> 16;
 
 	sprctl = SPRITE_ENABLE;
 
@@ -543,22 +555,20 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (crtc_w != src_w || crtc_h != src_h)
 		sprscale = SPRITE_SCALE_ENABLE | (src_w << 16) | src_h;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
-	sprsurf_offset =
-		intel_gen4_compute_page_offset(dev_priv,
-					       &x, &y, obj->tiling_mode,
-					       pixel_size, fb->pitches[0]);
+	linear_offset = y * fb->pitches[0] + x * cpp;
+	sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
+						   fb->modifier[0], cpp,
+						   fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
-	if (plane->state->rotation == BIT(DRM_ROTATE_180)) {
+	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
 		sprctl |= SPRITE_ROTATE_180;
 
 		/* HSW and BDW does this automagically in hardware */
 		if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
 			x += src_w;
 			y += src_h;
-			linear_offset += src_h * fb->pitches[0] +
-				src_w * pixel_size;
+			linear_offset += src_h * fb->pitches[0] + src_w * cpp;
 		}
 	}
 
@@ -612,23 +622,28 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 }
 
 static void
-ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
-		 struct drm_framebuffer *fb,
-		 int crtc_x, int crtc_y,
-		 unsigned int crtc_w, unsigned int crtc_h,
-		 uint32_t x, uint32_t y,
-		 uint32_t src_w, uint32_t src_h)
+ilk_update_plane(struct drm_plane *plane,
+		 const struct intel_crtc_state *crtc_state,
+		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int pipe = intel_plane->pipe;
-	unsigned long dvssurf_offset, linear_offset;
 	u32 dvscntr, dvsscale;
-	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
-	const struct drm_intel_sprite_colorkey *key =
-		&to_intel_plane_state(plane->state)->ckey;
+	u32 dvssurf_offset, linear_offset;
+	int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
+	int crtc_x = plane_state->dst.x1;
+	int crtc_y = plane_state->dst.y1;
+	uint32_t crtc_w = drm_rect_width(&plane_state->dst);
+	uint32_t crtc_h = drm_rect_height(&plane_state->dst);
+	uint32_t x = plane_state->src.x1 >> 16;
+	uint32_t y = plane_state->src.y1 >> 16;
+	uint32_t src_w = drm_rect_width(&plane_state->src) >> 16;
+	uint32_t src_h = drm_rect_height(&plane_state->src) >> 16;
 
 	dvscntr = DVS_ENABLE;
 
@@ -677,19 +692,18 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (crtc_w != src_w || crtc_h != src_h)
 		dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
-	dvssurf_offset =
-		intel_gen4_compute_page_offset(dev_priv,
-					       &x, &y, obj->tiling_mode,
-					       pixel_size, fb->pitches[0]);
+	linear_offset = y * fb->pitches[0] + x * cpp;
+	dvssurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
+						   fb->modifier[0], cpp,
+						   fb->pitches[0]);
 	linear_offset -= dvssurf_offset;
 
-	if (plane->state->rotation == BIT(DRM_ROTATE_180)) {
+	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
 		dvscntr |= DVS_ROTATE_180;
 
 		x += src_w;
 		y += src_h;
-		linear_offset += src_h * fb->pitches[0] + src_w * pixel_size;
+		linear_offset += src_h * fb->pitches[0] + src_w * cpp;
 	}
 
 	if (key->flags) {
@@ -754,7 +768,6 @@ intel_check_sprite_plane(struct drm_plane *plane,
 	int hscale, vscale;
 	int max_scale, min_scale;
 	bool can_scale;
-	int pixel_size;
 
 	if (!fb) {
 		state->visible = false;
@@ -876,6 +889,7 @@ intel_check_sprite_plane(struct drm_plane *plane,
 	/* Check size restrictions when scaling */
 	if (state->visible && (src_w != crtc_w || src_h != crtc_h)) {
 		unsigned int width_bytes;
+		int cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 
 		WARN_ON(!can_scale);
 
@@ -887,9 +901,7 @@ intel_check_sprite_plane(struct drm_plane *plane,
 		if (src_w < 3 || src_h < 3)
 			state->visible = false;
 
-		pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
-		width_bytes = ((src_x * pixel_size) & 63) +
-					src_w * pixel_size;
+		width_bytes = ((src_x * cpp) & 63) + src_w * cpp;
 
 		if (INTEL_INFO(dev)->gen < 9 && (src_w > 2048 || src_h > 2048 ||
 		    width_bytes > 4096 || fb->pitches[0] > 4096)) {
@@ -913,30 +925,6 @@ intel_check_sprite_plane(struct drm_plane *plane,
 	return 0;
 }
 
-static void
-intel_commit_sprite_plane(struct drm_plane *plane,
-			  struct intel_plane_state *state)
-{
-	struct drm_crtc *crtc = state->base.crtc;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
-	struct drm_framebuffer *fb = state->base.fb;
-
-	crtc = crtc ? crtc : plane->crtc;
-
-	if (state->visible) {
-		intel_plane->update_plane(plane, crtc, fb,
-					  state->dst.x1, state->dst.y1,
-					  drm_rect_width(&state->dst),
-					  drm_rect_height(&state->dst),
-					  state->src.x1 >> 16,
-					  state->src.y1 >> 16,
-					  drm_rect_width(&state->src) >> 16,
-					  drm_rect_height(&state->src) >> 16);
-	} else {
-		intel_plane->disable_plane(plane, crtc);
-	}
-}
-
 int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv)
 {
@@ -1118,7 +1106,6 @@ intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane)
 	intel_plane->plane = plane;
 	intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe, plane);
 	intel_plane->check_plane = intel_check_sprite_plane;
-	intel_plane->commit_plane = intel_commit_sprite_plane;
 	possible_crtcs = (1 << pipe);
 	ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
 				       &intel_plane_funcs,
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 948cbff6c..6745bad5b 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -897,6 +897,10 @@ intel_tv_mode_valid(struct drm_connector *connector,
 {
 	struct intel_tv *intel_tv = intel_attached_tv(connector);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+
+	if (mode->clock > max_dotclk)
+		return MODE_CLOCK_HIGH;
 
 	/* Ensure TV refresh is close to desired refresh */
 	if (tv_mode && abs(tv_mode->refresh - drm_mode_vrefresh(mode) * 1000)
@@ -1178,10 +1182,9 @@ static int
 intel_tv_detect_type(struct intel_tv *intel_tv,
 		      struct drm_connector *connector)
 {
-	struct drm_encoder *encoder = &intel_tv->base.base;
-	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_crtc *crtc = connector->state->crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 tv_ctl, save_tv_ctl;
 	u32 tv_dac, save_tv_dac;
@@ -1230,8 +1233,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	I915_WRITE(TV_DAC, tv_dac);
 	POSTING_READ(TV_DAC);
 
-	intel_wait_for_vblank(intel_tv->base.base.dev,
-			      to_intel_crtc(intel_tv->base.base.crtc)->pipe);
+	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	type = -1;
 	tv_dac = I915_READ(TV_DAC);
@@ -1261,8 +1263,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	POSTING_READ(TV_CTL);
 
 	/* For unknown reasons the hw barfs if we don't do this vblank wait. */
-	intel_wait_for_vblank(intel_tv->base.base.dev,
-			      to_intel_crtc(intel_tv->base.base.crtc)->pipe);
+	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	/* Restore interrupt config */
 	if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
@@ -1420,6 +1421,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 		if (!mode_ptr)
 			continue;
 		strncpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
+		mode_ptr->name[DRM_DISPLAY_MODE_LEN - 1] = '\0';
 
 		mode_ptr->hdisplay = hactive_s;
 		mode_ptr->hsync_start = hactive_s + 1;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 08961f7d1..68b6f69aa 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -327,13 +327,54 @@ static void intel_uncore_ellc_detect(struct drm_device *dev)
 	}
 }
 
+static bool
+fpga_check_for_unclaimed_mmio(struct drm_i915_private *dev_priv)
+{
+	u32 dbg;
+
+	dbg = __raw_i915_read32(dev_priv, FPGA_DBG);
+	if (likely(!(dbg & FPGA_DBG_RM_NOCLAIM)))
+		return false;
+
+	__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+
+	return true;
+}
+
+static bool
+vlv_check_for_unclaimed_mmio(struct drm_i915_private *dev_priv)
+{
+	u32 cer;
+
+	cer = __raw_i915_read32(dev_priv, CLAIM_ER);
+	if (likely(!(cer & (CLAIM_ER_OVERFLOW | CLAIM_ER_CTR_MASK))))
+		return false;
+
+	__raw_i915_write32(dev_priv, CLAIM_ER, CLAIM_ER_CLR);
+
+	return true;
+}
+
+static bool
+check_for_unclaimed_mmio(struct drm_i915_private *dev_priv)
+{
+	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv))
+		return fpga_check_for_unclaimed_mmio(dev_priv);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		return vlv_check_for_unclaimed_mmio(dev_priv);
+
+	return false;
+}
+
 static void __intel_uncore_early_sanitize(struct drm_device *dev,
 					  bool restore_forcewake)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (HAS_FPGA_DBG_UNCLAIMED(dev))
-		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	/* clear out unclaimed reg detection bit */
+	if (check_for_unclaimed_mmio(dev_priv))
+		DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n");
 
 	/* clear out old GT FIFO errors */
 	if (IS_GEN6(dev) || IS_GEN7(dev))
@@ -359,6 +400,8 @@ void intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake)
 
 void intel_uncore_sanitize(struct drm_device *dev)
 {
+	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
+
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
 	intel_disable_gt_powersave(dev);
 }
@@ -585,38 +628,38 @@ ilk_dummy_write(struct drm_i915_private *dev_priv)
 }
 
 static void
-hsw_unclaimed_reg_debug(struct drm_i915_private *dev_priv,
-			i915_reg_t reg, bool read, bool before)
+__unclaimed_reg_debug(struct drm_i915_private *dev_priv,
+		      const i915_reg_t reg,
+		      const bool read,
+		      const bool before)
 {
-	const char *op = read ? "reading" : "writing to";
-	const char *when = before ? "before" : "after";
-
-	if (!i915.mmio_debug)
+	/* XXX. We limit the auto arming traces for mmio
+	 * debugs on these platforms. There are just too many
+	 * revealed by these and CI/Bat suffers from the noise.
+	 * Please fix and then re-enable the automatic traces.
+	 */
+	if (i915.mmio_debug < 2 &&
+	    (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)))
 		return;
 
-	if (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM) {
-		WARN(1, "Unclaimed register detected %s %s register 0x%x\n",
-		     when, op, i915_mmio_reg_offset(reg));
-		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	if (WARN(check_for_unclaimed_mmio(dev_priv),
+		 "Unclaimed register detected %s %s register 0x%x\n",
+		 before ? "before" : "after",
+		 read ? "reading" : "writing to",
+		 i915_mmio_reg_offset(reg)))
 		i915.mmio_debug--; /* Only report the first N failures */
-	}
 }
 
-static void
-hsw_unclaimed_reg_detect(struct drm_i915_private *dev_priv)
+static inline void
+unclaimed_reg_debug(struct drm_i915_private *dev_priv,
+		    const i915_reg_t reg,
+		    const bool read,
+		    const bool before)
 {
-	static bool mmio_debug_once = true;
-
-	if (i915.mmio_debug || !mmio_debug_once)
+	if (likely(!i915.mmio_debug))
 		return;
 
-	if (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM) {
-		DRM_DEBUG("Unclaimed register detected, "
-			  "enabling oneshot unclaimed register reporting. "
-			  "Please use i915.mmio_debug=N for more information.\n");
-		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-		i915.mmio_debug = mmio_debug_once--;
-	}
+	__unclaimed_reg_debug(dev_priv, reg, read, before);
 }
 
 #define GEN2_READ_HEADER(x) \
@@ -664,9 +707,11 @@ __gen2_read(64)
 	unsigned long irqflags; \
 	u##x val = 0; \
 	assert_rpm_wakelock_held(dev_priv); \
-	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags)
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	unclaimed_reg_debug(dev_priv, reg, true, true)
 
 #define GEN6_READ_FOOTER \
+	unclaimed_reg_debug(dev_priv, reg, true, false); \
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
 	trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \
 	return val
@@ -699,11 +744,9 @@ static inline void __force_wake_get(struct drm_i915_private *dev_priv,
 static u##x \
 gen6_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
 	GEN6_READ_HEADER(x); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \
 	if (NEEDS_FORCE_WAKE(offset)) \
 		__force_wake_get(dev_priv, FORCEWAKE_RENDER); \
 	val = __raw_i915_read##x(dev_priv, reg); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \
 	GEN6_READ_FOOTER; \
 }
 
@@ -751,7 +794,6 @@ static u##x \
 gen9_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
 	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \
 	if (!SKL_NEEDS_FORCE_WAKE(offset)) \
 		fw_engine = 0; \
 	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \
@@ -765,7 +807,6 @@ gen9_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
 	if (fw_engine) \
 		__force_wake_get(dev_priv, fw_engine); \
 	val = __raw_i915_read##x(dev_priv, reg); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \
 	GEN6_READ_FOOTER; \
 }
 
@@ -864,9 +905,11 @@ __gen2_write(64)
 	unsigned long irqflags; \
 	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
 	assert_rpm_wakelock_held(dev_priv); \
-	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags)
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	unclaimed_reg_debug(dev_priv, reg, false, true)
 
 #define GEN6_WRITE_FOOTER \
+	unclaimed_reg_debug(dev_priv, reg, false, false); \
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags)
 
 #define __gen6_write(x) \
@@ -892,13 +935,10 @@ hsw_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool t
 	if (NEEDS_FORCE_WAKE(offset)) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (unlikely(__fifo_ret)) { \
 		gen6_gt_check_fifodbg(dev_priv); \
 	} \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \
-	hsw_unclaimed_reg_detect(dev_priv); \
 	GEN6_WRITE_FOOTER; \
 }
 
@@ -928,12 +968,9 @@ static bool is_gen8_shadowed(struct drm_i915_private *dev_priv,
 static void \
 gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \
 	GEN6_WRITE_HEADER; \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
 	if (NEEDS_FORCE_WAKE(offset) && !is_gen8_shadowed(dev_priv, reg)) \
 		__force_wake_get(dev_priv, FORCEWAKE_RENDER); \
 	__raw_i915_write##x(dev_priv, reg, val); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \
-	hsw_unclaimed_reg_detect(dev_priv); \
 	GEN6_WRITE_FOOTER; \
 }
 
@@ -987,7 +1024,6 @@ gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \
 		bool trace) { \
 	enum forcewake_domains fw_engine; \
 	GEN6_WRITE_HEADER; \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
 	if (!SKL_NEEDS_FORCE_WAKE(offset) || \
 	    is_gen9_shadowed(dev_priv, reg)) \
 		fw_engine = 0; \
@@ -1002,8 +1038,6 @@ gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \
 	if (fw_engine) \
 		__force_wake_get(dev_priv, fw_engine); \
 	__raw_i915_write##x(dev_priv, reg, val); \
-	hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \
-	hsw_unclaimed_reg_detect(dev_priv); \
 	GEN6_WRITE_FOOTER; \
 }
 
@@ -1227,6 +1261,8 @@ void intel_uncore_init(struct drm_device *dev)
 	intel_uncore_fw_domains_init(dev);
 	__intel_uncore_early_sanitize(dev, false);
 
+	dev_priv->uncore.unclaimed_mmio_check = 1;
+
 	switch (INTEL_INFO(dev)->gen) {
 	default:
 	case 9:
@@ -1584,13 +1620,26 @@ bool intel_has_gpu_reset(struct drm_device *dev)
 	return intel_get_gpu_reset(dev) != NULL;
 }
 
-void intel_uncore_check_errors(struct drm_device *dev)
+bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	return check_for_unclaimed_mmio(dev_priv);
+}
+
+bool
+intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv)
+{
+	if (unlikely(i915.mmio_debug ||
+		     dev_priv->uncore.unclaimed_mmio_check <= 0))
+		return false;
 
-	if (HAS_FPGA_DBG_UNCLAIMED(dev) &&
-	    (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unclaimed register before interrupt\n");
-		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	if (unlikely(intel_uncore_unclaimed_mmio(dev_priv))) {
+		DRM_DEBUG("Unclaimed register detected, "
+			  "enabling oneshot unclaimed register reporting. "
+			  "Please use i915.mmio_debug=N for more information.\n");
+		i915.mmio_debug++;
+		dev_priv->uncore.unclaimed_mmio_check--;
+		return true;
 	}
+
+	return false;
 }