Merge tag 'drm-intel-next-2016-02-14' of git://anongit.freedesktop.org/drm-intel into drm-next

- lots and lots of fbc work from Paulo
- max pixel clock checks from Mika Kahola
- prep work for nv12 offset handling from Ville
- piles of small fixes and refactorings all around

* tag 'drm-intel-next-2016-02-14' of git://anongit.freedesktop.org/drm-intel: (113 commits)
  drm/i915: Update DRIVER_DATE to 20160214
  drm/i915: edp resume/On time optimization.
  agp/intel-gtt: Only register fake agp driver for gen1
  drm/i915: TV pixel clock check
  drm/i915: CRT pixel clock check
  drm/i915: SDVO pixel clock check
  drm/i915: DisplayPort-MST pixel clock check
  drm/i915: HDMI pixel clock check
  drm/i915: DisplayPort pixel clock check
  drm/i915: check that rpm ref is held when accessing ringbuf in stolen mem
  drm/i915: fix error path in intel_setup_gmbus()
  drm/i915: Stop depending upon CONFIG_AGP_INTEL
  agp/intel-gtt: Don't leak the scratch page
  drm/i915: Capture PCI revision and subsytem details in error state
  drm/i915: fix context/engine cleanup order
  drm/i915: Handle PipeC fused off on IVB/HSW/BDW
  drm/i915/skl: Fix typo in DPLL_CFGCR1 definition
  drm/i915: Skip DDI PLL selection for DSI
  drm/i915/skl: Explicitly check for eDP in skl_ddi_pll_select()
  drm/i915/skl: Don't skip mst encoders in skl_ddi_pll_select()
  ...

46 files changed, 1568 insertions, 1093 deletions

diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 1341a94cc779..aef87fdbd187 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -555,8 +555,10 @@ static unsigned int intel_gtt_mappable_entries(void)
 static void intel_gtt_teardown_scratch_page(void)
 {
 	set_pages_wb(intel_private.scratch_page, 1);
-	pci_unmap_page(intel_private.pcidev, intel_private.scratch_page_dma,
-		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	if (intel_private.needs_dmar)
+		pci_unmap_page(intel_private.pcidev,
+			       intel_private.scratch_page_dma,
+			       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 	__free_page(intel_private.scratch_page);
 }
 
@@ -1346,16 +1348,6 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 {
 	int i, mask;
 
-	/*
-	 * Can be called from the fake agp driver but also directly from
-	 * drm/i915.ko. Hence we need to check whether everything is set up
-	 * already.
-	 */
-	if (intel_private.driver) {
-		intel_private.refcount++;
-		return 1;
-	}
-
 	for (i = 0; intel_gtt_chipsets[i].name != NULL; i++) {
 		if (gpu_pdev) {
 			if (gpu_pdev->device ==
@@ -1376,16 +1368,26 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 	if (!intel_private.driver)
 		return 0;
 
-	intel_private.refcount++;
-
 #if IS_ENABLED(CONFIG_AGP_INTEL)
 	if (bridge) {
+		if (INTEL_GTT_GEN > 1)
+			return 0;
+
 		bridge->driver = &intel_fake_agp_driver;
 		bridge->dev_private_data = &intel_private;
 		bridge->dev = bridge_pdev;
 	}
 #endif
 
+
+	/*
+	 * Can be called from the fake agp driver but also directly from
+	 * drm/i915.ko. Hence we need to check whether everything is set up
+	 * already.
+	 */
+	if (intel_private.refcount++)
+		return 1;
+
 	intel_private.bridge_dev = pci_dev_get(bridge_pdev);
 
 	dev_info(&bridge_pdev->dev, "Intel %s Chipset\n", intel_gtt_chipsets[i].name);
@@ -1430,6 +1432,8 @@ void intel_gmch_remove(void)
 	if (--intel_private.refcount)
 		return;
 
+	if (intel_private.scratch_page)
+		intel_gtt_teardown_scratch_page();
 	if (intel_private.pcidev)
 		pci_dev_put(intel_private.pcidev);
 	if (intel_private.bridge_dev)
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 051eab33e4c7..4c59793c4ccb 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
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c5db23511184..ec0c2a05eed6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2463,9 +2463,9 @@ 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);
 }
@@ -2502,10 +2502,10 @@ 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);
 
@@ -2583,6 +2583,10 @@ 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))
@@ -3221,9 +3225,11 @@ 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)
@@ -3231,15 +3237,18 @@ 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 1c3d2544fec4..2df2fac04708 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);
 
@@ -451,16 +444,15 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 cleanup_gem:
 	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_ringbuffer(dev);
 	i915_gem_context_fini(dev);
+	i915_gem_cleanup_engines(dev);
 	mutex_unlock(&dev->struct_mutex);
 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);
@@ -1196,31 +1256,21 @@ int i915_driver_unload(struct drm_device *dev)
 
 	intel_guc_ucode_fini(dev);
 	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_ringbuffer(dev);
 	i915_gem_context_fini(dev);
+	i915_gem_cleanup_engines(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;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index afb0beee9975..64cfd446453c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -59,7 +59,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20160124"
+#define DRIVER_DATE		"20160214"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -900,16 +900,15 @@ 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;
@@ -919,18 +918,52 @@ 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);
 };
 
 /**
@@ -970,6 +1003,7 @@ struct i915_psr {
 	unsigned busy_frontbuffer_bits;
 	bool psr2_support;
 	bool aux_frame_sync;
+	bool link_standby;
 };
 
 enum intel_pch {
@@ -1657,11 +1691,18 @@ 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 {
@@ -1758,7 +1799,7 @@ 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;
@@ -1993,6 +2034,9 @@ enum hdmi_force_audio {
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
+	unsigned int flags;
+#define I915_GEM_OBJECT_HAS_STRUCT_PAGE 0x1
+
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
 	 * of pages before to binding them into the GTT, and put_pages() is
@@ -2008,6 +2052,7 @@ struct drm_i915_gem_object_ops {
 	 */
 	int (*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *);
+
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };
@@ -2841,7 +2886,8 @@ 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,
@@ -3012,7 +3058,7 @@ int i915_gem_init_rings(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
 int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
-void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
+void i915_gem_cleanup_engines(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_suspend(struct drm_device *dev);
 void __i915_add_request(struct drm_i915_gem_request *req,
@@ -3254,6 +3300,7 @@ 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 */
@@ -3424,16 +3471,14 @@ 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 371bbb28c471..de57e7f0be0f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2680,7 +2680,7 @@ void i915_gem_request_free(struct kref *req_ref)
 
 	if (ctx) {
 		if (i915.enable_execlists && ctx != req->i915->kernel_context)
-			intel_lr_context_unpin(req);
+			intel_lr_context_unpin(ctx, req->ring);
 
 		i915_gem_context_unreference(ctx);
 	}
@@ -4465,6 +4465,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
 };
@@ -4912,7 +4913,7 @@ i915_gem_init_hw(struct drm_device *dev)
 		req = i915_gem_request_alloc(ring, NULL);
 		if (IS_ERR(req)) {
 			ret = PTR_ERR(req);
-			i915_gem_cleanup_ringbuffer(dev);
+			i915_gem_cleanup_engines(dev);
 			goto out;
 		}
 
@@ -4925,7 +4926,7 @@ i915_gem_init_hw(struct drm_device *dev)
 		if (ret && ret != -EIO) {
 			DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
 			i915_gem_request_cancel(req);
-			i915_gem_cleanup_ringbuffer(dev);
+			i915_gem_cleanup_engines(dev);
 			goto out;
 		}
 
@@ -4933,7 +4934,7 @@ i915_gem_init_hw(struct drm_device *dev)
 		if (ret && ret != -EIO) {
 			DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
 			i915_gem_request_cancel(req);
-			i915_gem_cleanup_ringbuffer(dev);
+			i915_gem_cleanup_engines(dev);
 			goto out;
 		}
 
@@ -5008,7 +5009,7 @@ out_unlock:
 }
 
 void
-i915_gem_cleanup_ringbuffer(struct drm_device *dev)
+i915_gem_cleanup_engines(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
@@ -5017,13 +5018,14 @@ i915_gem_cleanup_ringbuffer(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i)
 		dev_priv->gt.cleanup_ring(ring);
 
-    if (i915.enable_execlists)
-            /*
-             * Neither the BIOS, ourselves or any other kernel
-             * expects the system to be in execlists mode on startup,
-             * so we need to reset the GPU back to legacy mode.
-             */
-            intel_gpu_reset(dev);
+	if (i915.enable_execlists) {
+		/*
+		 * Neither the BIOS, ourselves or any other kernel
+		 * expects the system to be in execlists mode on startup,
+		 * so we need to reset the GPU back to legacy mode.
+		 */
+		intel_gpu_reset(dev);
+	}
 }
 
 static void
@@ -5034,7 +5036,7 @@ 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;
@@ -5100,11 +5102,18 @@ 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;
@@ -5302,7 +5311,7 @@ i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n)
 	struct page *page;
 
 	/* Only default objects have per-page dirty tracking */
-	if (WARN_ON(obj->ops != &i915_gem_object_ops))
+	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
 		return NULL;
 
 	page = i915_gem_object_get_page(obj, n);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 6a4f64b03db6..83a097c94911 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -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;
@@ -329,22 +341,15 @@ 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;
 		}
 	}
@@ -417,13 +422,6 @@ 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);
 	}
@@ -432,7 +430,7 @@ void i915_gem_context_fini(struct drm_device *dev)
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
 
 		if (ring->last_context) {
-			i915_gem_context_unreference(ring->last_context);
+			i915_gem_context_unpin(ring->last_context, ring);
 			ring->last_context = NULL;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 2dc08ce1079a..8fd00d279447 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1401,6 +1401,7 @@ eb_select_ring(struct drm_i915_private *dev_priv,
 			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",
@@ -1654,7 +1655,7 @@ 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 && req)
+	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_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7377b6725c33..9127f8f3561c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2132,6 +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;
@@ -2148,6 +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. */
@@ -2809,6 +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();
@@ -3181,6 +3204,14 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	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);
@@ -3200,6 +3231,11 @@ 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)
@@ -3333,6 +3369,7 @@ i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
 static struct scatterlist *
 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;
@@ -3344,7 +3381,7 @@ rotate_pages(const 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
@@ -3355,7 +3392,7 @@ rotate_pages(const 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;
 		}
 	}
 
@@ -3363,10 +3400,9 @@ rotate_pages(const 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;
@@ -3408,6 +3444,7 @@ 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. */
@@ -3423,6 +3460,7 @@ 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);
 	}
 
@@ -3504,7 +3542,7 @@ 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);
@@ -3598,7 +3636,7 @@ 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 e5737963ab79..66a6da2396a2 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -155,7 +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;
@@ -342,6 +342,8 @@ 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 */
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 16da9c1422cc..58c1e592bbdb 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -367,8 +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 c384dc9c8a63..ba1a00d815d3 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;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 19fb0bddc1cd..7107f2fd38f5 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;
@@ -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);
@@ -789,9 +708,10 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
-	.dmabuf_export = i915_gem_userptr_dmabuf_export,
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
+	.dmabuf_export = i915_gem_userptr_dmabuf_export,
 	.release = i915_gem_userptr_release,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 7eeb24427785..978c026963b8 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)) {
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 51ae5c1f806d..d7543efc8a5e 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -376,6 +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;
@@ -388,10 +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;
 
@@ -406,7 +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;
 
@@ -414,16 +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);
@@ -510,7 +509,6 @@ int i915_guc_wq_check_space(struct i915_guc_client *gc)
 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, space;
@@ -544,7 +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 */
@@ -560,29 +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
@@ -594,18 +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;
@@ -615,8 +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;
 }
@@ -848,7 +819,7 @@ static void init_guc_policies(struct guc_policies *policies)
 	policies->max_num_work_items = POLICY_MAX_NUM_WI;
 
 	for (p = 0; p < GUC_CTX_PRIORITY_NUM; p++) {
-		for (i = 0; i < I915_NUM_RINGS; i++) {
+		for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
 			policy = &policies->policy[p][i];
 
 			policy->execution_quantum = 1000000;
@@ -900,7 +871,7 @@ static void guc_create_ads(struct intel_guc *guc)
 	ads->golden_context_lrca = ring->status_page.gfx_addr;
 
 	for_each_ring(ring, dev_priv, i)
-		ads->eng_state_size[i] = intel_lr_context_size(ring);
+		ads->eng_state_size[ring->guc_id] = intel_lr_context_size(ring);
 
 	/* GuC scheduling policies */
 	policies = (void *)ads + sizeof(struct guc_ads);
@@ -912,12 +883,12 @@ static void guc_create_ads(struct intel_guc *guc)
 	/* MMIO reg state */
 	reg_state = (void *)policies + sizeof(struct guc_policies);
 
-	for (i = 0; i < I915_NUM_RINGS; i++) {
-		reg_state->mmio_white_list[i].mmio_start =
-			dev_priv->ring[i].mmio_base + GUC_MMIO_WHITE_LIST_START;
+	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[i].count = 0;
+		reg_state->mmio_white_list[ring->guc_id].count = 0;
 	}
 
 	ads->reg_state_addr = ads->scheduler_policies +
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 8d90c256520a..8b9f36814165 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -127,7 +127,8 @@ 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 [default], 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode)");
 
 module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, int, 0600);
 MODULE_PARM_DESC(preliminary_hw_support,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0a988895165f..144586ee74d5 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
@@ -5945,6 +5949,7 @@ 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)
@@ -5991,10 +5996,19 @@ 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))
@@ -6040,6 +6054,8 @@ 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)
@@ -6770,6 +6786,16 @@ 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)
@@ -6908,6 +6934,7 @@ 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)
@@ -7519,7 +7546,7 @@ enum skl_disp_power_wells {
 #define  DPLL_CFGCR2_PDIV_7 (4<<2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
-#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR2)
+#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
 #define DPLL_CFGCR2(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR2, _DPLL2_CFGCR2)
 
 /* BXT display engine PLL */
@@ -8159,4 +8186,11 @@ 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 a2aa09ce3202..34e061a9ef06 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -49,7 +49,7 @@ static void i915_save_display(struct drm_device *dev)
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PCH_PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PCH_PP_OFF_DELAYS);
 		dev_priv->regfile.savePP_DIVISOR = I915_READ(PCH_PP_DIVISOR);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PP_CONTROL);
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PP_OFF_DELAYS);
@@ -84,7 +84,7 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(PCH_PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PCH_PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
 		I915_WRITE(PCH_PP_CONTROL, dev_priv->regfile.savePP_CONTROL);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		I915_WRITE(PP_ON_DELAYS, dev_priv->regfile.savePP_ON_DELAYS);
 		I915_WRITE(PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
@@ -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/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 9c89df1af036..ad5dfabc452e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -216,6 +216,7 @@ 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)
@@ -231,6 +232,9 @@ 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))
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 5c2f9a40c81b..2a7ec3141c8d 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -179,7 +179,8 @@ static const struct stepping_info kbl_stepping_info[] = {
 static const struct stepping_info skl_stepping_info[] = {
 	{'A', '0'}, {'B', '0'}, {'C', '0'},
 	{'D', '0'}, {'E', '0'}, {'F', '0'},
-	{'G', '0'}, {'H', '0'}, {'I', '0'}
+	{'G', '0'}, {'H', '0'}, {'I', '0'},
+	{'J', '0'}, {'K', '0'}
 };
 
 static const struct stepping_info bxt_stepping_info[] = {
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 1f9a3687b540..cdf2e14aa45d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1531,7 +1531,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc,
 			 DPLL_CFGCR2_KDIV(wrpll_params.kdiv) |
 			 DPLL_CFGCR2_PDIV(wrpll_params.pdiv) |
 			 wrpll_params.central_freq;
-	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) {
+	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+		   intel_encoder->type == INTEL_OUTPUT_DP_MST) {
 		switch (crtc_state->port_clock / 2) {
 		case 81000:
 			ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0);
@@ -1545,8 +1546,10 @@ 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));
@@ -3281,7 +3284,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
 					  (DDI_BUF_PORT_REVERSAL |
 					   DDI_A_4_LANES);
-	intel_dig_port->max_lanes = max_lanes;
 
 	/*
 	 * Bspec says that DDI_A_4_LANES is the only supported configuration
@@ -3294,9 +3296,12 @@ 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 e1e7cdee3bbd..836bbdc239b6 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2284,7 +2284,7 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb,
 			const struct drm_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
-	struct intel_rotation_info *info = &view->params.rotation_info;
+	struct intel_rotation_info *info = &view->params.rotated;
 	unsigned int tile_size, tile_width, tile_height, cpp;
 
 	*view = i915_ggtt_view_normal;
@@ -2306,7 +2306,7 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb,
 	tile_size = intel_tile_size(dev_priv);
 
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
-	tile_width = intel_tile_width(dev_priv, cpp, fb->modifier[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);
@@ -2448,11 +2448,11 @@ 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_compute_tile_offset(struct drm_i915_private *dev_priv,
-					int *x, int *y,
-					uint64_t fb_modifier,
-					unsigned int cpp,
-					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)
 {
 	if (fb_modifier != DRM_FORMAT_MOD_NONE) {
 		unsigned int tile_size, tile_width, tile_height;
@@ -2706,14 +2706,12 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 	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;
-	int x = plane_state->src.x1 >> 16;
-	int y = plane_state->src.y1 >> 16;
+	u32 linear_offset;
 	u32 dspcntr;
 	i915_reg_t reg = DSPCNTR(plane);
-	int pixel_size;
-
-	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;
 
@@ -2771,13 +2769,12 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 	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_compute_tile_offset(dev_priv, &x, &y,
-						  fb->modifier[0],
-						  pixel_size,
+						  fb->modifier[0], cpp,
 						  fb->pitches[0]);
 		linear_offset -= intel_crtc->dspaddr_offset;
 	} else {
@@ -2794,7 +2791,7 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 		data and adding to linear_offset*/
 		linear_offset +=
 			(crtc_state->pipe_src_h - 1) * fb->pitches[0] +
-			(crtc_state->pipe_src_w - 1) * pixel_size;
+			(crtc_state->pipe_src_w - 1) * cpp;
 	}
 
 	intel_crtc->adjusted_x = x;
@@ -2839,10 +2836,10 @@ static void ironlake_update_primary_plane(struct drm_plane *primary,
 	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 = 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;
 
@@ -2881,11 +2878,10 @@ static void ironlake_update_primary_plane(struct drm_plane *primary,
 	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_compute_tile_offset(dev_priv, &x, &y,
-					  fb->modifier[0],
-					  pixel_size,
+					  fb->modifier[0], cpp,
 					  fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
 	if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) {
@@ -2899,7 +2895,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary,
 			data and adding to linear_offset*/
 			linear_offset +=
 				(crtc_state->pipe_src_h - 1) * fb->pitches[0] +
-				(crtc_state->pipe_src_w - 1) * pixel_size;
+				(crtc_state->pipe_src_w - 1) * cpp;
 		}
 	}
 
@@ -2951,7 +2947,7 @@ 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;
 	}
 
@@ -3160,9 +3156,6 @@ static void skylake_disable_primary_plane(struct drm_plane *primary,
 	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));
@@ -4803,7 +4796,7 @@ static void intel_post_plane_update(struct intel_crtc *crtc)
 		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);
@@ -4811,26 +4804,39 @@ 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)
@@ -4931,8 +4937,6 @@ 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. */
@@ -5045,8 +5049,6 @@ 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)
@@ -5127,8 +5129,6 @@ 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)
@@ -5179,8 +5179,6 @@ 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)
@@ -6291,8 +6289,6 @@ 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)
@@ -6355,8 +6351,6 @@ 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)
@@ -6380,6 +6374,7 @@ 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);
 
@@ -9853,8 +9848,13 @@ 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;
 
@@ -10914,6 +10914,7 @@ 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);
@@ -11629,6 +11630,7 @@ 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;
 
@@ -11713,7 +11715,6 @@ 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);
 
@@ -11724,7 +11725,7 @@ 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);
@@ -11835,7 +11836,6 @@ 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;
@@ -11901,39 +11901,8 @@ 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;
-
-		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;
+		intel_crtc->atomic.update_fbc = true;
 
 		/*
 		 * BDW signals flip done immediately if the plane
@@ -11943,7 +11912,6 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 		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;
@@ -13348,6 +13316,7 @@ 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;
@@ -13390,7 +13359,7 @@ 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;
@@ -13416,12 +13385,13 @@ 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;
@@ -13542,12 +13512,13 @@ static int intel_atomic_commit(struct drm_device *dev,
 		if (!needs_modeset(crtc->state))
 			continue;
 
-		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);
 
 			/*
@@ -13597,7 +13568,10 @@ static int intel_atomic_commit(struct drm_device *dev,
 		}
 
 		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))
@@ -14682,10 +14656,12 @@ 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) {
@@ -15934,6 +15910,8 @@ intel_modeset_setup_hw_state(struct drm_device *dev)
 			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)
@@ -16063,7 +16041,7 @@ 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();
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index da704c6ee5cb..23599c36503f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -203,6 +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)
@@ -220,7 +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)
@@ -979,7 +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) {
@@ -1798,12 +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);
 }
@@ -1955,7 +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);
@@ -2104,7 +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. */
@@ -3995,7 +4008,7 @@ 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;
 	}
 
@@ -5102,7 +5115,7 @@ 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;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 88887938e0bf..0b8eefc2acc5 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -215,27 +215,46 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 	}
 }
 
-static void
-intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+/*
+ * Pick training pattern for channel equalization. Training Pattern 3 for HBR2
+ * or 1.2 devices that support it, Training Pattern 2 otherwise.
+ */
+static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 {
-	bool channel_eq = false;
-	int tries, cr_tries;
-	uint32_t training_pattern = DP_TRAINING_PATTERN_2;
+	u32 training_pattern = DP_TRAINING_PATTERN_2;
+	bool source_tps3, sink_tps3;
 
 	/*
-	 * Training Pattern 3 for HBR2 or 1.2 devices that support it.
-	 *
 	 * Intel platforms that support HBR2 also support TPS3. TPS3 support is
-	 * also mandatory for downstream devices that support HBR2.
+	 * also mandatory for downstream devices that support HBR2. However, not
+	 * all sinks follow the spec.
 	 *
 	 * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is
-	 * supported but still not enabled.
+	 * supported in source but still not enabled.
 	 */
-	if (intel_dp_source_supports_hbr2(intel_dp) &&
-	    drm_dp_tps3_supported(intel_dp->dpcd))
+	source_tps3 = intel_dp_source_supports_hbr2(intel_dp);
+	sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd);
+
+	if (source_tps3 && sink_tps3) {
 		training_pattern = DP_TRAINING_PATTERN_3;
-	else if (intel_dp->link_rate == 540000)
-		DRM_ERROR("5.4 Gbps link rate without HBR2/TPS3 support\n");
+	} else if (intel_dp->link_rate == 540000) {
+		if (!source_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without source HBR2/TPS3 support\n");
+		if (!sink_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without sink TPS3 support\n");
+	}
+
+	return training_pattern;
+}
+
+static void
+intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+{
+	bool channel_eq = false;
+	int tries, cr_tries;
+	u32 training_pattern;
+
+	training_pattern = intel_dp_training_pattern(intel_dp);
 
 	/* channel equalization */
 	if (!intel_dp_set_link_train(intel_dp,
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 2a2ab306ad84..a2bd698fe2f7 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -371,6 +371,8 @@ 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;
@@ -378,6 +380,9 @@ 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 bf6f98134b50..3cae3768ea37 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -492,6 +492,8 @@ struct intel_crtc_state {
 
 	bool ips_enabled;
 
+	bool enable_fbc;
+
 	bool double_wide;
 
 	bool dp_encoder_is_mst;
@@ -542,16 +544,15 @@ 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 {
@@ -575,7 +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;
 
@@ -770,9 +771,9 @@ 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;
 
@@ -1172,11 +1173,11 @@ 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_compute_tile_offset(struct drm_i915_private *dev_priv,
-					int *x, int *y,
-					uint64_t fb_modifier,
-					unsigned int cpp,
-					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);
@@ -1327,13 +1328,16 @@ 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);
@@ -1559,6 +1563,7 @@ 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 91cef3525c93..378f879f4015 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)
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index 1d43e6f37fc1..787f01c63984 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -204,10 +204,28 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	struct drm_device *dev = intel_dsi->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	if (dev_priv->vbt.dsi.seq_version >= 3)
+		data++;
+
 	gpio = *data++;
 
 	/* pull up/down */
-	action = *data++;
+	action = *data++ & 1;
+
+	if (gpio >= ARRAY_SIZE(gtable)) {
+		DRM_DEBUG_KMS("unknown gpio %u\n", gpio);
+		goto out;
+	}
+
+	if (!IS_VALLEYVIEW(dev_priv)) {
+		DRM_DEBUG_KMS("GPIO element not supported on this platform\n");
+		goto out;
+	}
+
+	if (dev_priv->vbt.dsi.seq_version >= 3) {
+		DRM_DEBUG_KMS("GPIO element v3 not supported\n");
+		goto out;
+	}
 
 	function = gtable[gpio].function_reg;
 	pad = gtable[gpio].pad_reg;
@@ -216,16 +234,18 @@ 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;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index a1988a486b92..3614a951736b 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(&dev_priv->fbc.lock));
+	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	/* 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;
+	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() 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));
+	struct intel_fbc *fbc = &dev_priv->fbc;
 
-	intel_fbc_cancel_work(dev_priv);
+	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	if (dev_priv->fbc.active)
-		dev_priv->fbc.deactivate(dev_priv);
-}
+	/* 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;
 
-/*
- * 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;
-
-	mutex_lock(&dev_priv->fbc.lock);
-	if (dev_priv->fbc.crtc == crtc)
-		__intel_fbc_deactivate(dev_priv);
-	mutex_unlock(&dev_priv->fbc.lock);
+	if (fbc->active)
+		intel_fbc_hw_deactivate(dev_priv);
 }
 
-static void set_no_fbc_reason(struct drm_i915_private *dev_priv,
-			      const char *reason)
-{
-	if (dev_priv->fbc.no_fbc_reason == reason)
-		return;
-
-	dev_priv->fbc.no_fbc_reason = reason;
-	DRM_DEBUG_KMS("Disabling FBC: %s\n", reason);
-}
-
-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 +810,320 @@ 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;
+
+	if (intel_vgpu_active(dev_priv->dev)) {
+		fbc->no_fbc_reason = "VGPU is active";
+		return false;
+	}
+
+	if (i915.enable_fbc < 0) {
+		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;
 
-	mutex_unlock(&dev_priv->fbc.lock);
+		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;
+		}
+	}
+
+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);
+	mutex_lock(&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);
-
-	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 +1135,88 @@ 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 +1227,35 @@ 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_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 045b1491ff7a..73002e901ff2 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -46,7 +46,7 @@ struct i915_guc_client {
 	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;
@@ -106,8 +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 */
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 1856a4740b83..2de57ffe5e18 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -44,6 +44,13 @@
 #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
@@ -285,7 +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;
 
@@ -344,7 +351,7 @@ struct guc_policy {
 } __packed;
 
 struct guc_policies {
-	struct guc_policy policy[GUC_CTX_PRIORITY_NUM][I915_NUM_RINGS];
+	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).
@@ -388,14 +395,14 @@ struct guc_mmio_regset {
 
 struct guc_mmio_reg_state {
 	struct guc_mmio_regset global_reg;
-	struct guc_mmio_regset engine_reg[I915_NUM_RINGS];
+	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[I915_NUM_RINGS];
+	} mmio_white_list[GUC_MAX_ENGINES_NUM];
 } __packed;
 
 /* GuC Additional Data Struct */
@@ -406,7 +413,7 @@ struct guc_ads {
 	u32 golden_context_lrca;
 	u32 scheduler_policies;
 	u32 reserved0[3];
-	u32 eng_state_size[I915_NUM_RINGS];
+	u32 eng_state_size[GUC_MAX_ENGINES_NUM];
 	u32 reserved2[4];
 } __packed;
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 8698a643d027..edb7e901ba4a 100755..100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1202,11 +1202,19 @@ 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;
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 25254b5c1ac5..deb8282c26d8 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -683,7 +683,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 	return 0;
 
 err:
-	while (--pin) {
+	while (pin--) {
 		if (!intel_gmbus_is_valid_pin(dev_priv, pin))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 73d4347429df..3a03646e343d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -225,7 +225,8 @@ enum {
 #define GEN8_CTX_ID_SHIFT 32
 #define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT  0x17
 
-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);
 
@@ -393,7 +394,6 @@ static int execlists_update_context(struct drm_i915_gem_request *rq)
 	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] = rq->ringbuf->vma->node.start;
 
 	if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
 		/* True 32b PPGTT with dynamic page allocation: update PDP
@@ -599,7 +599,7 @@ static int execlists_context_queue(struct drm_i915_gem_request *request)
 	int num_elements = 0;
 
 	if (request->ctx != request->i915->kernel_context)
-		intel_lr_context_pin(request);
+		intel_lr_context_pin(request->ctx, ring);
 
 	i915_gem_request_reference(request);
 
@@ -704,7 +704,7 @@ int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request
 	}
 
 	if (request->ctx != request->i915->kernel_context)
-		ret = intel_lr_context_pin(request);
+		ret = intel_lr_context_pin(request->ctx, request->ring);
 
 	return ret;
 }
@@ -765,6 +765,7 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 {
 	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;
@@ -779,9 +780,20 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	intel_logical_ring_advance(ringbuf);
 
-	if (intel_ring_stopped(request->ring))
+	if (intel_ring_stopped(engine))
 		return 0;
 
+	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
@@ -1015,7 +1027,8 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 				ctx->engine[ring->id].state;
 
 		if (ctx_obj && (ctx != req->i915->kernel_context))
-			intel_lr_context_unpin(req);
+			intel_lr_context_unpin(ctx, ring);
+
 		list_del(&req->execlist_link);
 		i915_gem_request_unreference(req);
 	}
@@ -1059,14 +1072,15 @@ 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 intel_context *ctx)
+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;
 	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));
@@ -1088,7 +1102,9 @@ static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
 
 	ctx->engine[ring->id].lrc_vma = i915_gem_obj_to_ggtt(ctx_obj);
 	intel_lr_context_descriptor_update(ctx, ring);
-	ctx->engine[ring->id].lrc_reg_state = kmap(lrc_state_page);
+	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. */
@@ -1103,41 +1119,44 @@ 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;
 
-	if (rq->ctx->engine[ring->id].pin_count++ == 0) {
-		ret = intel_lr_context_do_pin(ring, rq->ctx);
+	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;
 
-	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+	WARN_ON(!mutex_is_locked(&ctx->i915->dev->struct_mutex));
 
-	if (!ctx_obj)
+	if (WARN_ON_ONCE(!ctx_obj))
 		return;
 
-	if (--rq->ctx->engine[ring->id].pin_count == 0) {
-		kunmap(kmap_to_page(rq->ctx->engine[ring->id].lrc_reg_state));
-		intel_unpin_ringbuffer_obj(ringbuf);
+	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);
-		rq->ctx->engine[ring->id].lrc_vma = NULL;
-		rq->ctx->engine[ring->id].lrc_desc = 0;
-		rq->ctx->engine[ring->id].lrc_reg_state = NULL;
+		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);
 	}
 }
 
@@ -2062,7 +2081,7 @@ logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
 		goto error;
 
 	/* As this is the default context, always pin it */
-	ret = intel_lr_context_do_pin(ring, dctx);
+	ret = intel_lr_context_do_pin(dctx, ring);
 	if (ret) {
 		DRM_ERROR(
 			"Failed to pin and map ringbuffer %s: %d\n",
@@ -2086,6 +2105,7 @@ 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;
 
 	logical_ring_default_irqs(ring, GEN8_RCS_IRQ_SHIFT);
@@ -2137,6 +2157,7 @@ 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;
 
 	logical_ring_default_irqs(ring, GEN8_VCS1_IRQ_SHIFT);
@@ -2153,6 +2174,7 @@ static int logical_bsd2_ring_init(struct drm_device *dev)
 	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;
 
 	logical_ring_default_irqs(ring, GEN8_VCS2_IRQ_SHIFT);
@@ -2169,6 +2191,7 @@ 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;
 
 	logical_ring_default_irqs(ring, GEN8_BCS_IRQ_SHIFT);
@@ -2185,6 +2208,7 @@ 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;
 
 	logical_ring_default_irqs(ring, GEN8_VECS_IRQ_SHIFT);
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 49af638f6213..e6cda3e225d0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -101,7 +101,8 @@ 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,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 20bf854eae8c..379eabe093cb 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -548,7 +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
@@ -564,8 +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;
@@ -576,7 +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);
 
@@ -640,13 +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);
@@ -656,7 +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);
@@ -665,7 +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);
@@ -674,7 +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);
@@ -698,7 +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;
 
@@ -713,10 +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;
@@ -728,7 +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;
@@ -784,7 +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;
@@ -800,21 +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;
 
@@ -906,13 +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;
@@ -941,7 +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;
@@ -949,7 +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;
@@ -965,7 +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);
 	}
 
@@ -1439,7 +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;
 
@@ -1447,7 +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)
@@ -1457,7 +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 -
@@ -1518,7 +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;
 
@@ -1540,7 +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;
 
@@ -1586,7 +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;
 
@@ -1594,7 +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;
@@ -1685,15 +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;
@@ -1701,7 +1699,7 @@ 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;
@@ -1712,13 +1710,13 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t 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)
 {
 	/*
 	 * Neither of these should be possible since this function shouldn't be
@@ -1726,12 +1724,12 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 	 * extra paranoid to avoid a potential divide-by-zero if we screw up
 	 * elsewhere in the driver.
 	 */
-	if (WARN_ON(!bytes_per_pixel))
+	if (WARN_ON(!cpp))
 		return 0;
 	if (WARN_ON(!horiz_pixels))
 		return 0;
 
-	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
+	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * cpp) + 2;
 }
 
 struct ilk_wm_maximums {
@@ -1750,13 +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;
@@ -1764,8 +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);
 }
@@ -1778,18 +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);
 }
 
@@ -1801,16 +1799,20 @@ static uint32_t ilk_compute_cur_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;
+	/*
+	 * We treat the cursor plane as always-on for the purposes of watermark
+	 * calculation.  Until we have two-stage watermark programming merged,
+	 * this is necessary to avoid flickering.
+	 */
+	int cpp = 4;
+	int width = pstate->visible ? pstate->base.crtc_w : 64;
 
-	if (!cstate->base.active || !pstate->visible)
+	if (!cstate->base.active)
 		return 0;
 
 	return ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 			      cstate->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&pstate->dst),
-			      bpp,
-			      mem_value);
+			      width, cpp, mem_value);
 }
 
 /* Only for WM_LP. */
@@ -1818,12 +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)
@@ -3042,26 +3045,25 @@ 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;
@@ -3071,7 +3073,7 @@ 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) {
@@ -3121,23 +3123,21 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	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;
 
 	if (latency == 0 || !cstate->base.active || !fb)
 		return false;
 
-	bytes_per_pixel = drm_format_plane_cpp(fb->pixel_format, 0);
+	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,
-				 fb->modifier[0],
+				 cpp, fb->modifier[0],
 				 latency);
 
-	plane_bytes_per_line = cstate->pipe_src_w * bytes_per_pixel;
+	plane_bytes_per_line = cstate->pipe_src_w * cpp;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
@@ -3145,11 +3145,11 @@ 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;
@@ -4562,12 +4562,62 @@ static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
 			      onoff(mode & GEN6_RC_CTL_RC6_ENABLE));
 }
 
-static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
+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;
+}
+
+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;
@@ -6057,7 +6107,6 @@ 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.
@@ -7189,9 +7238,10 @@ 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;
 }
@@ -7200,9 +7250,10 @@ 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 9ccff3011523..4ab757947f15 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)
@@ -280,6 +285,9 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp)
 	if (IS_HASWELL(dev))
 		val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
 
+	if (dev_priv->psr.link_standby)
+		val |= EDP_PSR_LINK_STANDBY;
+
 	I915_WRITE(EDP_PSR_CTL, val |
 		   max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
 		   idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
@@ -304,8 +312,15 @@ 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 +329,12 @@ 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 +348,6 @@ 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 +778,27 @@ 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;
 
+	/* 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 9030e2bca0c0..133321a5b3d0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -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,
@@ -1071,6 +1112,11 @@ 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);
 }
 
@@ -1106,6 +1152,20 @@ 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;
 }
 
@@ -1117,6 +1177,7 @@ 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);
@@ -2058,6 +2119,9 @@ 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) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b12f2aabd104..566b0ae10ce0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -158,6 +158,7 @@ struct  intel_engine_cs {
 #define I915_NUM_RINGS 5
 #define _VCS(n) (VCS + (n))
 	unsigned int exec_id;
+	unsigned int guc_id;
 	u32		mmio_base;
 	struct		drm_device *dev;
 	struct intel_ringbuffer *buffer;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 2e1da060b0e1..4ecc076c4041 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_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 8831fc579ade..c3998188cf35 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 0875c8e0ec0a..a2582c455b36 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -350,8 +350,8 @@ vlv_update_plane(struct drm_plane *dplane,
 	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);
+	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;
@@ -422,10 +422,9 @@ vlv_update_plane(struct drm_plane *dplane,
 	crtc_w--;
 	crtc_h--;
 
-	linear_offset = y * fb->pitches[0] + x * pixel_size;
+	linear_offset = y * fb->pitches[0] + x * cpp;
 	sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
-						   fb->modifier[0],
-						   pixel_size,
+						   fb->modifier[0], cpp,
 						   fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
@@ -434,7 +433,7 @@ vlv_update_plane(struct drm_plane *dplane,
 
 		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) {
@@ -493,8 +492,8 @@ ivb_update_plane(struct drm_plane *plane,
 	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);
+	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;
@@ -556,10 +555,9 @@ ivb_update_plane(struct drm_plane *plane,
 	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;
+	linear_offset = y * fb->pitches[0] + x * cpp;
 	sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
-						   fb->modifier[0],
-						   pixel_size,
+						   fb->modifier[0], cpp,
 						   fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
@@ -570,8 +568,7 @@ ivb_update_plane(struct drm_plane *plane,
 		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;
 		}
 	}
 
@@ -635,9 +632,9 @@ ilk_update_plane(struct drm_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);
+	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;
@@ -695,10 +692,9 @@ ilk_update_plane(struct drm_plane *plane,
 	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;
+	linear_offset = y * fb->pitches[0] + x * cpp;
 	dvssurf_offset = intel_compute_tile_offset(dev_priv, &x, &y,
-						   fb->modifier[0],
-						   pixel_size,
+						   fb->modifier[0], cpp,
 						   fb->pitches[0]);
 	linear_offset -= dvssurf_offset;
 
@@ -707,7 +703,7 @@ ilk_update_plane(struct drm_plane *plane,
 
 		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) {
@@ -772,7 +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;
@@ -894,6 +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);
 
@@ -905,9 +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)) {
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 948cbff6c62e..d21f75bda96e 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)
@@ -1420,6 +1424,7 @@ 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 bfa79e5c214e..436d8f2b8682 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -400,6 +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);
 }
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index f97020904717..9094599a1150 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -277,7 +277,9 @@
 	INTEL_VGA_DEVICE(0x191D, info)  /* WKS GT2 */
 
 #define INTEL_SKL_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x1923, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \
+	INTEL_VGA_DEVICE(0x1927, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \
 	INTEL_VGA_DEVICE(0x192A, info)  /* SRV GT3 */
 
@@ -296,7 +298,9 @@
 #define INTEL_BXT_IDS(info) \
 	INTEL_VGA_DEVICE(0x0A84, info), \
 	INTEL_VGA_DEVICE(0x1A84, info), \
-	INTEL_VGA_DEVICE(0x5A84, info)
+	INTEL_VGA_DEVICE(0x1A85, info), \
+	INTEL_VGA_DEVICE(0x5A84, info), /* APL HD Graphics 505 */ \
+	INTEL_VGA_DEVICE(0x5A85, info)  /* APL HD Graphics 500 */
 
 #define INTEL_KBL_GT1_IDS(info)	\
 	INTEL_VGA_DEVICE(0x5913, info), /* ULT GT1.5 */ \
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 6a19371391fa..a5524cc95ff8 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -772,10 +772,12 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_HANDLE_LUT		(1<<12)
 
 /** Used for switching BSD rings on the platforms with two BSD rings */
-#define I915_EXEC_BSD_MASK		(3<<13)
-#define I915_EXEC_BSD_DEFAULT		(0<<13) /* default ping-pong mode */
-#define I915_EXEC_BSD_RING1		(1<<13)
-#define I915_EXEC_BSD_RING2		(2<<13)
+#define I915_EXEC_BSD_SHIFT	 (13)
+#define I915_EXEC_BSD_MASK	 (3 << I915_EXEC_BSD_SHIFT)
+/* default ping-pong mode */
+#define I915_EXEC_BSD_DEFAULT	 (0 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING1	 (1 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING2	 (2 << I915_EXEC_BSD_SHIFT)
 
 /** Tell the kernel that the batchbuffer is processed by
  *  the resource streamer.