Merge airlied/drm-next into drm-misc-next

Backmerge 4.15 and hdcp topic branch

Signed-off-by: Sean Paul <seanpaul@chromium.org>

196 files changed, 8234 insertions, 3289 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 0bc374459440..deeefa7a1773 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -27,10 +27,6 @@ config DRM_MIPI_DSI
 	bool
 	depends on DRM
 
-# Separate option because drm_panel_orientation_quirks.c is shared with fbdev
-config DRM_PANEL_ORIENTATION_QUIRKS
-	tristate
-
 config DRM_DP_AUX_CHARDEV
 	bool "DRM DP AUX Interface"
 	depends on DRM
@@ -372,6 +368,10 @@ config DRM_SAVAGE
 
 endif # DRM_LEGACY
 
+# Separate option because drm_panel_orientation_quirks.c is shared with fbdev
+config DRM_PANEL_ORIENTATION_QUIRKS
+	tristate
+
 config DRM_LIB_RANDOM
 	bool
 	default n
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index dd5ae67f8e2b..50093ff4479b 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
 obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o
 obj-$(CONFIG_DRM_ARM)	+= arm/
 obj-$(CONFIG_DRM_TTM)	+= ttm/
+obj-$(CONFIG_DRM_SCHED)	+= scheduler/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
 obj-y			+= amd/lib/
@@ -102,4 +103,3 @@ obj-$(CONFIG_DRM_MXSFB)	+= mxsfb/
 obj-$(CONFIG_DRM_TINYDRM) += tinydrm/
 obj-$(CONFIG_DRM_PL111) += pl111/
 obj-$(CONFIG_DRM_TVE200) += tve200/
-obj-$(CONFIG_DRM_SCHED)	+= scheduler/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 9baf182d5418..00a50cc5ec9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1874,8 +1874,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * ignore it */
 	vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
 
-	if (amdgpu_runtime_pm == 1)
-		runtime = true;
 	if (amdgpu_device_is_px(ddev))
 		runtime = true;
 	if (!pci_is_thunderbolt_attached(adev->pdev))
@@ -2619,7 +2617,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	uint64_t reset_flags = 0;
 	int i, r, resched;
 
-	if (!amdgpu_device_ip_check_soft_reset(adev)) {
+	if (!force && !amdgpu_device_ip_check_soft_reset(adev)) {
 		DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index bb40d2529a30..239bf2a4b3c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
 
 		amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
 
-		/* Using pipes 2/3 from MEC 2 seems cause problems */
-		if (mec == 1 && pipe > 1)
+		/*
+		 * 1. Using pipes 2/3 from MEC 2 seems cause problems.
+		 * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
+		 * only can be issued on queue 0.
+		 */
+		if ((mec == 1 && pipe > 1) || queue != 0)
 			continue;
 
 		ring->me = mec + 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 55a726a322e3..d274ae535530 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -585,8 +585,8 @@ static int amdgpu_vce_validate_bo(struct amdgpu_cs_parser *p, uint32_t ib_idx,
 
 	for (i = 0; i < bo->placement.num_placement; ++i) {
 		bo->placements[i].fpfn = max(bo->placements[i].fpfn, fpfn);
-		bo->placements[i].lpfn = bo->placements[i].fpfn ?
-			min(bo->placements[i].fpfn, lpfn) : lpfn;
+		bo->placements[i].lpfn = bo->placements[i].lpfn ?
+			min(bo->placements[i].lpfn, lpfn) : lpfn;
 	}
 	return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index cd1752b6afa9..5afbc5e714d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -970,12 +970,16 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p,
 	amdgpu_gart_get_vm_pde(p->adev, AMDGPU_VM_PDB0,
 			       &dst, &flags);
 
-	if (parent->base.bo->shadow) {
-		pd_addr = amdgpu_bo_gpu_offset(parent->base.bo->shadow);
-		pde = pd_addr + (entry - parent->entries) * 8;
-		p->func(p, pde, dst, 1, 0, flags);
+	if (p->func == amdgpu_vm_cpu_set_ptes) {
+		pd_addr = (unsigned long)amdgpu_bo_kptr(parent->base.bo);
+	} else {
+		if (parent->base.bo->shadow) {
+			pd_addr = amdgpu_bo_gpu_offset(parent->base.bo->shadow);
+			pde = pd_addr + (entry - parent->entries) * 8;
+			p->func(p, pde, dst, 1, 0, flags);
+		}
+		pd_addr = amdgpu_bo_gpu_offset(parent->base.bo);
 	}
-	pd_addr = amdgpu_bo_gpu_offset(parent->base.bo);
 	pde = pd_addr + (entry - parent->entries) * 8;
 	p->func(p, pde, dst, 1, 0, flags);
 }
@@ -2258,12 +2262,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 {
 	const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
 		AMDGPU_VM_PTE_COUNT(adev) * 8);
+	uint64_t init_pde_value = 0, flags;
 	unsigned ring_instance;
 	struct amdgpu_ring *ring;
 	struct drm_sched_rq *rq;
+	unsigned long size;
 	int r, i;
-	u64 flags;
-	uint64_t init_pde_value = 0;
 
 	vm->va = RB_ROOT_CACHED;
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
@@ -2314,29 +2318,21 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
 				AMDGPU_GEM_CREATE_SHADOW);
 
-	r = amdgpu_bo_create(adev,
-			     amdgpu_vm_bo_size(adev, adev->vm_manager.root_level),
-			     align, true,
-			     AMDGPU_GEM_DOMAIN_VRAM,
-			     flags,
-			     NULL, NULL, init_pde_value, &vm->root.base.bo);
+	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
+	r = amdgpu_bo_create(adev, size, align, true, AMDGPU_GEM_DOMAIN_VRAM,
+			     flags, NULL, NULL, init_pde_value,
+			     &vm->root.base.bo);
 	if (r)
 		goto error_free_sched_entity;
 
+	r = amdgpu_bo_reserve(vm->root.base.bo, true);
+	if (r)
+		goto error_free_root;
+
 	vm->root.base.vm = vm;
 	list_add_tail(&vm->root.base.bo_list, &vm->root.base.bo->va);
-	INIT_LIST_HEAD(&vm->root.base.vm_status);
-
-	if (vm->use_cpu_for_update) {
-		r = amdgpu_bo_reserve(vm->root.base.bo, false);
-		if (r)
-			goto error_free_root;
-
-		r = amdgpu_bo_kmap(vm->root.base.bo, NULL);
-		amdgpu_bo_unreserve(vm->root.base.bo);
-		if (r)
-			goto error_free_root;
-	}
+	list_add_tail(&vm->root.base.vm_status, &vm->evicted);
+	amdgpu_bo_unreserve(vm->root.base.bo);
 
 	if (pasid) {
 		unsigned long flags;
@@ -2478,17 +2474,21 @@ bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 
 	spin_lock(&adev->vm_manager.pasid_lock);
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
-	spin_unlock(&adev->vm_manager.pasid_lock);
-	if (!vm)
+	if (!vm) {
 		/* VM not found, can't track fault credit */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		return true;
+	}
 
 	/* No lock needed. only accessed by IRQ handler */
-	if (!vm->fault_credit)
+	if (!vm->fault_credit) {
 		/* Too many faults in this VM */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		return false;
+	}
 
 	vm->fault_credit--;
+	spin_unlock(&adev->vm_manager.pasid_lock);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index fc270e2ef91a..c06479615e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1068,8 +1068,8 @@ static int gfx_v9_0_ngg_init(struct amdgpu_device *adev)
 	adev->gfx.ngg.gds_reserve_size = ALIGN(5 * 4, 0x40);
 	adev->gds.mem.total_size -= adev->gfx.ngg.gds_reserve_size;
 	adev->gds.mem.gfx_partition_size -= adev->gfx.ngg.gds_reserve_size;
-	adev->gfx.ngg.gds_reserve_addr = SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_BASE);
-	adev->gfx.ngg.gds_reserve_addr += adev->gds.mem.gfx_partition_size;
+	adev->gfx.ngg.gds_reserve_addr = RREG32_SOC15(GC, 0, mmGDS_VMID0_BASE);
+	adev->gfx.ngg.gds_reserve_addr += RREG32_SOC15(GC, 0, mmGDS_VMID0_SIZE);
 
 	/* Primitive Buffer */
 	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_PRIM],
@@ -1181,13 +1181,14 @@ static int gfx_v9_0_ngg_en(struct amdgpu_device *adev)
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_DMA_DATA, 5));
 	amdgpu_ring_write(ring, (PACKET3_DMA_DATA_CP_SYNC |
+				PACKET3_DMA_DATA_DST_SEL(1) |
 				PACKET3_DMA_DATA_SRC_SEL(2)));
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, 0);
 	amdgpu_ring_write(ring, adev->gfx.ngg.gds_reserve_addr);
 	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, adev->gfx.ngg.gds_reserve_size);
-
+	amdgpu_ring_write(ring, PACKET3_DMA_DATA_CMD_RAW_WAIT |
+				adev->gfx.ngg.gds_reserve_size);
 
 	gfx_v9_0_write_data_to_reg(ring, 0, false,
 				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE), 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 71d3aedefd69..100ec69f020a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -635,14 +635,16 @@ static int gmc_v9_0_late_init(void *handle)
 	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
 		BUG_ON(vm_inv_eng[i] > 16);
 
-	r = gmc_v9_0_ecc_available(adev);
-	if (r == 1) {
-		DRM_INFO("ECC is active.\n");
-	} else if (r == 0) {
-		DRM_INFO("ECC is not present.\n");
-	} else {
-		DRM_ERROR("gmc_v9_0_ecc_available() failed. r: %d\n", r);
-		return r;
+	if (adev->asic_type == CHIP_VEGA10) {
+		r = gmc_v9_0_ecc_available(adev);
+		if (r == 1) {
+			DRM_INFO("ECC is active.\n");
+		} else if (r == 0) {
+			DRM_INFO("ECC is not present.\n");
+		} else {
+			DRM_ERROR("gmc_v9_0_ecc_available() failed. r: %d\n", r);
+			return r;
+		}
 	}
 
 	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8f2cff7b7e0c..a04a033f57de 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -666,8 +666,8 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_MC_LS |
 			AMD_CG_SUPPORT_SDMA_MGCG |
 			AMD_CG_SUPPORT_SDMA_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				 AMD_PG_SUPPORT_MMHUB;
+		adev->pg_flags = AMD_PG_SUPPORT_SDMA;
+
 		adev->external_rev_id = 0x1;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 59271055a30e..b2bfedaf57f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -37,6 +37,9 @@
 #include "gmc/gmc_8_1_d.h"
 #include "vi.h"
 
+/* Polaris10/11/12 firmware version */
+#define FW_1_130_16 ((1 << 24) | (130 << 16) | (16 << 8))
+
 static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v6_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 
@@ -58,7 +61,9 @@ static void uvd_v6_0_enable_mgcg(struct amdgpu_device *adev,
 */
 static inline bool uvd_v6_0_enc_support(struct amdgpu_device *adev)
 {
-	return ((adev->asic_type >= CHIP_POLARIS10) && (adev->asic_type <= CHIP_POLARIS12));
+	return ((adev->asic_type >= CHIP_POLARIS10) &&
+			(adev->asic_type <= CHIP_POLARIS12) &&
+			(!adev->uvd.fw_version || adev->uvd.fw_version >= FW_1_130_16));
 }
 
 /**
@@ -411,7 +416,15 @@ static int uvd_v6_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	if (uvd_v6_0_enc_support(adev)) {
+	if (!uvd_v6_0_enc_support(adev)) {
+		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
+			adev->uvd.ring_enc[i].funcs = NULL;
+
+		adev->uvd.irq.num_types = 1;
+		adev->uvd.num_enc_rings = 0;
+
+		DRM_INFO("UVD ENC is disabled\n");
+	} else {
 		struct drm_sched_rq *rq;
 		ring = &adev->uvd.ring_enc[0];
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index b69ceafb7888..ee14d78be2a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -278,9 +278,9 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev)
 	/* Track retry faults in per-VM fault FIFO. */
 	spin_lock(&adev->vm_manager.pasid_lock);
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
-	spin_unlock(&adev->vm_manager.pasid_lock);
-	if (WARN_ON_ONCE(!vm)) {
+	if (!vm) {
 		/* VM not found, process it normally */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		amdgpu_ih_clear_fault(adev, key);
 		return true;
 	}
@@ -288,9 +288,11 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev)
 	r = kfifo_put(&vm->faults, key);
 	if (!r) {
 		/* FIFO is full. Ignore it until there is space */
+		spin_unlock(&adev->vm_manager.pasid_lock);
 		amdgpu_ih_clear_fault(adev, key);
 		goto ignore_iv;
 	}
+	spin_unlock(&adev->vm_manager.pasid_lock);
 
 	/* It's the first fault for this address, process it normally */
 	return true;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index da2b99c2d95f..1e3e05a11f7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1049,7 +1049,6 @@ static int vi_common_early_init(void *handle)
 			AMD_CG_SUPPORT_GFX_CP_LS |
 			AMD_CG_SUPPORT_GFX_CGTS |
 			AMD_CG_SUPPORT_GFX_CGTS_LS |
-			AMD_CG_SUPPORT_GFX_CGCG |
 			AMD_CG_SUPPORT_GFX_CGLS |
 			AMD_CG_SUPPORT_BIF_LS |
 			AMD_CG_SUPPORT_HDP_MGCG |
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d0693fd8cbf8..b21285afa4ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1013,13 +1013,13 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	list_del(&q->list);
 	qpd->queue_count--;
-	if (q->properties.is_active)
+	if (q->properties.is_active) {
 		dqm->queue_count--;
-
-	retval = execute_queues_cpsch(dqm,
+		retval = execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	if (retval == -ETIME)
-		qpd->reset_wavefronts = true;
+		if (retval == -ETIME)
+			qpd->reset_wavefronts = true;
+	}
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
@@ -1033,7 +1033,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	mutex_unlock(&dqm->lock);
 
-	return 0;
+	return retval;
 
 failed:
 failed_try_destroy_debugged_queue:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6a48d29ada47..0bedcf9cc08c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -41,9 +41,9 @@
 
 #define KFD_SYSFS_FILE_MODE 0444
 
-#define KFD_MMAP_DOORBELL_MASK 0x8000000000000
-#define KFD_MMAP_EVENTS_MASK 0x4000000000000
-#define KFD_MMAP_RESERVED_MEM_MASK 0x2000000000000
+#define KFD_MMAP_DOORBELL_MASK 0x8000000000000ull
+#define KFD_MMAP_EVENTS_MASK 0x4000000000000ull
+#define KFD_MMAP_RESERVED_MEM_MASK 0x2000000000000ull
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index a22fb0710f15..4ff5f0fe6db8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -461,7 +461,8 @@ int kfd_bind_processes_to_device(struct kfd_dev *dev)
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		mutex_lock(&p->mutex);
 		pdd = kfd_get_process_device_data(dev, p);
-		if (pdd->bound != PDD_BOUND_SUSPENDED) {
+
+		if (WARN_ON(!pdd) || pdd->bound != PDD_BOUND_SUSPENDED) {
 			mutex_unlock(&p->mutex);
 			continue;
 		}
@@ -501,6 +502,11 @@ void kfd_unbind_processes_from_device(struct kfd_dev *dev)
 		mutex_lock(&p->mutex);
 		pdd = kfd_get_process_device_data(dev, p);
 
+		if (WARN_ON(!pdd)) {
+			mutex_unlock(&p->mutex);
+			continue;
+		}
+
 		if (pdd->bound == PDD_BOUND)
 			pdd->bound = PDD_BOUND_SUSPENDED;
 		mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 1aefed8cf98b..4b5fdd577848 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -387,7 +387,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 		bp->cmd_tbl.transmitter_control = transmitter_control_v1_6;
 		break;
 	default:
-		dm_error("Don't have transmitter_control for v%d\n", crev);
+		dm_output_to_console("Don't have transmitter_control for v%d\n", crev);
 		bp->cmd_tbl.transmitter_control = NULL;
 		break;
 	}
@@ -911,7 +911,7 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7;
 		break;
 	default:
-		dm_error("Don't have set_pixel_clock for v%d\n",
+		dm_output_to_console("Don't have set_pixel_clock for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(SetPixelClock));
 		bp->cmd_tbl.set_pixel_clock = NULL;
 		break;
@@ -1230,7 +1230,7 @@ static void init_enable_spread_spectrum_on_ppll(struct bios_parser *bp)
 				enable_spread_spectrum_on_ppll_v3;
 		break;
 	default:
-		dm_error("Don't have enable_spread_spectrum_on_ppll for v%d\n",
+		dm_output_to_console("Don't have enable_spread_spectrum_on_ppll for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(EnableSpreadSpectrumOnPPLL));
 		bp->cmd_tbl.enable_spread_spectrum_on_ppll = NULL;
 		break;
@@ -1427,7 +1427,7 @@ static void init_adjust_display_pll(struct bios_parser *bp)
 		bp->cmd_tbl.adjust_display_pll = adjust_display_pll_v3;
 		break;
 	default:
-		dm_error("Don't have adjust_display_pll for v%d\n",
+		dm_output_to_console("Don't have adjust_display_pll for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(AdjustDisplayPll));
 		bp->cmd_tbl.adjust_display_pll = NULL;
 		break;
@@ -1702,7 +1702,7 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 					set_crtc_using_dtd_timing_v3;
 			break;
 		default:
-			dm_error("Don't have set_crtc_timing for dtd v%d\n",
+			dm_output_to_console("Don't have set_crtc_timing for dtd v%d\n",
 				 dtd_version);
 			bp->cmd_tbl.set_crtc_timing = NULL;
 			break;
@@ -1713,7 +1713,7 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 			bp->cmd_tbl.set_crtc_timing = set_crtc_timing_v1;
 			break;
 		default:
-			dm_error("Don't have set_crtc_timing for v%d\n",
+			dm_output_to_console("Don't have set_crtc_timing for v%d\n",
 				 BIOS_CMD_TABLE_PARA_REVISION(SetCRTC_Timing));
 			bp->cmd_tbl.set_crtc_timing = NULL;
 			break;
@@ -1901,7 +1901,7 @@ static void init_select_crtc_source(struct bios_parser *bp)
 		bp->cmd_tbl.select_crtc_source = select_crtc_source_v3;
 		break;
 	default:
-		dm_error("Don't select_crtc_source enable_crtc for v%d\n",
+		dm_output_to_console("Don't select_crtc_source enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(SelectCRTC_Source));
 		bp->cmd_tbl.select_crtc_source = NULL;
 		break;
@@ -2010,7 +2010,7 @@ static void init_enable_crtc(struct bios_parser *bp)
 		bp->cmd_tbl.enable_crtc = enable_crtc_v1;
 		break;
 	default:
-		dm_error("Don't have enable_crtc for v%d\n",
+		dm_output_to_console("Don't have enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(EnableCRTC));
 		bp->cmd_tbl.enable_crtc = NULL;
 		break;
@@ -2118,7 +2118,7 @@ static void init_program_clock(struct bios_parser *bp)
 		bp->cmd_tbl.program_clock = program_clock_v6;
 		break;
 	default:
-		dm_error("Don't have program_clock for v%d\n",
+		dm_output_to_console("Don't have program_clock for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(SetPixelClock));
 		bp->cmd_tbl.program_clock = NULL;
 		break;
@@ -2341,7 +2341,7 @@ static void init_enable_disp_power_gating(
 				enable_disp_power_gating_v2_1;
 		break;
 	default:
-		dm_error("Don't enable_disp_power_gating enable_crtc for v%d\n",
+		dm_output_to_console("Don't enable_disp_power_gating enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(EnableDispPowerGating));
 		bp->cmd_tbl.enable_disp_power_gating = NULL;
 		break;
@@ -2390,7 +2390,7 @@ static void init_set_dce_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1;
 		break;
 	default:
-		dm_error("Don't have set_dce_clock for v%d\n",
+		dm_output_to_console("Don't have set_dce_clock for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(SetDCEClock));
 		bp->cmd_tbl.set_dce_clock = NULL;
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 946db12388d6..fea5e83736fd 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -118,7 +118,7 @@ static void init_dig_encoder_control(struct bios_parser *bp)
 		bp->cmd_tbl.dig_encoder_control = encoder_control_digx_v1_5;
 		break;
 	default:
-		dm_error("Don't have dig_encoder_control for v%d\n", version);
+		dm_output_to_console("Don't have dig_encoder_control for v%d\n", version);
 		bp->cmd_tbl.dig_encoder_control = NULL;
 		break;
 	}
@@ -206,7 +206,7 @@ static void init_transmitter_control(struct bios_parser *bp)
 		bp->cmd_tbl.transmitter_control = transmitter_control_v1_6;
 		break;
 	default:
-		dm_error("Don't have transmitter_control for v%d\n", crev);
+		dm_output_to_console("Don't have transmitter_control for v%d\n", crev);
 		bp->cmd_tbl.transmitter_control = NULL;
 		break;
 	}
@@ -270,7 +270,7 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7;
 		break;
 	default:
-		dm_error("Don't have set_pixel_clock for v%d\n",
+		dm_output_to_console("Don't have set_pixel_clock for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(setpixelclock));
 		bp->cmd_tbl.set_pixel_clock = NULL;
 		break;
@@ -383,7 +383,7 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 			set_crtc_using_dtd_timing_v3;
 		break;
 	default:
-		dm_error("Don't have set_crtc_timing for v%d\n", dtd_version);
+		dm_output_to_console("Don't have set_crtc_timing for v%d\n", dtd_version);
 		bp->cmd_tbl.set_crtc_timing = NULL;
 		break;
 	}
@@ -503,7 +503,7 @@ static void init_select_crtc_source(struct bios_parser *bp)
 		bp->cmd_tbl.select_crtc_source = select_crtc_source_v3;
 		break;
 	default:
-		dm_error("Don't select_crtc_source enable_crtc for v%d\n",
+		dm_output_to_console("Don't select_crtc_source enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(selectcrtc_source));
 		bp->cmd_tbl.select_crtc_source = NULL;
 		break;
@@ -572,7 +572,7 @@ static void init_enable_crtc(struct bios_parser *bp)
 		bp->cmd_tbl.enable_crtc = enable_crtc_v1;
 		break;
 	default:
-		dm_error("Don't have enable_crtc for v%d\n",
+		dm_output_to_console("Don't have enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(enablecrtc));
 		bp->cmd_tbl.enable_crtc = NULL;
 		break;
@@ -670,7 +670,7 @@ static void init_enable_disp_power_gating(
 				enable_disp_power_gating_v2_1;
 		break;
 	default:
-		dm_error("Don't enable_disp_power_gating enable_crtc for v%d\n",
+		dm_output_to_console("Don't enable_disp_power_gating enable_crtc for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(enabledisppowergating));
 		bp->cmd_tbl.enable_disp_power_gating = NULL;
 		break;
@@ -721,7 +721,7 @@ static void init_set_dce_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1;
 		break;
 	default:
-		dm_error("Don't have set_dce_clock for v%d\n",
+		dm_output_to_console("Don't have set_dce_clock for v%d\n",
 			 BIOS_CMD_TABLE_PARA_REVISION(setdceclock));
 		bp->cmd_tbl.set_dce_clock = NULL;
 		break;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/rv_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/rv_smumgr.h
index 58888400f1b8..caebdbebdcd8 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/rv_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/rv_smumgr.h
@@ -40,7 +40,7 @@ struct smu_table_entry {
 	uint32_t table_addr_high;
 	uint32_t table_addr_low;
 	uint8_t *table;
-	uint32_t handle;
+	unsigned long handle;
 };
 
 struct smu_table_array {
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 9555a3542022..831b73392d82 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -644,6 +644,7 @@ static void ast_crtc_commit(struct drm_crtc *crtc)
 {
 	struct ast_private *ast = crtc->dev->dev_private;
 	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
+	ast_crtc_load_lut(crtc);
 }
 
 
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7d9ad20040a1..46733d534587 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1224,6 +1224,12 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		state->picture_aspect_ratio = val;
 	} else if (property == connector->scaling_mode_property) {
 		state->scaling_mode = val;
+	} else if (property == connector->content_protection_property) {
+		if (val == DRM_MODE_CONTENT_PROTECTION_ENABLED) {
+			DRM_DEBUG_KMS("only drivers can set CP Enabled\n");
+			return -EINVAL;
+		}
+		state->content_protection = val;
 	} else if (connector->funcs->atomic_set_property) {
 		return connector->funcs->atomic_set_property(connector,
 				state, property, val);
@@ -1303,6 +1309,8 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 		*val = state->picture_aspect_ratio;
 	} else if (property == connector->scaling_mode_property) {
 		*val = state->scaling_mode;
+	} else if (property == connector->content_protection_property) {
+		*val = state->content_protection;
 	} else if (connector->funcs->atomic_get_property) {
 		return connector->funcs->atomic_get_property(connector,
 				state, property, val);
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index aad468d170a7..d9c0f7573905 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -230,6 +230,12 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
 	if (!dev->master)
 		goto out_unlock;
 
+	if (file_priv->master->lessor != NULL) {
+		DRM_DEBUG_LEASE("Attempt to drop lessee %d as master\n", file_priv->master->lessee_id);
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	ret = 0;
 	drm_drop_master(dev, file_priv);
 out_unlock:
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index d6a7eba087a0..16b9c3810af2 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -761,6 +761,13 @@ static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = {
 DRM_ENUM_NAME_FN(drm_get_tv_subconnector_name,
 		 drm_tv_subconnector_enum_list)
 
+static struct drm_prop_enum_list drm_cp_enum_list[] = {
+	{ DRM_MODE_CONTENT_PROTECTION_UNDESIRED, "Undesired" },
+	{ DRM_MODE_CONTENT_PROTECTION_DESIRED, "Desired" },
+	{ DRM_MODE_CONTENT_PROTECTION_ENABLED, "Enabled" },
+};
+DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
+
 /**
  * DOC: standard connector properties
  *
@@ -822,14 +829,50 @@ DRM_ENUM_NAME_FN(drm_get_tv_subconnector_name,
  * 	should update this value using drm_mode_connector_set_tile_property().
  * 	Userspace cannot change this property.
  * link-status:
- *      Connector link-status property to indicate the status of link. The default
- *      value of link-status is "GOOD". If something fails during or after modeset,
- *      the kernel driver may set this to "BAD" and issue a hotplug uevent. Drivers
- *      should update this value using drm_mode_connector_set_link_status_property().
+ *      Connector link-status property to indicate the status of link. The
+ *      default value of link-status is "GOOD". If something fails during or
+ *      after modeset, the kernel driver may set this to "BAD" and issue a
+ *      hotplug uevent. Drivers should update this value using
+ *      drm_mode_connector_set_link_status_property().
  * non_desktop:
  * 	Indicates the output should be ignored for purposes of displaying a
  * 	standard desktop environment or console. This is most likely because
  * 	the output device is not rectilinear.
+ * Content Protection:
+ *	This property is used by userspace to request the kernel protect future
+ *	content communicated over the link. When requested, kernel will apply
+ *	the appropriate means of protection (most often HDCP), and use the
+ *	property to tell userspace the protection is active.
+ *
+ *	Drivers can set this up by calling
+ *	drm_connector_attach_content_protection_property() on initialization.
+ *
+ *	The value of this property can be one of the following:
+ *
+ *	- DRM_MODE_CONTENT_PROTECTION_UNDESIRED = 0
+ *		The link is not protected, content is transmitted in the clear.
+ *	- DRM_MODE_CONTENT_PROTECTION_DESIRED = 1
+ *		Userspace has requested content protection, but the link is not
+ *		currently protected. When in this state, kernel should enable
+ *		Content Protection as soon as possible.
+ *	- DRM_MODE_CONTENT_PROTECTION_ENABLED = 2
+ *		Userspace has requested content protection, and the link is
+ *		protected. Only the driver can set the property to this value.
+ *		If userspace attempts to set to ENABLED, kernel will return
+ *		-EINVAL.
+ *
+ *	A few guidelines:
+ *
+ *	- DESIRED state should be preserved until userspace de-asserts it by
+ *	  setting the property to UNDESIRED. This means ENABLED should only
+ *	  transition to UNDESIRED when the user explicitly requests it.
+ *	- If the state is DESIRED, kernel should attempt to re-authenticate the
+ *	  link whenever possible. This includes across disable/enable, dpms,
+ *	  hotplug, downstream device changes, link status failures, etc..
+ *	- Userspace is responsible for polling the property to determine when
+ *	  the value transitions from ENABLED to DESIRED. This signifies the link
+ *	  is no longer protected and userspace should take appropriate action
+ *	  (whatever that might be).
  *
  * Connectors also have one standardized atomic property:
  *
@@ -1131,6 +1174,42 @@ int drm_connector_attach_scaling_mode_property(struct drm_connector *connector,
 EXPORT_SYMBOL(drm_connector_attach_scaling_mode_property);
 
 /**
+ * drm_connector_attach_content_protection_property - attach content protection
+ * property
+ *
+ * @connector: connector to attach CP property on.
+ *
+ * This is used to add support for content protection on select connectors.
+ * Content Protection is intentionally vague to allow for different underlying
+ * technologies, however it is most implemented by HDCP.
+ *
+ * The content protection will be set to &drm_connector_state.content_protection
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int drm_connector_attach_content_protection_property(
+		struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_property *prop;
+
+	prop = drm_property_create_enum(dev, 0, "Content Protection",
+					drm_cp_enum_list,
+					ARRAY_SIZE(drm_cp_enum_list));
+	if (!prop)
+		return -ENOMEM;
+
+	drm_object_attach_property(&connector->base, prop,
+				   DRM_MODE_CONTENT_PROTECTION_UNDESIRED);
+
+	connector->content_protection_property = prop;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_connector_attach_content_protection_property);
+
+/**
  * drm_mode_create_aspect_ratio_property - create aspect ratio property
  * @dev: DRM device
  *
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index b3c6e997ccdb..e394799979a6 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -559,15 +559,15 @@ EXPORT_SYMBOL(drm_read);
  *
  * Mask of POLL flags indicating the current status of the file.
  */
-unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait)
+__poll_t drm_poll(struct file *filp, struct poll_table_struct *wait)
 {
 	struct drm_file *file_priv = filp->private_data;
-	unsigned int mask = 0;
+	__poll_t mask = 0;
 
 	poll_wait(filp, &file_priv->event_wait, wait);
 
 	if (!list_empty(&file_priv->event_list))
-		mask |= POLLIN | POLLRDNORM;
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	return mask;
 }
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index 8745971a7680..3a3bf752e03a 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -185,21 +185,22 @@ static int cdv_backlight_init(struct drm_device *dev)
  *	for this and the MID devices.
  */
 
-static inline u32 CDV_MSG_READ32(uint port, uint offset)
+static inline u32 CDV_MSG_READ32(int domain, uint port, uint offset)
 {
 	int mcr = (0x10<<24) | (port << 16) | (offset << 8);
 	uint32_t ret_val = 0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_read_config_dword(pci_root, 0xD4, &ret_val);
 	pci_dev_put(pci_root);
 	return ret_val;
 }
 
-static inline void CDV_MSG_WRITE32(uint port, uint offset, u32 value)
+static inline void CDV_MSG_WRITE32(int domain, uint port, uint offset,
+				   u32 value)
 {
 	int mcr = (0x11<<24) | (port << 16) | (offset << 8) | 0xF0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD4, value);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_dev_put(pci_root);
@@ -216,11 +217,12 @@ static void cdv_init_pm(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	u32 pwr_cnt;
+	int domain = pci_domain_nr(dev->pdev->bus);
 	int i;
 
-	dev_priv->apm_base = CDV_MSG_READ32(PSB_PUNIT_PORT,
+	dev_priv->apm_base = CDV_MSG_READ32(domain, PSB_PUNIT_PORT,
 							PSB_APMBA) & 0xFFFF;
-	dev_priv->ospm_base = CDV_MSG_READ32(PSB_PUNIT_PORT,
+	dev_priv->ospm_base = CDV_MSG_READ32(domain, PSB_PUNIT_PORT,
 							PSB_OSPMBA) & 0xFFFF;
 
 	/* Power status */
@@ -251,7 +253,7 @@ static void cdv_errata(struct drm_device *dev)
 	 *	Bonus Launch to work around the issue, by degrading
 	 *	performance.
 	 */
-	 CDV_MSG_WRITE32(3, 0x30, 0x08027108);
+	 CDV_MSG_WRITE32(pci_domain_nr(dev->pdev->bus), 3, 0x30, 0x08027108);
 }
 
 /**
diff --git a/drivers/gpu/drm/gma500/gma_device.c b/drivers/gpu/drm/gma500/gma_device.c
index 4a295f9ba067..a7fb6de4dd15 100644
--- a/drivers/gpu/drm/gma500/gma_device.c
+++ b/drivers/gpu/drm/gma500/gma_device.c
@@ -19,7 +19,9 @@
 void gma_get_core_freq(struct drm_device *dev)
 {
 	uint32_t clock;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root =
+		pci_get_domain_bus_and_slot(pci_domain_nr(dev->pdev->bus),
+					    0, 0);
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
 	/*pci_write_config_dword(pci_root, 0xD4, 0x00C32004);*/
diff --git a/drivers/gpu/drm/gma500/mid_bios.c b/drivers/gpu/drm/gma500/mid_bios.c
index 1fa163373a47..7171b7475f58 100644
--- a/drivers/gpu/drm/gma500/mid_bios.c
+++ b/drivers/gpu/drm/gma500/mid_bios.c
@@ -32,7 +32,9 @@
 static void mid_get_fuse_settings(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root =
+		pci_get_domain_bus_and_slot(pci_domain_nr(dev->pdev->bus),
+					    0, 0);
 	uint32_t fuse_value = 0;
 	uint32_t fuse_value_tmp = 0;
 
@@ -104,7 +106,9 @@ static void mid_get_fuse_settings(struct drm_device *dev)
 static void mid_get_pci_revID(struct drm_psb_private *dev_priv)
 {
 	uint32_t platform_rev_id = 0;
-	struct pci_dev *pci_gfx_root = pci_get_bus_and_slot(0, PCI_DEVFN(2, 0));
+	int domain = pci_domain_nr(dev_priv->dev->pdev->bus);
+	struct pci_dev *pci_gfx_root =
+		pci_get_domain_bus_and_slot(domain, 0, PCI_DEVFN(2, 0));
 
 	if (pci_gfx_root == NULL) {
 		WARN_ON(1);
@@ -281,7 +285,9 @@ static void mid_get_vbt_data(struct drm_psb_private *dev_priv)
 	u32 addr;
 	u8 __iomem *vbt_virtual;
 	struct mid_vbt_header vbt_header;
-	struct pci_dev *pci_gfx_root = pci_get_bus_and_slot(0, PCI_DEVFN(2, 0));
+	struct pci_dev *pci_gfx_root =
+		pci_get_domain_bus_and_slot(pci_domain_nr(dev->pdev->bus),
+					    0, PCI_DEVFN(2, 0));
 	int ret = -1;
 
 	/* Get the address of the platform config vbt */
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 38d09d4b3ed5..ac32ab5aa002 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -248,7 +248,11 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags)
 		goto out_err;
 
 	if (IS_MRST(dev)) {
-		dev_priv->aux_pdev = pci_get_bus_and_slot(0, PCI_DEVFN(3, 0));
+		int domain = pci_domain_nr(dev->pdev->bus);
+
+		dev_priv->aux_pdev =
+			pci_get_domain_bus_and_slot(domain, 0,
+						    PCI_DEVFN(3, 0));
 
 		if (dev_priv->aux_pdev) {
 			resource_start = pci_resource_start(dev_priv->aux_pdev,
@@ -268,7 +272,9 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags)
 		}
 		dev_priv->gmbus_reg = dev_priv->aux_reg;
 
-		dev_priv->lpc_pdev = pci_get_bus_and_slot(0, PCI_DEVFN(31, 0));
+		dev_priv->lpc_pdev =
+			pci_get_domain_bus_and_slot(domain, 0,
+						    PCI_DEVFN(31, 0));
 		if (dev_priv->lpc_pdev) {
 			pci_read_config_word(dev_priv->lpc_pdev, PSB_LPC_GBA,
 				&dev_priv->lpc_gpio_base);
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 4918efc57b7a..e8300f509023 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -780,38 +780,40 @@ extern const struct psb_ops cdv_chip_ops;
 extern int drm_idle_check_interval;
 
 /* Utilities */
-static inline u32 MRST_MSG_READ32(uint port, uint offset)
+static inline u32 MRST_MSG_READ32(int domain, uint port, uint offset)
 {
 	int mcr = (0xD0<<24) | (port << 16) | (offset << 8);
 	uint32_t ret_val = 0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_read_config_dword(pci_root, 0xD4, &ret_val);
 	pci_dev_put(pci_root);
 	return ret_val;
 }
-static inline void MRST_MSG_WRITE32(uint port, uint offset, u32 value)
+static inline void MRST_MSG_WRITE32(int domain, uint port, uint offset,
+				    u32 value)
 {
 	int mcr = (0xE0<<24) | (port << 16) | (offset << 8) | 0xF0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD4, value);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_dev_put(pci_root);
 }
-static inline u32 MDFLD_MSG_READ32(uint port, uint offset)
+static inline u32 MDFLD_MSG_READ32(int domain, uint port, uint offset)
 {
 	int mcr = (0x10<<24) | (port << 16) | (offset << 8);
 	uint32_t ret_val = 0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_read_config_dword(pci_root, 0xD4, &ret_val);
 	pci_dev_put(pci_root);
 	return ret_val;
 }
-static inline void MDFLD_MSG_WRITE32(uint port, uint offset, u32 value)
+static inline void MDFLD_MSG_WRITE32(int domain, uint port, uint offset,
+				     u32 value)
 {
 	int mcr = (0x11<<24) | (port << 16) | (offset << 8) | 0xF0;
-	struct pci_dev *pci_root = pci_get_bus_and_slot(0, 0);
+	struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0);
 	pci_write_config_dword(pci_root, 0xD4, value);
 	pci_write_config_dword(pci_root, 0xD0, mcr);
 	pci_dev_put(pci_root);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 091aef281963..3bddd8a06806 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -83,6 +83,7 @@ i915-y += i915_cmd_parser.o \
 i915-y += intel_uc.o \
 	  intel_uc_fw.o \
 	  intel_guc.o \
+	  intel_guc_ads.o \
 	  intel_guc_ct.o \
 	  intel_guc_fw.o \
 	  intel_guc_log.o \
@@ -108,6 +109,7 @@ i915-y += intel_audio.o \
 	  intel_fbc.o \
 	  intel_fifo_underrun.o \
 	  intel_frontbuffer.o \
+	  intel_hdcp.o \
 	  intel_hotplug.o \
 	  intel_modes.o \
 	  intel_overlay.o \
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 97bfc00d2a82..c62346fdc05d 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -119,16 +119,6 @@ static int map_aperture(struct intel_vgpu *vgpu, bool map)
 	if (map == vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked)
 		return 0;
 
-	if (map) {
-		vgpu->gm.aperture_va = memremap(aperture_pa, aperture_sz,
-						MEMREMAP_WC);
-		if (!vgpu->gm.aperture_va)
-			return -ENOMEM;
-	} else {
-		memunmap(vgpu->gm.aperture_va);
-		vgpu->gm.aperture_va = NULL;
-	}
-
 	val = vgpu_cfg_space(vgpu)[PCI_BASE_ADDRESS_2];
 	if (val & PCI_BASE_ADDRESS_MEM_TYPE_64)
 		val = *(u64 *)(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_2);
@@ -141,11 +131,8 @@ static int map_aperture(struct intel_vgpu *vgpu, bool map)
 						  aperture_pa >> PAGE_SHIFT,
 						  aperture_sz >> PAGE_SHIFT,
 						  map);
-	if (ret) {
-		memunmap(vgpu->gm.aperture_va);
-		vgpu->gm.aperture_va = NULL;
+	if (ret)
 		return ret;
-	}
 
 	vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked = map;
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2ab584f97dfb..2fb7b34ef561 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -472,7 +472,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id)
 		ret = PTR_ERR(dmabuf);
 		goto out_free_gem;
 	}
-	obj->base.dma_buf = dmabuf;
 
 	i915_gem_object_put(obj);
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 769c1c24ae75..70494e394d2c 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -521,24 +521,23 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, int ring_id)
 
 	ctx_status_ptr_reg = execlist_ring_mmio(vgpu->gvt, ring_id,
 			_EL_OFFSET_STATUS_PTR);
-
 	ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
 	ctx_status_ptr.read_ptr = 0;
 	ctx_status_ptr.write_ptr = 0x7;
 	vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
 }
 
-static void clean_execlist(struct intel_vgpu *vgpu)
+static void clean_execlist(struct intel_vgpu *vgpu, unsigned long engine_mask)
 {
-	enum intel_engine_id i;
+	unsigned int tmp;
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_engine_cs *engine;
+	struct intel_vgpu_submission *s = &vgpu->submission;
 
-	for_each_engine(engine, vgpu->gvt->dev_priv, i) {
-		struct intel_vgpu_submission *s = &vgpu->submission;
-
-		kfree(s->ring_scan_buffer[i]);
-		s->ring_scan_buffer[i] = NULL;
-		s->ring_scan_buffer_size[i] = 0;
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+		kfree(s->ring_scan_buffer[engine->id]);
+		s->ring_scan_buffer[engine->id] = NULL;
+		s->ring_scan_buffer_size[engine->id] = 0;
 	}
 }
 
@@ -553,9 +552,10 @@ static void reset_execlist(struct intel_vgpu *vgpu,
 		init_vgpu_execlist(vgpu, engine->id);
 }
 
-static int init_execlist(struct intel_vgpu *vgpu)
+static int init_execlist(struct intel_vgpu *vgpu,
+			 unsigned long engine_mask)
 {
-	reset_execlist(vgpu, ALL_ENGINES);
+	reset_execlist(vgpu, engine_mask);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index a529d2bd393c..8d5317d0122d 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -997,9 +997,11 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 {
 	struct intel_vgpu *vgpu = spt->vgpu;
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *s;
 	struct intel_gvt_gtt_entry se, ge;
-	unsigned long i;
+	unsigned long gfn, i;
 	int ret;
 
 	trace_spt_change(spt->vgpu->id, "born", spt,
@@ -1007,9 +1009,10 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 
 	if (gtt_type_is_pte_pt(spt->shadow_page.type)) {
 		for_each_present_guest_entry(spt, &ge, i) {
-			ret = gtt_entry_p2m(vgpu, &ge, &se);
-			if (ret)
-				goto fail;
+			gfn = ops->get_pfn(&ge);
+			if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn) ||
+				gtt_entry_p2m(vgpu, &ge, &se))
+				ops->set_pfn(&se, gvt->gtt.scratch_mfn);
 			ppgtt_set_shadow_entry(spt, &se, i);
 		}
 		return 0;
@@ -1906,7 +1909,7 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm;
 	struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops;
 	unsigned long g_gtt_index = off >> info->gtt_entry_size_shift;
-	unsigned long gma;
+	unsigned long gma, gfn;
 	struct intel_gvt_gtt_entry e, m;
 	int ret;
 
@@ -1925,6 +1928,16 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 			bytes);
 
 	if (ops->test_present(&e)) {
+		gfn = ops->get_pfn(&e);
+
+		/* one PTE update may be issued in multiple writes and the
+		 * first write may not construct a valid gfn
+		 */
+		if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn)) {
+			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+			goto out;
+		}
+
 		ret = gtt_entry_p2m(vgpu, &e, &m);
 		if (ret) {
 			gvt_vgpu_err("fail to translate guest gtt entry\n");
@@ -1939,6 +1952,7 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		ops->set_pfn(&m, gvt->gtt.scratch_mfn);
 	}
 
+out:
 	ggtt_set_shadow_entry(ggtt_mm, &m, g_gtt_index);
 	gtt_invalidate(gvt->dev_priv);
 	ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 7dc7a80213a8..c6197d990818 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -82,7 +82,6 @@ struct intel_gvt_device_info {
 struct intel_vgpu_gm {
 	u64 aperture_sz;
 	u64 hidden_sz;
-	void *aperture_va;
 	struct drm_mm_node low_gm_node;
 	struct drm_mm_node high_gm_node;
 };
@@ -127,7 +126,6 @@ struct intel_vgpu_irq {
 struct intel_vgpu_opregion {
 	bool mapped;
 	void *va;
-	void *va_gopregion;
 	u32 gfn[INTEL_GVT_OPREGION_PAGES];
 };
 
@@ -152,8 +150,8 @@ enum {
 
 struct intel_vgpu_submission_ops {
 	const char *name;
-	int (*init)(struct intel_vgpu *vgpu);
-	void (*clean)(struct intel_vgpu *vgpu);
+	int (*init)(struct intel_vgpu *vgpu, unsigned long engine_mask);
+	void (*clean)(struct intel_vgpu *vgpu, unsigned long engine_mask);
 	void (*reset)(struct intel_vgpu *vgpu, unsigned long engine_mask);
 };
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 92d6468daeee..9be639aa3b55 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1494,7 +1494,6 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	struct intel_vgpu_submission *s = &vgpu->submission;
 	u32 data = *(u32 *)p_data;
 	int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset);
 	bool enable_execlist;
@@ -1523,11 +1522,9 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		if (!enable_execlist)
 			return 0;
 
-		if (s->active)
-			return 0;
-
 		ret = intel_vgpu_select_submission_ops(vgpu,
-				INTEL_VGPU_EXECLIST_SUBMISSION);
+			       ENGINE_MASK(ring_id),
+			       INTEL_VGPU_EXECLIST_SUBMISSION);
 		if (ret)
 			return ret;
 
@@ -2843,6 +2840,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_A)), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_B)), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_C)), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_A)), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_B)), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_C)), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_A)), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_B)), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_C)), D_SKL_PLUS);
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index a1bd82feb827..f8e77e166246 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -58,6 +58,7 @@ struct intel_gvt_mpt {
 	int (*set_opregion)(void *vgpu);
 	int (*get_vfio_device)(void *vgpu);
 	void (*put_vfio_device)(void *vgpu);
+	bool (*is_valid_gfn)(unsigned long handle, unsigned long gfn);
 };
 
 extern struct intel_gvt_mpt xengt_mpt;
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 45bab5a6290b..909499b73d03 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -651,6 +651,39 @@ static int intel_vgpu_bar_rw(struct intel_vgpu *vgpu, int bar, uint64_t off,
 	return ret;
 }
 
+static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, uint64_t off)
+{
+	return off >= vgpu_aperture_offset(vgpu) &&
+	       off < vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu);
+}
+
+static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t off,
+		void *buf, unsigned long count, bool is_write)
+{
+	void *aperture_va;
+
+	if (!intel_vgpu_in_aperture(vgpu, off) ||
+	    !intel_vgpu_in_aperture(vgpu, off + count)) {
+		gvt_vgpu_err("Invalid aperture offset %llu\n", off);
+		return -EINVAL;
+	}
+
+	aperture_va = io_mapping_map_wc(&vgpu->gvt->dev_priv->ggtt.iomap,
+					ALIGN_DOWN(off, PAGE_SIZE),
+					count + offset_in_page(off));
+	if (!aperture_va)
+		return -EIO;
+
+	if (is_write)
+		memcpy(aperture_va + offset_in_page(off), buf, count);
+	else
+		memcpy(buf, aperture_va + offset_in_page(off), count);
+
+	io_mapping_unmap(aperture_va);
+
+	return 0;
+}
+
 static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 			size_t count, loff_t *ppos, bool is_write)
 {
@@ -679,8 +712,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 					buf, count, is_write);
 		break;
 	case VFIO_PCI_BAR2_REGION_INDEX:
-		ret = intel_vgpu_bar_rw(vgpu, PCI_BASE_ADDRESS_2, pos,
-					buf, count, is_write);
+		ret = intel_vgpu_aperture_rw(vgpu, pos, buf, count, is_write);
 		break;
 	case VFIO_PCI_BAR1_REGION_INDEX:
 	case VFIO_PCI_BAR3_REGION_INDEX:
@@ -1019,6 +1051,8 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			if (!sparse)
 				return -ENOMEM;
 
+			sparse->header.id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
+			sparse->header.version = 1;
 			sparse->nr_areas = nr_areas;
 			cap_type_id = VFIO_REGION_INFO_CAP_SPARSE_MMAP;
 			sparse->areas[0].offset =
@@ -1044,7 +1078,9 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			break;
 		default:
 			{
-				struct vfio_region_info_cap_type cap_type;
+				struct vfio_region_info_cap_type cap_type = {
+					.header.id = VFIO_REGION_INFO_CAP_TYPE,
+					.header.version = 1 };
 
 				if (info.index >= VFIO_PCI_NUM_REGIONS +
 						vgpu->vdev.num_regions)
@@ -1061,8 +1097,8 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 				cap_type.subtype = vgpu->vdev.region[i].subtype;
 
 				ret = vfio_info_add_capability(&caps,
-						VFIO_REGION_INFO_CAP_TYPE,
-						&cap_type);
+							&cap_type.header,
+							sizeof(cap_type));
 				if (ret)
 					return ret;
 			}
@@ -1072,8 +1108,9 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
 			switch (cap_type_id) {
 			case VFIO_REGION_INFO_CAP_SPARSE_MMAP:
 				ret = vfio_info_add_capability(&caps,
-					VFIO_REGION_INFO_CAP_SPARSE_MMAP,
-					sparse);
+					&sparse->header, sizeof(*sparse) +
+					(sparse->nr_areas *
+						sizeof(*sparse->areas)));
 				kfree(sparse);
 				if (ret)
 					return ret;
@@ -1570,6 +1607,21 @@ static unsigned long kvmgt_virt_to_pfn(void *addr)
 	return PFN_DOWN(__pa(addr));
 }
 
+static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn)
+{
+	struct kvmgt_guest_info *info;
+	struct kvm *kvm;
+
+	if (!handle_valid(handle))
+		return false;
+
+	info = (struct kvmgt_guest_info *)handle;
+	kvm = info->kvm;
+
+	return kvm_is_visible_gfn(kvm, gfn);
+
+}
+
 struct intel_gvt_mpt kvmgt_mpt = {
 	.host_init = kvmgt_host_init,
 	.host_exit = kvmgt_host_exit,
@@ -1585,6 +1637,7 @@ struct intel_gvt_mpt kvmgt_mpt = {
 	.set_opregion = kvmgt_set_opregion,
 	.get_vfio_device = kvmgt_get_vfio_device,
 	.put_vfio_device = kvmgt_put_vfio_device,
+	.is_valid_gfn = kvmgt_is_valid_gfn,
 };
 EXPORT_SYMBOL_GPL(kvmgt_mpt);
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 562b5ad857a4..5c869e3fdf3b 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -56,38 +56,6 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa)
 	(reg >= gvt->device_info.gtt_start_offset \
 	 && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
 
-static bool vgpu_gpa_is_aperture(struct intel_vgpu *vgpu, uint64_t gpa)
-{
-	u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2);
-	u64 aperture_sz = vgpu_aperture_sz(vgpu);
-
-	return gpa >= aperture_gpa && gpa < aperture_gpa + aperture_sz;
-}
-
-static int vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t gpa,
-			    void *pdata, unsigned int size, bool is_read)
-{
-	u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2);
-	u64 offset = gpa - aperture_gpa;
-
-	if (!vgpu_gpa_is_aperture(vgpu, gpa + size - 1)) {
-		gvt_vgpu_err("Aperture rw out of range, offset %llx, size %d\n",
-			     offset, size);
-		return -EINVAL;
-	}
-
-	if (!vgpu->gm.aperture_va) {
-		gvt_vgpu_err("BAR is not enabled\n");
-		return -ENXIO;
-	}
-
-	if (is_read)
-		memcpy(pdata, vgpu->gm.aperture_va + offset, size);
-	else
-		memcpy(vgpu->gm.aperture_va + offset, pdata, size);
-	return 0;
-}
-
 static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
 		void *p_data, unsigned int bytes, bool read)
 {
@@ -144,11 +112,6 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 	}
 	mutex_lock(&gvt->lock);
 
-	if (vgpu_gpa_is_aperture(vgpu, pa)) {
-		ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, true);
-		goto out;
-	}
-
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
 	if (WARN_ON(bytes > 8))
@@ -222,11 +185,6 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 
 	mutex_lock(&gvt->lock);
 
-	if (vgpu_gpa_is_aperture(vgpu, pa)) {
-		ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, false);
-		goto out;
-	}
-
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
 	if (WARN_ON(bytes > 8))
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 74834395dd89..73ad6e90e49d 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -80,7 +80,7 @@ static struct engine_mmio gen8_engine_mmio_list[] __cacheline_aligned = {
 	{BCS, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
 	{BCS, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
 	{BCS, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
-	{ /* Terminated */ }
+	{RCS, INVALID_MMIO_REG, 0, false } /* Terminated */
 };
 
 static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
@@ -146,7 +146,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
 	{RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
 	{RCS, FF_SLICE_CS_CHICKEN2, 0xffff, false}, /* 0x20e4 */
-	{ /* Terminated */ }
+	{RCS, INVALID_MMIO_REG, 0, false } /* Terminated */
 };
 
 static struct {
@@ -167,7 +167,7 @@ static void load_render_mocs(struct drm_i915_private *dev_priv)
 	};
 	int ring_id, i;
 
-	for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
+	for (ring_id = 0; ring_id < ARRAY_SIZE(regs); ring_id++) {
 		offset.reg = regs[ring_id];
 		for (i = 0; i < 64; i++) {
 			gen9_render_mocs.control_table[ring_id][i] =
@@ -310,8 +310,8 @@ static void switch_mmio(struct intel_vgpu *pre,
 	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
 		switch_mocs(pre, next, ring_id);
 
-	mmio = dev_priv->gvt->engine_mmio_list;
-	while (i915_mmio_reg_offset((mmio++)->reg)) {
+	for (mmio = dev_priv->gvt->engine_mmio_list;
+	     i915_mmio_reg_valid(mmio->reg); mmio++) {
 		if (mmio->ring_id != ring_id)
 			continue;
 		// save
diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h
index ca8005a6d5fa..81aff4eacbfe 100644
--- a/drivers/gpu/drm/i915/gvt/mpt.h
+++ b/drivers/gpu/drm/i915/gvt/mpt.h
@@ -339,4 +339,21 @@ static inline void intel_gvt_hypervisor_put_vfio_device(struct intel_vgpu *vgpu)
 	intel_gvt_host.mpt->put_vfio_device(vgpu);
 }
 
+/**
+ * intel_gvt_hypervisor_is_valid_gfn - check if a visible gfn
+ * @vgpu: a vGPU
+ * @gfn: guest PFN
+ *
+ * Returns:
+ * true on valid gfn, false on not.
+ */
+static inline bool intel_gvt_hypervisor_is_valid_gfn(
+		struct intel_vgpu *vgpu, unsigned long gfn)
+{
+	if (!intel_gvt_host.mpt->is_valid_gfn)
+		return true;
+
+	return intel_gvt_host.mpt->is_valid_gfn(vgpu->handle, gfn);
+}
+
 #endif /* _GVT_MPT_H_ */
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 8420d1fc3ddb..fa75a2eead90 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -299,21 +299,13 @@ int intel_vgpu_opregion_base_write_handler(struct intel_vgpu *vgpu, u32 gpa)
 {
 
 	int i, ret = 0;
-	unsigned long pfn;
 
 	gvt_dbg_core("emulate opregion from kernel\n");
 
 	switch (intel_gvt_host.hypervisor_type) {
 	case INTEL_GVT_HYPERVISOR_KVM:
-		pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, gpa >> PAGE_SHIFT);
-		vgpu_opregion(vgpu)->va_gopregion = memremap(pfn << PAGE_SHIFT,
-						INTEL_GVT_OPREGION_SIZE,
-						MEMREMAP_WB);
-		if (!vgpu_opregion(vgpu)->va_gopregion) {
-			gvt_vgpu_err("failed to map guest opregion\n");
-			ret = -EFAULT;
-		}
-		vgpu_opregion(vgpu)->mapped = true;
+		for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++)
+			vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i;
 		break;
 	case INTEL_GVT_HYPERVISOR_XEN:
 		/**
@@ -352,10 +344,7 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu)
 		if (vgpu_opregion(vgpu)->mapped)
 			map_vgpu_opregion(vgpu, false);
 	} else if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_KVM) {
-		if (vgpu_opregion(vgpu)->mapped) {
-			memunmap(vgpu_opregion(vgpu)->va_gopregion);
-			vgpu_opregion(vgpu)->va_gopregion = NULL;
-		}
+		/* Guest opregion is released by VFIO */
 	}
 	free_pages((unsigned long)vgpu_opregion(vgpu)->va,
 		   get_order(INTEL_GVT_OPREGION_SIZE));
@@ -480,19 +469,40 @@ static bool querying_capabilities(u32 scic)
  */
 int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
 {
-	u32 *scic, *parm;
+	u32 scic, parm;
 	u32 func, subfunc;
+	u64 scic_pa = 0, parm_pa = 0;
+	int ret;
 
 	switch (intel_gvt_host.hypervisor_type) {
 	case INTEL_GVT_HYPERVISOR_XEN:
-		scic = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_SCIC;
-		parm = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_PARM;
+		scic = *((u32 *)vgpu_opregion(vgpu)->va +
+					INTEL_GVT_OPREGION_SCIC);
+		parm = *((u32 *)vgpu_opregion(vgpu)->va +
+					INTEL_GVT_OPREGION_PARM);
 		break;
 	case INTEL_GVT_HYPERVISOR_KVM:
-		scic = vgpu_opregion(vgpu)->va_gopregion +
-						INTEL_GVT_OPREGION_SCIC;
-		parm = vgpu_opregion(vgpu)->va_gopregion +
-						INTEL_GVT_OPREGION_PARM;
+		scic_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) +
+					INTEL_GVT_OPREGION_SCIC;
+		parm_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) +
+					INTEL_GVT_OPREGION_PARM;
+
+		ret = intel_gvt_hypervisor_read_gpa(vgpu, scic_pa,
+						    &scic, sizeof(scic));
+		if (ret) {
+			gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n",
+				ret, scic_pa, sizeof(scic));
+			return ret;
+		}
+
+		ret = intel_gvt_hypervisor_read_gpa(vgpu, parm_pa,
+						    &parm, sizeof(parm));
+		if (ret) {
+			gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n",
+				ret, scic_pa, sizeof(scic));
+			return ret;
+		}
+
 		break;
 	default:
 		gvt_vgpu_err("not supported hypervisor\n");
@@ -510,9 +520,9 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
 		return 0;
 	}
 
-	func = GVT_OPREGION_FUNC(*scic);
-	subfunc = GVT_OPREGION_SUBFUNC(*scic);
-	if (!querying_capabilities(*scic)) {
+	func = GVT_OPREGION_FUNC(scic);
+	subfunc = GVT_OPREGION_SUBFUNC(scic);
+	if (!querying_capabilities(scic)) {
 		gvt_vgpu_err("requesting runtime service: func \"%s\","
 				" subfunc \"%s\"\n",
 				opregion_func_name(func),
@@ -521,11 +531,43 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
 		 * emulate exit status of function call, '0' means
 		 * "failure, generic, unsupported or unknown cause"
 		 */
-		*scic &= ~OPREGION_SCIC_EXIT_MASK;
-		return 0;
+		scic &= ~OPREGION_SCIC_EXIT_MASK;
+		goto out;
+	}
+
+	scic = 0;
+	parm = 0;
+
+out:
+	switch (intel_gvt_host.hypervisor_type) {
+	case INTEL_GVT_HYPERVISOR_XEN:
+		*((u32 *)vgpu_opregion(vgpu)->va +
+					INTEL_GVT_OPREGION_SCIC) = scic;
+		*((u32 *)vgpu_opregion(vgpu)->va +
+					INTEL_GVT_OPREGION_PARM) = parm;
+		break;
+	case INTEL_GVT_HYPERVISOR_KVM:
+		ret = intel_gvt_hypervisor_write_gpa(vgpu, scic_pa,
+						    &scic, sizeof(scic));
+		if (ret) {
+			gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n",
+				ret, scic_pa, sizeof(scic));
+			return ret;
+		}
+
+		ret = intel_gvt_hypervisor_write_gpa(vgpu, parm_pa,
+						    &parm, sizeof(parm));
+		if (ret) {
+			gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n",
+				ret, scic_pa, sizeof(scic));
+			return ret;
+		}
+
+		break;
+	default:
+		gvt_vgpu_err("not supported hypervisor\n");
+		return -EINVAL;
 	}
 
-	*scic = 0;
-	*parm = 0;
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index eea1a2f92099..cc1ce361cd76 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -50,6 +50,7 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu)
 struct vgpu_sched_data {
 	struct list_head lru_list;
 	struct intel_vgpu *vgpu;
+	bool active;
 
 	ktime_t sched_in_time;
 	ktime_t sched_out_time;
@@ -308,8 +309,15 @@ static int tbs_sched_init_vgpu(struct intel_vgpu *vgpu)
 
 static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu)
 {
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
+
 	kfree(vgpu->sched_data);
 	vgpu->sched_data = NULL;
+
+	/* this vgpu id has been removed */
+	if (idr_is_empty(&gvt->vgpu_idr))
+		hrtimer_cancel(&sched_data->timer);
 }
 
 static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
@@ -325,6 +333,7 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
 	if (!hrtimer_active(&sched_data->timer))
 		hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(),
 			sched_data->period), HRTIMER_MODE_ABS);
+	vgpu_data->active = true;
 }
 
 static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
@@ -332,6 +341,7 @@ static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
 	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
 
 	list_del_init(&vgpu_data->lru_list);
+	vgpu_data->active = false;
 }
 
 static struct intel_gvt_sched_policy_ops tbs_schedule_ops = {
@@ -367,9 +377,12 @@ void intel_vgpu_clean_sched_policy(struct intel_vgpu *vgpu)
 
 void intel_vgpu_start_schedule(struct intel_vgpu *vgpu)
 {
-	gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
 
-	vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
+	if (!vgpu_data->active) {
+		gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
+		vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
+	}
 }
 
 void intel_gvt_kick_schedule(struct intel_gvt *gvt)
@@ -382,6 +395,10 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 	struct intel_gvt_workload_scheduler *scheduler =
 		&vgpu->gvt->scheduler;
 	int ring_id;
+	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+
+	if (!vgpu_data->active)
+		return;
 
 	gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 0056638b0c16..b55b3580ca1d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -991,7 +991,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
 
-	intel_vgpu_select_submission_ops(vgpu, 0);
+	intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
 	i915_gem_context_put(s->shadow_ctx);
 	kmem_cache_destroy(s->workloads);
 }
@@ -1079,6 +1079,7 @@ out_shadow_ctx:
  *
  */
 int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
+				     unsigned long engine_mask,
 				     unsigned int interface)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
@@ -1091,21 +1092,21 @@ int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
 	if (WARN_ON(interface >= ARRAY_SIZE(ops)))
 		return -EINVAL;
 
-	if (s->active) {
-		s->ops->clean(vgpu);
-		s->active = false;
-		gvt_dbg_core("vgpu%d: de-select ops [ %s ] \n",
-				vgpu->id, s->ops->name);
-	}
+	if (WARN_ON(interface == 0 && engine_mask != ALL_ENGINES))
+		return -EINVAL;
+
+	if (s->active)
+		s->ops->clean(vgpu, engine_mask);
 
 	if (interface == 0) {
 		s->ops = NULL;
 		s->virtual_submission_interface = 0;
-		gvt_dbg_core("vgpu%d: no submission ops\n", vgpu->id);
+		s->active = false;
+		gvt_dbg_core("vgpu%d: remove submission ops\n", vgpu->id);
 		return 0;
 	}
 
-	ret = ops[interface]->init(vgpu);
+	ret = ops[interface]->init(vgpu, engine_mask);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 3de77dfa7c59..ff175a98b19e 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -141,6 +141,7 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu,
 void intel_vgpu_clean_submission(struct intel_vgpu *vgpu);
 
 int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
+				     unsigned long engine_mask,
 				     unsigned int interface);
 
 extern const struct intel_vgpu_submission_ops
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 4688619f6a1c..b87b19d8443c 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -258,6 +258,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 
 	intel_gvt_debugfs_remove_vgpu(vgpu);
 	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	if (idr_is_empty(&gvt->vgpu_idr))
+		intel_gvt_clean_irq(gvt);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
 	intel_vgpu_clean_display(vgpu);
@@ -518,8 +520,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 	intel_vgpu_reset_submission(vgpu, resetting_eng);
 	/* full GPU reset or device model level reset */
 	if (engine_mask == ALL_ENGINES || dmlr) {
-		intel_vgpu_select_submission_ops(vgpu, 0);
-
+		intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
 		/*fence will not be reset during virtual reset */
 		if (dmlr) {
 			intel_vgpu_reset_gtt(vgpu);
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index ccb5ba043b63..95478db9998b 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1032,7 +1032,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
 	const struct drm_i915_reg_table *table = engine->reg_tables;
 	int count = engine->reg_table_count;
 
-	do {
+	for (; count > 0; ++table, --count) {
 		if (!table->master || is_master) {
 			const struct drm_i915_reg_descriptor *reg;
 
@@ -1040,7 +1040,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
 			if (reg != NULL)
 				return reg;
 		}
-	} while (table++, --count);
+	}
 
 	return NULL;
 }
@@ -1212,6 +1212,12 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 					continue;
 			}
 
+			if (desc->bits[i].offset >= length) {
+				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
+						 *cmd, engine->name);
+				return false;
+			}
+
 			dword = cmd[desc->bits[i].offset] &
 				desc->bits[i].mask;
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e968aeae1d84..3849ded354e3 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -988,7 +988,10 @@ i915_next_seqno_set(void *data, u64 val)
 	if (ret)
 		return ret;
 
+	intel_runtime_pm_get(dev_priv);
 	ret = i915_gem_set_global_seqno(dev, val);
+	intel_runtime_pm_put(dev_priv);
+
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
@@ -2464,24 +2467,11 @@ static int i915_guc_log_control_get(void *data, u64 *val)
 static int i915_guc_log_control_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
-	int ret;
 
 	if (!HAS_GUC(dev_priv))
 		return -ENODEV;
 
-	if (!dev_priv->guc.log.vma)
-		return -EINVAL;
-
-	ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex);
-	if (ret)
-		return ret;
-
-	intel_runtime_pm_get(dev_priv);
-	ret = i915_guc_log_control(dev_priv, val);
-	intel_runtime_pm_put(dev_priv);
-
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-	return ret;
+	return intel_guc_log_control(&dev_priv->guc, val);
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_control_fops,
@@ -2518,15 +2508,19 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	u32 stat[3];
 	enum pipe pipe;
 	bool enabled = false;
+	bool sink_support;
 
 	if (!HAS_PSR(dev_priv))
 		return -ENODEV;
 
+	sink_support = dev_priv->psr.sink_support;
+	seq_printf(m, "Sink_Support: %s\n", yesno(sink_support));
+	if (!sink_support)
+		return 0;
+
 	intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->psr.lock);
-	seq_printf(m, "Sink_Support: %s\n", yesno(dev_priv->psr.sink_support));
-	seq_printf(m, "Source_OK: %s\n", yesno(dev_priv->psr.source_ok));
 	seq_printf(m, "Enabled: %s\n", yesno((bool)dev_priv->psr.enabled));
 	seq_printf(m, "Active: %s\n", yesno(dev_priv->psr.active));
 	seq_printf(m, "Busy frontbuffer bits: 0x%03x\n",
@@ -2584,9 +2578,9 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 		seq_printf(m, "Performance_Counter: %u\n", psrperf);
 	}
 	if (dev_priv->psr.psr2_support) {
-		u32 psr2 = I915_READ(EDP_PSR2_STATUS_CTL);
+		u32 psr2 = I915_READ(EDP_PSR2_STATUS);
 
-		seq_printf(m, "EDP_PSR2_STATUS_CTL: %x [%s]\n",
+		seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n",
 			   psr2, psr2_live_status(psr2));
 	}
 	mutex_unlock(&dev_priv->psr.lock);
@@ -2710,7 +2704,8 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 	if (!HAS_RUNTIME_PM(dev_priv))
 		seq_puts(m, "Runtime power management not supported\n");
 
-	seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->gt.awake));
+	seq_printf(m, "GPU idle: %s (epoch %u)\n",
+		   yesno(!dev_priv->gt.awake), dev_priv->gt.epoch);
 	seq_printf(m, "IRQs disabled: %s\n",
 		   yesno(!intel_irqs_enabled(dev_priv)));
 #ifdef CONFIG_PM
@@ -3143,8 +3138,8 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 
 	intel_runtime_pm_get(dev_priv);
 
-	seq_printf(m, "GT awake? %s\n",
-		   yesno(dev_priv->gt.awake));
+	seq_printf(m, "GT awake? %s (epoch %u)\n",
+		   yesno(dev_priv->gt.awake), dev_priv->gt.epoch);
 	seq_printf(m, "Global active requests: %d\n",
 		   dev_priv->gt.active_requests);
 	seq_printf(m, "CS timestamp frequency: %u kHz\n",
@@ -3363,7 +3358,10 @@ static void drrs_status_per_crtc(struct seq_file *m,
 
 		/* disable_drrs() will make drrs->dp NULL */
 		if (!drrs->dp) {
-			seq_puts(m, "Idleness DRRS: Disabled");
+			seq_puts(m, "Idleness DRRS: Disabled\n");
+			if (dev_priv->psr.enabled)
+				seq_puts(m,
+				"\tAs PSR is enabled, DRRS is not enabled\n");
 			mutex_unlock(&drrs->mutex);
 			return;
 		}
@@ -4606,6 +4604,46 @@ static const struct file_operations i915_hpd_storm_ctl_fops = {
 	.write = i915_hpd_storm_ctl_write
 };
 
+static int i915_drrs_ctl_set(void *data, u64 val)
+{
+	struct drm_i915_private *dev_priv = data;
+	struct drm_device *dev = &dev_priv->drm;
+	struct intel_crtc *intel_crtc;
+	struct intel_encoder *encoder;
+	struct intel_dp *intel_dp;
+
+	if (INTEL_GEN(dev_priv) < 7)
+		return -ENODEV;
+
+	drm_modeset_lock_all(dev);
+	for_each_intel_crtc(dev, intel_crtc) {
+		if (!intel_crtc->base.state->active ||
+					!intel_crtc->config->has_drrs)
+			continue;
+
+		for_each_encoder_on_crtc(dev, &intel_crtc->base, encoder) {
+			if (encoder->type != INTEL_OUTPUT_EDP)
+				continue;
+
+			DRM_DEBUG_DRIVER("Manually %sabling DRRS. %llu\n",
+						val ? "en" : "dis", val);
+
+			intel_dp = enc_to_intel_dp(&encoder->base);
+			if (val)
+				intel_edp_drrs_enable(intel_dp,
+							intel_crtc->config);
+			else
+				intel_edp_drrs_disable(intel_dp,
+							intel_crtc->config);
+		}
+	}
+	drm_modeset_unlock_all(dev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_drrs_ctl_fops, NULL, i915_drrs_ctl_set, "%llu\n");
+
 static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_capabilities", i915_capabilities, 0},
 	{"i915_gem_objects", i915_gem_object_info, 0},
@@ -4683,7 +4721,8 @@ static const struct i915_debugfs_files {
 	{"i915_dp_test_active", &i915_displayport_test_active_fops},
 	{"i915_guc_log_control", &i915_guc_log_control_fops},
 	{"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops},
-	{"i915_ipc_status", &i915_ipc_status_fops}
+	{"i915_ipc_status", &i915_ipc_status_fops},
+	{"i915_drrs_ctl", &i915_drrs_ctl_fops}
 };
 
 int i915_debugfs_register(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6c8da9d20c33..e9f1daf258fe 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -55,6 +55,7 @@
 
 static struct drm_driver driver;
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 static unsigned int i915_load_fail_count;
 
 bool __i915_inject_load_failure(const char *func, int line)
@@ -70,6 +71,7 @@ bool __i915_inject_load_failure(const char *func, int line)
 
 	return false;
 }
+#endif
 
 #define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
 #define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
@@ -107,8 +109,12 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 
 static bool i915_error_injected(struct drm_i915_private *dev_priv)
 {
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 	return i915_modparams.inject_load_failure &&
 	       i915_load_fail_count == i915_modparams.inject_load_failure;
+#else
+	return false;
+#endif
 }
 
 #define i915_load_error(dev_priv, fmt, ...)				     \
@@ -176,96 +182,103 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 	 * of only checking the first one.
 	 */
 	while ((pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, pch))) {
-		if (pch->vendor == PCI_VENDOR_ID_INTEL) {
-			unsigned short id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
-
-			dev_priv->pch_id = id;
-
-			if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_IBX;
-				DRM_DEBUG_KMS("Found Ibex Peak PCH\n");
-				WARN_ON(!IS_GEN5(dev_priv));
-			} else if (id == INTEL_PCH_CPT_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_CPT;
-				DRM_DEBUG_KMS("Found CougarPoint PCH\n");
-				WARN_ON(!IS_GEN6(dev_priv) &&
-					!IS_IVYBRIDGE(dev_priv));
-			} else if (id == INTEL_PCH_PPT_DEVICE_ID_TYPE) {
-				/* PantherPoint is CPT compatible */
-				dev_priv->pch_type = PCH_CPT;
-				DRM_DEBUG_KMS("Found PantherPoint PCH\n");
-				WARN_ON(!IS_GEN6(dev_priv) &&
-					!IS_IVYBRIDGE(dev_priv));
-			} else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_LPT;
-				DRM_DEBUG_KMS("Found LynxPoint PCH\n");
-				WARN_ON(!IS_HASWELL(dev_priv) &&
-					!IS_BROADWELL(dev_priv));
-				WARN_ON(IS_HSW_ULT(dev_priv) ||
-					IS_BDW_ULT(dev_priv));
-			} else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_LPT;
-				DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
-				WARN_ON(!IS_HASWELL(dev_priv) &&
-					!IS_BROADWELL(dev_priv));
-				WARN_ON(!IS_HSW_ULT(dev_priv) &&
-					!IS_BDW_ULT(dev_priv));
-			} else if (id == INTEL_PCH_WPT_DEVICE_ID_TYPE) {
-				/* WildcatPoint is LPT compatible */
-				dev_priv->pch_type = PCH_LPT;
-				DRM_DEBUG_KMS("Found WildcatPoint PCH\n");
-				WARN_ON(!IS_HASWELL(dev_priv) &&
-					!IS_BROADWELL(dev_priv));
-				WARN_ON(IS_HSW_ULT(dev_priv) ||
-					IS_BDW_ULT(dev_priv));
-			} else if (id == INTEL_PCH_WPT_LP_DEVICE_ID_TYPE) {
-				/* WildcatPoint is LPT compatible */
-				dev_priv->pch_type = PCH_LPT;
-				DRM_DEBUG_KMS("Found WildcatPoint LP PCH\n");
-				WARN_ON(!IS_HASWELL(dev_priv) &&
-					!IS_BROADWELL(dev_priv));
-				WARN_ON(!IS_HSW_ULT(dev_priv) &&
-					!IS_BDW_ULT(dev_priv));
-			} else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_SPT;
-				DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
-				WARN_ON(!IS_SKYLAKE(dev_priv) &&
-					!IS_KABYLAKE(dev_priv));
-			} else if (id == INTEL_PCH_SPT_LP_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_SPT;
-				DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
-				WARN_ON(!IS_SKYLAKE(dev_priv) &&
-					!IS_KABYLAKE(dev_priv));
-			} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_KBP;
-				DRM_DEBUG_KMS("Found Kaby Lake PCH (KBP)\n");
-				WARN_ON(!IS_SKYLAKE(dev_priv) &&
-					!IS_KABYLAKE(dev_priv) &&
-					!IS_COFFEELAKE(dev_priv));
-			} else if (id == INTEL_PCH_CNP_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_CNP;
-				DRM_DEBUG_KMS("Found Cannon Lake PCH (CNP)\n");
-				WARN_ON(!IS_CANNONLAKE(dev_priv) &&
-					!IS_COFFEELAKE(dev_priv));
-			} else if (id == INTEL_PCH_CNP_LP_DEVICE_ID_TYPE) {
-				dev_priv->pch_type = PCH_CNP;
-				DRM_DEBUG_KMS("Found Cannon Lake LP PCH (CNP-LP)\n");
-				WARN_ON(!IS_CANNONLAKE(dev_priv) &&
-					!IS_COFFEELAKE(dev_priv));
-			} else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE ||
-				   id == INTEL_PCH_P3X_DEVICE_ID_TYPE ||
-				   (id == INTEL_PCH_QEMU_DEVICE_ID_TYPE &&
-				    pch->subsystem_vendor ==
-					    PCI_SUBVENDOR_ID_REDHAT_QUMRANET &&
-				    pch->subsystem_device ==
-					    PCI_SUBDEVICE_ID_QEMU)) {
-				dev_priv->pch_type =
-					intel_virt_detect_pch(dev_priv);
-			} else
-				continue;
-
-			break;
+		unsigned short id;
+
+		if (pch->vendor != PCI_VENDOR_ID_INTEL)
+			continue;
+
+		id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
+
+		dev_priv->pch_id = id;
+
+		if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_IBX;
+			DRM_DEBUG_KMS("Found Ibex Peak PCH\n");
+			WARN_ON(!IS_GEN5(dev_priv));
+		} else if (id == INTEL_PCH_CPT_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_CPT;
+			DRM_DEBUG_KMS("Found CougarPoint PCH\n");
+			WARN_ON(!IS_GEN6(dev_priv) &&
+				!IS_IVYBRIDGE(dev_priv));
+		} else if (id == INTEL_PCH_PPT_DEVICE_ID_TYPE) {
+			/* PantherPoint is CPT compatible */
+			dev_priv->pch_type = PCH_CPT;
+			DRM_DEBUG_KMS("Found PantherPoint PCH\n");
+			WARN_ON(!IS_GEN6(dev_priv) &&
+				!IS_IVYBRIDGE(dev_priv));
+		} else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_LPT;
+			DRM_DEBUG_KMS("Found LynxPoint PCH\n");
+			WARN_ON(!IS_HASWELL(dev_priv) &&
+				!IS_BROADWELL(dev_priv));
+			WARN_ON(IS_HSW_ULT(dev_priv) ||
+				IS_BDW_ULT(dev_priv));
+		} else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_LPT;
+			DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
+			WARN_ON(!IS_HASWELL(dev_priv) &&
+				!IS_BROADWELL(dev_priv));
+			WARN_ON(!IS_HSW_ULT(dev_priv) &&
+				!IS_BDW_ULT(dev_priv));
+		} else if (id == INTEL_PCH_WPT_DEVICE_ID_TYPE) {
+			/* WildcatPoint is LPT compatible */
+			dev_priv->pch_type = PCH_LPT;
+			DRM_DEBUG_KMS("Found WildcatPoint PCH\n");
+			WARN_ON(!IS_HASWELL(dev_priv) &&
+				!IS_BROADWELL(dev_priv));
+			WARN_ON(IS_HSW_ULT(dev_priv) ||
+				IS_BDW_ULT(dev_priv));
+		} else if (id == INTEL_PCH_WPT_LP_DEVICE_ID_TYPE) {
+			/* WildcatPoint is LPT compatible */
+			dev_priv->pch_type = PCH_LPT;
+			DRM_DEBUG_KMS("Found WildcatPoint LP PCH\n");
+			WARN_ON(!IS_HASWELL(dev_priv) &&
+				!IS_BROADWELL(dev_priv));
+			WARN_ON(!IS_HSW_ULT(dev_priv) &&
+				!IS_BDW_ULT(dev_priv));
+		} else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_SPT;
+			DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
+			WARN_ON(!IS_SKYLAKE(dev_priv) &&
+				!IS_KABYLAKE(dev_priv));
+		} else if (id == INTEL_PCH_SPT_LP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_SPT;
+			DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
+			WARN_ON(!IS_SKYLAKE(dev_priv) &&
+				!IS_KABYLAKE(dev_priv));
+		} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_KBP;
+			DRM_DEBUG_KMS("Found Kaby Lake PCH (KBP)\n");
+			WARN_ON(!IS_SKYLAKE(dev_priv) &&
+				!IS_KABYLAKE(dev_priv) &&
+				!IS_COFFEELAKE(dev_priv));
+		} else if (id == INTEL_PCH_CNP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_CNP;
+			DRM_DEBUG_KMS("Found Cannon Lake PCH (CNP)\n");
+			WARN_ON(!IS_CANNONLAKE(dev_priv) &&
+				!IS_COFFEELAKE(dev_priv));
+		} else if (id == INTEL_PCH_CNP_LP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_CNP;
+			DRM_DEBUG_KMS("Found Cannon Lake LP PCH (CNP-LP)\n");
+			WARN_ON(!IS_CANNONLAKE(dev_priv) &&
+				!IS_COFFEELAKE(dev_priv));
+		} else if (id == INTEL_PCH_ICP_DEVICE_ID_TYPE) {
+			dev_priv->pch_type = PCH_ICP;
+			DRM_DEBUG_KMS("Found Ice Lake PCH\n");
+			WARN_ON(!IS_ICELAKE(dev_priv));
+		} else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE ||
+			   id == INTEL_PCH_P3X_DEVICE_ID_TYPE ||
+			   (id == INTEL_PCH_QEMU_DEVICE_ID_TYPE &&
+			    pch->subsystem_vendor ==
+			    PCI_SUBVENDOR_ID_REDHAT_QUMRANET &&
+			    pch->subsystem_device ==
+			    PCI_SUBDEVICE_ID_QEMU)) {
+			dev_priv->pch_type = intel_virt_detect_pch(dev_priv);
+		} else {
+			continue;
 		}
+
+		break;
 	}
 	if (!pch)
 		DRM_DEBUG_KMS("No PCH found.\n");
@@ -622,7 +635,7 @@ static void i915_gem_fini(struct drm_i915_private *dev_priv)
 	i915_gem_contexts_fini(dev_priv);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	intel_uc_fini_wq(dev_priv);
+	intel_uc_fini_misc(dev_priv);
 	i915_gem_cleanup_userptr(dev_priv);
 
 	i915_gem_drain_freed_objects(dev_priv);
@@ -1842,6 +1855,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	if (IS_GEN9_LP(dev_priv) ||
 	    !(dev_priv->suspended_to_idle && dev_priv->csr.dmc_payload))
 		intel_power_domains_init_hw(dev_priv, true);
+	else
+		intel_display_set_init_power(dev_priv, true);
 
 	i915_gem_sanitize(dev_priv);
 
@@ -2594,6 +2609,11 @@ static int intel_runtime_suspend(struct device *kdev)
 
 		intel_runtime_pm_enable_interrupts(dev_priv);
 
+		intel_guc_resume(dev_priv);
+
+		i915_gem_init_swizzling(dev_priv);
+		i915_gem_restore_fences(dev_priv);
+
 		enable_rpm_wakeref_asserts(dev_priv);
 
 		return ret;
@@ -2659,8 +2679,6 @@ static int intel_runtime_resume(struct device *kdev)
 	if (intel_uncore_unclaimed_mmio(dev_priv))
 		DRM_DEBUG_DRIVER("Unclaimed access during suspend, bios?\n");
 
-	intel_guc_resume(dev_priv);
-
 	if (IS_GEN9_LP(dev_priv)) {
 		bxt_disable_dc9(dev_priv);
 		bxt_display_core_init(dev_priv, true);
@@ -2675,6 +2693,10 @@ static int intel_runtime_resume(struct device *kdev)
 
 	intel_uncore_runtime_resume(dev_priv);
 
+	intel_runtime_pm_enable_interrupts(dev_priv);
+
+	intel_guc_resume(dev_priv);
+
 	/*
 	 * No point of rolling back things in case of an error, as the best
 	 * we can do is to hope that things will still work (and disable RPM).
@@ -2682,8 +2704,6 @@ static int intel_runtime_resume(struct device *kdev)
 	i915_gem_init_swizzling(dev_priv);
 	i915_gem_restore_fences(dev_priv);
 
-	intel_runtime_pm_enable_interrupts(dev_priv);
-
 	/*
 	 * On VLV/CHV display interrupts are part of the display
 	 * power well, so hpd is reinitialized from there. For
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index caebd5825279..ad1fc845cd1b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -83,8 +83,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20171222"
-#define DRIVER_TIMESTAMP	1513971710
+#define DRIVER_DATE		"20180207"
+#define DRIVER_TIMESTAMP	1517988364
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
@@ -104,9 +104,13 @@
 #define I915_STATE_WARN_ON(x)						\
 	I915_STATE_WARN((x), "%s", "WARN_ON(" __stringify(x) ")")
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 bool __i915_inject_load_failure(const char *func, int line);
 #define i915_inject_load_failure() \
 	__i915_inject_load_failure(__func__, __LINE__)
+#else
+#define i915_inject_load_failure() false
+#endif
 
 typedef struct {
 	uint32_t val;
@@ -453,9 +457,9 @@ struct intel_display_error_state;
 
 struct i915_gpu_state {
 	struct kref ref;
-	struct timeval time;
-	struct timeval boottime;
-	struct timeval uptime;
+	ktime_t time;
+	ktime_t boottime;
+	ktime_t uptime;
 
 	struct drm_i915_private *i915;
 
@@ -551,6 +555,7 @@ struct i915_gpu_state {
 			int ban_score;
 			int active;
 			int guilty;
+			bool bannable;
 		} context;
 
 		struct drm_i915_error_object {
@@ -754,7 +759,6 @@ struct i915_drrs {
 struct i915_psr {
 	struct mutex lock;
 	bool sink_support;
-	bool source_ok;
 	struct intel_dp *enabled;
 	bool active;
 	struct delayed_work work;
@@ -783,6 +787,7 @@ enum intel_pch {
 	PCH_SPT,        /* Sunrisepoint PCH */
 	PCH_KBP,        /* Kaby Lake PCH */
 	PCH_CNP,        /* Cannon Lake PCH */
+	PCH_ICP,	/* Ice Lake PCH */
 	PCH_NOP,
 };
 
@@ -1255,6 +1260,7 @@ enum modeset_restore {
 #define DP_AUX_B 0x10
 #define DP_AUX_C 0x20
 #define DP_AUX_D 0x30
+#define DP_AUX_F 0x60
 
 #define DDC_PIN_B  0x05
 #define DDC_PIN_C  0x04
@@ -1281,6 +1287,7 @@ struct ddi_vbt_port_info {
 
 	uint8_t dp_boost_level;
 	uint8_t hdmi_boost_level;
+	int dp_max_link_rate;		/* 0 for not limited by VBT */
 };
 
 enum psr_lines_to_wait {
@@ -1460,6 +1467,7 @@ struct skl_wm_params {
 	uint_fixed_16_16_t plane_blocks_per_line;
 	uint_fixed_16_16_t y_tile_minimum;
 	uint32_t linetime_us;
+	uint32_t dbuf_block_size;
 };
 
 /*
@@ -1792,7 +1800,7 @@ struct i915_oa_ops {
 };
 
 struct intel_cdclk_state {
-	unsigned int cdclk, vco, ref;
+	unsigned int cdclk, vco, ref, bypass;
 	u8 voltage_level;
 };
 
@@ -2313,6 +2321,12 @@ struct drm_i915_private {
 		bool awake;
 
 		/**
+		 * The number of times we have woken up.
+		 */
+		unsigned int epoch;
+#define I915_EPOCH_INVALID 0
+
+		/**
 		 * We leave the user IRQ off as much as possible,
 		 * but this means that requests will finish and never
 		 * be retired once the system goes idle. Set a timer to
@@ -2404,16 +2418,11 @@ enum hdmi_force_audio {
  *
  * We have one bit per pipe and per scanout plane type.
  */
-#define INTEL_MAX_SPRITE_BITS_PER_PIPE 5
 #define INTEL_FRONTBUFFER_BITS_PER_PIPE 8
-#define INTEL_FRONTBUFFER_PRIMARY(pipe) \
-	(1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
-#define INTEL_FRONTBUFFER_CURSOR(pipe) \
-	(1 << (1 + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
-#define INTEL_FRONTBUFFER_SPRITE(pipe, plane) \
-	(1 << (2 + plane + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER(pipe, plane_id) \
+	(1 << ((plane_id) + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
 #define INTEL_FRONTBUFFER_OVERLAY(pipe) \
-	(1 << (2 + INTEL_MAX_SPRITE_BITS_PER_PIPE + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+	(1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE - 1 + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
 #define INTEL_FRONTBUFFER_ALL_MASK(pipe) \
 	(0xff << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
 
@@ -2595,6 +2604,7 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define IS_GEMINILAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_GEMINILAKE)
 #define IS_COFFEELAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_COFFEELAKE)
 #define IS_CANNONLAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_CANNONLAKE)
+#define IS_ICELAKE(dev_priv)	IS_PLATFORM(dev_priv, INTEL_ICELAKE)
 #define IS_MOBILE(dev_priv)	((dev_priv)->info.is_mobile)
 #define IS_HSW_EARLY_SDV(dev_priv) (IS_HASWELL(dev_priv) && \
 				    (INTEL_DEVID(dev_priv) & 0xFF00) == 0x0C00)
@@ -2646,6 +2656,8 @@ intel_info(const struct drm_i915_private *dev_priv)
 				 (dev_priv)->info.gt == 2)
 #define IS_CFL_GT3(dev_priv)	(IS_COFFEELAKE(dev_priv) && \
 				 (dev_priv)->info.gt == 3)
+#define IS_CNL_WITH_PORT_F(dev_priv)   (IS_CANNONLAKE(dev_priv) && \
+					(INTEL_DEVID(dev_priv) & 0x0004) == 0x0004)
 
 #define IS_ALPHA_SUPPORT(intel_info) ((intel_info)->is_alpha_support)
 
@@ -2706,6 +2718,7 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define IS_GEN8(dev_priv)	(!!((dev_priv)->info.gen_mask & BIT(7)))
 #define IS_GEN9(dev_priv)	(!!((dev_priv)->info.gen_mask & BIT(8)))
 #define IS_GEN10(dev_priv)	(!!((dev_priv)->info.gen_mask & BIT(9)))
+#define IS_GEN11(dev_priv)	(!!((dev_priv)->info.gen_mask & BIT(10)))
 
 #define IS_LP(dev_priv)	(INTEL_INFO(dev_priv)->is_lp)
 #define IS_GEN9_LP(dev_priv)	(IS_GEN9(dev_priv) && IS_LP(dev_priv))
@@ -2843,11 +2856,13 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define INTEL_PCH_KBP_DEVICE_ID_TYPE		0xA280
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
+#define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 #define INTEL_PCH_P3X_DEVICE_ID_TYPE		0x7000
 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE		0x2900 /* qemu q35 has 2918 */
 
 #define INTEL_PCH_TYPE(dev_priv) ((dev_priv)->pch_type)
+#define HAS_PCH_ICP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_ICP)
 #define HAS_PCH_CNP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_CNP)
 #define HAS_PCH_CNP_LP(dev_priv) \
 	((dev_priv)->pch_id == INTEL_PCH_CNP_LP_DEVICE_ID_TYPE)
@@ -2950,8 +2965,10 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 void intel_hpd_init(struct drm_i915_private *dev_priv);
 void intel_hpd_init_work(struct drm_i915_private *dev_priv);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
-enum port intel_hpd_pin_to_port(enum hpd_pin pin);
-enum hpd_pin intel_hpd_pin(enum port port);
+enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
+				enum hpd_pin pin);
+enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
+				   enum port port);
 bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
 void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
 
@@ -3644,6 +3661,7 @@ extern int intel_setup_gmbus(struct drm_i915_private *dev_priv);
 extern void intel_teardown_gmbus(struct drm_i915_private *dev_priv);
 extern bool intel_gmbus_is_valid_pin(struct drm_i915_private *dev_priv,
 				     unsigned int pin);
+extern int intel_gmbus_output_aksv(struct i2c_adapter *adapter);
 
 extern struct i2c_adapter *
 intel_gmbus_get_adapter(struct drm_i915_private *dev_priv, unsigned int pin);
@@ -3717,7 +3735,12 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct intel_display_error_state *error);
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val);
-int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val);
+int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv, u32 mbox,
+				    u32 val, int fast_timeout_us,
+				    int slow_timeout_ms);
+#define sandybridge_pcode_write(dev_priv, mbox, val)	\
+	sandybridge_pcode_write_timeout(dev_priv, mbox, val, 500, 0)
+
 int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 		      u32 reply_mask, u32 reply, int timeout_base_ms);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8bc3283484be..1632f18e6a64 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -369,7 +369,8 @@ i915_gem_object_wait_fence(struct dma_fence *fence,
 	if (i915_gem_request_completed(rq))
 		goto out;
 
-	/* This client is about to stall waiting for the GPU. In many cases
+	/*
+	 * This client is about to stall waiting for the GPU. In many cases
 	 * this is undesirable and limits the throughput of the system, as
 	 * many clients cannot continue processing user input/output whilst
 	 * blocked. RPS autotuning may take tens of milliseconds to respond
@@ -384,11 +385,9 @@ i915_gem_object_wait_fence(struct dma_fence *fence,
 	 * forcing the clocks too high for the whole system, we only allow
 	 * each client to waitboost once in a busy period.
 	 */
-	if (rps_client) {
+	if (rps_client && !i915_gem_request_started(rq)) {
 		if (INTEL_GEN(rq->i915) >= 6)
 			gen6_rps_boost(rq, rps_client);
-		else
-			rps_client = NULL;
 	}
 
 	timeout = i915_wait_request(rq, flags, timeout);
@@ -2824,24 +2823,23 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
-static bool ban_context(const struct i915_gem_context *ctx,
-			unsigned int score)
-{
-	return (i915_gem_context_is_bannable(ctx) &&
-		score >= CONTEXT_SCORE_BAN_THRESHOLD);
-}
-
 static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 {
-	unsigned int score;
 	bool banned;
 
 	atomic_inc(&ctx->guilty_count);
 
-	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
-	banned = ban_context(ctx, score);
-	DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
-			 ctx->name, score, yesno(banned));
+	banned = false;
+	if (i915_gem_context_is_bannable(ctx)) {
+		unsigned int score;
+
+		score = atomic_add_return(CONTEXT_SCORE_GUILTY,
+					  &ctx->ban_score);
+		banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+
+		DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
+				 ctx->name, score, yesno(banned));
+	}
 	if (!banned)
 		return;
 
@@ -3135,7 +3133,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 		 * an incoherent read by the CS (presumably stale TLB). An
 		 * empty request appears sufficient to paper over the glitch.
 		 */
-		if (list_empty(&engine->timeline->requests)) {
+		if (intel_engine_is_idle(engine)) {
 			struct drm_i915_gem_request *rq;
 
 			rq = i915_gem_request_alloc(engine,
@@ -3200,6 +3198,13 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	if (drm_debug & DRM_UT_DRIVER) {
+		struct drm_printer p = drm_debug_printer(__func__);
+
+		for_each_engine(engine, i915, id)
+			intel_engine_dump(engine, &p, "%s\n", engine->name);
+	}
+
 	/*
 	 * First, stop submission to hw, but do not yet complete requests by
 	 * rolling the global seqno forward (since this would complete requests
@@ -3323,15 +3328,73 @@ i915_gem_retire_work_handler(struct work_struct *work)
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	/* Keep the retire handler running until we are finally idle.
+	/*
+	 * Keep the retire handler running until we are finally idle.
 	 * We do not need to do this test under locking as in the worst-case
 	 * we queue the retire worker once too often.
 	 */
-	if (READ_ONCE(dev_priv->gt.awake)) {
-		i915_queue_hangcheck(dev_priv);
+	if (READ_ONCE(dev_priv->gt.awake))
 		queue_delayed_work(dev_priv->wq,
 				   &dev_priv->gt.retire_work,
 				   round_jiffies_up_relative(HZ));
+}
+
+static void shrink_caches(struct drm_i915_private *i915)
+{
+	/*
+	 * kmem_cache_shrink() discards empty slabs and reorders partially
+	 * filled slabs to prioritise allocating from the mostly full slabs,
+	 * with the aim of reducing fragmentation.
+	 */
+	kmem_cache_shrink(i915->priorities);
+	kmem_cache_shrink(i915->dependencies);
+	kmem_cache_shrink(i915->requests);
+	kmem_cache_shrink(i915->luts);
+	kmem_cache_shrink(i915->vmas);
+	kmem_cache_shrink(i915->objects);
+}
+
+struct sleep_rcu_work {
+	union {
+		struct rcu_head rcu;
+		struct work_struct work;
+	};
+	struct drm_i915_private *i915;
+	unsigned int epoch;
+};
+
+static inline bool
+same_epoch(struct drm_i915_private *i915, unsigned int epoch)
+{
+	/*
+	 * There is a small chance that the epoch wrapped since we started
+	 * sleeping. If we assume that epoch is at least a u32, then it will
+	 * take at least 2^32 * 100ms for it to wrap, or about 326 years.
+	 */
+	return epoch == READ_ONCE(i915->gt.epoch);
+}
+
+static void __sleep_work(struct work_struct *work)
+{
+	struct sleep_rcu_work *s = container_of(work, typeof(*s), work);
+	struct drm_i915_private *i915 = s->i915;
+	unsigned int epoch = s->epoch;
+
+	kfree(s);
+	if (same_epoch(i915, epoch))
+		shrink_caches(i915);
+}
+
+static void __sleep_rcu(struct rcu_head *rcu)
+{
+	struct sleep_rcu_work *s = container_of(rcu, typeof(*s), rcu);
+	struct drm_i915_private *i915 = s->i915;
+
+	if (same_epoch(i915, s->epoch)) {
+		INIT_WORK(&s->work, __sleep_work);
+		queue_work(i915->wq, &s->work);
+	} else {
+		kfree(s);
 	}
 }
 
@@ -3347,6 +3410,7 @@ i915_gem_idle_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv), gt.idle_work.work);
+	unsigned int epoch = I915_EPOCH_INVALID;
 	bool rearm_hangcheck;
 	ktime_t end;
 
@@ -3406,6 +3470,8 @@ i915_gem_idle_work_handler(struct work_struct *work)
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
 	dev_priv->gt.awake = false;
+	epoch = dev_priv->gt.epoch;
+	GEM_BUG_ON(epoch == I915_EPOCH_INVALID);
 	rearm_hangcheck = false;
 
 	if (INTEL_GEN(dev_priv) >= 6)
@@ -3422,6 +3488,23 @@ out_rearm:
 		GEM_BUG_ON(!dev_priv->gt.awake);
 		i915_queue_hangcheck(dev_priv);
 	}
+
+	/*
+	 * When we are idle, it is an opportune time to reap our caches.
+	 * However, we have many objects that utilise RCU and the ordered
+	 * i915->wq that this work is executing on. To try and flush any
+	 * pending frees now we are idle, we first wait for an RCU grace
+	 * period, and then queue a task (that will run last on the wq) to
+	 * shrink and re-optimize the caches.
+	 */
+	if (same_epoch(dev_priv, epoch)) {
+		struct sleep_rcu_work *s = kmalloc(sizeof(*s), GFP_KERNEL);
+		if (s) {
+			s->i915 = dev_priv;
+			s->epoch = epoch;
+			call_rcu(&s->rcu, __sleep_rcu);
+		}
+	}
 }
 
 void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
@@ -3567,7 +3650,7 @@ static int wait_for_engines(struct drm_i915_private *i915)
 
 			for_each_engine(engine, i915, id)
 				intel_engine_dump(engine, &p,
-						  "%s", engine->name);
+						  "%s\n", engine->name);
 		}
 
 		i915_gem_set_wedged(i915);
@@ -4699,7 +4782,8 @@ static void __i915_gem_free_work(struct work_struct *work)
 		container_of(work, struct drm_i915_private, mm.free_work);
 	struct llist_node *freed;
 
-	/* All file-owned VMA should have been released by this point through
+	/*
+	 * All file-owned VMA should have been released by this point through
 	 * i915_gem_close_object(), or earlier by i915_gem_context_close().
 	 * However, the object may also be bound into the global GTT (e.g.
 	 * older GPUs without per-process support, or for direct access through
@@ -4726,13 +4810,18 @@ static void __i915_gem_free_object_rcu(struct rcu_head *head)
 		container_of(head, typeof(*obj), rcu);
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-	/* We can't simply use call_rcu() from i915_gem_free_object()
-	 * as we need to block whilst unbinding, and the call_rcu
-	 * task may be called from softirq context. So we take a
-	 * detour through a worker.
+	/*
+	 * Since we require blocking on struct_mutex to unbind the freed
+	 * object from the GPU before releasing resources back to the
+	 * system, we can not do that directly from the RCU callback (which may
+	 * be a softirq context), but must instead then defer that work onto a
+	 * kthread. We use the RCU callback rather than move the freed object
+	 * directly onto the work queue so that we can mix between using the
+	 * worker and performing frees directly from subsequent allocations for
+	 * crude but effective memory throttling.
 	 */
 	if (llist_add(&obj->freed, &i915->mm.free_list))
-		schedule_work(&i915->mm.free_work);
+		queue_work(i915->wq, &i915->mm.free_work);
 }
 
 void i915_gem_free_object(struct drm_gem_object *gem_obj)
@@ -4745,7 +4834,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	if (discard_backing_storage(obj))
 		obj->mm.madv = I915_MADV_DONTNEED;
 
-	/* Before we free the object, make sure any pure RCU-only
+	/*
+	 * Before we free the object, make sure any pure RCU-only
 	 * read-side critical sections are complete, e.g.
 	 * i915_gem_busy_ioctl(). For the corresponding synchronized
 	 * lookup see i915_gem_object_lookup_rcu().
@@ -5187,7 +5277,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	ret = intel_uc_init_wq(dev_priv);
+	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;
 
@@ -5283,6 +5373,8 @@ err_unlock:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+	intel_uc_fini_misc(dev_priv);
+
 	if (ret != -EIO)
 		i915_gem_cleanup_userptr(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 012250f25255..b8338d75c6f3 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -230,10 +230,14 @@ static int fence_update(struct drm_i915_fence_reg *fence,
 	}
 
 	if (fence->vma) {
-		ret = i915_gem_active_retire(&fence->vma->last_fence,
-				      &fence->vma->obj->base.dev->struct_mutex);
+		struct i915_vma *old = fence->vma;
+
+		ret = i915_gem_active_retire(&old->last_fence,
+					     &old->obj->base.dev->struct_mutex);
 		if (ret)
 			return ret;
+
+		i915_vma_flush_writes(old);
 	}
 
 	if (fence->vma && fence->vma != vma) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c5f393870532..955ce7bee448 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -377,6 +377,7 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
 static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 {
 	struct pagevec *pvec = &vm->free_pages;
+	struct pagevec stash;
 
 	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
 		i915_gem_shrink_all(vm->i915);
@@ -395,7 +396,15 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 	if (likely(pvec->nr))
 		return pvec->pages[--pvec->nr];
 
-	/* Otherwise batch allocate pages to amoritize cost of set_pages_wc. */
+	/*
+	 * Otherwise batch allocate pages to amoritize cost of set_pages_wc.
+	 *
+	 * We have to be careful as page allocation may trigger the shrinker
+	 * (via direct reclaim) which will fill up the WC stash underneath us.
+	 * So we add our WB pages into a temporary pvec on the stack and merge
+	 * them into the WC stash after all the allocations are complete.
+	 */
+	pagevec_init(&stash);
 	do {
 		struct page *page;
 
@@ -403,15 +412,24 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			break;
 
-		pvec->pages[pvec->nr++] = page;
-	} while (pagevec_space(pvec));
+		stash.pages[stash.nr++] = page;
+	} while (stash.nr < pagevec_space(pvec));
 
-	if (unlikely(!pvec->nr))
-		return NULL;
+	if (stash.nr) {
+		int nr = min_t(int, stash.nr, pagevec_space(pvec));
+		struct page **pages = stash.pages + stash.nr - nr;
 
-	set_pages_array_wc(pvec->pages, pvec->nr);
+		if (nr && !set_pages_array_wc(pages, nr)) {
+			memcpy(pvec->pages + pvec->nr,
+			       pages, sizeof(pages[0]) * nr);
+			pvec->nr += nr;
+			stash.nr -= nr;
+		}
 
-	return pvec->pages[--pvec->nr];
+		pagevec_release(&stash);
+	}
+
+	return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL;
 }
 
 static void vm_free_pages_release(struct i915_address_space *vm,
@@ -525,9 +543,7 @@ static void fill_page_dma_32(struct i915_address_space *vm,
 static int
 setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 {
-	struct page *page = NULL;
-	dma_addr_t addr;
-	int order;
+	unsigned long size;
 
 	/*
 	 * In order to utilize 64K pages for an object with a size < 2M, we will
@@ -541,48 +557,47 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 	 * TODO: we should really consider write-protecting the scratch-page and
 	 * sharing between ppgtt
 	 */
+	size = I915_GTT_PAGE_SIZE_4K;
 	if (i915_vm_is_48bit(vm) &&
 	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
-		order = get_order(I915_GTT_PAGE_SIZE_64K);
-		page = alloc_pages(gfp | __GFP_ZERO | __GFP_NOWARN, order);
-		if (page) {
-			addr = dma_map_page(vm->dma, page, 0,
-					    I915_GTT_PAGE_SIZE_64K,
-					    PCI_DMA_BIDIRECTIONAL);
-			if (unlikely(dma_mapping_error(vm->dma, addr))) {
-				__free_pages(page, order);
-				page = NULL;
-			}
-
-			if (!IS_ALIGNED(addr, I915_GTT_PAGE_SIZE_64K)) {
-				dma_unmap_page(vm->dma, addr,
-					       I915_GTT_PAGE_SIZE_64K,
-					       PCI_DMA_BIDIRECTIONAL);
-				__free_pages(page, order);
-				page = NULL;
-			}
-		}
+		size = I915_GTT_PAGE_SIZE_64K;
+		gfp |= __GFP_NOWARN;
 	}
+	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
+
+	do {
+		int order = get_order(size);
+		struct page *page;
+		dma_addr_t addr;
 
-	if (!page) {
-		order = 0;
-		page = alloc_page(gfp | __GFP_ZERO);
+		page = alloc_pages(gfp, order);
 		if (unlikely(!page))
-			return -ENOMEM;
+			goto skip;
 
-		addr = dma_map_page(vm->dma, page, 0, PAGE_SIZE,
+		addr = dma_map_page(vm->dma, page, 0, size,
 				    PCI_DMA_BIDIRECTIONAL);
-		if (unlikely(dma_mapping_error(vm->dma, addr))) {
-			__free_page(page);
-			return -ENOMEM;
-		}
-	}
+		if (unlikely(dma_mapping_error(vm->dma, addr)))
+			goto free_page;
 
-	vm->scratch_page.page = page;
-	vm->scratch_page.daddr = addr;
-	vm->scratch_page.order = order;
+		if (unlikely(!IS_ALIGNED(addr, size)))
+			goto unmap_page;
 
-	return 0;
+		vm->scratch_page.page = page;
+		vm->scratch_page.daddr = addr;
+		vm->scratch_page.order = order;
+		return 0;
+
+unmap_page:
+		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
+free_page:
+		__free_pages(page, order);
+skip:
+		if (size == I915_GTT_PAGE_SIZE_4K)
+			return -ENOMEM;
+
+		size = I915_GTT_PAGE_SIZE_4K;
+		gfp &= ~__GFP_NOWARN;
+	} while (1);
 }
 
 static void cleanup_scratch_page(struct i915_address_space *vm)
@@ -1341,15 +1356,18 @@ static int gen8_ppgtt_alloc_pd(struct i915_address_space *vm,
 		int count = gen8_pte_count(start, length);
 
 		if (pt == vm->scratch_pt) {
+			pd->used_pdes++;
+
 			pt = alloc_pt(vm);
-			if (IS_ERR(pt))
+			if (IS_ERR(pt)) {
+				pd->used_pdes--;
 				goto unwind;
+			}
 
 			if (count < GEN8_PTES || intel_vgpu_active(vm->i915))
 				gen8_initialize_pt(vm, pt);
 
 			gen8_ppgtt_set_pde(vm, pd, pt, pde);
-			pd->used_pdes++;
 			GEM_BUG_ON(pd->used_pdes > I915_PDES);
 		}
 
@@ -1373,13 +1391,16 @@ static int gen8_ppgtt_alloc_pdp(struct i915_address_space *vm,
 
 	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
 		if (pd == vm->scratch_pd) {
+			pdp->used_pdpes++;
+
 			pd = alloc_pd(vm);
-			if (IS_ERR(pd))
+			if (IS_ERR(pd)) {
+				pdp->used_pdpes--;
 				goto unwind;
+			}
 
 			gen8_initialize_pd(vm, pd);
 			gen8_ppgtt_set_pdpe(vm, pdp, pd, pdpe);
-			pdp->used_pdpes++;
 			GEM_BUG_ON(pdp->used_pdpes > i915_pdpes_per_pdp(vm));
 
 			mark_tlbs_dirty(i915_vm_to_ppgtt(vm));
@@ -2287,12 +2308,23 @@ static void gen8_check_and_clear_faults(struct drm_i915_private *dev_priv)
 	u32 fault = I915_READ(GEN8_RING_FAULT_REG);
 
 	if (fault & RING_FAULT_VALID) {
+		u32 fault_data0, fault_data1;
+		u64 fault_addr;
+
+		fault_data0 = I915_READ(GEN8_FAULT_TLB_DATA0);
+		fault_data1 = I915_READ(GEN8_FAULT_TLB_DATA1);
+		fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) |
+			     ((u64)fault_data0 << 12);
+
 		DRM_DEBUG_DRIVER("Unexpected fault\n"
-				 "\tAddr: 0x%08lx\n"
+				 "\tAddr: 0x%08x_%08x\n"
+				 "\tAddress space: %s\n"
 				 "\tEngine ID: %d\n"
 				 "\tSource ID: %d\n"
 				 "\tType: %d\n",
-				 fault & PAGE_MASK,
+				 upper_32_bits(fault_addr),
+				 lower_32_bits(fault_addr),
+				 fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT",
 				 GEN8_RING_FAULT_ENGINE_ID(fault),
 				 RING_FAULT_SRCID(fault),
 				 RING_FAULT_FAULT_TYPE(fault));
@@ -2335,9 +2367,10 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
 	do {
-		if (dma_map_sg(&obj->base.dev->pdev->dev,
-			       pages->sgl, pages->nents,
-			       PCI_DMA_BIDIRECTIONAL))
+		if (dma_map_sg_attrs(&obj->base.dev->pdev->dev,
+				     pages->sgl, pages->nents,
+				     PCI_DMA_BIDIRECTIONAL,
+				     DMA_ATTR_NO_WARN))
 			return 0;
 
 		/* If the DMA remap fails, one cause can be that we have
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index d575109f7a7f..8efa9e7a9e46 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -161,12 +161,16 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
 
 	GEM_BUG_ON(!list_empty(&pt->link));
 
-	/* Everyone we depended upon (the fences we wait to be signaled)
+	/*
+	 * Everyone we depended upon (the fences we wait to be signaled)
 	 * should retire before us and remove themselves from our list.
 	 * However, retirement is run independently on each timeline and
 	 * so we may be called out-of-order.
 	 */
 	list_for_each_entry_safe(dep, next, &pt->signalers_list, signal_link) {
+		GEM_BUG_ON(!i915_priotree_signaled(dep->signaler));
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
 		list_del(&dep->wait_link);
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(i915, dep);
@@ -174,6 +178,9 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt)
 
 	/* Remove ourselves from everyone who depends upon us */
 	list_for_each_entry_safe(dep, next, &pt->waiters_list, wait_link) {
+		GEM_BUG_ON(dep->signaler != pt);
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
 		list_del(&dep->signal_link);
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(i915, dep);
@@ -267,6 +274,8 @@ static void mark_busy(struct drm_i915_private *i915)
 	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 
 	i915->gt.awake = true;
+	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
+		i915->gt.epoch = 1;
 
 	intel_enable_gt_powersave(i915);
 	i915_update_gfx_val(i915);
@@ -276,6 +285,8 @@ static void mark_busy(struct drm_i915_private *i915)
 
 	intel_engines_unpark(i915);
 
+	i915_queue_hangcheck(i915);
+
 	queue_delayed_work(i915->wq,
 			   &i915->gt.retire_work,
 			   round_jiffies_up_relative(HZ));
@@ -434,7 +445,10 @@ static void i915_gem_request_retire(struct drm_i915_gem_request *request)
 	spin_lock_irq(&request->lock);
 	if (request->waitboost)
 		atomic_dec(&request->i915->gt_pm.rps.num_waiters);
-	dma_fence_signal_locked(&request->fence);
+	if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags))
+		dma_fence_signal_locked(&request->fence);
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
+		intel_engine_cancel_signaling(request);
 	spin_unlock_irq(&request->lock);
 
 	i915_priotree_fini(request->i915, &request->priotree);
@@ -528,6 +542,8 @@ void __i915_gem_request_unsubmit(struct drm_i915_gem_request *request)
 	 */
 	GEM_BUG_ON(!request->global_seqno);
 	GEM_BUG_ON(request->global_seqno != engine->timeline->seqno);
+	GEM_BUG_ON(i915_seqno_passed(intel_engine_get_seqno(engine),
+				     request->global_seqno));
 	engine->timeline->seqno--;
 
 	/* We may be recursing from the signal callback of another i915 fence */
@@ -689,6 +705,17 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 		if (ret)
 			goto err_unreserve;
 
+		/*
+		 * We've forced the client to stall and catch up with whatever
+		 * backlog there might have been. As we are assuming that we
+		 * caused the mempressure, now is an opportune time to
+		 * recover as much memory from the request pool as is possible.
+		 * Having already penalized the client to stall, we spend
+		 * a little extra time to re-optimise page allocation.
+		 */
+		kmem_cache_shrink(dev_priv->requests);
+		rcu_barrier(); /* Recover the TYPESAFE_BY_RCU pages */
+
 		req = kmem_cache_alloc(dev_priv->requests, GFP_KERNEL);
 		if (!req) {
 			ret = -ENOMEM;
@@ -720,6 +747,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 
 	/* No zalloc, must clear what we need by hand */
 	req->global_seqno = 0;
+	req->signaling.wait.seqno = 0;
 	req->file_priv = NULL;
 	req->batch = NULL;
 	req->capture_list = NULL;
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index 0d6d39f19506..2236e9188c5c 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -245,18 +245,6 @@ i915_gem_request_put(struct drm_i915_gem_request *req)
 	dma_fence_put(&req->fence);
 }
 
-static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
-					   struct drm_i915_gem_request *src)
-{
-	if (src)
-		i915_gem_request_get(src);
-
-	if (*pdst)
-		i915_gem_request_put(*pdst);
-
-	*pdst = src;
-}
-
 /**
  * i915_gem_request_global_seqno - report the current global seqno
  * @request - the request
@@ -341,6 +329,27 @@ i915_gem_request_completed(const struct drm_i915_gem_request *req)
 	return __i915_gem_request_completed(req, seqno);
 }
 
+static inline bool
+i915_gem_request_started(const struct drm_i915_gem_request *req)
+{
+	u32 seqno;
+
+	seqno = i915_gem_request_global_seqno(req);
+	if (!seqno)
+		return false;
+
+	return i915_seqno_passed(intel_engine_get_seqno(req->engine),
+				 seqno - 1);
+}
+
+static inline bool i915_priotree_signaled(const struct i915_priotree *pt)
+{
+	const struct drm_i915_gem_request *rq =
+		container_of(pt, const struct drm_i915_gem_request, priotree);
+
+	return i915_gem_request_completed(rq);
+}
+
 /* We treat requests as fences. This is not be to confused with our
  * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
  * We use the fences to synchronize access from the CPU with activity on the
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 9029ed04879c..0e158f9287c4 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -363,13 +363,13 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_PURGEABLE);
-	if (freed < sc->nr_to_scan)
+	if (sc->nr_scanned < sc->nr_to_scan)
 		freed += i915_gem_shrink(i915,
 					 sc->nr_to_scan - sc->nr_scanned,
 					 &sc->nr_scanned,
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
-	if (freed < sc->nr_to_scan && current_is_kswapd()) {
+	if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
 		intel_runtime_pm_get(i915);
 		freed += i915_gem_shrink(i915,
 					 sc->nr_to_scan - sc->nr_scanned,
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 944059322daa..67c902412193 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -34,16 +34,25 @@
 
 #include "i915_drv.h"
 
-static const char *engine_str(int engine)
-{
-	switch (engine) {
-	case RCS: return "render";
-	case VCS: return "bsd";
-	case BCS: return "blt";
-	case VECS: return "vebox";
-	case VCS2: return "bsd2";
-	default: return "";
-	}
+static inline const struct intel_engine_cs *
+engine_lookup(const struct drm_i915_private *i915, unsigned int id)
+{
+	if (id >= I915_NUM_ENGINES)
+		return NULL;
+
+	return i915->engine[id];
+}
+
+static inline const char *
+__engine_name(const struct intel_engine_cs *engine)
+{
+	return engine ? engine->name : "";
+}
+
+static const char *
+engine_name(const struct drm_i915_private *i915, unsigned int id)
+{
+	return __engine_name(engine_lookup(i915, id));
 }
 
 static const char *tiling_flag(int tiling)
@@ -345,7 +354,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 		err_puts(m, purgeable_flag(err->purgeable));
 		err_puts(m, err->userptr ? " userptr" : "");
 		err_puts(m, err->engine != -1 ? " " : "");
-		err_puts(m, engine_str(err->engine));
+		err_puts(m, engine_name(m->i915, err->engine));
 		err_puts(m, i915_cache_level_str(m->i915, err->cache_level));
 
 		if (err->name)
@@ -387,6 +396,11 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 			   ee->instdone.row[slice][subslice]);
 }
 
+static const char *bannable(const struct drm_i915_error_context *ctx)
+{
+	return ctx->bannable ? "" : " (unbannable)";
+}
+
 static void error_print_request(struct drm_i915_error_state_buf *m,
 				const char *prefix,
 				const struct drm_i915_error_request *erq)
@@ -405,9 +419,10 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
 				const struct drm_i915_error_context *ctx)
 {
-	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d guilty %d active %d\n",
+	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d%s guilty %d active %d\n",
 		   header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
-		   ctx->priority, ctx->ban_score, ctx->guilty, ctx->active);
+		   ctx->priority, ctx->ban_score, bannable(ctx),
+		   ctx->guilty, ctx->active);
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
@@ -415,7 +430,8 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 {
 	int n;
 
-	err_printf(m, "%s command stream:\n", engine_str(ee->engine_id));
+	err_printf(m, "%s command stream:\n",
+		   engine_name(m->i915, ee->engine_id));
 	err_printf(m, "  IDLE?: %s\n", yesno(ee->idle));
 	err_printf(m, "  START: 0x%08x\n", ee->start);
 	err_printf(m, "  HEAD:  0x%08x [0x%08x]\n", ee->head, ee->rq_head);
@@ -610,6 +626,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 {
 	struct drm_i915_private *dev_priv = m->i915;
 	struct drm_i915_error_object *obj;
+	struct timespec64 ts;
 	int i, j;
 
 	if (!error) {
@@ -620,21 +637,25 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	if (*error->error_msg)
 		err_printf(m, "%s\n", error->error_msg);
 	err_printf(m, "Kernel: " UTS_RELEASE "\n");
-	err_printf(m, "Time: %ld s %ld us\n",
-		   error->time.tv_sec, error->time.tv_usec);
-	err_printf(m, "Boottime: %ld s %ld us\n",
-		   error->boottime.tv_sec, error->boottime.tv_usec);
-	err_printf(m, "Uptime: %ld s %ld us\n",
-		   error->uptime.tv_sec, error->uptime.tv_usec);
+	ts = ktime_to_timespec64(error->time);
+	err_printf(m, "Time: %lld s %ld us\n",
+		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
+	ts = ktime_to_timespec64(error->boottime);
+	err_printf(m, "Boottime: %lld s %ld us\n",
+		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
+	ts = ktime_to_timespec64(error->uptime);
+	err_printf(m, "Uptime: %lld s %ld us\n",
+		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
 
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_stalled &&
 		    error->engine[i].context.pid) {
-			err_printf(m, "Active process (on ring %s): %s [%d], score %d\n",
-				   engine_str(i),
+			err_printf(m, "Active process (on ring %s): %s [%d], score %d%s\n",
+				   engine_name(m->i915, i),
 				   error->engine[i].context.comm,
 				   error->engine[i].context.pid,
-				   error->engine[i].context.ban_score);
+				   error->engine[i].context.ban_score,
+				   bannable(&error->engine[i].context));
 		}
 	}
 	err_printf(m, "Reset count: %u\n", error->reset_count);
@@ -722,12 +743,13 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		if (obj) {
 			err_puts(m, dev_priv->engine[i]->name);
 			if (ee->context.pid)
-				err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d)",
+				err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d%s)",
 					   ee->context.comm,
 					   ee->context.pid,
 					   ee->context.handle,
 					   ee->context.hw_id,
-					   ee->context.ban_score);
+					   ee->context.ban_score,
+					   bannable(&ee->context));
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
@@ -1369,6 +1391,7 @@ static void record_context(struct drm_i915_error_context *e,
 	e->hw_id = ctx->hw_id;
 	e->priority = ctx->priority;
 	e->ban_score = atomic_read(&ctx->ban_score);
+	e->bannable = i915_gem_context_is_bannable(ctx);
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
 }
@@ -1737,11 +1760,10 @@ static int capture(void *data)
 {
 	struct i915_gpu_state *error = data;
 
-	do_gettimeofday(&error->time);
-	error->boottime = ktime_to_timeval(ktime_get_boottime());
-	error->uptime =
-		ktime_to_timeval(ktime_sub(ktime_get(),
-					   error->i915->gt.last_init_time));
+	error->time = ktime_get_real();
+	error->boottime = ktime_get_boottime();
+	error->uptime = ktime_sub(ktime_get(),
+				  error->i915->gt.last_init_time);
 
 	capture_params(error);
 	capture_uc_state(error);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3517c6548e2c..b886bd459acc 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -452,6 +452,8 @@ void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv)
 
 void gen9_reset_guc_interrupts(struct drm_i915_private *dev_priv)
 {
+	assert_rpm_wakelock_held(dev_priv);
+
 	spin_lock_irq(&dev_priv->irq_lock);
 	gen6_reset_pm_iir(dev_priv, dev_priv->pm_guc_events);
 	spin_unlock_irq(&dev_priv->irq_lock);
@@ -459,6 +461,8 @@ void gen9_reset_guc_interrupts(struct drm_i915_private *dev_priv)
 
 void gen9_enable_guc_interrupts(struct drm_i915_private *dev_priv)
 {
+	assert_rpm_wakelock_held(dev_priv);
+
 	spin_lock_irq(&dev_priv->irq_lock);
 	if (!dev_priv->guc.interrupts_enabled) {
 		WARN_ON_ONCE(I915_READ(gen6_pm_iir(dev_priv)) &
@@ -471,6 +475,8 @@ void gen9_enable_guc_interrupts(struct drm_i915_private *dev_priv)
 
 void gen9_disable_guc_interrupts(struct drm_i915_private *dev_priv)
 {
+	assert_rpm_wakelock_held(dev_priv);
+
 	spin_lock_irq(&dev_priv->irq_lock);
 	dev_priv->guc.interrupts_enabled = false;
 
@@ -1407,37 +1413,25 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
 		tasklet_hi_schedule(&execlists->tasklet);
 }
 
-static irqreturn_t gen8_gt_irq_ack(struct drm_i915_private *dev_priv,
-				   u32 master_ctl,
-				   u32 gt_iir[4])
+static void gen8_gt_irq_ack(struct drm_i915_private *dev_priv,
+			    u32 master_ctl, u32 gt_iir[4])
 {
-	irqreturn_t ret = IRQ_NONE;
-
 	if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
 		gt_iir[0] = I915_READ_FW(GEN8_GT_IIR(0));
-		if (gt_iir[0]) {
+		if (gt_iir[0])
 			I915_WRITE_FW(GEN8_GT_IIR(0), gt_iir[0]);
-			ret = IRQ_HANDLED;
-		} else
-			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
 
 	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
 		gt_iir[1] = I915_READ_FW(GEN8_GT_IIR(1));
-		if (gt_iir[1]) {
+		if (gt_iir[1])
 			I915_WRITE_FW(GEN8_GT_IIR(1), gt_iir[1]);
-			ret = IRQ_HANDLED;
-		} else
-			DRM_ERROR("The master control interrupt lied (GT1)!\n");
 	}
 
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
 		gt_iir[3] = I915_READ_FW(GEN8_GT_IIR(3));
-		if (gt_iir[3]) {
+		if (gt_iir[3])
 			I915_WRITE_FW(GEN8_GT_IIR(3), gt_iir[3]);
-			ret = IRQ_HANDLED;
-		} else
-			DRM_ERROR("The master control interrupt lied (GT3)!\n");
 	}
 
 	if (master_ctl & (GEN8_GT_PM_IRQ | GEN8_GT_GUC_IRQ)) {
@@ -1447,12 +1441,8 @@ static irqreturn_t gen8_gt_irq_ack(struct drm_i915_private *dev_priv,
 			I915_WRITE_FW(GEN8_GT_IIR(2),
 				      gt_iir[2] & (dev_priv->pm_rps_events |
 						   dev_priv->pm_guc_events));
-			ret = IRQ_HANDLED;
-		} else
-			DRM_ERROR("The master control interrupt lied (PM)!\n");
+		}
 	}
-
-	return ret;
 }
 
 static void gen8_gt_irq_handler(struct drm_i915_private *dev_priv,
@@ -1568,10 +1558,11 @@ static bool i9xx_port_hotplug_long_detect(enum port port, u32 val)
  *
  * Note that the caller is expected to zero out the masks initially.
  */
-static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
-			     u32 hotplug_trigger, u32 dig_hotplug_reg,
-			     const u32 hpd[HPD_NUM_PINS],
-			     bool long_pulse_detect(enum port port, u32 val))
+static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
+			       u32 *pin_mask, u32 *long_mask,
+			       u32 hotplug_trigger, u32 dig_hotplug_reg,
+			       const u32 hpd[HPD_NUM_PINS],
+			       bool long_pulse_detect(enum port port, u32 val))
 {
 	enum port port;
 	int i;
@@ -1582,7 +1573,7 @@ static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
 
 		*pin_mask |= BIT(i);
 
-		port = intel_hpd_pin_to_port(i);
+		port = intel_hpd_pin_to_port(dev_priv, i);
 		if (port == PORT_NONE)
 			continue;
 
@@ -1970,8 +1961,9 @@ static void i9xx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
 
 		if (hotplug_trigger) {
-			intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
-					   hotplug_trigger, hpd_status_g4x,
+			intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+					   hotplug_trigger, hotplug_trigger,
+					   hpd_status_g4x,
 					   i9xx_port_hotplug_long_detect);
 
 			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
@@ -1983,8 +1975,9 @@ static void i9xx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
 
 		if (hotplug_trigger) {
-			intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
-					   hotplug_trigger, hpd_status_i915,
+			intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+					   hotplug_trigger, hotplug_trigger,
+					   hpd_status_i915,
 					   i9xx_port_hotplug_long_detect);
 			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 		}
@@ -2185,7 +2178,7 @@ static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	if (!hotplug_trigger)
 		return;
 
-	intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   pch_port_hotplug_long_detect);
 
@@ -2327,8 +2320,8 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
 		I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
 
-		intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
-				   dig_hotplug_reg, hpd_spt,
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   hotplug_trigger, dig_hotplug_reg, hpd_spt,
 				   spt_port_hotplug_long_detect);
 	}
 
@@ -2338,8 +2331,8 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG2);
 		I915_WRITE(PCH_PORT_HOTPLUG2, dig_hotplug_reg);
 
-		intel_get_hpd_pins(&pin_mask, &long_mask, hotplug2_trigger,
-				   dig_hotplug_reg, hpd_spt,
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   hotplug2_trigger, dig_hotplug_reg, hpd_spt,
 				   spt_port_hotplug2_long_detect);
 	}
 
@@ -2359,7 +2352,7 @@ static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	dig_hotplug_reg = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL);
 	I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg);
 
-	intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   ilk_port_hotplug_long_detect);
 
@@ -2536,7 +2529,7 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
 	I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
 
-	intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+	intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   bxt_port_hotplug_long_detect);
 
@@ -2579,6 +2572,9 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 					    GEN9_AUX_CHANNEL_C |
 					    GEN9_AUX_CHANNEL_D;
 
+			if (IS_CNL_WITH_PORT_F(dev_priv))
+				tmp_mask |= CNL_AUX_CHANNEL_F;
+
 			if (iir & tmp_mask) {
 				dp_aux_irq_handler(dev_priv);
 				found = true;
@@ -2683,7 +2679,6 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 master_ctl;
 	u32 gt_iir[4] = {};
-	irqreturn_t ret;
 
 	if (!intel_irqs_enabled(dev_priv))
 		return IRQ_NONE;
@@ -2699,16 +2694,16 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	disable_rpm_wakeref_asserts(dev_priv);
 
 	/* Find, clear, then process each source of interrupt */
-	ret = gen8_gt_irq_ack(dev_priv, master_ctl, gt_iir);
+	gen8_gt_irq_ack(dev_priv, master_ctl, gt_iir);
 	gen8_gt_irq_handler(dev_priv, gt_iir);
-	ret |= gen8_de_irq_handler(dev_priv, master_ctl);
+	gen8_de_irq_handler(dev_priv, master_ctl);
 
 	I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
 	POSTING_READ_FW(GEN8_MASTER_IRQ);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 
-	return ret;
+	return IRQ_HANDLED;
 }
 
 struct wedge_me {
@@ -3611,6 +3606,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 		de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 	}
 
+	if (IS_CNL_WITH_PORT_F(dev_priv))
+		de_port_masked |= CNL_AUX_CHANNEL_F;
+
 	de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
 					   GEN8_PIPE_FIFO_UNDERRUN;
 
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index b5f3eb4fa8a3..08108ce5be21 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -155,7 +155,8 @@ i915_param_named_unsafe(enable_guc, int, 0400,
 	"(-1=auto, 0=disable [default], 1=GuC submission, 2=HuC load)");
 
 i915_param_named(guc_log_level, int, 0400,
-	"GuC firmware logging level (-1:disabled (default), 0-3:enabled)");
+	"GuC firmware logging level. Requires GuC to be loaded. "
+	"(-1=auto [default], 0=disable, 1..4=enable with verbosity min..max)");
 
 i915_param_named_unsafe(guc_firmware_path, charp, 0400,
 	"GuC firmware path to use instead of the default one");
@@ -166,8 +167,10 @@ i915_param_named_unsafe(huc_firmware_path, charp, 0400,
 i915_param_named_unsafe(enable_dp_mst, bool, 0600,
 	"Enable multi-stream transport (MST) for new DisplayPort sinks. (default: true)");
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 i915_param_named_unsafe(inject_load_failure, uint, 0400,
 	"Force an error after a number of failure check points (0:disabled (default), N:force failure at the Nth failure check point)");
+#endif
 
 i915_param_named(enable_dpcd_backlight, bool, 0600,
 	"Enable support for DPCD backlight control (default:false)");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index c96360398072..430f5f9d0ff4 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -48,7 +48,7 @@ struct drm_printer;
 	param(int, enable_ips, 1) \
 	param(int, invert_brightness, 0) \
 	param(int, enable_guc, 0) \
-	param(int, guc_log_level, -1) \
+	param(int, guc_log_level, 0) \
 	param(char *, guc_firmware_path, NULL) \
 	param(char *, huc_firmware_path, NULL) \
 	param(int, mmio_debug, 0) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 36d48422b475..4e7a10c89782 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -74,19 +74,19 @@
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i830_info __initconst = {
+static const struct intel_device_info intel_i830_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I830,
 	.is_mobile = 1, .cursor_needs_physical = 1,
 	.num_pipes = 2, /* legal, last one wins */
 };
 
-static const struct intel_device_info intel_i845g_info __initconst = {
+static const struct intel_device_info intel_i845g_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I845G,
 };
 
-static const struct intel_device_info intel_i85x_info __initconst = {
+static const struct intel_device_info intel_i85x_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I85X, .is_mobile = 1,
 	.num_pipes = 2, /* legal, last one wins */
@@ -94,7 +94,7 @@ static const struct intel_device_info intel_i85x_info __initconst = {
 	.has_fbc = 1,
 };
 
-static const struct intel_device_info intel_i865g_info __initconst = {
+static const struct intel_device_info intel_i865g_info = {
 	GEN2_FEATURES,
 	.platform = INTEL_I865G,
 };
@@ -108,7 +108,7 @@ static const struct intel_device_info intel_i865g_info __initconst = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i915g_info __initconst = {
+static const struct intel_device_info intel_i915g_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I915G, .cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
@@ -116,7 +116,7 @@ static const struct intel_device_info intel_i915g_info __initconst = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i915gm_info __initconst = {
+static const struct intel_device_info intel_i915gm_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I915GM,
 	.is_mobile = 1,
@@ -128,7 +128,7 @@ static const struct intel_device_info intel_i915gm_info __initconst = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945g_info __initconst = {
+static const struct intel_device_info intel_i945g_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I945G,
 	.has_hotplug = 1, .cursor_needs_physical = 1,
@@ -137,7 +137,7 @@ static const struct intel_device_info intel_i945g_info __initconst = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945gm_info __initconst = {
+static const struct intel_device_info intel_i945gm_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_I945GM, .is_mobile = 1,
 	.has_hotplug = 1, .cursor_needs_physical = 1,
@@ -148,14 +148,14 @@ static const struct intel_device_info intel_i945gm_info __initconst = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_g33_info __initconst = {
+static const struct intel_device_info intel_g33_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_G33,
 	.has_hotplug = 1,
 	.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_info __initconst = {
+static const struct intel_device_info intel_pineview_info = {
 	GEN3_FEATURES,
 	.platform = INTEL_PINEVIEW, .is_mobile = 1,
 	.has_hotplug = 1,
@@ -172,7 +172,7 @@ static const struct intel_device_info intel_pineview_info __initconst = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_i965g_info __initconst = {
+static const struct intel_device_info intel_i965g_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_I965G,
 	.has_overlay = 1,
@@ -180,7 +180,7 @@ static const struct intel_device_info intel_i965g_info __initconst = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_i965gm_info __initconst = {
+static const struct intel_device_info intel_i965gm_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_I965GM,
 	.is_mobile = 1, .has_fbc = 1,
@@ -190,13 +190,13 @@ static const struct intel_device_info intel_i965gm_info __initconst = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_g45_info __initconst = {
+static const struct intel_device_info intel_g45_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_G45,
 	.ring_mask = RENDER_RING | BSD_RING,
 };
 
-static const struct intel_device_info intel_gm45_info __initconst = {
+static const struct intel_device_info intel_gm45_info = {
 	GEN4_FEATURES,
 	.platform = INTEL_GM45,
 	.is_mobile = 1, .has_fbc = 1,
@@ -215,12 +215,12 @@ static const struct intel_device_info intel_gm45_info __initconst = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS
 
-static const struct intel_device_info intel_ironlake_d_info __initconst = {
+static const struct intel_device_info intel_ironlake_d_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
 };
 
-static const struct intel_device_info intel_ironlake_m_info __initconst = {
+static const struct intel_device_info intel_ironlake_m_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
 	.is_mobile = 1, .has_fbc = 1,
@@ -243,12 +243,12 @@ static const struct intel_device_info intel_ironlake_m_info __initconst = {
 	GEN6_FEATURES, \
 	.platform = INTEL_SANDYBRIDGE
 
-static const struct intel_device_info intel_sandybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt1_info = {
 	SNB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt2_info = {
 	SNB_D_PLATFORM,
 	.gt = 2,
 };
@@ -259,12 +259,12 @@ static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst =
 	.is_mobile = 1
 
 
-static const struct intel_device_info intel_sandybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt1_info = {
 	SNB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	SNB_M_PLATFORM,
 	.gt = 2,
 };
@@ -288,12 +288,12 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst =
 	.platform = INTEL_IVYBRIDGE, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt1_info = {
 	IVB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt2_info = {
 	IVB_D_PLATFORM,
 	.gt = 2,
 };
@@ -304,17 +304,17 @@ static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = {
 	.is_mobile = 1, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt1_info = {
 	IVB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt2_info = {
 	IVB_M_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_ivybridge_q_info __initconst = {
+static const struct intel_device_info intel_ivybridge_q_info = {
 	GEN7_FEATURES,
 	.platform = INTEL_IVYBRIDGE,
 	.gt = 2,
@@ -322,7 +322,7 @@ static const struct intel_device_info intel_ivybridge_q_info __initconst = {
 	.has_l3_dpf = 1,
 };
 
-static const struct intel_device_info intel_valleyview_info __initconst = {
+static const struct intel_device_info intel_valleyview_info = {
 	.platform = INTEL_VALLEYVIEW,
 	.gen = 7,
 	.is_lp = 1,
@@ -358,17 +358,17 @@ static const struct intel_device_info intel_valleyview_info __initconst = {
 	.platform = INTEL_HASWELL, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_haswell_gt1_info __initconst = {
+static const struct intel_device_info intel_haswell_gt1_info = {
 	HSW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_haswell_gt2_info __initconst = {
+static const struct intel_device_info intel_haswell_gt2_info = {
 	HSW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_haswell_gt3_info __initconst = {
+static const struct intel_device_info intel_haswell_gt3_info = {
 	HSW_PLATFORM,
 	.gt = 3,
 };
@@ -388,17 +388,17 @@ static const struct intel_device_info intel_haswell_gt3_info __initconst = {
 	.gen = 8, \
 	.platform = INTEL_BROADWELL
 
-static const struct intel_device_info intel_broadwell_gt1_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt1_info = {
 	BDW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_broadwell_gt2_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt2_info = {
 	BDW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_broadwell_rsvd_info __initconst = {
+static const struct intel_device_info intel_broadwell_rsvd_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	/* According to the device ID those devices are GT3, they were
@@ -406,13 +406,13 @@ static const struct intel_device_info intel_broadwell_rsvd_info __initconst = {
 	 */
 };
 
-static const struct intel_device_info intel_broadwell_gt3_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt3_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
 };
 
-static const struct intel_device_info intel_cherryview_info __initconst = {
+static const struct intel_device_info intel_cherryview_info = {
 	.gen = 8, .num_pipes = 3,
 	.has_hotplug = 1,
 	.is_lp = 1,
@@ -455,12 +455,12 @@ static const struct intel_device_info intel_cherryview_info __initconst = {
 	.gen = 9, \
 	.platform = INTEL_SKYLAKE
 
-static const struct intel_device_info intel_skylake_gt1_info __initconst = {
+static const struct intel_device_info intel_skylake_gt1_info = {
 	SKL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_skylake_gt2_info __initconst = {
+static const struct intel_device_info intel_skylake_gt2_info = {
 	SKL_PLATFORM,
 	.gt = 2,
 };
@@ -470,12 +470,12 @@ static const struct intel_device_info intel_skylake_gt2_info __initconst = {
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING
 
 
-static const struct intel_device_info intel_skylake_gt3_info __initconst = {
+static const struct intel_device_info intel_skylake_gt3_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 3,
 };
 
-static const struct intel_device_info intel_skylake_gt4_info __initconst = {
+static const struct intel_device_info intel_skylake_gt4_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 4,
 };
@@ -511,13 +511,13 @@ static const struct intel_device_info intel_skylake_gt4_info __initconst = {
 	IVB_CURSOR_OFFSETS, \
 	BDW_COLORS
 
-static const struct intel_device_info intel_broxton_info __initconst = {
+static const struct intel_device_info intel_broxton_info = {
 	GEN9_LP_FEATURES,
 	.platform = INTEL_BROXTON,
 	.ddb_size = 512,
 };
 
-static const struct intel_device_info intel_geminilake_info __initconst = {
+static const struct intel_device_info intel_geminilake_info = {
 	GEN9_LP_FEATURES,
 	.platform = INTEL_GEMINILAKE,
 	.ddb_size = 1024,
@@ -529,17 +529,17 @@ static const struct intel_device_info intel_geminilake_info __initconst = {
 	.gen = 9, \
 	.platform = INTEL_KABYLAKE
 
-static const struct intel_device_info intel_kabylake_gt1_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt1_info = {
 	KBL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_kabylake_gt2_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt2_info = {
 	KBL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_kabylake_gt3_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt3_info = {
 	KBL_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
@@ -550,17 +550,17 @@ static const struct intel_device_info intel_kabylake_gt3_info __initconst = {
 	.gen = 9, \
 	.platform = INTEL_COFFEELAKE
 
-static const struct intel_device_info intel_coffeelake_gt1_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt1_info = {
 	CFL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_coffeelake_gt2_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt2_info = {
 	CFL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_coffeelake_gt3_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt3_info = {
 	CFL_PLATFORM,
 	.gt = 3,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
@@ -571,7 +571,7 @@ static const struct intel_device_info intel_coffeelake_gt3_info __initconst = {
 	.ddb_size = 1024, \
 	GLK_COLORS
 
-static const struct intel_device_info intel_cannonlake_gt2_info __initconst = {
+static const struct intel_device_info intel_cannonlake_info = {
 	GEN10_FEATURES,
 	.is_alpha_support = 1,
 	.platform = INTEL_CANNONLAKE,
@@ -579,6 +579,19 @@ static const struct intel_device_info intel_cannonlake_gt2_info __initconst = {
 	.gt = 2,
 };
 
+#define GEN11_FEATURES \
+	GEN10_FEATURES, \
+	.gen = 11, \
+	.ddb_size = 2048, \
+	.has_csr = 0
+
+static const struct intel_device_info intel_icelake_11_info = {
+	GEN11_FEATURES,
+	.platform = INTEL_ICELAKE,
+	.is_alpha_support = 1,
+	.has_resource_streamer = 0,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
@@ -636,8 +649,7 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_CFL_U_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
-	INTEL_CNL_U_GT2_IDS(&intel_cannonlake_gt2_info),
-	INTEL_CNL_Y_GT2_IDS(&intel_cannonlake_gt2_info),
+	INTEL_CNL_IDS(&intel_cannonlake_info),
 	{0, 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index f0cfdece14ae..0be50e43507d 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -244,7 +244,7 @@
  * The two separate pointers let us decouple read()s from tail pointer aging.
  *
  * The tail pointers are checked and updated at a limited rate within a hrtimer
- * callback (the same callback that is used for delivering POLLIN events)
+ * callback (the same callback that is used for delivering EPOLLIN events)
  *
  * Initially the tails are marked invalid with %INVALID_TAIL_PTR which
  * indicates that an updated tail pointer is needed.
@@ -2292,13 +2292,13 @@ static ssize_t i915_perf_read(struct file *file,
 		mutex_unlock(&dev_priv->perf.lock);
 	}
 
-	/* We allow the poll checking to sometimes report false positive POLLIN
+	/* We allow the poll checking to sometimes report false positive EPOLLIN
 	 * events where we might actually report EAGAIN on read() if there's
 	 * not really any data available. In this situation though we don't
-	 * want to enter a busy loop between poll() reporting a POLLIN event
+	 * want to enter a busy loop between poll() reporting a EPOLLIN event
 	 * and read() returning -EAGAIN. Clearing the oa.pollin state here
 	 * effectively ensures we back off until the next hrtimer callback
-	 * before reporting another POLLIN event.
+	 * before reporting another EPOLLIN event.
 	 */
 	if (ret >= 0 || ret == -EAGAIN) {
 		/* Maybe make ->pollin per-stream state if we support multiple
@@ -2342,12 +2342,12 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  *
  * Returns: any poll events that are ready without sleeping
  */
-static unsigned int i915_perf_poll_locked(struct drm_i915_private *dev_priv,
+static __poll_t i915_perf_poll_locked(struct drm_i915_private *dev_priv,
 					  struct i915_perf_stream *stream,
 					  struct file *file,
 					  poll_table *wait)
 {
-	unsigned int events = 0;
+	__poll_t events = 0;
 
 	stream->ops->poll_wait(stream, file, wait);
 
@@ -2358,7 +2358,7 @@ static unsigned int i915_perf_poll_locked(struct drm_i915_private *dev_priv,
 	 * samples to read.
 	 */
 	if (dev_priv->perf.oa.pollin)
-		events |= POLLIN;
+		events |= EPOLLIN;
 
 	return events;
 }
@@ -2376,11 +2376,11 @@ static unsigned int i915_perf_poll_locked(struct drm_i915_private *dev_priv,
  *
  * Returns: any poll events that are ready without sleeping
  */
-static unsigned int i915_perf_poll(struct file *file, poll_table *wait)
+static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
 	struct i915_perf_stream *stream = file->private_data;
 	struct drm_i915_private *dev_priv = stream->dev_priv;
-	int ret;
+	__poll_t ret;
 
 	mutex_lock(&dev_priv->perf.lock);
 	ret = i915_perf_poll_locked(dev_priv, stream, file, wait);
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 55a8a1e29424..1c440460255d 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -285,28 +285,69 @@ static u64 count_interrupts(struct drm_i915_private *i915)
 	return sum;
 }
 
-static void i915_pmu_event_destroy(struct perf_event *event)
+static void engine_event_destroy(struct perf_event *event)
 {
-	WARN_ON(event->parent);
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+
+	engine = intel_engine_lookup_user(i915,
+					  engine_event_class(event),
+					  engine_event_instance(event));
+	if (WARN_ON_ONCE(!engine))
+		return;
+
+	if (engine_event_sample(event) == I915_SAMPLE_BUSY &&
+	    intel_engine_supports_stats(engine))
+		intel_disable_engine_stats(engine);
 }
 
-static int engine_event_init(struct perf_event *event)
+static void i915_pmu_event_destroy(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	WARN_ON(event->parent);
 
-	if (!intel_engine_lookup_user(i915, engine_event_class(event),
-				      engine_event_instance(event)))
-		return -ENODEV;
+	if (is_engine_event(event))
+		engine_event_destroy(event);
+}
 
-	switch (engine_event_sample(event)) {
+static int
+engine_event_status(struct intel_engine_cs *engine,
+		    enum drm_i915_pmu_engine_sample sample)
+{
+	switch (sample) {
 	case I915_SAMPLE_BUSY:
 	case I915_SAMPLE_WAIT:
 		break;
 	case I915_SAMPLE_SEMA:
+		if (INTEL_GEN(engine->i915) < 6)
+			return -ENODEV;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static int
+config_status(struct drm_i915_private *i915, u64 config)
+{
+	switch (config) {
+	case I915_PMU_ACTUAL_FREQUENCY:
+		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+			/* Requires a mutex for sampling! */
+			return -ENODEV;
+		/* Fall-through. */
+	case I915_PMU_REQUESTED_FREQUENCY:
 		if (INTEL_GEN(i915) < 6)
 			return -ENODEV;
 		break;
+	case I915_PMU_INTERRUPTS:
+		break;
+	case I915_PMU_RC6_RESIDENCY:
+		if (!HAS_RC6(i915))
+			return -ENODEV;
+		break;
 	default:
 		return -ENOENT;
 	}
@@ -314,6 +355,30 @@ static int engine_event_init(struct perf_event *event)
 	return 0;
 }
 
+static int engine_event_init(struct perf_event *event)
+{
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+	u8 sample;
+	int ret;
+
+	engine = intel_engine_lookup_user(i915, engine_event_class(event),
+					  engine_event_instance(event));
+	if (!engine)
+		return -ENODEV;
+
+	sample = engine_event_sample(event);
+	ret = engine_event_status(engine, sample);
+	if (ret)
+		return ret;
+
+	if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine))
+		ret = intel_enable_engine_stats(engine);
+
+	return ret;
+}
+
 static int i915_pmu_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -337,30 +402,10 @@ static int i915_pmu_event_init(struct perf_event *event)
 	if (!cpumask_test_cpu(event->cpu, &i915_pmu_cpumask))
 		return -EINVAL;
 
-	if (is_engine_event(event)) {
+	if (is_engine_event(event))
 		ret = engine_event_init(event);
-	} else {
-		ret = 0;
-		switch (event->attr.config) {
-		case I915_PMU_ACTUAL_FREQUENCY:
-			if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
-				 /* Requires a mutex for sampling! */
-				ret = -ENODEV;
-		case I915_PMU_REQUESTED_FREQUENCY:
-			if (INTEL_GEN(i915) < 6)
-				ret = -ENODEV;
-			break;
-		case I915_PMU_INTERRUPTS:
-			break;
-		case I915_PMU_RC6_RESIDENCY:
-			if (!HAS_RC6(i915))
-				ret = -ENODEV;
-			break;
-		default:
-			ret = -ENOENT;
-			break;
-		}
-	}
+	else
+		ret = config_status(i915, event->attr.config);
 	if (ret)
 		return ret;
 
@@ -387,7 +432,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		if (WARN_ON_ONCE(!engine)) {
 			/* Do nothing */
 		} else if (sample == I915_SAMPLE_BUSY &&
-			   engine->pmu.busy_stats) {
+			   intel_engine_supports_stats(engine)) {
 			val = ktime_to_ns(intel_engine_get_busy_time(engine));
 		} else {
 			val = engine->pmu.sample[sample].cur;
@@ -442,12 +487,6 @@ again:
 	local64_add(new - prev, &event->count);
 }
 
-static bool engine_needs_busy_stats(struct intel_engine_cs *engine)
-{
-	return intel_engine_supports_stats(engine) &&
-	       (engine->pmu.enable & BIT(I915_SAMPLE_BUSY));
-}
-
 static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -487,21 +526,7 @@ static void i915_pmu_enable(struct perf_event *event)
 
 		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
-		if (engine->pmu.enable_count[sample]++ == 0) {
-			/*
-			 * Enable engine busy stats tracking if needed or
-			 * alternatively cancel the scheduled disable.
-			 *
-			 * If the delayed disable was pending, cancel it and
-			 * in this case do not enable since it already is.
-			 */
-			if (engine_needs_busy_stats(engine) &&
-			    !engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = true;
-				if (!cancel_delayed_work(&engine->pmu.disable_busy_stats))
-					intel_enable_engine_stats(engine);
-			}
-		}
+		engine->pmu.enable_count[sample]++;
 	}
 
 	/*
@@ -514,14 +539,6 @@ static void i915_pmu_enable(struct perf_event *event)
 	spin_unlock_irqrestore(&i915->pmu.lock, flags);
 }
 
-static void __disable_busy_stats(struct work_struct *work)
-{
-	struct intel_engine_cs *engine =
-	       container_of(work, typeof(*engine), pmu.disable_busy_stats.work);
-
-	intel_disable_engine_stats(engine);
-}
-
 static void i915_pmu_disable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -545,26 +562,8 @@ static void i915_pmu_disable(struct perf_event *event)
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
 		 */
-		if (--engine->pmu.enable_count[sample] == 0) {
+		if (--engine->pmu.enable_count[sample] == 0)
 			engine->pmu.enable &= ~BIT(sample);
-			if (!engine_needs_busy_stats(engine) &&
-			    engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = false;
-				/*
-				 * We request a delayed disable to handle the
-				 * rapid on/off cycles on events, which can
-				 * happen when tools like perf stat start, in a
-				 * nicer way.
-				 *
-				 * In addition, this also helps with busy stats
-				 * accuracy with background CPU offline/online
-				 * migration events.
-				 */
-				queue_delayed_work(system_wq,
-						   &engine->pmu.disable_busy_stats,
-						   round_jiffies_up_relative(HZ));
-			}
-		}
 	}
 
 	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
@@ -657,52 +656,9 @@ static ssize_t i915_pmu_event_show(struct device *dev,
 	return sprintf(buf, "config=0x%lx\n", eattr->val);
 }
 
-#define I915_EVENT_ATTR(_name, _config) \
-	(&((struct i915_ext_attribute[]) { \
-		{ .attr = __ATTR(_name, 0444, i915_pmu_event_show, NULL), \
-		  .val = _config, } \
-	})[0].attr.attr)
-
-#define I915_EVENT_STR(_name, _str) \
-	(&((struct perf_pmu_events_attr[]) { \
-		{ .attr	     = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
-		  .id	     = 0, \
-		  .event_str = _str, } \
-	})[0].attr.attr)
-
-#define I915_EVENT(_name, _config, _unit) \
-	I915_EVENT_ATTR(_name, _config), \
-	I915_EVENT_STR(_name.unit, _unit)
-
-#define I915_ENGINE_EVENT(_name, _class, _instance, _sample) \
-	I915_EVENT_ATTR(_name, __I915_PMU_ENGINE(_class, _instance, _sample)), \
-	I915_EVENT_STR(_name.unit, "ns")
-
-#define I915_ENGINE_EVENTS(_name, _class, _instance) \
-	I915_ENGINE_EVENT(_name##_instance-busy, _class, _instance, I915_SAMPLE_BUSY), \
-	I915_ENGINE_EVENT(_name##_instance-sema, _class, _instance, I915_SAMPLE_SEMA), \
-	I915_ENGINE_EVENT(_name##_instance-wait, _class, _instance, I915_SAMPLE_WAIT)
-
-static struct attribute *i915_pmu_events_attrs[] = {
-	I915_ENGINE_EVENTS(rcs, I915_ENGINE_CLASS_RENDER, 0),
-	I915_ENGINE_EVENTS(bcs, I915_ENGINE_CLASS_COPY, 0),
-	I915_ENGINE_EVENTS(vcs, I915_ENGINE_CLASS_VIDEO, 0),
-	I915_ENGINE_EVENTS(vcs, I915_ENGINE_CLASS_VIDEO, 1),
-	I915_ENGINE_EVENTS(vecs, I915_ENGINE_CLASS_VIDEO_ENHANCE, 0),
-
-	I915_EVENT(actual-frequency,    I915_PMU_ACTUAL_FREQUENCY,    "MHz"),
-	I915_EVENT(requested-frequency, I915_PMU_REQUESTED_FREQUENCY, "MHz"),
-
-	I915_EVENT_ATTR(interrupts, I915_PMU_INTERRUPTS),
-
-	I915_EVENT(rc6-residency,   I915_PMU_RC6_RESIDENCY,   "ns"),
-
-	NULL,
-};
-
-static const struct attribute_group i915_pmu_events_attr_group = {
+static struct attribute_group i915_pmu_events_attr_group = {
 	.name = "events",
-	.attrs = i915_pmu_events_attrs,
+	/* Patch in attrs at runtime. */
 };
 
 static ssize_t
@@ -720,7 +676,7 @@ static struct attribute *i915_cpumask_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group i915_pmu_cpumask_attr_group = {
+static const struct attribute_group i915_pmu_cpumask_attr_group = {
 	.attrs = i915_cpumask_attrs,
 };
 
@@ -731,6 +687,193 @@ static const struct attribute_group *i915_pmu_attr_groups[] = {
 	NULL
 };
 
+#define __event(__config, __name, __unit) \
+{ \
+	.config = (__config), \
+	.name = (__name), \
+	.unit = (__unit), \
+}
+
+#define __engine_event(__sample, __name) \
+{ \
+	.sample = (__sample), \
+	.name = (__name), \
+}
+
+static struct i915_ext_attribute *
+add_i915_attr(struct i915_ext_attribute *attr, const char *name, u64 config)
+{
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = name;
+	attr->attr.attr.mode = 0444;
+	attr->attr.show = i915_pmu_event_show;
+	attr->val = config;
+
+	return ++attr;
+}
+
+static struct perf_pmu_events_attr *
+add_pmu_attr(struct perf_pmu_events_attr *attr, const char *name,
+	     const char *str)
+{
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = name;
+	attr->attr.attr.mode = 0444;
+	attr->attr.show = perf_event_sysfs_show;
+	attr->event_str = str;
+
+	return ++attr;
+}
+
+static struct attribute **
+create_event_attributes(struct drm_i915_private *i915)
+{
+	static const struct {
+		u64 config;
+		const char *name;
+		const char *unit;
+	} events[] = {
+		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"),
+		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"),
+		__event(I915_PMU_INTERRUPTS, "interrupts", NULL),
+		__event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"),
+	};
+	static const struct {
+		enum drm_i915_pmu_engine_sample sample;
+		char *name;
+	} engine_events[] = {
+		__engine_event(I915_SAMPLE_BUSY, "busy"),
+		__engine_event(I915_SAMPLE_SEMA, "sema"),
+		__engine_event(I915_SAMPLE_WAIT, "wait"),
+	};
+	unsigned int count = 0;
+	struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter;
+	struct i915_ext_attribute *i915_attr = NULL, *i915_iter;
+	struct attribute **attr = NULL, **attr_iter;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	unsigned int i;
+
+	/* Count how many counters we will be exposing. */
+	for (i = 0; i < ARRAY_SIZE(events); i++) {
+		if (!config_status(i915, events[i].config))
+			count++;
+	}
+
+	for_each_engine(engine, i915, id) {
+		for (i = 0; i < ARRAY_SIZE(engine_events); i++) {
+			if (!engine_event_status(engine,
+						 engine_events[i].sample))
+				count++;
+		}
+	}
+
+	/* Allocate attribute objects and table. */
+	i915_attr = kcalloc(count, sizeof(*i915_attr), GFP_KERNEL);
+	if (!i915_attr)
+		goto err_alloc;
+
+	pmu_attr = kcalloc(count, sizeof(*pmu_attr), GFP_KERNEL);
+	if (!pmu_attr)
+		goto err_alloc;
+
+	/* Max one pointer of each attribute type plus a termination entry. */
+	attr = kcalloc(count * 2 + 1, sizeof(*attr), GFP_KERNEL);
+	if (!attr)
+		goto err_alloc;
+
+	i915_iter = i915_attr;
+	pmu_iter = pmu_attr;
+	attr_iter = attr;
+
+	/* Initialize supported non-engine counters. */
+	for (i = 0; i < ARRAY_SIZE(events); i++) {
+		char *str;
+
+		if (config_status(i915, events[i].config))
+			continue;
+
+		str = kstrdup(events[i].name, GFP_KERNEL);
+		if (!str)
+			goto err;
+
+		*attr_iter++ = &i915_iter->attr.attr;
+		i915_iter = add_i915_attr(i915_iter, str, events[i].config);
+
+		if (events[i].unit) {
+			str = kasprintf(GFP_KERNEL, "%s.unit", events[i].name);
+			if (!str)
+				goto err;
+
+			*attr_iter++ = &pmu_iter->attr.attr;
+			pmu_iter = add_pmu_attr(pmu_iter, str, events[i].unit);
+		}
+	}
+
+	/* Initialize supported engine counters. */
+	for_each_engine(engine, i915, id) {
+		for (i = 0; i < ARRAY_SIZE(engine_events); i++) {
+			char *str;
+
+			if (engine_event_status(engine,
+						engine_events[i].sample))
+				continue;
+
+			str = kasprintf(GFP_KERNEL, "%s-%s",
+					engine->name, engine_events[i].name);
+			if (!str)
+				goto err;
+
+			*attr_iter++ = &i915_iter->attr.attr;
+			i915_iter =
+				add_i915_attr(i915_iter, str,
+					      __I915_PMU_ENGINE(engine->uabi_class,
+								engine->instance,
+								engine_events[i].sample));
+
+			str = kasprintf(GFP_KERNEL, "%s-%s.unit",
+					engine->name, engine_events[i].name);
+			if (!str)
+				goto err;
+
+			*attr_iter++ = &pmu_iter->attr.attr;
+			pmu_iter = add_pmu_attr(pmu_iter, str, "ns");
+		}
+	}
+
+	i915->pmu.i915_attr = i915_attr;
+	i915->pmu.pmu_attr = pmu_attr;
+
+	return attr;
+
+err:;
+	for (attr_iter = attr; *attr_iter; attr_iter++)
+		kfree((*attr_iter)->name);
+
+err_alloc:
+	kfree(attr);
+	kfree(i915_attr);
+	kfree(pmu_attr);
+
+	return NULL;
+}
+
+static void free_event_attributes(struct drm_i915_private *i915)
+{
+	struct attribute **attr_iter = i915_pmu_events_attr_group.attrs;
+
+	for (; *attr_iter; attr_iter++)
+		kfree((*attr_iter)->name);
+
+	kfree(i915_pmu_events_attr_group.attrs);
+	kfree(i915->pmu.i915_attr);
+	kfree(i915->pmu.pmu_attr);
+
+	i915_pmu_events_attr_group.attrs = NULL;
+	i915->pmu.i915_attr = NULL;
+	i915->pmu.pmu_attr = NULL;
+}
+
 static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
 	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
@@ -797,8 +940,6 @@ static void i915_pmu_unregister_cpuhp_state(struct drm_i915_private *i915)
 
 void i915_pmu_register(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	int ret;
 
 	if (INTEL_GEN(i915) <= 2) {
@@ -806,6 +947,12 @@ void i915_pmu_register(struct drm_i915_private *i915)
 		return;
 	}
 
+	i915_pmu_events_attr_group.attrs = create_event_attributes(i915);
+	if (!i915_pmu_events_attr_group.attrs) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
 	i915->pmu.base.attr_groups	= i915_pmu_attr_groups;
 	i915->pmu.base.task_ctx_nr	= perf_invalid_context;
 	i915->pmu.base.event_init	= i915_pmu_event_init;
@@ -820,10 +967,6 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&i915->pmu.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	i915->pmu.timer.function = i915_sample;
 
-	for_each_engine(engine, i915, id)
-		INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats,
-				  __disable_busy_stats);
-
 	ret = perf_pmu_register(&i915->pmu.base, "i915", -1);
 	if (ret)
 		goto err;
@@ -838,14 +981,12 @@ err_unreg:
 	perf_pmu_unregister(&i915->pmu.base);
 err:
 	i915->pmu.base.event_init = NULL;
+	free_event_attributes(i915);
 	DRM_NOTE("Failed to register PMU! (err=%d)\n", ret);
 }
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
 	if (!i915->pmu.base.event_init)
 		return;
 
@@ -853,13 +994,9 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	hrtimer_cancel(&i915->pmu.timer);
 
-	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(engine->pmu.busy_stats);
-		flush_delayed_work(&engine->pmu.disable_busy_stats);
-	}
-
 	i915_pmu_unregister_cpuhp_state(i915);
 
 	perf_pmu_unregister(&i915->pmu.base);
 	i915->pmu.base.event_init = NULL;
+	free_event_attributes(i915);
 }
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 40c154d13565..5a2e013a56bb 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -94,6 +94,14 @@ struct i915_pmu {
 	 * struct intel_engine_cs.
 	 */
 	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
+	/**
+	 * @i915_attr: Memory block holding device attributes.
+	 */
+	void *i915_attr;
+	/**
+	 * @pmu_attr: Memory block holding device attributes.
+	 */
+	void *pmu_attr;
 };
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 505c605eff98..e9c79b560823 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1304,6 +1304,7 @@ enum i915_power_well_id {
 	SKL_DISP_PW_DDI_B,
 	SKL_DISP_PW_DDI_C,
 	SKL_DISP_PW_DDI_D,
+	CNL_DISP_PW_DDI_F = 6,
 
 	GLK_DISP_PW_AUX_A = 8,
 	GLK_DISP_PW_AUX_B,
@@ -1312,6 +1313,7 @@ enum i915_power_well_id {
 	CNL_DISP_PW_AUX_B = GLK_DISP_PW_AUX_B,
 	CNL_DISP_PW_AUX_C = GLK_DISP_PW_AUX_C,
 	CNL_DISP_PW_AUX_D,
+	CNL_DISP_PW_AUX_F,
 
 	SKL_DISP_PW_1 = 14,
 	SKL_DISP_PW_2,
@@ -1963,7 +1965,7 @@ enum i915_power_well_id {
 #define _CNL_PORT_TX_DW2_LN0_B		0x162648
 #define _CNL_PORT_TX_DW2_LN0_C		0x162C48
 #define _CNL_PORT_TX_DW2_LN0_D		0x162E48
-#define _CNL_PORT_TX_DW2_LN0_F		0x162A48
+#define _CNL_PORT_TX_DW2_LN0_F		0x162848
 #define CNL_PORT_TX_DW2_GRP(port)	_MMIO_PORT6(port, \
 						    _CNL_PORT_TX_DW2_GRP_AE, \
 						    _CNL_PORT_TX_DW2_GRP_B, \
@@ -2489,6 +2491,8 @@ enum i915_power_well_id {
 
 #define GEN8_FAULT_TLB_DATA0		_MMIO(0x4b10)
 #define GEN8_FAULT_TLB_DATA1		_MMIO(0x4b14)
+#define   FAULT_VA_HIGH_BITS		(0xf << 0)
+#define   FAULT_GTT_SEL			(1 << 4)
 
 #define FPGA_DBG		_MMIO(0x42300)
 #define   FPGA_DBG_RM_NOCLAIM	(1<<31)
@@ -2588,6 +2592,8 @@ enum i915_power_well_id {
 #define   GFX_FORWARD_VBLANK_ALWAYS	(1<<5)
 #define   GFX_FORWARD_VBLANK_COND	(2<<5)
 
+#define   GEN11_GFX_DISABLE_LEGACY_MODE	(1<<3)
+
 #define VLV_DISPLAY_BASE 0x180000
 #define VLV_MIPI_BASE VLV_DISPLAY_BASE
 #define BXT_MIPI_BASE 0x60000
@@ -2646,6 +2652,31 @@ enum i915_power_well_id {
 #define LM_FIFO_WATERMARK   0x0000001F
 #define MI_ARB_STATE	_MMIO(0x20e4) /* 915+ only */
 
+#define MBUS_ABOX_CTL			_MMIO(0x45038)
+#define MBUS_ABOX_BW_CREDIT_MASK	(3 << 20)
+#define MBUS_ABOX_BW_CREDIT(x)		((x) << 20)
+#define MBUS_ABOX_B_CREDIT_MASK		(0xF << 16)
+#define MBUS_ABOX_B_CREDIT(x)		((x) << 16)
+#define MBUS_ABOX_BT_CREDIT_POOL2_MASK	(0x1F << 8)
+#define MBUS_ABOX_BT_CREDIT_POOL2(x)	((x) << 8)
+#define MBUS_ABOX_BT_CREDIT_POOL1_MASK	(0x1F << 0)
+#define MBUS_ABOX_BT_CREDIT_POOL1(x)	((x) << 0)
+
+#define _PIPEA_MBUS_DBOX_CTL		0x7003C
+#define _PIPEB_MBUS_DBOX_CTL		0x7103C
+#define PIPE_MBUS_DBOX_CTL(pipe)	_MMIO_PIPE(pipe, _PIPEA_MBUS_DBOX_CTL, \
+						   _PIPEB_MBUS_DBOX_CTL)
+#define MBUS_DBOX_BW_CREDIT_MASK	(3 << 14)
+#define MBUS_DBOX_BW_CREDIT(x)		((x) << 14)
+#define MBUS_DBOX_B_CREDIT_MASK		(0x1F << 8)
+#define MBUS_DBOX_B_CREDIT(x)		((x) << 8)
+#define MBUS_DBOX_A_CREDIT_MASK		(0xF << 0)
+#define MBUS_DBOX_A_CREDIT(x)		((x) << 0)
+
+#define MBUS_UBOX_CTL			_MMIO(0x4503C)
+#define MBUS_BBOX_CTL_S1		_MMIO(0x45040)
+#define MBUS_BBOX_CTL_S2		_MMIO(0x45044)
+
 /* Make render/texture TLB fetches lower priorty than associated data
  *   fetches. This is not turned on by default
  */
@@ -3043,6 +3074,7 @@ enum i915_power_well_id {
 # define GPIO_DATA_PULLUP_DISABLE	(1 << 13)
 
 #define GMBUS0			_MMIO(dev_priv->gpio_mmio_base + 0x5100) /* clock/port select */
+#define   GMBUS_AKSV_SELECT	(1<<11)
 #define   GMBUS_RATE_100KHZ	(0<<8)
 #define   GMBUS_RATE_50KHZ	(1<<8)
 #define   GMBUS_RATE_400KHZ	(2<<8) /* reserved on Pineview */
@@ -3061,7 +3093,12 @@ enum i915_power_well_id {
 #define   GMBUS_PIN_2_BXT	2
 #define   GMBUS_PIN_3_BXT	3
 #define   GMBUS_PIN_4_CNP	4
-#define   GMBUS_NUM_PINS	7 /* including 0 */
+#define   GMBUS_PIN_9_TC1_ICP	9
+#define   GMBUS_PIN_10_TC2_ICP	10
+#define   GMBUS_PIN_11_TC3_ICP	11
+#define   GMBUS_PIN_12_TC4_ICP	12
+
+#define   GMBUS_NUM_PINS	13 /* including 0 */
 #define GMBUS1			_MMIO(dev_priv->gpio_mmio_base + 0x5104) /* command/status */
 #define   GMBUS_SW_CLR_INT	(1<<31)
 #define   GMBUS_SW_RDY		(1<<30)
@@ -4064,7 +4101,7 @@ enum {
 #define EDP_PSR_AUX_CTL				_MMIO(dev_priv->psr_mmio_base + 0x10)
 #define EDP_PSR_AUX_DATA(i)			_MMIO(dev_priv->psr_mmio_base + 0x14 + (i) * 4) /* 5 registers */
 
-#define EDP_PSR_STATUS_CTL			_MMIO(dev_priv->psr_mmio_base + 0x40)
+#define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
 #define   EDP_PSR_STATUS_STATE_MASK		(7<<29)
 #define   EDP_PSR_STATUS_STATE_IDLE		(0<<29)
 #define   EDP_PSR_STATUS_STATE_SRDONACK		(1<<29)
@@ -4091,7 +4128,7 @@ enum {
 #define EDP_PSR_PERF_CNT		_MMIO(dev_priv->psr_mmio_base + 0x44)
 #define   EDP_PSR_PERF_CNT_MASK		0xffffff
 
-#define EDP_PSR_DEBUG_CTL		_MMIO(dev_priv->psr_mmio_base + 0x60)
+#define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60)
 #define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1<<28)
 #define   EDP_PSR_DEBUG_MASK_LPSP              (1<<27)
 #define   EDP_PSR_DEBUG_MASK_MEMUP             (1<<26)
@@ -4114,7 +4151,7 @@ enum {
 #define   EDP_PSR2_IDLE_MASK		0xf
 #define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a)<<4)
 
-#define EDP_PSR2_STATUS_CTL            _MMIO(0x6f940)
+#define EDP_PSR2_STATUS			_MMIO(0x6f940)
 #define EDP_PSR2_STATUS_STATE_MASK     (0xf<<28)
 #define EDP_PSR2_STATUS_STATE_SHIFT    28
 
@@ -5276,6 +5313,13 @@ enum {
 #define _DPD_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64320)
 #define _DPD_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64324)
 
+#define _DPF_AUX_CH_CTL		(dev_priv->info.display_mmio_offset + 0x64510)
+#define _DPF_AUX_CH_DATA1	(dev_priv->info.display_mmio_offset + 0x64514)
+#define _DPF_AUX_CH_DATA2	(dev_priv->info.display_mmio_offset + 0x64518)
+#define _DPF_AUX_CH_DATA3	(dev_priv->info.display_mmio_offset + 0x6451c)
+#define _DPF_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64520)
+#define _DPF_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64524)
+
 #define DP_AUX_CH_CTL(port)	_MMIO_PORT(port, _DPA_AUX_CH_CTL, _DPB_AUX_CH_CTL)
 #define DP_AUX_CH_DATA(port, i)	_MMIO(_PORT(port, _DPA_AUX_CH_DATA1, _DPB_AUX_CH_DATA1) + (i) * 4) /* 5 registers */
 
@@ -6308,6 +6352,11 @@ enum {
 #define _PLANE_CTL_3_A				0x70380
 #define   PLANE_CTL_ENABLE			(1 << 31)
 #define   PLANE_CTL_PIPE_GAMMA_ENABLE		(1 << 30)   /* Pre-GLK */
+/*
+ * ICL+ uses the same PLANE_CTL_FORMAT bits, but the field definition
+ * expanded to include bit 23 as well. However, the shift-24 based values
+ * correctly map to the same formats in ICL, as long as bit 23 is set to 0
+ */
 #define   PLANE_CTL_FORMAT_MASK			(0xf << 24)
 #define   PLANE_CTL_FORMAT_YUV422		(  0 << 24)
 #define   PLANE_CTL_FORMAT_NV12			(  1 << 24)
@@ -6317,6 +6366,7 @@ enum {
 #define   PLANE_CTL_FORMAT_AYUV			(  8 << 24)
 #define   PLANE_CTL_FORMAT_INDEXED		( 12 << 24)
 #define   PLANE_CTL_FORMAT_RGB_565		( 14 << 24)
+#define   ICL_PLANE_CTL_FORMAT_MASK		(0x1f << 23)
 #define   PLANE_CTL_PIPE_CSC_ENABLE		(1 << 23) /* Pre-GLK */
 #define   PLANE_CTL_KEY_ENABLE_MASK		(0x3 << 21)
 #define   PLANE_CTL_KEY_ENABLE_SOURCE		(  1 << 21)
@@ -6931,6 +6981,7 @@ enum {
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
 #define GEN8_DE_PORT_IIR _MMIO(0x44448)
 #define GEN8_DE_PORT_IER _MMIO(0x4444c)
+#define  CNL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
 #define  GEN9_AUX_CHANNEL_B		(1 << 25)
@@ -6955,6 +7006,69 @@ enum {
 #define GEN8_PCU_IIR _MMIO(0x444e8)
 #define GEN8_PCU_IER _MMIO(0x444ec)
 
+#define GEN11_GFX_MSTR_IRQ		_MMIO(0x190010)
+#define  GEN11_MASTER_IRQ		(1 << 31)
+#define  GEN11_PCU_IRQ			(1 << 30)
+#define  GEN11_DISPLAY_IRQ		(1 << 16)
+#define  GEN11_GT_DW_IRQ(x)		(1 << (x))
+#define  GEN11_GT_DW1_IRQ		(1 << 1)
+#define  GEN11_GT_DW0_IRQ		(1 << 0)
+
+#define GEN11_DISPLAY_INT_CTL		_MMIO(0x44200)
+#define  GEN11_DISPLAY_IRQ_ENABLE	(1 << 31)
+#define  GEN11_AUDIO_CODEC_IRQ		(1 << 24)
+#define  GEN11_DE_PCH_IRQ		(1 << 23)
+#define  GEN11_DE_MISC_IRQ		(1 << 22)
+#define  GEN11_DE_PORT_IRQ		(1 << 20)
+#define  GEN11_DE_PIPE_C		(1 << 18)
+#define  GEN11_DE_PIPE_B		(1 << 17)
+#define  GEN11_DE_PIPE_A		(1 << 16)
+
+#define GEN11_GT_INTR_DW0		_MMIO(0x190018)
+#define  GEN11_CSME			(31)
+#define  GEN11_GUNIT			(28)
+#define  GEN11_GUC			(25)
+#define  GEN11_WDPERF			(20)
+#define  GEN11_KCR			(19)
+#define  GEN11_GTPM			(16)
+#define  GEN11_BCS			(15)
+#define  GEN11_RCS0			(0)
+
+#define GEN11_GT_INTR_DW1		_MMIO(0x19001c)
+#define  GEN11_VECS(x)			(31 - (x))
+#define  GEN11_VCS(x)			(x)
+
+#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + (x * 4))
+
+#define GEN11_INTR_IDENTITY_REG0	_MMIO(0x190060)
+#define GEN11_INTR_IDENTITY_REG1	_MMIO(0x190064)
+#define  GEN11_INTR_DATA_VALID		(1 << 31)
+#define  GEN11_INTR_ENGINE_MASK		(0xffff)
+
+#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + (x * 4))
+
+#define GEN11_IIR_REG0_SELECTOR		_MMIO(0x190070)
+#define GEN11_IIR_REG1_SELECTOR		_MMIO(0x190074)
+
+#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + (x * 4))
+
+#define GEN11_RENDER_COPY_INTR_ENABLE	_MMIO(0x190030)
+#define GEN11_VCS_VECS_INTR_ENABLE	_MMIO(0x190034)
+#define GEN11_GUC_SG_INTR_ENABLE	_MMIO(0x190038)
+#define GEN11_GPM_WGBOXPERF_INTR_ENABLE	_MMIO(0x19003c)
+#define GEN11_CRYPTO_RSVD_INTR_ENABLE	_MMIO(0x190040)
+#define GEN11_GUNIT_CSME_INTR_ENABLE	_MMIO(0x190044)
+
+#define GEN11_RCS0_RSVD_INTR_MASK	_MMIO(0x190090)
+#define GEN11_BCS_RSVD_INTR_MASK	_MMIO(0x1900a0)
+#define GEN11_VCS0_VCS1_INTR_MASK	_MMIO(0x1900a8)
+#define GEN11_VCS2_VCS3_INTR_MASK	_MMIO(0x1900ac)
+#define GEN11_VECS0_VECS1_INTR_MASK	_MMIO(0x1900d0)
+#define GEN11_GUC_SG_INTR_MASK		_MMIO(0x1900e8)
+#define GEN11_GPM_WGBOXPERF_INTR_MASK	_MMIO(0x1900ec)
+#define GEN11_CRYPTO_RSVD_INTR_MASK	_MMIO(0x1900f0)
+#define GEN11_GUNIT_CSME_INTR_MASK	_MMIO(0x1900f4)
+
 #define ILK_DISPLAY_CHICKEN2	_MMIO(0x42004)
 /* Required on all Ironlake and Sandybridge according to the B-Spec. */
 #define  ILK_ELPIN_409_SELECT	(1 << 25)
@@ -7009,8 +7123,12 @@ enum {
 #define CHICKEN_TRANS_A         0x420c0
 #define CHICKEN_TRANS_B         0x420c4
 #define CHICKEN_TRANS(trans) _MMIO_TRANS(trans, CHICKEN_TRANS_A, CHICKEN_TRANS_B)
-#define PSR2_VSC_ENABLE_PROG_HEADER    (1<<12)
-#define PSR2_ADD_VERTICAL_LINE_COUNT   (1<<15)
+#define  DDI_TRAINING_OVERRIDE_ENABLE	(1<<19)
+#define  DDI_TRAINING_OVERRIDE_VALUE	(1<<18)
+#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1<<17) /* CHICKEN_TRANS_A only */
+#define  DDIE_TRAINING_OVERRIDE_VALUE	(1<<16) /* CHICKEN_TRANS_A only */
+#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1<<15)
+#define  PSR2_VSC_ENABLE_PROG_HEADER    (1<<12)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
 #define  DISP_FBC_MEMORY_WAKE		(1<<31)
@@ -7349,6 +7467,8 @@ enum {
 #define  CNP_RAWCLK_DIV(div)	((div) << 16)
 #define  CNP_RAWCLK_FRAC_MASK	(0xf << 26)
 #define  CNP_RAWCLK_FRAC(frac)	((frac) << 26)
+#define  ICP_RAWCLK_DEN(den)	((den) << 26)
+#define  ICP_RAWCLK_NUM(num)	((num) << 11)
 
 #define PCH_DPLL_TMR_CFG        _MMIO(0xc6208)
 
@@ -8046,6 +8166,7 @@ enum {
 #define     GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT	8
 #define     GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT	16
 #define     GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT	24
+#define   SKL_PCODE_LOAD_HDCP_KEYS		0x5
 #define   SKL_PCODE_CDCLK_CONTROL		0x7
 #define     SKL_CDCLK_PREPARE_FOR_CHANGE	0x3
 #define     SKL_CDCLK_READY_FOR_CHANGE		0x1
@@ -8348,6 +8469,101 @@ enum skl_power_gate {
 #define  SKL_PW_TO_PG(pw)			((pw) - SKL_DISP_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
 
+#define _CNL_AUX_REG_IDX(pw)		((pw) - 9)
+#define _CNL_AUX_ANAOVRD1_B		0x162250
+#define _CNL_AUX_ANAOVRD1_C		0x162210
+#define _CNL_AUX_ANAOVRD1_D		0x1622D0
+#define _CNL_AUX_ANAOVRD1_F		0x162A90
+#define CNL_AUX_ANAOVRD1(pw)		_MMIO(_PICK(_CNL_AUX_REG_IDX(pw), \
+						    _CNL_AUX_ANAOVRD1_B, \
+						    _CNL_AUX_ANAOVRD1_C, \
+						    _CNL_AUX_ANAOVRD1_D, \
+						    _CNL_AUX_ANAOVRD1_F))
+#define   CNL_AUX_ANAOVRD1_ENABLE	(1<<16)
+#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1<<23)
+
+/* HDCP Key Registers */
+#define HDCP_KEY_CONF			_MMIO(0x66c00)
+#define  HDCP_AKSV_SEND_TRIGGER		BIT(31)
+#define  HDCP_CLEAR_KEYS_TRIGGER	BIT(30)
+#define  HDCP_KEY_LOAD_TRIGGER		BIT(8)
+#define HDCP_KEY_STATUS			_MMIO(0x66c04)
+#define  HDCP_FUSE_IN_PROGRESS		BIT(7)
+#define  HDCP_FUSE_ERROR		BIT(6)
+#define  HDCP_FUSE_DONE			BIT(5)
+#define  HDCP_KEY_LOAD_STATUS		BIT(1)
+#define  HDCP_KEY_LOAD_DONE		BIT(0)
+#define HDCP_AKSV_LO			_MMIO(0x66c10)
+#define HDCP_AKSV_HI			_MMIO(0x66c14)
+
+/* HDCP Repeater Registers */
+#define HDCP_REP_CTL			_MMIO(0x66d00)
+#define  HDCP_DDIB_REP_PRESENT		BIT(30)
+#define  HDCP_DDIA_REP_PRESENT		BIT(29)
+#define  HDCP_DDIC_REP_PRESENT		BIT(28)
+#define  HDCP_DDID_REP_PRESENT		BIT(27)
+#define  HDCP_DDIF_REP_PRESENT		BIT(26)
+#define  HDCP_DDIE_REP_PRESENT		BIT(25)
+#define  HDCP_DDIB_SHA1_M0		(1 << 20)
+#define  HDCP_DDIA_SHA1_M0		(2 << 20)
+#define  HDCP_DDIC_SHA1_M0		(3 << 20)
+#define  HDCP_DDID_SHA1_M0		(4 << 20)
+#define  HDCP_DDIF_SHA1_M0		(5 << 20)
+#define  HDCP_DDIE_SHA1_M0		(6 << 20) /* Bspec says 5? */
+#define  HDCP_SHA1_BUSY			BIT(16)
+#define  HDCP_SHA1_READY		BIT(17)
+#define  HDCP_SHA1_COMPLETE		BIT(18)
+#define  HDCP_SHA1_V_MATCH		BIT(19)
+#define  HDCP_SHA1_TEXT_32		(1 << 1)
+#define  HDCP_SHA1_COMPLETE_HASH	(2 << 1)
+#define  HDCP_SHA1_TEXT_24		(4 << 1)
+#define  HDCP_SHA1_TEXT_16		(5 << 1)
+#define  HDCP_SHA1_TEXT_8		(6 << 1)
+#define  HDCP_SHA1_TEXT_0		(7 << 1)
+#define HDCP_SHA_V_PRIME_H0		_MMIO(0x66d04)
+#define HDCP_SHA_V_PRIME_H1		_MMIO(0x66d08)
+#define HDCP_SHA_V_PRIME_H2		_MMIO(0x66d0C)
+#define HDCP_SHA_V_PRIME_H3		_MMIO(0x66d10)
+#define HDCP_SHA_V_PRIME_H4		_MMIO(0x66d14)
+#define HDCP_SHA_V_PRIME(h)		_MMIO((0x66d04 + h * 4))
+#define HDCP_SHA_TEXT			_MMIO(0x66d18)
+
+/* HDCP Auth Registers */
+#define _PORTA_HDCP_AUTHENC		0x66800
+#define _PORTB_HDCP_AUTHENC		0x66500
+#define _PORTC_HDCP_AUTHENC		0x66600
+#define _PORTD_HDCP_AUTHENC		0x66700
+#define _PORTE_HDCP_AUTHENC		0x66A00
+#define _PORTF_HDCP_AUTHENC		0x66900
+#define _PORT_HDCP_AUTHENC(port, x)	_MMIO(_PICK(port, \
+					  _PORTA_HDCP_AUTHENC, \
+					  _PORTB_HDCP_AUTHENC, \
+					  _PORTC_HDCP_AUTHENC, \
+					  _PORTD_HDCP_AUTHENC, \
+					  _PORTE_HDCP_AUTHENC, \
+					  _PORTF_HDCP_AUTHENC) + x)
+#define PORT_HDCP_CONF(port)		_PORT_HDCP_AUTHENC(port, 0x0)
+#define  HDCP_CONF_CAPTURE_AN		BIT(0)
+#define  HDCP_CONF_AUTH_AND_ENC		(BIT(1) | BIT(0))
+#define PORT_HDCP_ANINIT(port)		_PORT_HDCP_AUTHENC(port, 0x4)
+#define PORT_HDCP_ANLO(port)		_PORT_HDCP_AUTHENC(port, 0x8)
+#define PORT_HDCP_ANHI(port)		_PORT_HDCP_AUTHENC(port, 0xC)
+#define PORT_HDCP_BKSVLO(port)		_PORT_HDCP_AUTHENC(port, 0x10)
+#define PORT_HDCP_BKSVHI(port)		_PORT_HDCP_AUTHENC(port, 0x14)
+#define PORT_HDCP_RPRIME(port)		_PORT_HDCP_AUTHENC(port, 0x18)
+#define PORT_HDCP_STATUS(port)		_PORT_HDCP_AUTHENC(port, 0x1C)
+#define  HDCP_STATUS_STREAM_A_ENC	BIT(31)
+#define  HDCP_STATUS_STREAM_B_ENC	BIT(30)
+#define  HDCP_STATUS_STREAM_C_ENC	BIT(29)
+#define  HDCP_STATUS_STREAM_D_ENC	BIT(28)
+#define  HDCP_STATUS_AUTH		BIT(21)
+#define  HDCP_STATUS_ENC		BIT(20)
+#define  HDCP_STATUS_RI_MATCH		BIT(19)
+#define  HDCP_STATUS_R0_READY		BIT(18)
+#define  HDCP_STATUS_AN_READY		BIT(17)
+#define  HDCP_STATUS_CIPHER		BIT(16)
+#define  HDCP_STATUS_FRAME_CNT(x)	((x >> 8) & 0xff)
+
 /* Per-pipe DDI Function Control */
 #define _TRANS_DDI_FUNC_CTL_A		0x60400
 #define _TRANS_DDI_FUNC_CTL_B		0x61400
@@ -8379,6 +8595,7 @@ enum skl_power_gate {
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4<<12)
 #define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5<<12)
 #define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6<<12)
+#define  TRANS_DDI_HDCP_SIGNALLING	(1<<9)
 #define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1<<8)
 #define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1<<7)
 #define  TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ (1<<6)
@@ -8661,10 +8878,12 @@ enum skl_power_gate {
  * CNL Clocks
  */
 #define DPCLKA_CFGCR0				_MMIO(0x6C200)
-#define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port)+10))
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)	(3 << ((port)*2))
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port)*2)
-#define  DPCLKA_CFGCR0_DDI_CLK_SEL(pll, port)	((pll) << ((port)*2))
+#define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port) ==  PORT_F ? 23 : \
+						      (port)+10))
+#define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port) == PORT_F ? 21 : \
+						(port)*2)
+#define  DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)	(3 << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
+#define  DPCLKA_CFGCR0_DDI_CLK_SEL(pll, port)	((pll) << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
 
 /* CNL PLL */
 #define DPLL0_ENABLE		0x46010
@@ -8760,6 +8979,7 @@ enum skl_power_gate {
 #define  SFUSE_STRAP_RAW_FREQUENCY	(1<<8)
 #define  SFUSE_STRAP_DISPLAY_DISABLED	(1<<7)
 #define  SFUSE_STRAP_CRT_DISABLED	(1<<6)
+#define  SFUSE_STRAP_DDIF_DETECTED	(1<<3)
 #define  SFUSE_STRAP_DDIB_DETECTED	(1<<2)
 #define  SFUSE_STRAP_DDIC_DETECTED	(1<<1)
 #define  SFUSE_STRAP_DDID_DETECTED	(1<<0)
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 3669f5eeb91e..1de5173e53a2 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -365,18 +365,31 @@ int i915_sw_fence_await_sw_fence_gfp(struct i915_sw_fence *fence,
 struct i915_sw_dma_fence_cb {
 	struct dma_fence_cb base;
 	struct i915_sw_fence *fence;
+};
+
+struct i915_sw_dma_fence_cb_timer {
+	struct i915_sw_dma_fence_cb base;
 	struct dma_fence *dma;
 	struct timer_list timer;
 	struct irq_work work;
 	struct rcu_head rcu;
 };
 
+static void dma_i915_sw_fence_wake(struct dma_fence *dma,
+				   struct dma_fence_cb *data)
+{
+	struct i915_sw_dma_fence_cb *cb = container_of(data, typeof(*cb), base);
+
+	i915_sw_fence_complete(cb->fence);
+	kfree(cb);
+}
+
 static void timer_i915_sw_fence_wake(struct timer_list *t)
 {
-	struct i915_sw_dma_fence_cb *cb = from_timer(cb, t, timer);
+	struct i915_sw_dma_fence_cb_timer *cb = from_timer(cb, t, timer);
 	struct i915_sw_fence *fence;
 
-	fence = xchg(&cb->fence, NULL);
+	fence = xchg(&cb->base.fence, NULL);
 	if (!fence)
 		return;
 
@@ -388,13 +401,14 @@ static void timer_i915_sw_fence_wake(struct timer_list *t)
 	i915_sw_fence_complete(fence);
 }
 
-static void dma_i915_sw_fence_wake(struct dma_fence *dma,
-				   struct dma_fence_cb *data)
+static void dma_i915_sw_fence_wake_timer(struct dma_fence *dma,
+					 struct dma_fence_cb *data)
 {
-	struct i915_sw_dma_fence_cb *cb = container_of(data, typeof(*cb), base);
+	struct i915_sw_dma_fence_cb_timer *cb =
+		container_of(data, typeof(*cb), base.base);
 	struct i915_sw_fence *fence;
 
-	fence = xchg(&cb->fence, NULL);
+	fence = xchg(&cb->base.fence, NULL);
 	if (fence)
 		i915_sw_fence_complete(fence);
 
@@ -403,7 +417,8 @@ static void dma_i915_sw_fence_wake(struct dma_fence *dma,
 
 static void irq_i915_sw_fence_work(struct irq_work *wrk)
 {
-	struct i915_sw_dma_fence_cb *cb = container_of(wrk, typeof(*cb), work);
+	struct i915_sw_dma_fence_cb_timer *cb =
+		container_of(wrk, typeof(*cb), work);
 
 	del_timer_sync(&cb->timer);
 	dma_fence_put(cb->dma);
@@ -417,6 +432,7 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 				  gfp_t gfp)
 {
 	struct i915_sw_dma_fence_cb *cb;
+	dma_fence_func_t func;
 	int ret;
 
 	debug_fence_assert(fence);
@@ -425,7 +441,10 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 	if (dma_fence_is_signaled(dma))
 		return 0;
 
-	cb = kmalloc(sizeof(*cb), gfp);
+	cb = kmalloc(timeout ?
+		     sizeof(struct i915_sw_dma_fence_cb_timer) :
+		     sizeof(struct i915_sw_dma_fence_cb),
+		     gfp);
 	if (!cb) {
 		if (!gfpflags_allow_blocking(gfp))
 			return -ENOMEM;
@@ -436,19 +455,26 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 	cb->fence = fence;
 	i915_sw_fence_await(fence);
 
-	cb->dma = NULL;
-	timer_setup(&cb->timer, timer_i915_sw_fence_wake, TIMER_IRQSAFE);
-	init_irq_work(&cb->work, irq_i915_sw_fence_work);
+	func = dma_i915_sw_fence_wake;
 	if (timeout) {
-		cb->dma = dma_fence_get(dma);
-		mod_timer(&cb->timer, round_jiffies_up(jiffies + timeout));
+		struct i915_sw_dma_fence_cb_timer *timer =
+			container_of(cb, typeof(*timer), base);
+
+		timer->dma = dma_fence_get(dma);
+		init_irq_work(&timer->work, irq_i915_sw_fence_work);
+
+		timer_setup(&timer->timer,
+			    timer_i915_sw_fence_wake, TIMER_IRQSAFE);
+		mod_timer(&timer->timer, round_jiffies_up(jiffies + timeout));
+
+		func = dma_i915_sw_fence_wake_timer;
 	}
 
-	ret = dma_fence_add_callback(dma, &cb->base, dma_i915_sw_fence_wake);
+	ret = dma_fence_add_callback(dma, &cb->base, func);
 	if (ret == 0) {
 		ret = 1;
 	} else {
-		dma_i915_sw_fence_wake(dma, &cb->base);
+		func(dma, &cb->base);
 		if (ret == -ENOENT) /* fence already signaled */
 			ret = 0;
 	}
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index c74a20b80182..b33d2158c234 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -445,13 +445,13 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	return ret ?: count;
 }
 
-static DEVICE_ATTR(gt_act_freq_mhz, S_IRUGO, gt_act_freq_mhz_show, NULL);
-static DEVICE_ATTR(gt_cur_freq_mhz, S_IRUGO, gt_cur_freq_mhz_show, NULL);
-static DEVICE_ATTR(gt_boost_freq_mhz, S_IRUGO | S_IWUSR, gt_boost_freq_mhz_show, gt_boost_freq_mhz_store);
-static DEVICE_ATTR(gt_max_freq_mhz, S_IRUGO | S_IWUSR, gt_max_freq_mhz_show, gt_max_freq_mhz_store);
-static DEVICE_ATTR(gt_min_freq_mhz, S_IRUGO | S_IWUSR, gt_min_freq_mhz_show, gt_min_freq_mhz_store);
+static DEVICE_ATTR_RO(gt_act_freq_mhz);
+static DEVICE_ATTR_RO(gt_cur_freq_mhz);
+static DEVICE_ATTR_RW(gt_boost_freq_mhz);
+static DEVICE_ATTR_RW(gt_max_freq_mhz);
+static DEVICE_ATTR_RW(gt_min_freq_mhz);
 
-static DEVICE_ATTR(vlv_rpe_freq_mhz, S_IRUGO, vlv_rpe_freq_mhz_show, NULL);
+static DEVICE_ATTR_RO(vlv_rpe_freq_mhz);
 
 static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf);
 static DEVICE_ATTR(gt_RP0_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 36d4e635e4ce..d452c327dc1d 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -110,6 +110,8 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 		to_intel_digital_connector_state(old_state);
 	struct drm_crtc_state *crtc_state;
 
+	intel_hdcp_atomic_check(conn, old_state, new_state);
+
 	if (!new_state->crtc)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index c7984a80706e..0ee32275994a 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -56,7 +56,6 @@ intel_create_plane_state(struct drm_plane *plane)
 
 	state->base.plane = plane;
 	state->base.rotation = DRM_MODE_ROTATE_0;
-	state->ckey.flags = I915_SET_COLORKEY_NONE;
 
 	return state;
 }
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index f1502a0188eb..522d54fecb53 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -779,7 +779,7 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv,
 {
 	struct intel_encoder *encoder;
 
-	if (WARN_ON(pipe >= INTEL_INFO(dev_priv)->num_pipes))
+	if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map)))
 		return NULL;
 
 	/* MST */
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 51108ffc28d1..4e74aa2f16bc 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1107,6 +1107,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 }
 
 static const u8 cnp_ddc_pin_map[] = {
+	[0] = 0, /* N/A */
 	[DDC_BUS_DDI_B] = GMBUS_PIN_1_BXT,
 	[DDC_BUS_DDI_C] = GMBUS_PIN_2_BXT,
 	[DDC_BUS_DDI_D] = GMBUS_PIN_4_CNP, /* sic */
@@ -1115,9 +1116,14 @@ static const u8 cnp_ddc_pin_map[] = {
 
 static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin)
 {
-	if (HAS_PCH_CNP(dev_priv) &&
-	    vbt_pin > 0 && vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map))
-		return cnp_ddc_pin_map[vbt_pin];
+	if (HAS_PCH_CNP(dev_priv)) {
+		if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) {
+			return cnp_ddc_pin_map[vbt_pin];
+		} else {
+			DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin);
+			return 0;
+		}
+	}
 
 	return vbt_pin;
 }
@@ -1140,6 +1146,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 		{DVO_PORT_HDMIC, DVO_PORT_DPC, -1},
 		{DVO_PORT_HDMID, DVO_PORT_DPD, -1},
 		{DVO_PORT_CRT, DVO_PORT_HDMIE, DVO_PORT_DPE},
+		{DVO_PORT_HDMIF, DVO_PORT_DPF, -1},
 	};
 
 	/*
@@ -1267,6 +1274,27 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 		DRM_DEBUG_KMS("VBT HDMI boost level for port %c: %d\n",
 			      port_name(port), info->hdmi_boost_level);
 	}
+
+	/* DP max link rate for CNL+ */
+	if (bdb_version >= 216) {
+		switch (child->dp_max_link_rate) {
+		default:
+		case VBT_DP_MAX_LINK_RATE_HBR3:
+			info->dp_max_link_rate = 810000;
+			break;
+		case VBT_DP_MAX_LINK_RATE_HBR2:
+			info->dp_max_link_rate = 540000;
+			break;
+		case VBT_DP_MAX_LINK_RATE_HBR:
+			info->dp_max_link_rate = 270000;
+			break;
+		case VBT_DP_MAX_LINK_RATE_LBR:
+			info->dp_max_link_rate = 162000;
+			break;
+		}
+		DRM_DEBUG_KMS("VBT DP max link rate for port %c: %d\n",
+			      port_name(port), info->dp_max_link_rate);
+	}
 }
 
 static void parse_ddi_ports(struct drm_i915_private *dev_priv, u8 bdb_version)
@@ -1323,11 +1351,13 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 		expected_size = LEGACY_CHILD_DEVICE_CONFIG_SIZE;
 	} else if (bdb->version == 195) {
 		expected_size = 37;
-	} else if (bdb->version <= 197) {
+	} else if (bdb->version <= 215) {
 		expected_size = 38;
+	} else if (bdb->version <= 216) {
+		expected_size = 39;
 	} else {
-		expected_size = 38;
-		BUILD_BUG_ON(sizeof(*child) < 38);
+		expected_size = sizeof(*child);
+		BUILD_BUG_ON(sizeof(*child) < 39);
 		DRM_DEBUG_DRIVER("Expected child device config size for VBT version %u not known; assuming %u\n",
 				 bdb->version, expected_size);
 	}
@@ -1688,6 +1718,7 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
 		[PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
 		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+		[PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, },
 	};
 	int i;
 
@@ -1726,6 +1757,7 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 		[PORT_C] = DVO_PORT_DPC,
 		[PORT_D] = DVO_PORT_DPD,
 		[PORT_E] = DVO_PORT_DPE,
+		[PORT_F] = DVO_PORT_DPF,
 	};
 	int i;
 
@@ -1761,6 +1793,7 @@ static bool child_dev_is_dp_dual_mode(const struct child_device_config *child,
 		[PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
 		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+		[PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, },
 	};
 
 	if (port == PORT_A || port >= ARRAY_SIZE(port_mapping))
@@ -1927,6 +1960,11 @@ intel_bios_is_lspcon_present(struct drm_i915_private *dev_priv,
 			if (port == PORT_D)
 				return true;
 			break;
+		case DVO_PORT_DPF:
+		case DVO_PORT_HDMIF:
+			if (port == PORT_F)
+				return true;
+			break;
 		default:
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 58c624f982d9..efbc627a2a25 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -149,17 +149,6 @@ static void intel_breadcrumbs_fake_irq(struct timer_list *t)
 		return;
 
 	mod_timer(&b->fake_irq, jiffies + 1);
-
-	/* Ensure that even if the GPU hangs, we get woken up.
-	 *
-	 * However, note that if no one is waiting, we never notice
-	 * a gpu hang. Eventually, we will have to wait for a resource
-	 * held by the GPU and so trigger a hangcheck. In the most
-	 * pathological case, this will be upon memory starvation! To
-	 * prevent this, we also queue the hangcheck from the retire
-	 * worker.
-	 */
-	i915_queue_hangcheck(engine->i915);
 }
 
 static void irq_enable(struct intel_engine_cs *engine)
@@ -235,7 +224,7 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	struct intel_wait *wait, *n;
 
 	if (!b->irq_armed)
-		goto wakeup_signaler;
+		return;
 
 	/*
 	 * We only disarm the irq when we are idle (all requests completed),
@@ -260,14 +249,6 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	b->waiters = RB_ROOT;
 
 	spin_unlock_irq(&b->rb_lock);
-
-	/*
-	 * The signaling thread may be asleep holding a reference to a request,
-	 * that had its signaling cancelled prior to being preempted. We need
-	 * to kick the signaler, just in case, to release any such reference.
-	 */
-wakeup_signaler:
-	wake_up_process(b->signaler);
 }
 
 static bool use_fake_irq(const struct intel_breadcrumbs *b)
@@ -396,6 +377,8 @@ static bool __intel_engine_add_wait(struct intel_engine_cs *engine,
 	bool first, armed;
 	u32 seqno;
 
+	GEM_BUG_ON(!wait->seqno);
+
 	/* Insert the request into the retirement ordered list
 	 * of waiters by walking the rbtree. If we are the oldest
 	 * seqno in the tree (the first to be retired), then
@@ -642,6 +625,63 @@ static void signaler_set_rtpriority(void)
 	 sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
 }
 
+static void __intel_engine_remove_signal(struct intel_engine_cs *engine,
+					 struct drm_i915_gem_request *request)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+
+	lockdep_assert_held(&b->rb_lock);
+
+	/*
+	 * Wake up all other completed waiters and select the
+	 * next bottom-half for the next user interrupt.
+	 */
+	__intel_engine_remove_wait(engine, &request->signaling.wait);
+
+	/*
+	 * Find the next oldest signal. Note that as we have
+	 * not been holding the lock, another client may
+	 * have installed an even older signal than the one
+	 * we just completed - so double check we are still
+	 * the oldest before picking the next one.
+	 */
+	if (request->signaling.wait.seqno) {
+		if (request == rcu_access_pointer(b->first_signal)) {
+			struct rb_node *rb = rb_next(&request->signaling.node);
+			rcu_assign_pointer(b->first_signal,
+					   rb ? to_signaler(rb) : NULL);
+		}
+
+		rb_erase(&request->signaling.node, &b->signals);
+		request->signaling.wait.seqno = 0;
+	}
+}
+
+static struct drm_i915_gem_request *
+get_first_signal_rcu(struct intel_breadcrumbs *b)
+{
+	/*
+	 * See the big warnings for i915_gem_active_get_rcu() and similarly
+	 * for dma_fence_get_rcu_safe() that explain the intricacies involved
+	 * here with defeating CPU/compiler speculation and enforcing
+	 * the required memory barriers.
+	 */
+	do {
+		struct drm_i915_gem_request *request;
+
+		request = rcu_dereference(b->first_signal);
+		if (request)
+			request = i915_gem_request_get_rcu(request);
+
+		barrier();
+
+		if (!request || request == rcu_access_pointer(b->first_signal))
+			return rcu_pointer_handoff(request);
+
+		i915_gem_request_put(request);
+	} while (1);
+}
+
 static int intel_breadcrumbs_signaler(void *arg)
 {
 	struct intel_engine_cs *engine = arg;
@@ -665,41 +705,21 @@ static int intel_breadcrumbs_signaler(void *arg)
 		 * a new client.
 		 */
 		rcu_read_lock();
-		request = rcu_dereference(b->first_signal);
-		if (request)
-			request = i915_gem_request_get_rcu(request);
+		request = get_first_signal_rcu(b);
 		rcu_read_unlock();
 		if (signal_complete(request)) {
-			local_bh_disable();
-			dma_fence_signal(&request->fence);
-			local_bh_enable(); /* kick start the tasklets */
-
-			spin_lock_irq(&b->rb_lock);
-
-			/* Wake up all other completed waiters and select the
-			 * next bottom-half for the next user interrupt.
-			 */
-			__intel_engine_remove_wait(engine,
-						   &request->signaling.wait);
-
-			/* Find the next oldest signal. Note that as we have
-			 * not been holding the lock, another client may
-			 * have installed an even older signal than the one
-			 * we just completed - so double check we are still
-			 * the oldest before picking the next one.
-			 */
-			if (request == rcu_access_pointer(b->first_signal)) {
-				struct rb_node *rb =
-					rb_next(&request->signaling.node);
-				rcu_assign_pointer(b->first_signal,
-						   rb ? to_signaler(rb) : NULL);
+			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+				      &request->fence.flags)) {
+				local_bh_disable();
+				dma_fence_signal(&request->fence);
+				local_bh_enable(); /* kick start the tasklets */
 			}
-			rb_erase(&request->signaling.node, &b->signals);
-			RB_CLEAR_NODE(&request->signaling.node);
-
-			spin_unlock_irq(&b->rb_lock);
 
-			i915_gem_request_put(request);
+			if (READ_ONCE(request->signaling.wait.seqno)) {
+				spin_lock_irq(&b->rb_lock);
+				__intel_engine_remove_signal(engine, request);
+				spin_unlock_irq(&b->rb_lock);
+			}
 
 			/* If the engine is saturated we may be continually
 			 * processing completed requests. This angers the
@@ -710,19 +730,17 @@ static int intel_breadcrumbs_signaler(void *arg)
 			 */
 			do_schedule = need_resched();
 		}
+		i915_gem_request_put(request);
 
 		if (unlikely(do_schedule)) {
 			if (kthread_should_park())
 				kthread_parkme();
 
-			if (unlikely(kthread_should_stop())) {
-				i915_gem_request_put(request);
+			if (unlikely(kthread_should_stop()))
 				break;
-			}
 
 			schedule();
 		}
-		i915_gem_request_put(request);
 	} while (1);
 	__set_current_state(TASK_RUNNING);
 
@@ -751,12 +769,12 @@ void intel_engine_enable_signaling(struct drm_i915_gem_request *request,
 	if (!seqno)
 		return;
 
+	spin_lock(&b->rb_lock);
+
+	GEM_BUG_ON(request->signaling.wait.seqno);
 	request->signaling.wait.tsk = b->signaler;
 	request->signaling.wait.request = request;
 	request->signaling.wait.seqno = seqno;
-	i915_gem_request_get(request);
-
-	spin_lock(&b->rb_lock);
 
 	/* First add ourselves into the list of waiters, but register our
 	 * bottom-half as the signaller thread. As per usual, only the oldest
@@ -795,7 +813,7 @@ void intel_engine_enable_signaling(struct drm_i915_gem_request *request,
 			rcu_assign_pointer(b->first_signal, request);
 	} else {
 		__intel_engine_remove_wait(engine, &request->signaling.wait);
-		i915_gem_request_put(request);
+		request->signaling.wait.seqno = 0;
 		wakeup = false;
 	}
 
@@ -807,32 +825,17 @@ void intel_engine_enable_signaling(struct drm_i915_gem_request *request,
 
 void intel_engine_cancel_signaling(struct drm_i915_gem_request *request)
 {
-	struct intel_engine_cs *engine = request->engine;
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
-
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&request->lock);
-	GEM_BUG_ON(!request->signaling.wait.seqno);
 
-	spin_lock(&b->rb_lock);
+	if (READ_ONCE(request->signaling.wait.seqno)) {
+		struct intel_engine_cs *engine = request->engine;
+		struct intel_breadcrumbs *b = &engine->breadcrumbs;
 
-	if (!RB_EMPTY_NODE(&request->signaling.node)) {
-		if (request == rcu_access_pointer(b->first_signal)) {
-			struct rb_node *rb =
-				rb_next(&request->signaling.node);
-			rcu_assign_pointer(b->first_signal,
-					   rb ? to_signaler(rb) : NULL);
-		}
-		rb_erase(&request->signaling.node, &b->signals);
-		RB_CLEAR_NODE(&request->signaling.node);
-		i915_gem_request_put(request);
+		spin_lock(&b->rb_lock);
+		__intel_engine_remove_signal(engine, request);
+		spin_unlock(&b->rb_lock);
 	}
-
-	__intel_engine_remove_wait(engine, &request->signaling.wait);
-
-	spin_unlock(&b->rb_lock);
-
-	request->signaling.wait.seqno = 0;
 }
 
 int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index d77e2bec1e29..ee788d5be5e3 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -858,7 +858,7 @@ static void skl_get_cdclk(struct drm_i915_private *dev_priv,
 
 	skl_dpll0_update(dev_priv, cdclk_state);
 
-	cdclk_state->cdclk = cdclk_state->ref;
+	cdclk_state->cdclk = cdclk_state->bypass = cdclk_state->ref;
 
 	if (cdclk_state->vco == 0)
 		goto out;
@@ -1006,7 +1006,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 	/* Choose frequency for this cdclk */
 	switch (cdclk) {
 	default:
-		WARN_ON(cdclk != dev_priv->cdclk.hw.ref);
+		WARN_ON(cdclk != dev_priv->cdclk.hw.bypass);
 		WARN_ON(vco != 0);
 		/* fall through */
 	case 308571:
@@ -1085,7 +1085,7 @@ static void skl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 
 	/* Is PLL enabled and locked ? */
 	if (dev_priv->cdclk.hw.vco == 0 ||
-	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.ref)
+	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass)
 		goto sanitize;
 
 	/* DPLL okay; verify the cdclock
@@ -1159,7 +1159,7 @@ void skl_uninit_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state = dev_priv->cdclk.hw;
 
-	cdclk_state.cdclk = cdclk_state.ref;
+	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
 	cdclk_state.voltage_level = skl_calc_voltage_level(cdclk_state.cdclk);
 
@@ -1199,7 +1199,7 @@ static int bxt_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
 	int ratio;
 
-	if (cdclk == dev_priv->cdclk.hw.ref)
+	if (cdclk == dev_priv->cdclk.hw.bypass)
 		return 0;
 
 	switch (cdclk) {
@@ -1224,7 +1224,7 @@ static int glk_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
 	int ratio;
 
-	if (cdclk == dev_priv->cdclk.hw.ref)
+	if (cdclk == dev_priv->cdclk.hw.bypass)
 		return 0;
 
 	switch (cdclk) {
@@ -1268,7 +1268,7 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 
 	bxt_de_pll_update(dev_priv, cdclk_state);
 
-	cdclk_state->cdclk = cdclk_state->ref;
+	cdclk_state->cdclk = cdclk_state->bypass = cdclk_state->ref;
 
 	if (cdclk_state->vco == 0)
 		goto out;
@@ -1352,7 +1352,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	/* cdclk = vco / 2 / div{1,1.5,2,4} */
 	switch (DIV_ROUND_CLOSEST(vco, cdclk)) {
 	default:
-		WARN_ON(cdclk != dev_priv->cdclk.hw.ref);
+		WARN_ON(cdclk != dev_priv->cdclk.hw.bypass);
 		WARN_ON(vco != 0);
 		/* fall through */
 	case 2:
@@ -1370,10 +1370,15 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 		break;
 	}
 
-	/* Inform power controller of upcoming frequency change */
+	/*
+	 * Inform power controller of upcoming frequency change. BSpec
+	 * requires us to wait up to 150usec, but that leads to timeouts;
+	 * the 2ms used here is based on experiment.
+	 */
 	mutex_lock(&dev_priv->pcu_lock);
-	ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
-				      0x80000000);
+	ret = sandybridge_pcode_write_timeout(dev_priv,
+					      HSW_PCODE_DE_WRITE_FREQ_REQ,
+					      0x80000000, 150, 2);
 	mutex_unlock(&dev_priv->pcu_lock);
 
 	if (ret) {
@@ -1404,8 +1409,15 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	I915_WRITE(CDCLK_CTL, val);
 
 	mutex_lock(&dev_priv->pcu_lock);
-	ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
-				      cdclk_state->voltage_level);
+	/*
+	 * The timeout isn't specified, the 2ms used here is based on
+	 * experiment.
+	 * FIXME: Waiting for the request completion could be delayed until
+	 * the next PCODE request based on BSpec.
+	 */
+	ret = sandybridge_pcode_write_timeout(dev_priv,
+					      HSW_PCODE_DE_WRITE_FREQ_REQ,
+					      cdclk_state->voltage_level, 150, 2);
 	mutex_unlock(&dev_priv->pcu_lock);
 
 	if (ret) {
@@ -1425,7 +1437,7 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
 
 	if (dev_priv->cdclk.hw.vco == 0 ||
-	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.ref)
+	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass)
 		goto sanitize;
 
 	/* DPLL okay; verify the cdclock
@@ -1514,7 +1526,7 @@ void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state = dev_priv->cdclk.hw;
 
-	cdclk_state.cdclk = cdclk_state.ref;
+	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
 	cdclk_state.voltage_level = bxt_calc_voltage_level(cdclk_state.cdclk);
 
@@ -1574,7 +1586,7 @@ static void cnl_get_cdclk(struct drm_i915_private *dev_priv,
 
 	cnl_cdclk_pll_update(dev_priv, cdclk_state);
 
-	cdclk_state->cdclk = cdclk_state->ref;
+	cdclk_state->cdclk = cdclk_state->bypass = cdclk_state->ref;
 
 	if (cdclk_state->vco == 0)
 		goto out;
@@ -1660,7 +1672,7 @@ static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
 	/* cdclk = vco / 2 / div{1,2} */
 	switch (DIV_ROUND_CLOSEST(vco, cdclk)) {
 	default:
-		WARN_ON(cdclk != dev_priv->cdclk.hw.ref);
+		WARN_ON(cdclk != dev_priv->cdclk.hw.bypass);
 		WARN_ON(vco != 0);
 		/* fall through */
 	case 2:
@@ -1705,7 +1717,7 @@ static int cnl_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
 	int ratio;
 
-	if (cdclk == dev_priv->cdclk.hw.ref)
+	if (cdclk == dev_priv->cdclk.hw.bypass)
 		return 0;
 
 	switch (cdclk) {
@@ -1732,7 +1744,7 @@ static void cnl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
 
 	if (dev_priv->cdclk.hw.vco == 0 ||
-	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.ref)
+	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass)
 		goto sanitize;
 
 	/* DPLL okay; verify the cdclock
@@ -1805,7 +1817,7 @@ void cnl_uninit_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state = dev_priv->cdclk.hw;
 
-	cdclk_state.cdclk = cdclk_state.ref;
+	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
 	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
 
@@ -1846,9 +1858,10 @@ bool intel_cdclk_changed(const struct intel_cdclk_state *a,
 void intel_dump_cdclk_state(const struct intel_cdclk_state *cdclk_state,
 			    const char *context)
 {
-	DRM_DEBUG_DRIVER("%s %d kHz, VCO %d kHz, ref %d kHz, voltage level %d\n",
+	DRM_DEBUG_DRIVER("%s %d kHz, VCO %d kHz, ref %d kHz, bypass %d kHz, voltage level %d\n",
 			 context, cdclk_state->cdclk, cdclk_state->vco,
-			 cdclk_state->ref, cdclk_state->voltage_level);
+			 cdclk_state->ref, cdclk_state->bypass,
+			 cdclk_state->voltage_level);
 }
 
 /**
@@ -1940,6 +1953,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
 		min_cdclk = max(2 * 96000, min_cdclk);
 
+	/*
+	 * On Valleyview some DSI panels lose (v|h)sync when the clock is lower
+	 * than 320000KHz.
+	 */
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) &&
+	    IS_VALLEYVIEW(dev_priv))
+		min_cdclk = max(320000, min_cdclk);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);
@@ -2334,6 +2355,30 @@ static int cnp_rawclk(struct drm_i915_private *dev_priv)
 	return divider + fraction;
 }
 
+static int icp_rawclk(struct drm_i915_private *dev_priv)
+{
+	u32 rawclk;
+	int divider, numerator, denominator, frequency;
+
+	if (I915_READ(SFUSE_STRAP) & SFUSE_STRAP_RAW_FREQUENCY) {
+		frequency = 24000;
+		divider = 23;
+		numerator = 0;
+		denominator = 0;
+	} else {
+		frequency = 19200;
+		divider = 18;
+		numerator = 1;
+		denominator = 4;
+	}
+
+	rawclk = CNP_RAWCLK_DIV(divider) | ICP_RAWCLK_NUM(numerator) |
+		 ICP_RAWCLK_DEN(denominator);
+
+	I915_WRITE(PCH_RAWCLK_FREQ, rawclk);
+	return frequency;
+}
+
 static int pch_rawclk(struct drm_i915_private *dev_priv)
 {
 	return (I915_READ(PCH_RAWCLK_FREQ) & RAWCLK_FREQ_MASK) * 1000;
@@ -2381,8 +2426,9 @@ static int g4x_hrawclk(struct drm_i915_private *dev_priv)
  */
 void intel_update_rawclk(struct drm_i915_private *dev_priv)
 {
-
-	if (HAS_PCH_CNP(dev_priv))
+	if (HAS_PCH_ICP(dev_priv))
+		dev_priv->rawclk_freq = icp_rawclk(dev_priv);
+	else if (HAS_PCH_CNP(dev_priv))
 		dev_priv->rawclk_freq = cnp_rawclk(dev_priv);
 	else if (HAS_PCH_SPLIT(dev_priv))
 		dev_priv->rawclk_freq = pch_rawclk(dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 7fe4aac0facc..41e6c75a7f3c 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -37,8 +37,9 @@
 #define I915_CSR_GLK "i915/glk_dmc_ver1_04.bin"
 #define GLK_CSR_VERSION_REQUIRED	CSR_VERSION(1, 4)
 
-#define I915_CSR_CNL "i915/cnl_dmc_ver1_06.bin"
-#define CNL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 6)
+#define I915_CSR_CNL "i915/cnl_dmc_ver1_07.bin"
+MODULE_FIRMWARE(I915_CSR_CNL);
+#define CNL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
 
 #define I915_CSR_KBL "i915/kbl_dmc_ver1_04.bin"
 MODULE_FIRMWARE(I915_CSR_KBL);
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index f51645a08dca..cfcd9cb37d5d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1615,6 +1615,35 @@ void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
 	I915_WRITE(reg, val);
 }
 
+int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
+				     bool enable)
+{
+	struct drm_device *dev = intel_encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum pipe pipe = 0;
+	int ret = 0;
+	uint32_t tmp;
+
+	if (WARN_ON(!intel_display_power_get_if_enabled(dev_priv,
+						intel_encoder->power_domain)))
+		return -ENXIO;
+
+	if (WARN_ON(!intel_encoder->get_hw_state(intel_encoder, &pipe))) {
+		ret = -EIO;
+		goto out;
+	}
+
+	tmp = I915_READ(TRANS_DDI_FUNC_CTL(pipe));
+	if (enable)
+		tmp |= TRANS_DDI_HDCP_SIGNALLING;
+	else
+		tmp &= ~TRANS_DDI_HDCP_SIGNALLING;
+	I915_WRITE(TRANS_DDI_FUNC_CTL(pipe), tmp);
+out:
+	intel_display_power_put(dev_priv, intel_encoder->power_domain);
+	return ret;
+}
+
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 {
 	struct drm_device *dev = intel_connector->base.dev;
@@ -2404,6 +2433,48 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 					  crtc_state->hdmi_high_tmds_clock_ratio,
 					  crtc_state->hdmi_scrambling);
 
+	/* Display WA #1143: skl,kbl,cfl */
+	if (IS_GEN9_BC(dev_priv)) {
+		/*
+		 * For some reason these chicken bits have been
+		 * stuffed into a transcoder register, event though
+		 * the bits affect a specific DDI port rather than
+		 * a specific transcoder.
+		 */
+		static const enum transcoder port_to_transcoder[] = {
+			[PORT_A] = TRANSCODER_EDP,
+			[PORT_B] = TRANSCODER_A,
+			[PORT_C] = TRANSCODER_B,
+			[PORT_D] = TRANSCODER_C,
+			[PORT_E] = TRANSCODER_A,
+		};
+		enum transcoder transcoder = port_to_transcoder[port];
+		u32 val;
+
+		val = I915_READ(CHICKEN_TRANS(transcoder));
+
+		if (port == PORT_E)
+			val |= DDIE_TRAINING_OVERRIDE_ENABLE |
+				DDIE_TRAINING_OVERRIDE_VALUE;
+		else
+			val |= DDI_TRAINING_OVERRIDE_ENABLE |
+				DDI_TRAINING_OVERRIDE_VALUE;
+
+		I915_WRITE(CHICKEN_TRANS(transcoder), val);
+		POSTING_READ(CHICKEN_TRANS(transcoder));
+
+		udelay(1);
+
+		if (port == PORT_E)
+			val &= ~(DDIE_TRAINING_OVERRIDE_ENABLE |
+				 DDIE_TRAINING_OVERRIDE_VALUE);
+		else
+			val &= ~(DDI_TRAINING_OVERRIDE_ENABLE |
+				 DDI_TRAINING_OVERRIDE_VALUE);
+
+		I915_WRITE(CHICKEN_TRANS(transcoder), val);
+	}
+
 	/* In HDMI/DVI mode, the port width, and swing/emphasis values
 	 * are ignored so nothing special needs to be done besides
 	 * enabling the port.
@@ -2423,6 +2494,11 @@ static void intel_enable_ddi(struct intel_encoder *encoder,
 		intel_enable_ddi_hdmi(encoder, crtc_state, conn_state);
 	else
 		intel_enable_ddi_dp(encoder, crtc_state, conn_state);
+
+	/* Enable hdcp if it's desired */
+	if (conn_state->content_protection ==
+	    DRM_MODE_CONTENT_PROTECTION_DESIRED)
+		intel_hdcp_enable(to_intel_connector(conn_state->connector));
 }
 
 static void intel_disable_ddi_dp(struct intel_encoder *encoder,
@@ -2457,6 +2533,8 @@ static void intel_disable_ddi(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
+	intel_hdcp_disable(to_intel_connector(old_conn_state->connector));
+
 	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI))
 		intel_disable_ddi_hdmi(encoder, old_crtc_state, old_conn_state);
 	else
@@ -2868,6 +2946,10 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 		intel_dig_port->ddi_io_power_domain =
 			POWER_DOMAIN_PORT_DDI_E_IO;
 		break;
+	case PORT_F:
+		intel_dig_port->ddi_io_power_domain =
+			POWER_DOMAIN_PORT_DDI_F_IO;
+		break;
 	default:
 		MISSING_CASE(port);
 	}
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index d28592e43512..a2c16140169f 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -56,6 +56,7 @@ static const char * const platform_names[] = {
 	PLATFORM_NAME(GEMINILAKE),
 	PLATFORM_NAME(COFFEELAKE),
 	PLATFORM_NAME(CANNONLAKE),
+	PLATFORM_NAME(ICELAKE),
 };
 #undef PLATFORM_NAME
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 49cb27bd04c1..9542018d11d0 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -69,6 +69,8 @@ enum intel_platform {
 	INTEL_COFFEELAKE,
 	/* gen10 */
 	INTEL_CANNONLAKE,
+	/* gen11 */
+	INTEL_ICELAKE,
 	INTEL_MAX_PLATFORMS
 };
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9803da5fd6b3..60ba5bb3f34c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2387,6 +2387,20 @@ static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier)
 	}
 }
 
+/*
+ * From the Sky Lake PRM:
+ * "The Color Control Surface (CCS) contains the compression status of
+ *  the cache-line pairs. The compression state of the cache-line pair
+ *  is specified by 2 bits in the CCS. Each CCS cache-line represents
+ *  an area on the main surface of 16 x16 sets of 128 byte Y-tiled
+ *  cache-line-pairs. CCS is always Y tiled."
+ *
+ * Since cache line pairs refers to horizontally adjacent cache lines,
+ * each cache line in the CCS corresponds to an area of 32x16 cache
+ * lines on the main surface. Since each pixel is 4 bytes, this gives
+ * us a ratio of one byte in the CCS for each 8x16 pixels in the
+ * main surface.
+ */
 static const struct drm_format_info ccs_formats[] = {
 	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, },
 	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, },
@@ -2917,14 +2931,19 @@ static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state
 	return true;
 }
 
-static int skl_check_main_surface(struct intel_plane_state *plane_state)
+static int skl_check_main_surface(const struct intel_crtc_state *crtc_state,
+				  struct intel_plane_state *plane_state)
 {
+	struct drm_i915_private *dev_priv =
+		to_i915(plane_state->base.plane->dev);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	unsigned int rotation = plane_state->base.rotation;
 	int x = plane_state->base.src.x1 >> 16;
 	int y = plane_state->base.src.y1 >> 16;
 	int w = drm_rect_width(&plane_state->base.src) >> 16;
 	int h = drm_rect_height(&plane_state->base.src) >> 16;
+	int dst_x = plane_state->base.dst.x1;
+	int pipe_src_w = crtc_state->pipe_src_w;
 	int max_width = skl_max_plane_width(fb, 0, rotation);
 	int max_height = 4096;
 	u32 alignment, offset, aux_offset = plane_state->aux.offset;
@@ -2935,6 +2954,24 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 		return -EINVAL;
 	}
 
+	/*
+	 * Display WA #1175: cnl,glk
+	 * Planes other than the cursor may cause FIFO underflow and display
+	 * corruption if starting less than 4 pixels from the right edge of
+	 * the screen.
+	 * Besides the above WA fix the similar problem, where planes other
+	 * than the cursor ending less than 4 pixels from the left edge of the
+	 * screen may cause FIFO underflow and display corruption.
+	 */
+	if ((IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) &&
+	    (dst_x + w < 4 || dst_x > pipe_src_w - 4)) {
+		DRM_DEBUG_KMS("requested plane X %s position %d invalid (valid range %d-%d)\n",
+			      dst_x + w < 4 ? "end" : "start",
+			      dst_x + w < 4 ? dst_x + w : dst_x,
+			      4, pipe_src_w - 4);
+		return -ERANGE;
+	}
+
 	intel_add_fb_offsets(&x, &y, plane_state, 0);
 	offset = intel_compute_tile_offset(&x, &y, plane_state, 0);
 	alignment = intel_surf_alignment(fb, 0);
@@ -3027,6 +3064,7 @@ static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	int src_x = plane_state->base.src.x1 >> 16;
@@ -3037,17 +3075,8 @@ static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
 	int y = src_y / vsub;
 	u32 offset;
 
-	switch (plane->id) {
-	case PLANE_PRIMARY:
-	case PLANE_SPRITE0:
-		break;
-	default:
-		DRM_DEBUG_KMS("RC support only on plane 1 and 2\n");
-		return -EINVAL;
-	}
-
-	if (crtc->pipe == PIPE_C) {
-		DRM_DEBUG_KMS("No RC support on pipe C\n");
+	if (!skl_plane_has_ccs(dev_priv, crtc->pipe, plane->id)) {
+		DRM_DEBUG_KMS("No RC support on %s\n", plane->base.name);
 		return -EINVAL;
 	}
 
@@ -3067,7 +3096,8 @@ static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
 	return 0;
 }
 
-int skl_check_plane_surface(struct intel_plane_state *plane_state)
+int skl_check_plane_surface(const struct intel_crtc_state *crtc_state,
+			    struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	unsigned int rotation = plane_state->base.rotation;
@@ -3107,7 +3137,7 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
 		plane_state->aux.y = 0;
 	}
 
-	ret = skl_check_main_surface(plane_state);
+	ret = skl_check_main_surface(crtc_state, plane_state);
 	if (ret)
 		return ret;
 
@@ -4757,7 +4787,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	/* check colorkey */
-	if (plane_state->ckey.flags != I915_SET_COLORKEY_NONE) {
+	if (plane_state->ckey.flags) {
 		DRM_DEBUG_KMS("[PLANE:%d:%s] scaling with color key not allowed",
 			      intel_plane->base.base.id,
 			      intel_plane->base.name);
@@ -5641,6 +5671,8 @@ enum intel_display_power_domain intel_port_to_power_domain(enum port port)
 		return POWER_DOMAIN_PORT_DDI_D_LANES;
 	case PORT_E:
 		return POWER_DOMAIN_PORT_DDI_E_LANES;
+	case PORT_F:
+		return POWER_DOMAIN_PORT_DDI_F_LANES;
 	default:
 		MISSING_CASE(port);
 		return POWER_DOMAIN_PORT_OTHER;
@@ -5661,8 +5693,8 @@ static u64 get_crtc_power_domains(struct drm_crtc *crtc,
 	if (!crtc_state->base.active)
 		return 0;
 
-	mask = BIT(POWER_DOMAIN_PIPE(pipe));
-	mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
+	mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe));
+	mask |= BIT_ULL(POWER_DOMAIN_TRANSCODER(transcoder));
 	if (crtc_state->pch_pfit.enabled ||
 	    crtc_state->pch_pfit.force_thru)
 		mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
@@ -5674,7 +5706,7 @@ static u64 get_crtc_power_domains(struct drm_crtc *crtc,
 	}
 
 	if (HAS_DDI(dev_priv) && crtc_state->has_audio)
-		mask |= BIT(POWER_DOMAIN_AUDIO);
+		mask |= BIT_ULL(POWER_DOMAIN_AUDIO);
 
 	if (crtc_state->shared_dpll)
 		mask |= BIT_ULL(POWER_DOMAIN_PLLS);
@@ -8504,7 +8536,10 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 
 	val = I915_READ(PLANE_CTL(pipe, plane_id));
 
-	pixel_format = val & PLANE_CTL_FORMAT_MASK;
+	if (INTEL_GEN(dev_priv) >= 11)
+		pixel_format = val & ICL_PLANE_CTL_FORMAT_MASK;
+	else
+		pixel_format = val & PLANE_CTL_FORMAT_MASK;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		alpha = I915_READ(PLANE_COLOR_CTL(pipe, plane_id));
@@ -12533,7 +12568,13 @@ static int do_rps_boost(struct wait_queue_entry *_wait,
 	struct wait_rps_boost *wait = container_of(_wait, typeof(*wait), wait);
 	struct drm_i915_gem_request *rq = wait->request;
 
-	gen6_rps_boost(rq, NULL);
+	/*
+	 * If we missed the vblank, but the request is already running it
+	 * is reasonable to assume that it will complete before the next
+	 * vblank without our intervention, so leave RPS alone.
+	 */
+	if (!i915_gem_request_started(rq))
+		gen6_rps_boost(rq, NULL);
 	i915_gem_request_put(rq);
 
 	drm_crtc_vblank_put(wait->crtc);
@@ -12762,7 +12803,7 @@ intel_check_primary_plane(struct intel_plane *plane,
 
 	if (INTEL_GEN(dev_priv) >= 9) {
 		/* use scaler when colorkey is not required */
-		if (state->ckey.flags == I915_SET_COLORKEY_NONE) {
+		if (!state->ckey.flags) {
 			min_scale = 1;
 			max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state);
 		}
@@ -12785,7 +12826,7 @@ intel_check_primary_plane(struct intel_plane *plane,
 		return 0;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		ret = skl_check_plane_surface(state);
+		ret = skl_check_plane_surface(crtc_state, state);
 		if (ret)
 			return ret;
 
@@ -12963,8 +13004,6 @@ static bool intel_primary_plane_format_mod_supported(struct drm_plane *plane,
 		return i965_mod_supported(format, modifier);
 	else
 		return i8xx_mod_supported(format, modifier);
-
-	unreachable();
 }
 
 static bool intel_cursor_plane_format_mod_supported(struct drm_plane *plane,
@@ -13172,21 +13211,14 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	else
 		primary->i9xx_plane = (enum i9xx_plane_id) pipe;
 	primary->id = PLANE_PRIMARY;
-	primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe);
+	primary->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, primary->id);
 	primary->check_plane = intel_check_primary_plane;
 
-	if (INTEL_GEN(dev_priv) >= 10) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		intel_primary_formats = skl_primary_formats;
 		num_formats = ARRAY_SIZE(skl_primary_formats);
-		modifiers = skl_format_modifiers_ccs;
 
-		primary->update_plane = skl_update_plane;
-		primary->disable_plane = skl_disable_plane;
-		primary->get_hw_state = skl_plane_get_hw_state;
-	} else if (INTEL_GEN(dev_priv) >= 9) {
-		intel_primary_formats = skl_primary_formats;
-		num_formats = ARRAY_SIZE(skl_primary_formats);
-		if (pipe < PIPE_C)
+		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_PRIMARY))
 			modifiers = skl_format_modifiers_ccs;
 		else
 			modifiers = skl_format_modifiers_noccs;
@@ -13300,7 +13332,7 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv,
 	cursor->pipe = pipe;
 	cursor->i9xx_plane = (enum i9xx_plane_id) pipe;
 	cursor->id = PLANE_CURSOR;
-	cursor->frontbuffer_bit = INTEL_FRONTBUFFER_CURSOR(pipe);
+	cursor->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, cursor->id);
 
 	if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) {
 		cursor->update_plane = i845_update_cursor;
@@ -13616,7 +13648,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		if (found || IS_GEN9_BC(dev_priv))
 			intel_ddi_init(dev_priv, PORT_A);
 
-		/* DDI B, C and D detection is indicated by the SFUSE_STRAP
+		/* DDI B, C, D, and F detection is indicated by the SFUSE_STRAP
 		 * register */
 		found = I915_READ(SFUSE_STRAP);
 
@@ -13626,6 +13658,8 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 			intel_ddi_init(dev_priv, PORT_C);
 		if (found & SFUSE_STRAP_DDID_DETECTED)
 			intel_ddi_init(dev_priv, PORT_D);
+		if (found & SFUSE_STRAP_DDIF_DETECTED)
+			intel_ddi_init(dev_priv, PORT_F);
 		/*
 		 * On SKL we don't have a way to detect DDI-E so we rely on VBT.
 		 */
@@ -15263,6 +15297,10 @@ static void intel_hpd_poll_fini(struct drm_device *dev)
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->modeset_retry_work.func)
 			cancel_work_sync(&connector->modeset_retry_work);
+		if (connector->hdcp_shim) {
+			cancel_delayed_work_sync(&connector->hdcp_check_work);
+			cancel_work_sync(&connector->hdcp_prop_work);
+		}
 	}
 	drm_connector_list_iter_end(&conn_iter);
 }
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index a0d2b6169361..c4042e342f50 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -119,6 +119,7 @@ enum port {
 	PORT_C,
 	PORT_D,
 	PORT_E,
+	PORT_F,
 
 	I915_MAX_PORTS
 };
@@ -156,11 +157,13 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_PORT_DDI_C_LANES,
 	POWER_DOMAIN_PORT_DDI_D_LANES,
 	POWER_DOMAIN_PORT_DDI_E_LANES,
+	POWER_DOMAIN_PORT_DDI_F_LANES,
 	POWER_DOMAIN_PORT_DDI_A_IO,
 	POWER_DOMAIN_PORT_DDI_B_IO,
 	POWER_DOMAIN_PORT_DDI_C_IO,
 	POWER_DOMAIN_PORT_DDI_D_IO,
 	POWER_DOMAIN_PORT_DDI_E_IO,
+	POWER_DOMAIN_PORT_DDI_F_IO,
 	POWER_DOMAIN_PORT_DSI,
 	POWER_DOMAIN_PORT_CRT,
 	POWER_DOMAIN_PORT_OTHER,
@@ -171,6 +174,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
+	POWER_DOMAIN_AUX_F,
 	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 35c5299feab6..f10a14330e7c 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -36,7 +36,9 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_hdcp.h>
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -155,6 +157,28 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp)
 	intel_dp->num_sink_rates = i;
 }
 
+/* Get length of rates array potentially limited by max_rate. */
+static int intel_dp_rate_limit_len(const int *rates, int len, int max_rate)
+{
+	int i;
+
+	/* Limit results by potentially reduced max rate */
+	for (i = 0; i < len; i++) {
+		if (rates[len - i - 1] <= max_rate)
+			return len - i;
+	}
+
+	return 0;
+}
+
+/* Get length of common rates array potentially limited by max_rate. */
+static int intel_dp_common_len_rate_limit(const struct intel_dp *intel_dp,
+					  int max_rate)
+{
+	return intel_dp_rate_limit_len(intel_dp->common_rates,
+				       intel_dp->num_common_rates, max_rate);
+}
+
 /* Theoretical max between source and sink */
 static int intel_dp_max_common_rate(struct intel_dp *intel_dp)
 {
@@ -218,15 +242,38 @@ intel_dp_downstream_max_dotclock(struct intel_dp *intel_dp)
 	return max_dotclk;
 }
 
+static int cnl_max_source_rate(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
+	enum port port = dig_port->base.port;
+
+	u32 voltage = I915_READ(CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
+
+	/* Low voltage SKUs are limited to max of 5.4G */
+	if (voltage == VOLTAGE_INFO_0_85V)
+		return 540000;
+
+	/* For this SKU 8.1G is supported in all ports */
+	if (IS_CNL_WITH_PORT_F(dev_priv))
+		return 810000;
+
+	/* For other SKUs, max rate on ports A and B is 5.4G */
+	if (port == PORT_A || port == PORT_D)
+		return 540000;
+
+	return 810000;
+}
+
 static void
 intel_dp_set_source_rates(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum port port = dig_port->base.port;
+	const struct ddi_vbt_port_info *info =
+		&dev_priv->vbt.ddi_port_info[dig_port->base.port];
 	const int *source_rates;
-	int size;
-	u32 voltage;
+	int size, max_rate = 0, vbt_max_rate = info->dp_max_link_rate;
 
 	/* This should only be done once */
 	WARN_ON(intel_dp->source_rates || intel_dp->num_source_rates);
@@ -237,10 +284,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		source_rates = cnl_rates;
 		size = ARRAY_SIZE(cnl_rates);
-		voltage = I915_READ(CNL_PORT_COMP_DW3) & VOLTAGE_INFO_MASK;
-		if (port == PORT_A || port == PORT_D ||
-		    voltage == VOLTAGE_INFO_0_85V)
-			size -= 2;
+		max_rate = cnl_max_source_rate(intel_dp);
 	} else if (IS_GEN9_BC(dev_priv)) {
 		source_rates = skl_rates;
 		size = ARRAY_SIZE(skl_rates);
@@ -253,6 +297,14 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 		size = ARRAY_SIZE(default_rates) - 1;
 	}
 
+	if (max_rate && vbt_max_rate)
+		max_rate = min(max_rate, vbt_max_rate);
+	else if (vbt_max_rate)
+		max_rate = vbt_max_rate;
+
+	if (max_rate)
+		size = intel_dp_rate_limit_len(source_rates, size, max_rate);
+
 	intel_dp->source_rates = source_rates;
 	intel_dp->num_source_rates = size;
 }
@@ -309,22 +361,6 @@ static void intel_dp_set_common_rates(struct intel_dp *intel_dp)
 	}
 }
 
-/* get length of common rates potentially limited by max_rate */
-static int intel_dp_common_len_rate_limit(struct intel_dp *intel_dp,
-					  int max_rate)
-{
-	const int *common_rates = intel_dp->common_rates;
-	int i, common_len = intel_dp->num_common_rates;
-
-	/* Limit results by potentially reduced max rate */
-	for (i = 0; i < common_len; i++) {
-		if (common_rates[common_len - i - 1] <= max_rate)
-			return common_len - i;
-	}
-
-	return 0;
-}
-
 static bool intel_dp_link_params_valid(struct intel_dp *intel_dp, int link_rate,
 				       uint8_t lane_count)
 {
@@ -794,7 +830,8 @@ static void intel_pps_get_registers(struct intel_dp *intel_dp,
 	regs->pp_stat = PP_STATUS(pps_idx);
 	regs->pp_on = PP_ON_DELAYS(pps_idx);
 	regs->pp_off = PP_OFF_DELAYS(pps_idx);
-	if (!IS_GEN9_LP(dev_priv) && !HAS_PCH_CNP(dev_priv))
+	if (!IS_GEN9_LP(dev_priv) && !HAS_PCH_CNP(dev_priv) &&
+	    !HAS_PCH_ICP(dev_priv))
 		regs->pp_div = PP_DIVISOR(pps_idx);
 }
 
@@ -1025,10 +1062,29 @@ static uint32_t skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	       DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
 }
 
+static uint32_t intel_dp_get_aux_send_ctl(struct intel_dp *intel_dp,
+					  bool has_aux_irq,
+					  int send_bytes,
+					  uint32_t aux_clock_divider,
+					  bool aksv_write)
+{
+	uint32_t val = 0;
+
+	if (aksv_write) {
+		send_bytes += 5;
+		val |= DP_AUX_CH_CTL_AUX_AKSV_SELECT;
+	}
+
+	return val | intel_dp->get_aux_send_ctl(intel_dp,
+						has_aux_irq,
+						send_bytes,
+						aux_clock_divider);
+}
+
 static int
 intel_dp_aux_ch(struct intel_dp *intel_dp,
 		const uint8_t *send, int send_bytes,
-		uint8_t *recv, int recv_size)
+		uint8_t *recv, int recv_size, bool aksv_write)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv =
@@ -1088,10 +1144,11 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	}
 
 	while ((aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, clock++))) {
-		u32 send_ctl = intel_dp->get_aux_send_ctl(intel_dp,
-							  has_aux_irq,
-							  send_bytes,
-							  aux_clock_divider);
+		u32 send_ctl = intel_dp_get_aux_send_ctl(intel_dp,
+							 has_aux_irq,
+							 send_bytes,
+							 aux_clock_divider,
+							 aksv_write);
 
 		/* Must try at least 3 times according to DP spec */
 		for (try = 0; try < 5; try++) {
@@ -1228,7 +1285,8 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 		if (msg->buffer)
 			memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size);
 
-		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize);
+		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize,
+				      false);
 		if (ret > 0) {
 			msg->reply = rxbuf[0] >> 4;
 
@@ -1250,7 +1308,8 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 		if (WARN_ON(rxsize > 20))
 			return -E2BIG;
 
-		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize);
+		ret = intel_dp_aux_ch(intel_dp, txbuf, txsize, rxbuf, rxsize,
+				      false);
 		if (ret > 0) {
 			msg->reply = rxbuf[0] >> 4;
 			/*
@@ -1298,6 +1357,9 @@ static enum port intel_aux_port(struct drm_i915_private *dev_priv,
 	case DP_AUX_D:
 		aux_port = PORT_D;
 		break;
+	case DP_AUX_F:
+		aux_port = PORT_F;
+		break;
 	default:
 		MISSING_CASE(info->alternate_aux_channel);
 		aux_port = PORT_A;
@@ -1378,6 +1440,7 @@ static i915_reg_t skl_aux_ctl_reg(struct drm_i915_private *dev_priv,
 	case PORT_B:
 	case PORT_C:
 	case PORT_D:
+	case PORT_F:
 		return DP_AUX_CH_CTL(port);
 	default:
 		MISSING_CASE(port);
@@ -1393,6 +1456,7 @@ static i915_reg_t skl_aux_data_reg(struct drm_i915_private *dev_priv,
 	case PORT_B:
 	case PORT_C:
 	case PORT_D:
+	case PORT_F:
 		return DP_AUX_CH_DATA(port, index);
 	default:
 		MISSING_CASE(port);
@@ -4455,173 +4519,174 @@ edp_detect(struct intel_dp *intel_dp)
 	return status;
 }
 
-static bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool ibx_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	switch (port->base.port) {
-	case PORT_B:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_B:
 		bit = SDE_PORTB_HOTPLUG;
 		break;
-	case PORT_C:
+	case HPD_PORT_C:
 		bit = SDE_PORTC_HOTPLUG;
 		break;
-	case PORT_D:
+	case HPD_PORT_D:
 		bit = SDE_PORTD_HOTPLUG;
 		break;
 	default:
-		MISSING_CASE(port->base.port);
+		MISSING_CASE(encoder->hpd_pin);
 		return false;
 	}
 
 	return I915_READ(SDEISR) & bit;
 }
 
-static bool cpt_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool cpt_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	switch (port->base.port) {
-	case PORT_B:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_B:
 		bit = SDE_PORTB_HOTPLUG_CPT;
 		break;
-	case PORT_C:
+	case HPD_PORT_C:
 		bit = SDE_PORTC_HOTPLUG_CPT;
 		break;
-	case PORT_D:
+	case HPD_PORT_D:
 		bit = SDE_PORTD_HOTPLUG_CPT;
 		break;
 	default:
-		MISSING_CASE(port->base.port);
+		MISSING_CASE(encoder->hpd_pin);
 		return false;
 	}
 
 	return I915_READ(SDEISR) & bit;
 }
 
-static bool spt_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool spt_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	switch (port->base.port) {
-	case PORT_A:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_A:
 		bit = SDE_PORTA_HOTPLUG_SPT;
 		break;
-	case PORT_E:
+	case HPD_PORT_E:
 		bit = SDE_PORTE_HOTPLUG_SPT;
 		break;
 	default:
-		return cpt_digital_port_connected(dev_priv, port);
+		return cpt_digital_port_connected(encoder);
 	}
 
 	return I915_READ(SDEISR) & bit;
 }
 
-static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool g4x_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	switch (port->base.port) {
-	case PORT_B:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_B:
 		bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
 		break;
-	case PORT_C:
+	case HPD_PORT_C:
 		bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
 		break;
-	case PORT_D:
+	case HPD_PORT_D:
 		bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
 		break;
 	default:
-		MISSING_CASE(port->base.port);
+		MISSING_CASE(encoder->hpd_pin);
 		return false;
 	}
 
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv,
-					struct intel_digital_port *port)
+static bool gm45_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	switch (port->base.port) {
-	case PORT_B:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_B:
 		bit = PORTB_HOTPLUG_LIVE_STATUS_GM45;
 		break;
-	case PORT_C:
+	case HPD_PORT_C:
 		bit = PORTC_HOTPLUG_LIVE_STATUS_GM45;
 		break;
-	case PORT_D:
+	case HPD_PORT_D:
 		bit = PORTD_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	default:
-		MISSING_CASE(port->base.port);
+		MISSING_CASE(encoder->hpd_pin);
 		return false;
 	}
 
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool ilk_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool ilk_digital_port_connected(struct intel_encoder *encoder)
 {
-	if (port->base.port == PORT_A)
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (encoder->hpd_pin == HPD_PORT_A)
 		return I915_READ(DEISR) & DE_DP_A_HOTPLUG;
 	else
-		return ibx_digital_port_connected(dev_priv, port);
+		return ibx_digital_port_connected(encoder);
 }
 
-static bool snb_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool snb_digital_port_connected(struct intel_encoder *encoder)
 {
-	if (port->base.port == PORT_A)
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (encoder->hpd_pin == HPD_PORT_A)
 		return I915_READ(DEISR) & DE_DP_A_HOTPLUG;
 	else
-		return cpt_digital_port_connected(dev_priv, port);
+		return cpt_digital_port_connected(encoder);
 }
 
-static bool ivb_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool ivb_digital_port_connected(struct intel_encoder *encoder)
 {
-	if (port->base.port == PORT_A)
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (encoder->hpd_pin == HPD_PORT_A)
 		return I915_READ(DEISR) & DE_DP_A_HOTPLUG_IVB;
 	else
-		return cpt_digital_port_connected(dev_priv, port);
+		return cpt_digital_port_connected(encoder);
 }
 
-static bool bdw_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool bdw_digital_port_connected(struct intel_encoder *encoder)
 {
-	if (port->base.port == PORT_A)
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (encoder->hpd_pin == HPD_PORT_A)
 		return I915_READ(GEN8_DE_PORT_ISR) & GEN8_PORT_DP_A_HOTPLUG;
 	else
-		return cpt_digital_port_connected(dev_priv, port);
+		return cpt_digital_port_connected(encoder);
 }
 
-static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *intel_dig_port)
+static bool bxt_digital_port_connected(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	enum port port;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 bit;
 
-	port = intel_hpd_pin_to_port(intel_encoder->hpd_pin);
-	switch (port) {
-	case PORT_A:
+	switch (encoder->hpd_pin) {
+	case HPD_PORT_A:
 		bit = BXT_DE_PORT_HP_DDIA;
 		break;
-	case PORT_B:
+	case HPD_PORT_B:
 		bit = BXT_DE_PORT_HP_DDIB;
 		break;
-	case PORT_C:
+	case HPD_PORT_C:
 		bit = BXT_DE_PORT_HP_DDIC;
 		break;
 	default:
-		MISSING_CASE(port);
+		MISSING_CASE(encoder->hpd_pin);
 		return false;
 	}
 
@@ -4630,33 +4695,33 @@ static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv,
 
 /*
  * intel_digital_port_connected - is the specified port connected?
- * @dev_priv: i915 private structure
- * @port: the port to test
+ * @encoder: intel_encoder
  *
- * Return %true if @port is connected, %false otherwise.
+ * Return %true if port is connected, %false otherwise.
  */
-bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
-				  struct intel_digital_port *port)
+bool intel_digital_port_connected(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
 	if (HAS_GMCH_DISPLAY(dev_priv)) {
 		if (IS_GM45(dev_priv))
-			return gm45_digital_port_connected(dev_priv, port);
+			return gm45_digital_port_connected(encoder);
 		else
-			return g4x_digital_port_connected(dev_priv, port);
+			return g4x_digital_port_connected(encoder);
 	}
 
 	if (IS_GEN5(dev_priv))
-		return ilk_digital_port_connected(dev_priv, port);
+		return ilk_digital_port_connected(encoder);
 	else if (IS_GEN6(dev_priv))
-		return snb_digital_port_connected(dev_priv, port);
+		return snb_digital_port_connected(encoder);
 	else if (IS_GEN7(dev_priv))
-		return ivb_digital_port_connected(dev_priv, port);
+		return ivb_digital_port_connected(encoder);
 	else if (IS_GEN8(dev_priv))
-		return bdw_digital_port_connected(dev_priv, port);
+		return bdw_digital_port_connected(encoder);
 	else if (IS_GEN9_LP(dev_priv))
-		return bxt_digital_port_connected(dev_priv, port);
+		return bxt_digital_port_connected(encoder);
 	else
-		return spt_digital_port_connected(dev_priv, port);
+		return spt_digital_port_connected(encoder);
 }
 
 static struct edid *
@@ -4715,8 +4780,7 @@ intel_dp_long_pulse(struct intel_connector *connector)
 	/* Can't disconnect eDP, but you can close the lid... */
 	if (intel_dp_is_edp(intel_dp))
 		status = edp_detect(intel_dp);
-	else if (intel_digital_port_connected(dev_priv,
-					      dp_to_dig_port(intel_dp)))
+	else if (intel_digital_port_connected(&dp_to_dig_port(intel_dp)->base))
 		status = intel_dp_detect_dpcd(intel_dp);
 	else
 		status = connector_status_disconnected;
@@ -4985,6 +5049,236 @@ void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 	pps_unlock(intel_dp);
 }
 
+static
+int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
+				u8 *an)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_dig_port->base.base);
+	uint8_t txbuf[4], rxbuf[2], reply = 0;
+	ssize_t dpcd_ret;
+	int ret;
+
+	/* Output An first, that's easy */
+	dpcd_ret = drm_dp_dpcd_write(&intel_dig_port->dp.aux, DP_AUX_HDCP_AN,
+				     an, DRM_HDCP_AN_LEN);
+	if (dpcd_ret != DRM_HDCP_AN_LEN) {
+		DRM_ERROR("Failed to write An over DP/AUX (%zd)\n", dpcd_ret);
+		return dpcd_ret >= 0 ? -EIO : dpcd_ret;
+	}
+
+	/*
+	 * Since Aksv is Oh-So-Secret, we can't access it in software. So in
+	 * order to get it on the wire, we need to create the AUX header as if
+	 * we were writing the data, and then tickle the hardware to output the
+	 * data once the header is sent out.
+	 */
+	txbuf[0] = (DP_AUX_NATIVE_WRITE << 4) |
+		   ((DP_AUX_HDCP_AKSV >> 16) & 0xf);
+	txbuf[1] = (DP_AUX_HDCP_AKSV >> 8) & 0xff;
+	txbuf[2] = DP_AUX_HDCP_AKSV & 0xff;
+	txbuf[3] = DRM_HDCP_KSV_LEN - 1;
+
+	ret = intel_dp_aux_ch(intel_dp, txbuf, sizeof(txbuf), rxbuf,
+			      sizeof(rxbuf), true);
+	if (ret < 0) {
+		DRM_ERROR("Write Aksv over DP/AUX failed (%d)\n", ret);
+		return ret;
+	} else if (ret == 0) {
+		DRM_ERROR("Aksv write over DP/AUX was empty\n");
+		return -EIO;
+	}
+
+	reply = (rxbuf[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK;
+	return reply == DP_AUX_NATIVE_REPLY_ACK ? 0 : -EIO;
+}
+
+static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port,
+				   u8 *bksv)
+{
+	ssize_t ret;
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BKSV, bksv,
+			       DRM_HDCP_KSV_LEN);
+	if (ret != DRM_HDCP_KSV_LEN) {
+		DRM_ERROR("Read Bksv from DP/AUX failed (%zd)\n", ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+	return 0;
+}
+
+static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port,
+				      u8 *bstatus)
+{
+	ssize_t ret;
+	/*
+	 * For some reason the HDMI and DP HDCP specs call this register
+	 * definition by different names. In the HDMI spec, it's called BSTATUS,
+	 * but in DP it's called BINFO.
+	 */
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BINFO,
+			       bstatus, DRM_HDCP_BSTATUS_LEN);
+	if (ret != DRM_HDCP_BSTATUS_LEN) {
+		DRM_ERROR("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+	return 0;
+}
+
+static
+int intel_dp_hdcp_read_bcaps(struct intel_digital_port *intel_dig_port,
+			     u8 *bcaps)
+{
+	ssize_t ret;
+
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BCAPS,
+			       bcaps, 1);
+	if (ret != 1) {
+		DRM_ERROR("Read bcaps from DP/AUX failed (%zd)\n", ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+
+	return 0;
+}
+
+static
+int intel_dp_hdcp_repeater_present(struct intel_digital_port *intel_dig_port,
+				   bool *repeater_present)
+{
+	ssize_t ret;
+	u8 bcaps;
+
+	ret = intel_dp_hdcp_read_bcaps(intel_dig_port, &bcaps);
+	if (ret)
+		return ret;
+
+	*repeater_present = bcaps & DP_BCAPS_REPEATER_PRESENT;
+	return 0;
+}
+
+static
+int intel_dp_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port,
+				u8 *ri_prime)
+{
+	ssize_t ret;
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_RI_PRIME,
+			       ri_prime, DRM_HDCP_RI_LEN);
+	if (ret != DRM_HDCP_RI_LEN) {
+		DRM_ERROR("Read Ri' from DP/AUX failed (%zd)\n", ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+	return 0;
+}
+
+static
+int intel_dp_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port,
+				 bool *ksv_ready)
+{
+	ssize_t ret;
+	u8 bstatus;
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS,
+			       &bstatus, 1);
+	if (ret != 1) {
+		DRM_ERROR("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+	*ksv_ready = bstatus & DP_BSTATUS_READY;
+	return 0;
+}
+
+static
+int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port,
+				int num_downstream, u8 *ksv_fifo)
+{
+	ssize_t ret;
+	int i;
+
+	/* KSV list is read via 15 byte window (3 entries @ 5 bytes each) */
+	for (i = 0; i < num_downstream; i += 3) {
+		size_t len = min(num_downstream - i, 3) * DRM_HDCP_KSV_LEN;
+		ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux,
+				       DP_AUX_HDCP_KSV_FIFO,
+				       ksv_fifo + i * DRM_HDCP_KSV_LEN,
+				       len);
+		if (ret != len) {
+			DRM_ERROR("Read ksv[%d] from DP/AUX failed (%zd)\n", i,
+				  ret);
+			return ret >= 0 ? -EIO : ret;
+		}
+	}
+	return 0;
+}
+
+static
+int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
+				    int i, u32 *part)
+{
+	ssize_t ret;
+
+	if (i >= DRM_HDCP_V_PRIME_NUM_PARTS)
+		return -EINVAL;
+
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux,
+			       DP_AUX_HDCP_V_PRIME(i), part,
+			       DRM_HDCP_V_PRIME_PART_LEN);
+	if (ret != DRM_HDCP_V_PRIME_PART_LEN) {
+		DRM_ERROR("Read v'[%d] from DP/AUX failed (%zd)\n", i, ret);
+		return ret >= 0 ? -EIO : ret;
+	}
+	return 0;
+}
+
+static
+int intel_dp_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port,
+				    bool enable)
+{
+	/* Not used for single stream DisplayPort setups */
+	return 0;
+}
+
+static
+bool intel_dp_hdcp_check_link(struct intel_digital_port *intel_dig_port)
+{
+	ssize_t ret;
+	u8 bstatus;
+
+	ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS,
+			       &bstatus, 1);
+	if (ret != 1) {
+		DRM_ERROR("Read bstatus from DP/AUX failed (%zd)\n", ret);
+		return false;
+	}
+
+	return !(bstatus & (DP_BSTATUS_LINK_FAILURE | DP_BSTATUS_REAUTH_REQ));
+}
+
+static
+int intel_dp_hdcp_capable(struct intel_digital_port *intel_dig_port,
+			  bool *hdcp_capable)
+{
+	ssize_t ret;
+	u8 bcaps;
+
+	ret = intel_dp_hdcp_read_bcaps(intel_dig_port, &bcaps);
+	if (ret)
+		return ret;
+
+	*hdcp_capable = bcaps & DP_BCAPS_HDCP_CAPABLE;
+	return 0;
+}
+
+static const struct intel_hdcp_shim intel_dp_hdcp_shim = {
+	.write_an_aksv = intel_dp_hdcp_write_an_aksv,
+	.read_bksv = intel_dp_hdcp_read_bksv,
+	.read_bstatus = intel_dp_hdcp_read_bstatus,
+	.repeater_present = intel_dp_hdcp_repeater_present,
+	.read_ri_prime = intel_dp_hdcp_read_ri_prime,
+	.read_ksv_ready = intel_dp_hdcp_read_ksv_ready,
+	.read_ksv_fifo = intel_dp_hdcp_read_ksv_fifo,
+	.read_v_prime_part = intel_dp_hdcp_read_v_prime_part,
+	.toggle_signalling = intel_dp_hdcp_toggle_signalling,
+	.check_link = intel_dp_hdcp_check_link,
+	.hdcp_capable = intel_dp_hdcp_capable,
+};
+
 static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
@@ -5150,6 +5444,9 @@ err:
 		drm_modeset_acquire_fini(&ctx);
 		WARN(iret, "Acquiring modeset locks failed with %i\n", iret);
 
+		/* Short pulse can signify loss of hdcp authentication */
+		intel_hdcp_check_link(intel_dp->attached_connector);
+
 		if (!handled) {
 			intel_dp->detect_done = false;
 			goto put_power;
@@ -5227,7 +5524,8 @@ intel_pps_readout_hw_state(struct intel_dp *intel_dp, struct edp_power_seq *seq)
 
 	pp_on = I915_READ(regs.pp_on);
 	pp_off = I915_READ(regs.pp_off);
-	if (!IS_GEN9_LP(dev_priv) && !HAS_PCH_CNP(dev_priv)) {
+	if (!IS_GEN9_LP(dev_priv) && !HAS_PCH_CNP(dev_priv) &&
+	    !HAS_PCH_ICP(dev_priv)) {
 		I915_WRITE(regs.pp_ctrl, pp_ctl);
 		pp_div = I915_READ(regs.pp_div);
 	}
@@ -5245,7 +5543,8 @@ intel_pps_readout_hw_state(struct intel_dp *intel_dp, struct edp_power_seq *seq)
 	seq->t10 = (pp_off & PANEL_POWER_DOWN_DELAY_MASK) >>
 		   PANEL_POWER_DOWN_DELAY_SHIFT;
 
-	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv) ||
+	    HAS_PCH_ICP(dev_priv)) {
 		seq->t11_t12 = ((pp_ctl & BXT_POWER_CYCLE_DELAY_MASK) >>
 				BXT_POWER_CYCLE_DELAY_SHIFT) * 1000;
 	} else {
@@ -5416,7 +5715,8 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 		 (seq->t10 << PANEL_POWER_DOWN_DELAY_SHIFT);
 	/* Compute the divisor for the pp clock, simply match the Bspec
 	 * formula. */
-	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv) ||
+	    HAS_PCH_ICP(dev_priv)) {
 		pp_div = I915_READ(regs.pp_ctrl);
 		pp_div &= ~BXT_POWER_CYCLE_DELAY_MASK;
 		pp_div |= (DIV_ROUND_UP(seq->t11_t12, 1000)
@@ -5442,7 +5742,8 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 
 	I915_WRITE(regs.pp_on, pp_on);
 	I915_WRITE(regs.pp_off, pp_off);
-	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv))
+	if (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv) ||
+	    HAS_PCH_ICP(dev_priv))
 		I915_WRITE(regs.pp_ctrl, pp_div);
 	else
 		I915_WRITE(regs.pp_div, pp_div);
@@ -5450,7 +5751,8 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	DRM_DEBUG_KMS("panel power sequencer register settings: PP_ON %#x, PP_OFF %#x, PP_DIV %#x\n",
 		      I915_READ(regs.pp_on),
 		      I915_READ(regs.pp_off),
-		      (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv)) ?
+		      (IS_GEN9_LP(dev_priv) || HAS_PCH_CNP(dev_priv)  ||
+		       HAS_PCH_ICP(dev_priv)) ?
 		      (I915_READ(regs.pp_ctrl) & BXT_POWER_CYCLE_DELAY_MASK) :
 		      I915_READ(regs.pp_div));
 }
@@ -5970,8 +6272,10 @@ intel_dp_init_connector_port_info(struct intel_digital_port *intel_dig_port)
 {
 	struct intel_encoder *encoder = &intel_dig_port->base;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
 
-	encoder->hpd_pin = intel_hpd_pin(encoder->port);
+	encoder->hpd_pin = intel_hpd_pin_default(dev_priv, encoder->port);
 
 	switch (encoder->port) {
 	case PORT_A:
@@ -5990,6 +6294,9 @@ intel_dp_init_connector_port_info(struct intel_digital_port *intel_dig_port)
 		/* FIXME: Check VBT for actual wiring of PORT E */
 		intel_dp->aux_power_domain = POWER_DOMAIN_AUX_D;
 		break;
+	case PORT_F:
+		intel_dp->aux_power_domain = POWER_DOMAIN_AUX_F;
+		break;
 	default:
 		MISSING_CASE(encoder->port);
 	}
@@ -6116,7 +6423,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 
 	/* init MST on ports that can support it */
 	if (HAS_DP_MST(dev_priv) && !intel_dp_is_edp(intel_dp) &&
-	    (port == PORT_B || port == PORT_C || port == PORT_D))
+	    (port == PORT_B || port == PORT_C ||
+	     port == PORT_D || port == PORT_F))
 		intel_dp_mst_encoder_init(intel_dig_port,
 					  intel_connector->base.base.id);
 
@@ -6128,6 +6436,12 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 
 	intel_dp_add_properties(intel_dp, connector);
 
+	if (is_hdcp_supported(dev_priv, port) && !intel_dp_is_edp(intel_dp)) {
+		int ret = intel_hdcp_init(intel_connector, &intel_dp_hdcp_shim);
+		if (ret)
+			DRM_DEBUG_KMS("HDCP init failed, skipping.\n");
+	}
+
 	/* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written
 	 * 0xd.  Failure to do so will result in spurious interrupts being
 	 * generated on the port when a cable is not attached.
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 05907fa8a553..cf8fef8b6f58 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -328,14 +328,22 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	return;
 
  failure_handling:
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
-		      intel_connector->base.base.id,
-		      intel_connector->base.name,
-		      intel_dp->link_rate, intel_dp->lane_count);
-	if (!intel_dp_get_link_train_fallback_values(intel_dp,
-						     intel_dp->link_rate,
-						     intel_dp->lane_count))
-		/* Schedule a Hotplug Uevent to userspace to start modeset */
-		schedule_work(&intel_connector->modeset_retry_work);
+	/* Dont fallback and prune modes if its eDP */
+	if (!intel_dp_is_edp(intel_dp)) {
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+			      intel_connector->base.base.id,
+			      intel_connector->base.name,
+			      intel_dp->link_rate, intel_dp->lane_count);
+		if (!intel_dp_get_link_train_fallback_values(intel_dp,
+							     intel_dp->link_rate,
+							     intel_dp->lane_count))
+			/* Schedule a Hotplug Uevent to userspace to start modeset */
+			schedule_work(&intel_connector->modeset_retry_work);
+	} else {
+		DRM_ERROR("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+			  intel_connector->base.base.id,
+			  intel_connector->base.name,
+			  intel_dp->link_rate, intel_dp->lane_count);
+	}
 	return;
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index af2646d98512..468ec1e90e16 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -41,20 +41,21 @@
 #include <drm/drm_atomic.h>
 
 /**
- * _wait_for - magic (register) wait macro
+ * __wait_for - magic wait macro
  *
- * Does the right thing for modeset paths when run under kdgb or similar atomic
- * contexts. Note that it's important that we check the condition again after
- * having timed out, since the timeout could be due to preemption or similar and
- * we've never had a chance to check the condition before the timeout.
+ * Macro to help avoid open coding check/wait/timeout patterns. Note that it's
+ * important that we check the condition again after having timed out, since the
+ * timeout could be due to preemption or similar and we've never had a chance to
+ * check the condition before the timeout.
  */
-#define _wait_for(COND, US, Wmin, Wmax) ({ \
+#define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
 	unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1;	\
 	long wait__ = (Wmin); /* recommended min for usleep is 10 us */	\
 	int ret__;							\
 	might_sleep();							\
 	for (;;) {							\
 		bool expired__ = time_after(jiffies, timeout__);	\
+		OP;							\
 		if (COND) {						\
 			ret__ = 0;					\
 			break;						\
@@ -70,7 +71,9 @@
 	ret__;								\
 })
 
-#define wait_for(COND, MS)	_wait_for((COND), (MS) * 1000, 10, 1000)
+#define _wait_for(COND, US, Wmin, Wmax)	__wait_for(, (COND), (US), (Wmin), \
+						   (Wmax))
+#define wait_for(COND, MS)		_wait_for((COND), (MS) * 1000, 10, 1000)
 
 /* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */
 #if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT)
@@ -298,6 +301,80 @@ struct intel_panel {
 	} backlight;
 };
 
+/*
+ * This structure serves as a translation layer between the generic HDCP code
+ * and the bus-specific code. What that means is that HDCP over HDMI differs
+ * from HDCP over DP, so to account for these differences, we need to
+ * communicate with the receiver through this shim.
+ *
+ * For completeness, the 2 buses differ in the following ways:
+ *	- DP AUX vs. DDC
+ *		HDCP registers on the receiver are set via DP AUX for DP, and
+ *		they are set via DDC for HDMI.
+ *	- Receiver register offsets
+ *		The offsets of the registers are different for DP vs. HDMI
+ *	- Receiver register masks/offsets
+ *		For instance, the ready bit for the KSV fifo is in a different
+ *		place on DP vs HDMI
+ *	- Receiver register names
+ *		Seriously. In the DP spec, the 16-bit register containing
+ *		downstream information is called BINFO, on HDMI it's called
+ *		BSTATUS. To confuse matters further, DP has a BSTATUS register
+ *		with a completely different definition.
+ *	- KSV FIFO
+ *		On HDMI, the ksv fifo is read all at once, whereas on DP it must
+ *		be read 3 keys at a time
+ *	- Aksv output
+ *		Since Aksv is hidden in hardware, there's different procedures
+ *		to send it over DP AUX vs DDC
+ */
+struct intel_hdcp_shim {
+	/* Outputs the transmitter's An and Aksv values to the receiver. */
+	int (*write_an_aksv)(struct intel_digital_port *intel_dig_port, u8 *an);
+
+	/* Reads the receiver's key selection vector */
+	int (*read_bksv)(struct intel_digital_port *intel_dig_port, u8 *bksv);
+
+	/*
+	 * Reads BINFO from DP receivers and BSTATUS from HDMI receivers. The
+	 * definitions are the same in the respective specs, but the names are
+	 * different. Call it BSTATUS since that's the name the HDMI spec
+	 * uses and it was there first.
+	 */
+	int (*read_bstatus)(struct intel_digital_port *intel_dig_port,
+			    u8 *bstatus);
+
+	/* Determines whether a repeater is present downstream */
+	int (*repeater_present)(struct intel_digital_port *intel_dig_port,
+				bool *repeater_present);
+
+	/* Reads the receiver's Ri' value */
+	int (*read_ri_prime)(struct intel_digital_port *intel_dig_port, u8 *ri);
+
+	/* Determines if the receiver's KSV FIFO is ready for consumption */
+	int (*read_ksv_ready)(struct intel_digital_port *intel_dig_port,
+			      bool *ksv_ready);
+
+	/* Reads the ksv fifo for num_downstream devices */
+	int (*read_ksv_fifo)(struct intel_digital_port *intel_dig_port,
+			     int num_downstream, u8 *ksv_fifo);
+
+	/* Reads a 32-bit part of V' from the receiver */
+	int (*read_v_prime_part)(struct intel_digital_port *intel_dig_port,
+				 int i, u32 *part);
+
+	/* Enables HDCP signalling on the port */
+	int (*toggle_signalling)(struct intel_digital_port *intel_dig_port,
+				 bool enable);
+
+	/* Ensures the link is still protected */
+	bool (*check_link)(struct intel_digital_port *intel_dig_port);
+
+	/* Detects panel's hdcp capability. This is optional for HDMI. */
+	int (*hdcp_capable)(struct intel_digital_port *intel_dig_port,
+			    bool *hdcp_capable);
+};
+
 struct intel_connector {
 	struct drm_connector base;
 	/*
@@ -329,6 +406,12 @@ struct intel_connector {
 
 	/* Work struct to schedule a uevent on link train failure */
 	struct work_struct modeset_retry_work;
+
+	const struct intel_hdcp_shim *hdcp_shim;
+	struct mutex hdcp_mutex;
+	uint64_t hdcp_value; /* protected by hdcp_mutex */
+	struct delayed_work hdcp_check_work;
+	struct work_struct hdcp_prop_work;
 };
 
 struct intel_digital_connector_state {
@@ -1297,6 +1380,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 u32 bxt_signal_levels(struct intel_dp *intel_dp);
 uint32_t ddi_signal_levels(struct intel_dp *intel_dp);
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder);
+int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
+				     bool enable);
 
 unsigned int intel_fb_align_height(const struct drm_framebuffer *fb,
 				   int plane, unsigned int height);
@@ -1506,7 +1591,8 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state);
 u32 skl_plane_stride(const struct drm_framebuffer *fb, int plane,
 		     unsigned int rotation);
-int skl_check_plane_surface(struct intel_plane_state *plane_state);
+int skl_check_plane_surface(const struct intel_crtc_state *crtc_state,
+			    struct intel_plane_state *plane_state);
 int i9xx_check_plane_surface(struct intel_plane_state *plane_state);
 
 /* intel_csr.c */
@@ -1589,8 +1675,7 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 int intel_dp_link_required(int pixel_clock, int bpp);
 int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
-bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
-				  struct intel_digital_port *port);
+bool intel_digital_port_connected(struct intel_encoder *encoder);
 
 /* intel_dp_aux_backlight.c */
 int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
@@ -1757,8 +1842,19 @@ static inline void intel_backlight_device_unregister(struct intel_connector *con
 }
 #endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
 
+/* intel_hdcp.c */
+void intel_hdcp_atomic_check(struct drm_connector *connector,
+			     struct drm_connector_state *old_state,
+			     struct drm_connector_state *new_state);
+int intel_hdcp_init(struct intel_connector *connector,
+		    const struct intel_hdcp_shim *hdcp_shim);
+int intel_hdcp_enable(struct intel_connector *connector);
+int intel_hdcp_disable(struct intel_connector *connector);
+int intel_hdcp_check_link(struct intel_connector *connector);
+bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port);
 
 /* intel_psr.c */
+#define CAN_PSR(dev_priv) (HAS_PSR(dev_priv) && dev_priv->psr.sink_support)
 void intel_psr_enable(struct intel_dp *intel_dp,
 		      const struct intel_crtc_state *crtc_state);
 void intel_psr_disable(struct intel_dp *intel_dp,
@@ -1931,6 +2027,8 @@ void skl_update_plane(struct intel_plane *plane,
 		      const struct intel_plane_state *plane_state);
 void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
 bool skl_plane_get_hw_state(struct intel_plane *plane);
+bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
+		       enum pipe pipe, enum plane_id plane_id);
 
 /* intel_tv.c */
 void intel_tv_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 6bb51a502b8b..7eebfbb95e89 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -38,9 +38,11 @@
  */
 #define HSW_CXT_TOTAL_SIZE		(17 * PAGE_SIZE)
 
+#define DEFAULT_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
 #define GEN8_LR_CONTEXT_RENDER_SIZE	(20 * PAGE_SIZE)
 #define GEN9_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
 #define GEN10_LR_CONTEXT_RENDER_SIZE	(18 * PAGE_SIZE)
+#define GEN11_LR_CONTEXT_RENDER_SIZE	(14 * PAGE_SIZE)
 
 #define GEN8_LR_CONTEXT_OTHER_SIZE	( 2 * PAGE_SIZE)
 
@@ -157,6 +159,9 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		switch (INTEL_GEN(dev_priv)) {
 		default:
 			MISSING_CASE(INTEL_GEN(dev_priv));
+			return DEFAULT_LR_CONTEXT_RENDER_SIZE;
+		case 11:
+			return GEN11_LR_CONTEXT_RENDER_SIZE;
 		case 10:
 			return GEN10_LR_CONTEXT_RENDER_SIZE;
 		case 9:
@@ -1389,7 +1394,8 @@ int init_workarounds_ring(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->i915;
 	int err;
 
-	WARN_ON(engine->id != RCS);
+	if (GEM_WARN_ON(engine->id != RCS))
+		return -EINVAL;
 
 	dev_priv->workarounds.count = 0;
 	dev_priv->workarounds.hw_whitelist_count[engine->id] = 0;
@@ -1943,24 +1949,42 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
  */
 int intel_enable_engine_stats(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists *execlists = &engine->execlists;
 	unsigned long flags;
+	int err = 0;
 
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
+	tasklet_disable(&execlists->tasklet);
 	spin_lock_irqsave(&engine->stats.lock, flags);
-	if (engine->stats.enabled == ~0)
-		goto busy;
-	if (engine->stats.enabled++ == 0)
+
+	if (unlikely(engine->stats.enabled == ~0)) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	if (engine->stats.enabled++ == 0) {
+		const struct execlist_port *port = execlists->port;
+		unsigned int num_ports = execlists_num_ports(execlists);
+
 		engine->stats.enabled_at = ktime_get();
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
 
-	return 0;
+		/* XXX submission method oblivious? */
+		while (num_ports-- && port_isset(port)) {
+			engine->stats.active++;
+			port++;
+		}
 
-busy:
+		if (engine->stats.active)
+			engine->stats.start = engine->stats.enabled_at;
+	}
+
+unlock:
 	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	tasklet_enable(&execlists->tasklet);
 
-	return -EBUSY;
+	return err;
 }
 
 static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index eee1b02c827e..d7d1ac79c38a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -492,7 +492,8 @@ static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
 	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,
+				 const char *reason)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
@@ -505,6 +506,8 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv)
 
 	if (fbc->active)
 		intel_fbc_hw_deactivate(dev_priv);
+
+	fbc->no_fbc_reason = reason;
 }
 
 static bool multiple_pipes_ok(struct intel_crtc *crtc,
@@ -668,11 +671,13 @@ void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv)
 static bool stride_is_valid(struct drm_i915_private *dev_priv,
 			    unsigned int stride)
 {
-	/* These should have been caught earlier. */
-	WARN_ON(stride < 512);
-	WARN_ON((stride & (64 - 1)) != 0);
+	/* This should have been caught earlier. */
+	if (WARN_ON_ONCE((stride & (64 - 1)) != 0))
+		return false;
 
 	/* Below are the additional FBC restrictions. */
+	if (stride < 512)
+		return false;
 
 	if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv))
 		return stride == 4096 || stride == 8192;
@@ -920,6 +925,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
+	const char *reason = "update pending";
 
 	if (!fbc_supported(dev_priv))
 		return;
@@ -927,7 +933,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc,
 	mutex_lock(&fbc->lock);
 
 	if (!multiple_pipes_ok(crtc, plane_state)) {
-		fbc->no_fbc_reason = "more than one pipe active";
+		reason = "more than one pipe active";
 		goto deactivate;
 	}
 
@@ -937,7 +943,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc,
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
 
 deactivate:
-	intel_fbc_deactivate(dev_priv);
+	intel_fbc_deactivate(dev_priv, reason);
 unlock:
 	mutex_unlock(&fbc->lock);
 }
@@ -970,9 +976,8 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 	    intel_fbc_reg_params_equal(&old_params, &fbc->params))
 		return;
 
-	intel_fbc_deactivate(dev_priv);
+	intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
 	intel_fbc_schedule_activation(crtc);
-	fbc->no_fbc_reason = "FBC enabled (active or scheduled)";
 }
 
 void intel_fbc_post_update(struct intel_crtc *crtc)
@@ -1013,7 +1018,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 	fbc->busy_bits |= intel_fbc_get_frontbuffer_bit(fbc) & frontbuffer_bits;
 
 	if (fbc->enabled && fbc->busy_bits)
-		intel_fbc_deactivate(dev_priv);
+		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 
 	mutex_unlock(&fbc->lock);
 }
@@ -1243,7 +1248,7 @@ static void intel_fbc_underrun_work_fn(struct work_struct *work)
 	DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n");
 	fbc->underrun_detected = true;
 
-	intel_fbc_deactivate(dev_priv);
+	intel_fbc_deactivate(dev_priv, "FIFO underrun");
 out:
 	mutex_unlock(&fbc->lock);
 }
@@ -1370,7 +1375,7 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 
 	for_each_pipe(dev_priv, pipe) {
 		fbc->possible_framebuffer_bits |=
-				INTEL_FRONTBUFFER_PRIMARY(pipe);
+			INTEL_FRONTBUFFER(pipe, PLANE_PRIMARY);
 
 		if (fbc_on_pipe_a_only(dev_priv))
 			break;
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 3c6bf5a34c3c..21140ccd7a97 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -23,6 +23,7 @@
  */
 
 #include "intel_guc.h"
+#include "intel_guc_ads.h"
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
 
@@ -63,6 +64,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 {
 	intel_guc_fw_init_early(guc);
 	intel_guc_ct_init_early(&guc->ct);
+	intel_guc_log_init_early(guc);
 
 	mutex_init(&guc->send_mutex);
 	guc->send = intel_guc_send_nop;
@@ -86,8 +88,10 @@ int intel_guc_init_wq(struct intel_guc *guc)
 	 */
 	guc->log.runtime.flush_wq = alloc_ordered_workqueue("i915-guc_log",
 						WQ_HIGHPRI | WQ_FREEZABLE);
-	if (!guc->log.runtime.flush_wq)
+	if (!guc->log.runtime.flush_wq) {
+		DRM_ERROR("Couldn't allocate workqueue for GuC log\n");
 		return -ENOMEM;
+	}
 
 	/*
 	 * Even though both sending GuC action, and adding a new workitem to
@@ -108,6 +112,8 @@ int intel_guc_init_wq(struct intel_guc *guc)
 							  WQ_HIGHPRI);
 		if (!guc->preempt_wq) {
 			destroy_workqueue(guc->log.runtime.flush_wq);
+			DRM_ERROR("Couldn't allocate workqueue for GuC "
+				  "preemption\n");
 			return -ENOMEM;
 		}
 	}
@@ -163,10 +169,25 @@ int intel_guc_init(struct intel_guc *guc)
 		return ret;
 	GEM_BUG_ON(!guc->shared_data);
 
+	ret = intel_guc_log_create(guc);
+	if (ret)
+		goto err_shared;
+
+	ret = intel_guc_ads_create(guc);
+	if (ret)
+		goto err_log;
+	GEM_BUG_ON(!guc->ads_vma);
+
 	/* We need to notify the guc whenever we change the GGTT */
 	i915_ggtt_enable_guc(dev_priv);
 
 	return 0;
+
+err_log:
+	intel_guc_log_destroy(guc);
+err_shared:
+	guc_shared_data_destroy(guc);
+	return ret;
 }
 
 void intel_guc_fini(struct intel_guc *guc)
@@ -174,6 +195,8 @@ void intel_guc_fini(struct intel_guc *guc)
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
 	i915_ggtt_disable_guc(dev_priv);
+	intel_guc_ads_destroy(guc);
+	intel_guc_log_destroy(guc);
 	guc_shared_data_destroy(guc);
 }
 
@@ -197,6 +220,19 @@ static u32 get_core_family(struct drm_i915_private *dev_priv)
 	}
 }
 
+static u32 get_log_verbosity_flags(void)
+{
+	if (i915_modparams.guc_log_level > 0) {
+		u32 verbosity = i915_modparams.guc_log_level - 1;
+
+		GEM_BUG_ON(verbosity > GUC_LOG_VERBOSITY_MAX);
+		return verbosity << GUC_LOG_VERBOSITY_SHIFT;
+	}
+
+	GEM_BUG_ON(i915_modparams.enable_guc < 0);
+	return GUC_LOG_DISABLED;
+}
+
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -229,12 +265,7 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
 
-	if (i915_modparams.guc_log_level >= 0) {
-		params[GUC_CTL_DEBUG] =
-			i915_modparams.guc_log_level << GUC_LOG_VERBOSITY_SHIFT;
-	} else {
-		params[GUC_CTL_DEBUG] = GUC_LOG_DISABLED;
-	}
+	params[GUC_CTL_DEBUG] = get_log_verbosity_flags();
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (USES_GUC_SUBMISSION(dev_priv)) {
@@ -427,7 +458,7 @@ int intel_guc_resume(struct drm_i915_private *dev_priv)
 	if (guc->fw.load_status != INTEL_UC_FIRMWARE_SUCCESS)
 		return 0;
 
-	if (i915_modparams.guc_log_level >= 0)
+	if (i915_modparams.guc_log_level)
 		gen9_enable_guc_interrupts(dev_priv);
 
 	data[0] = INTEL_GUC_ACTION_EXIT_S_STATE;
diff --git a/drivers/gpu/drm/i915/intel_guc_ads.c b/drivers/gpu/drm/i915/intel_guc_ads.c
new file mode 100644
index 000000000000..ac627534667d
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_guc_ads.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright © 2014-2017 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include "intel_guc_ads.h"
+#include "intel_uc.h"
+#include "i915_drv.h"
+
+/*
+ * The Additional Data Struct (ADS) has pointers for different buffers used by
+ * the GuC. One single gem object contains the ADS struct itself (guc_ads), the
+ * scheduling policies (guc_policies), a structure describing a collection of
+ * register sets (guc_mmio_reg_state) and some extra pages for the GuC to save
+ * its internal state for sleep.
+ */
+
+static void guc_policy_init(struct guc_policy *policy)
+{
+	policy->execution_quantum = POLICY_DEFAULT_EXECUTION_QUANTUM_US;
+	policy->preemption_time = POLICY_DEFAULT_PREEMPTION_TIME_US;
+	policy->fault_time = POLICY_DEFAULT_FAULT_TIME_US;
+	policy->policy_flags = 0;
+}
+
+static void guc_policies_init(struct guc_policies *policies)
+{
+	struct guc_policy *policy;
+	u32 p, i;
+
+	policies->dpc_promote_time = POLICY_DEFAULT_DPC_PROMOTE_TIME_US;
+	policies->max_num_work_items = POLICY_MAX_NUM_WI;
+
+	for (p = 0; p < GUC_CLIENT_PRIORITY_NUM; p++) {
+		for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
+			policy = &policies->policy[p][i];
+
+			guc_policy_init(policy);
+		}
+	}
+
+	policies->is_valid = 1;
+}
+
+/*
+ * The first 80 dwords of the register state context, containing the
+ * execlists and ppgtt registers.
+ */
+#define LR_HW_CONTEXT_SIZE	(80 * sizeof(u32))
+
+/**
+ * intel_guc_ads_create() - creates GuC ADS
+ * @guc: intel_guc struct
+ *
+ */
+int intel_guc_ads_create(struct intel_guc *guc)
+{
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct i915_vma *vma;
+	struct page *page;
+	/* The ads obj includes the struct itself and buffers passed to GuC */
+	struct {
+		struct guc_ads ads;
+		struct guc_policies policies;
+		struct guc_mmio_reg_state reg_state;
+		u8 reg_state_buffer[GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE];
+	} __packed *blob;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	const u32 skipped_offset = LRC_HEADER_PAGES * PAGE_SIZE;
+	const u32 skipped_size = LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE;
+	u32 base;
+
+	GEM_BUG_ON(guc->ads_vma);
+
+	vma = intel_guc_allocate_vma(guc, PAGE_ALIGN(sizeof(*blob)));
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	guc->ads_vma = vma;
+
+	page = i915_vma_first_page(vma);
+	blob = kmap(page);
+
+	/* GuC scheduling policies */
+	guc_policies_init(&blob->policies);
+
+	/* MMIO reg state */
+	for_each_engine(engine, dev_priv, id) {
+		blob->reg_state.white_list[engine->guc_id].mmio_start =
+			engine->mmio_base + GUC_MMIO_WHITE_LIST_START;
+
+		/* Nothing to be saved or restored for now. */
+		blob->reg_state.white_list[engine->guc_id].count = 0;
+	}
+
+	/*
+	 * The GuC requires a "Golden Context" when it reinitialises
+	 * engines after a reset. Here we use the Render ring default
+	 * context, which must already exist and be pinned in the GGTT,
+	 * so its address won't change after we've told the GuC where
+	 * to find it. Note that we have to skip our header (1 page),
+	 * because our GuC shared data is there.
+	 */
+	blob->ads.golden_context_lrca =
+		guc_ggtt_offset(dev_priv->kernel_context->engine[RCS].state) +
+		skipped_offset;
+
+	/*
+	 * The GuC expects us to exclude the portion of the context image that
+	 * it skips from the size it is to read. It starts reading from after
+	 * the execlist context (so skipping the first page [PPHWSP] and 80
+	 * dwords). Weird guc is weird.
+	 */
+	for_each_engine(engine, dev_priv, id)
+		blob->ads.eng_state_size[engine->guc_id] =
+			engine->context_size - skipped_size;
+
+	base = guc_ggtt_offset(vma);
+	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
+	blob->ads.reg_state_buffer = base + ptr_offset(blob, reg_state_buffer);
+	blob->ads.reg_state_addr = base + ptr_offset(blob, reg_state);
+
+	kunmap(page);
+
+	return 0;
+}
+
+void intel_guc_ads_destroy(struct intel_guc *guc)
+{
+	i915_vma_unpin_and_release(&guc->ads_vma);
+}
diff --git a/drivers/gpu/drm/i915/intel_guc_ads.h b/drivers/gpu/drm/i915/intel_guc_ads.h
new file mode 100644
index 000000000000..c4735742c564
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_guc_ads.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright © 2014-2017 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _INTEL_GUC_ADS_H_
+#define _INTEL_GUC_ADS_H_
+
+struct intel_guc;
+
+int intel_guc_ads_create(struct intel_guc *guc);
+void intel_guc_ads_destroy(struct intel_guc *guc);
+
+#endif
diff --git a/drivers/gpu/drm/i915/intel_guc_fw.c b/drivers/gpu/drm/i915/intel_guc_fw.c
index cbc51c960425..3b0932942857 100644
--- a/drivers/gpu/drm/i915/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/intel_guc_fw.c
@@ -39,9 +39,6 @@
 #define KBL_FW_MAJOR 9
 #define KBL_FW_MINOR 39
 
-#define GLK_FW_MAJOR 10
-#define GLK_FW_MINOR 56
-
 #define GUC_FW_PATH(platform, major, minor) \
        "i915/" __stringify(platform) "_guc_ver" __stringify(major) "_" __stringify(minor) ".bin"
 
@@ -54,8 +51,6 @@ MODULE_FIRMWARE(I915_BXT_GUC_UCODE);
 #define I915_KBL_GUC_UCODE GUC_FW_PATH(kbl, KBL_FW_MAJOR, KBL_FW_MINOR)
 MODULE_FIRMWARE(I915_KBL_GUC_UCODE);
 
-#define I915_GLK_GUC_UCODE GUC_FW_PATH(glk, GLK_FW_MAJOR, GLK_FW_MINOR)
-
 static void guc_fw_select(struct intel_uc_fw *guc_fw)
 {
 	struct intel_guc *guc = container_of(guc_fw, struct intel_guc, fw);
@@ -82,10 +77,6 @@ static void guc_fw_select(struct intel_uc_fw *guc_fw)
 		guc_fw->path = I915_KBL_GUC_UCODE;
 		guc_fw->major_ver_wanted = KBL_FW_MAJOR;
 		guc_fw->minor_ver_wanted = KBL_FW_MINOR;
-	} else if (IS_GEMINILAKE(dev_priv)) {
-		guc_fw->path = I915_GLK_GUC_UCODE;
-		guc_fw->major_ver_wanted = GLK_FW_MAJOR;
-		guc_fw->minor_ver_wanted = GLK_FW_MINOR;
 	} else {
 		DRM_WARN("%s: No firmware known for this platform!\n",
 			 intel_uc_fw_type_repr(guc_fw->type));
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index eaedd63e3819..7b5074e2120c 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -33,11 +33,10 @@ static void guc_log_capture_logs(struct intel_guc *guc);
 /**
  * DOC: GuC firmware log
  *
- * Firmware log is enabled by setting i915.guc_log_level to non-negative level.
+ * Firmware log is enabled by setting i915.guc_log_level to the positive level.
  * Log data is printed out via reading debugfs i915_guc_log_dump. Reading from
  * i915_guc_load_status will print out firmware loading status and scratch
  * registers value.
- *
  */
 
 static int guc_log_flush_complete(struct intel_guc *guc)
@@ -59,11 +58,15 @@ static int guc_log_flush(struct intel_guc *guc)
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
-static int guc_log_control(struct intel_guc *guc, u32 control_val)
+static int guc_log_control(struct intel_guc *guc, bool enable, u32 verbosity)
 {
+	union guc_log_control control_val = {
+		.logging_enabled = enable,
+		.verbosity = verbosity,
+	};
 	u32 action[] = {
 		INTEL_GUC_ACTION_UK_LOG_ENABLE_LOGGING,
-		control_val
+		control_val.value
 	};
 
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
@@ -78,7 +81,8 @@ static int subbuf_start_callback(struct rchan_buf *buf,
 				 void *prev_subbuf,
 				 size_t prev_padding)
 {
-	/* Use no-overwrite mode by default, where relay will stop accepting
+	/*
+	 * Use no-overwrite mode by default, where relay will stop accepting
 	 * new data if there are no empty sub buffers left.
 	 * There is no strict synchronization enforced by relay between Consumer
 	 * and Producer. In overwrite mode, there is a possibility of getting
@@ -104,7 +108,8 @@ static struct dentry *create_buf_file_callback(const char *filename,
 {
 	struct dentry *buf_file;
 
-	/* This to enable the use of a single buffer for the relay channel and
+	/*
+	 * This to enable the use of a single buffer for the relay channel and
 	 * correspondingly have a single file exposed to User, through which
 	 * it can collect the logs in order without any post-processing.
 	 * Need to set 'is_global' even if parent is NULL for early logging.
@@ -114,7 +119,8 @@ static struct dentry *create_buf_file_callback(const char *filename,
 	if (!parent)
 		return NULL;
 
-	/* Not using the channel filename passed as an argument, since for each
+	/*
+	 * Not using the channel filename passed as an argument, since for each
 	 * channel relay appends the corresponding CPU number to the filename
 	 * passed in relay_open(). This should be fine as relay just needs a
 	 * dentry of the file associated with the channel buffer and that file's
@@ -147,13 +153,16 @@ static int guc_log_relay_file_create(struct intel_guc *guc)
 	struct dentry *log_dir;
 	int ret;
 
-	if (i915_modparams.guc_log_level < 0)
+	if (!i915_modparams.guc_log_level)
 		return 0;
 
+	mutex_lock(&guc->log.runtime.relay_lock);
+
 	/* For now create the log file in /sys/kernel/debug/dri/0 dir */
 	log_dir = dev_priv->drm.primary->debugfs_root;
 
-	/* If /sys/kernel/debug/dri/0 location do not exist, then debugfs is
+	/*
+	 * If /sys/kernel/debug/dri/0 location do not exist, then debugfs is
 	 * not mounted and so can't create the relay file.
 	 * The relay API seems to fit well with debugfs only, for availing relay
 	 * there are 3 requirements which can be met for debugfs file only in a
@@ -166,25 +175,41 @@ static int guc_log_relay_file_create(struct intel_guc *guc)
 	 */
 	if (!log_dir) {
 		DRM_ERROR("Debugfs dir not available yet for GuC log file\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_unlock;
 	}
 
 	ret = relay_late_setup_files(guc->log.runtime.relay_chan, "guc_log", log_dir);
 	if (ret < 0 && ret != -EEXIST) {
 		DRM_ERROR("Couldn't associate relay chan with file %d\n", ret);
-		return ret;
+		goto out_unlock;
 	}
 
-	return 0;
+	ret = 0;
+
+out_unlock:
+	mutex_unlock(&guc->log.runtime.relay_lock);
+	return ret;
+}
+
+static bool guc_log_has_relay(struct intel_guc *guc)
+{
+	lockdep_assert_held(&guc->log.runtime.relay_lock);
+
+	return guc->log.runtime.relay_chan != NULL;
 }
 
 static void guc_move_to_next_buf(struct intel_guc *guc)
 {
-	/* Make sure the updates made in the sub buffer are visible when
+	/*
+	 * Make sure the updates made in the sub buffer are visible when
 	 * Consumer sees the following update to offset inside the sub buffer.
 	 */
 	smp_wmb();
 
+	if (!guc_log_has_relay(guc))
+		return;
+
 	/* All data has been written, so now move the offset of sub buffer. */
 	relay_reserve(guc->log.runtime.relay_chan, guc->log.vma->obj->base.size);
 
@@ -194,10 +219,11 @@ static void guc_move_to_next_buf(struct intel_guc *guc)
 
 static void *guc_get_write_buffer(struct intel_guc *guc)
 {
-	if (!guc->log.runtime.relay_chan)
+	if (!guc_log_has_relay(guc))
 		return NULL;
 
-	/* Just get the base address of a new sub buffer and copy data into it
+	/*
+	 * Just get the base address of a new sub buffer and copy data into it
 	 * ourselves. NULL will be returned in no-overwrite mode, if all sub
 	 * buffers are full. Could have used the relay_write() to indirectly
 	 * copy the data, but that would have been bit convoluted, as we need to
@@ -262,15 +288,30 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 	/* Get the pointer to shared GuC log buffer */
 	log_buf_state = src_data = guc->log.runtime.buf_addr;
 
+	mutex_lock(&guc->log.runtime.relay_lock);
+
 	/* Get the pointer to local buffer to store the logs */
 	log_buf_snapshot_state = dst_data = guc_get_write_buffer(guc);
 
+	if (unlikely(!log_buf_snapshot_state)) {
+		/*
+		 * Used rate limited to avoid deluge of messages, logs might be
+		 * getting consumed by User at a slow rate.
+		 */
+		DRM_ERROR_RATELIMITED("no sub-buffer to capture logs\n");
+		guc->log.capture_miss_count++;
+		mutex_unlock(&guc->log.runtime.relay_lock);
+
+		return;
+	}
+
 	/* Actual logs are present from the 2nd page */
 	src_data += PAGE_SIZE;
 	dst_data += PAGE_SIZE;
 
 	for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
-		/* Make a copy of the state structure, inside GuC log buffer
+		/*
+		 * Make a copy of the state structure, inside GuC log buffer
 		 * (which is uncached mapped), on the stack to avoid reading
 		 * from it multiple times.
 		 */
@@ -290,14 +331,12 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 		log_buf_state->flush_to_file = 0;
 		log_buf_state++;
 
-		if (unlikely(!log_buf_snapshot_state))
-			continue;
-
 		/* First copy the state structure in snapshot buffer */
 		memcpy(log_buf_snapshot_state, &log_buf_state_local,
 		       sizeof(struct guc_log_buffer_state));
 
-		/* The write pointer could have been updated by GuC firmware,
+		/*
+		 * The write pointer could have been updated by GuC firmware,
 		 * after sending the flush interrupt to Host, for consistency
 		 * set write pointer value to same value of sampled_write_ptr
 		 * in the snapshot buffer.
@@ -332,15 +371,9 @@ static void guc_read_update_log_buffer(struct intel_guc *guc)
 		dst_data += buffer_size;
 	}
 
-	if (log_buf_snapshot_state)
-		guc_move_to_next_buf(guc);
-	else {
-		/* Used rate limited to avoid deluge of messages, logs might be
-		 * getting consumed by User at a slow rate.
-		 */
-		DRM_ERROR_RATELIMITED("no sub-buffer to capture logs\n");
-		guc->log.capture_miss_count++;
-	}
+	guc_move_to_next_buf(guc);
+
+	mutex_unlock(&guc->log.runtime.relay_lock);
 }
 
 static void capture_logs_work(struct work_struct *work)
@@ -360,19 +393,21 @@ static int guc_log_runtime_create(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	void *vaddr;
-	struct rchan *guc_log_relay_chan;
-	size_t n_subbufs, subbuf_size;
 	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
+	if (!guc->log.vma)
+		return -ENODEV;
+
 	GEM_BUG_ON(guc_log_has_runtime(guc));
 
 	ret = i915_gem_object_set_to_wc_domain(guc->log.vma->obj, true);
 	if (ret)
 		return ret;
 
-	/* Create a WC (Uncached for read) vmalloc mapping of log
+	/*
+	 * Create a WC (Uncached for read) vmalloc mapping of log
 	 * buffer pages, so that we can directly get the data
 	 * (up-to-date) from memory.
 	 */
@@ -384,17 +419,55 @@ static int guc_log_runtime_create(struct intel_guc *guc)
 
 	guc->log.runtime.buf_addr = vaddr;
 
+	return 0;
+}
+
+static void guc_log_runtime_destroy(struct intel_guc *guc)
+{
+	/*
+	 * It's possible that the runtime stuff was never allocated because
+	 * GuC log was disabled at the boot time.
+	 */
+	if (!guc_log_has_runtime(guc))
+		return;
+
+	i915_gem_object_unpin_map(guc->log.vma->obj);
+	guc->log.runtime.buf_addr = NULL;
+}
+
+void intel_guc_log_init_early(struct intel_guc *guc)
+{
+	mutex_init(&guc->log.runtime.relay_lock);
+	INIT_WORK(&guc->log.runtime.flush_work, capture_logs_work);
+}
+
+int intel_guc_log_relay_create(struct intel_guc *guc)
+{
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct rchan *guc_log_relay_chan;
+	size_t n_subbufs, subbuf_size;
+	int ret;
+
+	if (!i915_modparams.guc_log_level)
+		return 0;
+
+	mutex_lock(&guc->log.runtime.relay_lock);
+
+	GEM_BUG_ON(guc_log_has_relay(guc));
+
 	 /* Keep the size of sub buffers same as shared log buffer */
-	subbuf_size = guc->log.vma->obj->base.size;
+	subbuf_size = GUC_LOG_SIZE;
 
-	/* Store up to 8 snapshots, which is large enough to buffer sufficient
+	/*
+	 * Store up to 8 snapshots, which is large enough to buffer sufficient
 	 * boot time logs and provides enough leeway to User, in terms of
 	 * latency, for consuming the logs from relay. Also doesn't take
 	 * up too much memory.
 	 */
 	n_subbufs = 8;
 
-	/* Create a relay channel, so that we have buffers for storing
+	/*
+	 * Create a relay channel, so that we have buffers for storing
 	 * the GuC firmware logs, the channel will be linked with a file
 	 * later on when debugfs is registered.
 	 */
@@ -404,33 +477,39 @@ static int guc_log_runtime_create(struct intel_guc *guc)
 		DRM_ERROR("Couldn't create relay chan for GuC logging\n");
 
 		ret = -ENOMEM;
-		goto err_vaddr;
+		goto err;
 	}
 
 	GEM_BUG_ON(guc_log_relay_chan->subbuf_size < subbuf_size);
 	guc->log.runtime.relay_chan = guc_log_relay_chan;
 
-	INIT_WORK(&guc->log.runtime.flush_work, capture_logs_work);
+	mutex_unlock(&guc->log.runtime.relay_lock);
+
 	return 0;
 
-err_vaddr:
-	i915_gem_object_unpin_map(guc->log.vma->obj);
-	guc->log.runtime.buf_addr = NULL;
+err:
+	mutex_unlock(&guc->log.runtime.relay_lock);
+	/* logging will be off */
+	i915_modparams.guc_log_level = 0;
 	return ret;
 }
 
-static void guc_log_runtime_destroy(struct intel_guc *guc)
+void intel_guc_log_relay_destroy(struct intel_guc *guc)
 {
+	mutex_lock(&guc->log.runtime.relay_lock);
+
 	/*
-	 * It's possible that the runtime stuff was never allocated because
-	 * guc_log_level was < 0 at the time
-	 **/
-	if (!guc_log_has_runtime(guc))
-		return;
+	 * It's possible that the relay was never allocated because
+	 * GuC log was disabled at the boot time.
+	 */
+	if (!guc_log_has_relay(guc))
+		goto out_unlock;
 
 	relay_close(guc->log.runtime.relay_chan);
-	i915_gem_object_unpin_map(guc->log.vma->obj);
-	guc->log.runtime.buf_addr = NULL;
+	guc->log.runtime.relay_chan = NULL;
+
+out_unlock:
+	mutex_unlock(&guc->log.runtime.relay_lock);
 }
 
 static int guc_log_late_setup(struct intel_guc *guc)
@@ -438,16 +517,24 @@ static int guc_log_late_setup(struct intel_guc *guc)
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	int ret;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	if (!guc_log_has_runtime(guc)) {
-		/* If log_level was set as -1 at boot time, then setup needed to
-		 * handle log buffer flush interrupts would not have been done yet,
-		 * so do that now.
+		/*
+		 * If log was disabled at boot time, then setup needed to handle
+		 * log buffer flush interrupts would not have been done yet, so
+		 * do that now.
 		 */
-		ret = guc_log_runtime_create(guc);
+		ret = intel_guc_log_relay_create(guc);
 		if (ret)
 			goto err;
+
+		mutex_lock(&dev_priv->drm.struct_mutex);
+		intel_runtime_pm_get(dev_priv);
+		ret = guc_log_runtime_create(guc);
+		intel_runtime_pm_put(dev_priv);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
+
+		if (ret)
+			goto err_relay;
 	}
 
 	ret = guc_log_relay_file_create(guc);
@@ -457,10 +544,14 @@ static int guc_log_late_setup(struct intel_guc *guc)
 	return 0;
 
 err_runtime:
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	guc_log_runtime_destroy(guc);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+err_relay:
+	intel_guc_log_relay_destroy(guc);
 err:
 	/* logging will remain off */
-	i915_modparams.guc_log_level = -1;
+	i915_modparams.guc_log_level = 0;
 	return ret;
 }
 
@@ -470,7 +561,8 @@ static void guc_log_capture_logs(struct intel_guc *guc)
 
 	guc_read_update_log_buffer(guc);
 
-	/* Generally device is expected to be active only at this
+	/*
+	 * Generally device is expected to be active only at this
 	 * time, so get/put should be really quick.
 	 */
 	intel_runtime_pm_get(dev_priv);
@@ -482,20 +574,26 @@ static void guc_flush_logs(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
-	if (!USES_GUC_SUBMISSION(dev_priv) ||
-	    (i915_modparams.guc_log_level < 0))
+	if (!USES_GUC_SUBMISSION(dev_priv) || !i915_modparams.guc_log_level)
 		return;
 
 	/* First disable the interrupts, will be renabled afterwards */
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	intel_runtime_pm_get(dev_priv);
 	gen9_disable_guc_interrupts(dev_priv);
+	intel_runtime_pm_put(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	/* Before initiating the forceful flush, wait for any pending/ongoing
+	/*
+	 * Before initiating the forceful flush, wait for any pending/ongoing
 	 * flush to complete otherwise forceful flush may not actually happen.
 	 */
 	flush_work(&guc->log.runtime.flush_work);
 
 	/* Ask GuC to update the log buffer state */
+	intel_runtime_pm_get(dev_priv);
 	guc_log_flush(guc);
+	intel_runtime_pm_put(dev_priv);
 
 	/* GuC would have updated log buffer by now, so capture it */
 	guc_log_capture_logs(guc);
@@ -506,21 +604,12 @@ int intel_guc_log_create(struct intel_guc *guc)
 	struct i915_vma *vma;
 	unsigned long offset;
 	u32 flags;
-	u32 size;
 	int ret;
 
 	GEM_BUG_ON(guc->log.vma);
 
-	if (i915_modparams.guc_log_level > GUC_LOG_VERBOSITY_MAX)
-		i915_modparams.guc_log_level = GUC_LOG_VERBOSITY_MAX;
-
-	/* The first page is to save log buffer state. Allocate one
-	 * extra page for others in case for overlap */
-	size = (1 + GUC_LOG_DPC_PAGES + 1 +
-		GUC_LOG_ISR_PAGES + 1 +
-		GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT;
-
-	/* We require SSE 4.1 for fast reads from the GuC log buffer and
+	/*
+	 * We require SSE 4.1 for fast reads from the GuC log buffer and
 	 * it should be present on the chipsets supporting GuC based
 	 * submisssions.
 	 */
@@ -529,7 +618,7 @@ int intel_guc_log_create(struct intel_guc *guc)
 		goto err;
 	}
 
-	vma = intel_guc_allocate_vma(guc, size);
+	vma = intel_guc_allocate_vma(guc, GUC_LOG_SIZE);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
@@ -537,7 +626,7 @@ int intel_guc_log_create(struct intel_guc *guc)
 
 	guc->log.vma = vma;
 
-	if (i915_modparams.guc_log_level >= 0) {
+	if (i915_modparams.guc_log_level) {
 		ret = guc_log_runtime_create(guc);
 		if (ret < 0)
 			goto err_vma;
@@ -558,7 +647,7 @@ err_vma:
 	i915_vma_unpin_and_release(&guc->log.vma);
 err:
 	/* logging will be off */
-	i915_modparams.guc_log_level = -1;
+	i915_modparams.guc_log_level = 0;
 	return ret;
 }
 
@@ -568,35 +657,46 @@ void intel_guc_log_destroy(struct intel_guc *guc)
 	i915_vma_unpin_and_release(&guc->log.vma);
 }
 
-int i915_guc_log_control(struct drm_i915_private *dev_priv, u64 control_val)
+int intel_guc_log_control(struct intel_guc *guc, u64 control_val)
 {
-	struct intel_guc *guc = &dev_priv->guc;
-
-	union guc_log_control log_param;
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	bool enable_logging = control_val > 0;
+	u32 verbosity;
 	int ret;
 
-	log_param.value = control_val;
+	if (!guc->log.vma)
+		return -ENODEV;
 
-	if (log_param.verbosity < GUC_LOG_VERBOSITY_MIN ||
-	    log_param.verbosity > GUC_LOG_VERBOSITY_MAX)
+	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN);
+	if (control_val > 1 + GUC_LOG_VERBOSITY_MAX)
 		return -EINVAL;
 
 	/* This combination doesn't make sense & won't have any effect */
-	if (!log_param.logging_enabled && (i915_modparams.guc_log_level < 0))
+	if (!enable_logging && !i915_modparams.guc_log_level)
 		return 0;
 
-	ret = guc_log_control(guc, log_param.value);
+	verbosity = enable_logging ? control_val - 1 : 0;
+
+	ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex);
+	if (ret)
+		return ret;
+	intel_runtime_pm_get(dev_priv);
+	ret = guc_log_control(guc, enable_logging, verbosity);
+	intel_runtime_pm_put(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
 	if (ret < 0) {
 		DRM_DEBUG_DRIVER("guc_logging_control action failed %d\n", ret);
 		return ret;
 	}
 
-	if (log_param.logging_enabled) {
-		i915_modparams.guc_log_level = log_param.verbosity;
+	if (enable_logging) {
+		i915_modparams.guc_log_level = 1 + verbosity;
 
-		/* If log_level was set as -1 at boot time, then the relay channel file
-		 * wouldn't have been created by now and interrupts also would not have
-		 * been enabled. Try again now, just in case.
+		/*
+		 * If log was disabled at boot time, then the relay channel file
+		 * wouldn't have been created by now and interrupts also would
+		 * not have been enabled. Try again now, just in case.
 		 */
 		ret = guc_log_late_setup(guc);
 		if (ret < 0) {
@@ -605,9 +705,14 @@ int i915_guc_log_control(struct drm_i915_private *dev_priv, u64 control_val)
 		}
 
 		/* GuC logging is currently the only user of Guc2Host interrupts */
+		mutex_lock(&dev_priv->drm.struct_mutex);
+		intel_runtime_pm_get(dev_priv);
 		gen9_enable_guc_interrupts(dev_priv);
+		intel_runtime_pm_put(dev_priv);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
 	} else {
-		/* Once logging is disabled, GuC won't generate logs & send an
+		/*
+		 * Once logging is disabled, GuC won't generate logs & send an
 		 * interrupt. But there could be some data in the log buffer
 		 * which is yet to be captured. So request GuC to update the log
 		 * buffer state and then collect the left over logs.
@@ -615,7 +720,7 @@ int i915_guc_log_control(struct drm_i915_private *dev_priv, u64 control_val)
 		guc_flush_logs(guc);
 
 		/* As logging is disabled, update log level to reflect that */
-		i915_modparams.guc_log_level = -1;
+		i915_modparams.guc_log_level = 0;
 	}
 
 	return ret;
@@ -623,23 +728,27 @@ int i915_guc_log_control(struct drm_i915_private *dev_priv, u64 control_val)
 
 void i915_guc_log_register(struct drm_i915_private *dev_priv)
 {
-	if (!USES_GUC_SUBMISSION(dev_priv) ||
-	    (i915_modparams.guc_log_level < 0))
+	if (!USES_GUC_SUBMISSION(dev_priv) || !i915_modparams.guc_log_level)
 		return;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	guc_log_late_setup(&dev_priv->guc);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
 void i915_guc_log_unregister(struct drm_i915_private *dev_priv)
 {
+	struct intel_guc *guc = &dev_priv->guc;
+
 	if (!USES_GUC_SUBMISSION(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	/* GuC logging is currently the only user of Guc2Host interrupts */
+	intel_runtime_pm_get(dev_priv);
 	gen9_disable_guc_interrupts(dev_priv);
-	guc_log_runtime_destroy(&dev_priv->guc);
+	intel_runtime_pm_put(dev_priv);
+
+	guc_log_runtime_destroy(guc);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	intel_guc_log_relay_destroy(guc);
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index f512cf79339b..dab0e949567a 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -32,6 +32,13 @@
 struct drm_i915_private;
 struct intel_guc;
 
+/*
+ * The first page is to save log buffer state. Allocate one
+ * extra page for others in case for overlap
+ */
+#define GUC_LOG_SIZE	((1 + GUC_LOG_DPC_PAGES + 1 + GUC_LOG_ISR_PAGES + \
+			  1 + GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT)
+
 struct intel_guc_log {
 	u32 flags;
 	struct i915_vma *vma;
@@ -41,6 +48,8 @@ struct intel_guc_log {
 		struct workqueue_struct *flush_wq;
 		struct work_struct flush_work;
 		struct rchan *relay_chan;
+		/* To serialize the access to relay_chan */
+		struct mutex relay_lock;
 	} runtime;
 	/* logging related stats */
 	u32 capture_miss_count;
@@ -52,7 +61,10 @@ struct intel_guc_log {
 
 int intel_guc_log_create(struct intel_guc *guc);
 void intel_guc_log_destroy(struct intel_guc *guc);
-int i915_guc_log_control(struct drm_i915_private *dev_priv, u64 control_val);
+void intel_guc_log_init_early(struct intel_guc *guc);
+int intel_guc_log_relay_create(struct intel_guc *guc);
+void intel_guc_log_relay_destroy(struct intel_guc *guc);
+int intel_guc_log_control(struct intel_guc *guc, u64 control_val);
 void i915_guc_log_register(struct drm_i915_private *dev_priv);
 void i915_guc_log_unregister(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 4d2409466a3a..1f3a8786bbdc 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -73,13 +73,6 @@
  * ELSP context descriptor dword into Work Item.
  * See guc_add_request()
  *
- * ADS:
- * The Additional Data Struct (ADS) has pointers for different buffers used by
- * the GuC. One single gem object contains the ADS struct itself (guc_ads), the
- * scheduling policies (guc_policies), a structure describing a collection of
- * register sets (guc_mmio_reg_state) and some extra pages for the GuC to save
- * its internal state for sleep.
- *
  */
 
 static inline bool is_high_priority(struct intel_guc_client *client)
@@ -1012,117 +1005,6 @@ static void guc_clients_destroy(struct intel_guc *guc)
 	guc_client_free(client);
 }
 
-static void guc_policy_init(struct guc_policy *policy)
-{
-	policy->execution_quantum = POLICY_DEFAULT_EXECUTION_QUANTUM_US;
-	policy->preemption_time = POLICY_DEFAULT_PREEMPTION_TIME_US;
-	policy->fault_time = POLICY_DEFAULT_FAULT_TIME_US;
-	policy->policy_flags = 0;
-}
-
-static void guc_policies_init(struct guc_policies *policies)
-{
-	struct guc_policy *policy;
-	u32 p, i;
-
-	policies->dpc_promote_time = POLICY_DEFAULT_DPC_PROMOTE_TIME_US;
-	policies->max_num_work_items = POLICY_MAX_NUM_WI;
-
-	for (p = 0; p < GUC_CLIENT_PRIORITY_NUM; p++) {
-		for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
-			policy = &policies->policy[p][i];
-
-			guc_policy_init(policy);
-		}
-	}
-
-	policies->is_valid = 1;
-}
-
-/*
- * The first 80 dwords of the register state context, containing the
- * execlists and ppgtt registers.
- */
-#define LR_HW_CONTEXT_SIZE	(80 * sizeof(u32))
-
-static int guc_ads_create(struct intel_guc *guc)
-{
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct i915_vma *vma;
-	struct page *page;
-	/* The ads obj includes the struct itself and buffers passed to GuC */
-	struct {
-		struct guc_ads ads;
-		struct guc_policies policies;
-		struct guc_mmio_reg_state reg_state;
-		u8 reg_state_buffer[GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE];
-	} __packed *blob;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	const u32 skipped_offset = LRC_HEADER_PAGES * PAGE_SIZE;
-	const u32 skipped_size = LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE;
-	u32 base;
-
-	GEM_BUG_ON(guc->ads_vma);
-
-	vma = intel_guc_allocate_vma(guc, PAGE_ALIGN(sizeof(*blob)));
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	guc->ads_vma = vma;
-
-	page = i915_vma_first_page(vma);
-	blob = kmap(page);
-
-	/* GuC scheduling policies */
-	guc_policies_init(&blob->policies);
-
-	/* MMIO reg state */
-	for_each_engine(engine, dev_priv, id) {
-		blob->reg_state.white_list[engine->guc_id].mmio_start =
-			engine->mmio_base + GUC_MMIO_WHITE_LIST_START;
-
-		/* Nothing to be saved or restored for now. */
-		blob->reg_state.white_list[engine->guc_id].count = 0;
-	}
-
-	/*
-	 * The GuC requires a "Golden Context" when it reinitialises
-	 * engines after a reset. Here we use the Render ring default
-	 * context, which must already exist and be pinned in the GGTT,
-	 * so its address won't change after we've told the GuC where
-	 * to find it. Note that we have to skip our header (1 page),
-	 * because our GuC shared data is there.
-	 */
-	blob->ads.golden_context_lrca =
-		guc_ggtt_offset(dev_priv->kernel_context->engine[RCS].state) +
-		skipped_offset;
-
-	/*
-	 * The GuC expects us to exclude the portion of the context image that
-	 * it skips from the size it is to read. It starts reading from after
-	 * the execlist context (so skipping the first page [PPHWSP] and 80
-	 * dwords). Weird guc is weird.
-	 */
-	for_each_engine(engine, dev_priv, id)
-		blob->ads.eng_state_size[engine->guc_id] =
-			engine->context_size - skipped_size;
-
-	base = guc_ggtt_offset(vma);
-	blob->ads.scheduler_policies = base + ptr_offset(blob, policies);
-	blob->ads.reg_state_buffer = base + ptr_offset(blob, reg_state_buffer);
-	blob->ads.reg_state_addr = base + ptr_offset(blob, reg_state);
-
-	kunmap(page);
-
-	return 0;
-}
-
-static void guc_ads_destroy(struct intel_guc *guc)
-{
-	i915_vma_unpin_and_release(&guc->ads_vma);
-}
-
 /*
  * Set up the memory resources to be shared with the GuC (via the GGTT)
  * at firmware loading time.
@@ -1146,15 +1028,6 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	 */
 	GEM_BUG_ON(!guc->stage_desc_pool);
 
-	ret = intel_guc_log_create(guc);
-	if (ret < 0)
-		goto err_stage_desc_pool;
-
-	ret = guc_ads_create(guc);
-	if (ret < 0)
-		goto err_log;
-	GEM_BUG_ON(!guc->ads_vma);
-
 	WARN_ON(!guc_verify_doorbells(guc));
 	ret = guc_clients_create(guc);
 	if (ret)
@@ -1167,11 +1040,6 @@ int intel_guc_submission_init(struct intel_guc *guc)
 
 	return 0;
 
-err_log:
-	intel_guc_log_destroy(guc);
-err_stage_desc_pool:
-	guc_stage_desc_pool_destroy(guc);
-	return ret;
 }
 
 void intel_guc_submission_fini(struct intel_guc *guc)
@@ -1186,8 +1054,6 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 	guc_clients_destroy(guc);
 	WARN_ON(!guc_verify_doorbells(guc));
 
-	guc_ads_destroy(guc);
-	intel_guc_log_destroy(guc);
 	guc_stage_desc_pool_destroy(guc);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index 31f01d64c021..42e45ae87393 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -359,7 +359,7 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 	case ENGINE_DEAD:
 		if (drm_debug & DRM_UT_DRIVER) {
 			struct drm_printer p = drm_debug_printer("hangcheck");
-			intel_engine_dump(engine, &p, "%s", engine->name);
+			intel_engine_dump(engine, &p, "%s\n", engine->name);
 		}
 		break;
 
@@ -411,7 +411,6 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	unsigned int hung = 0, stuck = 0;
-	int busy_count = 0;
 
 	if (!i915_modparams.enable_hangcheck)
 		return;
@@ -429,7 +428,6 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		const bool busy = intel_engine_has_waiter(engine);
 		struct intel_engine_hangcheck hc;
 
 		semaphore_clear_deadlocks(dev_priv);
@@ -443,16 +441,13 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			if (hc.action != ENGINE_DEAD)
 				stuck |= intel_engine_flag(engine);
 		}
-
-		busy_count += busy;
 	}
 
 	if (hung)
 		hangcheck_declare_hang(dev_priv, hung, stuck);
 
 	/* Reset timer in case GPU hangs without another request being added */
-	if (busy_count)
-		i915_queue_hangcheck(dev_priv);
+	i915_queue_hangcheck(dev_priv);
 }
 
 void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_hdcp.c b/drivers/gpu/drm/i915/intel_hdcp.c
new file mode 100644
index 000000000000..14ca5d3057a7
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_hdcp.c
@@ -0,0 +1,807 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * Authors:
+ * Sean Paul <seanpaul@chromium.org>
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_hdcp.h>
+#include <linux/i2c.h>
+#include <linux/random.h>
+
+#include "intel_drv.h"
+#include "i915_reg.h"
+
+#define KEY_LOAD_TRIES	5
+
+static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *intel_dig_port,
+				    const struct intel_hdcp_shim *shim)
+{
+	int ret, read_ret;
+	bool ksv_ready;
+
+	/* Poll for ksv list ready (spec says max time allowed is 5s) */
+	ret = __wait_for(read_ret = shim->read_ksv_ready(intel_dig_port,
+							 &ksv_ready),
+			 read_ret || ksv_ready, 5 * 1000 * 1000, 1000,
+			 100 * 1000);
+	if (ret)
+		return ret;
+	if (read_ret)
+		return read_ret;
+	if (!ksv_ready)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void intel_hdcp_clear_keys(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(HDCP_KEY_CONF, HDCP_CLEAR_KEYS_TRIGGER);
+	I915_WRITE(HDCP_KEY_STATUS, HDCP_KEY_LOAD_DONE | HDCP_KEY_LOAD_STATUS |
+		   HDCP_FUSE_IN_PROGRESS | HDCP_FUSE_ERROR | HDCP_FUSE_DONE);
+}
+
+static int intel_hdcp_load_keys(struct drm_i915_private *dev_priv)
+{
+	int ret;
+	u32 val;
+
+	val = I915_READ(HDCP_KEY_STATUS);
+	if ((val & HDCP_KEY_LOAD_DONE) && (val & HDCP_KEY_LOAD_STATUS))
+		return 0;
+
+	/*
+	 * On HSW and BDW HW loads the HDCP1.4 Key when Display comes
+	 * out of reset. So if Key is not already loaded, its an error state.
+	 */
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		if (!(I915_READ(HDCP_KEY_STATUS) & HDCP_KEY_LOAD_DONE))
+			return -ENXIO;
+
+	/*
+	 * Initiate loading the HDCP key from fuses.
+	 *
+	 * BXT+ platforms, HDCP key needs to be loaded by SW. Only SKL and KBL
+	 * differ in the key load trigger process from other platforms.
+	 */
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+		mutex_lock(&dev_priv->pcu_lock);
+		ret = sandybridge_pcode_write(dev_priv,
+					      SKL_PCODE_LOAD_HDCP_KEYS, 1);
+		mutex_unlock(&dev_priv->pcu_lock);
+		if (ret) {
+			DRM_ERROR("Failed to initiate HDCP key load (%d)\n",
+			          ret);
+			return ret;
+		}
+	} else {
+		I915_WRITE(HDCP_KEY_CONF, HDCP_KEY_LOAD_TRIGGER);
+	}
+
+	/* Wait for the keys to load (500us) */
+	ret = __intel_wait_for_register(dev_priv, HDCP_KEY_STATUS,
+					HDCP_KEY_LOAD_DONE, HDCP_KEY_LOAD_DONE,
+					10, 1, &val);
+	if (ret)
+		return ret;
+	else if (!(val & HDCP_KEY_LOAD_STATUS))
+		return -ENXIO;
+
+	/* Send Aksv over to PCH display for use in authentication */
+	I915_WRITE(HDCP_KEY_CONF, HDCP_AKSV_SEND_TRIGGER);
+
+	return 0;
+}
+
+/* Returns updated SHA-1 index */
+static int intel_write_sha_text(struct drm_i915_private *dev_priv, u32 sha_text)
+{
+	I915_WRITE(HDCP_SHA_TEXT, sha_text);
+	if (intel_wait_for_register(dev_priv, HDCP_REP_CTL,
+				    HDCP_SHA1_READY, HDCP_SHA1_READY, 1)) {
+		DRM_ERROR("Timed out waiting for SHA1 ready\n");
+		return -ETIMEDOUT;
+	}
+	return 0;
+}
+
+static
+u32 intel_hdcp_get_repeater_ctl(struct intel_digital_port *intel_dig_port)
+{
+	enum port port = intel_dig_port->base.port;
+	switch (port) {
+	case PORT_A:
+		return HDCP_DDIA_REP_PRESENT | HDCP_DDIA_SHA1_M0;
+	case PORT_B:
+		return HDCP_DDIB_REP_PRESENT | HDCP_DDIB_SHA1_M0;
+	case PORT_C:
+		return HDCP_DDIC_REP_PRESENT | HDCP_DDIC_SHA1_M0;
+	case PORT_D:
+		return HDCP_DDID_REP_PRESENT | HDCP_DDID_SHA1_M0;
+	case PORT_E:
+		return HDCP_DDIE_REP_PRESENT | HDCP_DDIE_SHA1_M0;
+	default:
+		break;
+	}
+	DRM_ERROR("Unknown port %d\n", port);
+	return -EINVAL;
+}
+
+static
+bool intel_hdcp_is_ksv_valid(u8 *ksv)
+{
+	int i, ones = 0;
+	/* KSV has 20 1's and 20 0's */
+	for (i = 0; i < DRM_HDCP_KSV_LEN; i++)
+		ones += hweight8(ksv[i]);
+	if (ones != 20)
+		return false;
+	return true;
+}
+
+/* Implements Part 2 of the HDCP authorization procedure */
+static
+int intel_hdcp_auth_downstream(struct intel_digital_port *intel_dig_port,
+			       const struct intel_hdcp_shim *shim)
+{
+	struct drm_i915_private *dev_priv;
+	u32 vprime, sha_text, sha_leftovers, rep_ctl;
+	u8 bstatus[2], num_downstream, *ksv_fifo;
+	int ret, i, j, sha_idx;
+
+	dev_priv = intel_dig_port->base.base.dev->dev_private;
+
+	ret = intel_hdcp_poll_ksv_fifo(intel_dig_port, shim);
+	if (ret) {
+		DRM_ERROR("KSV list failed to become ready (%d)\n", ret);
+		return ret;
+	}
+
+	ret = shim->read_bstatus(intel_dig_port, bstatus);
+	if (ret)
+		return ret;
+
+	if (DRM_HDCP_MAX_DEVICE_EXCEEDED(bstatus[0]) ||
+	    DRM_HDCP_MAX_CASCADE_EXCEEDED(bstatus[1])) {
+		DRM_ERROR("Max Topology Limit Exceeded\n");
+		return -EPERM;
+	}
+
+	/*
+	 * When repeater reports 0 device count, HDCP1.4 spec allows disabling
+	 * the HDCP encryption. That implies that repeater can't have its own
+	 * display. As there is no consumption of encrypted content in the
+	 * repeater with 0 downstream devices, we are failing the
+	 * authentication.
+	 */
+	num_downstream = DRM_HDCP_NUM_DOWNSTREAM(bstatus[0]);
+	if (num_downstream == 0)
+		return -EINVAL;
+
+	ksv_fifo = kzalloc(num_downstream * DRM_HDCP_KSV_LEN, GFP_KERNEL);
+	if (!ksv_fifo)
+		return -ENOMEM;
+
+	ret = shim->read_ksv_fifo(intel_dig_port, num_downstream, ksv_fifo);
+	if (ret)
+		return ret;
+
+	/* Process V' values from the receiver */
+	for (i = 0; i < DRM_HDCP_V_PRIME_NUM_PARTS; i++) {
+		ret = shim->read_v_prime_part(intel_dig_port, i, &vprime);
+		if (ret)
+			return ret;
+		I915_WRITE(HDCP_SHA_V_PRIME(i), vprime);
+	}
+
+	/*
+	 * We need to write the concatenation of all device KSVs, BINFO (DP) ||
+	 * BSTATUS (HDMI), and M0 (which is added via HDCP_REP_CTL). This byte
+	 * stream is written via the HDCP_SHA_TEXT register in 32-bit
+	 * increments. Every 64 bytes, we need to write HDCP_REP_CTL again. This
+	 * index will keep track of our progress through the 64 bytes as well as
+	 * helping us work the 40-bit KSVs through our 32-bit register.
+	 *
+	 * NOTE: data passed via HDCP_SHA_TEXT should be big-endian
+	 */
+	sha_idx = 0;
+	sha_text = 0;
+	sha_leftovers = 0;
+	rep_ctl = intel_hdcp_get_repeater_ctl(intel_dig_port);
+	I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
+	for (i = 0; i < num_downstream; i++) {
+		unsigned int sha_empty;
+		u8 *ksv = &ksv_fifo[i * DRM_HDCP_KSV_LEN];
+
+		/* Fill up the empty slots in sha_text and write it out */
+		sha_empty = sizeof(sha_text) - sha_leftovers;
+		for (j = 0; j < sha_empty; j++)
+			sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8);
+
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+
+		/* Programming guide writes this every 64 bytes */
+		sha_idx += sizeof(sha_text);
+		if (!(sha_idx % 64))
+			I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
+
+		/* Store the leftover bytes from the ksv in sha_text */
+		sha_leftovers = DRM_HDCP_KSV_LEN - sha_empty;
+		sha_text = 0;
+		for (j = 0; j < sha_leftovers; j++)
+			sha_text |= ksv[sha_empty + j] <<
+					((sizeof(sha_text) - j - 1) * 8);
+
+		/*
+		 * If we still have room in sha_text for more data, continue.
+		 * Otherwise, write it out immediately.
+		 */
+		if (sizeof(sha_text) > sha_leftovers)
+			continue;
+
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_leftovers = 0;
+		sha_text = 0;
+		sha_idx += sizeof(sha_text);
+	}
+
+	/*
+	 * We need to write BINFO/BSTATUS, and M0 now. Depending on how many
+	 * bytes are leftover from the last ksv, we might be able to fit them
+	 * all in sha_text (first 2 cases), or we might need to split them up
+	 * into 2 writes (last 2 cases).
+	 */
+	if (sha_leftovers == 0) {
+		/* Write 16 bits of text, 16 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_16);
+		ret = intel_write_sha_text(dev_priv,
+					   bstatus[0] << 8 | bstatus[1]);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 32 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_0);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 16 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_16);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+	} else if (sha_leftovers == 1) {
+		/* Write 24 bits of text, 8 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_24);
+		sha_text |= bstatus[0] << 16 | bstatus[1] << 8;
+		/* Only 24-bits of data, must be in the LSB */
+		sha_text = (sha_text & 0xffffff00) >> 8;
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 32 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_0);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 24 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_8);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+	} else if (sha_leftovers == 2) {
+		/* Write 32 bits of text */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
+		sha_text |= bstatus[0] << 24 | bstatus[1] << 16;
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 64 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_0);
+		for (i = 0; i < 2; i++) {
+			ret = intel_write_sha_text(dev_priv, 0);
+			if (ret < 0)
+				return ret;
+			sha_idx += sizeof(sha_text);
+		}
+	} else if (sha_leftovers == 3) {
+		/* Write 32 bits of text */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
+		sha_text |= bstatus[0] << 24;
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 8 bits of text, 24 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_8);
+		ret = intel_write_sha_text(dev_priv, bstatus[1]);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 32 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_0);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+
+		/* Write 8 bits of M0 */
+		I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_24);
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+	} else {
+		DRM_ERROR("Invalid number of leftovers %d\n", sha_leftovers);
+		return -EINVAL;
+	}
+
+	I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
+	/* Fill up to 64-4 bytes with zeros (leave the last write for length) */
+	while ((sha_idx % 64) < (64 - sizeof(sha_text))) {
+		ret = intel_write_sha_text(dev_priv, 0);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
+	}
+
+	/*
+	 * Last write gets the length of the concatenation in bits. That is:
+	 *  - 5 bytes per device
+	 *  - 10 bytes for BINFO/BSTATUS(2), M0(8)
+	 */
+	sha_text = (num_downstream * 5 + 10) * 8;
+	ret = intel_write_sha_text(dev_priv, sha_text);
+	if (ret < 0)
+		return ret;
+
+	/* Tell the HW we're done with the hash and wait for it to ACK */
+	I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_COMPLETE_HASH);
+	if (intel_wait_for_register(dev_priv, HDCP_REP_CTL,
+				    HDCP_SHA1_COMPLETE,
+				    HDCP_SHA1_COMPLETE, 1)) {
+		DRM_ERROR("Timed out waiting for SHA1 complete\n");
+		return -ETIMEDOUT;
+	}
+	if (!(I915_READ(HDCP_REP_CTL) & HDCP_SHA1_V_MATCH)) {
+		DRM_ERROR("SHA-1 mismatch, HDCP failed\n");
+		return -ENXIO;
+	}
+
+	DRM_DEBUG_KMS("HDCP is enabled (%d downstream devices)\n",
+		      num_downstream);
+	return 0;
+}
+
+/* Implements Part 1 of the HDCP authorization procedure */
+static int intel_hdcp_auth(struct intel_digital_port *intel_dig_port,
+			   const struct intel_hdcp_shim *shim)
+{
+	struct drm_i915_private *dev_priv;
+	enum port port;
+	unsigned long r0_prime_gen_start;
+	int ret, i, tries = 2;
+	union {
+		u32 reg[2];
+		u8 shim[DRM_HDCP_AN_LEN];
+	} an;
+	union {
+		u32 reg[2];
+		u8 shim[DRM_HDCP_KSV_LEN];
+	} bksv;
+	union {
+		u32 reg;
+		u8 shim[DRM_HDCP_RI_LEN];
+	} ri;
+	bool repeater_present, hdcp_capable;
+
+	dev_priv = intel_dig_port->base.base.dev->dev_private;
+
+	port = intel_dig_port->base.port;
+
+	/*
+	 * Detects whether the display is HDCP capable. Although we check for
+	 * valid Bksv below, the HDCP over DP spec requires that we check
+	 * whether the display supports HDCP before we write An. For HDMI
+	 * displays, this is not necessary.
+	 */
+	if (shim->hdcp_capable) {
+		ret = shim->hdcp_capable(intel_dig_port, &hdcp_capable);
+		if (ret)
+			return ret;
+		if (!hdcp_capable) {
+			DRM_ERROR("Panel is not HDCP capable\n");
+			return -EINVAL;
+		}
+	}
+
+	/* Initialize An with 2 random values and acquire it */
+	for (i = 0; i < 2; i++)
+		I915_WRITE(PORT_HDCP_ANINIT(port), get_random_u32());
+	I915_WRITE(PORT_HDCP_CONF(port), HDCP_CONF_CAPTURE_AN);
+
+	/* Wait for An to be acquired */
+	if (intel_wait_for_register(dev_priv, PORT_HDCP_STATUS(port),
+				    HDCP_STATUS_AN_READY,
+				    HDCP_STATUS_AN_READY, 1)) {
+		DRM_ERROR("Timed out waiting for An\n");
+		return -ETIMEDOUT;
+	}
+
+	an.reg[0] = I915_READ(PORT_HDCP_ANLO(port));
+	an.reg[1] = I915_READ(PORT_HDCP_ANHI(port));
+	ret = shim->write_an_aksv(intel_dig_port, an.shim);
+	if (ret)
+		return ret;
+
+	r0_prime_gen_start = jiffies;
+
+	memset(&bksv, 0, sizeof(bksv));
+
+	/* HDCP spec states that we must retry the bksv if it is invalid */
+	for (i = 0; i < tries; i++) {
+		ret = shim->read_bksv(intel_dig_port, bksv.shim);
+		if (ret)
+			return ret;
+		if (intel_hdcp_is_ksv_valid(bksv.shim))
+			break;
+	}
+	if (i == tries) {
+		DRM_ERROR("HDCP failed, Bksv is invalid\n");
+		return -ENODEV;
+	}
+
+	I915_WRITE(PORT_HDCP_BKSVLO(port), bksv.reg[0]);
+	I915_WRITE(PORT_HDCP_BKSVHI(port), bksv.reg[1]);
+
+	ret = shim->repeater_present(intel_dig_port, &repeater_present);
+	if (ret)
+		return ret;
+	if (repeater_present)
+		I915_WRITE(HDCP_REP_CTL,
+			   intel_hdcp_get_repeater_ctl(intel_dig_port));
+
+	ret = shim->toggle_signalling(intel_dig_port, true);
+	if (ret)
+		return ret;
+
+	I915_WRITE(PORT_HDCP_CONF(port), HDCP_CONF_AUTH_AND_ENC);
+
+	/* Wait for R0 ready */
+	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+		     (HDCP_STATUS_R0_READY | HDCP_STATUS_ENC), 1)) {
+		DRM_ERROR("Timed out waiting for R0 ready\n");
+		return -ETIMEDOUT;
+	}
+
+	/*
+	 * Wait for R0' to become available. The spec says 100ms from Aksv, but
+	 * some monitors can take longer than this. We'll set the timeout at
+	 * 300ms just to be sure.
+	 *
+	 * On DP, there's an R0_READY bit available but no such bit
+	 * exists on HDMI. Since the upper-bound is the same, we'll just do
+	 * the stupid thing instead of polling on one and not the other.
+	 */
+	wait_remaining_ms_from_jiffies(r0_prime_gen_start, 300);
+
+	ri.reg = 0;
+	ret = shim->read_ri_prime(intel_dig_port, ri.shim);
+	if (ret)
+		return ret;
+	I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+
+	/* Wait for Ri prime match */
+	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
+		DRM_ERROR("Timed out waiting for Ri prime match (%x)\n",
+			  I915_READ(PORT_HDCP_STATUS(port)));
+		return -ETIMEDOUT;
+	}
+
+	/* Wait for encryption confirmation */
+	if (intel_wait_for_register(dev_priv, PORT_HDCP_STATUS(port),
+				    HDCP_STATUS_ENC, HDCP_STATUS_ENC, 20)) {
+		DRM_ERROR("Timed out waiting for encryption\n");
+		return -ETIMEDOUT;
+	}
+
+	/*
+	 * XXX: If we have MST-connected devices, we need to enable encryption
+	 * on those as well.
+	 */
+
+	if (repeater_present)
+		return intel_hdcp_auth_downstream(intel_dig_port, shim);
+
+	DRM_DEBUG_KMS("HDCP is enabled (no repeater present)\n");
+	return 0;
+}
+
+static
+struct intel_digital_port *conn_to_dig_port(struct intel_connector *connector)
+{
+	return enc_to_dig_port(&intel_attached_encoder(&connector->base)->base);
+}
+
+static int _intel_hdcp_disable(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = connector->base.dev->dev_private;
+	struct intel_digital_port *intel_dig_port = conn_to_dig_port(connector);
+	enum port port = intel_dig_port->base.port;
+	int ret;
+
+	DRM_DEBUG_KMS("[%s:%d] HDCP is being disabled...\n",
+		      connector->base.name, connector->base.base.id);
+
+	I915_WRITE(PORT_HDCP_CONF(port), 0);
+	if (intel_wait_for_register(dev_priv, PORT_HDCP_STATUS(port), ~0, 0,
+				    20)) {
+		DRM_ERROR("Failed to disable HDCP, timeout clearing status\n");
+		return -ETIMEDOUT;
+	}
+
+	ret = connector->hdcp_shim->toggle_signalling(intel_dig_port, false);
+	if (ret) {
+		DRM_ERROR("Failed to disable HDCP signalling\n");
+		return ret;
+	}
+
+	DRM_DEBUG_KMS("HDCP is disabled\n");
+	return 0;
+}
+
+static int _intel_hdcp_enable(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = connector->base.dev->dev_private;
+	int i, ret, tries = 3;
+
+	DRM_DEBUG_KMS("[%s:%d] HDCP is being enabled...\n",
+		      connector->base.name, connector->base.base.id);
+
+	if (!(I915_READ(SKL_FUSE_STATUS) & SKL_FUSE_PG_DIST_STATUS(1))) {
+		DRM_ERROR("PG1 is disabled, cannot load keys\n");
+		return -ENXIO;
+	}
+
+	for (i = 0; i < KEY_LOAD_TRIES; i++) {
+		ret = intel_hdcp_load_keys(dev_priv);
+		if (!ret)
+			break;
+		intel_hdcp_clear_keys(dev_priv);
+	}
+	if (ret) {
+		DRM_ERROR("Could not load HDCP keys, (%d)\n", ret);
+		return ret;
+	}
+
+	/* Incase of authentication failures, HDCP spec expects reauth. */
+	for (i = 0; i < tries; i++) {
+		ret = intel_hdcp_auth(conn_to_dig_port(connector),
+				      connector->hdcp_shim);
+		if (!ret)
+			return 0;
+
+		DRM_DEBUG_KMS("HDCP Auth failure (%d)\n", ret);
+
+		/* Ensuring HDCP encryption and signalling are stopped. */
+		_intel_hdcp_disable(connector);
+	}
+
+	DRM_ERROR("HDCP authentication failed (%d tries/%d)\n", tries, ret);
+	return ret;
+}
+
+static void intel_hdcp_check_work(struct work_struct *work)
+{
+	struct intel_connector *connector = container_of(to_delayed_work(work),
+							 struct intel_connector,
+							 hdcp_check_work);
+	if (!intel_hdcp_check_link(connector))
+		schedule_delayed_work(&connector->hdcp_check_work,
+				      DRM_HDCP_CHECK_PERIOD_MS);
+}
+
+static void intel_hdcp_prop_work(struct work_struct *work)
+{
+	struct intel_connector *connector = container_of(work,
+							 struct intel_connector,
+							 hdcp_prop_work);
+	struct drm_device *dev = connector->base.dev;
+	struct drm_connector_state *state;
+
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+	mutex_lock(&connector->hdcp_mutex);
+
+	/*
+	 * This worker is only used to flip between ENABLED/DESIRED. Either of
+	 * those to UNDESIRED is handled by core. If hdcp_value == UNDESIRED,
+	 * we're running just after hdcp has been disabled, so just exit
+	 */
+	if (connector->hdcp_value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) {
+		state = connector->base.state;
+		state->content_protection = connector->hdcp_value;
+	}
+
+	mutex_unlock(&connector->hdcp_mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+}
+
+bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port)
+{
+	/* PORT E doesn't have HDCP, and PORT F is disabled */
+	return ((INTEL_GEN(dev_priv) >= 8 || IS_HASWELL(dev_priv)) &&
+		!IS_CHERRYVIEW(dev_priv) && port < PORT_E);
+}
+
+int intel_hdcp_init(struct intel_connector *connector,
+		    const struct intel_hdcp_shim *hdcp_shim)
+{
+	int ret;
+
+	ret = drm_connector_attach_content_protection_property(
+			&connector->base);
+	if (ret)
+		return ret;
+
+	connector->hdcp_shim = hdcp_shim;
+	mutex_init(&connector->hdcp_mutex);
+	INIT_DELAYED_WORK(&connector->hdcp_check_work, intel_hdcp_check_work);
+	INIT_WORK(&connector->hdcp_prop_work, intel_hdcp_prop_work);
+	return 0;
+}
+
+int intel_hdcp_enable(struct intel_connector *connector)
+{
+	int ret;
+
+	if (!connector->hdcp_shim)
+		return -ENOENT;
+
+	mutex_lock(&connector->hdcp_mutex);
+
+	ret = _intel_hdcp_enable(connector);
+	if (ret)
+		goto out;
+
+	connector->hdcp_value = DRM_MODE_CONTENT_PROTECTION_ENABLED;
+	schedule_work(&connector->hdcp_prop_work);
+	schedule_delayed_work(&connector->hdcp_check_work,
+			      DRM_HDCP_CHECK_PERIOD_MS);
+out:
+	mutex_unlock(&connector->hdcp_mutex);
+	return ret;
+}
+
+int intel_hdcp_disable(struct intel_connector *connector)
+{
+	int ret = 0;
+
+	if (!connector->hdcp_shim)
+		return -ENOENT;
+
+	mutex_lock(&connector->hdcp_mutex);
+
+	if (connector->hdcp_value != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) {
+		connector->hdcp_value = DRM_MODE_CONTENT_PROTECTION_UNDESIRED;
+		ret = _intel_hdcp_disable(connector);
+	}
+
+	mutex_unlock(&connector->hdcp_mutex);
+	cancel_delayed_work_sync(&connector->hdcp_check_work);
+	return ret;
+}
+
+void intel_hdcp_atomic_check(struct drm_connector *connector,
+			     struct drm_connector_state *old_state,
+			     struct drm_connector_state *new_state)
+{
+	uint64_t old_cp = old_state->content_protection;
+	uint64_t new_cp = new_state->content_protection;
+	struct drm_crtc_state *crtc_state;
+
+	if (!new_state->crtc) {
+		/*
+		 * If the connector is being disabled with CP enabled, mark it
+		 * desired so it's re-enabled when the connector is brought back
+		 */
+		if (old_cp == DRM_MODE_CONTENT_PROTECTION_ENABLED)
+			new_state->content_protection =
+				DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		return;
+	}
+
+	/*
+	 * Nothing to do if the state didn't change, or HDCP was activated since
+	 * the last commit
+	 */
+	if (old_cp == new_cp ||
+	    (old_cp == DRM_MODE_CONTENT_PROTECTION_DESIRED &&
+	     new_cp == DRM_MODE_CONTENT_PROTECTION_ENABLED))
+		return;
+
+	crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
+						   new_state->crtc);
+	crtc_state->mode_changed = true;
+}
+
+/* Implements Part 3 of the HDCP authorization procedure */
+int intel_hdcp_check_link(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = connector->base.dev->dev_private;
+	struct intel_digital_port *intel_dig_port = conn_to_dig_port(connector);
+	enum port port = intel_dig_port->base.port;
+	int ret = 0;
+
+	if (!connector->hdcp_shim)
+		return -ENOENT;
+
+	mutex_lock(&connector->hdcp_mutex);
+
+	if (connector->hdcp_value == DRM_MODE_CONTENT_PROTECTION_UNDESIRED)
+		goto out;
+
+	if (!(I915_READ(PORT_HDCP_STATUS(port)) & HDCP_STATUS_ENC)) {
+		DRM_ERROR("%s:%d HDCP check failed: link is not encrypted,%x\n",
+			  connector->base.name, connector->base.base.id,
+			  I915_READ(PORT_HDCP_STATUS(port)));
+		ret = -ENXIO;
+		connector->hdcp_value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		schedule_work(&connector->hdcp_prop_work);
+		goto out;
+	}
+
+	if (connector->hdcp_shim->check_link(intel_dig_port)) {
+		if (connector->hdcp_value !=
+		    DRM_MODE_CONTENT_PROTECTION_UNDESIRED) {
+			connector->hdcp_value =
+				DRM_MODE_CONTENT_PROTECTION_ENABLED;
+			schedule_work(&connector->hdcp_prop_work);
+		}
+		goto out;
+	}
+
+	DRM_DEBUG_KMS("[%s:%d] HDCP link failed, retrying authentication\n",
+		      connector->base.name, connector->base.base.id);
+
+	ret = _intel_hdcp_disable(connector);
+	if (ret) {
+		DRM_ERROR("Failed to disable hdcp (%d)\n", ret);
+		connector->hdcp_value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		schedule_work(&connector->hdcp_prop_work);
+		goto out;
+	}
+
+	ret = _intel_hdcp_enable(connector);
+	if (ret) {
+		DRM_ERROR("Failed to enable hdcp (%d)\n", ret);
+		connector->hdcp_value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		schedule_work(&connector->hdcp_prop_work);
+		goto out;
+	}
+
+out:
+	mutex_unlock(&connector->hdcp_mutex);
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 8a9a925410e5..f5d7bfb43006 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -34,6 +34,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_hdcp.h>
 #include <drm/drm_scdc_helper.h>
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
@@ -876,6 +877,248 @@ void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
 					 adapter, enable);
 }
 
+static int intel_hdmi_hdcp_read(struct intel_digital_port *intel_dig_port,
+				unsigned int offset, void *buffer, size_t size)
+{
+	struct intel_hdmi *hdmi = &intel_dig_port->hdmi;
+	struct drm_i915_private *dev_priv =
+		intel_dig_port->base.base.dev->dev_private;
+	struct i2c_adapter *adapter = intel_gmbus_get_adapter(dev_priv,
+							      hdmi->ddc_bus);
+	int ret;
+	u8 start = offset & 0xff;
+	struct i2c_msg msgs[] = {
+		{
+			.addr = DRM_HDCP_DDC_ADDR,
+			.flags = 0,
+			.len = 1,
+			.buf = &start,
+		},
+		{
+			.addr = DRM_HDCP_DDC_ADDR,
+			.flags = I2C_M_RD,
+			.len = size,
+			.buf = buffer
+		}
+	};
+	ret = i2c_transfer(adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret == ARRAY_SIZE(msgs))
+		return 0;
+	return ret >= 0 ? -EIO : ret;
+}
+
+static int intel_hdmi_hdcp_write(struct intel_digital_port *intel_dig_port,
+				 unsigned int offset, void *buffer, size_t size)
+{
+	struct intel_hdmi *hdmi = &intel_dig_port->hdmi;
+	struct drm_i915_private *dev_priv =
+		intel_dig_port->base.base.dev->dev_private;
+	struct i2c_adapter *adapter = intel_gmbus_get_adapter(dev_priv,
+							      hdmi->ddc_bus);
+	int ret;
+	u8 *write_buf;
+	struct i2c_msg msg;
+
+	write_buf = kzalloc(size + 1, GFP_KERNEL);
+	if (!write_buf)
+		return -ENOMEM;
+
+	write_buf[0] = offset & 0xff;
+	memcpy(&write_buf[1], buffer, size);
+
+	msg.addr = DRM_HDCP_DDC_ADDR;
+	msg.flags = 0,
+	msg.len = size + 1,
+	msg.buf = write_buf;
+
+	ret = i2c_transfer(adapter, &msg, 1);
+	if (ret == 1)
+		return 0;
+	return ret >= 0 ? -EIO : ret;
+}
+
+static
+int intel_hdmi_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
+				  u8 *an)
+{
+	struct intel_hdmi *hdmi = &intel_dig_port->hdmi;
+	struct drm_i915_private *dev_priv =
+		intel_dig_port->base.base.dev->dev_private;
+	struct i2c_adapter *adapter = intel_gmbus_get_adapter(dev_priv,
+							      hdmi->ddc_bus);
+	int ret;
+
+	ret = intel_hdmi_hdcp_write(intel_dig_port, DRM_HDCP_DDC_AN, an,
+				    DRM_HDCP_AN_LEN);
+	if (ret) {
+		DRM_ERROR("Write An over DDC failed (%d)\n", ret);
+		return ret;
+	}
+
+	ret = intel_gmbus_output_aksv(adapter);
+	if (ret < 0) {
+		DRM_ERROR("Failed to output aksv (%d)\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int intel_hdmi_hdcp_read_bksv(struct intel_digital_port *intel_dig_port,
+				     u8 *bksv)
+{
+	int ret;
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BKSV, bksv,
+				   DRM_HDCP_KSV_LEN);
+	if (ret)
+		DRM_ERROR("Read Bksv over DDC failed (%d)\n", ret);
+	return ret;
+}
+
+static
+int intel_hdmi_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port,
+				 u8 *bstatus)
+{
+	int ret;
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BSTATUS,
+				   bstatus, DRM_HDCP_BSTATUS_LEN);
+	if (ret)
+		DRM_ERROR("Read bstatus over DDC failed (%d)\n", ret);
+	return ret;
+}
+
+static
+int intel_hdmi_hdcp_repeater_present(struct intel_digital_port *intel_dig_port,
+				     bool *repeater_present)
+{
+	int ret;
+	u8 val;
+
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1);
+	if (ret) {
+		DRM_ERROR("Read bcaps over DDC failed (%d)\n", ret);
+		return ret;
+	}
+	*repeater_present = val & DRM_HDCP_DDC_BCAPS_REPEATER_PRESENT;
+	return 0;
+}
+
+static
+int intel_hdmi_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port,
+				  u8 *ri_prime)
+{
+	int ret;
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_RI_PRIME,
+				   ri_prime, DRM_HDCP_RI_LEN);
+	if (ret)
+		DRM_ERROR("Read Ri' over DDC failed (%d)\n", ret);
+	return ret;
+}
+
+static
+int intel_hdmi_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port,
+				   bool *ksv_ready)
+{
+	int ret;
+	u8 val;
+
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1);
+	if (ret) {
+		DRM_ERROR("Read bcaps over DDC failed (%d)\n", ret);
+		return ret;
+	}
+	*ksv_ready = val & DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY;
+	return 0;
+}
+
+static
+int intel_hdmi_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port,
+				  int num_downstream, u8 *ksv_fifo)
+{
+	int ret;
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_KSV_FIFO,
+				   ksv_fifo, num_downstream * DRM_HDCP_KSV_LEN);
+	if (ret) {
+		DRM_ERROR("Read ksv fifo over DDC failed (%d)\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static
+int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port,
+				      int i, u32 *part)
+{
+	int ret;
+
+	if (i >= DRM_HDCP_V_PRIME_NUM_PARTS)
+		return -EINVAL;
+
+	ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_V_PRIME(i),
+				   part, DRM_HDCP_V_PRIME_PART_LEN);
+	if (ret)
+		DRM_ERROR("Read V'[%d] over DDC failed (%d)\n", i, ret);
+	return ret;
+}
+
+static
+int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port,
+				      bool enable)
+{
+	int ret;
+
+	if (!enable)
+		usleep_range(6, 60); /* Bspec says >= 6us */
+
+	ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, enable);
+	if (ret) {
+		DRM_ERROR("%s HDCP signalling failed (%d)\n",
+			  enable ? "Enable" : "Disable", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static
+bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
+{
+	struct drm_i915_private *dev_priv =
+		intel_dig_port->base.base.dev->dev_private;
+	enum port port = intel_dig_port->base.port;
+	int ret;
+	union {
+		u32 reg;
+		u8 shim[DRM_HDCP_RI_LEN];
+	} ri;
+
+	ret = intel_hdmi_hdcp_read_ri_prime(intel_dig_port, ri.shim);
+	if (ret)
+		return false;
+
+	I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+
+	/* Wait for Ri prime match */
+	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
+		DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n",
+			  I915_READ(PORT_HDCP_STATUS(port)));
+		return false;
+	}
+	return true;
+}
+
+static const struct intel_hdcp_shim intel_hdmi_hdcp_shim = {
+	.write_an_aksv = intel_hdmi_hdcp_write_an_aksv,
+	.read_bksv = intel_hdmi_hdcp_read_bksv,
+	.read_bstatus = intel_hdmi_hdcp_read_bstatus,
+	.repeater_present = intel_hdmi_hdcp_repeater_present,
+	.read_ri_prime = intel_hdmi_hdcp_read_ri_prime,
+	.read_ksv_ready = intel_hdmi_hdcp_read_ksv_ready,
+	.read_ksv_fifo = intel_hdmi_hdcp_read_ksv_fifo,
+	.read_v_prime_part = intel_hdmi_hdcp_read_v_prime_part,
+	.toggle_signalling = intel_hdmi_hdcp_toggle_signalling,
+	.check_link = intel_hdmi_hdcp_check_link,
+};
+
 static void intel_hdmi_prepare(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *crtc_state)
 {
@@ -1564,7 +1807,10 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
 	 * there's nothing connected to the port.
 	 */
 	if (type == DRM_DP_DUAL_MODE_UNKNOWN) {
-		if (has_edid &&
+		/* An overridden EDID imply that we want this port for testing.
+		 * Make sure not to set limits for that port.
+		 */
+		if (has_edid && !connector->override_edid &&
 		    intel_bios_is_port_dp_dual_mode(dev_priv, port)) {
 			DRM_DEBUG_KMS("Assuming DP dual mode adaptor presence based on VBT\n");
 			type = DRM_DP_DUAL_MODE_TYPE1_DVI;
@@ -1592,12 +1838,20 @@ intel_hdmi_set_edid(struct drm_connector *connector)
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 	struct edid *edid;
 	bool connected = false;
+	struct i2c_adapter *i2c;
 
 	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
-	edid = drm_get_edid(connector,
-			    intel_gmbus_get_adapter(dev_priv,
-			    intel_hdmi->ddc_bus));
+	i2c = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
+
+	edid = drm_get_edid(connector, i2c);
+
+	if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
+		DRM_DEBUG_KMS("HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n");
+		intel_gmbus_force_bit(i2c, true);
+		edid = drm_get_edid(connector, i2c);
+		intel_gmbus_force_bit(i2c, false);
+	}
 
 	intel_hdmi_dp_dual_mode_detect(connector, edid != NULL);
 
@@ -1921,6 +2175,9 @@ static u8 cnp_port_to_ddc_pin(struct drm_i915_private *dev_priv,
 	case PORT_D:
 		ddc_pin = GMBUS_PIN_4_CNP;
 		break;
+	case PORT_F:
+		ddc_pin = GMBUS_PIN_3_BXT;
+		break;
 	default:
 		MISSING_CASE(port);
 		ddc_pin = GMBUS_PIN_1_BXT;
@@ -1929,6 +2186,37 @@ static u8 cnp_port_to_ddc_pin(struct drm_i915_private *dev_priv,
 	return ddc_pin;
 }
 
+static u8 icl_port_to_ddc_pin(struct drm_i915_private *dev_priv, enum port port)
+{
+	u8 ddc_pin;
+
+	switch (port) {
+	case PORT_A:
+		ddc_pin = GMBUS_PIN_1_BXT;
+		break;
+	case PORT_B:
+		ddc_pin = GMBUS_PIN_2_BXT;
+		break;
+	case PORT_C:
+		ddc_pin = GMBUS_PIN_9_TC1_ICP;
+		break;
+	case PORT_D:
+		ddc_pin = GMBUS_PIN_10_TC2_ICP;
+		break;
+	case PORT_E:
+		ddc_pin = GMBUS_PIN_11_TC3_ICP;
+		break;
+	case PORT_F:
+		ddc_pin = GMBUS_PIN_12_TC4_ICP;
+		break;
+	default:
+		MISSING_CASE(port);
+		ddc_pin = GMBUS_PIN_2_BXT;
+		break;
+	}
+	return ddc_pin;
+}
+
 static u8 g4x_port_to_ddc_pin(struct drm_i915_private *dev_priv,
 			      enum port port)
 {
@@ -1971,6 +2259,8 @@ static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
 		ddc_pin = bxt_port_to_ddc_pin(dev_priv, port);
 	else if (HAS_PCH_CNP(dev_priv))
 		ddc_pin = cnp_port_to_ddc_pin(dev_priv, port);
+	else if (IS_ICELAKE(dev_priv))
+		ddc_pin = icl_port_to_ddc_pin(dev_priv, port);
 	else
 		ddc_pin = g4x_port_to_ddc_pin(dev_priv, port);
 
@@ -2041,7 +2331,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 
 	if (WARN_ON(port == PORT_A))
 		return;
-	intel_encoder->hpd_pin = intel_hpd_pin(port);
+	intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port);
 
 	if (HAS_DDI(dev_priv))
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
@@ -2050,6 +2340,13 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 
 	intel_hdmi_add_properties(intel_hdmi, connector);
 
+	if (is_hdcp_supported(dev_priv, port)) {
+		int ret = intel_hdcp_init(intel_connector,
+					  &intel_hdmi_hdcp_shim);
+		if (ret)
+			DRM_DEBUG_KMS("HDCP init failed, skipping.\n");
+	}
+
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_hdmi->attached_connector = intel_connector;
 
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 875d5d218d5c..fe28c1ea84a5 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -78,12 +78,14 @@
 
 /**
  * intel_hpd_port - return port hard associated with certain pin.
+ * @dev_priv: private driver data pointer
  * @pin: the hpd pin to get associated port
  *
  * Return port that is associatade with @pin and PORT_NONE if no port is
  * hard associated with that @pin.
  */
-enum port intel_hpd_pin_to_port(enum hpd_pin pin)
+enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
+				enum hpd_pin pin)
 {
 	switch (pin) {
 	case HPD_PORT_A:
@@ -95,6 +97,8 @@ enum port intel_hpd_pin_to_port(enum hpd_pin pin)
 	case HPD_PORT_D:
 		return PORT_D;
 	case HPD_PORT_E:
+		if (IS_CNL_WITH_PORT_F(dev_priv))
+			return PORT_F;
 		return PORT_E;
 	default:
 		return PORT_NONE; /* no port for this pin */
@@ -102,13 +106,17 @@ enum port intel_hpd_pin_to_port(enum hpd_pin pin)
 }
 
 /**
- * intel_hpd_pin - return pin hard associated with certain port.
+ * intel_hpd_pin_default - return default pin associated with certain port.
+ * @dev_priv: private driver data pointer
  * @port: the hpd port to get associated pin
  *
+ * It is only valid and used by digital port encoder.
+ *
  * Return pin that is associatade with @port and HDP_NONE if no pin is
  * hard associated with that @port.
  */
-enum hpd_pin intel_hpd_pin(enum port port)
+enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
+				   enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -121,6 +129,9 @@ enum hpd_pin intel_hpd_pin(enum port port)
 		return HPD_PORT_D;
 	case PORT_E:
 		return HPD_PORT_E;
+	case PORT_F:
+		if (IS_CNL_WITH_PORT_F(dev_priv))
+			return HPD_PORT_E;
 	default:
 		MISSING_CASE(port);
 		return HPD_NONE;
@@ -417,7 +428,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		if (!(BIT(i) & pin_mask))
 			continue;
 
-		port = intel_hpd_pin_to_port(i);
+		port = intel_hpd_pin_to_port(dev_priv, i);
 		is_dig_port = port != PORT_NONE &&
 			dev_priv->hotplug.irq_port[port];
 
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 974be3defa70..8ed05182f944 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -54,10 +54,6 @@
 #define KBL_HUC_FW_MINOR 00
 #define KBL_BLD_NUM 1810
 
-#define GLK_HUC_FW_MAJOR 02
-#define GLK_HUC_FW_MINOR 00
-#define GLK_BLD_NUM 1748
-
 #define HUC_FW_PATH(platform, major, minor, bld_num) \
 	"i915/" __stringify(platform) "_huc_ver" __stringify(major) "_" \
 	__stringify(minor) "_" __stringify(bld_num) ".bin"
@@ -74,9 +70,6 @@ MODULE_FIRMWARE(I915_BXT_HUC_UCODE);
 	KBL_HUC_FW_MINOR, KBL_BLD_NUM)
 MODULE_FIRMWARE(I915_KBL_HUC_UCODE);
 
-#define I915_GLK_HUC_UCODE HUC_FW_PATH(glk, GLK_HUC_FW_MAJOR, \
-	GLK_HUC_FW_MINOR, GLK_BLD_NUM)
-
 static void huc_fw_select(struct intel_uc_fw *huc_fw)
 {
 	struct intel_huc *huc = container_of(huc_fw, struct intel_huc, fw);
@@ -103,10 +96,6 @@ static void huc_fw_select(struct intel_uc_fw *huc_fw)
 		huc_fw->path = I915_KBL_HUC_UCODE;
 		huc_fw->major_ver_wanted = KBL_HUC_FW_MAJOR;
 		huc_fw->minor_ver_wanted = KBL_HUC_FW_MINOR;
-	} else if (IS_GEMINILAKE(dev_priv)) {
-		huc_fw->path = I915_GLK_HUC_UCODE;
-		huc_fw->major_ver_wanted = GLK_HUC_FW_MAJOR;
-		huc_fw->minor_ver_wanted = GLK_HUC_FW_MINOR;
 	} else {
 		DRM_WARN("%s: No firmware known for this platform!\n",
 			 intel_uc_fw_type_repr(huc_fw->type));
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index ef9f91a0b0c9..e6875509bcd9 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -30,6 +30,7 @@
 #include <linux/i2c-algo-bit.h>
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include <drm/drm_hdcp.h>
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -75,11 +76,22 @@ static const struct gmbus_pin gmbus_pins_cnp[] = {
 	[GMBUS_PIN_4_CNP] = { "dpd", GPIOE },
 };
 
+static const struct gmbus_pin gmbus_pins_icp[] = {
+	[GMBUS_PIN_1_BXT] = { "dpa", GPIOA },
+	[GMBUS_PIN_2_BXT] = { "dpb", GPIOB },
+	[GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOC },
+	[GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOD },
+	[GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOE },
+	[GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOF },
+};
+
 /* pin is expected to be valid */
 static const struct gmbus_pin *get_gmbus_pin(struct drm_i915_private *dev_priv,
 					     unsigned int pin)
 {
-	if (HAS_PCH_CNP(dev_priv))
+	if (HAS_PCH_ICP(dev_priv))
+		return &gmbus_pins_icp[pin];
+	else if (HAS_PCH_CNP(dev_priv))
 		return &gmbus_pins_cnp[pin];
 	else if (IS_GEN9_LP(dev_priv))
 		return &gmbus_pins_bxt[pin];
@@ -96,7 +108,9 @@ bool intel_gmbus_is_valid_pin(struct drm_i915_private *dev_priv,
 {
 	unsigned int size;
 
-	if (HAS_PCH_CNP(dev_priv))
+	if (HAS_PCH_ICP(dev_priv))
+		size = ARRAY_SIZE(gmbus_pins_icp);
+	else if (HAS_PCH_CNP(dev_priv))
 		size = ARRAY_SIZE(gmbus_pins_cnp);
 	else if (IS_GEN9_LP(dev_priv))
 		size = ARRAY_SIZE(gmbus_pins_bxt);
@@ -402,7 +416,8 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 
 static int
 gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
-		       unsigned short addr, u8 *buf, unsigned int len)
+		       unsigned short addr, u8 *buf, unsigned int len,
+		       u32 gmbus1_index)
 {
 	unsigned int chunk_size = len;
 	u32 val, loop;
@@ -415,7 +430,7 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
 
 	I915_WRITE_FW(GMBUS3, val);
 	I915_WRITE_FW(GMBUS1,
-		      GMBUS_CYCLE_WAIT |
+		      gmbus1_index | GMBUS_CYCLE_WAIT |
 		      (chunk_size << GMBUS_BYTE_COUNT_SHIFT) |
 		      (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		      GMBUS_SLAVE_WRITE | GMBUS_SW_RDY);
@@ -438,7 +453,8 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
 }
 
 static int
-gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
+gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
+		 u32 gmbus1_index)
 {
 	u8 *buf = msg->buf;
 	unsigned int tx_size = msg->len;
@@ -448,7 +464,8 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
 	do {
 		len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
 
-		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len);
+		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len,
+					     gmbus1_index);
 		if (ret)
 			return ret;
 
@@ -460,21 +477,21 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
 }
 
 /*
- * The gmbus controller can combine a 1 or 2 byte write with a read that
- * immediately follows it by using an "INDEX" cycle.
+ * The gmbus controller can combine a 1 or 2 byte write with another read/write
+ * that immediately follows it by using an "INDEX" cycle.
  */
 static bool
-gmbus_is_index_read(struct i2c_msg *msgs, int i, int num)
+gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num)
 {
 	return (i + 1 < num &&
 		msgs[i].addr == msgs[i + 1].addr &&
 		!(msgs[i].flags & I2C_M_RD) &&
 		(msgs[i].len == 1 || msgs[i].len == 2) &&
-		(msgs[i + 1].flags & I2C_M_RD));
+		msgs[i + 1].len > 0);
 }
 
 static int
-gmbus_xfer_index_read(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
+gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 {
 	u32 gmbus1_index = 0;
 	u32 gmbus5 = 0;
@@ -491,7 +508,10 @@ gmbus_xfer_index_read(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 	if (gmbus5)
 		I915_WRITE_FW(GMBUS5, gmbus5);
 
-	ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
+	if (msgs[1].flags & I2C_M_RD)
+		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
+	else
+		ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index);
 
 	/* Clear GMBUS5 after each index transfer */
 	if (gmbus5)
@@ -501,7 +521,8 @@ gmbus_xfer_index_read(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 }
 
 static int
-do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
+do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num,
+	      u32 gmbus0_source)
 {
 	struct intel_gmbus *bus = container_of(adapter,
 					       struct intel_gmbus,
@@ -518,17 +539,17 @@ do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
 		pch_gmbus_clock_gating(dev_priv, false);
 
 retry:
-	I915_WRITE_FW(GMBUS0, bus->reg0);
+	I915_WRITE_FW(GMBUS0, gmbus0_source | bus->reg0);
 
 	for (; i < num; i += inc) {
 		inc = 1;
-		if (gmbus_is_index_read(msgs, i, num)) {
-			ret = gmbus_xfer_index_read(dev_priv, &msgs[i]);
-			inc = 2; /* an index read is two msgs */
+		if (gmbus_is_index_xfer(msgs, i, num)) {
+			ret = gmbus_index_xfer(dev_priv, &msgs[i]);
+			inc = 2; /* an index transmission is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
 			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
 		} else {
-			ret = gmbus_xfer_write(dev_priv, &msgs[i]);
+			ret = gmbus_xfer_write(dev_priv, &msgs[i], 0);
 		}
 
 		if (!ret)
@@ -643,7 +664,7 @@ gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
 		if (ret < 0)
 			bus->force_bit &= ~GMBUS_FORCE_BIT_RETRY;
 	} else {
-		ret = do_gmbus_xfer(adapter, msgs, num);
+		ret = do_gmbus_xfer(adapter, msgs, num, 0);
 		if (ret == -EAGAIN)
 			bus->force_bit |= GMBUS_FORCE_BIT_RETRY;
 	}
@@ -653,6 +674,45 @@ gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
 	return ret;
 }
 
+int intel_gmbus_output_aksv(struct i2c_adapter *adapter)
+{
+	struct intel_gmbus *bus = container_of(adapter, struct intel_gmbus,
+					       adapter);
+	struct drm_i915_private *dev_priv = bus->dev_priv;
+	int ret;
+	u8 cmd = DRM_HDCP_DDC_AKSV;
+	u8 buf[DRM_HDCP_KSV_LEN] = { 0 };
+	struct i2c_msg msgs[] = {
+		{
+			.addr = DRM_HDCP_DDC_ADDR,
+			.flags = 0,
+			.len = sizeof(cmd),
+			.buf = &cmd,
+		},
+		{
+			.addr = DRM_HDCP_DDC_ADDR,
+			.flags = 0,
+			.len = sizeof(buf),
+			.buf = buf,
+		}
+	};
+
+	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+	mutex_lock(&dev_priv->gmbus_mutex);
+
+	/*
+	 * In order to output Aksv to the receiver, use an indexed write to
+	 * pass the i2c command, and tell GMBUS to use the HW-provided value
+	 * instead of sourcing GMBUS3 for the data.
+	 */
+	ret = do_gmbus_xfer(adapter, msgs, ARRAY_SIZE(msgs), GMBUS_AKSV_SELECT);
+
+	mutex_unlock(&dev_priv->gmbus_mutex);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+
+	return ret;
+}
+
 static u32 gmbus_func(struct i2c_adapter *adapter)
 {
 	return i2c_bit_algo.functionality(adapter) &
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7ece2f061b9e..380c0838d8b3 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -137,6 +137,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_gem_render_state.h"
+#include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 
 #define RING_EXECLIST_QFULL		(1 << 0x2)
@@ -156,55 +157,6 @@
 #define GEN8_CTX_STATUS_COMPLETED_MASK \
 	 (GEN8_CTX_STATUS_COMPLETE | GEN8_CTX_STATUS_PREEMPTED)
 
-#define CTX_LRI_HEADER_0		0x01
-#define CTX_CONTEXT_CONTROL		0x02
-#define CTX_RING_HEAD			0x04
-#define CTX_RING_TAIL			0x06
-#define CTX_RING_BUFFER_START		0x08
-#define CTX_RING_BUFFER_CONTROL		0x0a
-#define CTX_BB_HEAD_U			0x0c
-#define CTX_BB_HEAD_L			0x0e
-#define CTX_BB_STATE			0x10
-#define CTX_SECOND_BB_HEAD_U		0x12
-#define CTX_SECOND_BB_HEAD_L		0x14
-#define CTX_SECOND_BB_STATE		0x16
-#define CTX_BB_PER_CTX_PTR		0x18
-#define CTX_RCS_INDIRECT_CTX		0x1a
-#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
-#define CTX_LRI_HEADER_1		0x21
-#define CTX_CTX_TIMESTAMP		0x22
-#define CTX_PDP3_UDW			0x24
-#define CTX_PDP3_LDW			0x26
-#define CTX_PDP2_UDW			0x28
-#define CTX_PDP2_LDW			0x2a
-#define CTX_PDP1_UDW			0x2c
-#define CTX_PDP1_LDW			0x2e
-#define CTX_PDP0_UDW			0x30
-#define CTX_PDP0_LDW			0x32
-#define CTX_LRI_HEADER_2		0x41
-#define CTX_R_PWR_CLK_STATE		0x42
-#define CTX_GPGPU_CSR_BASE_ADDRESS	0x44
-
-#define CTX_REG(reg_state, pos, reg, val) do { \
-	(reg_state)[(pos)+0] = i915_mmio_reg_offset(reg); \
-	(reg_state)[(pos)+1] = (val); \
-} while (0)
-
-#define ASSIGN_CTX_PDP(ppgtt, reg_state, n) do {		\
-	const u64 _addr = i915_page_dir_dma_addr((ppgtt), (n));	\
-	reg_state[CTX_PDP ## n ## _UDW+1] = upper_32_bits(_addr); \
-	reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
-} while (0)
-
-#define ASSIGN_CTX_PML4(ppgtt, reg_state) do { \
-	reg_state[CTX_PDP0_UDW + 1] = upper_32_bits(px_dma(&ppgtt->pml4)); \
-	reg_state[CTX_PDP0_LDW + 1] = lower_32_bits(px_dma(&ppgtt->pml4)); \
-} while (0)
-
-#define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
-#define GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x26
-#define GEN10_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x19
-
 /* Typical size of the average request (2 pipecontrols and a MI_BB) */
 #define EXECLISTS_REQUEST_SIZE 64 /* bytes */
 #define WA_TAIL_DWORDS 2
@@ -504,6 +456,12 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 	ce->ring->tail &= (ce->ring->size - 1);
 	ce->lrc_reg_state[CTX_RING_TAIL+1] = ce->ring->tail;
 
+	GEM_BUG_ON((ce->lrc_reg_state[CTX_CONTEXT_CONTROL + 1] &
+		    _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
+				       CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT)) !=
+		   _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
+				      CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT));
+
 	GEM_TRACE("%s\n", engine->name);
 	for (n = execlists_num_ports(&engine->execlists); --n; )
 		elsp_write(0, engine->execlists.elsp);
@@ -778,6 +736,7 @@ static void execlists_submission_tasklet(unsigned long data)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port * const port = execlists->port;
 	struct drm_i915_private *dev_priv = engine->i915;
+	bool fw = false;
 
 	/* We can skip acquiring intel_runtime_pm_get() here as it was taken
 	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
@@ -788,8 +747,6 @@ static void execlists_submission_tasklet(unsigned long data)
 	 */
 	GEM_BUG_ON(!dev_priv->gt.awake);
 
-	intel_uncore_forcewake_get(dev_priv, execlists->fw_domains);
-
 	/* Prefer doing test_and_clear_bit() as a two stage operation to avoid
 	 * imposing the cost of a locked atomic transaction when submitting a
 	 * new request (outside of the context-switch interrupt).
@@ -818,6 +775,12 @@ static void execlists_submission_tasklet(unsigned long data)
 		 */
 		__clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 		if (unlikely(execlists->csb_head == -1)) { /* following a reset */
+			if (!fw) {
+				intel_uncore_forcewake_get(dev_priv,
+							   execlists->fw_domains);
+				fw = true;
+			}
+
 			head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
 			tail = GEN8_CSB_WRITE_PTR(head);
 			head = GEN8_CSB_READ_PTR(head);
@@ -830,10 +793,10 @@ static void execlists_submission_tasklet(unsigned long data)
 			head = execlists->csb_head;
 			tail = READ_ONCE(buf[write_idx]);
 		}
-		GEM_TRACE("%s cs-irq head=%d [%d], tail=%d [%d]\n",
+		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
 			  engine->name,
-			  head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))),
-			  tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))));
+			  head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
+			  tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
 		while (head != tail) {
 			struct drm_i915_gem_request *rq;
@@ -943,7 +906,8 @@ static void execlists_submission_tasklet(unsigned long data)
 	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
 
-	intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+	if (fw)
+		intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
 }
 
 static void insert_request(struct intel_engine_cs *engine,
@@ -1014,7 +978,8 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 	stack.signaler = &request->priotree;
 	list_add(&stack.dfs_link, &dfs);
 
-	/* Recursively bump all dependent priorities to match the new request.
+	/*
+	 * Recursively bump all dependent priorities to match the new request.
 	 *
 	 * A naive approach would be to use recursion:
 	 * static void update_priorities(struct i915_priotree *pt, prio) {
@@ -1031,27 +996,29 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
 	 * end result is a topological list of requests in reverse order, the
 	 * last element in the list is the request we must execute first.
 	 */
-	list_for_each_entry_safe(dep, p, &dfs, dfs_link) {
+	list_for_each_entry(dep, &dfs, dfs_link) {
 		struct i915_priotree *pt = dep->signaler;
 
-		/* Within an engine, there can be no cycle, but we may
+		/*
+		 * Within an engine, there can be no cycle, but we may
 		 * refer to the same dependency chain multiple times
 		 * (redundant dependencies are not eliminated) and across
 		 * engines.
 		 */
 		list_for_each_entry(p, &pt->signalers_list, signal_link) {
-			if (i915_gem_request_completed(pt_to_request(p->signaler)))
+			GEM_BUG_ON(p == dep); /* no cycles! */
+
+			if (i915_priotree_signaled(p->signaler))
 				continue;
 
 			GEM_BUG_ON(p->signaler->priority < pt->priority);
 			if (prio > READ_ONCE(p->signaler->priority))
 				list_move_tail(&p->dfs_link, &dfs);
 		}
-
-		list_safe_reset_next(dep, p, dfs_link);
 	}
 
-	/* If we didn't need to bump any existing priorities, and we haven't
+	/*
+	 * If we didn't need to bump any existing priorities, and we haven't
 	 * yet submitted this request (i.e. there is no potential race with
 	 * execlists_submit_request()), we can set our own priority and skip
 	 * acquiring the engine locks.
@@ -1125,11 +1092,9 @@ execlists_context_pin(struct intel_engine_cs *engine,
 		goto out;
 	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	if (!ce->state) {
-		ret = execlists_context_deferred_alloc(ctx, engine);
-		if (ret)
-			goto err;
-	}
+	ret = execlists_context_deferred_alloc(ctx, engine);
+	if (ret)
+		goto err;
 	GEM_BUG_ON(!ce->state);
 
 	ret = __context_pin(ctx, ce->state);
@@ -1363,6 +1328,40 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
+static u32 *
+gen10_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
+{
+	int i;
+
+	/*
+	 * WaPipeControlBefore3DStateSamplePattern: cnl
+	 *
+	 * Ensure the engine is idle prior to programming a
+	 * 3DSTATE_SAMPLE_PATTERN during a context restore.
+	 */
+	batch = gen8_emit_pipe_control(batch,
+				       PIPE_CONTROL_CS_STALL,
+				       0);
+	/*
+	 * WaPipeControlBefore3DStateSamplePattern says we need 4 dwords for
+	 * the PIPE_CONTROL followed by 12 dwords of 0x0, so 16 dwords in
+	 * total. However, a PIPE_CONTROL is 6 dwords long, not 4, which is
+	 * confusing. Since gen8_emit_pipe_control() already advances the
+	 * batch by 6 dwords, we advance the other 10 here, completing a
+	 * cacheline. It's not clear if the workaround requires this padding
+	 * before other commands, or if it's just the regular padding we would
+	 * already have for the workaround bb, so leave it here for now.
+	 */
+	for (i = 0; i < 10; i++)
+		*batch++ = MI_NOOP;
+
+	/* Pad to end of cacheline */
+	while ((unsigned long)batch % CACHELINE_BYTES)
+		*batch++ = MI_NOOP;
+
+	return batch;
+}
+
 #define CTX_WA_BB_OBJ_SIZE (PAGE_SIZE)
 
 static int lrc_setup_wa_ctx(struct intel_engine_cs *engine)
@@ -1411,12 +1410,14 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	unsigned int i;
 	int ret;
 
-	if (WARN_ON(engine->id != RCS || !engine->scratch))
+	if (GEM_WARN_ON(engine->id != RCS))
 		return -EINVAL;
 
 	switch (INTEL_GEN(engine->i915)) {
 	case 10:
-		return 0;
+		wa_bb_fn[0] = gen10_init_indirectctx_bb;
+		wa_bb_fn[1] = NULL;
+		break;
 	case 9:
 		wa_bb_fn[0] = gen9_init_indirectctx_bb;
 		wa_bb_fn[1] = NULL;
@@ -1446,7 +1447,8 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	 */
 	for (i = 0; i < ARRAY_SIZE(wa_bb_fn); i++) {
 		wa_bb[i]->offset = batch_ptr - batch;
-		if (WARN_ON(!IS_ALIGNED(wa_bb[i]->offset, CACHELINE_BYTES))) {
+		if (GEM_WARN_ON(!IS_ALIGNED(wa_bb[i]->offset,
+					    CACHELINE_BYTES))) {
 			ret = -EINVAL;
 			break;
 		}
@@ -1472,47 +1474,48 @@ static u8 gtiir[] = {
 	[VECS] = 3,
 };
 
-static int gen8_init_common_ring(struct intel_engine_cs *engine)
+static void enable_execlists(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	int ret;
 
-	ret = intel_mocs_init_engine(engine);
-	if (ret)
-		return ret;
+	I915_WRITE(RING_HWSTAM(engine->mmio_base), 0xffffffff);
 
-	intel_engine_reset_breadcrumbs(engine);
-	intel_engine_init_hangcheck(engine);
+	/*
+	 * Make sure we're not enabling the new 12-deep CSB
+	 * FIFO as that requires a slightly updated handling
+	 * in the ctx switch irq. Since we're currently only
+	 * using only 2 elements of the enhanced execlists the
+	 * deeper FIFO it's not needed and it's not worth adding
+	 * more statements to the irq handler to support it.
+	 */
+	if (INTEL_GEN(dev_priv) >= 11)
+		I915_WRITE(RING_MODE_GEN7(engine),
+			   _MASKED_BIT_DISABLE(GEN11_GFX_DISABLE_LEGACY_MODE));
+	else
+		I915_WRITE(RING_MODE_GEN7(engine),
+			   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
 
-	I915_WRITE(RING_HWSTAM(engine->mmio_base), 0xffffffff);
-	I915_WRITE(RING_MODE_GEN7(engine),
-		   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
 
-	DRM_DEBUG_DRIVER("Execlists enabled for %s\n", engine->name);
+	/* Following the reset, we need to reload the CSB read/write pointers */
+	engine->execlists.csb_head = -1;
+}
 
-	GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
+static int gen8_init_common_ring(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	int ret;
 
-	/*
-	 * Clear any pending interrupt state.
-	 *
-	 * We do it twice out of paranoia that some of the IIR are double
-	 * buffered, and if we only reset it once there may still be
-	 * an interrupt pending.
-	 */
-	I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-		   GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
-	I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-		   GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-	execlists->csb_head = -1;
-	execlists->active = 0;
+	ret = intel_mocs_init_engine(engine);
+	if (ret)
+		return ret;
+
+	intel_engine_reset_breadcrumbs(engine);
+	intel_engine_init_hangcheck(engine);
 
-	execlists->elsp =
-		dev_priv->regs + i915_mmio_reg_offset(RING_ELSP(engine));
+	enable_execlists(engine);
 
 	/* After a GPU reset, we may have requests to replay */
 	if (execlists->first)
@@ -1554,6 +1557,31 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine)
 	return init_workarounds_ring(engine);
 }
 
+static void reset_irq(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	int i;
+
+	GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
+
+	/*
+	 * Clear any pending interrupt state.
+	 *
+	 * We do it twice out of paranoia that some of the IIR are double
+	 * buffered, and if we only reset it once there may still be
+	 * an interrupt pending.
+	 */
+	for (i = 0; i < 2; i++) {
+		I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
+			   GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
+		POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
+	}
+	GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
+		   (GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift));
+
+	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+}
+
 static void reset_common_ring(struct intel_engine_cs *engine,
 			      struct drm_i915_gem_request *request)
 {
@@ -1563,6 +1591,9 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 
 	GEM_TRACE("%s seqno=%x\n",
 		  engine->name, request ? request->global_seqno : 0);
+
+	reset_irq(engine);
+
 	spin_lock_irqsave(&engine->timeline->lock, flags);
 
 	/*
@@ -1581,6 +1612,9 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 
 	spin_unlock_irqrestore(&engine->timeline->lock, flags);
 
+	/* Mark all CS interrupts as complete */
+	execlists->active = 0;
+
 	/* If the request was innocent, we leave the request in the ELSP
 	 * and will try to replay it on restarting. The context image may
 	 * have been corrupted by the reset, in which case we may have
@@ -1912,6 +1946,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	intel_engine_cleanup_common(engine);
 
 	lrc_destroy_wa_ctx(engine);
+
 	engine->i915 = NULL;
 	dev_priv->engine[engine->id] = NULL;
 	kfree(engine);
@@ -2001,6 +2036,9 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 	if (ret)
 		goto error;
 
+	engine->execlists.elsp =
+		engine->i915->regs + i915_mmio_reg_offset(RING_ELSP(engine));
+
 	return 0;
 
 error:
@@ -2142,6 +2180,8 @@ static void execlists_init_reg_state(u32 *regs,
 				 MI_LRI_FORCE_POSTED;
 
 	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(engine),
+		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
+				    CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT) |
 		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
 				   (HAS_RESOURCE_STREAMER(dev_priv) ?
 				   CTX_CTRL_RS_CTX_ENABLE : 0)));
@@ -2261,6 +2301,10 @@ populate_lr_context(struct i915_gem_context *ctx,
 	if (!engine->default_state)
 		regs[CTX_CONTEXT_CONTROL + 1] |=
 			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	if (ctx->hw_id == PREEMPT_ID)
+		regs[CTX_CONTEXT_CONTROL + 1] |=
+			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
+					   CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT);
 
 	i915_gem_object_unpin_map(ctx_obj);
 
@@ -2277,7 +2321,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 	struct intel_ring *ring;
 	int ret;
 
-	WARN_ON(ce->state);
+	if (ce->state)
+		return 0;
 
 	context_size = round_up(engine->context_size, I915_GTT_PAGE_SIZE);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 6d4f9b995a11..636ced41225d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -37,6 +37,7 @@
 #define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	(1 << 3)
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define   CTX_CTRL_RS_CTX_ENABLE                (1 << 1)
+#define	  CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT	(1 << 2)
 #define RING_CONTEXT_STATUS_BUF_BASE(engine)	_MMIO((engine)->mmio_base + 0x370)
 #define RING_CONTEXT_STATUS_BUF_LO(engine, i)	_MMIO((engine)->mmio_base + 0x370 + (i) * 8)
 #define RING_CONTEXT_STATUS_BUF_HI(engine, i)	_MMIO((engine)->mmio_base + 0x370 + (i) * 8 + 4)
diff --git a/drivers/gpu/drm/i915/intel_lrc_reg.h b/drivers/gpu/drm/i915/intel_lrc_reg.h
new file mode 100644
index 000000000000..a53336e2fc97
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_lrc_reg.h
@@ -0,0 +1,67 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2014-2018 Intel Corporation
+ */
+
+#ifndef _INTEL_LRC_REG_H_
+#define _INTEL_LRC_REG_H_
+
+#include <linux/types.h>
+
+/* GEN8+ Reg State Context */
+#define CTX_LRI_HEADER_0		0x01
+#define CTX_CONTEXT_CONTROL		0x02
+#define CTX_RING_HEAD			0x04
+#define CTX_RING_TAIL			0x06
+#define CTX_RING_BUFFER_START		0x08
+#define CTX_RING_BUFFER_CONTROL		0x0a
+#define CTX_BB_HEAD_U			0x0c
+#define CTX_BB_HEAD_L			0x0e
+#define CTX_BB_STATE			0x10
+#define CTX_SECOND_BB_HEAD_U		0x12
+#define CTX_SECOND_BB_HEAD_L		0x14
+#define CTX_SECOND_BB_STATE		0x16
+#define CTX_BB_PER_CTX_PTR		0x18
+#define CTX_RCS_INDIRECT_CTX		0x1a
+#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
+#define CTX_LRI_HEADER_1		0x21
+#define CTX_CTX_TIMESTAMP		0x22
+#define CTX_PDP3_UDW			0x24
+#define CTX_PDP3_LDW			0x26
+#define CTX_PDP2_UDW			0x28
+#define CTX_PDP2_LDW			0x2a
+#define CTX_PDP1_UDW			0x2c
+#define CTX_PDP1_LDW			0x2e
+#define CTX_PDP0_UDW			0x30
+#define CTX_PDP0_LDW			0x32
+#define CTX_LRI_HEADER_2		0x41
+#define CTX_R_PWR_CLK_STATE		0x42
+#define CTX_GPGPU_CSR_BASE_ADDRESS	0x44
+
+#define CTX_REG(reg_state, pos, reg, val) do { \
+	u32 *reg_state__ = (reg_state); \
+	const u32 pos__ = (pos); \
+	(reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \
+	(reg_state__)[(pos__) + 1] = (val); \
+} while (0)
+
+#define ASSIGN_CTX_PDP(ppgtt, reg_state, n) do { \
+	u32 *reg_state__ = (reg_state); \
+	const u64 addr__ = i915_page_dir_dma_addr((ppgtt), (n)); \
+	(reg_state__)[CTX_PDP ## n ## _UDW + 1] = upper_32_bits(addr__); \
+	(reg_state__)[CTX_PDP ## n ## _LDW + 1] = lower_32_bits(addr__); \
+} while (0)
+
+#define ASSIGN_CTX_PML4(ppgtt, reg_state) do { \
+	u32 *reg_state__ = (reg_state); \
+	const u64 addr__ = px_dma(&ppgtt->pml4); \
+	(reg_state__)[CTX_PDP0_UDW + 1] = upper_32_bits(addr__); \
+	(reg_state__)[CTX_PDP0_LDW + 1] = lower_32_bits(addr__); \
+} while (0)
+
+#define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
+#define GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x26
+#define GEN10_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x19
+
+#endif /* _INTEL_LRC_REG_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c
index dcbc786479f9..8ae8f42f430a 100644
--- a/drivers/gpu/drm/i915/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/intel_lspcon.c
@@ -167,11 +167,10 @@ static void lspcon_resume_in_pcon_wa(struct intel_lspcon *lspcon)
 {
 	struct intel_dp *intel_dp = lspcon_to_intel_dp(lspcon);
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
 	unsigned long start = jiffies;
 
 	while (1) {
-		if (intel_digital_port_connected(dev_priv, dig_port)) {
+		if (intel_digital_port_connected(&dig_port->base)) {
 			DRM_DEBUG_KMS("LSPCON recovering in PCON mode after %u ms\n",
 				      jiffies_to_msecs(jiffies - start));
 			return;
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 4e43f873c889..b39846613e3c 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -30,21 +30,6 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-static void intel_connector_update_eld_conn_type(struct drm_connector *connector)
-{
-	u8 conn_type;
-
-	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
-	    connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
-		conn_type = DRM_ELD_CONN_TYPE_DP;
-	} else {
-		conn_type = DRM_ELD_CONN_TYPE_HDMI;
-	}
-
-	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK;
-	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type;
-}
-
 /**
  * intel_connector_update_modes - update connector from edid
  * @connector: DRM connector device to use
@@ -58,8 +43,6 @@ int intel_connector_update_modes(struct drm_connector *connector,
 	drm_mode_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 
-	intel_connector_update_eld_conn_type(connector);
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index fa6831f8c004..e702a6487aa9 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1719,9 +1719,9 @@ cnp_setup_backlight(struct intel_connector *connector, enum pipe unused)
 	u32 pwm_ctl, val;
 
 	/*
-	 * CNP has the BXT implementation of backlight, but with only
-	 * one controller. Future platforms could have multiple controllers
-	 * so let's make this extensible and prepared for the future.
+	 * CNP has the BXT implementation of backlight, but with only one
+	 * controller. TODO: ICP has multiple controllers but we only use
+	 * controller 0 for now.
 	 */
 	panel->backlight.controller = 0;
 
@@ -1865,7 +1865,7 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel)
 		panel->backlight.set = bxt_set_backlight;
 		panel->backlight.get = bxt_get_backlight;
 		panel->backlight.hz_to_pwm = bxt_hz_to_pwm;
-	} else if (HAS_PCH_CNP(dev_priv)) {
+	} else if (HAS_PCH_CNP(dev_priv) || HAS_PCH_ICP(dev_priv)) {
 		panel->backlight.setup = cnp_setup_backlight;
 		panel->backlight.enable = cnp_enable_backlight;
 		panel->backlight.disable = cnp_disable_backlight;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1db79a860b96..eb68abf6a8e9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3694,11 +3694,18 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state)
 	struct intel_crtc_state *cstate;
 	enum pipe pipe;
 	int level, latency;
-	int sagv_block_time_us = IS_GEN9(dev_priv) ? 30 : 20;
+	int sagv_block_time_us;
 
 	if (!intel_has_sagv(dev_priv))
 		return false;
 
+	if (IS_GEN9(dev_priv))
+		sagv_block_time_us = 30;
+	else if (IS_GEN10(dev_priv))
+		sagv_block_time_us = 20;
+	else
+		sagv_block_time_us = 10;
+
 	/*
 	 * SKL+ workaround: bspec recommends we disable the SAGV when we have
 	 * more then one pipe enabled
@@ -3778,7 +3785,8 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 	ddb_size = INTEL_INFO(dev_priv)->ddb_size;
 	WARN_ON(ddb_size == 0);
 
-	ddb_size -= 4; /* 4 blocks for bypass path allocation */
+	if (INTEL_GEN(dev_priv) < 11)
+		ddb_size -= 4; /* 4 blocks for bypass path allocation */
 
 	/*
 	 * If the state doesn't change the active CRTC's, then there's
@@ -4311,7 +4319,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 */
 static uint_fixed_16_16_t
 skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
-	       uint8_t cpp, uint32_t latency)
+	       uint8_t cpp, uint32_t latency, uint32_t dbuf_block_size)
 {
 	uint32_t wm_intermediate_val;
 	uint_fixed_16_16_t ret;
@@ -4320,7 +4328,7 @@ skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
 		return FP_16_16_MAX;
 
 	wm_intermediate_val = latency * pixel_rate * cpp;
-	ret = div_fixed16(wm_intermediate_val, 1000 * 512);
+	ret = div_fixed16(wm_intermediate_val, 1000 * dbuf_block_size);
 
 	if (INTEL_GEN(dev_priv) >= 10)
 		ret = add_fixed16_u32(ret, 1);
@@ -4430,6 +4438,12 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 	wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate,
 							     intel_pstate);
 
+	if (INTEL_GEN(dev_priv) >= 11 &&
+	    fb->modifier == I915_FORMAT_MOD_Yf_TILED && wp->cpp == 8)
+		wp->dbuf_block_size = 256;
+	else
+		wp->dbuf_block_size = 512;
+
 	if (drm_rotation_90_or_270(pstate->rotation)) {
 
 		switch (wp->cpp) {
@@ -4456,7 +4470,8 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 	wp->plane_bytes_per_line = wp->width * wp->cpp;
 	if (wp->y_tiled) {
 		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line *
-					   wp->y_min_scanlines, 512);
+					   wp->y_min_scanlines,
+					   wp->dbuf_block_size);
 
 		if (INTEL_GEN(dev_priv) >= 10)
 			interm_pbpl++;
@@ -4464,10 +4479,12 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv,
 		wp->plane_blocks_per_line = div_fixed16(interm_pbpl,
 							wp->y_min_scanlines);
 	} else if (wp->x_tiled && IS_GEN9(dev_priv)) {
-		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, 512);
+		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
+					   wp->dbuf_block_size);
 		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	} else {
-		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, 512) + 1;
+		interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line,
+					   wp->dbuf_block_size) + 1;
 		wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
 	}
 
@@ -4497,6 +4514,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	struct intel_atomic_state *state =
 		to_intel_atomic_state(cstate->base.state);
 	bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
+	uint32_t min_disp_buf_needed;
 
 	if (latency == 0 ||
 	    !intel_wm_plane_visible(cstate, intel_pstate)) {
@@ -4514,7 +4532,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		latency += 15;
 
 	method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
-				 wp->cpp, latency);
+				 wp->cpp, latency, wp->dbuf_block_size);
 	method2 = skl_wm_method2(wp->plane_pixel_rate,
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 latency,
@@ -4524,7 +4542,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		selected_result = max_fixed16(method2, wp->y_tile_minimum);
 	} else {
 		if ((wp->cpp * cstate->base.adjusted_mode.crtc_htotal /
-		     512 < 1) && (wp->plane_bytes_per_line / 512 < 1))
+		     wp->dbuf_block_size < 1) &&
+		     (wp->plane_bytes_per_line / wp->dbuf_block_size < 1))
 			selected_result = method2;
 		else if (ddb_allocation >=
 			 fixed16_to_u32_round_up(wp->plane_blocks_per_line))
@@ -4554,7 +4573,31 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		}
 	}
 
-	if (res_blocks >= ddb_allocation || res_lines > 31) {
+	if (INTEL_GEN(dev_priv) >= 11) {
+		if (wp->y_tiled) {
+			uint32_t extra_lines;
+			uint_fixed_16_16_t fp_min_disp_buf_needed;
+
+			if (res_lines % wp->y_min_scanlines == 0)
+				extra_lines = wp->y_min_scanlines;
+			else
+				extra_lines = wp->y_min_scanlines * 2 -
+					      res_lines % wp->y_min_scanlines;
+
+			fp_min_disp_buf_needed = mul_u32_fixed16(res_lines +
+						extra_lines,
+						wp->plane_blocks_per_line);
+			min_disp_buf_needed = fixed16_to_u32_round_up(
+						fp_min_disp_buf_needed);
+		} else {
+			min_disp_buf_needed = DIV_ROUND_UP(res_blocks * 11, 10);
+		}
+	} else {
+		min_disp_buf_needed = res_blocks;
+	}
+
+	if (res_blocks >= ddb_allocation || res_lines > 31 ||
+	    min_disp_buf_needed >= ddb_allocation) {
 		*enabled = false;
 
 		/*
@@ -4790,8 +4833,10 @@ static void skl_write_plane_wm(struct intel_crtc *intel_crtc,
 
 	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
 			    &ddb->plane[pipe][plane_id]);
-	skl_ddb_entry_write(dev_priv, PLANE_NV12_BUF_CFG(pipe, plane_id),
-			    &ddb->y_plane[pipe][plane_id]);
+	if (INTEL_GEN(dev_priv) < 11)
+		skl_ddb_entry_write(dev_priv,
+				    PLANE_NV12_BUF_CFG(pipe, plane_id),
+				    &ddb->y_plane[pipe][plane_id]);
 }
 
 static void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
@@ -6626,9 +6671,29 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 
-	/* 2c: Program Coarse Power Gating Policies. */
-	I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 25);
-	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 25);
+	/*
+	 * 2c: Program Coarse Power Gating Policies.
+	 *
+	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
+	 * use instead is a more conservative estimate for the maximum time
+	 * it takes us to service a CS interrupt and submit a new ELSP - that
+	 * is the time which the GPU is idle waiting for the CPU to select the
+	 * next request to execute. If the idle hysteresis is less than that
+	 * interrupt service latency, the hardware will automatically gate
+	 * the power well and we will then incur the wake up cost on top of
+	 * the service latency. A similar guide from intel_pstate is that we
+	 * do not want the enable hysteresis to less than the wakeup latency.
+	 *
+	 * igt/gem_exec_nop/sequential provides a rough estimate for the
+	 * service latency, and puts it around 10us for Broadwell (and other
+	 * big core) and around 40us for Broxton (and other low power cores).
+	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
+	 * However, the wakeup latency on Broxton is closer to 100us. To be
+	 * conservative, we have to factor in a context switch on top (due
+	 * to ksoftirqd).
+	 */
+	I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
+	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
 
 	/* 3a: Enable RC6 */
 	I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
@@ -9149,8 +9214,9 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 	return 0;
 }
 
-int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
-			    u32 mbox, u32 val)
+int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
+				    u32 mbox, u32 val,
+				    int fast_timeout_us, int slow_timeout_ms)
 {
 	int status;
 
@@ -9173,7 +9239,8 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 
 	if (__intel_wait_for_register_fw(dev_priv,
 					 GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
-					 500, 0, NULL)) {
+					 fast_timeout_us, slow_timeout_ms,
+					 NULL)) {
 		DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n",
 			  val, mbox, __builtin_return_address(0));
 		return -ETIMEDOUT;
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 2e32615eeada..e9feffdea899 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -56,14 +56,6 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-static bool is_edp_psr(struct intel_dp *intel_dp)
-{
-	if (!intel_dp_is_edp(intel_dp))
-		return false;
-
-	return intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED;
-}
-
 static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -358,10 +350,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 		&crtc_state->base.adjusted_mode;
 	int psr_setup_time;
 
-	if (!HAS_PSR(dev_priv))
-		return;
-
-	if (!is_edp_psr(intel_dp))
+	if (!CAN_PSR(dev_priv))
 		return;
 
 	if (!i915_modparams.enable_psr) {
@@ -476,7 +465,7 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 			chicken |= PSR2_ADD_VERTICAL_LINE_COUNT;
 		I915_WRITE(CHICKEN_TRANS(cpu_transcoder), chicken);
 
-		I915_WRITE(EDP_PSR_DEBUG_CTL,
+		I915_WRITE(EDP_PSR_DEBUG,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
 			   EDP_PSR_DEBUG_MASK_LPSP |
@@ -490,7 +479,7 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 		 * preventing  other hw tracking issues now we can rely
 		 * on frontbuffer tracking.
 		 */
-		I915_WRITE(EDP_PSR_DEBUG_CTL,
+		I915_WRITE(EDP_PSR_DEBUG,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
 			   EDP_PSR_DEBUG_MASK_LPSP);
@@ -514,6 +503,9 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	if (!crtc_state->has_psr)
 		return;
 
+	if (WARN_ON(!CAN_PSR(dev_priv)))
+		return;
+
 	WARN_ON(dev_priv->drrs.dp);
 	mutex_lock(&dev_priv->psr.lock);
 	if (dev_priv->psr.enabled) {
@@ -522,8 +514,6 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	}
 
 	dev_priv->psr.psr2_support = crtc_state->has_psr2;
-	dev_priv->psr.source_ok = true;
-
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 
 	dev_priv->psr.setup_vsc(intel_dp, crtc_state);
@@ -599,7 +589,7 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 					0);
 
 		if (dev_priv->psr.psr2_support) {
-			psr_status = EDP_PSR2_STATUS_CTL;
+			psr_status = EDP_PSR2_STATUS;
 			psr_status_mask = EDP_PSR2_STATUS_STATE_MASK;
 
 			I915_WRITE(EDP_PSR2_CTL,
@@ -607,7 +597,7 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 				   ~(EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE));
 
 		} else {
-			psr_status = EDP_PSR_STATUS_CTL;
+			psr_status = EDP_PSR_STATUS;
 			psr_status_mask = EDP_PSR_STATUS_STATE_MASK;
 
 			I915_WRITE(EDP_PSR_CTL,
@@ -646,6 +636,9 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 	if (!old_crtc_state->has_psr)
 		return;
 
+	if (WARN_ON(!CAN_PSR(dev_priv)))
+		return;
+
 	mutex_lock(&dev_priv->psr.lock);
 	if (!dev_priv->psr.enabled) {
 		mutex_unlock(&dev_priv->psr.lock);
@@ -679,19 +672,19 @@ static void intel_psr_work(struct work_struct *work)
 	if (HAS_DDI(dev_priv)) {
 		if (dev_priv->psr.psr2_support) {
 			if (intel_wait_for_register(dev_priv,
-						EDP_PSR2_STATUS_CTL,
-						EDP_PSR2_STATUS_STATE_MASK,
-						0,
-						50)) {
+						    EDP_PSR2_STATUS,
+						    EDP_PSR2_STATUS_STATE_MASK,
+						    0,
+						    50)) {
 				DRM_ERROR("Timed out waiting for PSR2 Idle for re-enable\n");
 				return;
 			}
 		} else {
 			if (intel_wait_for_register(dev_priv,
-						EDP_PSR_STATUS_CTL,
-						EDP_PSR_STATUS_STATE_MASK,
-						0,
-						50)) {
+						    EDP_PSR_STATUS,
+						    EDP_PSR_STATUS_STATE_MASK,
+						    0,
+						    50)) {
 				DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
 				return;
 			}
@@ -796,7 +789,7 @@ void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
 	enum pipe pipe;
 	u32 val;
 
-	if (!HAS_PSR(dev_priv))
+	if (!CAN_PSR(dev_priv))
 		return;
 
 	/*
@@ -845,7 +838,7 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
-	if (!HAS_PSR(dev_priv))
+	if (!CAN_PSR(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -885,7 +878,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
-	if (!HAS_PSR(dev_priv))
+	if (!CAN_PSR(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -926,6 +919,9 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
 		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
 
+	if (!dev_priv->psr.sink_support)
+		return;
+
 	/* Per platform default: all disabled. */
 	if (i915_modparams.enable_psr == -1)
 		i915_modparams.enable_psr = 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c5ff203e42d6..a0e7a6c2a57c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -366,20 +366,6 @@ struct intel_engine_cs {
 		 */
 #define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1)
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
-		/**
-		 * @busy_stats: Has enablement of engine stats tracking been
-		 * 		requested.
-		 */
-		bool busy_stats;
-		/**
-		 * @disable_busy_stats: Work item for busy stats disabling.
-		 *
-		 * Same as with @enable_busy_stats action, with the difference
-		 * that we delay it in case there are rapid enable-disable
-		 * actions, which can happen during tool startup (like perf
-		 * stat).
-		 */
-		struct delayed_work disable_busy_stats;
 	} pmu;
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d758da6156a8..70e659772a7a 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -94,6 +94,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "PORT_DDI_D_LANES";
 	case POWER_DOMAIN_PORT_DDI_E_LANES:
 		return "PORT_DDI_E_LANES";
+	case POWER_DOMAIN_PORT_DDI_F_LANES:
+		return "PORT_DDI_F_LANES";
 	case POWER_DOMAIN_PORT_DDI_A_IO:
 		return "PORT_DDI_A_IO";
 	case POWER_DOMAIN_PORT_DDI_B_IO:
@@ -104,6 +106,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "PORT_DDI_D_IO";
 	case POWER_DOMAIN_PORT_DDI_E_IO:
 		return "PORT_DDI_E_IO";
+	case POWER_DOMAIN_PORT_DDI_F_IO:
+		return "PORT_DDI_F_IO";
 	case POWER_DOMAIN_PORT_DSI:
 		return "PORT_DSI";
 	case POWER_DOMAIN_PORT_CRT:
@@ -124,6 +128,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
 		return "AUX_D";
+	case POWER_DOMAIN_AUX_F:
+		return "AUX_F";
 	case POWER_DOMAIN_GMBUS:
 		return "GMBUS";
 	case POWER_DOMAIN_INIT:
@@ -390,6 +396,15 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id), val | HSW_PWR_WELL_CTL_REQ(id));
 	hsw_wait_for_power_well_enable(dev_priv, power_well);
 
+	/* Display WA #1178: cnl */
+	if (IS_CANNONLAKE(dev_priv) &&
+	    (id == CNL_DISP_PW_AUX_B || id == CNL_DISP_PW_AUX_C ||
+	     id == CNL_DISP_PW_AUX_D || id == CNL_DISP_PW_AUX_F)) {
+		val = I915_READ(CNL_AUX_ANAOVRD1(id));
+		val |= CNL_AUX_ANAOVRD1_ENABLE | CNL_AUX_ANAOVRD1_LDO_BYPASS;
+		I915_WRITE(CNL_AUX_ANAOVRD1(id), val);
+	}
+
 	if (wait_fuses)
 		gen9_wait_for_power_well_fuses(dev_priv, pg);
 
@@ -1816,9 +1831,11 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |                       \
 	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
 	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
 	BIT_ULL(POWER_DOMAIN_VGA) |				\
 	BIT_ULL(POWER_DOMAIN_INIT))
@@ -1846,8 +1863,15 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 #define CNL_DISPLAY_AUX_D_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
+#define CNL_DISPLAY_AUX_F_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+#define CNL_DISPLAY_DDI_F_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO) |		\
+	BIT_ULL(POWER_DOMAIN_INIT))
 #define CNL_DISPLAY_DC_OFF_POWER_DOMAINS (		\
 	CNL_DISPLAY_POWERWELL_2_POWER_DOMAINS |		\
+	BIT_ULL(POWER_DOMAIN_GT_IRQ) |			\
 	BIT_ULL(POWER_DOMAIN_MODESET) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
@@ -2395,6 +2419,18 @@ static struct i915_power_well cnl_power_wells[] = {
 		.ops = &hsw_power_well_ops,
 		.id = SKL_DISP_PW_DDI_D,
 	},
+	{
+		.name = "DDI F IO power well",
+		.domains = CNL_DISPLAY_DDI_F_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = CNL_DISP_PW_DDI_F,
+	},
+	{
+		.name = "AUX F",
+		.domains = CNL_DISPLAY_AUX_F_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = CNL_DISP_PW_AUX_F,
+	},
 };
 
 static int
@@ -2510,6 +2546,16 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 		set_power_wells(power_domains, skl_power_wells);
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		set_power_wells(power_domains, cnl_power_wells);
+
+		/*
+		 * DDI and Aux IO are getting enabled for all ports
+		 * regardless the presence or use. So, in order to avoid
+		 * timeouts, lets remove them from the list
+		 * for the SKUs without port F.
+		 */
+		if (!IS_CNL_WITH_PORT_F(dev_priv))
+			power_domains->power_well_count -= 2;
+
 	} else if (IS_BROXTON(dev_priv)) {
 		set_power_wells(power_domains, bxt_power_wells);
 	} else if (IS_GEMINILAKE(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index cffa7a8b0f9c..3be22c0fcfb5 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -865,6 +865,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	struct drm_rect *src = &state->base.src;
 	struct drm_rect *dst = &state->base.dst;
 	struct drm_rect clip = {};
+	int max_stride = INTEL_GEN(dev_priv) >= 9 ? 32768 : 16384;
 	int hscale, vscale;
 	int max_scale, min_scale;
 	bool can_scale;
@@ -885,7 +886,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	}
 
 	/* FIXME check all gen limits */
-	if (fb->width < 3 || fb->height < 3 || fb->pitches[0] > 16384) {
+	if (fb->width < 3 || fb->height < 3 || fb->pitches[0] > max_stride) {
 		DRM_DEBUG_KMS("Unsuitable framebuffer for plane\n");
 		return -EINVAL;
 	}
@@ -893,7 +894,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	/* setup can_scale, min_scale, max_scale */
 	if (INTEL_GEN(dev_priv) >= 9) {
 		/* use scaler when colorkey is not required */
-		if (state->ckey.flags == I915_SET_COLORKEY_NONE) {
+		if (!state->ckey.flags) {
 			can_scale = 1;
 			min_scale = 1;
 			max_scale = skl_max_scale(crtc, crtc_state);
@@ -1031,7 +1032,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	dst->y2 = crtc_y + crtc_h;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		ret = skl_check_plane_surface(state);
+		ret = skl_check_plane_surface(crtc_state, state);
 		if (ret)
 			return ret;
 
@@ -1073,6 +1074,9 @@ int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 	struct drm_modeset_acquire_ctx ctx;
 	int ret = 0;
 
+	/* ignore the pointless "none" flag */
+	set->flags &= ~I915_SET_COLORKEY_NONE;
+
 	/* Make sure we don't try to enable both src & dest simultaneously */
 	if ((set->flags & (I915_SET_COLORKEY_DESTINATION | I915_SET_COLORKEY_SOURCE)) == (I915_SET_COLORKEY_DESTINATION | I915_SET_COLORKEY_SOURCE))
 		return -EINVAL;
@@ -1165,18 +1169,27 @@ static uint32_t skl_plane_formats[] = {
 	DRM_FORMAT_VYUY,
 };
 
-static const uint64_t skl_plane_format_modifiers[] = {
+static const uint64_t skl_plane_format_modifiers_noccs[] = {
+	I915_FORMAT_MOD_Yf_TILED,
+	I915_FORMAT_MOD_Y_TILED,
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
 	DRM_FORMAT_MOD_INVALID
 };
 
-static bool g4x_sprite_plane_format_mod_supported(struct drm_plane *plane,
-						  uint32_t format,
-						  uint64_t modifier)
+static const uint64_t skl_plane_format_modifiers_ccs[] = {
+	I915_FORMAT_MOD_Yf_TILED_CCS,
+	I915_FORMAT_MOD_Y_TILED_CCS,
+	I915_FORMAT_MOD_Yf_TILED,
+	I915_FORMAT_MOD_Y_TILED,
+	I915_FORMAT_MOD_X_TILED,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
+static bool g4x_mod_supported(uint32_t format, uint64_t modifier)
 {
 	switch (format) {
-	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
@@ -1191,22 +1204,38 @@ static bool g4x_sprite_plane_format_mod_supported(struct drm_plane *plane,
 	}
 }
 
-static bool vlv_sprite_plane_format_mod_supported(struct drm_plane *plane,
-						  uint32_t format,
-						  uint64_t modifier)
+static bool snb_mod_supported(uint32_t format, uint64_t modifier)
 {
 	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_VYUY:
+		if (modifier == DRM_FORMAT_MOD_LINEAR ||
+		    modifier == I915_FORMAT_MOD_X_TILED)
+			return true;
+		/* fall through */
+	default:
+		return false;
+	}
+}
+
+static bool vlv_mod_supported(uint32_t format, uint64_t modifier)
+{
+	switch (format) {
 	case DRM_FORMAT_RGB565:
-	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR2101010:
 	case DRM_FORMAT_ABGR2101010:
-	case DRM_FORMAT_XBGR8888:
-	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
 		if (modifier == DRM_FORMAT_MOD_LINEAR ||
 		    modifier == I915_FORMAT_MOD_X_TILED)
 			return true;
@@ -1216,16 +1245,17 @@ static bool vlv_sprite_plane_format_mod_supported(struct drm_plane *plane,
 	}
 }
 
-static bool skl_sprite_plane_format_mod_supported(struct drm_plane *plane,
-						  uint32_t format,
-						  uint64_t modifier)
+static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 {
-	/* This is the same as primary plane since SKL has universal planes */
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_ABGR8888:
+		if (modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+		    modifier == I915_FORMAT_MOD_Y_TILED_CCS)
+			return true;
+		/* fall through */
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
@@ -1261,13 +1291,13 @@ static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane,
 		return false;
 
 	if (INTEL_GEN(dev_priv) >= 9)
-		return skl_sprite_plane_format_mod_supported(plane, format, modifier);
+		return skl_mod_supported(format, modifier);
 	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_sprite_plane_format_mod_supported(plane, format, modifier);
+		return vlv_mod_supported(format, modifier);
+	else if (INTEL_GEN(dev_priv) >= 6)
+		return snb_mod_supported(format, modifier);
 	else
-		return g4x_sprite_plane_format_mod_supported(plane, format, modifier);
-
-	unreachable();
+		return g4x_mod_supported(format, modifier);
 }
 
 static const struct drm_plane_funcs intel_sprite_plane_funcs = {
@@ -1281,6 +1311,23 @@ static const struct drm_plane_funcs intel_sprite_plane_funcs = {
         .format_mod_supported = intel_sprite_plane_format_mod_supported,
 };
 
+bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
+		       enum pipe pipe, enum plane_id plane_id)
+{
+	if (plane_id == PLANE_CURSOR)
+		return false;
+
+	if (INTEL_GEN(dev_priv) >= 10)
+		return true;
+
+	if (IS_GEMINILAKE(dev_priv))
+		return pipe != PIPE_C;
+
+	return pipe != PIPE_C &&
+		(plane_id == PLANE_PRIMARY ||
+		 plane_id == PLANE_SPRITE0);
+}
+
 struct intel_plane *
 intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, int plane)
@@ -1307,7 +1354,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 	}
 	intel_plane->base.state = &state->base;
 
-	if (INTEL_GEN(dev_priv) >= 10) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		intel_plane->can_scale = true;
 		state->scaler_id = -1;
 
@@ -1317,18 +1364,11 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 
 		plane_formats = skl_plane_formats;
 		num_plane_formats = ARRAY_SIZE(skl_plane_formats);
-		modifiers = skl_plane_format_modifiers;
-	} else if (INTEL_GEN(dev_priv) >= 9) {
-		intel_plane->can_scale = true;
-		state->scaler_id = -1;
 
-		intel_plane->update_plane = skl_update_plane;
-		intel_plane->disable_plane = skl_disable_plane;
-		intel_plane->get_hw_state = skl_plane_get_hw_state;
-
-		plane_formats = skl_plane_formats;
-		num_plane_formats = ARRAY_SIZE(skl_plane_formats);
-		modifiers = skl_plane_format_modifiers;
+		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_SPRITE0 + plane))
+			modifiers = skl_plane_format_modifiers_ccs;
+		else
+			modifiers = skl_plane_format_modifiers_noccs;
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		intel_plane->can_scale = false;
 		intel_plane->max_downscale = 1;
@@ -1390,7 +1430,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 	intel_plane->pipe = pipe;
 	intel_plane->i9xx_plane = plane;
 	intel_plane->id = PLANE_SPRITE0 + plane;
-	intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe, plane);
+	intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER(pipe, intel_plane->id);
 	intel_plane->check_plane = intel_check_sprite_plane;
 
 	possible_crtcs = (1 << pipe);
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 907deac6e3fa..9f1bac6398fb 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -27,6 +27,8 @@
 #include "intel_guc.h"
 #include "i915_drv.h"
 
+static void guc_free_load_err_log(struct intel_guc *guc);
+
 /* Reset GuC providing us with fresh state for both GuC and HuC.
  */
 static int __intel_uc_reset_hw(struct drm_i915_private *dev_priv)
@@ -65,6 +67,21 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
 	return enable_guc;
 }
 
+static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
+{
+	int guc_log_level = 0; /* disabled */
+
+	/* Enable if we're running on platform with GuC and debug config */
+	if (HAS_GUC(dev_priv) && intel_uc_is_using_guc() &&
+	    (IS_ENABLED(CONFIG_DRM_I915_DEBUG) ||
+	     IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)))
+		guc_log_level = 1 + GUC_LOG_VERBOSITY_MAX;
+
+	/* Any platform specific fine-tuning can be done here */
+
+	return guc_log_level;
+}
+
 /**
  * intel_uc_sanitize_options - sanitize uC related modparam options
  * @dev_priv: device private
@@ -74,6 +91,13 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
  * modparam varies between platforms and it is hardcoded in driver code.
  * Any other modparam value is only monitored against availability of the
  * related hardware or firmware definitions.
+ *
+ * In case of "guc_log_level" option this function will attempt to modify
+ * it only if it was initially set to "auto(-1)" or if initial value was
+ * "enable(1..4)" on platforms without the GuC. Default value for this
+ * modparam varies between platforms and is usually set to "disable(0)"
+ * unless GuC is enabled on given platform and the driver is compiled with
+ * debug config when this modparam will default to "enable(1..4)".
  */
 void intel_uc_sanitize_options(struct drm_i915_private *dev_priv)
 {
@@ -91,22 +115,48 @@ void intel_uc_sanitize_options(struct drm_i915_private *dev_priv)
 
 	/* Verify GuC firmware availability */
 	if (intel_uc_is_using_guc() && !intel_uc_fw_is_selected(guc_fw)) {
-		DRM_WARN("Incompatible option detected: enable_guc=%d, %s!\n",
-			 i915_modparams.enable_guc,
+		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
+			 "enable_guc", i915_modparams.enable_guc,
 			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
 					      "no GuC firmware");
 	}
 
 	/* Verify HuC firmware availability */
 	if (intel_uc_is_using_huc() && !intel_uc_fw_is_selected(huc_fw)) {
-		DRM_WARN("Incompatible option detected: enable_guc=%d, %s!\n",
-			 i915_modparams.enable_guc,
+		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
+			 "enable_guc", i915_modparams.enable_guc,
 			 !HAS_HUC(dev_priv) ? "no HuC hardware" :
 					      "no HuC firmware");
 	}
 
+	/* A negative value means "use platform/config default" */
+	if (i915_modparams.guc_log_level < 0)
+		i915_modparams.guc_log_level =
+			__get_default_guc_log_level(dev_priv);
+
+	if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc()) {
+		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
+			 "guc_log_level", i915_modparams.guc_log_level,
+			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
+					      "GuC not enabled");
+		i915_modparams.guc_log_level = 0;
+	}
+
+	if (i915_modparams.guc_log_level > 1 + GUC_LOG_VERBOSITY_MAX) {
+		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
+			 "guc_log_level", i915_modparams.guc_log_level,
+			 "verbosity too high");
+		i915_modparams.guc_log_level = 1 + GUC_LOG_VERBOSITY_MAX;
+	}
+
+	DRM_DEBUG_DRIVER("guc_log_level=%d (enabled:%s verbosity:%d)\n",
+			 i915_modparams.guc_log_level,
+			 yesno(i915_modparams.guc_log_level),
+			 i915_modparams.guc_log_level - 1);
+
 	/* Make sure that sanitization was done */
 	GEM_BUG_ON(i915_modparams.enable_guc < 0);
+	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
 }
 
 void intel_uc_init_early(struct drm_i915_private *dev_priv)
@@ -135,6 +185,8 @@ void intel_uc_fini_fw(struct drm_i915_private *dev_priv)
 
 	if (USES_HUC(dev_priv))
 		intel_uc_fw_fini(&dev_priv->huc.fw);
+
+	guc_free_load_err_log(&dev_priv->guc);
 }
 
 /**
@@ -152,7 +204,7 @@ void intel_uc_init_mmio(struct drm_i915_private *dev_priv)
 
 static void guc_capture_load_err_log(struct intel_guc *guc)
 {
-	if (!guc->log.vma || i915_modparams.guc_log_level < 0)
+	if (!guc->log.vma || !i915_modparams.guc_log_level)
 		return;
 
 	if (!guc->load_err_log)
@@ -188,30 +240,44 @@ static void guc_disable_communication(struct intel_guc *guc)
 	guc->send = intel_guc_send_nop;
 }
 
-int intel_uc_init_wq(struct drm_i915_private *dev_priv)
+int intel_uc_init_misc(struct drm_i915_private *dev_priv)
 {
+	struct intel_guc *guc = &dev_priv->guc;
 	int ret;
 
 	if (!USES_GUC(dev_priv))
 		return 0;
 
-	ret = intel_guc_init_wq(&dev_priv->guc);
+	ret = intel_guc_init_wq(guc);
 	if (ret) {
 		DRM_ERROR("Couldn't allocate workqueues for GuC\n");
-		return ret;
+		goto err;
+	}
+
+	ret = intel_guc_log_relay_create(guc);
+	if (ret) {
+		DRM_ERROR("Couldn't allocate relay for GuC log\n");
+		goto err_relay;
 	}
 
 	return 0;
+
+err_relay:
+	intel_guc_fini_wq(guc);
+err:
+	return ret;
 }
 
-void intel_uc_fini_wq(struct drm_i915_private *dev_priv)
+void intel_uc_fini_misc(struct drm_i915_private *dev_priv)
 {
+	struct intel_guc *guc = &dev_priv->guc;
+
 	if (!USES_GUC(dev_priv))
 		return;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	intel_guc_fini_wq(guc);
 
-	intel_guc_fini_wq(&dev_priv->guc);
+	intel_guc_log_relay_destroy(guc);
 }
 
 int intel_uc_init(struct drm_i915_private *dev_priv)
@@ -324,7 +390,7 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	}
 
 	if (USES_GUC_SUBMISSION(dev_priv)) {
-		if (i915_modparams.guc_log_level >= 0)
+		if (i915_modparams.guc_log_level)
 			gen9_enable_guc_interrupts(dev_priv);
 
 		ret = intel_guc_submission_enable(guc);
@@ -366,8 +432,6 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 
-	guc_free_load_err_log(guc);
-
 	if (!USES_GUC(dev_priv))
 		return;
 
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index 8a7249722ef1..f2984e01e257 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -33,8 +33,8 @@ void intel_uc_init_early(struct drm_i915_private *dev_priv);
 void intel_uc_init_mmio(struct drm_i915_private *dev_priv);
 void intel_uc_init_fw(struct drm_i915_private *dev_priv);
 void intel_uc_fini_fw(struct drm_i915_private *dev_priv);
-int intel_uc_init_wq(struct drm_i915_private *dev_priv);
-void intel_uc_fini_wq(struct drm_i915_private *dev_priv);
+int intel_uc_init_misc(struct drm_i915_private *dev_priv);
+void intel_uc_fini_misc(struct drm_i915_private *dev_priv);
 int intel_uc_init_hw(struct drm_i915_private *dev_priv);
 void intel_uc_fini_hw(struct drm_i915_private *dev_priv);
 int intel_uc_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 89547b614aa6..164dbb8cfa36 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1452,7 +1452,7 @@ static const struct reg_whitelist {
 } reg_read_whitelist[] = { {
 	.offset_ldw = RING_TIMESTAMP(RENDER_RING_BASE),
 	.offset_udw = RING_TIMESTAMP_UDW(RENDER_RING_BASE),
-	.gen_mask = INTEL_GEN_MASK(4, 10),
+	.gen_mask = INTEL_GEN_MASK(4, 11),
 	.size = 8
 } };
 
@@ -1767,12 +1767,14 @@ int __intel_wait_for_register_fw(struct drm_i915_private *dev_priv,
 }
 
 /**
- * intel_wait_for_register - wait until register matches expected state
+ * __intel_wait_for_register - wait until register matches expected state
  * @dev_priv: the i915 device
  * @reg: the register to read
  * @mask: mask to apply to register value
  * @value: expected value
- * @timeout_ms: timeout in millisecond
+ * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait
+ * @slow_timeout_ms: slow timeout in millisecond
+ * @out_value: optional placeholder to hold registry value
  *
  * This routine waits until the target register @reg contains the expected
  * @value after applying the @mask, i.e. it waits until ::
@@ -1783,14 +1785,17 @@ int __intel_wait_for_register_fw(struct drm_i915_private *dev_priv,
  *
  * Returns 0 if the register matches the desired condition, or -ETIMEOUT.
  */
-int intel_wait_for_register(struct drm_i915_private *dev_priv,
+int __intel_wait_for_register(struct drm_i915_private *dev_priv,
 			    i915_reg_t reg,
 			    u32 mask,
 			    u32 value,
-			    unsigned int timeout_ms)
+			    unsigned int fast_timeout_us,
+			    unsigned int slow_timeout_ms,
+			    u32 *out_value)
 {
 	unsigned fw =
 		intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+	u32 reg_value;
 	int ret;
 
 	might_sleep();
@@ -1800,14 +1805,18 @@ int intel_wait_for_register(struct drm_i915_private *dev_priv,
 
 	ret = __intel_wait_for_register_fw(dev_priv,
 					   reg, mask, value,
-					   2, 0, NULL);
+					   fast_timeout_us, 0, &reg_value);
 
 	intel_uncore_forcewake_put__locked(dev_priv, fw);
 	spin_unlock_irq(&dev_priv->uncore.lock);
 
 	if (ret)
-		ret = wait_for((I915_READ_NOTRACE(reg) & mask) == value,
-			       timeout_ms);
+		ret = __wait_for(reg_value = I915_READ_NOTRACE(reg),
+				 (reg_value & mask) == value,
+				 slow_timeout_ms * 1000, 10, 1000);
+
+	if (out_value)
+		*out_value = reg_value;
 
 	return ret;
 }
@@ -1936,8 +1945,7 @@ int intel_reset_guc(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	if (!HAS_GUC(dev_priv))
-		return -EINVAL;
+	GEM_BUG_ON(!HAS_GUC(dev_priv));
 
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 	ret = gen6_hw_domain_reset(dev_priv, GEN9_GRDOM_GUC);
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 9ce079b5dd0d..bed019ef000f 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -163,11 +163,23 @@ void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv,
 void intel_uncore_forcewake_user_get(struct drm_i915_private *dev_priv);
 void intel_uncore_forcewake_user_put(struct drm_i915_private *dev_priv);
 
+int __intel_wait_for_register(struct drm_i915_private *dev_priv,
+			      i915_reg_t reg,
+			      u32 mask,
+			      u32 value,
+			      unsigned int fast_timeout_us,
+			      unsigned int slow_timeout_ms,
+			      u32 *out_value);
+static inline
 int intel_wait_for_register(struct drm_i915_private *dev_priv,
 			    i915_reg_t reg,
 			    u32 mask,
 			    u32 value,
-			    unsigned int timeout_ms);
+			    unsigned int timeout_ms)
+{
+	return __intel_wait_for_register(dev_priv, reg, mask, value, 2,
+					 timeout_ms, NULL);
+}
 int __intel_wait_for_register_fw(struct drm_i915_private *dev_priv,
 				 i915_reg_t reg,
 				 u32 mask,
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index e3d7745a9151..458468237b5f 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -227,7 +227,7 @@ struct bdb_general_features {
 #define DEVICE_TYPE_COMPOSITE_OUTPUT	(1 << 9)
 #define DEVICE_TYPE_DUAL_CHANNEL	(1 << 8)
 #define DEVICE_TYPE_HIGH_SPEED_LINK	(1 << 6)
-#define DEVICE_TYPE_LVDS_SINGALING	(1 << 5)
+#define DEVICE_TYPE_LVDS_SIGNALING	(1 << 5)
 #define DEVICE_TYPE_TMDS_DVI_SIGNALING	(1 << 4)
 #define DEVICE_TYPE_VIDEO_SIGNALING	(1 << 3)
 #define DEVICE_TYPE_DISPLAYPORT_OUTPUT	(1 << 2)
@@ -243,7 +243,7 @@ struct bdb_general_features {
 	 DEVICE_TYPE_MIPI_OUTPUT |		\
 	 DEVICE_TYPE_COMPOSITE_OUTPUT |		\
 	 DEVICE_TYPE_DUAL_CHANNEL |		\
-	 DEVICE_TYPE_LVDS_SINGALING |		\
+	 DEVICE_TYPE_LVDS_SIGNALING |		\
 	 DEVICE_TYPE_TMDS_DVI_SIGNALING |	\
 	 DEVICE_TYPE_VIDEO_SIGNALING |		\
 	 DEVICE_TYPE_DISPLAYPORT_OUTPUT |	\
@@ -253,7 +253,7 @@ struct bdb_general_features {
 	(DEVICE_TYPE_INTERNAL_CONNECTOR |	\
 	 DEVICE_TYPE_MIPI_OUTPUT |		\
 	 DEVICE_TYPE_COMPOSITE_OUTPUT |		\
-	 DEVICE_TYPE_LVDS_SINGALING |		\
+	 DEVICE_TYPE_LVDS_SIGNALING |		\
 	 DEVICE_TYPE_TMDS_DVI_SIGNALING |	\
 	 DEVICE_TYPE_VIDEO_SIGNALING |		\
 	 DEVICE_TYPE_DISPLAYPORT_OUTPUT |	\
@@ -299,6 +299,8 @@ struct bdb_general_features {
 #define DVO_PORT_DPA		10
 #define DVO_PORT_DPE		11				/* 193 */
 #define DVO_PORT_HDMIE		12				/* 193 */
+#define DVO_PORT_DPF		13				/* N/A */
+#define DVO_PORT_HDMIF		14				/* N/A */
 #define DVO_PORT_MIPIA		21				/* 171 */
 #define DVO_PORT_MIPIB		22				/* 171 */
 #define DVO_PORT_MIPIC		23				/* 171 */
@@ -318,6 +320,11 @@ enum vbt_gmbus_ddi {
 	DDC_BUS_DDI_F,
 };
 
+#define VBT_DP_MAX_LINK_RATE_HBR3	0
+#define VBT_DP_MAX_LINK_RATE_HBR2	1
+#define VBT_DP_MAX_LINK_RATE_HBR	2
+#define VBT_DP_MAX_LINK_RATE_LBR	3
+
 /*
  * The child device config, aka the display device data structure, provides a
  * description of a port and its configuration on the platform.
@@ -412,6 +419,8 @@ struct child_device_config {
 	u16 dp_gpio_pin_num;					/* 195 */
 	u8 dp_iboost_level:4;					/* 196 */
 	u8 hdmi_iboost_level:4;					/* 196 */
+	u8 dp_max_link_rate:2;					/* 216 CNL+ */
+	u8 dp_max_link_rate_reserved:6;				/* 216 */
 } __packed;
 
 struct bdb_general_definitions {
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 4a28d713a7d8..d8064276431c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -885,6 +885,84 @@ static int shrink_hole(struct drm_i915_private *i915,
 	return err;
 }
 
+static int shrink_boom(struct drm_i915_private *i915,
+		       struct i915_address_space *vm,
+		       u64 hole_start, u64 hole_end,
+		       unsigned long end_time)
+{
+	unsigned int sizes[] = { SZ_2M, SZ_1G };
+	struct drm_i915_gem_object *purge;
+	struct drm_i915_gem_object *explode;
+	int err;
+	int i;
+
+	/*
+	 * Catch the case which shrink_hole seems to miss. The setup here
+	 * requires invoking the shrinker as we do the alloc_pt/alloc_pd, while
+	 * ensuring that all vma assiocated with the respective pd/pdp are
+	 * unpinned at the time.
+	 */
+
+	for (i = 0; i < ARRAY_SIZE(sizes); ++i) {
+		unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
+		unsigned int size = sizes[i];
+		struct i915_vma *vma;
+
+		purge = fake_dma_object(i915, size);
+		if (IS_ERR(purge))
+			return PTR_ERR(purge);
+
+		vma = i915_vma_instance(purge, vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto err_purge;
+		}
+
+		err = i915_vma_pin(vma, 0, 0, flags);
+		if (err)
+			goto err_purge;
+
+		/* Should now be ripe for purging */
+		i915_vma_unpin(vma);
+
+		explode = fake_dma_object(i915, size);
+		if (IS_ERR(explode)) {
+			err = PTR_ERR(purge);
+			goto err_purge;
+		}
+
+		vm->fault_attr.probability = 100;
+		vm->fault_attr.interval = 1;
+		atomic_set(&vm->fault_attr.times, -1);
+
+		vma = i915_vma_instance(explode, vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto err_explode;
+		}
+
+		err = i915_vma_pin(vma, 0, 0, flags | size);
+		if (err)
+			goto err_explode;
+
+		i915_vma_unpin(vma);
+
+		i915_gem_object_put(purge);
+		i915_gem_object_put(explode);
+
+		memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
+	}
+
+	return 0;
+
+err_explode:
+	i915_gem_object_put(explode);
+err_purge:
+	i915_gem_object_put(purge);
+	memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
+	return err;
+}
+
 static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 			  int (*func)(struct drm_i915_private *i915,
 				      struct i915_address_space *vm,
@@ -953,6 +1031,11 @@ static int igt_ppgtt_shrink(void *arg)
 	return exercise_ppgtt(arg, shrink_hole);
 }
 
+static int igt_ppgtt_shrink_boom(void *arg)
+{
+	return exercise_ppgtt(arg, shrink_boom);
+}
+
 static int sort_holes(void *priv, struct list_head *A, struct list_head *B)
 {
 	struct drm_mm_node *a = list_entry(A, typeof(*a), hole_stack);
@@ -1052,35 +1135,38 @@ static int igt_ggtt_page(void *arg)
 
 	memset(&tmp, 0, sizeof(tmp));
 	err = drm_mm_insert_node_in_range(&ggtt->base.mm, &tmp,
-					  1024 * PAGE_SIZE, 0,
+					  count * PAGE_SIZE, 0,
 					  I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
 					  DRM_MM_INSERT_LOW);
 	if (err)
 		goto out_unpin;
 
+	intel_runtime_pm_get(i915);
+
+	for (n = 0; n < count; n++) {
+		u64 offset = tmp.start + n * PAGE_SIZE;
+
+		ggtt->base.insert_page(&ggtt->base,
+				       i915_gem_object_get_dma_address(obj, 0),
+				       offset, I915_CACHE_NONE, 0);
+	}
+
 	order = i915_random_order(count, &prng);
 	if (!order) {
 		err = -ENOMEM;
 		goto out_remove;
 	}
 
-	intel_runtime_pm_get(i915);
 	for (n = 0; n < count; n++) {
 		u64 offset = tmp.start + order[n] * PAGE_SIZE;
 		u32 __iomem *vaddr;
 
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, 0),
-				       offset, I915_CACHE_NONE, 0);
-
 		vaddr = io_mapping_map_atomic_wc(&ggtt->iomap, offset);
 		iowrite32(n, vaddr + n);
 		io_mapping_unmap_atomic(vaddr);
-
-		wmb();
-		ggtt->base.clear_range(&ggtt->base, offset, PAGE_SIZE);
 	}
+	i915_gem_flush_ggtt_writes(i915);
 
 	i915_random_reorder(order, count, &prng);
 	for (n = 0; n < count; n++) {
@@ -1088,16 +1174,10 @@ static int igt_ggtt_page(void *arg)
 		u32 __iomem *vaddr;
 		u32 val;
 
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, 0),
-				       offset, I915_CACHE_NONE, 0);
-
 		vaddr = io_mapping_map_atomic_wc(&ggtt->iomap, offset);
 		val = ioread32(vaddr + n);
 		io_mapping_unmap_atomic(vaddr);
 
-		ggtt->base.clear_range(&ggtt->base, offset, PAGE_SIZE);
-
 		if (val != n) {
 			pr_err("insert page failed: found %d, expected %d\n",
 			       val, n);
@@ -1105,10 +1185,11 @@ static int igt_ggtt_page(void *arg)
 			break;
 		}
 	}
-	intel_runtime_pm_put(i915);
 
 	kfree(order);
 out_remove:
+	ggtt->base.clear_range(&ggtt->base, tmp.start, tmp.size);
+	intel_runtime_pm_put(i915);
 	drm_mm_remove_node(&tmp);
 out_unpin:
 	i915_gem_object_unpin_pages(obj);
@@ -1579,6 +1660,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_pot),
 		SUBTEST(igt_ppgtt_fill),
 		SUBTEST(igt_ppgtt_shrink),
+		SUBTEST(igt_ppgtt_shrink_boom),
 		SUBTEST(igt_ggtt_lowlevel),
 		SUBTEST(igt_ggtt_drunk),
 		SUBTEST(igt_ggtt_walk),
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
index 2088ae57aa89..1f415ce47018 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.c
+++ b/drivers/gpu/drm/i915/selftests/i915_random.c
@@ -57,7 +57,8 @@ unsigned int *i915_random_order(unsigned int count, struct rnd_state *state)
 {
 	unsigned int *order, i;
 
-	order = kmalloc_array(count, sizeof(*order), GFP_KERNEL | __GFP_NOWARN);
+	order = kmalloc_array(count, sizeof(*order),
+			      GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (!order)
 		return order;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c
index ea01d0fe3ace..570e325af93e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c
@@ -606,6 +606,139 @@ err:
 	return -EINVAL;
 }
 
+static const char *mock_name(struct dma_fence *fence)
+{
+	return "mock";
+}
+
+static bool mock_enable_signaling(struct dma_fence *fence)
+{
+	return true;
+}
+
+static const struct dma_fence_ops mock_fence_ops = {
+	.get_driver_name = mock_name,
+	.get_timeline_name = mock_name,
+	.enable_signaling = mock_enable_signaling,
+	.wait = dma_fence_default_wait,
+	.release = dma_fence_free,
+};
+
+static DEFINE_SPINLOCK(mock_fence_lock);
+
+static struct dma_fence *alloc_dma_fence(void)
+{
+	struct dma_fence *dma;
+
+	dma = kmalloc(sizeof(*dma), GFP_KERNEL);
+	if (dma)
+		dma_fence_init(dma, &mock_fence_ops, &mock_fence_lock, 0, 0);
+
+	return dma;
+}
+
+static struct i915_sw_fence *
+wrap_dma_fence(struct dma_fence *dma, unsigned long delay)
+{
+	struct i915_sw_fence *fence;
+	int err;
+
+	fence = alloc_fence();
+	if (!fence)
+		return ERR_PTR(-ENOMEM);
+
+	err = i915_sw_fence_await_dma_fence(fence, dma, delay, GFP_NOWAIT);
+	i915_sw_fence_commit(fence);
+	if (err < 0) {
+		free_fence(fence);
+		return ERR_PTR(err);
+	}
+
+	return fence;
+}
+
+static int test_dma_fence(void *arg)
+{
+	struct i915_sw_fence *timeout = NULL, *not = NULL;
+	unsigned long delay = i915_selftest.timeout_jiffies;
+	unsigned long end, sleep;
+	struct dma_fence *dma;
+	int err;
+
+	dma = alloc_dma_fence();
+	if (!dma)
+		return -ENOMEM;
+
+	timeout = wrap_dma_fence(dma, delay);
+	if (IS_ERR(timeout)) {
+		err = PTR_ERR(timeout);
+		goto err;
+	}
+
+	not = wrap_dma_fence(dma, 0);
+	if (IS_ERR(not)) {
+		err = PTR_ERR(not);
+		goto err;
+	}
+
+	err = -EINVAL;
+	if (i915_sw_fence_done(timeout) || i915_sw_fence_done(not)) {
+		pr_err("Fences immediately signaled\n");
+		goto err;
+	}
+
+	/* We round the timeout for the fence up to the next second */
+	end = round_jiffies_up(jiffies + delay);
+
+	sleep = jiffies_to_usecs(delay) / 3;
+	usleep_range(sleep, 2 * sleep);
+	if (time_after(jiffies, end)) {
+		pr_debug("Slept too long, delay=%lu, (target=%lu, now=%lu) skipping\n",
+			 delay, end, jiffies);
+		goto skip;
+	}
+
+	if (i915_sw_fence_done(timeout) || i915_sw_fence_done(not)) {
+		pr_err("Fences signaled too early\n");
+		goto err;
+	}
+
+	if (!wait_event_timeout(timeout->wait,
+				i915_sw_fence_done(timeout),
+				2 * (end - jiffies) + 1)) {
+		pr_err("Timeout fence unsignaled!\n");
+		goto err;
+	}
+
+	if (i915_sw_fence_done(not)) {
+		pr_err("No timeout fence signaled!\n");
+		goto err;
+	}
+
+skip:
+	dma_fence_signal(dma);
+
+	if (!i915_sw_fence_done(timeout) || !i915_sw_fence_done(not)) {
+		pr_err("Fences unsignaled\n");
+		goto err;
+	}
+
+	free_fence(not);
+	free_fence(timeout);
+	dma_fence_put(dma);
+
+	return 0;
+
+err:
+	dma_fence_signal(dma);
+	if (!IS_ERR_OR_NULL(timeout))
+		free_fence(timeout);
+	if (!IS_ERR_OR_NULL(not))
+		free_fence(not);
+	dma_fence_put(dma);
+	return err;
+}
+
 int i915_sw_fence_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
@@ -618,6 +751,7 @@ int i915_sw_fence_mock_selftests(void)
 		SUBTEST(test_chain),
 		SUBTEST(test_ipc),
 		SUBTEST(test_timer),
+		SUBTEST(test_dma_fence),
 	};
 
 	return i915_subtests(tests, NULL);
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index d1f91a533afa..d1d2c2456f69 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -33,6 +33,7 @@ struct hang {
 	struct drm_i915_private *i915;
 	struct drm_i915_gem_object *hws;
 	struct drm_i915_gem_object *obj;
+	struct i915_gem_context *ctx;
 	u32 *seqno;
 	u32 *batch;
 };
@@ -45,9 +46,15 @@ static int hang_init(struct hang *h, struct drm_i915_private *i915)
 	memset(h, 0, sizeof(*h));
 	h->i915 = i915;
 
+	h->ctx = kernel_context(i915);
+	if (IS_ERR(h->ctx))
+		return PTR_ERR(h->ctx);
+
 	h->hws = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(h->hws))
-		return PTR_ERR(h->hws);
+	if (IS_ERR(h->hws)) {
+		err = PTR_ERR(h->hws);
+		goto err_ctx;
+	}
 
 	h->obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(h->obj)) {
@@ -79,6 +86,8 @@ err_obj:
 	i915_gem_object_put(h->obj);
 err_hws:
 	i915_gem_object_put(h->hws);
+err_ctx:
+	kernel_context_close(h->ctx);
 	return err;
 }
 
@@ -196,9 +205,7 @@ unpin_vma:
 }
 
 static struct drm_i915_gem_request *
-hang_create_request(struct hang *h,
-		    struct intel_engine_cs *engine,
-		    struct i915_gem_context *ctx)
+hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *rq;
 	int err;
@@ -225,7 +232,7 @@ hang_create_request(struct hang *h,
 		h->batch = vaddr;
 	}
 
-	rq = i915_gem_request_alloc(engine, ctx);
+	rq = i915_gem_request_alloc(engine, h->ctx);
 	if (IS_ERR(rq))
 		return rq;
 
@@ -244,6 +251,58 @@ static u32 hws_seqno(const struct hang *h,
 	return READ_ONCE(h->seqno[rq->fence.context % (PAGE_SIZE/sizeof(u32))]);
 }
 
+struct wedge_me {
+	struct delayed_work work;
+	struct drm_i915_private *i915;
+	const void *symbol;
+};
+
+static void wedge_me(struct work_struct *work)
+{
+	struct wedge_me *w = container_of(work, typeof(*w), work.work);
+
+	pr_err("%pS timed out, cancelling all further testing.\n",
+	       w->symbol);
+	i915_gem_set_wedged(w->i915);
+}
+
+static void __init_wedge(struct wedge_me *w,
+			 struct drm_i915_private *i915,
+			 long timeout,
+			 const void *symbol)
+{
+	w->i915 = i915;
+	w->symbol = symbol;
+
+	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
+	schedule_delayed_work(&w->work, timeout);
+}
+
+static void __fini_wedge(struct wedge_me *w)
+{
+	cancel_delayed_work_sync(&w->work);
+	destroy_delayed_work_on_stack(&w->work);
+	w->i915 = NULL;
+}
+
+#define wedge_on_timeout(W, DEV, TIMEOUT)				\
+	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
+	     (W)->i915;							\
+	     __fini_wedge((W)))
+
+static noinline int
+flush_test(struct drm_i915_private *i915, unsigned int flags)
+{
+	struct wedge_me w;
+
+	cond_resched();
+
+	wedge_on_timeout(&w, i915, HZ)
+		i915_gem_wait_for_idle(i915, flags);
+
+	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
+}
+
 static void hang_fini(struct hang *h)
 {
 	*h->batch = MI_BATCH_BUFFER_END;
@@ -255,7 +314,9 @@ static void hang_fini(struct hang *h)
 	i915_gem_object_unpin_map(h->hws);
 	i915_gem_object_put(h->hws);
 
-	i915_gem_wait_for_idle(h->i915, I915_WAIT_LOCKED);
+	kernel_context_close(h->ctx);
+
+	flush_test(h->i915, I915_WAIT_LOCKED);
 }
 
 static bool wait_for_hang(struct hang *h, struct drm_i915_gem_request *rq)
@@ -290,7 +351,7 @@ static int igt_hang_sanitycheck(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		rq = hang_create_request(&h, engine, i915->kernel_context);
+		rq = hang_create_request(&h, engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			pr_err("Failed to create request for %s, err=%d\n",
@@ -427,8 +488,7 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				struct drm_i915_gem_request *rq;
 
 				mutex_lock(&i915->drm.struct_mutex);
-				rq = hang_create_request(&h, engine,
-							 i915->kernel_context);
+				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					mutex_unlock(&i915->drm.struct_mutex);
@@ -487,7 +547,9 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 		if (err)
 			break;
 
-		cond_resched();
+		err = flush_test(i915, 0);
+		if (err)
+			break;
 	}
 
 	if (i915_terminally_wedged(&i915->gpu_error))
@@ -633,8 +695,7 @@ static int __igt_reset_engine_others(struct drm_i915_private *i915,
 				struct drm_i915_gem_request *rq;
 
 				mutex_lock(&i915->drm.struct_mutex);
-				rq = hang_create_request(&h, engine,
-							 i915->kernel_context);
+				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					mutex_unlock(&i915->drm.struct_mutex);
@@ -726,7 +787,9 @@ unwind:
 		if (err)
 			break;
 
-		cond_resched();
+		err = flush_test(i915, 0);
+		if (err)
+			break;
 	}
 
 	if (i915_terminally_wedged(&i915->gpu_error))
@@ -787,7 +850,7 @@ static int igt_wait_reset(void *arg)
 	if (err)
 		goto unlock;
 
-	rq = hang_create_request(&h, i915->engine[RCS], i915->kernel_context);
+	rq = hang_create_request(&h, i915->engine[RCS]);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto fini;
@@ -866,7 +929,7 @@ static int igt_reset_queue(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		prev = hang_create_request(&h, engine, i915->kernel_context);
+		prev = hang_create_request(&h, engine);
 		if (IS_ERR(prev)) {
 			err = PTR_ERR(prev);
 			goto fini;
@@ -880,9 +943,7 @@ static int igt_reset_queue(void *arg)
 			struct drm_i915_gem_request *rq;
 			unsigned int reset_count;
 
-			rq = hang_create_request(&h,
-						 engine,
-						 i915->kernel_context);
+			rq = hang_create_request(&h, engine);
 			if (IS_ERR(rq)) {
 				err = PTR_ERR(rq);
 				goto fini;
@@ -952,6 +1013,10 @@ static int igt_reset_queue(void *arg)
 		i915_gem_chipset_flush(i915);
 
 		i915_gem_request_put(prev);
+
+		err = flush_test(i915, I915_WAIT_LOCKED);
+		if (err)
+			break;
 	}
 
 fini:
@@ -989,7 +1054,7 @@ static int igt_handle_error(void *arg)
 	if (err)
 		goto err_unlock;
 
-	rq = hang_create_request(&h, engine, i915->kernel_context);
+	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_fini;
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c
index bbf80d42e793..501becc47c0c 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/selftests/mock_context.c
@@ -92,3 +92,14 @@ live_context(struct drm_i915_private *i915, struct drm_file *file)
 
 	return i915_gem_create_context(i915, file->driver_priv);
 }
+
+struct i915_gem_context *
+kernel_context(struct drm_i915_private *i915)
+{
+	return i915_gem_context_create_kernel(i915, I915_PRIORITY_NORMAL);
+}
+
+void kernel_context_close(struct i915_gem_context *ctx)
+{
+	context_close(ctx);
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.h b/drivers/gpu/drm/i915/selftests/mock_context.h
index 2f432c03d413..29b9d60a158b 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.h
+++ b/drivers/gpu/drm/i915/selftests/mock_context.h
@@ -36,4 +36,7 @@ void mock_context_close(struct i915_gem_context *ctx);
 struct i915_gem_context *
 live_context(struct drm_i915_private *i915, struct drm_file *file);
 
+struct i915_gem_context *kernel_context(struct drm_i915_private *i915);
+void kernel_context_close(struct i915_gem_context *ctx);
+
 #endif /* !__MOCK_CONTEXT_H */
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
index fe15aa64086f..71fe60e5f01f 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
@@ -698,7 +698,7 @@ static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(width);
 
 	return divider_recalc_rate(hw, parent_rate, val, NULL,
-				   postdiv->flags);
+				   postdiv->flags, width);
 }
 
 static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw,
diff --git a/drivers/gpu/drm/nouveau/dispnv04/arb.c b/drivers/gpu/drm/nouveau/dispnv04/arb.c
index 90075b676256..c79160c37f84 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/arb.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/arb.c
@@ -213,8 +213,10 @@ nv04_update_arb(struct drm_device *dev, int VClk, int bpp,
 	if ((dev->pdev->device & 0xffff) == 0x01a0 /*CHIPSET_NFORCE*/ ||
 	    (dev->pdev->device & 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) {
 		uint32_t type;
+		int domain = pci_domain_nr(dev->pdev->bus);
 
-		pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type);
+		pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 1),
+				      0x7c, &type);
 
 		sim_data.memory_type = (type >> 12) & 1;
 		sim_data.memory_width = 64;
diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c
index b98599002831..0c9bdf023f5b 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/hw.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c
@@ -216,12 +216,15 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 {
 	struct nvkm_pll_vals pllvals;
 	int ret;
+	int domain;
+
+	domain = pci_domain_nr(dev->pdev->bus);
 
 	if (plltype == PLL_MEMORY &&
 	    (dev->pdev->device & 0x0ff0) == CHIPSET_NFORCE) {
 		uint32_t mpllP;
-
-		pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
+		pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 3),
+				      0x6c, &mpllP);
 		mpllP = (mpllP >> 8) & 0xf;
 		if (!mpllP)
 			mpllP = 4;
@@ -232,7 +235,8 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 	    (dev->pdev->device & 0xff0) == CHIPSET_NFORCE2) {
 		uint32_t clock;
 
-		pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
+		pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 5),
+				      0x4c, &clock);
 		return clock / 1000;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index adb78f7d083a..92be0e5269c6 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -75,6 +75,7 @@ int mcp89_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gf100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gf108_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gk104_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int gk110_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gk20a_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gm107_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gm200_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
index 0760b93e9d1f..baab93398e54 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h
@@ -121,6 +121,7 @@ int nv41_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int nv44_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int nv50_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int g84_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
+int mcp77_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gf100_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gk104_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
 int gk20a_mmu_new(struct nvkm_device *, int, struct nvkm_mmu **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
index 59f3ba551681..b57fe4ae93ba 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
@@ -60,6 +60,7 @@ int nvkm_secboot_reset(struct nvkm_secboot *, unsigned long);
 int gm200_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
 int gm20b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
 int gp102_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
+int gp108_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
 int gp10b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h
index b1ac47eb786e..9398d9f09339 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h
@@ -46,6 +46,16 @@ enum nvkm_therm_attr_type {
 	NVKM_THERM_ATTR_THRS_SHUTDOWN_HYST = 17,
 };
 
+struct nvkm_therm_clkgate_init {
+	u32 addr;
+	u8  count;
+	u32 data;
+};
+
+struct nvkm_therm_clkgate_pack {
+	const struct nvkm_therm_clkgate_init *init;
+};
+
 struct nvkm_therm {
 	const struct nvkm_therm_func *func;
 	struct nvkm_subdev subdev;
@@ -85,17 +95,24 @@ struct nvkm_therm {
 
 	int (*attr_get)(struct nvkm_therm *, enum nvkm_therm_attr_type);
 	int (*attr_set)(struct nvkm_therm *, enum nvkm_therm_attr_type, int);
+
+	bool clkgating_enabled;
 };
 
 int nvkm_therm_temp_get(struct nvkm_therm *);
 int nvkm_therm_fan_sense(struct nvkm_therm *);
 int nvkm_therm_cstate(struct nvkm_therm *, int, int);
+void nvkm_therm_clkgate_init(struct nvkm_therm *,
+			     const struct nvkm_therm_clkgate_pack *);
+void nvkm_therm_clkgate_enable(struct nvkm_therm *);
+void nvkm_therm_clkgate_fini(struct nvkm_therm *, bool);
 
 int nv40_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int nv50_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int g84_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int gt215_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int gf119_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
+int gk104_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int gm107_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int gm200_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
 int gp100_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 41e7f2927443..80fa68d54bd3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1453,11 +1453,13 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg)
 				args.nv50.ro = 0;
 				args.nv50.kind = mem->kind;
 				args.nv50.comp = mem->comp;
+				argc = sizeof(args.nv50);
 				break;
 			case NVIF_CLASS_MEM_GF100:
 				args.gf100.version = 0;
 				args.gf100.ro = 0;
 				args.gf100.kind = mem->kind;
+				argc = sizeof(args.gf100);
 				break;
 			default:
 				WARN_ON(1);
@@ -1465,7 +1467,7 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg)
 			}
 
 			ret = nvif_object_map_handle(&mem->mem.object,
-						     &argc, argc,
+						     &args, argc,
 						     &handle, &length);
 			if (ret != 1)
 				return ret ? ret : -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index 7b5cc5c73d20..be8e00b49cde 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -105,4 +105,32 @@ nvbo_kmap_obj_iovirtual(struct nouveau_bo *nvbo)
 	return ioptr;
 }
 
+static inline void
+nouveau_bo_unmap_unpin_unref(struct nouveau_bo **pnvbo)
+{
+	if (*pnvbo) {
+		nouveau_bo_unmap(*pnvbo);
+		nouveau_bo_unpin(*pnvbo);
+		nouveau_bo_ref(NULL, pnvbo);
+	}
+}
+
+static inline int
+nouveau_bo_new_pin_map(struct nouveau_cli *cli, u64 size, int align, u32 flags,
+		       struct nouveau_bo **pnvbo)
+{
+	int ret = nouveau_bo_new(cli, size, align, flags,
+				 0, 0, NULL, NULL, pnvbo);
+	if (ret == 0) {
+		ret = nouveau_bo_pin(*pnvbo, flags, true);
+		if (ret == 0) {
+			ret = nouveau_bo_map(*pnvbo);
+			if (ret == 0)
+				return ret;
+			nouveau_bo_unpin(*pnvbo);
+		}
+		nouveau_bo_ref(NULL, pnvbo);
+	}
+	return ret;
+}
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_crtc.h b/drivers/gpu/drm/nouveau/nouveau_crtc.h
index b7a18fbee6dc..366acb928f57 100644
--- a/drivers/gpu/drm/nouveau/nouveau_crtc.h
+++ b/drivers/gpu/drm/nouveau/nouveau_crtc.h
@@ -60,7 +60,6 @@ struct nouveau_crtc {
 	} cursor;
 
 	struct {
-		struct nouveau_bo *nvbo;
 		int depth;
 	} lut;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 56fe261b6268..3e293029e3a6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -524,7 +524,8 @@ nouveau_get_hdmi_dev(struct nouveau_drm *drm)
 	}
 
 	/* subfunction one is a hdmi audio device? */
-	drm->hdmi_device = pci_get_bus_and_slot((unsigned int)pdev->bus->number,
+	drm->hdmi_device = pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+						(unsigned int)pdev->bus->number,
 						PCI_DEVFN(PCI_SLOT(pdev->devfn), 1));
 
 	if (!drm->hdmi_device) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index ee5d1dc2eaf5..85c1f10bc2b6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -56,6 +56,10 @@ MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration");
 int nouveau_nofbaccel = 0;
 module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
 
+MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)");
+static int nouveau_fbcon_bpp;
+module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400);
+
 static void
 nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
 {
@@ -488,7 +492,7 @@ nouveau_fbcon_init(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_fbdev *fbcon;
-	int preferred_bpp;
+	int preferred_bpp = nouveau_fbcon_bpp;
 	int ret;
 
 	if (!dev->mode_config.num_crtc ||
@@ -512,13 +516,15 @@ nouveau_fbcon_init(struct drm_device *dev)
 	if (ret)
 		goto fini;
 
-	if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
-		preferred_bpp = 8;
-	else
-	if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
-		preferred_bpp = 16;
-	else
-		preferred_bpp = 32;
+	if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) {
+		if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
+			preferred_bpp = 8;
+		else
+		if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
+			preferred_bpp = 16;
+		else
+			preferred_bpp = 32;
+	}
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	if (!drm_drv_uses_atomic_modeset(dev))
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 5a9a51c735f0..1f55b3d80a56 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -137,8 +137,10 @@ struct nv50_head_atom {
 	} mode;
 
 	struct {
+		bool visible;
 		u32 handle;
 		u64 offset:40;
+		u8  mode:4;
 	} lut;
 
 	struct {
@@ -192,6 +194,7 @@ struct nv50_head_atom {
 
 	union {
 		struct {
+			bool ilut:1;
 			bool core:1;
 			bool curs:1;
 		};
@@ -200,6 +203,7 @@ struct nv50_head_atom {
 
 	union {
 		struct {
+			bool ilut:1;
 			bool core:1;
 			bool curs:1;
 			bool view:1;
@@ -658,6 +662,10 @@ nv50_ovly_create(struct nvif_device *device, struct nvif_object *disp,
 
 struct nv50_head {
 	struct nouveau_crtc base;
+	struct {
+		struct nouveau_bo *nvbo[2];
+		int next;
+	} lut;
 	struct nv50_ovly ovly;
 	struct nv50_oimm oimm;
 };
@@ -1799,6 +1807,54 @@ nv50_head_lut_clr(struct nv50_head *head)
 }
 
 static void
+nv50_head_lut_load(struct drm_property_blob *blob, int mode,
+		   struct nouveau_bo *nvbo)
+{
+	struct drm_color_lut *in = (struct drm_color_lut *)blob->data;
+	void __iomem *lut = (u8 *)nvbo_kmap_obj_iovirtual(nvbo);
+	const int size = blob->length / sizeof(*in);
+	int bits, shift, i;
+	u16 zero, r, g, b;
+
+	/* This can't happen.. But it shuts the compiler up. */
+	if (WARN_ON(size != 256))
+		return;
+
+	switch (mode) {
+	case 0: /* LORES. */
+	case 1: /* HIRES. */
+		bits = 11;
+		shift = 3;
+		zero = 0x0000;
+		break;
+	case 7: /* INTERPOLATE_257_UNITY_RANGE. */
+		bits = 14;
+		shift = 0;
+		zero = 0x6000;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	for (i = 0; i < size; i++) {
+		r = (drm_color_lut_extract(in[i].  red, bits) + zero) << shift;
+		g = (drm_color_lut_extract(in[i].green, bits) + zero) << shift;
+		b = (drm_color_lut_extract(in[i]. blue, bits) + zero) << shift;
+		writew(r, lut + (i * 0x08) + 0);
+		writew(g, lut + (i * 0x08) + 2);
+		writew(b, lut + (i * 0x08) + 4);
+	}
+
+	/* INTERPOLATE modes require a "next" entry to interpolate with,
+	 * so we replicate the last entry to deal with this for now.
+	 */
+	writew(r, lut + (i * 0x08) + 0);
+	writew(g, lut + (i * 0x08) + 2);
+	writew(b, lut + (i * 0x08) + 4);
+}
+
+static void
 nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
 	struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base;
@@ -1806,18 +1862,18 @@ nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 	if ((push = evo_wait(core, 7))) {
 		if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
 			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
-			evo_data(push, 0xc0000000);
+			evo_data(push, 0x80000000 | asyh->lut.mode << 30);
 			evo_data(push, asyh->lut.offset >> 8);
 		} else
 		if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
 			evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
-			evo_data(push, 0xc0000000);
+			evo_data(push, 0x80000000 | asyh->lut.mode << 30);
 			evo_data(push, asyh->lut.offset >> 8);
 			evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
 			evo_data(push, asyh->lut.handle);
 		} else {
 			evo_mthd(push, 0x0440 + (head->base.index * 0x300), 4);
-			evo_data(push, 0x83000000);
+			evo_data(push, 0x80000000 | asyh->lut.mode << 24);
 			evo_data(push, asyh->lut.offset >> 8);
 			evo_data(push, 0x00000000);
 			evo_data(push, 0x00000000);
@@ -1900,7 +1956,7 @@ nv50_head_view(struct nv50_head *head, struct nv50_head_atom *asyh)
 static void
 nv50_head_flush_clr(struct nv50_head *head, struct nv50_head_atom *asyh, bool y)
 {
-	if (asyh->clr.core && (!asyh->set.core || y))
+	if (asyh->clr.ilut && (!asyh->set.ilut || y))
 		nv50_head_lut_clr(head);
 	if (asyh->clr.core && (!asyh->set.core || y))
 		nv50_head_core_clr(head);
@@ -1913,7 +1969,15 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
 	if (asyh->set.view   ) nv50_head_view    (head, asyh);
 	if (asyh->set.mode   ) nv50_head_mode    (head, asyh);
-	if (asyh->set.core   ) nv50_head_lut_set (head, asyh);
+	if (asyh->set.ilut   ) {
+		struct nouveau_bo *nvbo = head->lut.nvbo[head->lut.next];
+		struct drm_property_blob *blob = asyh->state.gamma_lut;
+		if (blob)
+			nv50_head_lut_load(blob, asyh->lut.mode, nvbo);
+		asyh->lut.offset = nvbo->bo.offset;
+		head->lut.next ^= 1;
+		nv50_head_lut_set(head, asyh);
+	}
 	if (asyh->set.core   ) nv50_head_core_set(head, asyh);
 	if (asyh->set.curs   ) nv50_head_curs_set(head, asyh);
 	if (asyh->set.base   ) nv50_head_base    (head, asyh);
@@ -2048,6 +2112,37 @@ nv50_head_atomic_check_view(struct nv50_head_atom *armh,
 }
 
 static void
+nv50_head_atomic_check_lut(struct nv50_head *head,
+			   struct nv50_head_atom *armh,
+			   struct nv50_head_atom *asyh)
+{
+	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
+
+	/* An I8 surface without an input LUT makes no sense, and
+	 * EVO will throw an error if you try.
+	 *
+	 * Legacy clients actually cause this due to the order in
+	 * which they call ioctls, so we will enable the LUT with
+	 * whatever contents the buffer already contains to avoid
+	 * triggering the error check.
+	 */
+	if (!asyh->state.gamma_lut && asyh->base.cpp != 1) {
+		asyh->lut.handle = 0;
+		asyh->clr.ilut = armh->lut.visible;
+		return;
+	}
+
+	if (disp->disp->oclass < GF110_DISP) {
+		asyh->lut.mode = (asyh->base.cpp == 1) ? 0 : 1;
+		asyh->set.ilut = true;
+	} else {
+		asyh->lut.mode = 7;
+		asyh->set.ilut = asyh->state.color_mgmt_changed;
+	}
+	asyh->lut.handle = disp->mast.base.vram.handle;
+}
+
+static void
 nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
 	struct drm_display_mode *mode = &asyh->state.adjusted_mode;
@@ -2132,6 +2227,11 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 		if (asyh->state.mode_changed)
 			nv50_head_atomic_check_mode(head, asyh);
 
+		if (asyh->state.color_mgmt_changed ||
+		    asyh->base.cpp != armh->base.cpp)
+			nv50_head_atomic_check_lut(head, armh, asyh);
+		asyh->lut.visible = asyh->lut.handle != 0;
+
 		if (asyc) {
 			if (asyc->set.scaler)
 				nv50_head_atomic_check_view(armh, asyh, asyc);
@@ -2147,7 +2247,8 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 			asyh->core.w = asyh->base.w;
 			asyh->core.h = asyh->base.h;
 		} else
-		if ((asyh->core.visible = asyh->curs.visible)) {
+		if ((asyh->core.visible = asyh->curs.visible) ||
+		    (asyh->core.visible = asyh->lut.visible)) {
 			/*XXX: We need to either find some way of having the
 			 *     primary base layer appear black, while still
 			 *     being able to display the other layers, or we
@@ -2165,11 +2266,10 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 		asyh->core.layout = 1;
 		asyh->core.block = 0;
 		asyh->core.pitch = ALIGN(asyh->core.w, 64) * 4;
-		asyh->lut.handle = disp->mast.base.vram.handle;
-		asyh->lut.offset = head->base.lut.nvbo->bo.offset;
 		asyh->set.base = armh->base.cpp != asyh->base.cpp;
 		asyh->set.ovly = armh->ovly.cpp != asyh->ovly.cpp;
 	} else {
+		asyh->lut.visible = false;
 		asyh->core.visible = false;
 		asyh->curs.visible = false;
 		asyh->base.cpp = 0;
@@ -2193,8 +2293,10 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 			asyh->clr.curs = true;
 		}
 	} else {
+		asyh->clr.ilut = armh->lut.visible;
 		asyh->clr.core = armh->core.visible;
 		asyh->clr.curs = armh->curs.visible;
+		asyh->set.ilut = asyh->lut.visible;
 		asyh->set.core = asyh->core.visible;
 		asyh->set.curs = asyh->curs.visible;
 	}
@@ -2204,47 +2306,11 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 	return 0;
 }
 
-static void
-nv50_head_lut_load(struct drm_crtc *crtc)
-{
-	struct nv50_disp *disp = nv50_disp(crtc->dev);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
-	void __iomem *lut = nvbo_kmap_obj_iovirtual(nv_crtc->lut.nvbo);
-	u16 *r, *g, *b;
-	int i;
-
-	r = crtc->gamma_store;
-	g = r + crtc->gamma_size;
-	b = g + crtc->gamma_size;
-
-	for (i = 0; i < 256; i++) {
-		if (disp->disp->oclass < GF110_DISP) {
-			writew((*r++ >> 2) + 0x0000, lut + (i * 0x08) + 0);
-			writew((*g++ >> 2) + 0x0000, lut + (i * 0x08) + 2);
-			writew((*b++ >> 2) + 0x0000, lut + (i * 0x08) + 4);
-		} else {
-			/* 0x6000 interferes with the 14-bit color??? */
-			writew((*r++ >> 2) + 0x6000, lut + (i * 0x20) + 0);
-			writew((*g++ >> 2) + 0x6000, lut + (i * 0x20) + 2);
-			writew((*b++ >> 2) + 0x6000, lut + (i * 0x20) + 4);
-		}
-	}
-}
-
 static const struct drm_crtc_helper_funcs
 nv50_head_help = {
 	.atomic_check = nv50_head_atomic_check,
 };
 
-static int
-nv50_head_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-		    uint32_t size,
-		    struct drm_modeset_acquire_ctx *ctx)
-{
-	nv50_head_lut_load(crtc);
-	return 0;
-}
-
 static void
 nv50_head_atomic_destroy_state(struct drm_crtc *crtc,
 			       struct drm_crtc_state *state)
@@ -2300,17 +2366,15 @@ nv50_head_reset(struct drm_crtc *crtc)
 static void
 nv50_head_destroy(struct drm_crtc *crtc)
 {
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	struct nv50_disp *disp = nv50_disp(crtc->dev);
 	struct nv50_head *head = nv50_head(crtc);
+	int i;
 
 	nv50_dmac_destroy(&head->ovly.base, disp->disp);
 	nv50_pioc_destroy(&head->oimm.base);
 
-	nouveau_bo_unmap(nv_crtc->lut.nvbo);
-	if (nv_crtc->lut.nvbo)
-		nouveau_bo_unpin(nv_crtc->lut.nvbo);
-	nouveau_bo_ref(NULL, &nv_crtc->lut.nvbo);
+	for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++)
+		nouveau_bo_unmap_unpin_unref(&head->lut.nvbo[i]);
 
 	drm_crtc_cleanup(crtc);
 	kfree(crtc);
@@ -2319,7 +2383,7 @@ nv50_head_destroy(struct drm_crtc *crtc)
 static const struct drm_crtc_funcs
 nv50_head_func = {
 	.reset = nv50_head_reset,
-	.gamma_set = nv50_head_gamma_set,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.destroy = nv50_head_destroy,
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
@@ -2337,7 +2401,7 @@ nv50_head_create(struct drm_device *dev, int index)
 	struct nv50_base *base;
 	struct nv50_curs *curs;
 	struct drm_crtc *crtc;
-	int ret;
+	int ret, i;
 
 	head = kzalloc(sizeof(*head), GFP_KERNEL);
 	if (!head)
@@ -2359,22 +2423,14 @@ nv50_head_create(struct drm_device *dev, int index)
 	drm_crtc_helper_add(crtc, &nv50_head_help);
 	drm_mode_crtc_set_gamma_size(crtc, 256);
 
-	ret = nouveau_bo_new(&drm->client, 8192, 0x100, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, NULL, &head->base.lut.nvbo);
-	if (!ret) {
-		ret = nouveau_bo_pin(head->base.lut.nvbo, TTM_PL_FLAG_VRAM, true);
-		if (!ret) {
-			ret = nouveau_bo_map(head->base.lut.nvbo);
-			if (ret)
-				nouveau_bo_unpin(head->base.lut.nvbo);
-		}
+	for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++) {
+		ret = nouveau_bo_new_pin_map(&drm->client, 1025 * 8, 0x100,
+					     TTM_PL_FLAG_VRAM,
+					     &head->lut.nvbo[i]);
 		if (ret)
-			nouveau_bo_ref(NULL, &head->base.lut.nvbo);
+			goto out;
 	}
 
-	if (ret)
-		goto out;
-
 	/* allocate overlay resources */
 	ret = nv50_oimm_create(device, disp->disp, index, &head->oimm);
 	if (ret)
@@ -4354,7 +4410,6 @@ nv50_display_init(struct drm_device *dev)
 {
 	struct drm_encoder *encoder;
 	struct drm_plane *plane;
-	struct drm_crtc *crtc;
 	u32 *push;
 
 	push = evo_wait(nv50_mast(dev), 32);
@@ -4373,10 +4428,6 @@ nv50_display_init(struct drm_device *dev)
 		}
 	}
 
-	drm_for_each_crtc(crtc, dev) {
-		nv50_head_lut_load(crtc);
-	}
-
 	drm_for_each_plane(plane, dev) {
 		struct nv50_wndw *wndw = nv50_wndw(plane);
 		if (plane->funcs != &nv50_wndw)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 00eeaaffeae5..05cd674326a6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -28,6 +28,7 @@
 #include <core/option.h>
 
 #include <subdev/bios.h>
+#include <subdev/therm.h>
 
 static DEFINE_MUTEX(nv_devices_mutex);
 static LIST_HEAD(nv_devices);
@@ -1251,7 +1252,7 @@ nvaa_chipset = {
 	.i2c = g94_i2c_new,
 	.imem = nv50_instmem_new,
 	.mc = g98_mc_new,
-	.mmu = g84_mmu_new,
+	.mmu = mcp77_mmu_new,
 	.mxm = nv50_mxm_new,
 	.pci = g94_pci_new,
 	.therm = g84_therm_new,
@@ -1283,7 +1284,7 @@ nvac_chipset = {
 	.i2c = g94_i2c_new,
 	.imem = nv50_instmem_new,
 	.mc = g98_mc_new,
-	.mmu = g84_mmu_new,
+	.mmu = mcp77_mmu_new,
 	.mxm = nv50_mxm_new,
 	.pci = g94_pci_new,
 	.therm = g84_therm_new,
@@ -1682,7 +1683,7 @@ nve4_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk104_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1721,7 +1722,7 @@ nve6_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk104_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1760,7 +1761,7 @@ nve7_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk104_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1811,7 +1812,7 @@ nvf0_chipset = {
 	.bus = gf100_bus_new,
 	.clk = gk104_clk_new,
 	.devinit = gf100_devinit_new,
-	.fb = gk104_fb_new,
+	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gk104_i2c_new,
@@ -1824,7 +1825,7 @@ nvf0_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk110_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1849,7 +1850,7 @@ nvf1_chipset = {
 	.bus = gf100_bus_new,
 	.clk = gk104_clk_new,
 	.devinit = gf100_devinit_new,
-	.fb = gk104_fb_new,
+	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gk104_i2c_new,
@@ -1862,7 +1863,7 @@ nvf1_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk110_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1887,7 +1888,7 @@ nv106_chipset = {
 	.bus = gf100_bus_new,
 	.clk = gk104_clk_new,
 	.devinit = gf100_devinit_new,
-	.fb = gk104_fb_new,
+	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gk104_i2c_new,
@@ -1900,7 +1901,7 @@ nv106_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk208_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -1925,7 +1926,7 @@ nv108_chipset = {
 	.bus = gf100_bus_new,
 	.clk = gk104_clk_new,
 	.devinit = gf100_devinit_new,
-	.fb = gk104_fb_new,
+	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
 	.i2c = gk104_i2c_new,
@@ -1938,7 +1939,7 @@ nv108_chipset = {
 	.mxm = nv50_mxm_new,
 	.pci = gk104_pci_new,
 	.pmu = gk208_pmu_new,
-	.therm = gf119_therm_new,
+	.therm = gk104_therm_new,
 	.timer = nv41_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2345,6 +2346,7 @@ nv138_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
+	.secboot = gp108_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2356,6 +2358,10 @@ nv138_chipset = {
 	.disp = gp102_disp_new,
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
+	.gr = gp107_gr_new,
+	.nvdec = gp102_nvdec_new,
+	.sec2 = gp102_sec2_new,
+	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
@@ -2508,6 +2514,7 @@ nvkm_device_fini(struct nvkm_device *device, bool suspend)
 		}
 	}
 
+	nvkm_therm_clkgate_fini(device->therm, suspend);
 
 	if (device->func->fini)
 		device->func->fini(device, suspend);
@@ -2597,6 +2604,7 @@ nvkm_device_init(struct nvkm_device *device)
 	}
 
 	nvkm_acpi_init(device);
+	nvkm_therm_clkgate_enable(device->therm);
 
 	time = ktime_to_us(ktime_get()) - time;
 	nvdev_trace(device, "init completed in %lldus\n", time);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index d7c2adb9b543..c8ec3fd97155 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -137,6 +137,7 @@ struct gf100_gr_func {
 	int (*rops)(struct gf100_gr *);
 	int ppc_nr;
 	const struct gf100_grctx_func *grctx;
+	const struct nvkm_therm_clkgate_pack *clkgate_pack;
 	struct nvkm_sclass sclass[];
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
index 5e82f94c2245..1b52fcb2c49a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "gf100.h"
+#include "gk104.h"
 #include "ctxgf100.h"
 
 #include <nvif/class.h>
@@ -173,6 +174,208 @@ gk104_gr_pack_mmio[] = {
 	{}
 };
 
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_main_0[] = {
+	{ 0x4041f0, 1, 0x00004046 },
+	{ 0x409890, 1, 0x00000045 },
+	{ 0x4098b0, 1, 0x0000007f },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rstr2d_0[] = {
+	{ 0x4078c0, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_unk_0[] = {
+	{ 0x406000, 1, 0x00004044 },
+	{ 0x405860, 1, 0x00004042 },
+	{ 0x40590c, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gcc_0[] = {
+	{ 0x408040, 1, 0x00004044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_sked_0[] = {
+	{ 0x407000, 1, 0x00004044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_unk_1[] = {
+	{ 0x405bf0, 1, 0x00004044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ctxctl_0[] = {
+	{ 0x41a890, 1, 0x00000042 },
+	{ 0x41a8b0, 1, 0x0000007f },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_0[] = {
+	{ 0x418500, 1, 0x00004042 },
+	{ 0x418608, 1, 0x00004042 },
+	{ 0x418688, 1, 0x00004042 },
+	{ 0x418718, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_esetup_0[] = {
+	{ 0x418828, 1, 0x00000044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tpbus_0[] = {
+	{ 0x418bbc, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_zcull_0[] = {
+	{ 0x418970, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tpconf_0[] = {
+	{ 0x418c70, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_1[] = {
+	{ 0x418cf0, 1, 0x00004042 },
+	{ 0x418d70, 1, 0x00004042 },
+	{ 0x418f0c, 1, 0x00004042 },
+	{ 0x418e0c, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_gcc_0[] = {
+	{ 0x419020, 1, 0x00004042 },
+	{ 0x419038, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ffb_0[] = {
+	{ 0x418898, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tex_0[] = {
+	{ 0x419a40, 9, 0x00004042 },
+	{ 0x419acc, 1, 0x00004047 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_poly_0[] = {
+	{ 0x419868, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_l1c_0[] = {
+	{ 0x419ccc, 3, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_2[] = {
+	{ 0x419c70, 1, 0x00004045 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_mp_0[] = {
+	{ 0x419fd0, 1, 0x00004043 },
+	{ 0x419fd8, 1, 0x00004049 },
+	{ 0x419fe0, 2, 0x00004042 },
+	{ 0x419ff0, 1, 0x00004046 },
+	{ 0x419ff8, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ppc_0[] = {
+	{ 0x41be28, 1, 0x00000042 },
+	{ 0x41bfe8, 1, 0x00004042 },
+	{ 0x41bed0, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_zrop_0[] = {
+	{ 0x408810, 2, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_0[] = {
+	{ 0x408a80, 6, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_crop_0[] = {
+	{ 0x4089a8, 1, 0x00004042 },
+	{ 0x4089b0, 1, 0x00000042 },
+	{ 0x4089b8, 1, 0x00004042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_pxbar_0[] = {
+	{ 0x13c820, 1, 0x0001007f },
+	{ 0x13cbe0, 1, 0x00000042 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk104_clkgate_pack[] = {
+	{ gk104_clkgate_blcg_init_main_0 },
+	{ gk104_clkgate_blcg_init_rstr2d_0 },
+	{ gk104_clkgate_blcg_init_unk_0 },
+	{ gk104_clkgate_blcg_init_gcc_0 },
+	{ gk104_clkgate_blcg_init_sked_0 },
+	{ gk104_clkgate_blcg_init_unk_1 },
+	{ gk104_clkgate_blcg_init_gpc_ctxctl_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_0 },
+	{ gk104_clkgate_blcg_init_gpc_esetup_0 },
+	{ gk104_clkgate_blcg_init_gpc_tpbus_0 },
+	{ gk104_clkgate_blcg_init_gpc_zcull_0 },
+	{ gk104_clkgate_blcg_init_gpc_tpconf_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_1 },
+	{ gk104_clkgate_blcg_init_gpc_gcc_0 },
+	{ gk104_clkgate_blcg_init_gpc_ffb_0 },
+	{ gk104_clkgate_blcg_init_gpc_tex_0 },
+	{ gk104_clkgate_blcg_init_gpc_poly_0 },
+	{ gk104_clkgate_blcg_init_gpc_l1c_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_2 },
+	{ gk104_clkgate_blcg_init_gpc_mp_0 },
+	{ gk104_clkgate_blcg_init_gpc_ppc_0 },
+	{ gk104_clkgate_blcg_init_rop_zrop_0 },
+	{ gk104_clkgate_blcg_init_rop_0 },
+	{ gk104_clkgate_blcg_init_rop_crop_0 },
+	{ gk104_clkgate_blcg_init_pxbar_0 },
+	{}
+};
+
 /*******************************************************************************
  * PGRAPH engine/subdev functions
  ******************************************************************************/
@@ -214,6 +417,9 @@ gk104_gr_init(struct gf100_gr *gr)
 	gr->func->init_gpc_mmu(gr);
 
 	gf100_gr_mmio(gr, gr->func->mmio);
+	if (gr->func->clkgate_pack)
+		nvkm_therm_clkgate_init(gr->base.engine.subdev.device->therm,
+					gr->func->clkgate_pack);
 
 	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
 
@@ -338,6 +544,7 @@ gk104_gr = {
 	.rops = gf100_gr_rops,
 	.ppc_nr = 1,
 	.grctx = &gk104_grctx,
+	.clkgate_pack = gk104_clkgate_pack,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_A },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h
new file mode 100644
index 000000000000..a24c177365d1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul <lyude@redhat.com>
+ */
+#ifndef __GK104_GR_H__
+#define __GK104_GR_H__
+
+#include <subdev/therm.h>
+
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_main_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rstr2d_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gcc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_sked_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_1[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ctxctl_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_esetup_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpbus_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_zcull_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpconf_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_1[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_gcc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ffb_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tex_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_poly_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_l1c_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_2[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_mp_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ppc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_zrop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_crop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_pxbar_0[];
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
index a38e19b61c1d..4da916a9fc73 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 #include "gf100.h"
+#include "gk104.h"
 #include "ctxgf100.h"
 
 #include <subdev/timer.h>
@@ -156,6 +157,159 @@ gk110_gr_pack_mmio[] = {
 	{}
 };
 
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_sked_0[] = {
+	{ 0x407000, 1, 0x00004041 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_gcc_0[] = {
+	{ 0x419020, 1, 0x00000042 },
+	{ 0x419038, 1, 0x00000042 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_l1c_0[] = {
+	{ 0x419cd4, 2, 0x00004042 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_mp_0[] = {
+	{ 0x419fd0, 1, 0x00004043 },
+	{ 0x419fd8, 1, 0x00004049 },
+	{ 0x419fe0, 2, 0x00004042 },
+	{ 0x419ff0, 1, 0x00000046 },
+	{ 0x419ff8, 1, 0x00004042 },
+	{ 0x419f90, 1, 0x00004042 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_main_0[] = {
+	{ 0x4041f4, 1, 0x00000000 },
+	{ 0x409894, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_unk_0[] = {
+	{ 0x406004, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_sked_0[] = {
+	{ 0x407004, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_ctxctl_0[] = {
+	{ 0x41a894, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_unk_0[] = {
+	{ 0x418504, 1, 0x00000000 },
+	{ 0x41860c, 1, 0x00000000 },
+	{ 0x41868c, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_esetup_0[] = {
+	{ 0x41882c, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_zcull_0[] = {
+	{ 0x418974, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_l1c_0[] = {
+	{ 0x419cd8, 2, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_unk_1[] = {
+	{ 0x419c74, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_mp_0[] = {
+	{ 0x419fd4, 1, 0x00004a4a },
+	{ 0x419fdc, 1, 0x00000014 },
+	{ 0x419fe4, 1, 0x00000000 },
+	{ 0x419ff4, 1, 0x00001724 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_ppc_0[] = {
+	{ 0x41be2c, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_pcounter_0[] = {
+	{ 0x1be018, 1, 0x000001ff },
+	{ 0x1bc018, 1, 0x000001ff },
+	{ 0x1b8018, 1, 0x000001ff },
+	{ 0x1b4124, 1, 0x00000000 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk110_clkgate_pack[] = {
+	{ gk104_clkgate_blcg_init_main_0 },
+	{ gk104_clkgate_blcg_init_rstr2d_0 },
+	{ gk104_clkgate_blcg_init_unk_0 },
+	{ gk104_clkgate_blcg_init_gcc_0 },
+	{ gk110_clkgate_blcg_init_sked_0 },
+	{ gk104_clkgate_blcg_init_unk_1 },
+	{ gk104_clkgate_blcg_init_gpc_ctxctl_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_0 },
+	{ gk104_clkgate_blcg_init_gpc_esetup_0 },
+	{ gk104_clkgate_blcg_init_gpc_tpbus_0 },
+	{ gk104_clkgate_blcg_init_gpc_zcull_0 },
+	{ gk104_clkgate_blcg_init_gpc_tpconf_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_1 },
+	{ gk110_clkgate_blcg_init_gpc_gcc_0 },
+	{ gk104_clkgate_blcg_init_gpc_ffb_0 },
+	{ gk104_clkgate_blcg_init_gpc_tex_0 },
+	{ gk104_clkgate_blcg_init_gpc_poly_0 },
+	{ gk110_clkgate_blcg_init_gpc_l1c_0 },
+	{ gk104_clkgate_blcg_init_gpc_unk_2 },
+	{ gk110_clkgate_blcg_init_gpc_mp_0 },
+	{ gk104_clkgate_blcg_init_gpc_ppc_0 },
+	{ gk104_clkgate_blcg_init_rop_zrop_0 },
+	{ gk104_clkgate_blcg_init_rop_0 },
+	{ gk104_clkgate_blcg_init_rop_crop_0 },
+	{ gk104_clkgate_blcg_init_pxbar_0 },
+	{ gk110_clkgate_slcg_init_main_0 },
+	{ gk110_clkgate_slcg_init_unk_0 },
+	{ gk110_clkgate_slcg_init_sked_0 },
+	{ gk110_clkgate_slcg_init_gpc_ctxctl_0 },
+	{ gk110_clkgate_slcg_init_gpc_unk_0 },
+	{ gk110_clkgate_slcg_init_gpc_esetup_0 },
+	{ gk110_clkgate_slcg_init_gpc_zcull_0 },
+	{ gk110_clkgate_slcg_init_gpc_l1c_0 },
+	{ gk110_clkgate_slcg_init_gpc_unk_1 },
+	{ gk110_clkgate_slcg_init_gpc_mp_0 },
+	{ gk110_clkgate_slcg_init_gpc_ppc_0 },
+	{ gk110_clkgate_slcg_init_pcounter_0 },
+	{}
+};
+
 /*******************************************************************************
  * PGRAPH engine/subdev functions
  ******************************************************************************/
@@ -192,6 +346,7 @@ gk110_gr = {
 	.rops = gf100_gr_rops,
 	.ppc_nr = 2,
 	.grctx = &gk110_grctx,
+	.clkgate_pack = gk110_clkgate_pack,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
index dde89a4a0f5b..53859b6254d6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
@@ -462,7 +462,7 @@ nvkm_perfmon_mthd_query_domain(struct nvkm_perfmon *perfmon,
 
 		args->v0.id         = di;
 		args->v0.signal_nr  = nvkm_perfdom_count_perfsig(dom);
-		strncpy(args->v0.name, dom->name, sizeof(args->v0.name));
+		strncpy(args->v0.name, dom->name, sizeof(args->v0.name) - 1);
 
 		/* Currently only global counters (PCOUNTER) are implemented
 		 * but this will be different for local counters (MP). */
@@ -514,7 +514,7 @@ nvkm_perfmon_mthd_query_signal(struct nvkm_perfmon *perfmon,
 				 "/%s/%02x", dom->name, si);
 		} else {
 			strncpy(args->v0.name, sig->name,
-				sizeof(args->v0.name));
+				sizeof(args->v0.name) - 1);
 		}
 
 		args->v0.signal = si;
@@ -572,7 +572,7 @@ nvkm_perfmon_mthd_query_source(struct nvkm_perfmon *perfmon,
 
 		args->v0.source = sig->source[si];
 		args->v0.mask   = src->mask;
-		strncpy(args->v0.name, src->name, sizeof(args->v0.name));
+		strncpy(args->v0.name, src->name, sizeof(args->v0.name) - 1);
 	}
 
 	if (++si < source_nr) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
index 77273b53672c..58a59b7db2e5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
@@ -505,6 +505,7 @@ nvkm_msgqueue_new(u32 version, struct nvkm_falcon *falcon,
 		ret = msgqueue_0137bca5_new(falcon, sb, queue);
 		break;
 	case 0x0148cdec:
+	case 0x015ccf3e:
 		ret = msgqueue_0148cdec_new(falcon, sb, queue);
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c
index 9646adec57cb..243f0a5c8a62 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c
@@ -73,7 +73,8 @@ static int
 nvkm_bar_fini(struct nvkm_subdev *subdev, bool suspend)
 {
 	struct nvkm_bar *bar = nvkm_bar(subdev);
-	bar->func->bar1.fini(bar);
+	if (bar->func->bar1.fini)
+		bar->func->bar1.fini(bar);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gk20a.c
index b10077d38839..35878fb538f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gk20a.c
@@ -26,7 +26,6 @@ gk20a_bar_func = {
 	.dtor = gf100_bar_dtor,
 	.oneinit = gf100_bar_oneinit,
 	.bar1.init = gf100_bar_bar1_init,
-	.bar1.fini = gf100_bar_bar1_fini,
 	.bar1.wait = gf100_bar_bar1_wait,
 	.bar1.vmm = gf100_bar_bar1_vmm,
 	.flush = g84_bar_flush,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
index 96e0941c8edd..f0a26881d9b9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
@@ -110,6 +110,7 @@ read_pll(struct gt215_clk *clk, int idx, u32 pll)
 	struct nvkm_device *device = clk->base.subdev.device;
 	u32 ctrl = nvkm_rd32(device, pll + 0);
 	u32 sclk = 0, P = 1, N = 1, M = 1;
+	u32 MP;
 
 	if (!(ctrl & 0x00000008)) {
 		if (ctrl & 0x00000001) {
@@ -130,10 +131,12 @@ read_pll(struct gt215_clk *clk, int idx, u32 pll)
 		sclk = read_clk(clk, 0x10 + idx, false);
 	}
 
-	if (M * P)
-		return sclk * N / (M * P);
+	MP = M * P;
 
-	return 0;
+	if (!MP)
+		return 0;
+
+	return sclk * N / MP;
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 2571530e82f1..b4f22cce5d43 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -22,6 +22,7 @@ nvkm-y += nvkm/subdev/fb/mcp89.o
 nvkm-y += nvkm/subdev/fb/gf100.o
 nvkm-y += nvkm/subdev/fb/gf108.o
 nvkm-y += nvkm/subdev/fb/gk104.o
+nvkm-y += nvkm/subdev/fb/gk110.o
 nvkm-y += nvkm/subdev/fb/gk20a.o
 nvkm-y += nvkm/subdev/fb/gm107.o
 nvkm-y += nvkm/subdev/fb/gm200.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
index 47d28c279707..cdc4e0a2cc6b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
@@ -26,6 +26,7 @@
 
 #include <core/memory.h>
 #include <core/option.h>
+#include <subdev/therm.h>
 
 void
 gf100_fb_intr(struct nvkm_fb *base)
@@ -92,6 +93,11 @@ gf100_fb_init(struct nvkm_fb *base)
 
 	if (fb->r100c10_page)
 		nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8);
+
+	if (base->func->clkgate_pack) {
+		nvkm_therm_clkgate_init(device->therm,
+					base->func->clkgate_pack);
+	}
 }
 
 void *
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
index 0a6e8eaad42c..48fd98e08baa 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
@@ -20,10 +20,56 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: Ben Skeggs
+ *          Lyude Paul
  */
+#include "gk104.h"
 #include "gf100.h"
 #include "ram.h"
 
+/*
+ *******************************************************************************
+ * PGRAPH registers for clockgating
+ *******************************************************************************
+ */
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_unk_0[] = {
+	{ 0x100d10, 1, 0x0000c244 },
+	{ 0x100d30, 1, 0x0000c242 },
+	{ 0x100d3c, 1, 0x00000242 },
+	{ 0x100d48, 1, 0x00000242 },
+	{ 0x100d1c, 1, 0x00000042 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_vm_0[] = {
+	{ 0x100c98, 1, 0x00000242 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_main_0[] = {
+	{ 0x10f000, 1, 0x00000042 },
+	{ 0x17e030, 1, 0x00000044 },
+	{ 0x17e040, 1, 0x00000044 },
+	{}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_bcast_0[] = {
+	{ 0x17ea60, 4, 0x00000044 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk104_fb_clkgate_pack[] = {
+	{ gk104_fb_clkgate_blcg_init_unk_0 },
+	{ gk104_fb_clkgate_blcg_init_vm_0 },
+	{ gk104_fb_clkgate_blcg_init_main_0 },
+	{ gk104_fb_clkgate_blcg_init_bcast_0 },
+	{}
+};
+
 static const struct nvkm_fb_func
 gk104_fb = {
 	.dtor = gf100_fb_dtor,
@@ -33,6 +79,7 @@ gk104_fb = {
 	.intr = gf100_fb_intr,
 	.ram_new = gk104_ram_new,
 	.default_bigpage = 17,
+	.clkgate_pack = gk104_fb_clkgate_pack,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h
new file mode 100644
index 000000000000..b3c78e4ff706
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GK104_FB_H__
+#define __GK104_FB_H__
+
+#include <subdev/therm.h>
+
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_vm_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_main_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_bcast_0[];
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c
new file mode 100644
index 000000000000..0695e5dd360e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c
@@ -0,0 +1,71 @@
+/*
+ * Copyright 2017 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+#include "gf100.h"
+#include "gk104.h"
+#include "ram.h"
+#include <subdev/therm.h>
+#include <subdev/fb.h>
+
+/*
+ *******************************************************************************
+ * PGRAPH registers for clockgating
+ *******************************************************************************
+ */
+
+static const struct nvkm_therm_clkgate_init
+gk110_fb_clkgate_blcg_init_unk_0[] = {
+	{ 0x100d10, 1, 0x0000c242 },
+	{ 0x100d30, 1, 0x0000c242 },
+	{ 0x100d3c, 1, 0x00000242 },
+	{ 0x100d48, 1, 0x0000c242 },
+	{ 0x100d1c, 1, 0x00000042 },
+	{}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk110_fb_clkgate_pack[] = {
+	{ gk110_fb_clkgate_blcg_init_unk_0 },
+	{ gk104_fb_clkgate_blcg_init_vm_0 },
+	{ gk104_fb_clkgate_blcg_init_main_0 },
+	{ gk104_fb_clkgate_blcg_init_bcast_0 },
+	{}
+};
+
+static const struct nvkm_fb_func
+gk110_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gf100_fb_init,
+	.init_page = gf100_fb_init_page,
+	.intr = gf100_fb_intr,
+	.ram_new = gk104_ram_new,
+	.default_bigpage = 17,
+	.clkgate_pack = gk110_fb_clkgate_pack,
+};
+
+int
+gk110_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gf100_fb_new_(&gk110_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 9351188d5d76..414a423e0e55 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -3,6 +3,7 @@
 #define __NVKM_FB_PRIV_H__
 #define nvkm_fb(p) container_of((p), struct nvkm_fb, subdev)
 #include <subdev/fb.h>
+#include <subdev/therm.h>
 struct nvkm_bios;
 
 struct nvkm_fb_func {
@@ -27,6 +28,7 @@ struct nvkm_fb_func {
 	int (*ram_new)(struct nvkm_fb *, struct nvkm_ram **);
 
 	u8 default_bigpage;
+	const struct nvkm_therm_clkgate_pack *clkgate_pack;
 };
 
 void nvkm_fb_ctor(const struct nvkm_fb_func *, struct nvkm_device *device,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv1a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv1a.c
index 4c07d10bb976..18241c6ba5fa 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv1a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv1a.c
@@ -28,8 +28,16 @@ nv1a_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
 {
 	struct pci_dev *bridge;
 	u32 mem, mib;
+	int domain = 0;
+	struct pci_dev *pdev = NULL;
 
-	bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 1));
+	if (dev_is_pci(fb->subdev.device->dev))
+		pdev = to_pci_dev(fb->subdev.device->dev);
+
+	if (pdev)
+		domain = pci_domain_nr(pdev->bus);
+
+	bridge = pci_get_domain_bus_and_slot(domain, 0, PCI_DEVFN(0, 1));
 	if (!bridge) {
 		nvkm_error(&fb->subdev, "no bridge device\n");
 		return -ENODEV;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
index 352a65f9371c..67ee983bb026 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
@@ -4,6 +4,7 @@ nvkm-y += nvkm/subdev/mmu/nv41.o
 nvkm-y += nvkm/subdev/mmu/nv44.o
 nvkm-y += nvkm/subdev/mmu/nv50.o
 nvkm-y += nvkm/subdev/mmu/g84.o
+nvkm-y += nvkm/subdev/mmu/mcp77.o
 nvkm-y += nvkm/subdev/mmu/gf100.o
 nvkm-y += nvkm/subdev/mmu/gk104.o
 nvkm-y += nvkm/subdev/mmu/gk20a.o
@@ -22,6 +23,7 @@ nvkm-y += nvkm/subdev/mmu/vmmnv04.o
 nvkm-y += nvkm/subdev/mmu/vmmnv41.o
 nvkm-y += nvkm/subdev/mmu/vmmnv44.o
 nvkm-y += nvkm/subdev/mmu/vmmnv50.o
+nvkm-y += nvkm/subdev/mmu/vmmmcp77.o
 nvkm-y += nvkm/subdev/mmu/vmmgf100.o
 nvkm-y += nvkm/subdev/mmu/vmmgk104.o
 nvkm-y += nvkm/subdev/mmu/vmmgk20a.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/mcp77.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/mcp77.c
new file mode 100644
index 000000000000..0527b50730d9
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/mcp77.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2017 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "mem.h"
+#include "vmm.h"
+
+#include <nvif/class.h>
+
+static const struct nvkm_mmu_func
+mcp77_mmu = {
+	.dma_bits = 40,
+	.mmu = {{ -1, -1, NVIF_CLASS_MMU_NV50}},
+	.mem = {{ -1,  0, NVIF_CLASS_MEM_NV50}, nv50_mem_new, nv50_mem_map },
+	.vmm = {{ -1, -1, NVIF_CLASS_VMM_NV50}, mcp77_vmm_new, false, 0x0200 },
+	.kind = nv50_mmu_kind,
+	.kind_sys = true,
+};
+
+int
+mcp77_mmu_new(struct nvkm_device *device, int index, struct nvkm_mmu **pmmu)
+{
+	return nvkm_mmu_new_(&mcp77_mmu, device, index, pmmu);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c
index fa81d0c1ba41..37b201b95f15 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c
@@ -106,7 +106,8 @@ nvkm_uvmm_mthd_map(struct nvkm_uvmm *uvmm, void *argv, u32 argc)
 	} else
 		return ret;
 
-	if (IS_ERR((memory = nvkm_umem_search(client, handle)))) {
+	memory = nvkm_umem_search(client, handle);
+	if (IS_ERR(memory)) {
 		VMM_DEBUG(vmm, "memory %016llx %ld\n", handle, PTR_ERR(memory));
 		return PTR_ERR(memory);
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
index e35d3e17cd7c..93946dcee319 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
@@ -642,7 +642,7 @@ nvkm_vmm_ptes_sparse(struct nvkm_vmm *vmm, u64 addr, u64 size, bool ref)
 			else
 				block = (size >> page[i].shift) << page[i].shift;
 		} else {
-			block = (size >> page[i].shift) << page[i].shift;;
+			block = (size >> page[i].shift) << page[i].shift;
 		}
 
 		/* Perform operation. */
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
index 6d8f61ea467a..da06e64d8a7d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
@@ -95,6 +95,9 @@ struct nvkm_vmm_desc {
 	const struct nvkm_vmm_desc_func *func;
 };
 
+extern const struct nvkm_vmm_desc nv50_vmm_desc_12[];
+extern const struct nvkm_vmm_desc nv50_vmm_desc_16[];
+
 extern const struct nvkm_vmm_desc gk104_vmm_desc_16_12[];
 extern const struct nvkm_vmm_desc gk104_vmm_desc_16_16[];
 extern const struct nvkm_vmm_desc gk104_vmm_desc_17_12[];
@@ -169,6 +172,11 @@ int nv04_vmm_new_(const struct nvkm_vmm_func *, struct nvkm_mmu *, u32,
 		  const char *, struct nvkm_vmm **);
 int nv04_vmm_valid(struct nvkm_vmm *, void *, u32, struct nvkm_vmm_map *);
 
+int nv50_vmm_join(struct nvkm_vmm *, struct nvkm_memory *);
+void nv50_vmm_part(struct nvkm_vmm *, struct nvkm_memory *);
+int nv50_vmm_valid(struct nvkm_vmm *, void *, u32, struct nvkm_vmm_map *);
+void nv50_vmm_flush(struct nvkm_vmm *, int);
+
 int gf100_vmm_new_(const struct nvkm_vmm_func *, const struct nvkm_vmm_func *,
 		   struct nvkm_mmu *, u64, u64, void *, u32,
 		   struct lock_class_key *, const char *, struct nvkm_vmm **);
@@ -200,6 +208,8 @@ int nv44_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
 		 struct lock_class_key *, const char *, struct nvkm_vmm **);
 int nv50_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
 		 struct lock_class_key *, const char *, struct nvkm_vmm **);
+int mcp77_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
+		  struct lock_class_key *, const char *, struct nvkm_vmm **);
 int g84_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
 		struct lock_class_key *, const char *, struct nvkm_vmm **);
 int gf100_vmm_new(struct nvkm_mmu *, u64, u64, void *, u32,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmmcp77.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmmcp77.c
new file mode 100644
index 000000000000..e63d984cbfd4
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmmcp77.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2017 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "vmm.h"
+
+static const struct nvkm_vmm_func
+mcp77_vmm = {
+	.join = nv50_vmm_join,
+	.part = nv50_vmm_part,
+	.valid = nv50_vmm_valid,
+	.flush = nv50_vmm_flush,
+	.page_block = 1 << 29,
+	.page = {
+		{ 16, &nv50_vmm_desc_16[0], NVKM_VMM_PAGE_xVxx },
+		{ 12, &nv50_vmm_desc_12[0], NVKM_VMM_PAGE_xVHx },
+		{}
+	}
+};
+
+int
+mcp77_vmm_new(struct nvkm_mmu *mmu, u64 addr, u64 size, void *argv, u32 argc,
+	      struct lock_class_key *key, const char *name,
+	      struct nvkm_vmm **pvmm)
+{
+	return nv04_vmm_new_(&mcp77_vmm, mmu, 0, addr, size,
+			     argv, argc, key, name, pvmm);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
index 863a2edd9861..64f75d906202 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
@@ -32,7 +32,7 @@ static inline void
 nv50_vmm_pgt_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
 		 u32 ptei, u32 ptes, struct nvkm_vmm_map *map, u64 addr)
 {
-	u64 next = addr | map->type, data;
+	u64 next = addr + map->type, data;
 	u32 pten;
 	int log2blk;
 
@@ -69,7 +69,7 @@ nv50_vmm_pgt_dma(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
 		VMM_SPAM(vmm, "DMAA %08x %08x PTE(s)", ptei, ptes);
 		nvkm_kmap(pt->memory);
 		while (ptes--) {
-			const u64 data = *map->dma++ | map->type;
+			const u64 data = *map->dma++ + map->type;
 			VMM_WO064(pt, vmm, ptei++ * 8, data);
 			map->type += map->ctag;
 		}
@@ -163,21 +163,21 @@ nv50_vmm_pgd = {
 	.pde = nv50_vmm_pgd_pde,
 };
 
-static const struct nvkm_vmm_desc
+const struct nvkm_vmm_desc
 nv50_vmm_desc_12[] = {
 	{ PGT, 17, 8, 0x1000, &nv50_vmm_pgt },
 	{ PGD, 11, 0, 0x0000, &nv50_vmm_pgd },
 	{}
 };
 
-static const struct nvkm_vmm_desc
+const struct nvkm_vmm_desc
 nv50_vmm_desc_16[] = {
 	{ PGT, 13, 8, 0x1000, &nv50_vmm_pgt },
 	{ PGD, 11, 0, 0x0000, &nv50_vmm_pgd },
 	{}
 };
 
-static void
+void
 nv50_vmm_flush(struct nvkm_vmm *vmm, int level)
 {
 	struct nvkm_subdev *subdev = &vmm->mmu->subdev;
@@ -223,7 +223,7 @@ nv50_vmm_flush(struct nvkm_vmm *vmm, int level)
 	mutex_unlock(&subdev->mutex);
 }
 
-static int
+int
 nv50_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	       struct nvkm_vmm_map *map)
 {
@@ -321,7 +321,7 @@ nv50_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	return 0;
 }
 
-static void
+void
 nv50_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst)
 {
 	struct nvkm_vmm_join *join;
@@ -335,7 +335,7 @@ nv50_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst)
 	}
 }
 
-static int
+int
 nv50_vmm_join(struct nvkm_vmm *vmm, struct nvkm_memory *inst)
 {
 	const u32 pd_offset = vmm->mmu->func->vmm.pd_offset;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
index deb96de54b00..ee2431a7804e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
@@ -71,6 +71,10 @@ nvkm_pci_intr(int irq, void *arg)
 	struct nvkm_pci *pci = arg;
 	struct nvkm_device *device = pci->subdev.device;
 	bool handled = false;
+
+	if (pci->irq < 0)
+		return IRQ_HANDLED;
+
 	nvkm_mc_intr_unarm(device);
 	if (pci->msi)
 		pci->func->msi_rearm(pci);
@@ -84,11 +88,6 @@ nvkm_pci_fini(struct nvkm_subdev *subdev, bool suspend)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
 
-	if (pci->irq >= 0) {
-		free_irq(pci->irq, pci);
-		pci->irq = -1;
-	}
-
 	if (pci->agp.bridge)
 		nvkm_agp_fini(pci);
 
@@ -108,8 +107,20 @@ static int
 nvkm_pci_oneinit(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
-	if (pci_is_pcie(pci->pdev))
-		return nvkm_pcie_oneinit(pci);
+	struct pci_dev *pdev = pci->pdev;
+	int ret;
+
+	if (pci_is_pcie(pci->pdev)) {
+		ret = nvkm_pcie_oneinit(pci);
+		if (ret)
+			return ret;
+	}
+
+	ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
+	if (ret)
+		return ret;
+
+	pci->irq = pdev->irq;
 	return 0;
 }
 
@@ -117,7 +128,6 @@ static int
 nvkm_pci_init(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
-	struct pci_dev *pdev = pci->pdev;
 	int ret;
 
 	if (pci->agp.bridge) {
@@ -131,28 +141,34 @@ nvkm_pci_init(struct nvkm_subdev *subdev)
 	if (pci->func->init)
 		pci->func->init(pci);
 
-	ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
-	if (ret)
-		return ret;
-
-	pci->irq = pdev->irq;
-
 	/* Ensure MSI interrupts are armed, for the case where there are
 	 * already interrupts pending (for whatever reason) at load time.
 	 */
 	if (pci->msi)
 		pci->func->msi_rearm(pci);
 
-	return ret;
+	return 0;
 }
 
 static void *
 nvkm_pci_dtor(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
+
 	nvkm_agp_dtor(pci);
+
+	if (pci->irq >= 0) {
+		/* freq_irq() will call the handler, we use pci->irq == -1
+		 * to signal that it's been torn down and should be a noop.
+		 */
+		int irq = pci->irq;
+		pci->irq = -1;
+		free_irq(irq, pci);
+	}
+
 	if (pci->msi)
 		pci_disable_msi(pci->pdev);
+
 	return nvkm_pci(subdev);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
index 53d01fb00a8b..1dbe593e5960 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
@@ -47,8 +47,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x00000756,
-	0x00000748,
+	0x00000754,
+	0x00000746,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -69,8 +69,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x0000075a,
 	0x00000758,
+	0x00000756,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -91,8 +91,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000b8a,
-	0x00000a2d,
+	0x00000b88,
+	0x00000a2b,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -113,8 +113,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000bb3,
-	0x00000b8c,
+	0x00000bb1,
+	0x00000b8a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -135,8 +135,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000bbf,
 	0x00000bbd,
+	0x00000bbb,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -237,19 +237,19 @@ static uint32_t gf100_pmu_data[] = {
 	0x000005d3,
 	0x00000003,
 	0x00000002,
-	0x0000069d,
+	0x0000069b,
 	0x00040004,
 	0x00000000,
-	0x000006b9,
+	0x000006b7,
 	0x00010005,
 	0x00000000,
-	0x000006d6,
+	0x000006d4,
 	0x00010006,
 	0x00000000,
 	0x0000065b,
 	0x00000007,
 	0x00000000,
-	0x000006e1,
+	0x000006df,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1373,432 +1373,432 @@ static uint32_t gf100_pmu_code[] = {
 /* 0x065b: memx_func_wait_vblank */
 	0x9800f840,
 	0x66b00016,
-	0x130bf400,
+	0x120bf400,
 	0xf40166b0,
 	0x0ef4060b,
 /* 0x066d: memx_func_wait_vblank_head1 */
-	0x2077f12e,
-	0x070ef400,
-/* 0x0674: memx_func_wait_vblank_head0 */
-	0x000877f1,
-/* 0x0678: memx_func_wait_vblank_0 */
-	0x07c467f1,
-	0xcf0664b6,
-	0x67fd0066,
-	0xf31bf404,
-/* 0x0688: memx_func_wait_vblank_1 */
-	0x07c467f1,
-	0xcf0664b6,
-	0x67fd0066,
-	0xf30bf404,
-/* 0x0698: memx_func_wait_vblank_fini */
-	0xf80410b6,
-/* 0x069d: memx_func_wr32 */
-	0x00169800,
-	0xb6011598,
-	0x60f90810,
-	0xd0fc50f9,
-	0x21f4e0fc,
-	0x0242b640,
-	0xf8e91bf4,
-/* 0x06b9: memx_func_wait */
-	0x2c87f000,
-	0xcf0684b6,
-	0x1e980088,
-	0x011d9800,
-	0x98021c98,
-	0x10b6031b,
-	0xa321f410,
-/* 0x06d6: memx_func_delay */
-	0x1e9800f8,
-	0x0410b600,
-	0xf87e21f4,
-/* 0x06e1: memx_func_train */
-/* 0x06e3: memx_exec */
-	0xf900f800,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x06ed: memx_exec_next */
-	0x00139802,
-	0xe70410b6,
-	0xe701f034,
-	0xb601e033,
-	0x30f00132,
-	0xde35980c,
-	0x12b855f9,
-	0xe41ef406,
-	0x98f10b98,
-	0xcbbbf20c,
-	0xc4b7f102,
-	0x06b4b607,
-	0xfc00bbcf,
-	0xf5e0fcd0,
-	0xf8033621,
-/* 0x0729: memx_info */
-	0x01c67000,
-/* 0x072f: memx_info_data */
-	0xf10e0bf4,
-	0xf103ccc7,
-	0xf40800b7,
-/* 0x073a: memx_info_train */
-	0xc7f10b0e,
-	0xb7f10bcc,
-/* 0x0742: memx_info_send */
-	0x21f50100,
-	0x00f80336,
-/* 0x0748: memx_recv */
-	0xf401d6b0,
-	0xd6b0980b,
-	0xd80bf400,
-/* 0x0756: memx_init */
-	0x00f800f8,
-/* 0x0758: perf_recv */
-/* 0x075a: perf_init */
+	0x2077f02c,
+/* 0x0673: memx_func_wait_vblank_head0 */
+	0xf0060ef4,
+/* 0x0676: memx_func_wait_vblank_0 */
+	0x67f10877,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x0686: memx_func_wait_vblank_1 */
+	0x67f1f31b,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x0696: memx_func_wait_vblank_fini */
+	0x10b6f30b,
+/* 0x069b: memx_func_wr32 */
+	0x9800f804,
+	0x15980016,
+	0x0810b601,
+	0x50f960f9,
+	0xe0fcd0fc,
+	0xb64021f4,
+	0x1bf40242,
+/* 0x06b7: memx_func_wait */
+	0xf000f8e9,
+	0x84b62c87,
+	0x0088cf06,
+	0x98001e98,
+	0x1c98011d,
+	0x031b9802,
+	0xf41010b6,
+	0x00f8a321,
+/* 0x06d4: memx_func_delay */
+	0xb6001e98,
+	0x21f40410,
+/* 0x06df: memx_func_train */
+	0xf800f87e,
+/* 0x06e1: memx_exec */
+	0xf9e0f900,
+	0x02c1b9d0,
+/* 0x06eb: memx_exec_next */
+	0x9802b2b9,
+	0x10b60013,
+	0xf034e704,
+	0xe033e701,
+	0x0132b601,
+	0x980c30f0,
+	0x55f9de35,
+	0xf40612b8,
+	0x0b98e41e,
+	0xf20c98f1,
+	0xf102cbbb,
+	0xb607c4b7,
+	0xbbcf06b4,
+	0xfcd0fc00,
+	0x3621f5e0,
+/* 0x0727: memx_info */
+	0x7000f803,
+	0x0bf401c6,
+/* 0x072d: memx_info_data */
+	0xccc7f10e,
+	0x00b7f103,
+	0x0b0ef408,
+/* 0x0738: memx_info_train */
+	0x0bccc7f1,
+	0x0100b7f1,
+/* 0x0740: memx_info_send */
+	0x033621f5,
+/* 0x0746: memx_recv */
+	0xd6b000f8,
+	0x980bf401,
+	0xf400d6b0,
+	0x00f8d80b,
+/* 0x0754: memx_init */
+/* 0x0756: perf_recv */
 	0x00f800f8,
-/* 0x075c: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x0770: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x077e: i2c_drive_sda */
+/* 0x0758: perf_init */
+/* 0x075a: i2c_drive_scl */
 	0x36b000f8,
 	0x110bf400,
 	0x07e007f1,
 	0xd00604b6,
-	0x04bd0002,
-/* 0x0792: i2c_drive_sda_lo */
+	0x04bd0001,
+/* 0x076e: i2c_drive_scl_lo */
 	0x07f100f8,
 	0x04b607e4,
+	0x0001d006,
+	0x00f804bd,
+/* 0x077c: i2c_drive_sda */
+	0xf40036b0,
+	0x07f1110b,
+	0x04b607e0,
 	0x0002d006,
 	0x00f804bd,
-/* 0x07a0: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x07b6: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x07b8: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x07ce: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x07d0: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x5c21f501,
-/* 0x07dd: i2c_raise_scl_wait */
-	0xe8e7f107,
-	0x7e21f403,
-	0x07a021f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x07f1: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x07f5: i2c_start */
-	0xa021f500,
-	0x0d11f407,
-	0x07b821f5,
-	0xf40611f4,
-/* 0x0806: i2c_start_rep */
-	0x37f0300e,
-	0x5c21f500,
-	0x0137f007,
-	0x077e21f5,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xd021f550,
-	0x0464b607,
-/* 0x0833: i2c_start_send */
-	0xf01f11f4,
+/* 0x0790: i2c_drive_sda_lo */
+	0x07e407f1,
+	0xd00604b6,
+	0x04bd0002,
+/* 0x079e: i2c_sense_scl */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40431,
+	0x0131f406,
+/* 0x07b4: i2c_sense_scl_done */
+/* 0x07b6: i2c_sense_sda */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40432,
+	0x0131f406,
+/* 0x07cc: i2c_sense_sda_done */
+/* 0x07ce: i2c_raise_scl */
+	0x40f900f8,
+	0x089847f1,
+	0xf50137f0,
+/* 0x07db: i2c_raise_scl_wait */
+	0xf1075a21,
+	0xf403e8e7,
+	0x21f57e21,
+	0x01f4079e,
+	0x0142b609,
+/* 0x07ef: i2c_raise_scl_done */
+	0xfcef1bf4,
+/* 0x07f3: i2c_start */
+	0xf500f840,
+	0xf4079e21,
+	0x21f50d11,
+	0x11f407b6,
+	0x300ef406,
+/* 0x0804: i2c_start_rep */
+	0xf50037f0,
+	0xf0075a21,
+	0x21f50137,
+	0x76bb077c,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb607ce21,
+	0x11f40464,
+/* 0x0831: i2c_start_send */
+	0x0037f01f,
+	0x077c21f5,
+	0x1388e7f1,
+	0xf07e21f4,
 	0x21f50037,
-	0xe7f1077e,
+	0xe7f1075a,
 	0x21f41388,
-	0x0037f07e,
-	0x075c21f5,
-	0x1388e7f1,
-/* 0x084f: i2c_start_out */
-	0xf87e21f4,
-/* 0x0851: i2c_stop */
-	0x0037f000,
-	0x075c21f5,
-	0xf50037f0,
-	0xf1077e21,
-	0xf403e8e7,
-	0x37f07e21,
-	0x5c21f501,
-	0x88e7f107,
-	0x7e21f413,
+/* 0x084d: i2c_start_out */
+/* 0x084f: i2c_stop */
+	0xf000f87e,
+	0x21f50037,
+	0x37f0075a,
+	0x7c21f500,
+	0xe8e7f107,
+	0x7e21f403,
 	0xf50137f0,
-	0xf1077e21,
+	0xf1075a21,
 	0xf41388e7,
-	0x00f87e21,
-/* 0x0884: i2c_bitw */
-	0x077e21f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x07d021f5,
-	0xf40464b6,
-	0xe7f11811,
-	0x21f41388,
-	0x0037f07e,
-	0x075c21f5,
-	0x1388e7f1,
-/* 0x08c3: i2c_bitw_out */
-	0xf87e21f4,
-/* 0x08c5: i2c_bitr */
-	0x0137f000,
-	0x077e21f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x07d021f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f007b8,
-	0x5c21f500,
+	0x37f07e21,
+	0x7c21f501,
 	0x88e7f107,
 	0x7e21f413,
-	0xf4013cf0,
-/* 0x090a: i2c_bitr_done */
-	0x00f80131,
-/* 0x090c: i2c_get_byte */
-	0xf00057f0,
-/* 0x0912: i2c_get_byte_next */
-	0x54b60847,
-	0x0076bb01,
+/* 0x0882: i2c_bitw */
+	0x21f500f8,
+	0xe7f1077c,
+	0x21f403e8,
+	0x0076bb7e,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b608c5,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x8421f550,
-	0x0464b608,
-/* 0x095c: i2c_get_byte_done */
-/* 0x095e: i2c_put_byte */
-	0x47f000f8,
-/* 0x0961: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
+	0x64b607ce,
+	0x1811f404,
+	0x1388e7f1,
+	0xf07e21f4,
+	0x21f50037,
+	0xe7f1075a,
+	0x21f41388,
+/* 0x08c1: i2c_bitw_out */
+/* 0x08c3: i2c_bitr */
+	0xf000f87e,
+	0x21f50137,
+	0xe7f1077c,
+	0x21f403e8,
+	0x0076bb7e,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b607ce,
+	0x1b11f404,
+	0x07b621f5,
+	0xf50037f0,
+	0xf1075a21,
+	0xf41388e7,
+	0x3cf07e21,
+	0x0131f401,
+/* 0x0908: i2c_bitr_done */
+/* 0x090a: i2c_get_byte */
+	0x57f000f8,
+	0x0847f000,
+/* 0x0910: i2c_get_byte_next */
+	0xbb0154b6,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x088421f5,
+	0x08c321f5,
 	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xc521f550,
-	0x0464b608,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x09b7: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x09b9: i2c_addr */
-	0x0076bb00,
+	0x53fd2b11,
+	0x0142b605,
+	0xf0d81bf4,
+	0x76bb0137,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb6088221,
+/* 0x095a: i2c_get_byte_done */
+	0x00f80464,
+/* 0x095c: i2c_put_byte */
+/* 0x095f: i2c_put_byte_next */
+	0xb60847f0,
+	0x54ff0142,
+	0x0076bb38,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b607f5,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b60882,
+	0x3411f404,
+	0xf40046b0,
+	0x76bbd81b,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6095e21,
-/* 0x09fe: i2c_addr_done */
-	0x00f80464,
-/* 0x0a00: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980d1c,
-/* 0x0a0f: i2c_acquire */
-	0xf500f800,
-	0xf40a0021,
-	0xd9f00421,
-	0x4021f403,
-/* 0x0a1e: i2c_release */
-	0x21f500f8,
-	0x21f40a00,
-	0x03daf004,
-	0xf84021f4,
-/* 0x0a2d: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xf413a001,
-	0x0032980c,
-	0x0ccc13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb608c321,
+	0x11f40464,
+	0x0076bb0f,
+	0xf40136b0,
+	0x32f4061b,
+/* 0x09b5: i2c_put_byte_done */
+/* 0x09b7: i2c_addr */
+	0xbb00f801,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0a0f21f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x09b921f5,
-	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
-	0x0465b600,
-	0x659450f9,
-	0x0256bb04,
-	0x75fd50bd,
-	0xf550fc04,
-	0xb6095e21,
-	0x11f50464,
-	0x57f000ad,
+	0x07f321f5,
+	0xf40464b6,
+	0xc3e72911,
+	0x34b6012e,
+	0x0553fd01,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x5c21f550,
+	0x0464b609,
+/* 0x09fc: i2c_addr_done */
+/* 0x09fe: i2c_acquire_addr */
+	0xcec700f8,
+	0x02e4b6f8,
+	0x0d1ce0b7,
+	0xf800ee98,
+/* 0x0a0d: i2c_acquire */
+	0xfe21f500,
+	0x0421f409,
+	0xf403d9f0,
+	0x00f84021,
+/* 0x0a1c: i2c_release */
+	0x09fe21f5,
+	0xf00421f4,
+	0x21f403da,
+/* 0x0a2b: i2c_recv */
+	0xf400f840,
+	0xc1c70132,
+	0x0214b6f8,
+	0xf52816b0,
+	0xa0013a1f,
+	0x980cf413,
+	0x13a00032,
+	0x31980ccc,
+	0x0231f400,
+	0xe0f9d0f9,
+	0x67f1d0f9,
+	0x63f10000,
+	0x67921000,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b609b9,
-	0x8a11f504,
+	0x64b60a0d,
+	0xb0d0fc04,
+	0x1bf500d6,
+	0x57f000b3,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b6090c,
-	0x6a11f404,
-	0xbbe05bcb,
+	0x64b609b7,
+	0xd011f504,
+	0xe0c5c700,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x5c21f550,
+	0x0464b609,
+	0x00ad11f5,
+	0xbb0157f0,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x085121f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x0b33: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x09b921f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f4095e,
-	0x0057f029,
-	0x09b921f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f4095e,
-	0x5121f515,
-	0xc774bd08,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x0b73: i2c_recv_not_wr08 */
-/* 0x0b73: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc0a1e,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x033621f5,
-/* 0x0b88: i2c_recv_exit */
-/* 0x0b8a: i2c_init */
-	0x00f800f8,
-/* 0x0b8c: test_recv */
-	0x05d817f1,
+	0x09b721f5,
+	0xf50464b6,
+	0xbb008a11,
+	0x65b60076,
+	0x9450f904,
+	0x56bb0465,
+	0xfd50bd02,
+	0x50fc0475,
+	0x090a21f5,
+	0xf40464b6,
+	0x5bcb6a11,
+	0x0076bbe0,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b6084f,
+	0x025bb904,
+	0x0ef474bd,
+/* 0x0b31: i2c_recv_not_rd08 */
+	0x01d6b043,
+	0xf03d1bf4,
+	0x21f50057,
+	0x11f409b7,
+	0xe0c5c733,
+	0x095c21f5,
+	0xf02911f4,
+	0x21f50057,
+	0x11f409b7,
+	0xe0b5c71f,
+	0x095c21f5,
+	0xf51511f4,
+	0xbd084f21,
+	0x08c5c774,
+	0xf4091bf4,
+	0x0ef40232,
+/* 0x0b71: i2c_recv_not_wr08 */
+/* 0x0b71: i2c_recv_done */
+	0xf8cec703,
+	0x0a1c21f5,
+	0xd0fce0fc,
+	0xb90a12f4,
+	0x21f5027c,
+/* 0x0b86: i2c_recv_exit */
+	0x00f80336,
+/* 0x0b88: i2c_init */
+/* 0x0b8a: test_recv */
+	0x17f100f8,
+	0x14b605d8,
+	0x0011cf06,
+	0xf10110b6,
+	0xb605d807,
+	0x01d00604,
+	0xf104bd00,
+	0xf1d900e7,
+	0xf5134fe3,
+	0xf8025621,
+/* 0x0bb1: test_init */
+	0x00e7f100,
+	0x5621f508,
+/* 0x0bbb: idle_recv */
+	0xf800f802,
+/* 0x0bbd: idle */
+	0x0031f400,
+	0x05d417f1,
 	0xcf0614b6,
 	0x10b60011,
-	0xd807f101,
+	0xd407f101,
 	0x0604b605,
 	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0x5621f513,
-/* 0x0bb3: test_init */
-	0xf100f802,
-	0xf50800e7,
-	0xf8025621,
-/* 0x0bbd: idle_recv */
-/* 0x0bbf: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x0bdb: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x0be1: idle_proc */
-/* 0x0be1: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc033f,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0bf5: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
+/* 0x0bd9: idle_loop */
+	0x5817f004,
+/* 0x0bdf: idle_proc */
+/* 0x0bdf: idle_proc_exec */
+	0xf90232f4,
+	0x021eb910,
+	0x033f21f5,
+	0x11f410fc,
+	0x0231f409,
+/* 0x0bf3: idle_proc_next */
+	0xb6ef0ef4,
+	0x1fb85810,
+	0xe61bf406,
+	0xf4dd02f4,
+	0x0ef40028,
+	0x000000bb,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
index c4edbc79e41a..e0222cb832fb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
@@ -47,8 +47,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x000005f3,
-	0x000005e5,
+	0x000005ee,
+	0x000005e0,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -69,8 +69,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x000005f7,
-	0x000005f5,
+	0x000005f2,
+	0x000005f0,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -91,8 +91,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x000009f8,
-	0x000008a2,
+	0x000009f3,
+	0x0000089d,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -113,8 +113,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000a16,
-	0x000009fa,
+	0x00000a11,
+	0x000009f5,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -135,8 +135,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000a21,
-	0x00000a1f,
+	0x00000a1c,
+	0x00000a1a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -234,22 +234,22 @@ static uint32_t gk208_pmu_data[] = {
 /* 0x037c: memx_func_next */
 	0x00000002,
 	0x00000000,
-	0x000004cf,
+	0x000004cc,
 	0x00000003,
 	0x00000002,
-	0x00000546,
+	0x00000541,
 	0x00040004,
 	0x00000000,
-	0x00000563,
+	0x0000055e,
 	0x00010005,
 	0x00000000,
-	0x0000057d,
+	0x00000578,
 	0x00010006,
 	0x00000000,
-	0x00000541,
+	0x0000053c,
 	0x00000007,
 	0x00000000,
-	0x00000589,
+	0x00000584,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1239,454 +1239,454 @@ static uint32_t gk208_pmu_code[] = {
 	0x0001f604,
 	0x00f804bd,
 /* 0x045c: memx_func_enter */
-	0x162067f1,
-	0xf55d77f1,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90487fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0x0700002d,
-	0x7e6eb2fe,
+	0x47162046,
+	0x6eb2f55d,
+	0x0000047e,
+	0x87fdd8b2,
+	0xf960f904,
+	0xfcd0fc80,
+	0x002d7ee0,
+	0xb2fe0700,
+	0x00047e6e,
+	0xfdd8b200,
+	0x60f90487,
+	0xd0fc80f9,
+	0x2d7ee0fc,
+	0xf0460000,
+	0x7e6eb226,
 	0xb2000004,
 	0x0487fdd8,
 	0x80f960f9,
 	0xe0fcd0fc,
 	0x00002d7e,
-	0x26f067f1,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90487fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0x0600002d,
-	0x07e04004,
-	0xbd0006f6,
-/* 0x04b9: memx_func_enter_wait */
-	0x07c04604,
-	0xf00066cf,
-	0x0bf40464,
-	0xcf2c06f7,
-	0x06b50066,
-/* 0x04cf: memx_func_leave */
-	0x0600f8f1,
-	0x0066cf2c,
-	0x06f206b5,
-	0x07e44004,
-	0xbd0006f6,
-/* 0x04e1: memx_func_leave_wait */
-	0x07c04604,
-	0xf00066cf,
-	0x1bf40464,
-	0xf067f1f7,
+	0xe0400406,
+	0x0006f607,
+/* 0x04b6: memx_func_enter_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0x2c06f70b,
+	0xb50066cf,
+	0x00f8f106,
+/* 0x04cc: memx_func_leave */
+	0x66cf2c06,
+	0xf206b500,
+	0xe4400406,
+	0x0006f607,
+/* 0x04de: memx_func_leave_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0xf046f71b,
 	0xb2010726,
 	0x00047e6e,
 	0xfdd8b200,
 	0x60f90587,
 	0xd0fc80f9,
 	0x2d7ee0fc,
-	0x67f10000,
-	0x6eb21620,
-	0x0000047e,
-	0x87fdd8b2,
-	0xf960f905,
-	0xfcd0fc80,
-	0x002d7ee0,
-	0x0aa24700,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90587fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0xf800002d,
-/* 0x0541: memx_func_wait_vblank */
+	0x20460000,
+	0x7e6eb216,
+	0xb2000004,
+	0x0587fdd8,
+	0x80f960f9,
+	0xe0fcd0fc,
+	0x00002d7e,
+	0xb20aa247,
+	0x00047e6e,
+	0xfdd8b200,
+	0x60f90587,
+	0xd0fc80f9,
+	0x2d7ee0fc,
+	0x00f80000,
+/* 0x053c: memx_func_wait_vblank */
+	0xf80410b6,
+/* 0x0541: memx_func_wr32 */
+	0x00169800,
+	0xb6011598,
+	0x60f90810,
+	0xd0fc50f9,
+	0x2d7ee0fc,
+	0x42b60000,
+	0xe81bf402,
+/* 0x055e: memx_func_wait */
+	0x2c0800f8,
+	0x980088cf,
+	0x1d98001e,
+	0x021c9801,
+	0xb6031b98,
+	0x747e1010,
+	0x00f80000,
+/* 0x0578: memx_func_delay */
+	0xb6001e98,
+	0x587e0410,
+	0x00f80000,
+/* 0x0584: memx_func_train */
+/* 0x0586: memx_exec */
+	0xe0f900f8,
+	0xc1b2d0f9,
+/* 0x058e: memx_exec_next */
+	0x1398b2b2,
 	0x0410b600,
-/* 0x0546: memx_func_wr32 */
-	0x169800f8,
-	0x01159800,
-	0xf90810b6,
-	0xfc50f960,
+	0x01f034e7,
+	0x01e033e7,
+	0xf00132b6,
+	0x35980c30,
+	0xa655f9de,
+	0xe51ef412,
+	0x98f10b98,
+	0xcbbbf20c,
+	0x07c44b02,
+	0xfc00bbcf,
 	0x7ee0fcd0,
-	0xb600002d,
-	0x1bf40242,
-/* 0x0563: memx_func_wait */
-	0x0800f8e8,
-	0x0088cf2c,
-	0x98001e98,
-	0x1c98011d,
-	0x031b9802,
-	0x7e1010b6,
-	0xf8000074,
-/* 0x057d: memx_func_delay */
-	0x001e9800,
-	0x7e0410b6,
-	0xf8000058,
-/* 0x0589: memx_func_train */
-/* 0x058b: memx_exec */
-	0xf900f800,
-	0xb2d0f9e0,
-/* 0x0593: memx_exec_next */
-	0x98b2b2c1,
-	0x10b60013,
-	0xf034e704,
-	0xe033e701,
-	0x0132b601,
-	0x980c30f0,
-	0x55f9de35,
-	0x1ef412a6,
-	0xf10b98e5,
-	0xbbf20c98,
-	0xc44b02cb,
-	0x00bbcf07,
-	0xe0fcd0fc,
-	0x00029f7e,
-/* 0x05ca: memx_info */
-	0xc67000f8,
-	0x0c0bf401,
-/* 0x05d0: memx_info_data */
-	0x4b03cc4c,
-	0x0ef40800,
-/* 0x05d9: memx_info_train */
-	0x0bcc4c09,
-/* 0x05df: memx_info_send */
-	0x7e01004b,
 	0xf800029f,
-/* 0x05e5: memx_recv */
-	0x01d6b000,
-	0xb0a30bf4,
-	0x0bf400d6,
-/* 0x05f3: memx_init */
-	0xf800f8dc,
-/* 0x05f5: perf_recv */
-/* 0x05f7: perf_init */
-	0xf800f800,
-/* 0x05f9: i2c_drive_scl */
-	0x0036b000,
-	0x400d0bf4,
-	0x01f607e0,
-	0xf804bd00,
-/* 0x0609: i2c_drive_scl_lo */
-	0x07e44000,
-	0xbd0001f6,
-/* 0x0613: i2c_drive_sda */
-	0xb000f804,
-	0x0bf40036,
-	0x07e0400d,
-	0xbd0002f6,
-/* 0x0623: i2c_drive_sda_lo */
-	0x4000f804,
-	0x02f607e4,
-	0xf804bd00,
-/* 0x062d: i2c_sense_scl */
-	0x0132f400,
-	0xcf07c443,
-	0x31fd0033,
-	0x060bf404,
-/* 0x063f: i2c_sense_scl_done */
-	0xf80131f4,
-/* 0x0641: i2c_sense_sda */
-	0x0132f400,
-	0xcf07c443,
-	0x32fd0033,
-	0x060bf404,
-/* 0x0653: i2c_sense_sda_done */
-	0xf80131f4,
-/* 0x0655: i2c_raise_scl */
-	0x4440f900,
-	0x01030898,
-	0x0005f97e,
-/* 0x0660: i2c_raise_scl_wait */
-	0x7e03e84e,
-	0x7e000058,
-	0xf400062d,
-	0x42b60901,
-	0xef1bf401,
-/* 0x0674: i2c_raise_scl_done */
-	0x00f840fc,
-/* 0x0678: i2c_start */
-	0x00062d7e,
-	0x7e0d11f4,
-	0xf4000641,
-	0x0ef40611,
-/* 0x0689: i2c_start_rep */
-	0x7e00032e,
-	0x030005f9,
-	0x06137e01,
+/* 0x05c5: memx_info */
+	0x01c67000,
+/* 0x05cb: memx_info_data */
+	0x4c0c0bf4,
+	0x004b03cc,
+	0x090ef408,
+/* 0x05d4: memx_info_train */
+	0x4b0bcc4c,
+/* 0x05da: memx_info_send */
+	0x9f7e0100,
+	0x00f80002,
+/* 0x05e0: memx_recv */
+	0xf401d6b0,
+	0xd6b0a30b,
+	0xdc0bf400,
+/* 0x05ee: memx_init */
+	0x00f800f8,
+/* 0x05f0: perf_recv */
+/* 0x05f2: perf_init */
+	0x00f800f8,
+/* 0x05f4: i2c_drive_scl */
+	0xf40036b0,
+	0xe0400d0b,
+	0x0001f607,
+	0x00f804bd,
+/* 0x0604: i2c_drive_scl_lo */
+	0xf607e440,
+	0x04bd0001,
+/* 0x060e: i2c_drive_sda */
+	0x36b000f8,
+	0x0d0bf400,
+	0xf607e040,
+	0x04bd0002,
+/* 0x061e: i2c_drive_sda_lo */
+	0xe44000f8,
+	0x0002f607,
+	0x00f804bd,
+/* 0x0628: i2c_sense_scl */
+	0x430132f4,
+	0x33cf07c4,
+	0x0431fd00,
+	0xf4060bf4,
+/* 0x063a: i2c_sense_scl_done */
+	0x00f80131,
+/* 0x063c: i2c_sense_sda */
+	0x430132f4,
+	0x33cf07c4,
+	0x0432fd00,
+	0xf4060bf4,
+/* 0x064e: i2c_sense_sda_done */
+	0x00f80131,
+/* 0x0650: i2c_raise_scl */
+	0x984440f9,
+	0x7e010308,
+/* 0x065b: i2c_raise_scl_wait */
+	0x4e0005f4,
+	0x587e03e8,
+	0x287e0000,
+	0x01f40006,
+	0x0142b609,
+/* 0x066f: i2c_raise_scl_done */
+	0xfcef1bf4,
+/* 0x0673: i2c_start */
+	0x7e00f840,
+	0xf4000628,
+	0x3c7e0d11,
+	0x11f40006,
+	0x2e0ef406,
+/* 0x0684: i2c_start_rep */
+	0xf47e0003,
+	0x01030005,
+	0x00060e7e,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x06507e50,
+	0x0464b600,
+/* 0x06af: i2c_start_send */
+	0x031d11f4,
+	0x060e7e00,
+	0x13884e00,
+	0x0000587e,
+	0xf47e0003,
+	0x884e0005,
+	0x00587e13,
+/* 0x06c9: i2c_start_out */
+/* 0x06cb: i2c_stop */
+	0x0300f800,
+	0x05f47e00,
+	0x7e000300,
+	0x4e00060e,
+	0x587e03e8,
+	0x01030000,
+	0x0005f47e,
+	0x7e13884e,
+	0x03000058,
+	0x060e7e01,
+	0x13884e00,
+	0x0000587e,
+/* 0x06fa: i2c_bitw */
+	0x0e7e00f8,
+	0xe84e0006,
+	0x00587e03,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x557e50fc,
+	0x507e50fc,
 	0x64b60006,
-	0x1d11f404,
-/* 0x06b4: i2c_start_send */
-	0x137e0003,
-	0x884e0006,
-	0x00587e13,
-	0x7e000300,
-	0x4e0005f9,
-	0x587e1388,
-/* 0x06ce: i2c_start_out */
-	0x00f80000,
-/* 0x06d0: i2c_stop */
-	0xf97e0003,
-	0x00030005,
-	0x0006137e,
-	0x7e03e84e,
+	0x1711f404,
+	0x7e13884e,
 	0x03000058,
-	0x05f97e01,
+	0x05f47e00,
 	0x13884e00,
 	0x0000587e,
-	0x137e0103,
-	0x884e0006,
-	0x00587e13,
-/* 0x06ff: i2c_bitw */
-	0x7e00f800,
-	0x4e000613,
-	0x587e03e8,
-	0x76bb0000,
+/* 0x0738: i2c_bitw_out */
+/* 0x073a: i2c_bitr */
+	0x010300f8,
+	0x00060e7e,
+	0x7e03e84e,
+	0xbb000058,
+	0x65b60076,
+	0x9450f904,
+	0x56bb0465,
+	0xfd50bd02,
+	0x50fc0475,
+	0x0006507e,
+	0xf40464b6,
+	0x3c7e1a11,
+	0x00030006,
+	0x0005f47e,
+	0x7e13884e,
+	0xf0000058,
+	0x31f4013c,
+/* 0x077d: i2c_bitr_done */
+/* 0x077f: i2c_get_byte */
+	0x0500f801,
+/* 0x0783: i2c_get_byte_next */
+	0xb6080400,
+	0x76bb0154,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb6000655,
+	0xb600073a,
 	0x11f40464,
-	0x13884e17,
-	0x0000587e,
-	0xf97e0003,
-	0x884e0005,
-	0x00587e13,
-/* 0x073d: i2c_bitw_out */
-/* 0x073f: i2c_bitr */
-	0x0300f800,
-	0x06137e01,
-	0x03e84e00,
-	0x0000587e,
+	0x0553fd2a,
+	0xf40142b6,
+	0x0103d81b,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x06557e50,
+	0x06fa7e50,
 	0x0464b600,
-	0x7e1a11f4,
-	0x03000641,
-	0x05f97e00,
-	0x13884e00,
-	0x0000587e,
-	0xf4013cf0,
-/* 0x0782: i2c_bitr_done */
-	0x00f80131,
-/* 0x0784: i2c_get_byte */
-	0x08040005,
-/* 0x0788: i2c_get_byte_next */
-	0xbb0154b6,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x00073f7e,
-	0xf40464b6,
-	0x53fd2a11,
-	0x0142b605,
-	0x03d81bf4,
-	0x0076bb01,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0xff7e50fc,
-	0x64b60006,
-/* 0x07d1: i2c_get_byte_done */
-/* 0x07d3: i2c_put_byte */
-	0x0400f804,
-/* 0x07d5: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
+/* 0x07cc: i2c_get_byte_done */
+/* 0x07ce: i2c_put_byte */
+	0x080400f8,
+/* 0x07d0: i2c_put_byte_next */
+	0xff0142b6,
+	0x76bb3854,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb60006fa,
+	0x11f40464,
+	0x0046b034,
+	0xbbd81bf4,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0006ff7e,
+	0x00073a7e,
 	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
+	0x76bb0f11,
+	0x0136b000,
+	0xf4061bf4,
+/* 0x0826: i2c_put_byte_done */
+	0x00f80132,
+/* 0x0828: i2c_addr */
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x073f7e50,
+	0x06737e50,
 	0x0464b600,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x082b: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x082d: i2c_addr */
-	0x0076bb00,
+	0xe72911f4,
+	0xb6012ec3,
+	0x53fd0134,
+	0x0076bb05,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x787e50fc,
-	0x64b60006,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
-	0x0465b600,
-	0x659450f9,
-	0x0256bb04,
-	0x75fd50bd,
-	0x7e50fc04,
-	0xb60007d3,
-/* 0x0872: i2c_addr_done */
-	0x00f80464,
-/* 0x0874: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b705e4,
-	0x00f8d014,
-/* 0x0880: i2c_acquire */
-	0x0008747e,
+	0xce7e50fc,
+	0x64b60007,
+/* 0x086d: i2c_addr_done */
+/* 0x086f: i2c_acquire_addr */
+	0xc700f804,
+	0xe4b6f8ce,
+	0x14e0b705,
+/* 0x087b: i2c_acquire */
+	0x7e00f8d0,
+	0x7e00086f,
+	0xf0000004,
+	0x2d7e03d9,
+	0x00f80000,
+/* 0x088c: i2c_release */
+	0x00086f7e,
 	0x0000047e,
-	0x7e03d9f0,
+	0x7e03daf0,
 	0xf800002d,
-/* 0x0891: i2c_release */
-	0x08747e00,
-	0x00047e00,
-	0x03daf000,
-	0x00002d7e,
-/* 0x08a2: i2c_recv */
-	0x32f400f8,
-	0xf8c1c701,
-	0xb00214b6,
-	0x1ff52816,
-	0x13b80134,
-	0x98000cf4,
-	0x13b80032,
-	0x98000ccc,
-	0x31f40031,
-	0xf9d0f902,
-	0xd6d0f9e0,
-	0x10000000,
-	0xbb016792,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x0008807e,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b01bf5,
-	0x76bb0005,
+/* 0x089d: i2c_recv */
+	0x0132f400,
+	0xb6f8c1c7,
+	0x16b00214,
+	0x341ff528,
+	0xf413b801,
+	0x3298000c,
+	0xcc13b800,
+	0x3198000c,
+	0x0231f400,
+	0xe0f9d0f9,
+	0x00d6d0f9,
+	0x92100000,
+	0x76bb0167,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb600082d,
-	0x11f50464,
-	0xc5c700cc,
-	0x0076bbe0,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0xd37e50fc,
-	0x64b60007,
-	0xa911f504,
-	0xbb010500,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x00082d7e,
-	0xf50464b6,
-	0xbb008711,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x0007847e,
-	0xf40464b6,
-	0x5bcb6711,
-	0x0076bbe0,
+	0xb600087b,
+	0xd0fc0464,
+	0xf500d6b0,
+	0x0500b01b,
+	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0xd07e50fc,
-	0x64b60006,
-	0xbd5bb204,
-	0x410ef474,
-/* 0x09a4: i2c_recv_not_rd08 */
-	0xf401d6b0,
-	0x00053b1b,
-	0x00082d7e,
-	0xc73211f4,
-	0xd37ee0c5,
-	0x11f40007,
-	0x7e000528,
-	0xf400082d,
-	0xb5c71f11,
-	0x07d37ee0,
-	0x1511f400,
-	0x0006d07e,
-	0xc5c774bd,
-	0x091bf408,
-	0xf40232f4,
-/* 0x09e2: i2c_recv_not_wr08 */
-/* 0x09e2: i2c_recv_done */
-	0xcec7030e,
-	0x08917ef8,
-	0xfce0fc00,
-	0x0912f4d0,
-	0x9f7e7cb2,
-/* 0x09f6: i2c_recv_exit */
-	0x00f80002,
-/* 0x09f8: i2c_init */
-/* 0x09fa: test_recv */
-	0x584100f8,
-	0x0011cf04,
-	0x400110b6,
-	0x01f60458,
-	0xde04bd00,
-	0x134fd900,
-	0x0001de7e,
-/* 0x0a16: test_init */
-	0x004e00f8,
-	0x01de7e08,
-/* 0x0a1f: idle_recv */
+	0x287e50fc,
+	0x64b60008,
+	0xcc11f504,
+	0xe0c5c700,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x07ce7e50,
+	0x0464b600,
+	0x00a911f5,
+	0x76bb0105,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb6000828,
+	0x11f50464,
+	0x76bb0087,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb600077f,
+	0x11f40464,
+	0xe05bcb67,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x06cb7e50,
+	0x0464b600,
+	0x74bd5bb2,
+/* 0x099f: i2c_recv_not_rd08 */
+	0xb0410ef4,
+	0x1bf401d6,
+	0x7e00053b,
+	0xf4000828,
+	0xc5c73211,
+	0x07ce7ee0,
+	0x2811f400,
+	0x287e0005,
+	0x11f40008,
+	0xe0b5c71f,
+	0x0007ce7e,
+	0x7e1511f4,
+	0xbd0006cb,
+	0x08c5c774,
+	0xf4091bf4,
+	0x0ef40232,
+/* 0x09dd: i2c_recv_not_wr08 */
+/* 0x09dd: i2c_recv_done */
+	0xf8cec703,
+	0x00088c7e,
+	0xd0fce0fc,
+	0xb20912f4,
+	0x029f7e7c,
+/* 0x09f1: i2c_recv_exit */
+/* 0x09f3: i2c_init */
 	0xf800f800,
-/* 0x0a21: idle */
-	0x0031f400,
-	0xcf045441,
-	0x10b60011,
-	0x04544001,
-	0xbd0001f6,
-/* 0x0a35: idle_loop */
-	0xf4580104,
-/* 0x0a3a: idle_proc */
-/* 0x0a3a: idle_proc_exec */
-	0x10f90232,
-	0xa87e1eb2,
-	0x10fc0002,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0a4d: idle_proc_next */
-	0x5810b6f0,
-	0x1bf41fa6,
-	0xe002f4e8,
-	0xf40028f4,
-	0x0000c60e,
+/* 0x09f5: test_recv */
+	0x04584100,
+	0xb60011cf,
+	0x58400110,
+	0x0001f604,
+	0x00de04bd,
+	0x7e134fd9,
+	0xf80001de,
+/* 0x0a11: test_init */
+	0x08004e00,
+	0x0001de7e,
+/* 0x0a1a: idle_recv */
+	0x00f800f8,
+/* 0x0a1c: idle */
+	0x410031f4,
+	0x11cf0454,
+	0x0110b600,
+	0xf6045440,
+	0x04bd0001,
+/* 0x0a30: idle_loop */
+	0x32f45801,
+/* 0x0a35: idle_proc */
+/* 0x0a35: idle_proc_exec */
+	0xb210f902,
+	0x02a87e1e,
+	0xf410fc00,
+	0x31f40911,
+	0xf00ef402,
+/* 0x0a48: idle_proc_next */
+	0xa65810b6,
+	0xe81bf41f,
+	0xf4e002f4,
+	0x0ef40028,
+	0x000000c6,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
index 6a2572e8945a..defddf5957ee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
@@ -47,8 +47,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x0000083a,
-	0x0000082c,
+	0x00000833,
+	0x00000825,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -69,8 +69,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x0000083e,
-	0x0000083c,
+	0x00000837,
+	0x00000835,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -91,8 +91,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000c6e,
-	0x00000b11,
+	0x00000c67,
+	0x00000b0a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -113,8 +113,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000c97,
-	0x00000c70,
+	0x00000c90,
+	0x00000c69,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -135,8 +135,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000ca3,
-	0x00000ca1,
+	0x00000c9c,
+	0x00000c9a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -234,22 +234,22 @@ static uint32_t gt215_pmu_data[] = {
 /* 0x037c: memx_func_next */
 	0x00000002,
 	0x00000000,
-	0x000005a0,
+	0x0000059f,
 	0x00000003,
 	0x00000002,
-	0x00000632,
+	0x0000062f,
 	0x00040004,
 	0x00000000,
-	0x0000064e,
+	0x0000064b,
 	0x00010005,
 	0x00000000,
-	0x0000066b,
+	0x00000668,
 	0x00010006,
 	0x00000000,
-	0x000005f0,
+	0x000005ef,
 	0x00000007,
 	0x00000000,
-	0x00000676,
+	0x00000673,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1305,560 +1305,560 @@ static uint32_t gt215_pmu_code[] = {
 	0x67f102d7,
 	0x63f1fffc,
 	0x76fdffff,
-	0x0267f104,
-	0x0576fd00,
-	0x70f980f9,
-	0xe0fcd0fc,
-	0xf04021f4,
+	0x0267f004,
+	0xf90576fd,
+	0xfc70f980,
+	0xf4e0fcd0,
+	0x67f04021,
+	0xe007f104,
+	0x0604b607,
+	0xbd0006d0,
+/* 0x0581: memx_func_enter_wait */
+	0xc067f104,
+	0x0664b607,
+	0xf00066cf,
+	0x0bf40464,
+	0x2c67f0f3,
+	0xcf0664b6,
+	0x06800066,
+/* 0x059f: memx_func_leave */
+	0xf000f8f1,
+	0x64b62c67,
+	0x0066cf06,
+	0xf0f20680,
 	0x07f10467,
-	0x04b607e0,
+	0x04b607e4,
 	0x0006d006,
-/* 0x0582: memx_func_enter_wait */
+/* 0x05ba: memx_func_leave_wait */
 	0x67f104bd,
 	0x64b607c0,
 	0x0066cf06,
 	0xf40464f0,
-	0x67f0f30b,
-	0x0664b62c,
-	0x800066cf,
-	0x00f8f106,
-/* 0x05a0: memx_func_leave */
-	0xb62c67f0,
-	0x66cf0664,
-	0xf2068000,
-	0xf10467f0,
-	0xb607e407,
-	0x06d00604,
-/* 0x05bb: memx_func_leave_wait */
-	0xf104bd00,
-	0xb607c067,
-	0x66cf0664,
-	0x0464f000,
-	0xf1f31bf4,
-	0xb9161087,
-	0x21f4028e,
-	0x02d7b904,
-	0xffcc67f1,
-	0xffff63f1,
-	0xf90476fd,
-	0xfc70f980,
-	0xf4e0fcd0,
-	0x00f84021,
-/* 0x05f0: memx_func_wait_vblank */
-	0xb0001698,
-	0x0bf40066,
-	0x0166b013,
-	0xf4060bf4,
-/* 0x0602: memx_func_wait_vblank_head1 */
-	0x77f12e0e,
-	0x0ef40020,
-/* 0x0609: memx_func_wait_vblank_head0 */
-	0x0877f107,
-/* 0x060d: memx_func_wait_vblank_0 */
-	0xc467f100,
-	0x0664b607,
-	0xfd0066cf,
-	0x1bf40467,
-/* 0x061d: memx_func_wait_vblank_1 */
-	0xc467f1f3,
-	0x0664b607,
-	0xfd0066cf,
-	0x0bf40467,
-/* 0x062d: memx_func_wait_vblank_fini */
-	0x0410b6f3,
-/* 0x0632: memx_func_wr32 */
-	0x169800f8,
-	0x01159800,
-	0xf90810b6,
-	0xfc50f960,
-	0xf4e0fcd0,
-	0x42b64021,
-	0xe91bf402,
-/* 0x064e: memx_func_wait */
-	0x87f000f8,
-	0x0684b62c,
-	0x980088cf,
-	0x1d98001e,
-	0x021c9801,
-	0xb6031b98,
-	0x21f41010,
-/* 0x066b: memx_func_delay */
-	0x9800f8a3,
-	0x10b6001e,
-	0x7e21f404,
-/* 0x0676: memx_func_train */
-	0x57f100f8,
-	0x77f10003,
-	0x97f10000,
-	0x93f00000,
-	0x029eb970,
-	0xb90421f4,
-	0xe7f102d8,
-	0x21f42710,
-/* 0x0695: memx_func_train_loop_outer */
-	0x0158e07e,
-	0x0083f101,
-	0xe097f102,
-	0x1193f011,
-	0x80f990f9,
+	0x87f1f31b,
+	0x8eb91610,
+	0x0421f402,
+	0xf102d7b9,
+	0xf1ffcc67,
+	0xfdffff63,
+	0x80f90476,
+	0xd0fc70f9,
+	0x21f4e0fc,
+/* 0x05ef: memx_func_wait_vblank */
+	0x9800f840,
+	0x66b00016,
+	0x120bf400,
+	0xf40166b0,
+	0x0ef4060b,
+/* 0x0601: memx_func_wait_vblank_head1 */
+	0x2077f02c,
+/* 0x0607: memx_func_wait_vblank_head0 */
+	0xf0060ef4,
+/* 0x060a: memx_func_wait_vblank_0 */
+	0x67f10877,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x061a: memx_func_wait_vblank_1 */
+	0x67f1f31b,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x062a: memx_func_wait_vblank_fini */
+	0x10b6f30b,
+/* 0x062f: memx_func_wr32 */
+	0x9800f804,
+	0x15980016,
+	0x0810b601,
+	0x50f960f9,
 	0xe0fcd0fc,
-	0xf94021f4,
-	0x0067f150,
-/* 0x06b5: memx_func_train_loop_inner */
-	0x1187f100,
-	0x9068ff11,
-	0xfd109894,
-	0x97f10589,
-	0x93f00720,
-	0xf990f910,
-	0xfcd0fc80,
-	0x4021f4e0,
-	0x008097f1,
-	0xb91093f0,
-	0x21f4029e,
-	0x02d8b904,
-	0xf92088c5,
+	0xb64021f4,
+	0x1bf40242,
+/* 0x064b: memx_func_wait */
+	0xf000f8e9,
+	0x84b62c87,
+	0x0088cf06,
+	0x98001e98,
+	0x1c98011d,
+	0x031b9802,
+	0xf41010b6,
+	0x00f8a321,
+/* 0x0668: memx_func_delay */
+	0xb6001e98,
+	0x21f40410,
+/* 0x0673: memx_func_train */
+	0xf000f87e,
+	0x77f00357,
+	0x0097f100,
+	0x7093f000,
+	0xf4029eb9,
+	0xd8b90421,
+	0x10e7f102,
+	0x7e21f427,
+/* 0x0690: memx_func_train_loop_outer */
+	0x010158e0,
+	0x020083f1,
+	0x11e097f1,
+	0xf91193f0,
+	0xfc80f990,
+	0xf4e0fcd0,
+	0x50f94021,
+/* 0x06af: memx_func_train_loop_inner */
+	0xf10067f0,
+	0xff111187,
+	0x98949068,
+	0x0589fd10,
+	0x072097f1,
+	0xf91093f0,
 	0xfc80f990,
 	0xf4e0fcd0,
 	0x97f14021,
-	0x93f0053c,
-	0x0287f110,
-	0x0083f130,
-	0xf990f980,
+	0x93f00080,
+	0x029eb910,
+	0xb90421f4,
+	0x88c502d8,
+	0xf990f920,
 	0xfcd0fc80,
 	0x4021f4e0,
-	0x0560e7f1,
-	0xf110e3f0,
-	0xf10000d7,
-	0x908000d3,
-	0xb7f100dc,
-	0xb3f08480,
-	0xa321f41e,
-	0x000057f1,
-	0xffff97f1,
-	0x830093f1,
-/* 0x0734: memx_func_train_loop_4x */
-	0x0080a7f1,
-	0xb910a3f0,
-	0x21f402ae,
-	0x02d8b904,
-	0xffdfb7f1,
-	0xffffb3f1,
-	0xf9048bfd,
-	0xfc80f9a0,
+	0x053c97f1,
+	0xf11093f0,
+	0xf1300287,
+	0xf9800083,
+	0xfc80f990,
 	0xf4e0fcd0,
-	0xa7f14021,
-	0xa3f0053c,
-	0x0287f110,
-	0x0083f130,
-	0xf9a0f980,
-	0xfcd0fc80,
-	0x4021f4e0,
-	0x0560e7f1,
-	0xf110e3f0,
-	0xf10000d7,
-	0xb98000d3,
-	0xb7f102dc,
-	0xb3f02710,
-	0xa321f400,
-	0xf402eeb9,
-	0xddb90421,
-	0x949dff02,
+	0xe7f14021,
+	0xe3f00560,
+	0x00d7f110,
+	0x00d3f100,
+	0x00dc9080,
+	0x8480b7f1,
+	0xf41eb3f0,
+	0x57f0a321,
+	0xff97f100,
+	0x0093f1ff,
+/* 0x072d: memx_func_train_loop_4x */
+	0x80a7f183,
+	0x10a3f000,
+	0xf402aeb9,
+	0xd8b90421,
+	0xdfb7f102,
+	0xffb3f1ff,
+	0x048bfdff,
+	0x80f9a0f9,
+	0xe0fcd0fc,
+	0xf14021f4,
+	0xf0053ca7,
+	0x87f110a3,
+	0x83f13002,
+	0xa0f98000,
+	0xd0fc80f9,
+	0x21f4e0fc,
+	0x60e7f140,
+	0x10e3f005,
+	0x0000d7f1,
+	0x8000d3f1,
+	0xf102dcb9,
+	0xf02710b7,
+	0x21f400b3,
+	0x02eeb9a3,
+	0xb90421f4,
+	0x9dff02dd,
+	0x0150b694,
+	0xf4045670,
+	0x7aa0921e,
+	0xa9800bcc,
+	0x0160b600,
+	0x700470b6,
+	0x1ef51066,
+	0x50fcff01,
 	0x700150b6,
-	0x1ef40456,
-	0xcc7aa092,
-	0x00a9800b,
-	0xb60160b6,
-	0x66700470,
-	0x001ef510,
-	0xb650fcff,
-	0x56700150,
-	0xd41ef507,
-/* 0x07c7: memx_exec */
-	0xf900f8fe,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x07d1: memx_exec_next */
-	0x00139802,
-	0xe70410b6,
-	0xe701f034,
-	0xb601e033,
-	0x30f00132,
-	0xde35980c,
-	0x12b855f9,
-	0xe41ef406,
-	0x98f10b98,
-	0xcbbbf20c,
-	0xc4b7f102,
-	0x06b4b607,
-	0xfc00bbcf,
-	0xf5e0fcd0,
+	0x1ef50756,
+	0x00f8fed6,
+/* 0x07c0: memx_exec */
+	0xd0f9e0f9,
+	0xb902c1b9,
+/* 0x07ca: memx_exec_next */
+	0x139802b2,
+	0x0410b600,
+	0x01f034e7,
+	0x01e033e7,
+	0xf00132b6,
+	0x35980c30,
+	0xb855f9de,
+	0x1ef40612,
+	0xf10b98e4,
+	0xbbf20c98,
+	0xb7f102cb,
+	0xb4b607c4,
+	0x00bbcf06,
+	0xe0fcd0fc,
+	0x033621f5,
+/* 0x0806: memx_info */
+	0xc67000f8,
+	0x0e0bf401,
+/* 0x080c: memx_info_data */
+	0x03ccc7f1,
+	0x0800b7f1,
+/* 0x0817: memx_info_train */
+	0xf10b0ef4,
+	0xf10bccc7,
+/* 0x081f: memx_info_send */
+	0xf50100b7,
 	0xf8033621,
-/* 0x080d: memx_info */
-	0x01c67000,
-/* 0x0813: memx_info_data */
-	0xf10e0bf4,
-	0xf103ccc7,
-	0xf40800b7,
-/* 0x081e: memx_info_train */
-	0xc7f10b0e,
-	0xb7f10bcc,
-/* 0x0826: memx_info_send */
-	0x21f50100,
-	0x00f80336,
-/* 0x082c: memx_recv */
-	0xf401d6b0,
-	0xd6b0980b,
-	0xd80bf400,
-/* 0x083a: memx_init */
-	0x00f800f8,
-/* 0x083c: perf_recv */
-/* 0x083e: perf_init */
-	0x00f800f8,
-/* 0x0840: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x0854: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x0862: i2c_drive_sda */
-	0x36b000f8,
-	0x110bf400,
-	0x07e007f1,
-	0xd00604b6,
-	0x04bd0002,
-/* 0x0876: i2c_drive_sda_lo */
-	0x07f100f8,
-	0x04b607e4,
-	0x0002d006,
-	0x00f804bd,
-/* 0x0884: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x089a: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x089c: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x08b2: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x08b4: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x4021f501,
-/* 0x08c1: i2c_raise_scl_wait */
+/* 0x0825: memx_recv */
+	0x01d6b000,
+	0xb0980bf4,
+	0x0bf400d6,
+/* 0x0833: memx_init */
+	0xf800f8d8,
+/* 0x0835: perf_recv */
+/* 0x0837: perf_init */
+	0xf800f800,
+/* 0x0839: i2c_drive_scl */
+	0x0036b000,
+	0xf1110bf4,
+	0xb607e007,
+	0x01d00604,
+	0xf804bd00,
+/* 0x084d: i2c_drive_scl_lo */
+	0xe407f100,
+	0x0604b607,
+	0xbd0001d0,
+/* 0x085b: i2c_drive_sda */
+	0xb000f804,
+	0x0bf40036,
+	0xe007f111,
+	0x0604b607,
+	0xbd0002d0,
+/* 0x086f: i2c_drive_sda_lo */
+	0xf100f804,
+	0xb607e407,
+	0x02d00604,
+	0xf804bd00,
+/* 0x087d: i2c_sense_scl */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x31fd0033,
+	0x060bf404,
+/* 0x0893: i2c_sense_scl_done */
+	0xf80131f4,
+/* 0x0895: i2c_sense_sda */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x32fd0033,
+	0x060bf404,
+/* 0x08ab: i2c_sense_sda_done */
+	0xf80131f4,
+/* 0x08ad: i2c_raise_scl */
+	0xf140f900,
+	0xf0089847,
+	0x21f50137,
+/* 0x08ba: i2c_raise_scl_wait */
+	0xe7f10839,
+	0x21f403e8,
+	0x7d21f57e,
+	0x0901f408,
+	0xf40142b6,
+/* 0x08ce: i2c_raise_scl_done */
+	0x40fcef1b,
+/* 0x08d2: i2c_start */
+	0x21f500f8,
+	0x11f4087d,
+	0x9521f50d,
+	0x0611f408,
+/* 0x08e3: i2c_start_rep */
+	0xf0300ef4,
+	0x21f50037,
+	0x37f00839,
+	0x5b21f501,
+	0x0076bb08,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b608ad,
+	0x1f11f404,
+/* 0x0910: i2c_start_send */
+	0xf50037f0,
+	0xf1085b21,
+	0xf41388e7,
+	0x37f07e21,
+	0x3921f500,
+	0x88e7f108,
+	0x7e21f413,
+/* 0x092c: i2c_start_out */
+/* 0x092e: i2c_stop */
+	0x37f000f8,
+	0x3921f500,
+	0x0037f008,
+	0x085b21f5,
+	0x03e8e7f1,
+	0xf07e21f4,
+	0x21f50137,
+	0xe7f10839,
+	0x21f41388,
+	0x0137f07e,
+	0x085b21f5,
+	0x1388e7f1,
+	0xf87e21f4,
+/* 0x0961: i2c_bitw */
+	0x5b21f500,
 	0xe8e7f108,
 	0x7e21f403,
-	0x088421f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x08d5: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x08d9: i2c_start */
-	0x8421f500,
-	0x0d11f408,
-	0x089c21f5,
-	0xf40611f4,
-/* 0x08ea: i2c_start_rep */
-	0x37f0300e,
-	0x4021f500,
-	0x0137f008,
-	0x086221f5,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xb421f550,
+	0xad21f550,
 	0x0464b608,
-/* 0x0917: i2c_start_send */
-	0xf01f11f4,
-	0x21f50037,
-	0xe7f10862,
-	0x21f41388,
-	0x0037f07e,
-	0x084021f5,
-	0x1388e7f1,
-/* 0x0933: i2c_start_out */
-	0xf87e21f4,
-/* 0x0935: i2c_stop */
-	0x0037f000,
-	0x084021f5,
-	0xf50037f0,
-	0xf1086221,
-	0xf403e8e7,
+	0xf11811f4,
+	0xf41388e7,
 	0x37f07e21,
-	0x4021f501,
+	0x3921f500,
 	0x88e7f108,
 	0x7e21f413,
-	0xf50137f0,
-	0xf1086221,
-	0xf41388e7,
-	0x00f87e21,
-/* 0x0968: i2c_bitw */
-	0x086221f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x08b421f5,
-	0xf40464b6,
-	0xe7f11811,
+/* 0x09a0: i2c_bitw_out */
+/* 0x09a2: i2c_bitr */
+	0x37f000f8,
+	0x5b21f501,
+	0xe8e7f108,
+	0x7e21f403,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xad21f550,
+	0x0464b608,
+	0xf51b11f4,
+	0xf0089521,
+	0x21f50037,
+	0xe7f10839,
 	0x21f41388,
-	0x0037f07e,
-	0x084021f5,
-	0x1388e7f1,
-/* 0x09a7: i2c_bitw_out */
-	0xf87e21f4,
-/* 0x09a9: i2c_bitr */
-	0x0137f000,
-	0x086221f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x08b421f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f0089c,
-	0x4021f500,
-	0x88e7f108,
-	0x7e21f413,
-	0xf4013cf0,
-/* 0x09ee: i2c_bitr_done */
-	0x00f80131,
-/* 0x09f0: i2c_get_byte */
-	0xf00057f0,
-/* 0x09f6: i2c_get_byte_next */
-	0x54b60847,
+	0x013cf07e,
+/* 0x09e7: i2c_bitr_done */
+	0xf80131f4,
+/* 0x09e9: i2c_get_byte */
+	0x0057f000,
+/* 0x09ef: i2c_get_byte_next */
+	0xb60847f0,
+	0x76bb0154,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb609a221,
+	0x11f40464,
+	0x0553fd2b,
+	0xf40142b6,
+	0x37f0d81b,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b609a9,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x6821f550,
-	0x0464b609,
-/* 0x0a40: i2c_get_byte_done */
-/* 0x0a42: i2c_put_byte */
-	0x47f000f8,
-/* 0x0a45: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x096821f5,
-	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
+	0x64b60961,
+/* 0x0a39: i2c_get_byte_done */
+/* 0x0a3b: i2c_put_byte */
+	0xf000f804,
+/* 0x0a3e: i2c_put_byte_next */
+	0x42b60847,
+	0x3854ff01,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xa921f550,
+	0x6121f550,
 	0x0464b609,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x0a9b: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x0a9d: i2c_addr */
-	0x0076bb00,
+	0xb03411f4,
+	0x1bf40046,
+	0x0076bbd8,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b608d9,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b609a2,
+	0x0f11f404,
+	0xb00076bb,
+	0x1bf40136,
+	0x0132f406,
+/* 0x0a94: i2c_put_byte_done */
+/* 0x0a96: i2c_addr */
+	0x76bb00f8,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb60a4221,
-/* 0x0ae2: i2c_addr_done */
-	0x00f80464,
-/* 0x0ae4: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980d1c,
-/* 0x0af3: i2c_acquire */
-	0xf500f800,
-	0xf40ae421,
-	0xd9f00421,
-	0x4021f403,
-/* 0x0b02: i2c_release */
-	0x21f500f8,
-	0x21f40ae4,
-	0x03daf004,
-	0xf84021f4,
-/* 0x0b11: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xf413a001,
-	0x0032980c,
-	0x0ccc13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb608d221,
+	0x11f40464,
+	0x2ec3e729,
+	0x0134b601,
+	0xbb0553fd,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0af321f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
+	0x0a3b21f5,
+/* 0x0adb: i2c_addr_done */
+	0xf80464b6,
+/* 0x0add: i2c_acquire_addr */
+	0xf8cec700,
+	0xb702e4b6,
+	0x980d1ce0,
+	0x00f800ee,
+/* 0x0aec: i2c_acquire */
+	0x0add21f5,
+	0xf00421f4,
+	0x21f403d9,
+/* 0x0afb: i2c_release */
+	0xf500f840,
+	0xf40add21,
+	0xdaf00421,
+	0x4021f403,
+/* 0x0b0a: i2c_recv */
+	0x32f400f8,
+	0xf8c1c701,
+	0xb00214b6,
+	0x1ff52816,
+	0x13a0013a,
+	0x32980cf4,
+	0xcc13a000,
+	0x0031980c,
+	0xf90231f4,
+	0xf9e0f9d0,
+	0x0067f1d0,
+	0x0063f100,
+	0x01679210,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xec21f550,
+	0x0464b60a,
+	0xd6b0d0fc,
+	0xb31bf500,
+	0x0057f000,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x9621f550,
+	0x0464b60a,
+	0x00d011f5,
+	0xbbe0c5c7,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0a9d21f5,
+	0x0a3b21f5,
 	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
+	0xf000ad11,
+	0x76bb0157,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb60a4221,
+	0xb60a9621,
 	0x11f50464,
-	0x57f000ad,
-	0x0076bb01,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b60a9d,
-	0x8a11f504,
-	0x0076bb00,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b609f0,
-	0x6a11f404,
-	0xbbe05bcb,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x093521f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x0c17: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x0a9d21f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f40a42,
-	0x0057f029,
-	0x0a9d21f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f40a42,
-	0x3521f515,
-	0xc774bd09,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x0c57: i2c_recv_not_wr08 */
-/* 0x0c57: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc0b02,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x033621f5,
-/* 0x0c6c: i2c_recv_exit */
-/* 0x0c6e: i2c_init */
+	0x76bb008a,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb609e921,
+	0x11f40464,
+	0xe05bcb6a,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x2e21f550,
+	0x0464b609,
+	0xbd025bb9,
+	0x430ef474,
+/* 0x0c10: i2c_recv_not_rd08 */
+	0xf401d6b0,
+	0x57f03d1b,
+	0x9621f500,
+	0x3311f40a,
+	0xf5e0c5c7,
+	0xf40a3b21,
+	0x57f02911,
+	0x9621f500,
+	0x1f11f40a,
+	0xf5e0b5c7,
+	0xf40a3b21,
+	0x21f51511,
+	0x74bd092e,
+	0xf408c5c7,
+	0x32f4091b,
+	0x030ef402,
+/* 0x0c50: i2c_recv_not_wr08 */
+/* 0x0c50: i2c_recv_done */
+	0xf5f8cec7,
+	0xfc0afb21,
+	0xf4d0fce0,
+	0x7cb90a12,
+	0x3621f502,
+/* 0x0c65: i2c_recv_exit */
+/* 0x0c67: i2c_init */
+	0xf800f803,
+/* 0x0c69: test_recv */
+	0xd817f100,
+	0x0614b605,
+	0xb60011cf,
+	0x07f10110,
+	0x04b605d8,
+	0x0001d006,
+	0xe7f104bd,
+	0xe3f1d900,
+	0x21f5134f,
+	0x00f80256,
+/* 0x0c90: test_init */
+	0x0800e7f1,
+	0x025621f5,
+/* 0x0c9a: idle_recv */
 	0x00f800f8,
-/* 0x0c70: test_recv */
-	0x05d817f1,
-	0xcf0614b6,
-	0x10b60011,
-	0xd807f101,
-	0x0604b605,
-	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0x5621f513,
-/* 0x0c97: test_init */
-	0xf100f802,
-	0xf50800e7,
-	0xf8025621,
-/* 0x0ca1: idle_recv */
-/* 0x0ca3: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x0cbf: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x0cc5: idle_proc */
-/* 0x0cc5: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc033f,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0cd9: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
+/* 0x0c9c: idle */
+	0xf10031f4,
+	0xb605d417,
+	0x11cf0614,
+	0x0110b600,
+	0x05d407f1,
+	0xd00604b6,
+	0x04bd0001,
+/* 0x0cb8: idle_loop */
+	0xf45817f0,
+/* 0x0cbe: idle_proc */
+/* 0x0cbe: idle_proc_exec */
+	0x10f90232,
+	0xf5021eb9,
+	0xfc033f21,
+	0x0911f410,
+	0xf40231f4,
+/* 0x0cd2: idle_proc_next */
+	0x10b6ef0e,
+	0x061fb858,
+	0xf4e61bf4,
+	0x28f4dd02,
+	0xbb0ef400,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
index ec03f9a4290b..1663bf943d77 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
@@ -82,15 +82,15 @@ memx_train_tail:
 // $r0  - zero
 memx_func_enter:
 #if NVKM_PPWR_CHIPSET == GT215
-	movw $r8 0x1610
+	mov $r8 0x1610
 	nv_rd32($r7, $r8)
 	imm32($r6, 0xfffffffc)
 	and $r7 $r6
-	movw $r6 0x2
+	mov $r6 0x2
 	or $r7 $r6
 	nv_wr32($r8, $r7)
 #else
-	movw $r6 0x001620
+	mov $r6 0x001620
 	imm32($r7, ~0x00000aa2);
 	nv_rd32($r8, $r6)
 	and $r8 $r7
@@ -101,7 +101,7 @@ memx_func_enter:
 	and $r8 $r7
 	nv_wr32($r6, $r8)
 
-	movw $r6 0x0026f0
+	mov $r6 0x0026f0
 	nv_rd32($r8, $r6)
 	and $r8 $r7
 	nv_wr32($r6, $r8)
@@ -136,19 +136,19 @@ memx_func_leave:
 		bra nz #memx_func_leave_wait
 
 #if NVKM_PPWR_CHIPSET == GT215
-	movw $r8 0x1610
+	mov $r8 0x1610
 	nv_rd32($r7, $r8)
 	imm32($r6, 0xffffffcc)
 	and $r7 $r6
 	nv_wr32($r8, $r7)
 #else
-	movw $r6 0x0026f0
+	mov $r6 0x0026f0
 	imm32($r7, 0x00000001)
 	nv_rd32($r8, $r6)
 	or $r8 $r7
 	nv_wr32($r6, $r8)
 
-	movw $r6 0x001620
+	mov $r6 0x001620
 	nv_rd32($r8, $r6)
 	or $r8 $r7
 	nv_wr32($r6, $r8)
@@ -177,11 +177,11 @@ memx_func_wait_vblank:
 	bra #memx_func_wait_vblank_fini
 
 	memx_func_wait_vblank_head1:
-	movw $r7 0x20
+	mov $r7 0x20
 	bra #memx_func_wait_vblank_0
 
 	memx_func_wait_vblank_head0:
-	movw $r7 0x8
+	mov $r7 0x8
 
 	memx_func_wait_vblank_0:
 		nv_iord($r6, NV_PPWR_INPUT)
@@ -273,13 +273,13 @@ memx_func_train:
 // $r5 - outer loop counter
 // $r6 - inner loop counter
 // $r7 - entry counter (#memx_train_head + $r7)
-	movw $r5 0x3
-	movw $r7 0x0
+	mov $r5 0x3
+	mov $r7 0x0
 
 // Read random memory to wake up... things
 	imm32($r9, 0x700000)
 	nv_rd32($r8,$r9)
-	movw $r14 0x2710
+	mov $r14 0x2710
 	call(nsec)
 
 	memx_func_train_loop_outer:
@@ -289,9 +289,9 @@ memx_func_train:
 		nv_wr32($r9, $r8)
 		push $r5
 
-		movw $r6 0x0
+		mov $r6 0x0
 		memx_func_train_loop_inner:
-			movw $r8 0x1111
+			mov $r8 0x1111
 			mulu $r9 $r6 $r8
 			shl b32 $r8 $r9 0x10
 			or $r8 $r9
@@ -315,7 +315,7 @@ memx_func_train:
 
 			// $r5 - inner inner loop counter
 			// $r9 - result
-			movw $r5 0
+			mov $r5 0
 			imm32($r9, 0x8300ffff)
 			memx_func_train_loop_4x:
 				imm32($r10, 0x100080)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
index e698f4836521..ed08120eefe0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
@@ -7,8 +7,10 @@ nvkm-y += nvkm/subdev/secboot/acr_r352.o
 nvkm-y += nvkm/subdev/secboot/acr_r361.o
 nvkm-y += nvkm/subdev/secboot/acr_r364.o
 nvkm-y += nvkm/subdev/secboot/acr_r367.o
+nvkm-y += nvkm/subdev/secboot/acr_r370.o
 nvkm-y += nvkm/subdev/secboot/acr_r375.o
 nvkm-y += nvkm/subdev/secboot/gm200.o
 nvkm-y += nvkm/subdev/secboot/gm20b.o
 nvkm-y += nvkm/subdev/secboot/gp102.o
+nvkm-y += nvkm/subdev/secboot/gp108.o
 nvkm-y += nvkm/subdev/secboot/gp10b.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h
index b615fc81aca4..73a2ac81ac69 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h
@@ -64,6 +64,7 @@ struct nvkm_acr *acr_r352_new(unsigned long);
 struct nvkm_acr *acr_r361_new(unsigned long);
 struct nvkm_acr *acr_r364_new(unsigned long);
 struct nvkm_acr *acr_r367_new(enum nvkm_secboot_falcon, unsigned long);
+struct nvkm_acr *acr_r370_new(enum nvkm_secboot_falcon, unsigned long);
 struct nvkm_acr *acr_r375_new(enum nvkm_secboot_falcon, unsigned long);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c
new file mode 100644
index 000000000000..2f890dfae7fc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c
@@ -0,0 +1,144 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "acr_r370.h"
+#include "acr_r367.h"
+
+#include <core/msgqueue.h>
+#include <engine/falcon.h>
+#include <engine/sec2.h>
+
+static void
+acr_r370_generate_flcn_bl_desc(const struct nvkm_acr *acr,
+			       const struct ls_ucode_img *img, u64 wpr_addr,
+			       void *_desc)
+{
+	struct acr_r370_flcn_bl_desc *desc = _desc;
+	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+	u64 base, addr_code, addr_data;
+
+	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+	addr_code = base + pdesc->app_resident_code_offset;
+	addr_data = base + pdesc->app_resident_data_offset;
+
+	desc->ctx_dma = FALCON_DMAIDX_UCODE;
+	desc->code_dma_base = u64_to_flcn64(addr_code);
+	desc->non_sec_code_off = pdesc->app_resident_code_offset;
+	desc->non_sec_code_size = pdesc->app_resident_code_size;
+	desc->code_entry_point = pdesc->app_imem_entry;
+	desc->data_dma_base = u64_to_flcn64(addr_data);
+	desc->data_size = pdesc->app_resident_data_size;
+}
+
+const struct acr_r352_ls_func
+acr_r370_ls_fecs_func = {
+	.load = acr_ls_ucode_load_fecs,
+	.generate_bl_desc = acr_r370_generate_flcn_bl_desc,
+	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+};
+
+const struct acr_r352_ls_func
+acr_r370_ls_gpccs_func = {
+	.load = acr_ls_ucode_load_gpccs,
+	.generate_bl_desc = acr_r370_generate_flcn_bl_desc,
+	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+	/* GPCCS will be loaded using PRI */
+	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
+};
+
+static void
+acr_r370_generate_sec2_bl_desc(const struct nvkm_acr *acr,
+			       const struct ls_ucode_img *img, u64 wpr_addr,
+			       void *_desc)
+{
+	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+	const struct nvkm_sec2 *sec = acr->subdev->device->sec2;
+	struct acr_r370_flcn_bl_desc *desc = _desc;
+	u64 base, addr_code, addr_data;
+	u32 addr_args;
+
+	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+	/* For some reason we should not add app_resident_code_offset here */
+	addr_code = base;
+	addr_data = base + pdesc->app_resident_data_offset;
+	addr_args = sec->falcon->data.limit;
+	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
+
+	desc->ctx_dma = FALCON_SEC2_DMAIDX_UCODE;
+	desc->code_dma_base = u64_to_flcn64(addr_code);
+	desc->non_sec_code_off = pdesc->app_resident_code_offset;
+	desc->non_sec_code_size = pdesc->app_resident_code_size;
+	desc->code_entry_point = pdesc->app_imem_entry;
+	desc->data_dma_base = u64_to_flcn64(addr_data);
+	desc->data_size = pdesc->app_resident_data_size;
+	desc->argc = 1;
+	/* args are stored at the beginning of EMEM */
+	desc->argv = 0x01000000;
+}
+
+const struct acr_r352_ls_func
+acr_r370_ls_sec2_func = {
+	.load = acr_ls_ucode_load_sec2,
+	.generate_bl_desc = acr_r370_generate_sec2_bl_desc,
+	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+	.post_run = acr_ls_sec2_post_run,
+};
+
+void
+acr_r370_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
+			     u64 offset)
+{
+	struct acr_r370_flcn_bl_desc *bl_desc = _bl_desc;
+
+	bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
+	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
+	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
+	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
+	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
+	bl_desc->code_entry_point = 0;
+	bl_desc->code_dma_base = u64_to_flcn64(offset);
+	bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
+	bl_desc->data_size = hdr->data_size;
+}
+
+const struct acr_r352_func
+acr_r370_func = {
+	.fixup_hs_desc = acr_r367_fixup_hs_desc,
+	.generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
+	.hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+	.shadow_blob = true,
+	.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
+	.ls_fill_headers = acr_r367_ls_fill_headers,
+	.ls_write_wpr = acr_r367_ls_write_wpr,
+	.ls_func = {
+		[NVKM_SECBOOT_FALCON_SEC2] = &acr_r370_ls_sec2_func,
+		[NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
+		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
+	},
+};
+
+struct nvkm_acr *
+acr_r370_new(enum nvkm_secboot_falcon boot_falcon,
+	     unsigned long managed_falcons)
+{
+	return acr_r352_new_(&acr_r370_func, boot_falcon, managed_falcons);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h
new file mode 100644
index 000000000000..3426f86a15e4
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __NVKM_SECBOOT_ACR_R370_H__
+#define __NVKM_SECBOOT_ACR_R370_H__
+
+#include "priv.h"
+struct hsf_load_header;
+
+/* Same as acr_r361_flcn_bl_desc, plus argc/argv */
+struct acr_r370_flcn_bl_desc {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	struct flcn_u64 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	struct flcn_u64 data_dma_base;
+	u32 data_size;
+	u32 argc;
+	u32 argv;
+};
+
+void acr_r370_generate_hs_bl_desc(const struct hsf_load_header *, void *, u64);
+extern const struct acr_r352_ls_func acr_r370_ls_fecs_func;
+extern const struct acr_r352_ls_func acr_r370_ls_gpccs_func;
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c
index ddb795bb007b..7bdef93cb7ae 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c
@@ -20,90 +20,12 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include "acr_r370.h"
 #include "acr_r367.h"
 
-#include <engine/falcon.h>
 #include <core/msgqueue.h>
 #include <subdev/pmu.h>
 
-/*
- * r375 ACR: similar to r367, but with a unified bootloader descriptor
- * structure for GR and PMU falcons.
- */
-
-/* Same as acr_r361_flcn_bl_desc, plus argc/argv */
-struct acr_r375_flcn_bl_desc {
-	u32 reserved[4];
-	u32 signature[4];
-	u32 ctx_dma;
-	struct flcn_u64 code_dma_base;
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 sec_code_off;
-	u32 sec_code_size;
-	u32 code_entry_point;
-	struct flcn_u64 data_dma_base;
-	u32 data_size;
-	u32 argc;
-	u32 argv;
-};
-
-static void
-acr_r375_generate_flcn_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	struct acr_r375_flcn_bl_desc *desc = _desc;
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	u64 base, addr_code, addr_data;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = base + pdesc->app_resident_code_offset;
-	addr_data = base + pdesc->app_resident_data_offset;
-
-	desc->ctx_dma = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-}
-
-static void
-acr_r375_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
-			     u64 offset)
-{
-	struct acr_r375_flcn_bl_desc *bl_desc = _bl_desc;
-
-	bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
-	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
-	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
-	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
-	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
-	bl_desc->code_entry_point = 0;
-	bl_desc->code_dma_base = u64_to_flcn64(offset);
-	bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
-	bl_desc->data_size = hdr->data_size;
-}
-
-const struct acr_r352_ls_func
-acr_r375_ls_fecs_func = {
-	.load = acr_ls_ucode_load_fecs,
-	.generate_bl_desc = acr_r375_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r375_ls_gpccs_func = {
-	.load = acr_ls_ucode_load_gpccs,
-	.generate_bl_desc = acr_r375_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
-	/* GPCCS will be loaded using PRI */
-	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
-};
-
-
 static void
 acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr,
 			      const struct ls_ucode_img *img, u64 wpr_addr,
@@ -111,7 +33,7 @@ acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr,
 {
 	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
 	const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
-	struct acr_r375_flcn_bl_desc *desc = _desc;
+	struct acr_r370_flcn_bl_desc *desc = _desc;
 	u64 base, addr_code, addr_data;
 	u32 addr_args;
 
@@ -136,23 +58,22 @@ const struct acr_r352_ls_func
 acr_r375_ls_pmu_func = {
 	.load = acr_ls_ucode_load_pmu,
 	.generate_bl_desc = acr_r375_generate_pmu_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
+	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
 	.post_run = acr_ls_pmu_post_run,
 };
 
-
 const struct acr_r352_func
 acr_r375_func = {
 	.fixup_hs_desc = acr_r367_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r375_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
+	.generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
+	.hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
 	.shadow_blob = true,
 	.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
 	.ls_fill_headers = acr_r367_ls_fill_headers,
 	.ls_write_wpr = acr_r367_ls_write_wpr,
 	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r375_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r375_ls_gpccs_func,
+		[NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
+		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
 		[NVKM_SECBOOT_FALCON_PMU] = &acr_r375_ls_pmu_func,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c
index f3b3c66349d2..1f7a3c1a7f50 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c
@@ -133,7 +133,7 @@ gp102_secboot_run_blob(struct nvkm_secboot *sb, struct nvkm_gpuobj *blob,
 	return gm200_secboot_run_blob(sb, blob, falcon);
 }
 
-static const struct nvkm_secboot_func
+const struct nvkm_secboot_func
 gp102_secboot = {
 	.dtor = gm200_secboot_dtor,
 	.oneinit = gm200_secboot_oneinit,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
new file mode 100644
index 000000000000..e8c27ec700de
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
@@ -0,0 +1,67 @@
+/*
+ * Copyright 2017 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gm200.h"
+#include "acr.h"
+
+int
+gp108_secboot_new(struct nvkm_device *device, int index,
+		  struct nvkm_secboot **psb)
+{
+	struct gm200_secboot *gsb;
+	struct nvkm_acr *acr;
+
+	acr = acr_r370_new(NVKM_SECBOOT_FALCON_SEC2,
+			   BIT(NVKM_SECBOOT_FALCON_FECS) |
+			   BIT(NVKM_SECBOOT_FALCON_GPCCS) |
+			   BIT(NVKM_SECBOOT_FALCON_SEC2));
+	if (IS_ERR(acr))
+		return PTR_ERR(acr);
+
+	if (!(gsb = kzalloc(sizeof(*gsb), GFP_KERNEL))) {
+		acr->func->dtor(acr);
+		return -ENOMEM;
+	}
+	*psb = &gsb->base;
+
+	return nvkm_secboot_ctor(&gp102_secboot, acr, device, index, &gsb->base);
+}
+
+MODULE_FIRMWARE("nvidia/gp108/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_load.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_method_init.bin");
+MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
index d9091f029506..959a7b2dbdc9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
@@ -40,6 +40,8 @@ int nvkm_secboot_ctor(const struct nvkm_secboot_func *, struct nvkm_acr *,
 int nvkm_secboot_falcon_reset(struct nvkm_secboot *);
 int nvkm_secboot_falcon_run(struct nvkm_secboot *);
 
+extern const struct nvkm_secboot_func gp102_secboot;
+
 struct flcn_u64 {
 	u32 lo;
 	u32 hi;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
index 7ba56b12badd..550702eab0b1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
@@ -9,7 +9,9 @@ nvkm-y += nvkm/subdev/therm/nv40.o
 nvkm-y += nvkm/subdev/therm/nv50.o
 nvkm-y += nvkm/subdev/therm/g84.o
 nvkm-y += nvkm/subdev/therm/gt215.o
+nvkm-y += nvkm/subdev/therm/gf100.o
 nvkm-y += nvkm/subdev/therm/gf119.o
+nvkm-y += nvkm/subdev/therm/gk104.o
 nvkm-y += nvkm/subdev/therm/gm107.o
 nvkm-y += nvkm/subdev/therm/gm200.o
 nvkm-y += nvkm/subdev/therm/gp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
index f27fc6d0d4c6..bf62303571b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
@@ -21,6 +21,7 @@
  *
  * Authors: Martin Peres
  */
+#include <nvkm/core/option.h>
 #include "priv.h"
 
 int
@@ -297,6 +298,38 @@ nvkm_therm_attr_set(struct nvkm_therm *therm,
 	return -EINVAL;
 }
 
+void
+nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
+{
+	if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+		return;
+
+	nvkm_debug(&therm->subdev,
+		   "Enabling clockgating\n");
+	therm->func->clkgate_enable(therm);
+}
+
+void
+nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend)
+{
+	if (!therm->func->clkgate_fini || !therm->clkgating_enabled)
+		return;
+
+	nvkm_debug(&therm->subdev,
+		   "Preparing clockgating for %s\n",
+		   suspend ? "suspend" : "fini");
+	therm->func->clkgate_fini(therm, suspend);
+}
+
+static void
+nvkm_therm_clkgate_oneinit(struct nvkm_therm *therm)
+{
+	if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+		return;
+
+	nvkm_info(&therm->subdev, "Clockgating enabled\n");
+}
+
 static void
 nvkm_therm_intr(struct nvkm_subdev *subdev)
 {
@@ -333,6 +366,7 @@ nvkm_therm_oneinit(struct nvkm_subdev *subdev)
 	nvkm_therm_fan_ctor(therm);
 	nvkm_therm_fan_mode(therm, NVKM_THERM_CTRL_AUTO);
 	nvkm_therm_sensor_preinit(therm);
+	nvkm_therm_clkgate_oneinit(therm);
 	return 0;
 }
 
@@ -357,6 +391,16 @@ nvkm_therm_init(struct nvkm_subdev *subdev)
 	return 0;
 }
 
+void
+nvkm_therm_clkgate_init(struct nvkm_therm *therm,
+			const struct nvkm_therm_clkgate_pack *p)
+{
+	if (!therm->func->clkgate_init || !therm->clkgating_enabled)
+		return;
+
+	therm->func->clkgate_init(therm, p);
+}
+
 static void *
 nvkm_therm_dtor(struct nvkm_subdev *subdev)
 {
@@ -374,15 +418,10 @@ nvkm_therm = {
 	.intr = nvkm_therm_intr,
 };
 
-int
-nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device,
-		int index, struct nvkm_therm **ptherm)
+void
+nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device,
+		int index, const struct nvkm_therm_func *func)
 {
-	struct nvkm_therm *therm;
-
-	if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL)))
-		return -ENOMEM;
-
 	nvkm_subdev_ctor(&nvkm_therm, device, index, &therm->subdev);
 	therm->func = func;
 
@@ -395,5 +434,20 @@ nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device,
 	therm->attr_get = nvkm_therm_attr_get;
 	therm->attr_set = nvkm_therm_attr_set;
 	therm->mode = therm->suspend = -1; /* undefined */
+
+	therm->clkgating_enabled = nvkm_boolopt(device->cfgopt,
+						"NvPmEnableGating", false);
+}
+
+int
+nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device,
+		int index, struct nvkm_therm **ptherm)
+{
+	struct nvkm_therm *therm;
+
+	if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL)))
+		return -ENOMEM;
+
+	nvkm_therm_ctor(therm, device, index, func);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c
new file mode 100644
index 000000000000..5ae6913320e8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+#include <core/device.h>
+
+#include "priv.h"
+
+#define pack_for_each_init(init, pack, head)                          \
+	for (pack = head; pack && pack->init; pack++)                 \
+		  for (init = pack->init; init && init->count; init++)
+void
+gf100_clkgate_init(struct nvkm_therm *therm,
+		   const struct nvkm_therm_clkgate_pack *p)
+{
+	struct nvkm_device *device = therm->subdev.device;
+	const struct nvkm_therm_clkgate_pack *pack;
+	const struct nvkm_therm_clkgate_init *init;
+	u32 next, addr;
+
+	pack_for_each_init(init, pack, p) {
+		next = init->addr + init->count * 8;
+		addr = init->addr;
+
+		nvkm_trace(&therm->subdev, "{ 0x%06x, %d, 0x%08x }\n",
+			   init->addr, init->count, init->data);
+		while (addr < next) {
+			nvkm_trace(&therm->subdev, "\t0x%06x = 0x%08x\n",
+				   addr, init->data);
+			nvkm_wr32(device, addr, init->data);
+			addr += 8;
+		}
+	}
+}
+
+/*
+ * TODO: Fermi clockgating isn't understood fully yet, so we don't specify any
+ * clockgate functions to use
+ */
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h
new file mode 100644
index 000000000000..cfb25af77c60
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GF100_THERM_H__
+#define __GF100_THERM_H__
+
+#include <core/device.h>
+
+struct gf100_idle_filter {
+	u32 fecs;
+	u32 hubmmu;
+};
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c
index 06dcfd6ee966..0981b02790e2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c
@@ -49,7 +49,7 @@ pwm_info(struct nvkm_therm *therm, int line)
 	return -ENODEV;
 }
 
-static int
+int
 gf119_fan_pwm_ctrl(struct nvkm_therm *therm, int line, bool enable)
 {
 	struct nvkm_device *device = therm->subdev.device;
@@ -63,7 +63,7 @@ gf119_fan_pwm_ctrl(struct nvkm_therm *therm, int line, bool enable)
 	return 0;
 }
 
-static int
+int
 gf119_fan_pwm_get(struct nvkm_therm *therm, int line, u32 *divs, u32 *duty)
 {
 	struct nvkm_device *device = therm->subdev.device;
@@ -85,7 +85,7 @@ gf119_fan_pwm_get(struct nvkm_therm *therm, int line, u32 *divs, u32 *duty)
 	return -EINVAL;
 }
 
-static int
+int
 gf119_fan_pwm_set(struct nvkm_therm *therm, int line, u32 divs, u32 duty)
 {
 	struct nvkm_device *device = therm->subdev.device;
@@ -102,7 +102,7 @@ gf119_fan_pwm_set(struct nvkm_therm *therm, int line, u32 divs, u32 duty)
 	return 0;
 }
 
-static int
+int
 gf119_fan_pwm_clock(struct nvkm_therm *therm, int line)
 {
 	struct nvkm_device *device = therm->subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c
new file mode 100644
index 000000000000..4e03971d2e3d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+#include <core/device.h>
+
+#include "priv.h"
+#include "gk104.h"
+
+void
+gk104_clkgate_enable(struct nvkm_therm *base)
+{
+	struct gk104_therm *therm = gk104_therm(base);
+	struct nvkm_device *dev = therm->base.subdev.device;
+	const struct gk104_clkgate_engine_info *order = therm->clkgate_order;
+	int i;
+
+	/* Program ENG_MANT, ENG_FILTER */
+	for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+		if (!nvkm_device_subdev(dev, order[i].engine))
+			continue;
+
+		nvkm_mask(dev, 0x20200 + order[i].offset, 0xff00, 0x4500);
+	}
+
+	/* magic */
+	nvkm_wr32(dev, 0x020288, therm->idle_filter->fecs);
+	nvkm_wr32(dev, 0x02028c, therm->idle_filter->hubmmu);
+
+	/* Enable clockgating (ENG_CLK = RUN->AUTO) */
+	for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+		if (!nvkm_device_subdev(dev, order[i].engine))
+			continue;
+
+		nvkm_mask(dev, 0x20200 + order[i].offset, 0x00ff, 0x0045);
+	}
+}
+
+void
+gk104_clkgate_fini(struct nvkm_therm *base, bool suspend)
+{
+	struct gk104_therm *therm = gk104_therm(base);
+	struct nvkm_device *dev = therm->base.subdev.device;
+	const struct gk104_clkgate_engine_info *order = therm->clkgate_order;
+	int i;
+
+	/* ENG_CLK = AUTO->RUN, ENG_PWR = RUN->AUTO */
+	for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+		if (!nvkm_device_subdev(dev, order[i].engine))
+			continue;
+
+		nvkm_mask(dev, 0x20200 + order[i].offset, 0xff, 0x54);
+	}
+}
+
+const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[] = {
+	{ NVKM_ENGINE_GR,     0x00 },
+	{ NVKM_ENGINE_MSPDEC, 0x04 },
+	{ NVKM_ENGINE_MSPPP,  0x08 },
+	{ NVKM_ENGINE_MSVLD,  0x0c },
+	{ NVKM_ENGINE_CE0,    0x10 },
+	{ NVKM_ENGINE_CE1,    0x14 },
+	{ NVKM_ENGINE_MSENC,  0x18 },
+	{ NVKM_ENGINE_CE2,    0x1c },
+	{ NVKM_SUBDEV_NR, 0 },
+};
+
+const struct gf100_idle_filter gk104_idle_filter = {
+	.fecs = 0x00001000,
+	.hubmmu = 0x00001000,
+};
+
+static const struct nvkm_therm_func
+gk104_therm_func = {
+	.init = gf119_therm_init,
+	.fini = g84_therm_fini,
+	.pwm_ctrl = gf119_fan_pwm_ctrl,
+	.pwm_get = gf119_fan_pwm_get,
+	.pwm_set = gf119_fan_pwm_set,
+	.pwm_clock = gf119_fan_pwm_clock,
+	.temp_get = g84_temp_get,
+	.fan_sense = gt215_therm_fan_sense,
+	.program_alarms = nvkm_therm_program_alarms_polling,
+	.clkgate_init = gf100_clkgate_init,
+	.clkgate_enable = gk104_clkgate_enable,
+	.clkgate_fini = gk104_clkgate_fini,
+};
+
+static int
+gk104_therm_new_(const struct nvkm_therm_func *func,
+		 struct nvkm_device *device,
+		 int index,
+		 const struct gk104_clkgate_engine_info *clkgate_order,
+		 const struct gf100_idle_filter *idle_filter,
+		 struct nvkm_therm **ptherm)
+{
+	struct gk104_therm *therm = kzalloc(sizeof(*therm), GFP_KERNEL);
+
+	if (!therm)
+		return -ENOMEM;
+
+	nvkm_therm_ctor(&therm->base, device, index, func);
+	*ptherm = &therm->base;
+	therm->clkgate_order = clkgate_order;
+	therm->idle_filter = idle_filter;
+
+	return 0;
+}
+
+int
+gk104_therm_new(struct nvkm_device *device,
+		int index, struct nvkm_therm **ptherm)
+{
+	return gk104_therm_new_(&gk104_therm_func, device, index,
+				gk104_clkgate_engine_info, &gk104_idle_filter,
+				ptherm);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h
new file mode 100644
index 000000000000..293e7743b19b
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GK104_THERM_H__
+#define __GK104_THERM_H__
+#define gk104_therm(p) (container_of((p), struct gk104_therm, base))
+
+#include <subdev/therm.h>
+#include "priv.h"
+#include "gf100.h"
+
+struct gk104_clkgate_engine_info {
+	enum nvkm_devidx engine;
+	u8 offset;
+};
+
+struct gk104_therm {
+	struct nvkm_therm base;
+
+	const struct gk104_clkgate_engine_info *clkgate_order;
+	const struct gf100_idle_filter *idle_filter;
+};
+
+extern const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[];
+extern const struct gf100_idle_filter gk104_idle_filter;
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c
index c08097f2aff5..4caf401d001a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c
@@ -36,7 +36,7 @@ gt215_therm_fan_sense(struct nvkm_therm *therm)
 	return -ENODEV;
 }
 
-static void
+void
 gt215_therm_init(struct nvkm_therm *therm)
 {
 	struct nvkm_device *device = therm->subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h
index 1f46e371d7c4..21659daf1864 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h
@@ -32,6 +32,8 @@
 
 int nvkm_therm_new_(const struct nvkm_therm_func *, struct nvkm_device *,
 		    int index, struct nvkm_therm **);
+void nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device,
+		     int index, const struct nvkm_therm_func *func);
 
 struct nvkm_fan {
 	struct nvkm_therm *parent;
@@ -66,8 +68,6 @@ int nvkm_therm_fan_set(struct nvkm_therm *, bool now, int percent);
 int nvkm_therm_fan_user_get(struct nvkm_therm *);
 int nvkm_therm_fan_user_set(struct nvkm_therm *, int percent);
 
-int nvkm_therm_preinit(struct nvkm_therm *);
-
 int  nvkm_therm_sensor_init(struct nvkm_therm *);
 int  nvkm_therm_sensor_fini(struct nvkm_therm *, bool suspend);
 void nvkm_therm_sensor_preinit(struct nvkm_therm *);
@@ -96,6 +96,11 @@ struct nvkm_therm_func {
 	int (*fan_sense)(struct nvkm_therm *);
 
 	void (*program_alarms)(struct nvkm_therm *);
+
+	void (*clkgate_init)(struct nvkm_therm *,
+			     const struct nvkm_therm_clkgate_pack *);
+	void (*clkgate_enable)(struct nvkm_therm *);
+	void (*clkgate_fini)(struct nvkm_therm *, bool);
 };
 
 void nv40_therm_intr(struct nvkm_therm *);
@@ -111,9 +116,21 @@ void g84_therm_fini(struct nvkm_therm *);
 
 int gt215_therm_fan_sense(struct nvkm_therm *);
 
+void gf100_clkgate_init(struct nvkm_therm *,
+			const struct nvkm_therm_clkgate_pack *);
+
 void g84_therm_init(struct nvkm_therm *);
+
+int gf119_fan_pwm_ctrl(struct nvkm_therm *, int, bool);
+int gf119_fan_pwm_get(struct nvkm_therm *, int, u32 *, u32 *);
+int gf119_fan_pwm_set(struct nvkm_therm *, int, u32, u32);
+int gf119_fan_pwm_clock(struct nvkm_therm *, int);
 void gf119_therm_init(struct nvkm_therm *);
 
+void gk104_therm_init(struct nvkm_therm *);
+void gk104_clkgate_enable(struct nvkm_therm *);
+void gk104_clkgate_fini(struct nvkm_therm *, bool);
+
 int nvkm_fanpwm_create(struct nvkm_therm *, struct dcb_gpio_func *);
 int nvkm_fantog_create(struct nvkm_therm *, struct dcb_gpio_func *);
 int nvkm_fannil_create(struct nvkm_therm *);
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 57e38a9e7ab4..b5e3994f0aa8 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -215,8 +215,15 @@ static int panel_lvds_probe(struct platform_device *pdev)
 	lvds->supply = devm_regulator_get_optional(lvds->dev, "power");
 	if (IS_ERR(lvds->supply)) {
 		ret = PTR_ERR(lvds->supply);
-		dev_err(lvds->dev, "failed to request regulator: %d\n", ret);
-		return ret;
+
+		if (ret != -ENODEV) {
+			if (ret != -EPROBE_DEFER)
+				dev_err(lvds->dev, "failed to request regulator: %d\n",
+					ret);
+			return ret;
+		}
+
+		lvds->supply = NULL;
 	}
 
 	/* Get GPIOs and backlight controller. */
diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c
index 8fdc56c1c953..b9bfa806d346 100644
--- a/drivers/gpu/drm/r128/r128_state.c
+++ b/drivers/gpu/drm/r128/r128_state.c
@@ -982,25 +982,14 @@ static int r128_cce_dispatch_write_pixels(struct drm_device *dev,
 
 	xbuf_size = count * sizeof(*x);
 	ybuf_size = count * sizeof(*y);
-	x = kmalloc(xbuf_size, GFP_KERNEL);
-	if (x == NULL)
-		return -ENOMEM;
-	y = kmalloc(ybuf_size, GFP_KERNEL);
-	if (y == NULL) {
-		kfree(x);
-		return -ENOMEM;
-	}
-	if (copy_from_user(x, depth->x, xbuf_size)) {
-		kfree(x);
-		kfree(y);
-		return -EFAULT;
-	}
-	if (copy_from_user(y, depth->y, xbuf_size)) {
+	x = memdup_user(depth->x, xbuf_size);
+	if (IS_ERR(x))
+		return PTR_ERR(x);
+	y = memdup_user(depth->y, ybuf_size);
+	if (IS_ERR(y)) {
 		kfree(x);
-		kfree(y);
-		return -EFAULT;
+		return PTR_ERR(y);
 	}
-
 	buffer_size = depth->n * sizeof(u32);
 	buffer = memdup_user(depth->buffer, buffer_size);
 	if (IS_ERR(buffer)) {
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 24fe66c89dfb..5712d63dca20 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3513,6 +3513,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
 						EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
 	}
+	rdev->config.evergreen.backend_map = tmp;
 	WREG32(GB_BACKEND_MAP, tmp);
 
 	WREG32(CGTS_SYS_TCC_DISABLE, 0);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 9eccd0c81d88..381b0255ff02 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1148,6 +1148,7 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 						rdev->config.cayman.max_shader_engines,
 						CAYMAN_MAX_BACKENDS, disabled_rb_mask);
 	}
+	rdev->config.cayman.backend_map = tmp;
 	WREG32(GB_BACKEND_MAP, tmp);
 
 	cgts_tcc_disable = 0xffff0000;
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 183b4b482138..238e6eb842ea 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -328,7 +328,7 @@ static void radeon_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 	drm_kms_helper_hotplug_event(dev);
 }
 
-const struct drm_dp_mst_topology_cbs mst_cbs = {
+static const struct drm_dp_mst_topology_cbs mst_cbs = {
 	.add_connector = radeon_dp_add_mst_connector,
 	.register_connector = radeon_dp_register_mst_connector,
 	.destroy_connector = radeon_dp_destroy_mst_connector,
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index d34d1cf33895..95f4db70dd22 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -995,7 +995,7 @@ int radeon_uvd_calc_upll_dividers(struct radeon_device *rdev,
 		/* calc dclk divider with current vco freq */
 		dclk_div = radeon_uvd_calc_upll_post_div(vco_freq, dclk,
 							 pd_min, pd_even);
-		if (vclk_div > pd_max)
+		if (dclk_div > pd_max)
 			break; /* vco is too big, it has to stop */
 
 		/* calc score with current vco freq */
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 84911bdc27d1..e67f4ea28c0e 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -25,6 +25,7 @@
 #include <linux/clk.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_graph.h>
+#include <linux/pinctrl/devinfo.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
index dc332ea56f6c..3ecffa52c814 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
@@ -102,10 +102,13 @@ static int sun4i_tmds_determine_rate(struct clk_hw *hw,
 					goto out;
 				}
 
-				if (abs(rate - rounded / i) <
-				    abs(rate - best_parent / best_div)) {
+				if (!best_parent ||
+				    abs(rate - rounded / i / j) <
+				    abs(rate - best_parent / best_half /
+					best_div)) {
 					best_parent = rounded;
-					best_div = i;
+					best_half = i;
+					best_div = j;
 				}
 			}
 		}
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 8416899266cf..0d6c5ed44795 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -913,7 +913,7 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
 				has_lvds_alt = false;
 			} else {
 				dev_err(dev, "Couldn't get the LVDS PLL\n");
-				return PTR_ERR(tcon->lvds_rst);
+				return PTR_ERR(tcon->lvds_pll);
 			}
 		} else {
 			has_lvds_alt = true;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 2eb71ffe95a6..2fef09a56d16 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -170,7 +170,8 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 		list_add_tail(&bo->lru, &man->lru[bo->priority]);
 		kref_get(&bo->list_kref);
 
-		if (bo->ttm && !(bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) {
+		if (bo->ttm && !(bo->ttm->page_flags &
+				 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
 			list_add_tail(&bo->swap,
 				      &bo->glob->swap_lru[bo->priority]);
 			kref_get(&bo->list_kref);
@@ -1726,7 +1727,7 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 	kref_get(&bo->list_kref);
 
 	if (!list_empty(&bo->ddestroy)) {
-		ret = ttm_bo_cleanup_refs(bo, false, false, true);
+		ret = ttm_bo_cleanup_refs(bo, false, false, locked);
 		kref_put(&bo->list_kref, ttm_bo_release_list);
 		return ret;
 	}
@@ -1779,8 +1780,8 @@ out:
 	 * Unreserve without putting on LRU to avoid swapping out an
 	 * already swapped buffer.
 	 */
-
-	reservation_object_unlock(bo->resv);
+	if (locked)
+		reservation_object_unlock(bo->resv);
 	kref_put(&bo->list_kref, ttm_bo_release_list);
 	return ret;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 08a3c324242e..60fcef1593dd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -316,7 +316,7 @@ static void ttm_bo_vm_close(struct vm_area_struct *vma)
 
 static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
 				 unsigned long offset,
-				 void *buf, int len, int write)
+				 uint8_t *buf, int len, int write)
 {
 	unsigned long page = offset >> PAGE_SHIFT;
 	unsigned long bytes_left = len;
@@ -345,6 +345,7 @@ static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
 		ttm_bo_kunmap(&map);
 
 		page++;
+		buf += bytes;
 		bytes_left -= bytes;
 		offset = 0;
 	} while (bytes_left);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 79854ab3bc47..2b12c55a3bff 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -477,12 +477,12 @@ ttm_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	return count;
 }
 
-static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
+static int ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
 {
 	manager->mm_shrink.count_objects = ttm_pool_shrink_count;
 	manager->mm_shrink.scan_objects = ttm_pool_shrink_scan;
 	manager->mm_shrink.seeks = 1;
-	register_shrinker(&manager->mm_shrink);
+	return register_shrinker(&manager->mm_shrink);
 }
 
 static void ttm_pool_mm_shrink_fini(struct ttm_pool_manager *manager)
@@ -1034,15 +1034,18 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 
 	ret = kobject_init_and_add(&_manager->kobj, &ttm_pool_kobj_type,
 				   &glob->kobj, "pool");
-	if (unlikely(ret != 0)) {
-		kobject_put(&_manager->kobj);
-		_manager = NULL;
-		return ret;
-	}
-
-	ttm_pool_mm_shrink_init(_manager);
+	if (unlikely(ret != 0))
+		goto error;
 
+	ret = ttm_pool_mm_shrink_init(_manager);
+	if (unlikely(ret != 0))
+		goto error;
 	return 0;
+
+error:
+	kobject_put(&_manager->kobj);
+	_manager = NULL;
+	return ret;
 }
 
 void ttm_page_alloc_fini(void)
@@ -1072,7 +1075,8 @@ int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 	ret = ttm_get_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
 			    ttm->caching_state);
 	if (unlikely(ret != 0)) {
-		ttm_pool_unpopulate(ttm);
+		ttm_put_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
+			      ttm->caching_state);
 		return ret;
 	}
 
@@ -1080,7 +1084,8 @@ int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
 						PAGE_SIZE, ctx);
 		if (unlikely(ret != 0)) {
-			ttm_pool_unpopulate(ttm);
+			ttm_put_pages(ttm->pages, ttm->num_pages,
+				      ttm->page_flags, ttm->caching_state);
 			return -ENOMEM;
 		}
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 4c659405a008..a88051552ace 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -61,6 +61,7 @@
 #define SMALL_ALLOCATION		4
 #define FREE_ALL_PAGES			(~0U)
 #define VADDR_FLAG_HUGE_POOL		1UL
+#define VADDR_FLAG_UPDATED_COUNT	2UL
 
 enum pool_type {
 	IS_UNDEFINED	= 0,
@@ -874,18 +875,18 @@ static int ttm_dma_page_pool_fill_locked(struct dma_pool *pool,
 }
 
 /*
- * @return count of pages still required to fulfill the request.
  * The populate list is actually a stack (not that is matters as TTM
  * allocates one page at a time.
+ * return dma_page pointer if success, otherwise NULL.
  */
-static int ttm_dma_pool_get_pages(struct dma_pool *pool,
+static struct dma_page *ttm_dma_pool_get_pages(struct dma_pool *pool,
 				  struct ttm_dma_tt *ttm_dma,
 				  unsigned index)
 {
-	struct dma_page *d_page;
+	struct dma_page *d_page = NULL;
 	struct ttm_tt *ttm = &ttm_dma->ttm;
 	unsigned long irq_flags;
-	int count, r = -ENOMEM;
+	int count;
 
 	spin_lock_irqsave(&pool->lock, irq_flags);
 	count = ttm_dma_page_pool_fill_locked(pool, &irq_flags);
@@ -894,12 +895,11 @@ static int ttm_dma_pool_get_pages(struct dma_pool *pool,
 		ttm->pages[index] = d_page->p;
 		ttm_dma->dma_address[index] = d_page->dma;
 		list_move_tail(&d_page->page_list, &ttm_dma->pages_list);
-		r = 0;
 		pool->npages_in_use += 1;
 		pool->npages_free -= 1;
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
-	return r;
+	return d_page;
 }
 
 static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
@@ -934,6 +934,7 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 	struct ttm_mem_global *mem_glob = ttm->glob->mem_glob;
 	unsigned long num_pages = ttm->num_pages;
 	struct dma_pool *pool;
+	struct dma_page *d_page;
 	enum pool_type type;
 	unsigned i;
 	int ret;
@@ -962,8 +963,8 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 	while (num_pages >= HPAGE_PMD_NR) {
 		unsigned j;
 
-		ret = ttm_dma_pool_get_pages(pool, ttm_dma, i);
-		if (ret != 0)
+		d_page = ttm_dma_pool_get_pages(pool, ttm_dma, i);
+		if (!d_page)
 			break;
 
 		ret = ttm_mem_global_alloc_page(mem_glob, ttm->pages[i],
@@ -973,6 +974,7 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 			return -ENOMEM;
 		}
 
+		d_page->vaddr |= VADDR_FLAG_UPDATED_COUNT;
 		for (j = i + 1; j < (i + HPAGE_PMD_NR); ++j) {
 			ttm->pages[j] = ttm->pages[j - 1] + 1;
 			ttm_dma->dma_address[j] = ttm_dma->dma_address[j - 1] +
@@ -996,8 +998,8 @@ skip_huge:
 	}
 
 	while (num_pages) {
-		ret = ttm_dma_pool_get_pages(pool, ttm_dma, i);
-		if (ret != 0) {
+		d_page = ttm_dma_pool_get_pages(pool, ttm_dma, i);
+		if (!d_page) {
 			ttm_dma_unpopulate(ttm_dma, dev);
 			return -ENOMEM;
 		}
@@ -1009,6 +1011,7 @@ skip_huge:
 			return -ENOMEM;
 		}
 
+		d_page->vaddr |= VADDR_FLAG_UPDATED_COUNT;
 		++i;
 		--num_pages;
 	}
@@ -1049,8 +1052,11 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 				continue;
 
 			count++;
-			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 d_page->p, pool->size);
+			if (d_page->vaddr & VADDR_FLAG_UPDATED_COUNT) {
+				ttm_mem_global_free_page(ttm->glob->mem_glob,
+							 d_page->p, pool->size);
+				d_page->vaddr &= ~VADDR_FLAG_UPDATED_COUNT;
+			}
 			ttm_dma_page_put(pool, d_page);
 		}
 
@@ -1070,9 +1076,19 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 
 	/* make sure pages array match list and count number of pages */
 	count = 0;
-	list_for_each_entry(d_page, &ttm_dma->pages_list, page_list) {
+	list_for_each_entry_safe(d_page, next, &ttm_dma->pages_list,
+				 page_list) {
 		ttm->pages[count] = d_page->p;
 		count++;
+
+		if (d_page->vaddr & VADDR_FLAG_UPDATED_COUNT) {
+			ttm_mem_global_free_page(ttm->glob->mem_glob,
+						 d_page->p, pool->size);
+			d_page->vaddr &= ~VADDR_FLAG_UPDATED_COUNT;
+		}
+
+		if (is_cached)
+			ttm_dma_page_put(pool, d_page);
 	}
 
 	spin_lock_irqsave(&pool->lock, irq_flags);
@@ -1092,19 +1108,6 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 
-	if (is_cached) {
-		list_for_each_entry_safe(d_page, next, &ttm_dma->pages_list, page_list) {
-			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 d_page->p, pool->size);
-			ttm_dma_page_put(pool, d_page);
-		}
-	} else {
-		for (i = 0; i < count; i++) {
-			ttm_mem_global_free_page(ttm->glob->mem_glob,
-						 ttm->pages[i], pool->size);
-		}
-	}
-
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	for (i = 0; i < ttm->num_pages; i++) {
 		ttm->pages[i] = NULL;
@@ -1182,12 +1185,12 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	return count;
 }
 
-static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
+static int ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
 {
 	manager->mm_shrink.count_objects = ttm_dma_pool_shrink_count;
 	manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan;
 	manager->mm_shrink.seeks = 1;
-	register_shrinker(&manager->mm_shrink);
+	return register_shrinker(&manager->mm_shrink);
 }
 
 static void ttm_dma_pool_mm_shrink_fini(struct ttm_pool_manager *manager)
@@ -1197,7 +1200,7 @@ static void ttm_dma_pool_mm_shrink_fini(struct ttm_pool_manager *manager)
 
 int ttm_dma_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 {
-	int ret = -ENOMEM;
+	int ret;
 
 	WARN_ON(_manager);
 
@@ -1205,7 +1208,7 @@ int ttm_dma_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 
 	_manager = kzalloc(sizeof(*_manager), GFP_KERNEL);
 	if (!_manager)
-		goto err;
+		return -ENOMEM;
 
 	mutex_init(&_manager->lock);
 	INIT_LIST_HEAD(&_manager->pools);
@@ -1217,13 +1220,17 @@ int ttm_dma_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 	/* This takes care of auto-freeing the _manager */
 	ret = kobject_init_and_add(&_manager->kobj, &ttm_pool_kobj_type,
 				   &glob->kobj, "dma_pool");
-	if (unlikely(ret != 0)) {
-		kobject_put(&_manager->kobj);
-		goto err;
-	}
-	ttm_dma_pool_mm_shrink_init(_manager);
+	if (unlikely(ret != 0))
+		goto error;
+
+	ret = ttm_dma_pool_mm_shrink_init(_manager);
+	if (unlikely(ret != 0))
+		goto error;
 	return 0;
-err:
+
+error:
+	kobject_put(&_manager->kobj);
+	_manager = NULL;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 3ac801b14d4e..2107b0daf8ef 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -146,7 +146,7 @@ vc4_save_hang_state(struct drm_device *dev)
 	struct vc4_exec_info *exec[2];
 	struct vc4_bo *bo;
 	unsigned long irqflags;
-	unsigned int i, j, unref_list_count, prev_idx;
+	unsigned int i, j, k, unref_list_count;
 
 	kernel_state = kcalloc(1, sizeof(*kernel_state), GFP_KERNEL);
 	if (!kernel_state)
@@ -182,7 +182,7 @@ vc4_save_hang_state(struct drm_device *dev)
 		return;
 	}
 
-	prev_idx = 0;
+	k = 0;
 	for (i = 0; i < 2; i++) {
 		if (!exec[i])
 			continue;
@@ -197,7 +197,7 @@ vc4_save_hang_state(struct drm_device *dev)
 			WARN_ON(!refcount_read(&bo->usecnt));
 			refcount_inc(&bo->usecnt);
 			drm_gem_object_get(&exec[i]->bo[j]->base);
-			kernel_state->bo[j + prev_idx] = &exec[i]->bo[j]->base;
+			kernel_state->bo[k++] = &exec[i]->bo[j]->base;
 		}
 
 		list_for_each_entry(bo, &exec[i]->unref_list, unref_head) {
@@ -205,12 +205,12 @@ vc4_save_hang_state(struct drm_device *dev)
 			 * because they are naturally unpurgeable.
 			 */
 			drm_gem_object_get(&bo->base.base);
-			kernel_state->bo[j + prev_idx] = &bo->base.base;
-			j++;
+			kernel_state->bo[k++] = &bo->base.base;
 		}
-		prev_idx = j + 1;
 	}
 
+	WARN_ON_ONCE(k != state->bo_count);
+
 	if (exec[0])
 		state->start_bin = exec[0]->ct0ca;
 	if (exec[1])
@@ -436,6 +436,19 @@ vc4_flush_caches(struct drm_device *dev)
 		  VC4_SET_FIELD(0xf, V3D_SLCACTL_ICC));
 }
 
+static void
+vc4_flush_texture_caches(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	V3D_WRITE(V3D_L2CACTL,
+		  V3D_L2CACTL_L2CCLR);
+
+	V3D_WRITE(V3D_SLCACTL,
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T1CC) |
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T0CC));
+}
+
 /* Sets the registers for the next job to be actually be executed in
  * the hardware.
  *
@@ -490,6 +503,14 @@ vc4_submit_next_render_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	/* A previous RCL may have written to one of our textures, and
+	 * our full cache flush at bin time may have occurred before
+	 * that RCL completed.  Flush the texture cache now, but not
+	 * the instructions or uniforms (since we don't write those
+	 * from an RCL).
+	 */
+	vc4_flush_texture_caches(dev);
+
 	submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 7e5f30e234b1..d08753e8fd94 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -713,7 +713,7 @@ extern int vmw_present_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 extern int vmw_present_readback_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
-extern unsigned int vmw_fops_poll(struct file *filp,
+extern __poll_t vmw_fops_poll(struct file *filp,
 				  struct poll_table_struct *wait);
 extern ssize_t vmw_fops_read(struct file *filp, char __user *buffer,
 			     size_t count, loff_t *offset);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 01be355525e4..67f844678ac8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -412,7 +412,7 @@ out_clips:
  * Wrapper around the drm_poll function that makes sure the device is
  * processing the fifo if drm_poll decides to wait.
  */
-unsigned int vmw_fops_poll(struct file *filp, struct poll_table_struct *wait)
+__poll_t vmw_fops_poll(struct file *filp, struct poll_table_struct *wait)
 {
 	struct drm_file *file_priv = filp->private_data;
 	struct vmw_private *dev_priv =
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 2fb21250f847..1107d6d03506 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1848,7 +1848,7 @@ u32 vmw_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
  */
 int vmw_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	return -ENOSYS;
+	return -EINVAL;
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index b8a09807c5de..3824595fece1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -266,8 +266,8 @@ static const struct drm_connector_funcs vmw_legacy_connector_funcs = {
 	.set_property = vmw_du_connector_set_property,
 	.destroy = vmw_ldu_connector_destroy,
 	.reset = vmw_du_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = vmw_du_connector_duplicate_state,
+	.atomic_destroy_state = vmw_du_connector_destroy_state,
 	.atomic_set_property = vmw_du_connector_atomic_set_property,
 	.atomic_get_property = vmw_du_connector_atomic_get_property,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index bc5f6026573d..63a4cd794b73 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -420,8 +420,8 @@ static const struct drm_connector_funcs vmw_sou_connector_funcs = {
 	.set_property = vmw_du_connector_set_property,
 	.destroy = vmw_sou_connector_destroy,
 	.reset = vmw_du_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = vmw_du_connector_duplicate_state,
+	.atomic_destroy_state = vmw_du_connector_destroy_state,
 	.atomic_set_property = vmw_du_connector_atomic_set_property,
 	.atomic_get_property = vmw_du_connector_atomic_get_property,
 };