Merge tag 'v4.6-rc6' into x86/asm, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

32 files changed, 401 insertions, 111 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b77489dec6e8..1bcbade479dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1591,6 +1591,7 @@ struct amdgpu_uvd {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
+	unsigned		fw_version;
 	void			*saved_bo;
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index d6b0bff510aa..b7b583c42ea8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -425,6 +425,10 @@ static int acp_resume(void *handle)
 	struct acp_pm_domain *apd;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	/* return early if no ACP */
+	if (!adev->acp.acp_genpd)
+		return 0;
+
 	/* SMU block will power on ACP irrespective of ACP runtime status.
 	 * Power off explicitly based on genpd ACP runtime status so that ACP
 	 * hw and ACP-genpd status are in sync.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 0020a0ea43ff..35a1248aaa77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -63,10 +63,6 @@ bool amdgpu_has_atpx(void) {
 	return amdgpu_atpx_priv.atpx_detected;
 }
 
-bool amdgpu_has_atpx_dgpu_power_cntl(void) {
-	return amdgpu_atpx_priv.atpx.functions.power_cntl;
-}
-
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
@@ -146,6 +142,13 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
  */
 static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 {
+	/* make sure required functions are enabled */
+	/* dGPU power control is required */
+	if (atpx->functions.power_cntl == false) {
+		printk("ATPX dGPU power cntl not present, forcing\n");
+		atpx->functions.power_cntl = true;
+	}
+
 	if (atpx->functions.px_params) {
 		union acpi_object *info;
 		struct atpx_px_params output;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 612117478b57..2139da773da6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -62,12 +62,6 @@ static const char *amdgpu_asic_name[] = {
 	"LAST",
 };
 
-#if defined(CONFIG_VGA_SWITCHEROO)
-bool amdgpu_has_atpx_dgpu_power_cntl(void);
-#else
-static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; }
-#endif
-
 bool amdgpu_device_is_px(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = dev->dev_private;
@@ -1485,7 +1479,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 	if (amdgpu_runtime_pm == 1)
 		runtime = true;
-	if (amdgpu_device_is_px(ddev) && amdgpu_has_atpx_dgpu_power_cntl())
+	if (amdgpu_device_is_px(ddev))
 		runtime = true;
 	vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, runtime);
 	if (runtime)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index aef70db16832..b04337de65d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			fw_info.feature = adev->vce.fb_version;
 			break;
 		case AMDGPU_INFO_FW_UVD:
-			fw_info.ver = 0;
+			fw_info.ver = adev->uvd.fw_version;
 			fw_info.feature = 0;
 			break;
 		case AMDGPU_INFO_FW_GMC:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 8d432e6901af..81bd964d3dfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -53,7 +53,7 @@ struct amdgpu_hpd;
 
 #define AMDGPU_MAX_HPD_PINS 6
 #define AMDGPU_MAX_CRTCS 6
-#define AMDGPU_MAX_AFMT_BLOCKS 7
+#define AMDGPU_MAX_AFMT_BLOCKS 9
 
 enum amdgpu_rmx_type {
 	RMX_OFF,
@@ -309,8 +309,8 @@ struct amdgpu_mode_info {
 	struct atom_context *atom_context;
 	struct card_info *atom_card_info;
 	bool mode_config_initialized;
-	struct amdgpu_crtc *crtcs[6];
-	struct amdgpu_afmt *afmt[7];
+	struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS];
+	struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS];
 	/* DVI-I properties */
 	struct drm_property *coherent_mode_property;
 	/* DAC enable load detect */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6f3369de232f..11af4492b4be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -223,6 +223,8 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
 	struct amdgpu_bo *rbo = container_of(bo, struct amdgpu_bo, tbo);
 
+	if (amdgpu_ttm_tt_get_usermm(bo->ttm))
+		return -EPERM;
 	return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 338da80006b6..871018c634e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -158,6 +158,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
 		version_major, version_minor, family_id);
 
+	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
+				(family_id << 8));
+
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		 +  AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE;
 	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
@@ -255,6 +258,8 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_UVD_HANDLES)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
 	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
 	ptr = adev->uvd.cpu_addr;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 4bec0c108cea..481a64fa9b47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -234,6 +234,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_VCE_HANDLES)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
 	/* TODO: suspending running encoding sessions isn't supported */
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 05b0353d3880..a4a2e6cc61bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -910,7 +910,10 @@ static int gmc_v7_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 static int gmc_v7_0_sw_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 02deb3229405..7a9db2c72c89 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -870,7 +870,10 @@ static int gmc_v8_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 #define mmMC_SEQ_MISC0_FIJI 0xA71
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 27fbd79d0daf..71ea0521ea96 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1672,13 +1672,19 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	u8 sinks[DRM_DP_MAX_SDP_STREAMS];
 	int i;
 
+	port = drm_dp_get_validated_port_ref(mgr, port);
+	if (!port)
+		return -EINVAL;
+
 	port_num = port->port_num;
 	mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent);
 	if (!mstb) {
 		mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num);
 
-		if (!mstb)
+		if (!mstb) {
+			drm_dp_put_port(port);
 			return -EINVAL;
+		}
 	}
 
 	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
@@ -1707,6 +1713,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	kfree(txmsg);
 fail_put:
 	drm_dp_put_mst_branch_device(mstb);
+	drm_dp_put_port(port);
 	return ret;
 }
 
@@ -1789,6 +1796,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 		req_payload.start_slot = cur_slots;
 		if (mgr->proposed_vcpis[i]) {
 			port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi);
+			port = drm_dp_get_validated_port_ref(mgr, port);
+			if (!port) {
+				mutex_unlock(&mgr->payload_lock);
+				return -EINVAL;
+			}
 			req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots;
 			req_payload.vcpi = mgr->proposed_vcpis[i]->vcpi;
 		} else {
@@ -1816,6 +1828,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			mgr->payloads[i].payload_state = req_payload.payload_state;
 		}
 		cur_slots += req_payload.num_slots;
+
+		if (port)
+			drm_dp_put_port(port);
 	}
 
 	for (i = 0; i < mgr->max_payloads; i++) {
@@ -2121,6 +2136,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 
 	if (mgr->mst_primary) {
 		int sret;
+		u8 guid[16];
+
 		sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE);
 		if (sret != DP_RECEIVER_CAP_SIZE) {
 			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
@@ -2135,6 +2152,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 			ret = -1;
 			goto out_unlock;
 		}
+
+		/* Some hubs forget their guids after they resume */
+		sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+		if (sret != 16) {
+			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
+			ret = -1;
+			goto out_unlock;
+		}
+		drm_dp_check_mstb_guid(mgr->mst_primary, guid);
+
 		ret = 0;
 	} else
 		ret = -1;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 09198d0b5814..306dde18a94a 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -572,6 +572,24 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 		goto fail;
 	}
 
+	/*
+	 * Set the GPU linear window to be at the end of the DMA window, where
+	 * the CMA area is likely to reside. This ensures that we are able to
+	 * map the command buffers while having the linear window overlap as
+	 * much RAM as possible, so we can optimize mappings for other buffers.
+	 *
+	 * For 3D cores only do this if MC2.0 is present, as with MC1.0 it leads
+	 * to different views of the memory on the individual engines.
+	 */
+	if (!(gpu->identity.features & chipFeatures_PIPE_3D) ||
+	    (gpu->identity.minor_features0 & chipMinorFeatures0_MC20)) {
+		u32 dma_mask = (u32)dma_get_required_mask(gpu->dev);
+		if (dma_mask < PHYS_OFFSET + SZ_2G)
+			gpu->memory_base = PHYS_OFFSET;
+		else
+			gpu->memory_base = dma_mask - SZ_2G + 1;
+	}
+
 	ret = etnaviv_hw_reset(gpu);
 	if (ret)
 		goto fail;
@@ -1566,7 +1584,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct etnaviv_gpu *gpu;
-	u32 dma_mask;
 	int err = 0;
 
 	gpu = devm_kzalloc(dev, sizeof(*gpu), GFP_KERNEL);
@@ -1576,18 +1593,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 	gpu->dev = &pdev->dev;
 	mutex_init(&gpu->lock);
 
-	/*
-	 * Set the GPU linear window to be at the end of the DMA window, where
-	 * the CMA area is likely to reside. This ensures that we are able to
-	 * map the command buffers while having the linear window overlap as
-	 * much RAM as possible, so we can optimize mappings for other buffers.
-	 */
-	dma_mask = (u32)dma_get_required_mask(dev);
-	if (dma_mask < PHYS_OFFSET + SZ_2G)
-		gpu->memory_base = PHYS_OFFSET;
-	else
-		gpu->memory_base = dma_mask - SZ_2G + 1;
-
 	/* Map registers: */
 	gpu->mmio = etnaviv_ioremap(pdev, NULL, dev_name(gpu->dev));
 	if (IS_ERR(gpu->mmio))
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 10480939159c..daba7ebb9699 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2634,8 +2634,9 @@ struct drm_i915_cmd_table {
 
 /* WaRsDisableCoarsePowerGating:skl,bxt */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \
-						 ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && \
-						  IS_SKL_REVID(dev, 0, SKL_REVID_F0)))
+						 IS_SKL_GT3(dev) || \
+						 IS_SKL_GT4(dev))
+
 /*
  * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
  * even when in MSI mode. This results in spurious interrupt warnings if the
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 18ba8139e922..4d30b60defda 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -501,19 +501,24 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
-		down_read(&mm->mmap_sem);
-		while (pinned < npages) {
-			ret = get_user_pages_remote(work->task, mm,
-					obj->userptr.ptr + pinned * PAGE_SIZE,
-					npages - pinned,
-					!obj->userptr.read_only, 0,
-					pvec + pinned, NULL);
-			if (ret < 0)
-				break;
-
-			pinned += ret;
+		ret = -EFAULT;
+		if (atomic_inc_not_zero(&mm->mm_users)) {
+			down_read(&mm->mmap_sem);
+			while (pinned < npages) {
+				ret = get_user_pages_remote
+					(work->task, mm,
+					 obj->userptr.ptr + pinned * PAGE_SIZE,
+					 npages - pinned,
+					 !obj->userptr.read_only, 0,
+					 pvec + pinned, NULL);
+				if (ret < 0)
+					break;
+
+				pinned += ret;
+			}
+			up_read(&mm->mmap_sem);
+			mmput(mm);
 		}
-		up_read(&mm->mmap_sem);
 	}
 
 	mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 6a978ce80244..5c6080fd0968 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -841,11 +841,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
@@ -1913,15 +1913,18 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	int ret;
 
-	ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS);
+	ret = intel_logical_ring_begin(request, 8 + WA_TAIL_DWORDS);
 	if (ret)
 		return ret;
 
+	/* We're using qword write, seqno should be aligned to 8 bytes. */
+	BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1);
+
 	/* w/a for post sync ops following a GPGPU operation we
 	 * need a prior CS_STALL, which is emitted by the flush
 	 * following the batch.
 	 */
-	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(5));
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf,
 				(PIPE_CONTROL_GLOBAL_GTT_IVB |
 				 PIPE_CONTROL_CS_STALL |
@@ -1929,7 +1932,10 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf, hws_seqno_address(request->ring));
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	/* We're thrashing one dword of HWS. */
+	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	return intel_logical_ring_advance_and_submit(request);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 347d4df49a9b..8ed3cf34f82d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2876,25 +2876,28 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
 			     int y)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	struct drm_framebuffer *fb = pstate->fb;
+	uint32_t width = 0, height = 0;
+
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(pstate->rotation))
+		swap(width, height);
 
 	/* for planar format */
 	if (fb->pixel_format == DRM_FORMAT_NV12) {
 		if (y)  /* y-plane data rate */
-			return intel_crtc->config->pipe_src_w *
-				intel_crtc->config->pipe_src_h *
+			return width * height *
 				drm_format_plane_cpp(fb->pixel_format, 0);
 		else    /* uv-plane data rate */
-			return (intel_crtc->config->pipe_src_w/2) *
-				(intel_crtc->config->pipe_src_h/2) *
+			return (width / 2) * (height / 2) *
 				drm_format_plane_cpp(fb->pixel_format, 1);
 	}
 
 	/* for packed formats */
-	return intel_crtc->config->pipe_src_w *
-		intel_crtc->config->pipe_src_h *
-		drm_format_plane_cpp(fb->pixel_format, 0);
+	return width * height * drm_format_plane_cpp(fb->pixel_format, 0);
 }
 
 /*
@@ -2973,8 +2976,9 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		struct drm_framebuffer *fb = plane->state->fb;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (fb == NULL)
+		if (!to_intel_plane_state(plane->state)->visible)
 			continue;
+
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
 
@@ -3000,7 +3004,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		uint16_t plane_blocks, y_plane_blocks = 0;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (pstate->fb == NULL)
+		if (!to_intel_plane_state(pstate)->visible)
 			continue;
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
@@ -3123,26 +3127,36 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 {
 	struct drm_plane *plane = &intel_plane->base;
 	struct drm_framebuffer *fb = plane->state->fb;
+	struct intel_plane_state *intel_pstate =
+					to_intel_plane_state(plane->state);
 	uint32_t latency = dev_priv->wm.skl_latency[level];
 	uint32_t method1, method2;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
 	uint32_t res_blocks, res_lines;
 	uint32_t selected_result;
 	uint8_t cpp;
+	uint32_t width = 0, height = 0;
 
-	if (latency == 0 || !cstate->base.active || !fb)
+	if (latency == 0 || !cstate->base.active || !intel_pstate->visible)
 		return false;
 
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(plane->state->rotation))
+		swap(width, height);
+
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 	method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate),
 				 cpp, latency);
 	method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate),
 				 cstate->base.adjusted_mode.crtc_htotal,
-				 cstate->pipe_src_w,
-				 cpp, fb->modifier[0],
+				 width,
+				 cpp,
+				 fb->modifier[0],
 				 latency);
 
-	plane_bytes_per_line = cstate->pipe_src_w * cpp;
+	plane_bytes_per_line = width * cpp;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 45ce45a5e122..9121646d7c4d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -968,7 +968,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 
 	/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
 	tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
-	if (IS_SKL_REVID(dev, SKL_REVID_F0, SKL_REVID_F0) ||
+	if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
 	    IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
 		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
 	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
@@ -1085,7 +1085,8 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_F0)) {
+	/* This is tied to WaForceContextSaveRestoreNonCoherent */
+	if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
 		/*
 		 *Use Force Non-Coherent whenever executing a 3D context. This
 		 * is a workaround for a possible hang in the unlikely event
@@ -2090,10 +2091,12 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = ringbuf->obj;
+	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+	unsigned flags = PIN_OFFSET_BIAS | 4096;
 	int ret;
 
 	if (HAS_LLC(dev_priv) && !obj->stolen) {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, 0);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, flags);
 		if (ret)
 			return ret;
 
@@ -2109,7 +2112,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return -ENOMEM;
 		}
 	} else {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE,
+					    flags | PIN_MAPPABLE);
 		if (ret)
 			return ret;
 
@@ -2454,11 +2458,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 436d8f2b8682..68b6f69aa682 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1189,7 +1189,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		dev_priv->uncore.funcs.force_wake_get =
 			fw_domains_get_with_thread_status;
-		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
+		if (IS_HASWELL(dev))
+			dev_priv->uncore.funcs.force_wake_put =
+				fw_domains_put_with_fifo;
+		else
+			dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_ACK_HSW);
 	} else if (IS_IVYBRIDGE(dev)) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index ae96ebc490fb..e81aefe5ffa7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1276,18 +1276,18 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		break;
 	default:
 		if (disp->dithering_mode) {
+			nv_connector->dithering_mode = DITHERING_MODE_AUTO;
 			drm_object_attach_property(&connector->base,
 						   disp->dithering_mode,
 						   nv_connector->
 						   dithering_mode);
-			nv_connector->dithering_mode = DITHERING_MODE_AUTO;
 		}
 		if (disp->dithering_depth) {
+			nv_connector->dithering_depth = DITHERING_DEPTH_AUTO;
 			drm_object_attach_property(&connector->base,
 						   disp->dithering_depth,
 						   nv_connector->
 						   dithering_depth);
-			nv_connector->dithering_depth = DITHERING_DEPTH_AUTO;
 		}
 		break;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index c56a886229f1..b2de290da16f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/eng