Merge tag 'drm-fixes-for-v4.13-rc1' of git://people.freedesktop.org/~airlied/linux

Pull more drm updates from Dave Airlie:
 "i915, amd and some core fixes + mediatek color support.

  Some fixes tree came in since the main pull request for rc1, primarily
  i915 and drm-misc and one amd fix. The drm core vblank regression fix
  is probably the most important thing.

  I've also added the mediatek feature pull, it wasn't that big and
  didn't look like it would have any impact outside of mediatek, in fact
  it looks to just be a single feature, and some cleanups"

* tag 'drm-fixes-for-v4.13-rc1' of git://people.freedesktop.org/~airlied/linux: (31 commits)
  drm/i915: Make DP-MST connector info work
  drm/i915/gvt: Use fence error from GVT request for workload status
  drm/i915/gvt: remove scheduler_mutex in per-engine workload_thread
  drm/i915/gvt: Revert "drm/i915/gvt: Fix possible recursive locking issue"
  drm/i915/gvt: Audit the command buffer address
  drm/i915/gvt: Fix a memory leak in intel_gvt_init_gtt()
  drm/rockchip: fix NULL check on devm_kzalloc() return value
  drm/i915/fbdev: Check for existence of ifbdev->vma before operations
  drm/radeon: Fix eDP for single-display iMac10,1 (v2)
  drm/i915: Hold RPM wakelock while initializing OA buffer
  drm/i915/cnl: Fix the CURSOR_COEFF_MASK used in DDI Vswing Programming
  drm/i915/cfl: Fix Workarounds.
  drm/i915: Avoid undefined behaviour of "u32 >> 32"
  drm/i915: reintroduce VLV/CHV PFI programming power domain workaround
  drm/i915: Fix an error checking test
  drm/i915: Disable MSI for all pre-gen5
  drm/atomic: Add missing drm_atomic_state_clear to atomic_remove_fb
  drm: vblank: Fix vblank timestamp update
  drm/i915/gvt: Make function dpy_reg_mmio_readx safe
  drm/mediatek: separate color module to fixup error memory reallocation
  ...

32 files changed, 372 insertions, 214 deletions

diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 99f9a4beb859..67fe19e5a9c6 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -161,7 +161,7 @@ struct drm_bridge *drm_panel_bridge_add(struct drm_panel *panel,
 	int ret;
 
 	if (!panel)
-		return ERR_PTR(EINVAL);
+		return ERR_PTR(-EINVAL);
 
 	panel_bridge = devm_kzalloc(panel->dev, sizeof(*panel_bridge),
 				    GFP_KERNEL);
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index fc8ef42203ec..b3ef4f1c2630 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -832,6 +832,7 @@ unlock:
 		drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK) {
+		drm_atomic_state_clear(state);
 		drm_modeset_backoff(&ctx);
 		goto retry;
 	}
diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index 463e4d81fb0d..e9f33cd805dd 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -242,7 +242,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 	 * Otherwise reinitialize delayed at next vblank interrupt and assign 0
 	 * for now, to mark the vblanktimestamp as invalid.
 	 */
-	if (!rc && in_vblank_irq)
+	if (!rc && !in_vblank_irq)
 		t_vblank = (struct timeval) {0, 0};
 
 	store_vblank(dev, pipe, diff, &t_vblank, cur_vblank);
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 51241de5e7a7..713848c36349 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -2536,6 +2536,11 @@ static int scan_workload(struct intel_vgpu_workload *workload)
 		gma_head == gma_tail)
 		return 0;
 
+	if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = ip_gma_set(&s, gma_head);
 	if (ret)
 		goto out;
@@ -2579,6 +2584,11 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	s.rb_va = wa_ctx->indirect_ctx.shadow_va;
 	s.workload = workload;
 
+	if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = ip_gma_set(&s, gma_head);
 	if (ret)
 		goto out;
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e0261fcc5b50..2deb05f618fb 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -197,6 +197,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 			(PORT_B << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
+		if (IS_BROADWELL(dev_priv)) {
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_B)) &=
+				~PORT_CLK_SEL_MASK;
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_B)) |=
+				PORT_CLK_SEL_LCPLL_810;
+		}
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_B)) |= DDI_BUF_CTL_ENABLE;
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_B)) &= ~DDI_BUF_IS_IDLE;
 		vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT;
@@ -211,6 +217,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 			(PORT_C << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
+		if (IS_BROADWELL(dev_priv)) {
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_C)) &=
+				~PORT_CLK_SEL_MASK;
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_C)) |=
+				PORT_CLK_SEL_LCPLL_810;
+		}
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_C)) |= DDI_BUF_CTL_ENABLE;
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_C)) &= ~DDI_BUF_IS_IDLE;
 		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED;
@@ -225,6 +237,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 			(PORT_D << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
+		if (IS_BROADWELL(dev_priv)) {
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_D)) &=
+				~PORT_CLK_SEL_MASK;
+			vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_D)) |=
+				PORT_CLK_SEL_LCPLL_810;
+		}
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_D)) |= DDI_BUF_CTL_ENABLE;
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_D)) &= ~DDI_BUF_IS_IDLE;
 		vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
@@ -244,6 +262,10 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 
 		vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED;
 	}
+
+	/* Clear host CRT status, so guest couldn't detect this host CRT. */
+	if (IS_BROADWELL(dev_priv))
+		vgpu_vreg(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK;
 }
 
 static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 66374dba3b1a..6166e34d892b 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2259,6 +2259,8 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt)
 		ret = setup_spt_oos(gvt);
 		if (ret) {
 			gvt_err("fail to initialize SPT oos\n");
+			dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL);
+			__free_page(gvt->gtt.scratch_ggtt_page);
 			return ret;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1414d7e6148d..17febe830ff6 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -367,21 +367,24 @@ static int lcpll_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int dpy_reg_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	*(u32 *)p_data = (1 << 17);
-	return 0;
-}
-
-static int dpy_reg_mmio_read_2(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes)
-{
-	*(u32 *)p_data = 3;
-	return 0;
-}
+	switch (offset) {
+	case 0xe651c:
+	case 0xe661c:
+	case 0xe671c:
+	case 0xe681c:
+		vgpu_vreg(vgpu, offset) = 1 << 17;
+		break;
+	case 0xe6c04:
+		vgpu_vreg(vgpu, offset) = 0x3;
+		break;
+	case 0xe6e1c:
+		vgpu_vreg(vgpu, offset) = 0x2f << 16;
+		break;
+	default:
+		return -EINVAL;
+	}
 
-static int dpy_reg_mmio_read_3(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes)
-{
-	*(u32 *)p_data = (0x2f << 16);
+	read_vreg(vgpu, offset, p_data, bytes);
 	return 0;
 }
 
@@ -1925,7 +1928,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_F(_PCH_DPD_AUX_CH_CTL, 6 * 4, 0, 0, 0, D_PRE_SKL, NULL,
 		dp_aux_ch_ctl_mmio_write);
 
-	MMIO_RO(PCH_ADPA, D_ALL, 0, ADPA_CRT_HOTPLUG_MONITOR_MASK, NULL, pch_adpa_mmio_write);
+	MMIO_DH(PCH_ADPA, D_PRE_SKL, NULL, pch_adpa_mmio_write);
 
 	MMIO_DH(_PCH_TRANSACONF, D_ALL, NULL, transconf_mmio_write);
 	MMIO_DH(_PCH_TRANSBCONF, D_ALL, NULL, transconf_mmio_write);
@@ -2011,8 +2014,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(0xe661c, D_ALL, dpy_reg_mmio_read, NULL);
 	MMIO_DH(0xe671c, D_ALL, dpy_reg_mmio_read, NULL);
 	MMIO_DH(0xe681c, D_ALL, dpy_reg_mmio_read, NULL);
-	MMIO_DH(0xe6c04, D_ALL, dpy_reg_mmio_read_2, NULL);
-	MMIO_DH(0xe6e1c, D_ALL, dpy_reg_mmio_read_3, NULL);
+	MMIO_DH(0xe6c04, D_ALL, dpy_reg_mmio_read, NULL);
+	MMIO_DH(0xe6e1c, D_ALL, dpy_reg_mmio_read, NULL);
 
 	MMIO_RO(PCH_PORT_HOTPLUG, D_ALL, 0,
 		PORTA_HOTPLUG_STATUS_MASK
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 1ae0b4083ce1..fd0c85f9ef3c 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -232,16 +232,20 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu)
 	struct device *dev = mdev_dev(vgpu->vdev.mdev);
 	unsigned long gfn;
 
-	mutex_lock(&vgpu->vdev.cache_lock);
-	while ((node = rb_first(&vgpu->vdev.cache))) {
+	for (;;) {
+		mutex_lock(&vgpu->vdev.cache_lock);
+		node = rb_first(&vgpu->vdev.cache);
+		if (!node) {
+			mutex_unlock(&vgpu->vdev.cache_lock);
+			break;
+		}
 		dma = rb_entry(node, struct gvt_dma, node);
 		gvt_dma_unmap_iova(vgpu, dma->iova);
 		gfn = dma->gfn;
-
-		vfio_unpin_pages(dev, &gfn, 1);
 		__gvt_cache_remove_entry(vgpu, dma);
+		mutex_unlock(&vgpu->vdev.cache_lock);
+		vfio_unpin_pages(dev, &gfn, 1);
 	}
-	mutex_unlock(&vgpu->vdev.cache_lock);
 }
 
 static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt,
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 488fdea348a9..4f7057d62d88 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -174,15 +174,6 @@ static int shadow_context_status_change(struct notifier_block *nb,
 		atomic_set(&workload->shadow_ctx_active, 1);
 		break;
 	case INTEL_CONTEXT_SCHEDULE_OUT:
-		/* If the status is -EINPROGRESS means this workload
-		 * doesn't meet any issue during dispatching so when
-		 * get the SCHEDULE_OUT set the status to be zero for
-		 * good. If the status is NOT -EINPROGRESS means there
-		 * is something wrong happened during dispatching and
-		 * the status should not be set to zero
-		 */
-		if (workload->status == -EINPROGRESS)
-			workload->status = 0;
 		atomic_set(&workload->shadow_ctx_active, 0);
 		break;
 	default:
@@ -427,6 +418,18 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
+		/* If this request caused GPU hang, req->fence.error will
+		 * be set to -EIO. Use -EIO to set workload status so
+		 * that when this request caused GPU hang, didn't trigger
+		 * context switch interrupt to guest.
+		 */
+		if (likely(workload->status == -EINPROGRESS)) {
+			if (workload->req->fence.error == -EIO)
+				workload->status = -EIO;
+			else
+				workload->status = 0;
+		}
+
 		i915_gem_request_put(fetch_and_zero(&workload->req));
 
 		if (!workload->status && !vgpu->resetting) {
@@ -464,8 +467,6 @@ struct workload_thread_param {
 	int ring_id;
 };
 
-static DEFINE_MUTEX(scheduler_mutex);
-
 static int workload_thread(void *priv)
 {
 	struct workload_thread_param *p = (struct workload_thread_param *)priv;
@@ -497,8 +498,6 @@ static int workload_thread(void *priv)
 		if (!workload)
 			break;
 
-		mutex_lock(&scheduler_mutex);
-
 		gvt_dbg_sched("ring id %d next workload %p vgpu %d\n",
 				workload->ring_id, workload,
 				workload->vgpu->id);
@@ -537,9 +536,6 @@ complete:
 					FORCEWAKE_ALL);
 
 		intel_runtime_pm_put(gvt->dev_priv);
-
-		mutex_unlock(&scheduler_mutex);
-
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3f44076ec8a0..00d8967c8512 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3087,7 +3087,7 @@ static void intel_connector_info(struct seq_file *m,
 			   connector->display_info.cea_rev);
 	}
 
-	if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST)
+	if (!intel_encoder)
 		return;
 
 	switch (connector->connector_type) {
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ee2325b180e7..fc307e03943c 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1132,10 +1132,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	 * and the registers being closely associated.
 	 *
 	 * According to chipset errata, on the 965GM, MSI interrupts may
-	 * be lost or delayed, but we use them anyways to avoid
-	 * stuck interrupts on some machines.
+	 * be lost or delayed, and was defeatured. MSI interrupts seem to
+	 * get lost on g4x as well, and interrupt delivery seems to stay
+	 * properly dead afterwards. So we'll just disable them for all
+	 * pre-gen5 chipsets.
 	 */
-	if (!IS_I945G(dev_priv) && !IS_I945GM(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 5) {
 		if (pci_enable_msi(pdev) < 0)
 			DRM_DEBUG_DRIVER("can't enable MSI");
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 9337446f1068..054b2e54cdaf 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -288,20 +288,26 @@ static int eb_create(struct i915_execbuffer *eb)
 		 * direct lookup.
 		 */
 		do {
+			unsigned int flags;
+
+			/* While we can still reduce the allocation size, don't
+			 * raise a warning and allow the allocation to fail.
+			 * On the last pass though, we want to try as hard
+			 * as possible to perform the allocation and warn
+			 * if it fails.
+			 */
+			flags = GFP_TEMPORARY;
+			if (size > 1)
+				flags |= __GFP_NORETRY | __GFP_NOWARN;
+
 			eb->buckets = kzalloc(sizeof(struct hlist_head) << size,
-					      GFP_TEMPORARY |
-					      __GFP_NORETRY |
-					      __GFP_NOWARN);
+					      flags);
 			if (eb->buckets)
 				break;
 		} while (--size);
 
-		if (unlikely(!eb->buckets)) {
-			eb->buckets = kzalloc(sizeof(struct hlist_head),
-					      GFP_TEMPORARY);
-			if (unlikely(!eb->buckets))
-				return -ENOMEM;
-		}
+		if (unlikely(!size))
+			return -ENOMEM;
 
 		eb->lut_size = size;
 	} else {
@@ -452,7 +458,7 @@ eb_add_vma(struct i915_execbuffer *eb,
 			return err;
 	}
 
-	if (eb->lut_size >= 0) {
+	if (eb->lut_size > 0) {
 		vma->exec_handle = entry->handle;
 		hlist_add_head(&vma->exec_node,
 			       &eb->buckets[hash_32(entry->handle,
@@ -894,7 +900,7 @@ static void eb_release_vmas(const struct i915_execbuffer *eb)
 static void eb_reset_vmas(const struct i915_execbuffer *eb)
 {
 	eb_release_vmas(eb);
-	if (eb->lut_size >= 0)
+	if (eb->lut_size > 0)
 		memset(eb->buckets, 0,
 		       sizeof(struct hlist_head) << eb->lut_size);
 }
@@ -903,7 +909,7 @@ static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
-	if (eb->lut_size >= 0)
+	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
 
@@ -2180,8 +2186,11 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		}
 	}
 
-	if (eb_create(&eb))
-		return -ENOMEM;
+	err = eb_create(&eb);
+	if (err)
+		goto err_out_fence;
+
+	GEM_BUG_ON(!eb.lut_size);
 
 	/*
 	 * Take a local wakeref for preparing to dispatch the execbuf as
@@ -2340,6 +2349,7 @@ err_unlock:
 err_rpm:
 	intel_runtime_pm_put(eb.i915);
 	eb_destroy(&eb);
+err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
 err_in_fence:
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 38c44407bafc..9cd22f83b0cf 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2067,10 +2067,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			return ret;
 	}
 
-	ret = alloc_oa_buffer(dev_priv);
-	if (ret)
-		goto err_oa_buf_alloc;
-
 	/* PRM - observability performance counters:
 	 *
 	 *   OACONTROL, performance counter enable, note:
@@ -2086,6 +2082,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	intel_runtime_pm_get(dev_priv);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
+	ret = alloc_oa_buffer(dev_priv);
+	if (ret)
+		goto err_oa_buf_alloc;
+
 	ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv);
 	if (ret)
 		goto err_enable;
@@ -2097,11 +2097,11 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	return 0;
 
 err_enable:
-	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
 	free_oa_buffer(dev_priv);
 
 err_oa_buf_alloc:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	intel_runtime_pm_put(dev_priv);
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c8647cfa81ba..64cc674b652a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1802,7 +1802,7 @@ enum skl_disp_power_wells {
 #define   POST_CURSOR_2(x)		((x) << 6)
 #define   POST_CURSOR_2_MASK		(0x3F << 6)
 #define   CURSOR_COEFF(x)		((x) << 0)
-#define   CURSOR_COEFF_MASK		(0x3F << 6)
+#define   CURSOR_COEFF_MASK		(0x3F << 0)
 
 #define _CNL_PORT_TX_DW5_GRP_AE		0x162354
 #define _CNL_PORT_TX_DW5_GRP_B		0x1623D4
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index b8914db7d2e1..1241e5891b29 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -491,6 +491,14 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 	int cdclk = cdclk_state->cdclk;
 	u32 val, cmd;
 
+	/* There are cases where we can end up here with power domains
+	 * off and a CDCLK frequency other than the minimum, like when
+	 * issuing a modeset without actually changing any display after
+	 * a system suspend.  So grab the PIPE-A domain, which covers
+	 * the HW blocks needed for the following programming.
+	 */
+	intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
+
 	if (cdclk >= 320000) /* jump to highest voltage for 400MHz too */
 		cmd = 2;
 	else if (cdclk == 266667)
@@ -549,6 +557,8 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 	intel_update_cdclk(dev_priv);
 
 	vlv_program_pfi_credits(dev_priv);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
 }
 
 static void chv_set_cdclk(struct drm_i915_private *dev_priv,
@@ -568,6 +578,14 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 		return;
 	}
 
+	/* There are cases where we can end up here with power domains
+	 * off and a CDCLK frequency other than the minimum, like when
+	 * issuing a modeset without actually changing any display after
+	 * a system suspend.  So grab the PIPE-A domain, which covers
+	 * the HW blocks needed for the following programming.
+	 */
+	intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
+
 	/*
 	 * Specs are full of misinformation, but testing on actual
 	 * hardware has shown that we just need to write the desired
@@ -590,6 +608,8 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 	intel_update_cdclk(dev_priv);
 
 	vlv_program_pfi_credits(dev_priv);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
 }
 
 static int bdw_calc_cdclk(int max_pixclk)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index a4487c5b7e37..5b4de719bec3 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -821,9 +821,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
 		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
 
-	/* WaDisableKillLogic:bxt,skl,kbl,cfl */
-	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-		   ECOCHK_DIS_TLB);
+	/* WaDisableKillLogic:bxt,skl,kbl */
+	if (!IS_COFFEELAKE(dev_priv))
+		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+			   ECOCHK_DIS_TLB);
 
 	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
 	/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
@@ -894,10 +895,9 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 	WA_SET_BIT_MASKED(HDC_CHICKEN0,
 			  HDC_FORCE_NON_COHERENT);
 
-	/* WaDisableHDCInvalidation:skl,bxt,kbl */
-	if (!IS_COFFEELAKE(dev_priv))
-		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-			   BDW_DISABLE_HDC_INVALIDATION);
+	/* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
+	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+		   BDW_DISABLE_HDC_INVALIDATION);
 
 	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
 	if (IS_SKYLAKE(dev_priv) ||
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 03347c6ae599..0c4cde6b2e6f 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -535,13 +535,14 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
 
 	drm_fb_helper_fini(&ifbdev->helper);
 
-	if (ifbdev->fb) {
+	if (ifbdev->vma) {
 		mutex_lock(&ifbdev->helper.dev->struct_mutex);
 		intel_unpin_fb_vma(ifbdev->vma);
 		mutex_unlock(&ifbdev->helper.dev->struct_mutex);
+	}
 
+	if (ifbdev->fb)
 		drm_framebuffer_remove(&ifbdev->fb->base);
-	}
 
 	kfree(ifbdev);
 }
@@ -765,7 +766,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 	struct fb_info *info;
 
-	if (!ifbdev || !ifbdev->fb)
+	if (!ifbdev || !ifbdev->vma)
 		return;
 
 	info = ifbdev->helper.fbdev;
@@ -812,7 +813,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
 
-	if (ifbdev && ifbdev->fb)
+	if (ifbdev && ifbdev->vma)
 		drm_fb_helper_hotplug_event(&ifbdev->helper);
 }
 
@@ -824,7 +825,7 @@ void intel_fbdev_restore_mode(struct drm_device *dev)
 		return;
 
 	intel_fbdev_sync(ifbdev);
-	if (!ifbdev->fb)
+	if (!ifbdev->vma)
 		return;
 
 	if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper) == 0)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
index d15cc9d3a5cd..89dc25a5a53b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
@@ -246,9 +246,9 @@ static int igt_dmabuf_export_vmap(void *arg)
 	i915_gem_object_put(obj);
 
 	ptr = dma_buf_vmap(dmabuf);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
-		pr_err("dma_buf_vmap failed with err=%d\n", err);
+	if (!ptr) {
+		pr_err("dma_buf_vmap failed\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index bf2e5be1ab30..e37b55a23a65 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -1,4 +1,5 @@
-mediatek-drm-y := mtk_disp_ovl.o \
+mediatek-drm-y := mtk_disp_color.o \
+		  mtk_disp_ovl.o \
 		  mtk_disp_rdma.o \
 		  mtk_drm_crtc.o \
 		  mtk_drm_ddp.o \
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c
new file mode 100644
index 000000000000..ef79a6d55646
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c
@@ -0,0 +1,176 @@
+/*
+ * Copyright (c) 2017 MediaTek Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <drm/drmP.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+
+#include "mtk_drm_crtc.h"
+#include "mtk_drm_ddp_comp.h"
+
+#define DISP_COLOR_CFG_MAIN			0x0400
+#define DISP_COLOR_START_MT2701			0x0f00
+#define DISP_COLOR_START_MT8173			0x0c00
+#define DISP_COLOR_START(comp)			((comp)->data->color_offset)
+#define DISP_COLOR_WIDTH(comp)			(DISP_COLOR_START(comp) + 0x50)
+#define DISP_COLOR_HEIGHT(comp)			(DISP_COLOR_START(comp) + 0x54)
+
+#define COLOR_BYPASS_ALL			BIT(7)
+#define COLOR_SEQ_SEL				BIT(13)
+
+struct mtk_disp_color_data {
+	unsigned int color_offset;
+};
+
+/**
+ * struct mtk_disp_color - DISP_COLOR driver structure
+ * @ddp_comp - structure containing type enum and hardware resources
+ * @crtc - associated crtc to report irq events to
+ */
+struct mtk_disp_color {
+	struct mtk_ddp_comp			ddp_comp;
+	struct drm_crtc				*crtc;
+	const struct mtk_disp_color_data	*data;
+};
+
+static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp)
+{
+	return container_of(comp, struct mtk_disp_color, ddp_comp);
+}
+
+static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w,
+			     unsigned int h, unsigned int vrefresh,
+			     unsigned int bpc)
+{
+	struct mtk_disp_color *color = comp_to_color(comp);
+
+	writel(w, comp->regs + DISP_COLOR_WIDTH(color));
+	writel(h, comp->regs + DISP_COLOR_HEIGHT(color));
+}
+
+static void mtk_color_start(struct mtk_ddp_comp *comp)
+{
+	struct mtk_disp_color *color = comp_to_color(comp);
+
+	writel(COLOR_BYPASS_ALL | COLOR_SEQ_SEL,
+	       comp->regs + DISP_COLOR_CFG_MAIN);
+	writel(0x1, comp->regs + DISP_COLOR_START(color));
+}
+
+static const struct mtk_ddp_comp_funcs mtk_disp_color_funcs = {
+	.config = mtk_color_config,
+	.start = mtk_color_start,
+};
+
+static int mtk_disp_color_bind(struct device *dev, struct device *master,
+			       void *data)
+{
+	struct mtk_disp_color *priv = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	int ret;
+
+	ret = mtk_ddp_comp_register(d