Merge tag 'drm-fixes-2018-11-16' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Live from Vancouver, SoC maintainer talk, this weeks drm fixes pull
  for rc3:

  omapdrm:
   - regression fixes for the reordering bridge stuff that went into rc1

  i915:
   - incorrect EU count fix
   - HPD storm fix
   - MST fix
   - relocation fix for gen4/5

  amdgpu:
   - huge page handling fix
   - IH ring setup
   - XGMI aperture setup
   - watermark setup fix

  misc:
   - docs and MST fix"

* tag 'drm-fixes-2018-11-16' of git://anongit.freedesktop.org/drm/drm: (23 commits)
  drm/i915: Account for scale factor when calculating initial phase
  drm/i915: Clean up skl_program_scaler()
  drm/i915: Move programming plane scaler to its own function.
  drm/i915/icl: Drop spurious register read from icl_dbuf_slices_update
  drm/i915: fix broadwell EU computation
  drm/amdgpu: fix huge page handling on Vega10
  drm/amd/pp: Fix truncated clock value when set watermark
  drm/amdgpu: fix bug with IH ring setup
  drm/meson: venc: dmt mode must use encp
  drm/amdgpu: set system aperture to cover whole FB region
  drm/i915: Fix hpd handling for pins with two encoders
  drm/i915/execlists: Force write serialisation into context image vs execution
  drm/i915/icl: Fix power well 2 wrt. DC-off toggling order
  drm/i915: Fix NULL deref when re-enabling HPD IRQs on systems with MST
  drm/i915: Fix possible race in intel_dp_add_mst_connector()
  drm/i915/ringbuffer: Delay after EMIT_INVALIDATE for gen4/gen5
  drm/omap: dsi: Fix missing of_platform_depopulate()
  drm/omap: Move DISPC runtime PM handling to omapdrm
  drm/omap: dsi: Ensure the device is active during probe
  drm/omap: hdmi4: Ensure the device is active during bind
  ...

arch/arm/mach-omap2/display.c

@@ -209,11 +209,61 @@ static int __init omapdss_init_fbdev(void)
 
 	return 0;
 }
-#else
-static inline int omapdss_init_fbdev(void)
+
+static const char * const omapdss_compat_names[] __initconst = {
+	"ti,omap2-dss",
+	"ti,omap3-dss",
+	"ti,omap4-dss",
+	"ti,omap5-dss",
+	"ti,dra7-dss",
+};
+
+static struct device_node * __init omapdss_find_dss_of_node(void)
 {
-	return 0;
+	struct device_node *node;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
+		node = of_find_compatible_node(NULL, NULL,
+			omapdss_compat_names[i]);
+		if (node)
+			return node;
+	}
+
+	return NULL;
 }
+
+static int __init omapdss_init_of(void)
+{
+	int r;
+	struct device_node *node;
+	struct platform_device *pdev;
+
+	/* only create dss helper devices if dss is enabled in the .dts */
+
+	node = omapdss_find_dss_of_node();
+	if (!node)
+		return 0;
+
+	if (!of_device_is_available(node))
+		return 0;
+
+	pdev = of_find_device_by_node(node);
+
+	if (!pdev) {
+		pr_err("Unable to find DSS platform device\n");
+		return -ENODEV;
+	}
+
+	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
+	if (r) {
+		pr_err("Unable to populate DSS submodule devices\n");
+		return r;
+	}
+
+	return omapdss_init_fbdev();
+}
+omap_device_initcall(omapdss_init_of);
 #endif /* CONFIG_FB_OMAP2 */
 
 static void dispc_disable_outputs(void)
@@ -361,58 +411,3 @@ int omap_dss_reset(struct omap_hwmod *oh)
 
 	return r;
 }
-
-static const char * const omapdss_compat_names[] __initconst = {
-	"ti,omap2-dss",
-	"ti,omap3-dss",
-	"ti,omap4-dss",
-	"ti,omap5-dss",
-	"ti,dra7-dss",
-};
-
-static struct device_node * __init omapdss_find_dss_of_node(void)
-{
-	struct device_node *node;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
-		node = of_find_compatible_node(NULL, NULL,
-			omapdss_compat_names[i]);
-		if (node)
-			return node;
-	}
-
-	return NULL;
-}
-
-static int __init omapdss_init_of(void)
-{
-	int r;
-	struct device_node *node;
-	struct platform_device *pdev;
-
-	/* only create dss helper devices if dss is enabled in the .dts */
-
-	node = omapdss_find_dss_of_node();
-	if (!node)
-		return 0;
-
-	if (!of_device_is_available(node))
-		return 0;
-
-	pdev = of_find_device_by_node(node);
-
-	if (!pdev) {
-		pr_err("Unable to find DSS platform device\n");
-		return -ENODEV;
-	}
-
-	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
-	if (r) {
-		pr_err("Unable to populate DSS submodule devices\n");
-		return r;
-	}
-
-	return omapdss_init_fbdev();
-}
-omap_device_initcall(omapdss_init_of);

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -1632,13 +1632,6 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			continue;
 		}
 
-		/* First check if the entry is already handled */
-		if (cursor.pfn < frag_start) {
-			cursor.entry->huge = true;
-			amdgpu_vm_pt_next(adev, &cursor);
-			continue;
-		}
-
 		/* If it isn't already handled it can't be a huge page */
 		if (cursor.entry->huge) {
 			/* Add the entry to the relocated list to update it. */
@@ -1701,8 +1694,17 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 			}
 		} while (frag_start < entry_end);
 
-		if (frag >= shift)
+		if (amdgpu_vm_pt_descendant(adev, &cursor)) {
+			/* Mark all child entries as huge */
+			while (cursor.pfn < frag_start) {
+				cursor.entry->huge = true;
+				amdgpu_vm_pt_next(adev, &cursor);
+			}
+
+		} else if (frag >= shift) {
+			/* or just move on to the next on the same level. */
 			amdgpu_vm_pt_next(adev, &cursor);
+		}
 	}
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c

@@ -72,7 +72,7 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 
 	/* Program the system aperture low logical page number. */
 	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
-		     min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18);
+		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
 	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
 		/*
@@ -82,11 +82,11 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 		 * to get rid of the VM fault and hardware hang.
 		 */
 		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max((adev->gmc.vram_end >> 18) + 0x1,
+			     max((adev->gmc.fb_end >> 18) + 0x1,
 				 adev->gmc.agp_end >> 18));
 	else
 		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
+			     max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
 
 	/* Set default page address. */
 	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start

drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c

@@ -90,7 +90,7 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 
 	/* Program the system aperture low logical page number. */
 	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
-		     min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18);
+		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
 	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
 		/*
@@ -100,11 +100,11 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 		 * to get rid of the VM fault and hardware hang.
 		 */
 		WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max((adev->gmc.vram_end >> 18) + 0x1,
+			     max((adev->gmc.fb_end >> 18) + 0x1,
 				 adev->gmc.agp_end >> 18));
 	else
 		WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
+			     max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
 
 	/* Set default page address. */
 	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +

drivers/gpu/drm/amd/amdgpu/vega10_ih.c

@@ -129,7 +129,7 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	else
 		wptr_off = adev->wb.gpu_addr + (adev->irq.ih.wptr_offs * 4);
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO, lower_32_bits(wptr_off));
-	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFF);
+	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFFFF);
 
 	/* set rptr, wptr to 0 */
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0);

drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c

@@ -713,20 +713,20 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table,
 	for (i = 0; i < wm_with_clock_ranges->num_wm_dmif_sets; i++) {
 		table->WatermarkRow[1][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz /
+			1000));
 		table->WatermarkRow[1][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz /
+			1000));
 		table->WatermarkRow[1][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz /
+			1000));
 		table->WatermarkRow[1][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz /
+			1000));
 		table->WatermarkRow[1][i].WmSetting = (uint8_t)
 				wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
 	}
@@ -734,20 +734,20 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table,
 	for (i = 0; i < wm_with_clock_ranges->num_wm_mcif_sets; i++) {
 		table->WatermarkRow[0][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz /
+			1000));
 		table->WatermarkRow[0][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz /
+			1000));
 		table->WatermarkRow[0][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz /
+			1000));
 		table->WatermarkRow[0][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
-			1000);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz /
+			1000));
 		table->WatermarkRow[0][i].WmSetting = (uint8_t)
 				wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
 	}

drivers/gpu/drm/drm_dp_mst_topology.c

@@ -1275,6 +1275,9 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_
 	mutex_lock(&mgr->lock);
 	mstb = mgr->mst_primary;
 
+	if (!mstb)
+		goto out;
+
 	for (i = 0; i < lct - 1; i++) {
 		int shift = (i % 2) ? 0 : 4;
 		int port_num = (rad[i / 2] >> shift) & 0xf;

drivers/gpu/drm/drm_fourcc.c

@@ -97,9 +97,9 @@ EXPORT_SYMBOL(drm_mode_legacy_fb_format);
 
 /**
  * drm_driver_legacy_fb_format - compute drm fourcc code from legacy description
+ * @dev: DRM device
  * @bpp: bits per pixels
  * @depth: bit depth per pixel
- * @native: use host native byte order
  *
  * Computes a drm fourcc pixel format code for the given @bpp/@depth values.
  * Unlike drm_mode_legacy_fb_format() this looks at the drivers mode_config,

drivers/gpu/drm/i915/intel_device_info.c

@@ -474,7 +474,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 			u8 eu_disabled_mask;
 			u32 n_disabled;
 
-			if (!(sseu->subslice_mask[ss] & BIT(ss)))
+			if (!(sseu->subslice_mask[s] & BIT(ss)))
 				/* skip disabled subslice */
 				continue;
 

drivers/gpu/drm/i915/intel_display.c

@@ -4850,8 +4850,31 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe)
  * chroma samples for both of the luma samples, and thus we don't
  * actually get the expected MPEG2 chroma siting convention :(
  * The same behaviour is observed on pre-SKL platforms as well.
+ *
+ * Theory behind the formula (note that we ignore sub-pixel
+ * source coordinates):
+ * s = source sample position
+ * d = destination sample position
+ *
+ * Downscaling 4:1:
+ * -0.5
+ * | 0.0
+ * | |     1.5 (initial phase)
+ * | |     |
+ * v v     v
+ * | s | s | s | s |
+ * |       d       |
+ *
+ * Upscaling 1:4:
+ * -0.5
+ * | -0.375 (initial phase)
+ * | |     0.0
+ * | |     |
+ * v v     v
+ * |       s       |
+ * | d | d | d | d |
  */
-u16 skl_scaler_calc_phase(int sub, bool chroma_cosited)
+u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_cosited)
 {
 	int phase = -0x8000;
 	u16 trip = 0;
@@ -4859,6 +4882,15 @@ u16 skl_scaler_calc_phase(int sub, bool chroma_cosited)
 	if (chroma_cosited)
 		phase += (sub - 1) * 0x8000 / sub;
 
+	phase += scale / (2 * sub);
+
+	/*
+	 * Hardware initial phase limited to [-0.5:1.5].
+	 * Since the max hardware scale factor is 3.0, we
+	 * should never actually excdeed 1.0 here.
+	 */
+	WARN_ON(phase < -0x8000 || phase > 0x18000);
+
 	if (phase < 0)
 		phase = 0x10000 + phase;
 	else
@@ -5067,13 +5099,20 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 
 	if (crtc->config->pch_pfit.enabled) {
 		u16 uv_rgb_hphase, uv_rgb_vphase;
+		int pfit_w, pfit_h, hscale, vscale;
 		int id;
 
 		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
 
-		uv_rgb_hphase = skl_scaler_calc_phase(1, false);
-		uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+		pfit_w = (crtc->config->pch_pfit.size >> 16) & 0xFFFF;
+		pfit_h = crtc->config->pch_pfit.size & 0xFFFF;
+
+		hscale = (crtc->config->pipe_src_w << 16) / pfit_w;
+		vscale = (crtc->config->pipe_src_h << 16) / pfit_h;
+
+		uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false);
+		uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false);
 
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |

drivers/gpu/drm/i915/intel_dp_mst.c

@@ -452,6 +452,10 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	if (!intel_connector)
 		return NULL;
 
+	intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
+	intel_connector->mst_port = intel_dp;
+	intel_connector->port = port;
+
 	connector = &intel_connector->base;
 	ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs,
 				 DRM_MODE_CONNECTOR_DisplayPort);
@@ -462,10 +466,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 
 	drm_connector_helper_add(connector, &intel_dp_mst_connector_helper_funcs);
 
-	intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
-	intel_connector->mst_port = intel_dp;
-	intel_connector->port = port;
-
 	for_each_pipe(dev_priv, pipe) {
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;

drivers/gpu/drm/i915/intel_drv.h

@@ -1646,7 +1646,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
 
-u16 skl_scaler_calc_phase(int sub, bool chroma_center);
+u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(const struct intel_crtc_state *crtc_state,
 		  u32 pixel_format);

drivers/gpu/drm/i915/intel_hotplug.c

@@ -228,7 +228,9 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		drm_for_each_connector_iter(connector, &conn_iter) {
 			struct intel_connector *intel_connector = to_intel_connector(connector);
 
-			if (intel_connector->encoder->hpd_pin == pin) {
+			/* Don't check MST ports, they don't have pins */
+			if (!intel_connector->mst_port &&
+			    intel_connector->encoder->hpd_pin == pin) {
 				if (connector->polled != intel_connector->polled)
 					DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
 							 connector->name);
@@ -395,37 +397,54 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	struct intel_encoder *encoder;
 	bool storm_detected = false;
 	bool queue_dig = false, queue_hp = false;
+	u32 long_hpd_pulse_mask = 0;
+	u32 short_hpd_pulse_mask = 0;
+	enum hpd_pin pin;
 
 	if (!pin_mask)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
+
+	/*
+	 * Determine whether ->hpd_pulse() exists for each pin, and
+	 * whether we have a short or a long pulse. This is needed
+	 * as each pin may have up to two encoders (HDMI and DP) and
+	 * only the one of them (DP) will have ->hpd_pulse().
+	 */
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		enum hpd_pin pin = encoder->hpd_pin;
 		bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder);
+		enum port port = encoder->port;
+		bool long_hpd;
 
+		pin = encoder->hpd_pin;
 		if (!(BIT(pin) & pin_mask))
 			continue;
 
-		if (has_hpd_pulse) {
-			bool long_hpd = long_mask & BIT(pin);
-			enum port port = encoder->port;
+		if (!has_hpd_pulse)
+			continue;
 
-			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
-					 long_hpd ? "long" : "short");
-			/*
-			 * For long HPD pulses we want to have the digital queue happen,
-			 * but we still want HPD storm detection to function.
-			 */
-			queue_dig = true;
-			if (long_hpd) {
-				dev_priv->hotplug.long_port_mask |= (1 << port);
-			} else {
-				/* for short HPD just trigger the digital queue */
-				dev_priv->hotplug.short_port_mask |= (1 << port);
-				continue;
-			}
+		long_hpd = long_mask & BIT(pin);
+
+		DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
+				 long_hpd ? "long" : "short");
+		queue_dig = true;
+
+		if (long_hpd) {
+			long_hpd_pulse_mask |= BIT(pin);
+			dev_priv->hotplug.long_port_mask |= BIT(port);
+		} else {
+			short_hpd_pulse_mask |= BIT(pin);
+			dev_priv->hotplug.short_port_mask |= BIT(port);
 		}
+	}
+
+	/* Now process each pin just once */
+	for_each_hpd_pin(pin) {
+		bool long_hpd;
+
+		if (!(BIT(pin) & pin_mask))
+			continue;
 
 		if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) {
 			/*
@@ -442,11 +461,22 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED)
 			continue;
 
-		if (!has_hpd_pulse) {
+		/*
+		 * Delegate to ->hpd_pulse() if one of the encoders for this
+		 * pin has it, otherwise let the hotplug_work deal with this
+		 * pin directly.
+		 */
+		if (((short_hpd_pulse_mask | long_hpd_pulse_mask) & BIT(pin))) {
+			long_hpd = long_hpd_pulse_mask & BIT(pin);
+		} else {
 			dev_priv->hotplug.event_bits |= BIT(pin);
+			long_hpd = true;
 			queue_hp = true;
 		}
 
+		if (!long_hpd)
+			continue;
+
 		if (intel_hpd_irq_storm_detect(dev_priv, pin)) {
 			dev_priv->hotplug.event_bits &= ~BIT(pin);
 			storm_detected = true;

drivers/gpu/drm/i915/intel_lrc.c

@@ -424,7 +424,8 @@ static u64 execlists_update_context(struct i915_request *rq)
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
 
-	/* True 32b PPGTT with dynamic page allocation: update PDP
+	/*
+	 * True 32b PPGTT with dynamic page allocation: update PDP
 	 * registers and point the unallocated PDPs to scratch page.
 	 * PML4 is allocated during ppgtt init, so this is not needed
 	 * in 48-bit mode.
@@ -432,6 +433,17 @@ static u64 execlists_update_context(struct i915_request *rq)
 	if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm))
 		execlists_update_context_pdps(ppgtt, reg_state);
 
+	/*
+	 * Make sure the context image is complete before we submit it to HW.
+	 *
+	 * Ostensibly, writes (including the WCB) should be flushed prior to
+	 * an uncached write such as our mmio register access, the empirical
+	 * evidence (esp. on Braswell) suggests that the WC write into memory
+	 * may not be visible to the HW prior to the completion of the UC
+	 * register write and that we may begin execution from the context
+	 * before its image is complete leading to invalid PD chasing.
+	 */
+	wmb();
 	return ce->lrc_desc;
 }
 

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -91,6 +91,7 @@ static int
 gen4_render_ring_flush(struct i915_request *rq, u32 mode)
 {
 	u32 cmd, *cs;
+	int i;
 
 	/*
 	 * read/write caches:
@@ -127,12 +128,45 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode)
 			cmd |= MI_INVALIDATE_ISP;
 	}
 
-	cs = intel_ring_begin(rq, 2);
+	i = 2;
+	if (mode & EMIT_INVALIDATE)
+		i += 20;
+
+	cs = intel_ring_begin(rq, i);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
 	*cs++ = cmd;
-	*cs++ = MI_NOOP;
+
+	/*
+	 * A random delay to let the CS invalidate take effect? Without this
+	 * delay, the GPU relocation path fails as the CS does not see
+	 * the updated contents. Just as important, if we apply the flushes
+	 * to the EMIT_FLUSH branch (i.e. immediately after the relocation
+	 * write and before the invalidate on the next batch), the relocations
+	 * still fail. This implies that is a delay following invalidation
+	 * that is required to reset the caches as opposed to a delay to
+	 * ensure the memory is written.
+	 */
+	if (mode & EMIT_INVALIDATE) {
+		*cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+		*cs++ = i915_ggtt_offset(rq->engine->scratch) |
+			PIPE_CONTROL_GLOBAL_GTT;
+		*cs++ = 0;
+		*cs++ = 0;
+
+		for (i = 0; i < 12; i++)
+			*cs++ = MI_FLUSH;
+
+		*cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+		*cs++ = i915_ggtt_offset(rq->engine->scratch) |
+			PIPE_CONTROL_GLOBAL_GTT;
+		*cs++ = 0;
+		*cs++ = 0;
+	}
+
+	*cs++ = cmd;
+
 	intel_ring_advance(rq, cs);
 
 	return 0;

drivers/gpu/drm/i915/intel_runtime_pm.c

@@ -2748,6 +2748,12 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 			.hsw.has_fuses = true,
 		},
 	},
+	{
+		.name = "DC off",
+		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
+		.ops = &gen9_dc_off_power_well_ops,
+		.id = DISP_PW_ID_NONE,
+	},
 	{
 		.name = "power well 2",
 		.domains = ICL_PW_2_POWER_DOMAINS,
@@ -2759,12 +2765,6 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 			.hsw.has_fuses = true,
 		},
 	},
-	{
-		.name = "DC off",
-		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
-		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
-	},
 	{
 		.name = "power well 3",
 		.domains = ICL_PW_3_POWER_DOMAINS,
@@ -3176,8 +3176,7 @@ static u8 intel_dbuf_max_slices(struct drm_i915_private *dev_priv)
 void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 			    u8 req_slices)
 {
-	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
-	u32 val;
+	const u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
 	bool ret;
 
 	if (req_slices > intel_dbuf_max_slices(dev_priv)) {
@@ -3188,7 +3187,6 @@ void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 	if (req_slices == hw_enabled_slices || req_slices == 0)
 		return;
 
-	val = I915_READ(DBUF_CTL_S2);
 	if (req_slices > hw_enabled_slices)
 		ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, true);
 	else

drivers/gpu/drm/i915/intel_sprite.c

@@ -302,13 +302,65 @@ skl_plane_max_stride(struct intel_plane *plane,
 		return min(8192 * cpp, 32768);
 }
 
+static void
+skl_program_scaler(struct intel_plane *plane,
+		   const struct intel_crtc_state *crtc_state,
+		   const struct intel_plane_state *plane_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	enum pipe pipe = plane->pipe;
+	int scaler_id = plane_state->scaler_id;
+	const struct intel_scaler *scaler =
+		&crtc_state->scaler_state.scalers[scaler_id];
+	int crtc_x = plane_state->base.dst.x1;
+	int crtc_y = plane_state->base.dst.y1;
+	uint32_t crtc_w = drm_rect_width(&plane_state->base.dst);
+	uint32_t crtc_h = drm_rect_height(&plane_state->base.dst);
+	u16 y_hphase, uv_rgb_hphase;
+	u16 y_vphase, uv_rgb_vphase;
+	int hscale, vscale;
+
+	hscale = drm_rect_calc_hscale(&plane_state->base.src,
+				      &plane_state->base.dst,
+				      0, INT_MAX);
+	vscale = drm_rect_calc_vscale(&plane_state->base.src,
+				      &plane_state->base.dst,
+				      0, INT_MAX);
+
+	/* TODO: handle sub-pixel coordinates */
+	if (plane_state->base.fb->format->format == DRM_FORMAT_NV12) {
+		y_hphase = skl_scaler_calc_phase(1, hscale, false);
+		y_vphase = skl_scaler_calc_phase(1, vscale, false);
+
+		/* MPEG2 chroma siting convention */
+		uv_rgb_hphase = skl_scaler_calc_phase(2, hscale, true);
+		uv_rgb_vphase = skl_scaler_calc_phase(2, vscale, false);
+	} else {
+		/* not used */
+		y_hphase = 0;
+		y_vphase = 0;
+
+		uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false);
+		uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false);
+	}
+
+	I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id),
+		      PS_SCALER_EN | PS_PLANE_SEL(plane->id) | scaler->mode);
+	I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
+	I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id),
+		      PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+	I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id),
+		      PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase));
+	I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
+	I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id), (crtc_w << 16) | crtc_h);
+}
+
 void
 skl_update_plane(struct intel_plane *plane,
 		 const struct intel_crtc_state *crtc_state,
 		 const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 	u32 plane_ctl = plane_state->ctl;
@@ -318,8 +370,6 @@ skl_update_plane(struct intel_plane *plane,
 	u32 aux_stride = skl_plane_stride(plane_state, 1);
 	int crtc_x = plane_state->base.dst.x1;
 	int crtc_y = plane_state->base.dst.y1;
-	uint32_t crtc_w = drm_rect_width(&plane_state->base.dst);
-	uint32_t crtc_h = drm_rect_height(&plane_state->base.dst);
 	uint32_t x = plane_state->color_plane[0].x;
 	uint32_t y = plane_state->color_plane[0].y;
 	uint32_t src_w = drm_rect_width(&plane_state->base.src) >> 16;
@@ -329,8 +379,6 @@ skl_update_plane(struct intel_plane *plane,
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
-	crtc_w--;
-	crtc_h--;
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
@@ -353,41 +401,8 @@ skl_update_plane(struct intel_plane *plane,
 		      (plane_state->color_plane[1].y << 16) |
 		      plane_state->color_plane[1].x);
 
-	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {
-		int scaler_id = plane_state->scaler_id;
-		const struct intel_scaler *scaler =
-			&crtc_state->scaler_state.scalers[scaler_id];
-		u16 y_hphase, uv_rgb_hphase;
-		u16 y_vphase, uv_rgb_vphase;
-
-		/* TODO: handle sub-pixel coordinates */
-		if (fb->format->format == DRM_FORMAT_NV12) {
-			y_hphase = skl_scaler_calc_phase(1, false);
-			y_vphase = skl_scaler_calc_phase(1, false);
-
-			/* MPEG2 chroma siting convention */
-			uv_rgb_hphase = skl_scaler_calc_phase(2, true);
-			uv_rgb_vphase = skl_scaler_calc_phase(2, false);
-		} else {
-			/* not used */
-			y_hphase = 0;
-			y_vphase = 0;
-
-			uv_rgb_hphase = skl_scaler_calc_phase(1, false);
-			uv_rgb_vphase = skl_scaler_calc_phase(1, false);
-		}
-
-		I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id),
-			      PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode);
-		I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
-		I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id),
-			      PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase));
-		I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id),
-			      PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase));
-		I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
-		I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id),
-			      ((crtc_w + 1) << 16)|(crtc_h + 1));
+		skl_program_scaler(plane, crtc_state, plane_state);
 
 		I915_WRITE_FW(PLANE_POS(pipe, plane_id), 0);
 	} else {

drivers/gpu/drm/meson/meson_venc.c

@@ -854,6 +854,13 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 	unsigned int sof_lines;
 	unsigned int vsync_lines;
 
+	/* Use VENCI for 480i and 576i and double HDMI pixels */
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK) {
+		hdmi_repeat = true;
+		use_enci = true;
+		venc_hdmi_latency = 1;
+	}
+
 	if (meson_venc_hdmi_supported_vic(vic)) {
 		vmode = meson_venc_hdmi_get_vic_vmode(vic);
 		if (!vmode) {
@@ -865,13 +872,7 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 	} else {
 		meson_venc_hdmi_get_dmt_vmode(mode, &vmode_dmt);
 		vmode = &vmode_dmt;
-	}
-
-	/* Use VENCI for 480i and 576i and double HDMI pixels */
-	if (mode->flags & DRM_MODE_FLAG_DBLCLK) {
-		hdmi_repeat = true;
-		use_enci = true;
-		venc_hdmi_latency = 1;
+		use_enci = false;
 	}
 
 	/* Repeat VENC pixels for 480/576i/p, 720p50/60 and 1080p50/60 */

drivers/gpu/drm/omapdrm/dss/dsi.c

@@ -5409,11 +5409,14 @@ static int dsi_probe(struct platform_device *pdev)
 
 	/* DSI on OMAP3 doesn't have register DSI_GNQ, set number
 	 * of data to 3 by default */
-	if (dsi->data->quirks & DSI_QUIRK_GNQ)
+	if (dsi->data->quirks & DSI_QUIRK_GNQ) {
+		dsi_runtime_get(dsi);
 		/* NB_DATA_LANES */
 		dsi->num_lanes_supported = 1 + REG_GET(dsi, DSI_GNQ, 11, 9);
-	else
+		dsi_runtime_put(dsi);
+	} else {
 		dsi->num_lanes_supported = 3;
+	}
 
 	r = dsi_init_output(dsi);
 	if (r)
@@ -5426,15 +5429,19 @@ static int dsi_probe(struct platform_device *pdev)
 	}
 
 	r = of_platform_populate(dev->of_node, NULL, NULL, dev);
-	if (r)
+	if (r) {
 		DSSERR("Failed to populate DSI child devices: %d\n", r);
+		goto err_uninit_output;
+	}
 
 	r = component_add(&pdev->dev, &dsi_component_ops);
 	if (r)
-		goto err_uninit_output;
+		goto err_of_depopulate;
 
 	return 0;
 
+err_of_depopulate:
+	of_platform_depopulate(dev);
 err_uninit_output:
 	dsi_uninit_output(dsi);
 err_pm_disable:
@@ -5470,19 +5477,12 @@ static int dsi_runtime_suspend(struct device *dev)
 	/* wait for current handler to finish before turning the DSI off */
 	synchronize_irq(dsi->irq);
 
-	dispc_runtime_put(dsi->dss->dispc);
-
 	return 0;
 }
 
 static int dsi_runtime_resume(struct device *dev)
 {
 	struct dsi_data *dsi = dev_get_drvdata(dev);
-	int r;
-
-	r = dispc_runtime_get(dsi->dss->dispc);
-	if (r)
-		return r;
 
 	dsi->is_enabled = true;
 	/* ensure the irq handler sees the is_enabled value */

drivers/gpu/drm/omapdrm/dss/dss.c

@@ -1484,16 +1484,23 @@ static int dss_probe(struct platform_device *pdev)
 						   dss);
 
 	/* Add all the child devices as components. */
+	r = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
+	if (r)
+		goto err_uninit_debugfs;
+
 	omapdss_gather_components(&pdev->dev);
 
 	device_for_each_child(&pdev->dev, &match, dss_add_child_component);
 
 	r = component_master_add_with_match(&pdev->dev, &dss_component_ops, match);
 	if (r)
-		goto err_uninit_debugfs;
+		goto err_of_depopulate;
 
 	return 0;
 
+err_of_depopulate:
+	of_platform_depopulate(&pdev->dev);
+
 err_uninit_debugfs:
 	dss_debugfs_remove_file(dss->debugfs.clk);
 	dss_debugfs_remove_file(dss->debugfs.dss);
@@ -1522,6 +1529,8 @@ static int dss_remove(struct platform_device *pdev)
 {
 	struct dss_device *dss = platform_get_drvdata(pdev);
 
+	of_platform_depopulate(&pdev->dev);
+
 	component_master_del(&pdev->dev, &dss_component_ops);
 
 	dss_debugfs_remove_file(dss->debugfs.clk);

drivers/gpu/drm/omapdrm/dss/hdmi4.c

@@ -635,10 +635,14 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data)
 
 	hdmi->dss = dss;
 
-	r = hdmi_pll_init(dss, hdmi->pdev, &hdmi->pll, &hdmi->wp);
+	r = hdmi_runtime_get(hdmi);
 	if (r)
 		return r;
 
+	r = hdmi_pll_init(dss, hdmi->pdev, &hdmi->pll, &hdmi->wp);
+	if (r)
+		goto err_runtime_put;
+
 	r = hdmi4_cec_init(hdmi->pdev, &hdmi->core, &hdmi->wp);
 	if (r)
 		goto err_pll_uninit;
@@ -652,12 +656,16 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data)
 	hdmi->debugfs = dss_debugfs_create_file(dss, "hdmi", hdmi_dump_regs,
 					       hdmi);
 
+	hdmi_runtime_put(hdmi);
+
 	return 0;
 
 err_cec_uninit:
 	hdmi4_cec_uninit(&hdmi->core);
 err_pll_uninit:
 	hdmi_pll_uninit(&hdmi->pll);
+err_runtime_put:
+	hdmi_runtime_put(hdmi);
 	return r;
 }
 
@@ -833,32 +841,6 @@ static int hdmi4_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int hdmi_runtime_suspend(struct device *dev)
-{
-	struct omap_hdmi *hdmi = dev_get_drvdata(dev);
-
-	dispc_runtime_put(hdmi->dss->dispc);
-
-	return 0;
-}
-
-static int hdmi_runtime_resume(struct device *dev)
-{
-	struct omap_hdmi *hdmi = dev_get_drvdata(dev);
-	int r;
-
-	r = dispc_runtime_get(hdmi->dss->dispc);
-	if (r < 0)
-		return r;
-
-	return 0;
-}
-
-static const struct dev_pm_ops hdmi_pm_ops = {
-	.runtime_suspend = hdmi_runtime_suspend,
-	.runtime_resume = hdmi_runtime_resume,
-};
-
 static const struct of_device_id hdmi_of_match[] = {
 	{ .compatible = "ti,omap4-hdmi", },
 	{},
@@ -869,7 +851,6 @@ struct platform_driver omapdss_hdmi4hw_driver = {
 	.remove		= hdmi4_remove,
 	.driver         = {
 		.name   = "omapdss_hdmi",
-		.pm	= &hdmi_pm_ops,
 		.of_match_table = hdmi_of_match,
 		.suppress_bind_attrs = true,
 	},

drivers/gpu/drm/omapdrm/dss/hdmi5.c

@@ -825,32 +825,6 @@ static int hdmi5_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int hdmi_runtime_suspend(struct device *dev)
-{
-	struct omap_hdmi *hdmi = dev_get_drvdata(dev);
-
-	dispc_runtime_put(hdmi->dss->dispc);
-
-	return 0;
-}
-
-static int hdmi_runtime_resume(struct device *dev)
-{
-	struct omap_hdmi *hdmi = dev_get_drvdata(dev);
-	int r;
-
-	r = dispc_runtime_get(hdmi->dss->dispc);
-	if (r < 0)
-		return r;
-
-	return 0;
-}
-
-static const struct dev_pm_ops hdmi_pm_ops = {
-	.runtime_suspend = hdmi_runtime_suspend,
-	.runtime_resume = hdmi_runtime_resume,
-};
-
 static const struct of_device_id hdmi_of_match[] = {
 	{ .compatible = "ti,omap5-hdmi", },
 	{ .compatible = "ti,dra7-hdmi", },
@@ -862,7 +836,6 @@ struct platform_driver omapdss_hdmi5hw_driver = {
 	.remove		= hdmi5_remove,
 	.driver         = {
 		.name   = "omapdss_hdmi5",
-		.pm	= &hdmi_pm_ops,
 		.of_match_table = hdmi_of_match,
 		.suppress_bind_attrs = true,
 	},

drivers/gpu/drm/omapdrm/dss/venc.c

@@ -946,19 +946,12 @@ static int venc_runtime_suspend(struct device *dev)
 	if (venc->tv_dac_clk)
 		clk_disable_unprepare(venc->tv_dac_clk);
 
-	dispc_runtime_put(venc->dss->dispc);
-
 	return 0;
 }
 
 static int venc_runtime_resume(struct device *dev)
 {
 	struct venc_device *venc = dev_get_drvdata(dev);
-	int r;
-
-	r = dispc_runtime_get(venc->dss->dispc);
-	if (r < 0)
-		return r;
 
 	if (venc->tv_dac_clk)
 		clk_prepare_enable(venc->tv_dac_clk);

drivers/gpu/drm/omapdrm/omap_crtc.c

@@ -350,11 +350,14 @@ static void omap_crtc_arm_event(struct drm_crtc *crtc)
 static void omap_crtc_atomic_enable(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_state)
 {
+	struct omap_drm_private *priv = crtc->dev->dev_private;
 	struct omap_crtc *omap_crtc = to_omap_crtc(crtc);
 	int ret;
 
 	DBG("%s", omap_crtc->name);
 
+	priv->dispc_ops->runtime_get(priv->dispc);
+
 	spin_lock_irq(&crtc->dev->event_lock);
 	drm_crtc_vblank_on(crtc);
 	ret = drm_crtc_vblank_get(crtc);
@@ -367,6 +370,7 @@ static void omap_crtc_atomic_enable(struct drm_crtc *crtc,
 static void omap_crtc_atomic_disable(struct drm_crtc *crtc,
 				     struct drm_crtc_state *old_state)
 {
+	struct omap_drm_private *priv = crtc->dev->dev_private;
 	struct omap_crtc *omap_crtc = to_omap_crtc(crtc);
 
 	DBG("%s", omap_crtc->name);
@@ -379,6 +383,8 @@ static void omap_crtc_atomic_disable(struct drm_crtc *crtc,
 	spin_unlock_irq(&crtc->dev->event_lock);
 
 	drm_crtc_vblank_off(crtc);
+
+	priv->dispc_ops->runtime_put(priv->dispc);
 }
 
 static enum drm_mode_status omap_crtc_mode_valid(struct drm_crtc *crtc,