Merge branch 'master' into for-3.19/drivers

8 files changed, 106 insertions, 48 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 055d5e7fbf12..2318b4c7a8f8 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -986,6 +986,15 @@ static int i915_pm_freeze(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
+static int i915_pm_freeze_late(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+
+	return intel_suspend_complete(dev_priv);
+}
+
 static int i915_pm_thaw_early(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1570,6 +1579,7 @@ static const struct dev_pm_ops i915_pm_ops = {
 	.resume_early = i915_pm_resume_early,
 	.resume = i915_pm_resume,
 	.freeze = i915_pm_freeze,
+	.freeze_late = i915_pm_freeze_late,
 	.thaw_early = i915_pm_thaw_early,
 	.thaw = i915_pm_thaw,
 	.poweroff = i915_pm_poweroff,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b672b843fd5e..728938f02341 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1902,6 +1902,22 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
 	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
 	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
 
+	if (!USES_PPGTT(dev_priv->dev))
+		/* Spec: "For GGTT, there is NO pat_sel[2:0] from the entry,
+		 * so RTL will always use the value corresponding to
+		 * pat_sel = 000".
+		 * So let's disable cache for GGTT to avoid screen corruptions.
+		 * MOCS still can be used though.
+		 * - System agent ggtt writes (i.e. cpu gtt mmaps) already work
+		 * before this patch, i.e. the same uncached + snooping access
+		 * like on gen6/7 seems to be in effect.
+		 * - So this just fixes blitter/render access. Again it looks
+		 * like it's not just uncached access, but uncached + snooping.
+		 * So we can still hold onto all our assumptions wrt cpu
+		 * clflushing on LLC machines.
+		 */
+		pat = GEN8_PPAT(0, GEN8_PPAT_UC);
+
 	/* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
 	 * write would work. */
 	I915_WRITE(GEN8_PRIVATE_PAT, pat);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 2cefb597df6d..2b1eaa29ada4 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -364,22 +364,9 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 * has to also include the unfenced register the GPU uses
 		 * whilst executing a fenced command for an untiled object.
 		 */
-
-		obj->map_and_fenceable =
-			!i915_gem_obj_ggtt_bound(obj) ||
-			(i915_gem_obj_ggtt_offset(obj) +
-			 obj->base.size <= dev_priv->gtt.mappable_end &&
-			 i915_gem_object_fence_ok(obj, args->tiling_mode));
-
-		/* Rebind if we need a change of alignment */
-		if (!obj->map_and_fenceable) {
-			u32 unfenced_align =
-				i915_gem_get_gtt_alignment(dev, obj->base.size,
-							    args->tiling_mode,
-							    false);
-			if (i915_gem_obj_ggtt_offset(obj) & (unfenced_align - 1))
-				ret = i915_gem_object_ggtt_unbind(obj);
-		}
+		if (obj->map_and_fenceable &&
+		    !i915_gem_object_fence_ok(obj, args->tiling_mode))
+			ret = i915_gem_object_ggtt_unbind(obj);
 
 		if (ret == 0) {
 			obj->fence_dirty =
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3201986bf25e..f66392b6e287 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1711,7 +1711,7 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 #define HPD_STORM_DETECT_PERIOD 1000
 #define HPD_STORM_THRESHOLD 5
 
-static int ilk_port_to_hotplug_shift(enum port port)
+static int pch_port_to_hotplug_shift(enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -1727,7 +1727,7 @@ static int ilk_port_to_hotplug_shift(enum port port)
 	}
 }
 
-static int g4x_port_to_hotplug_shift(enum port port)
+static int i915_port_to_hotplug_shift(enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -1785,12 +1785,12 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 		if (port && dev_priv->hpd_irq_port[port]) {
 			bool long_hpd;
 
-			if (IS_G4X(dev)) {
-				dig_shift = g4x_port_to_hotplug_shift(port);
-				long_hpd = (hotplug_trigger >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
-			} else {
-				dig_shift = ilk_port_to_hotplug_shift(port);
+			if (HAS_PCH_SPLIT(dev)) {
+				dig_shift = pch_port_to_hotplug_shift(port);
 				long_hpd = (dig_hotplug_reg >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
+			} else {
+				dig_shift = i915_port_to_hotplug_shift(port);
+				long_hpd = (hotplug_trigger >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
 			}
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n",
@@ -3458,12 +3458,13 @@ static void gen8_irq_reset(struct drm_device *dev)
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv)
 {
 	unsigned long irqflags;
+	uint32_t extra_ier = GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_B, dev_priv->de_irq_mask[PIPE_B],
-			  ~dev_priv->de_irq_mask[PIPE_B]);
+			  ~dev_priv->de_irq_mask[PIPE_B] | extra_ier);
 	GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_C, dev_priv->de_irq_mask[PIPE_C],
-			  ~dev_priv->de_irq_mask[PIPE_C]);
+			  ~dev_priv->de_irq_mask[PIPE_C] | extra_ier);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 507370513f3d..f0a1a56406eb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -73,9 +73,6 @@ static const uint32_t intel_cursor_formats[] = {
 	DRM_FORMAT_ARGB8888,
 };
 
-#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
-({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
-
 static void intel_increase_pllclock(struct drm_device *dev,
 				    enum pipe pipe);
 static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
@@ -4588,7 +4585,7 @@ static void vlv_update_cdclk(struct drm_device *dev)
 	 * BSpec erroneously claims we should aim for 4MHz, but
 	 * in fact 1MHz is the correct frequency.
 	 */
-	I915_WRITE(GMBUSFREQ_VLV, dev_priv->vlv_cdclk_freq);
+	I915_WRITE(GMBUSFREQ_VLV, DIV_ROUND_UP(dev_priv->vlv_cdclk_freq, 1000));
 }
 
 /* Adjust CDclk dividers to allow high res or save power if possible */
@@ -12357,27 +12354,36 @@ static void intel_setup_outputs(struct drm_device *dev)
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev)) {
-		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED) {
+		/*
+		 * The DP_DETECTED bit is the latched state of the DDC
+		 * SDA pin at boot. However since eDP doesn't require DDC
+		 * (no way to plug in a DP->HDMI dongle) the DDC pins for
+		 * eDP ports may have been muxed to an alternate function.
+		 * Thus we can't rely on the DP_DETECTED bit alone to detect
+		 * eDP ports. Consult the VBT as well as DP_DETECTED to
+		 * detect eDP ports.
+		 */
+		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED)
 			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIB,
 					PORT_B);
-			if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED)
-				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B);
-		}
+		if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED ||
+		    intel_dp_is_edp(dev, PORT_B))
+			intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B);
 
-		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED) {
+		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED)
 			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIC,
 					PORT_C);
-			if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED)
-				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
-		}
+		if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED ||
+		    intel_dp_is_edp(dev, PORT_C))
+			intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
 
 		if (IS_CHERRYVIEW(dev)) {
-			if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) {
+			if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED)
 				intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID,
 						PORT_D);
-				if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED)
-					intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D);
-			}
+			/* eDP not supported on port D, so don't check VBT */
+			if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED)
+				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D);
 		}
 
 		intel_dsi_init(dev);
@@ -12879,6 +12885,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* Acer C720 Chromebook (Core i3 4005U) */
 	{ 0x0a16, 0x1025, 0x0a11, quirk_backlight_present },
 
+	/* Apple Macbook 2,1 (Core 2 T7400) */
+	{ 0x27a2, 0x8086, 0x7270, quirk_backlight_present },
+
 	/* Toshiba CB35 Chromebook (Celeron 2955U) */
 	{ 0x0a06, 0x1179, 0x0a88, quirk_backlight_present },
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f6a3fdd5589e..5ad45bfff3fe 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2806,6 +2806,13 @@ intel_dp_dpcd_read_wake(struct drm_dp_aux *aux, unsigned int offset,
 	ssize_t ret;
 	int i;
 
+	/*
+	 * Sometime we just get the same incorrect byte repeated
+	 * over the entire buffer. Doing just one throw away read
+	 * initially seems to "solve" it.
+	 */
+	drm_dp_dpcd_read(aux, DP_DPCD_REV, buffer, 1);
+
 	for (i = 0; i < 3; i++) {
 		ret = drm_dp_dpcd_read(aux, offset, buffer, size);
 		if (ret == size)
@@ -3724,9 +3731,10 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		}
 	}
 
-	/* Training Pattern 3 support */
+	/* Training Pattern 3 support, both source and sink */
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 &&
-	    intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED) {
+	    intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED &&
+	    (IS_HASWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 8)) {
 		intel_dp->use_tps3 = true;
 		DRM_DEBUG_KMS("Displayport TPS3 supported\n");
 	} else
@@ -4491,6 +4499,18 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	if (intel_dig_port->base.type != INTEL_OUTPUT_EDP)
 		intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT;
 
+	if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
+		/*
+		 * vdd off can generate a long pulse on eDP which
+		 * would require vdd on to handle it, and thus we
+		 * would end up in an endless cycle of
+		 * "vdd off -> long hpd -> vdd on -> detect -> vdd off -> ..."
+		 */
+		DRM_DEBUG_KMS("ignoring long hpd on eDP port %c\n",
+			      port_name(intel_dig_port->port));
+		return false;
+	}
+
 	DRM_DEBUG_KMS("got hpd irq on port %c - %s\n",
 		      port_name(intel_dig_port->port),
 		      long_hpd ? "long" : "short");
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 07ce04683c30..ba715229a540 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -35,6 +35,9 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_dp_mst_helper.h>
 
+#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
+({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
+
 /**
  * _wait_for - magic (register) wait macro
  *
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 18784470a760..41b3be217493 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -419,9 +419,8 @@ static uint32_t scale(uint32_t source_val,
 	source_val = clamp(source_val, source_min, source_max);
 
 	/* avoid overflows */
-	target_val = (uint64_t)(source_val - source_min) *
-		(target_max - target_min);
-	do_div(target_val, source_max - source_min);
+	target_val = DIV_ROUND_CLOSEST_ULL((uint64_t)(source_val - source_min) *
+			(target_max - target_min), source_max - source_min);
 	target_val += target_min;
 
 	return target_val;
@@ -1099,12 +1098,25 @@ static u32 get_backlight_min_vbt(struct intel_connector *connector)
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_panel *panel = &connector->panel;
+	int min;
 
 	WARN_ON(panel->backlight.max == 0);
 
+	/*
+	 * XXX: If the vbt value is 255, it makes min equal to max, which leads
+	 * to problems. There are such machines out there. Either our
+	 * interpretation is wrong or the vbt has bogus data. Or both. Safeguard
+	 * against this by letting the minimum be at most (arbitrarily chosen)
+	 * 25% of the max.
+	 */
+	min = clamp_t(int, dev_priv->vbt.backlight.min_brightness, 0, 64);
+	if (min != dev_priv->vbt.backlight.min_brightness) {
+		DRM_DEBUG_KMS("clamping VBT min backlight %d/255 to %d/255\n",
+			      dev_priv->vbt.backlight.min_brightness, min);
+	}
+
 	/* vbt value is a coefficient in range [0..255] */
-	return scale(dev_priv->vbt.backlight.min_brightness, 0, 255,
-		     0, panel->backlight.max);
+	return scale(min, 0, 255, 0, panel->backlight.max);
 }
 
 static int bdw_setup_backlight(struct intel_connector *connector)