Merge branch 'drm-intel-fixes' of git://people.freedesktop.org/~danve…

…t/drm-intel into drm-next

So here's my promised pile of fixes for 3.9. I've dropped the core prep
patches for vt-switchless suspend/resume as discussed on irc. Highlights:
- Fix dmar on g4x. Not really gfx related, but I'm fed up with getting
  blamed for dmar crapouts.
- Disable wc ptes updates on ilk when dmar is enabled (Chris). So again,
  dmar, but this time gfx related :(
- Reduced range support for hsw, using the pipe CSC (Ville).
- Fixup pll limits for gen3/4 (Patrick Jakobsson). The sdvo patch is
  already confirmed to fix 2 bug reports, so added cc: stable on that one.
- Regression fix for 8bit fb console (Ville).
- Preserve lane reversal bits on DDI/FDI ports (Damien).
- Page flip vs. gpu hang fixes (Ville). Unfortuntely not quite all of
  them, need to decide what to do with the currently still in-flight ones.
- Panel fitter regression fix from Mika Kuoppala (was accidentally left on
  on some pipes with the new modset code since 3.7). This also improves
  the modeset sequence and might help a few other unrelated issues with
  lvds.
- Write backlight regs even harder ... another installement in our eternal
  fight against the BIOS and backlights.
- Fixup lid notifier vs. suspend/resume races (Zhang Rui). Prep work for
  new ACPI stuff, but closing the race itself seems worthwile on its own.
- A few other small fixes and tiny cleanups all over.

Lots of the patches are cc: stable since I've stalled on a few
not-so-important fixes for 3.8 due to the grumpy noise Linus made.

* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel: (33 commits)
  intel/iommu: force writebuffer-flush quirk on Gen 4 Chipsets
  drm/i915: Disable WC PTE updates to w/a buggy IOMMU on ILK
  drm/i915: Implement pipe CSC based limited range RGB output
  drm/i915: inverted brightness quirk for Acer Aspire 4736Z
  drm/i915: Print the hw context status is debugfs
  drm/i915: Use HAS_L3_GPU_CACHE in i915_gem_l3_remap
  drm/i915: Fix PIPE_CONTROL DW/QW write through global GTT on IVB+
  drm/i915: Set i9xx sdvo clock limits according to specifications
  drm/i915: Set i9xx lvds clock limits according to specifications
  drm/i915: Preserve the DDI link reversal configuration
  drm/i915: Preserve the FDI line reversal override bit on CPT
  drm/i915: add missing \n to UTS_RELEASE in the error_state
  drm: Use C8 instead of RGB332 when determining the format from depth/bpp
  drm: Fill depth/bits_per_pixel for C8 format
  drm/i915: don't clflush gem objects in stolen memory
  drm/i915: Don't wait for page flips if there was GPU reset
  drm/i915: Kill obj->pending_flip
  drm/i915: Fix a typo in a intel_modeset_stage_output_state() comment
  drm/i915: remove bogus mutex_unlock from error-path
  drm/i915: Print the pipe control page GTT address
  ...

drivers/char/agp/intel-gtt.c

@@ -572,6 +572,40 @@ static void intel_gtt_cleanup(void)
 	intel_gtt_teardown_scratch_page();
 }
 
+/* Certain Gen5 chipsets require require idling the GPU before
+ * unmapping anything from the GTT when VT-d is enabled.
+ */
+static inline int needs_ilk_vtd_wa(void)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	const unsigned short gpu_devid = intel_private.pcidev->device;
+
+	/* Query intel_iommu to see if we need the workaround. Presumably that
+	 * was loaded first.
+	 */
+	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
+	     intel_iommu_gfx_mapped)
+		return 1;
+#endif
+	return 0;
+}
+
+static bool intel_gtt_can_wc(void)
+{
+	if (INTEL_GTT_GEN <= 2)
+		return false;
+
+	if (INTEL_GTT_GEN >= 6)
+		return false;
+
+	/* Reports of major corruption with ILK vt'd enabled */
+	if (needs_ilk_vtd_wa())
+		return false;
+
+	return true;
+}
+
 static int intel_gtt_init(void)
 {
 	u32 gma_addr;
@@ -601,7 +635,7 @@ static int intel_gtt_init(void)
 	gtt_map_size = intel_private.gtt_total_entries * 4;
 
 	intel_private.gtt = NULL;
-	if (INTEL_GTT_GEN < 6 && INTEL_GTT_GEN > 2)
+	if (intel_gtt_can_wc())
 		intel_private.gtt = ioremap_wc(intel_private.gtt_bus_addr,
 					       gtt_map_size);
 	if (intel_private.gtt == NULL)
@@ -1072,7 +1106,6 @@ static void i965_write_entry(dma_addr_t addr,
 	writel(addr | pte_flags, intel_private.gtt + entry);
 }
 
-
 static int i9xx_setup(void)
 {
 	u32 reg_addr, gtt_addr;
@@ -1371,10 +1404,13 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 }
 EXPORT_SYMBOL(intel_gmch_probe);
 
-void intel_gtt_get(size_t *gtt_total, size_t *stolen_size)
+void intel_gtt_get(size_t *gtt_total, size_t *stolen_size,
+		   phys_addr_t *mappable_base, unsigned long *mappable_end)
 {
 	*gtt_total = intel_private.gtt_total_entries << PAGE_SHIFT;
 	*stolen_size = intel_private.stolen_size;
+	*mappable_base = intel_private.gma_bus_addr;
+	*mappable_end = intel_private.gtt_mappable_entries << PAGE_SHIFT;
 }
 EXPORT_SYMBOL(intel_gtt_get);
 

drivers/gpu/drm/drm_crtc.c

@@ -2267,7 +2267,7 @@ uint32_t drm_mode_legacy_fb_format(uint32_t bpp, uint32_t depth)
 
 	switch (bpp) {
 	case 8:
-		fmt = DRM_FORMAT_RGB332;
+		fmt = DRM_FORMAT_C8;
 		break;
 	case 16:
 		if (depth == 15)
@@ -3870,6 +3870,7 @@ void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
 			  int *bpp)
 {
 	switch (format) {
+	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB332:
 	case DRM_FORMAT_BGR233:
 		*depth = 8;

drivers/gpu/drm/i915/i915_debugfs.c

@@ -694,7 +694,7 @@ static int i915_error_state(struct seq_file *m, void *unused)
 
 	seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
-	seq_printf(m, "Kernel: " UTS_RELEASE);
+	seq_printf(m, "Kernel: " UTS_RELEASE "\n");
 	seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
 	seq_printf(m, "EIR: 0x%08x\n", error->eir);
 	seq_printf(m, "IER: 0x%08x\n", error->ier);
@@ -1484,7 +1484,8 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	struct intel_ring_buffer *ring;
+	int ret, i;
 
 	ret = mutex_lock_interruptible(&dev->mode_config.mutex);
 	if (ret)
@@ -1502,6 +1503,14 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_printf(m, "\n");
 	}
 
+	for_each_ring(ring, dev_priv, i) {
+		if (ring->default_context) {
+			seq_printf(m, "HW default context %s ring ", ring->name);
+			describe_obj(m, ring->default_context->obj);
+			seq_printf(m, "\n");
+		}
+	}
+
 	mutex_unlock(&dev->mode_config.mutex);
 
 	return 0;

drivers/gpu/drm/i915/i915_dma.c

@@ -1610,6 +1610,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	mutex_init(&dev_priv->dpio_lock);
 
 	mutex_init(&dev_priv->rps.hw_lock);
+	mutex_init(&dev_priv->modeset_restore_lock);
 
 	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
 		dev_priv->num_pipe = 3;

drivers/gpu/drm/i915/i915_drv.c

@@ -470,6 +470,11 @@ static int i915_drm_freeze(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* ignore lid events during suspend */
+	mutex_lock(&dev_priv->modeset_restore_lock);
+	dev_priv->modeset_restore = MODESET_SUSPENDED;
+	mutex_unlock(&dev_priv->modeset_restore_lock);
+
 	intel_set_power_well(dev, true);
 
 	drm_kms_helper_poll_disable(dev);
@@ -496,9 +501,6 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	intel_opregion_fini(dev);
 
-	/* Modeset on resume, not lid events */
-	dev_priv->modeset_on_lid = 0;
-
 	console_lock();
 	intel_fbdev_set_suspend(dev, 1);
 	console_unlock();
@@ -574,8 +576,6 @@ static int __i915_drm_thaw(struct drm_device *dev)
 
 	intel_opregion_init(dev);
 
-	dev_priv->modeset_on_lid = 0;
-
 	/*
 	 * The console lock can be pretty contented on resume due
 	 * to all the printk activity.  Try to keep it out of the hot
@@ -588,6 +588,9 @@ static int __i915_drm_thaw(struct drm_device *dev)
 		schedule_work(&dev_priv->console_resume_work);
 	}
 
+	mutex_lock(&dev_priv->modeset_restore_lock);
+	dev_priv->modeset_restore = MODESET_DONE;
+	mutex_unlock(&dev_priv->modeset_restore_lock);
 	return error;
 }
 

drivers/gpu/drm/i915/i915_drv.h

@@ -399,7 +399,8 @@ struct i915_gtt {
 
 	/* global gtt ops */
 	int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total,
-			  size_t *stolen);
+			  size_t *stolen, phys_addr_t *mappable_base,
+			  unsigned long *mappable_end);
 	void (*gtt_remove)(struct drm_device *dev);
 	void (*gtt_clear_range)(struct drm_device *dev,
 				unsigned int first_entry,
@@ -846,6 +847,12 @@ struct i915_gpu_error {
 	unsigned int stop_rings;
 };
 
+enum modeset_restore {
+	MODESET_ON_LID_OPEN,
+	MODESET_DONE,
+	MODESET_SUSPENDED,
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -919,7 +926,7 @@ typedef struct drm_i915_private {
 
 	/* overlay */
 	struct intel_overlay *overlay;
-	bool sprite_scaling_enabled;
+	unsigned int sprite_scaling_enabled;
 
 	/* LVDS info */
 	int backlight_level;  /* restore backlight to this value */
@@ -967,8 +974,8 @@ typedef struct drm_i915_private {
 
 	unsigned long quirks;
 
-	/* Register state */
-	bool modeset_on_lid;
+	enum modeset_restore modeset_restore;
+	struct mutex modeset_restore_lock;
 
 	struct i915_gtt gtt;
 
@@ -1033,7 +1040,7 @@ typedef struct drm_i915_private {
 	bool hw_contexts_disabled;
 	uint32_t hw_context_size;
 
-	bool fdi_rx_polarity_reversed;
+	u32 fdi_rx_config;
 
 	struct i915_suspend_saved_registers regfile;
 
@@ -1208,13 +1215,6 @@ struct drm_i915_gem_object {
 
 	/** for phy allocated objects */
 	struct drm_i915_gem_phys_object *phys_obj;
-
-	/**
-	 * Number of crtcs where this object is currently the fb, but
-	 * will be page flipped away on the next vblank.  When it
-	 * reaches 0, dev_priv->pending_flip_queue will be woken up.
-	 */
-	atomic_t pending_flip;
 };
 #define to_gem_object(obj) (&((struct drm_i915_gem_object *)(obj))->base)
 

drivers/gpu/drm/i915/i915_gem.c

@@ -3021,6 +3021,13 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 	if (obj->pages == NULL)
 		return;
 
+	/*
+	 * Stolen memory is always coherent with the GPU as it is explicitly
+	 * marked as wc by the system, or the system is cache-coherent.
+	 */
+	if (obj->stolen)
+		return;
+
 	/* If the GPU is snooping the contents of the CPU cache,
 	 * we do not need to manually clear the CPU cache lines.  However,
 	 * the caches are only snooped when the render cache is
@@ -3865,7 +3872,7 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	u32 misccpctl;
 	int i;
 
-	if (!IS_IVYBRIDGE(dev))
+	if (!HAS_L3_GPU_CACHE(dev))
 		return;
 
 	if (!dev_priv->l3_parity.remap_info)
@@ -3930,22 +3937,11 @@ intel_enable_blt(struct drm_device *dev)
 	return true;
 }
 
-int
-i915_gem_init_hw(struct drm_device *dev)
+static int i915_gem_init_rings(struct drm_device *dev)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
-		return -EIO;
-
-	if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1))
-		I915_WRITE(0x9008, I915_READ(0x9008) | 0xf0000);
-
-	i915_gem_l3_remap(dev);
-
-	i915_gem_init_swizzling(dev);
-
 	ret = intel_init_render_ring_buffer(dev);
 	if (ret)
 		return ret;
@@ -3963,6 +3959,38 @@ i915_gem_init_hw(struct drm_device *dev)
 	}
 
 	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
+	if (ret)
+		goto cleanup_blt_ring;
+
+	return 0;
+
+cleanup_blt_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[BCS]);
+cleanup_bsd_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[VCS]);
+cleanup_render_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[RCS]);
+
+	return ret;
+}
+
+int
+i915_gem_init_hw(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int ret;
+
+	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
+		return -EIO;
+
+	if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1))
+		I915_WRITE(0x9008, I915_READ(0x9008) | 0xf0000);
+
+	i915_gem_l3_remap(dev);
+
+	i915_gem_init_swizzling(dev);
+
+	ret = i915_gem_init_rings(dev);
 	if (ret)
 		return ret;
 
@@ -3974,12 +4002,6 @@ i915_gem_init_hw(struct drm_device *dev)
 	i915_gem_init_ppgtt(dev);
 
 	return 0;
-
-cleanup_bsd_ring:
-	intel_cleanup_ring_buffer(&dev_priv->ring[VCS]);
-cleanup_render_ring:
-	intel_cleanup_ring_buffer(&dev_priv->ring[RCS]);
-	return ret;
 }
 
 int i915_gem_init(struct drm_device *dev)

drivers/gpu/drm/i915/i915_gem_context.c

@@ -126,13 +126,8 @@ static int get_context_size(struct drm_device *dev)
 
 static void do_destroy(struct i915_hw_context *ctx)
 {
-	struct drm_device *dev = ctx->obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (ctx->file_priv)
 		idr_remove(&ctx->file_priv->context_idr, ctx->id);
-	else
-		BUG_ON(ctx != dev_priv->ring[RCS].default_context);
 
 	drm_gem_object_unreference(&ctx->obj->base);
 	kfree(ctx);
@@ -242,7 +237,6 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 void i915_gem_context_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t ctx_size;
 
 	if (!HAS_HW_CONTEXTS(dev)) {
 		dev_priv->hw_contexts_disabled = true;
@@ -254,11 +248,9 @@ void i915_gem_context_init(struct drm_device *dev)
 	    dev_priv->ring[RCS].default_context)
 		return;
 
-	ctx_size = get_context_size(dev);
-	dev_priv->hw_context_size = get_context_size(dev);
-	dev_priv->hw_context_size = round_up(dev_priv->hw_context_size, 4096);
+	dev_priv->hw_context_size = round_up(get_context_size(dev), 4096);
 
-	if (ctx_size <= 0 || ctx_size > (1<<20)) {
+	if (dev_priv->hw_context_size > (1<<20)) {
 		dev_priv->hw_contexts_disabled = true;
 		return;
 	}