Merge tag 'drm-intel-next-2013-08-23' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

Need to get my stuff out the door ;-) Highlights:
- pc8+ support from Paulo
- more vma patches from Ben.
- Kconfig option to enable preliminary support by default (Josh
  Triplett)
- Optimized cpu cache flush handling and support for write-through caching
  of display planes on Iris (Chris)
- rc6 tuning from Stéphane Marchesin for more stability
- VECS seqno wrap/semaphores fix (Ben)
- a pile of smaller cleanups and improvements all over

Note that I've ditched Ben's execbuf vma conversion for 3.12 since not yet
ready. But there's still other vma conversion stuff in here.

* tag 'drm-intel-next-2013-08-23' of git://people.freedesktop.org/~danvet/drm-intel: (62 commits)
  drm/i915: Print seqnos as unsigned in debugfs
  drm/i915: Fix context size calculation on SNB/IVB/VLV
  drm/i915: Use POSTING_READ in lcpll code
  drm/i915: enable Package C8+ by default
  drm/i915: add i915.pc8_timeout function
  drm/i915: add i915_pc8_status debugfs file
  drm/i915: allow package C8+ states on Haswell (disabled)
  drm/i915: fix SDEIMR assertion when disabling LCPLL
  drm/i915: grab force_wake when restoring LCPLL
  drm/i915: drop WaMbcDriverBootEnable workaround
  drm/i915: Cleaning up the relocate entry function
  drm/i915: merge HSW and SNB PM irq handlers
  drm/i915: fix how we mask PMIMR when adding work to the queue
  drm/i915: don't queue PM events we won't process
  drm/i915: don't disable/reenable IVB error interrupts when not needed
  drm/i915: add dev_priv->pm_irq_mask
  drm/i915: don't update GEN6_PMIMR when it's not needed
  drm/i915: wrap GEN6_PMIMR changes
  drm/i915: wrap GTIMR changes
  drm/i915: add the FCLK case to intel_ddi_get_cdclk_freq
  ...

drivers/gpu/drm/Kconfig

@@ -168,6 +168,17 @@ config DRM_I915_KMS
 	  the driver to bind to PCI devices, which precludes loading things
 	  like intelfb.
 
+config DRM_I915_PRELIMINARY_HW_SUPPORT
+	bool "Enable preliminary support for prerelease Intel hardware by default"
+	depends on DRM_I915
+	help
+	  Choose this option if you have prerelease Intel hardware and want the
+	  i915 driver to support it by default.  You can enable such support at
+	  runtime with the module option i915.preliminary_hw_support=1; this
+	  option changes the default for that module option.
+
+	  If in doubt, say "N".
+
 config DRM_MGA
 	tristate "Matrox g200/g400"
 	depends on DRM && PCI

drivers/gpu/drm/drm_mm.c

@@ -254,6 +254,9 @@ void drm_mm_remove_node(struct drm_mm_node *node)
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
 
+	if (WARN_ON(!node->allocated))
+		return;
+
 	BUG_ON(node->scanned_block || node->scanned_prev_free
 				   || node->scanned_next_free);
 

drivers/gpu/drm/i915/i915_debugfs.c

@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/list_sort.h>
+#include <asm/msr-index.h>
 #include <drm/drmP.h>
 #include "intel_drv.h"
 #include "intel_ringbuffer.h"
@@ -99,7 +100,7 @@ static void
 describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
-	seq_printf(m, "%pK: %s%s%s %8zdKiB %02x %02x %d %d %d%s%s%s",
+	seq_printf(m, "%pK: %s%s%s %8zdKiB %02x %02x %u %u %u%s%s%s",
 		   &obj->base,
 		   get_pin_flag(obj),
 		   get_tiling_flag(obj),
@@ -117,6 +118,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (name: %d)", obj->base.name);
 	if (obj->pin_count)
 		seq_printf(m, " (pinned x %d)", obj->pin_count);
+	if (obj->pin_display)
+		seq_printf(m, " (display)");
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
 	list_for_each_entry(vma, &obj->vma_list, vma_link) {
@@ -193,9 +196,9 @@ static int obj_rank_by_stolen(void *priv,
 			      struct list_head *A, struct list_head *B)
 {
 	struct drm_i915_gem_object *a =
-		container_of(A, struct drm_i915_gem_object, exec_list);
+		container_of(A, struct drm_i915_gem_object, obj_exec_link);
 	struct drm_i915_gem_object *b =
-		container_of(B, struct drm_i915_gem_object, exec_list);
+		container_of(B, struct drm_i915_gem_object, obj_exec_link);
 
 	return a->stolen->start - b->stolen->start;
 }
@@ -219,7 +222,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 		if (obj->stolen == NULL)
 			continue;
 
-		list_add(&obj->exec_list, &stolen);
+		list_add(&obj->obj_exec_link, &stolen);
 
 		total_obj_size += obj->base.size;
 		total_gtt_size += i915_gem_obj_ggtt_size(obj);
@@ -229,7 +232,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 		if (obj->stolen == NULL)
 			continue;
 
-		list_add(&obj->exec_list, &stolen);
+		list_add(&obj->obj_exec_link, &stolen);
 
 		total_obj_size += obj->base.size;
 		count++;
@@ -237,11 +240,11 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 	list_sort(NULL, &stolen, obj_rank_by_stolen);
 	seq_puts(m, "Stolen:\n");
 	while (!list_empty(&stolen)) {
-		obj = list_first_entry(&stolen, typeof(*obj), exec_list);
+		obj = list_first_entry(&stolen, typeof(*obj), obj_exec_link);
 		seq_puts(m, "   ");
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
-		list_del_init(&obj->exec_list);
+		list_del_init(&obj->obj_exec_link);
 	}
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1767,6 +1770,52 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	return 0;
 }
 
+static int i915_energy_uJ(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u64 power;
+	u32 units;
+
+	if (INTEL_INFO(dev)->gen < 6)
+		return -ENODEV;
+
+	rdmsrl(MSR_RAPL_POWER_UNIT, power);
+	power = (power & 0x1f00) >> 8;
+	units = 1000000 / (1 << power); /* convert to uJ */
+	power = I915_READ(MCH_SECP_NRG_STTS);
+	power *= units;
+
+	seq_printf(m, "%llu", (long long unsigned)power);
+
+	return 0;
+}
+
+static int i915_pc8_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;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_HASWELL(dev)) {
+		seq_puts(m, "not supported\n");
+		return 0;
+	}
+
+	mutex_lock(&dev_priv->pc8.lock);
+	seq_printf(m, "Requirements met: %s\n",
+		   yesno(dev_priv->pc8.requirements_met));
+	seq_printf(m, "GPU idle: %s\n", yesno(dev_priv->pc8.gpu_idle));
+	seq_printf(m, "Disable count: %d\n", dev_priv->pc8.disable_count);
+	seq_printf(m, "IRQs disabled: %s\n",
+		   yesno(dev_priv->pc8.irqs_disabled));
+	seq_printf(m, "Enabled: %s\n", yesno(dev_priv->pc8.enabled));
+	mutex_unlock(&dev_priv->pc8.lock);
+
+	return 0;
+}
+
 static int
 i915_wedged_get(void *data, u64 *val)
 {
@@ -2206,6 +2255,8 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_dpio", i915_dpio_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
+	{"i915_energy_uJ", i915_energy_uJ, 0},
+	{"i915_pc8_status", i915_pc8_status, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 

drivers/gpu/drm/i915/i915_dma.c

@@ -976,6 +976,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_LLC:
 		value = HAS_LLC(dev);
 		break;
+	case I915_PARAM_HAS_WT:
+		value = HAS_WT(dev);
+		break;
 	case I915_PARAM_HAS_ALIASING_PPGTT:
 		value = dev_priv->mm.aliasing_ppgtt ? 1 : 0;
 		break;
@@ -1483,8 +1486,24 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	mutex_init(&dev_priv->rps.hw_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
+	mutex_init(&dev_priv->pc8.lock);
+	dev_priv->pc8.requirements_met = false;
+	dev_priv->pc8.gpu_idle = false;
+	dev_priv->pc8.irqs_disabled = false;
+	dev_priv->pc8.enabled = false;
+	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
+
 	i915_dump_device_info(dev_priv);
 
+	/* Not all pre-production machines fall into this category, only the
+	 * very first ones. Almost everything should work, except for maybe
+	 * suspend/resume. And we don't implement workarounds that affect only
+	 * pre-production machines. */
+	if (IS_HSW_EARLY_SDV(dev))
+		DRM_INFO("This is an early pre-production Haswell machine. "
+			 "It may not be fully functional.\n");
+
 	if (i915_get_bridge_dev(dev)) {
 		ret = -EIO;
 		goto free_priv;
@@ -1677,8 +1696,13 @@ int i915_driver_unload(struct drm_device *dev)
 
 	intel_gpu_ips_teardown();
 
-	if (HAS_POWER_WELL(dev))
+	if (HAS_POWER_WELL(dev)) {
+		/* The i915.ko module is still not prepared to be loaded when
+		 * the power well is not enabled, so just enable it in case
+		 * we're going to unload/reload. */
+		intel_set_power_well(dev, true);
 		i915_remove_power_well(dev);
+	}
 
 	i915_teardown_sysfs(dev);
 
@@ -1724,6 +1748,8 @@ int i915_driver_unload(struct drm_device *dev)
 	cancel_work_sync(&dev_priv->gpu_error.work);
 	i915_destroy_error_state(dev);
 
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
 

drivers/gpu/drm/i915/i915_drv.c

@@ -122,10 +122,10 @@ int i915_enable_psr __read_mostly = 0;
 module_param_named(enable_psr, i915_enable_psr, int, 0600);
 MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)");
 
-unsigned int i915_preliminary_hw_support __read_mostly = 0;
+unsigned int i915_preliminary_hw_support __read_mostly = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT);
 module_param_named(preliminary_hw_support, i915_preliminary_hw_support, int, 0600);
 MODULE_PARM_DESC(preliminary_hw_support,
-		"Enable preliminary hardware support. (default: false)");
+		"Enable preliminary hardware support.");
 
 int i915_disable_power_well __read_mostly = 1;
 module_param_named(disable_power_well, i915_disable_power_well, int, 0600);
@@ -141,6 +141,14 @@ module_param_named(fastboot, i915_fastboot, bool, 0600);
 MODULE_PARM_DESC(fastboot, "Try to skip unnecessary mode sets at boot time "
 		 "(default: false)");
 
+int i915_enable_pc8 __read_mostly = 1;
+module_param_named(enable_pc8, i915_enable_pc8, int, 0600);
+MODULE_PARM_DESC(enable_pc8, "Enable support for low power package C states (PC8+) (default: true)");
+
+int i915_pc8_timeout __read_mostly = 5000;
+module_param_named(pc8_timeout, i915_pc8_timeout, int, 0600);
+MODULE_PARM_DESC(pc8_timeout, "Number of msecs of idleness required to enter PC8+ (default: 5000)");
+
 bool i915_prefault_disable __read_mostly;
 module_param_named(prefault_disable, i915_prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
@@ -557,6 +565,9 @@ static int i915_drm_freeze(struct drm_device *dev)
 	dev_priv->modeset_restore = MODESET_SUSPENDED;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
+	/* We do a lot of poking in a lot of registers, make sure they work
+	 * properly. */
+	hsw_disable_package_c8(dev_priv);
 	intel_set_power_well(dev, true);
 
 	drm_kms_helper_poll_disable(dev);
@@ -713,6 +724,10 @@ static int __i915_drm_thaw(struct drm_device *dev)
 		schedule_work(&dev_priv->console_resume_work);
 	}
 
+	/* Undo what we did at i915_drm_freeze so the refcount goes back to the
+	 * expected level. */
+	hsw_enable_package_c8(dev_priv);
+
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);

drivers/gpu/drm/i915/i915_drv.h

@@ -455,6 +455,7 @@ enum i915_cache_level {
 			      caches, eg sampler/render caches, and the
 			      large Last-Level-Cache. LLC is coherent with
 			      the CPU, but L3 is only visible to the GPU. */
+	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
 };
 
 typedef uint32_t gen6_gtt_pte_t;
@@ -563,6 +564,10 @@ struct i915_vma {
 	struct list_head mm_list;
 
 	struct list_head vma_link; /* Link in the object's VMA list */
+
+	/** This vma's place in the batchbuffer or on the eviction list */
+	struct list_head exec_list;
+
 };
 
 struct i915_ctx_hang_stats {
@@ -1072,6 +1077,75 @@ struct intel_wm_level {
 	uint32_t fbc_val;
 };
 
+/*
+ * This struct tracks the state needed for the Package C8+ feature.
+ *
+ * Package states C8 and deeper are really deep PC states that can only be
+ * reached when all the devices on the system allow it, so even if the graphics
+ * device allows PC8+, it doesn't mean the system will actually get to these
+ * states.
+ *
+ * Our driver only allows PC8+ when all the outputs are disabled, the power well
+ * is disabled and the GPU is idle. When these conditions are met, we manually
+ * do the other conditions: disable the interrupts, clocks and switch LCPLL
+ * refclk to Fclk.
+ *
+ * When we really reach PC8 or deeper states (not just when we allow it) we lose
+ * the state of some registers, so when we come back from PC8+ we need to
+ * restore this state. We don't get into PC8+ if we're not in RC6, so we don't
+ * need to take care of the registers kept by RC6.
+ *
+ * The interrupt disabling is part of the requirements. We can only leave the
+ * PCH HPD interrupts enabled. If we're in PC8+ and we get another interrupt we
+ * can lock the machine.
+ *
+ * Ideally every piece of our code that needs PC8+ disabled would call
+ * hsw_disable_package_c8, which would increment disable_count and prevent the
+ * system from reaching PC8+. But we don't have a symmetric way to do this for
+ * everything, so we have the requirements_met and gpu_idle variables. When we
+ * switch requirements_met or gpu_idle to true we decrease disable_count, and
+ * increase it in the opposite case. The requirements_met variable is true when
+ * all the CRTCs, encoders and the power well are disabled. The gpu_idle
+ * variable is true when the GPU is idle.
+ *
+ * In addition to everything, we only actually enable PC8+ if disable_count
+ * stays at zero for at least some seconds. This is implemented with the
+ * enable_work variable. We do this so we don't enable/disable PC8 dozens of
+ * consecutive times when all screens are disabled and some background app
+ * queries the state of our connectors, or we have some application constantly
+ * waking up to use the GPU. Only after the enable_work function actually
+ * enables PC8+ the "enable" variable will become true, which means that it can
+ * be false even if disable_count is 0.
+ *
+ * The irqs_disabled variable becomes true exactly after we disable the IRQs and
+ * goes back to false exactly before we reenable the IRQs. We use this variable
+ * to check if someone is trying to enable/disable IRQs while they're supposed
+ * to be disabled. This shouldn't happen and we'll print some error messages in
+ * case it happens, but if it actually happens we'll also update the variables
+ * inside struct regsave so when we restore the IRQs they will contain the
+ * latest expected values.
+ *
+ * For more, read "Display Sequences for Package C8" on our documentation.
+ */
+struct i915_package_c8 {
+	bool requirements_met;
+	bool gpu_idle;
+	bool irqs_disabled;
+	/* Only true after the delayed work task actually enables it. */
+	bool enabled;
+	int disable_count;
+	struct mutex lock;
+	struct delayed_work enable_work;
+
+	struct {
+		uint32_t deimr;
+		uint32_t sdeimr;
+		uint32_t gtimr;
+		uint32_t gtier;
+		uint32_t gen6_pmimr;
+	} regsave;
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1119,6 +1193,7 @@ typedef struct drm_i915_private {
 	/** Cached value of IMR to avoid reads in updating the bitfield */
 	u32 irq_mask;
 	u32 gt_irq_mask;
+	u32 pm_irq_mask;
 
 	struct work_struct hotplug_work;
 	bool enable_hotplug_processing;
@@ -1255,6 +1330,8 @@ typedef struct drm_i915_private {
 		uint16_t cur_latency[5];
 	} wm;
 
+	struct i915_package_c8 pc8;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
@@ -1312,6 +1389,8 @@ struct drm_i915_gem_object {
 	struct list_head global_list;
 
 	struct list_head ring_list;
+	/** Used in execbuf to temporarily hold a ref */
+	struct list_head obj_exec_link;
 	/** This object's place in the batchbuffer or on the eviction list */
 	struct list_head exec_list;
 
@@ -1378,6 +1457,7 @@ struct drm_i915_gem_object {
 	 */
 	unsigned int fault_mappable:1;
 	unsigned int pin_mappable:1;
+	unsigned int pin_display:1;
 
 	/*
 	 * Is the GPU currently using a fence to access this buffer,
@@ -1385,7 +1465,7 @@ struct drm_i915_gem_object {
 	unsigned int pending_fenced_gpu_access:1;
 	unsigned int fenced_gpu_access:1;
 
-	unsigned int cache_level:2;
+	unsigned int cache_level:3;
 
 	unsigned int has_aliasing_ppgtt_mapping:1;
 	unsigned int has_global_gtt_mapping:1;
@@ -1498,7 +1578,6 @@ struct drm_i915_file_private {
 #define IS_PINEVIEW_M(dev)	((dev)->pci_device == 0xa011)
 #define IS_PINEVIEW(dev)	(INTEL_INFO(dev)->is_pineview)
 #define IS_G33(dev)		(INTEL_INFO(dev)->is_g33)
-#define IS_IRONLAKE_D(dev)	((dev)->pci_device == 0x0042)
 #define IS_IRONLAKE_M(dev)	((dev)->pci_device == 0x0046)
 #define IS_IVYBRIDGE(dev)	(INTEL_INFO(dev)->is_ivybridge)
 #define IS_IVB_GT1(dev)		((dev)->pci_device == 0x0156 || \
@@ -1510,6 +1589,8 @@ struct drm_i915_file_private {
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
+#define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
+				 ((dev)->pci_device & 0xFF00) == 0x0C00)
 #define IS_ULT(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pci_device & 0xFF00) == 0x0A00)
 
@@ -1530,6 +1611,7 @@ struct drm_i915_file_private {
 #define HAS_BLT(dev)            (INTEL_INFO(dev)->has_blt_ring)
 #define HAS_VEBOX(dev)          (INTEL_INFO(dev)->has_vebox_ring)
 #define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
+#define HAS_WT(dev)            (IS_HASWELL(dev) && to_i915(dev)->ellc_size)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
@@ -1552,8 +1634,6 @@ struct drm_i915_file_private {
 #define SUPPORTS_EDP(dev)		(IS_IRONLAKE_M(dev))
 #define SUPPORTS_TV(dev)		(INTEL_INFO(dev)->supports_tv)
 #define I915_HAS_HOTPLUG(dev)		 (INTEL_INFO(dev)->has_hotplug)
-/* dsparb controlled by hw only */
-#define DSPARB_HWCONTROL(dev) (IS_G4X(dev) || IS_IRONLAKE(dev))
 
 #define HAS_FW_BLC(dev) (INTEL_INFO(dev)->gen > 2)
 #define HAS_PIPE_CXSR(dev) (INTEL_INFO(dev)->has_pipe_cxsr)
@@ -1561,8 +1641,6 @@ struct drm_i915_file_private {
 
 #define HAS_IPS(dev)		(IS_ULT(dev))
 
-#define HAS_PIPE_CONTROL(dev) (INTEL_INFO(dev)->gen >= 5)
-
 #define HAS_DDI(dev)		(INTEL_INFO(dev)->has_ddi)
 #define HAS_POWER_WELL(dev)	(IS_HASWELL(dev))
 #define HAS_FPGA_DBG_UNCLAIMED(dev)	(INTEL_INFO(dev)->has_fpga_dbg)
@@ -1629,6 +1707,8 @@ extern unsigned int i915_preliminary_hw_support __read_mostly;
 extern int i915_disable_power_well __read_mostly;
 extern int i915_enable_ips __read_mostly;
 extern bool i915_fastboot __read_mostly;
+extern int i915_enable_pc8 __read_mostly;
+extern int i915_pc8_timeout __read_mostly;
 extern bool i915_prefault_disable __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
@@ -1839,7 +1919,7 @@ static inline bool i915_terminally_wedged(struct i915_gpu_error *error)
 }
 
 void i915_gem_reset(struct drm_device *dev);
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj);
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
@@ -1866,6 +1946,7 @@ int __must_check
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
 				     struct intel_ring_buffer *pipelined);
+void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj);
 int i915_gem_attach_phys_object(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				int id,
@@ -1901,6 +1982,9 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 				struct i915_address_space *vm);
 struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 				     struct i915_address_space *vm);
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm);
 /* Some GGTT VM helpers */
 #define obj_to_ggtt(obj) \
 	(&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base)

drivers/gpu/drm/i915/i915_gem.c

@@ -38,7 +38,8 @@
 #include <linux/dma-buf.h>
 
 static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj);
-static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj);
+static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+						   bool force);
 static __must_check int
 i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 			   struct i915_address_space *vm,
@@ -62,6 +63,20 @@ static long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static void i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
 
+static bool cpu_cache_is_coherent(struct drm_device *dev,
+				  enum i915_cache_level level)
+{
+	return HAS_LLC(dev) || level != I915_CACHE_NONE;
+}
+
+static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
+		return true;
+
+	return obj->pin_display;
+}
+
 static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
 {
 	if (obj->tiling_mode)
@@ -414,8 +429,7 @@ i915_gem_shmem_pread(struct drm_device *dev,
 		 * read domain and manually flush cachelines (if required). This
 		 * optimizes for the case when the gpu will dirty the data
 		 * anyway again before the next pread happens. */
-		if (obj->cache_level == I915_CACHE_NONE)
-			needs_clflush = 1;
+		needs_clflush = !cpu_cache_is_coherent(dev, obj->cache_level);
 		if (i915_gem_obj_bound_any(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, false);
 			if (ret)
@@ -731,19 +745,18 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 		 * write domain and manually flush cachelines (if required). This
 		 * optimizes for the case when the gpu will use the data
 		 * right away and we therefore have to clflush anyway. */
-		if (obj->cache_level == I915_CACHE_NONE)
-			needs_clflush_after = 1;
+		needs_clflush_after = cpu_write_needs_clflush(obj);
 		if (i915_gem_obj_bound_any(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, true);
 			if (ret)
 				return ret;
 		}
 	}
-	/* Same trick applies for invalidate partially written cachelines before
-	 * writing.  */
-	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)
-	    && obj->cache_level == I915_CACHE_NONE)
-		needs_clflush_before = 1;
+	/* Same trick applies to invalidate partially written cachelines read
+	 * before writing. */
+	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0)
+		needs_clflush_before =
+			!cpu_cache_is_coherent(dev, obj->cache_level);
 
 	ret = i915_gem_object_get_pages(obj);
 	if (ret)
@@ -822,8 +835,8 @@ out:
 		 */
 		if (!needs_clflush_after &&
 		    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
-			i915_gem_clflush_object(obj);
-			i915_gem_chipset_flush(dev);
+			if (i915_gem_clflush_object(obj, obj->pin_display))
+				i915_gem_chipset_flush(dev);
 		}
 	}
 
@@ -900,9 +913,9 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->cache_level == I915_CACHE_NONE &&
-	    obj->tiling_mode == I915_TILING_NONE &&
-	    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+	if (obj->tiling_mode == I915_TILING_NONE &&
+	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
+	    cpu_write_needs_clflush(obj)) {
 		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
 		 * pointers (e.g. gtt mappings when moving data between
@@ -986,6 +999,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	bool wait_forever = true;
 	int ret;
 
+	WARN(dev_priv->pc8.irqs_disabled, "IRQs disabled\n");
+
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
 
@@ -1251,8 +1266,8 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 	}
 
 	/* Pinned buffers may be scanout, so flush the cache */
-	if (obj->pin_count)
-		i915_gem_object_flush_cpu_write_domain(obj);
+	if (obj->pin_display)
+		i915_gem_object_flush_cpu_write_domain(obj, true);
 
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -1622,7 +1637,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 		 * hope for the best.
 		 */
 		WARN_ON(ret != -EIO);
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, true);
 		obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
@@ -2188,7 +2203,7 @@ static void i915_set_reset_status(struct intel_ring_buffer *ring,
 		offset = i915_gem_obj_offset(request->batch_obj,
 					     request_to_vm(request));
 
-	if (ring->hangcheck.action != wait &&
+	if (ring->hangcheck.action != HANGCHECK_WAIT &&
 	    i915_request_guilty(request, acthd, &inside)) {
 		DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n",
 			  ring->name,
@@ -2593,6 +2608,9 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (list_empty(&vma->vma_link))
 		return 0;
 
+	if (!drm_mm_node_allocated(&vma->node))
+		goto destroy;
+
 	if (obj->pin_count)
 		return -EBUSY;
 
@@ -2630,6 +2648,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 		obj->map_and_fenceable = true;
 
 	drm_mm_remove_node(&vma->node);
+
+destroy:
 	i915_gem_vma_destroy(vma);
 
 	/* Since the unbound list is global, only move to that list if
@@ -3088,15 +3108,11 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
-	bool mappable, fenceable;
 	size_t gtt_max =
 		map_and_fenceable ? dev_priv->gtt.mappable_end : vm->total;
 	struct i915_vma *vma;
 	int ret;
 
-	if (WARN_ON(!list_empty(&obj->vma_list)))
-		return -EBUSY;
-
 	fence_size = i915_gem_get_gtt_size(dev,
 					   obj->base.size,
 					   obj->tiling_mode);
@@ -3135,16 +3151,17 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_pin_pages(obj);
 
-	/* FIXME: For now we only ever use 1 VMA per object */
 	BUG_ON(!i915_is_ggtt(vm));
-	WARN_ON(!list_empty(&obj->vma_list));
 
-	vma = i915_gem_vma_create(obj, vm);
+	vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unpin;
 	}
 
+	/* For now we only ever use 1 vma per object */
+	WARN_ON(!list_is_singular(&obj->vma_list));
+
 search_free:
 	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
 						  size, alignment,
@@ -3173,18 +3190,19 @@ search_free:
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&vma->mm_list, &vm->inactive_list);
 
-	fenceable =
-		i915_is_ggtt(vm) &&
-		i915_gem_obj_ggtt_size(obj) == fence_size &&
-		(i915_gem_obj_ggtt_offset(obj) & (fence_alignment - 1)) == 0;
+	if (i915_is_ggtt(vm)) {
+		bool mappable, fenceable;
 
-	mappable =
-		i915_is_ggtt(vm) &&
-		vma->node.start + obj->base.size <= dev_priv->gtt.mappable_end;
+		fenceable = (vma->node.size == fence_size &&
+			     (vma->node.start & (fence_alignment - 1)) == 0);
+
+		mappable = (vma->node.start + obj->base.size <=
+			    dev_priv->gtt.mappable_end);
 
-	/* Map and fenceable only changes if the VM is the global GGTT */
-	if (i915_is_ggtt(vm))
 		obj->map_and_fenceable = mappable && fenceable;
+	}
+
+	WARN_ON(map_and_fenceable && !obj->map_and_fenceable);
 
 	trace_i915_vma_bind(vma, map_and_fenceable);
 	i915_gem_verify_gtt(dev);
@@ -3199,22 +3217,23 @@ err_unpin:
 	return ret;
 }
 
-void
-i915_gem_clflush_object(struct drm_i915_gem_object *obj)
+bool
+i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+			bool force)
 {
 	/* If we don't have a page list set up, then we're not pinned
 	 * to GPU, and we can ignore the cache flush because it'll happen
 	 * again at bind time.
 	 */
 	if (obj->pages == NULL)
-		return;
+		return false;
 
 	/*
 	 * 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;
+		return false;
 
 	/* If the GPU is snooping the contents of the CPU cache,
 	 * we do not need to manually clear the CPU cache lines.  However,
@@ -3224,12 +3243,13 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 	 * snooping behaviour occurs naturally as the result of our domain
 	 * tracking.
 	 */
-	if (obj->cache_level != I915_CACHE_NONE)
-		return;
+	if (!force && cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
+		return false;
 
 	trace_i915_gem_object_clflush(obj);
-
 	drm_clflush_sg(obj->pages);
+
+	return true;
 }
 
 /** Flushes the GTT write domain for the object if it's dirty. */
@@ -3261,15 +3281,17 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 
 /** Flushes the CPU write domain for the object if it's dirty. */
 static void
-i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
+i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+				       bool force)
 {
 	uint32_t old_write_domain;
 
 	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU)
 		return;
 
-	i915_gem_clflush_object(obj);
-	i915_gem_chipset_flush(obj->base.dev);
+	if (i915_gem_clflush_object(obj, force))
+		i915_gem_chipset_flush(obj->base.dev);
+
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
@@ -3302,7 +3324,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
-	i915_gem_object_flush_cpu_write_domain(obj);
+	i915_gem_object_flush_cpu_write_domain(obj, false);
 
 	/* Serialise direct access to this object with the barriers for
 	 * coherent writes from the GPU, by effectively invalidating the
@@ -3392,7 +3414,11 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 					       obj, cache_level);
 	}
 
-	if (cache_level == I915_CACHE_NONE) {
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		vma->node.color = cache_level;
+	obj->cache_level = cache_level;
+
+	if (cpu_write_needs_clflush(obj)) {
 		u32 old_read_domains, old_write_domain;
 
 		/* If we're coming from LLC cached, then we haven't
@@ -3402,7 +3428,6 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		 * Just set it to the CPU cache for now.
 		 */
 		WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
-		WARN_ON(obj->base.read_domains & ~I915_GEM_DOMAIN_CPU);
 
 		old_read_domains = obj->base.read_domains;
 		old_write_domain = obj->base.write_domain;
@@ -3415,9 +3440,6 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 						    old_write_domain);
 	}
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
-		vma->node.color = cache_level;
-	obj->cache_level = cache_level;
 	i915_gem_verify_gtt(dev);
 	return 0;
 }
@@ -3439,7 +3461,20 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 		goto unlock;
 	}
 
-	args->caching = obj->cache_level != I915_CACHE_NONE;
+	switch (obj->cache_level) {
+	case I915_CACHE_LLC:
+	case I915_CACHE_L3_LLC:
+		args->caching = I915_CACHING_CACHED;
+		break;
+
+	case I915_CACHE_WT:
+		args->caching = I915_CACHING_DISPLAY;
+		break;
+
+	default:
+		args->caching = I915_CACHING_NONE;
+		break;
+	}
 
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -3462,6 +3497,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	case I915_CACHING_CACHED:
 		level = I915_CACHE_LLC;
 		break;
+	case I915_CACHING_DISPLAY:
+		level = HAS_WT(dev) ? I915_CACHE_WT : I915_CACHE_NONE;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3484,6 +3522,22 @@ unlock:
 	return ret;
 }
 
+static bool is_pin_display(struct drm_i915_gem_object *obj)
+{
+	/* There are 3 sources that pin objects:
+	 *   1. The display engine (scanouts, sprites, cursors);
+	 *   2. Reservations for execbuffer;
+	 *   3. The user.
+	 *
+	 * We can ignore reservations as we hold the struct_mutex and
+	 * are only called outside of the reservation path.  The user
+	 * can only increment pin_count once, and so if after
+	 * subtracting the potential reference by the user, any pin_count
+	 * remains, it must be due to another use by the display engine.
+	 */
+	return obj->pin_count - !!obj->user_pin_count;
+}
+
 /*
  * Prepare buffer for display plane (scanout, cursors, etc).
  * Can be called from an uninterruptible phase (modesetting) and allows
@@ -3503,6 +3557,11 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 			return ret;
 	}
 
+	/* Mark the pin_display early so that we account for the
+	 * display coherency whilst setting up the cache domains.
+	 */
+	obj->pin_display = true;
+
 	/* The display engine is not coherent with the LLC cache on gen6.  As
 	 * a result, we make sure that the pinning that is about to occur is
 	 * done with uncached PTEs. This is lowest common denominator for all
@@ -3512,9 +3571,10 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * of uncaching, which would allow us to flush all the LLC-cached data
 	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
 	 */
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
+	ret = i915_gem_object_set_cache_level(obj,
+					      HAS_WT(obj->base.dev) ? I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
-		return ret;
+		goto err_unpin_display;
 
 	/* As the user may map the buffer once pinned in the display plane
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
@@ -3522,9 +3582,9 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 */
 	ret = i915_gem_obj_ggtt_pin(obj, alignment, true, false);
 	if (ret)
-		return ret;
+		goto err_unpin_display;
 
-	i915_gem_object_flush_cpu_write_domain(obj);
+	i915_gem_object_flush_cpu_write_domain(obj, true);
 
 	old_write_domain = obj->base.write_domain;
 	old_read_domains = obj->base.read_domains;
@@ -3540,6 +3600,17 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 					    old_write_domain);
 
 	return 0;
+
+err_unpin_display:
+	obj->pin_display = is_pin_display(obj);
+	return ret;
+}
+
+void
+i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_unpin(obj);
+	obj->pin_display = is_pin_display(obj);
 }
 
 int
@@ -3585,7 +3656,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 
 	/* Flush the CPU cache if it's still invalid. */
 	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) {
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, false);
 
 		obj->base.read_domains |= I915_GEM_DOMAIN_CPU;
 	}
@@ -3767,10 +3838,6 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	obj->user_pin_count++;
 	obj->pin_filp = file;
 
-	/* XXX - flush the CPU caches for pinned objects
-	 * as the X server doesn't manage domains yet
-	 */
-	i915_gem_object_flush_cpu_write_domain(obj);
 	args->offset = i915_gem_obj_ggtt_offset(obj);
 out:
 	drm_gem_object_unreference(&obj->base);
@@ -3913,6 +3980,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 	INIT_LIST_HEAD(&obj->global_list);
 	INIT_LIST_HEAD(&obj->ring_list);
 	INIT_LIST_HEAD(&obj->exec_list);
+	INIT_LIST_HEAD(&obj->obj_exec_link);
 	INIT_LIST_HEAD(&obj->vma_list);
 
 	obj->ops = ops;
@@ -4052,6 +4120,7 @@ struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&vma->vma_link);
 	INIT_LIST_HEAD(&vma->mm_list);
+	INIT_LIST_HEAD(&vma->exec_list);
 	vma->vm = vm;
 	vma->obj = obj;
 
@@ -4801,3 +4870,16 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 
 	return NULL;
 }
+
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm)
+{
+	struct i915_vma *vma;
+
+	vma = i915_gem_obj_to_vma(obj, vm);
+	if (!vma)
+		vma = i915_gem_vma_create(obj, vm);
+
+	return vma;
+}

drivers/gpu/drm/i915/i915_gem_dmabuf.c

@@ -27,10 +27,15 @@
 #include "i915_drv.h"
 #include <linux/dma-buf.h>
 
+static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
+{
+	return to_intel_bo(buf->priv);
+}
+
 static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment,
 					     enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = attachment->dmabuf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
 	struct sg_table *st;
 	struct scatterlist *src, *dst;
 	int ret, i;
@@ -85,14 +90,22 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 				   struct sg_table *sg,
 				   enum dma_data_direction dir)
 {
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
+
+	mutex_lock(&obj->base.dev->struct_mutex);
+
 	dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir);
 	sg_free_table(sg);
 	kfree(sg);
+
+	i915_gem_object_unpin_pages(obj);
+
+	mutex_unlock(&obj->base.dev->struct_mutex);
 }
 
 static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	struct sg_page_iter sg_iter;
 	struct page **pages;
@@ -140,7 +153,7 @@ error:
 
 static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	int ret;
 
@@ -183,7 +196,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 
 static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t length, enum dma_data_direction direction)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	int ret;
 	bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE);
@@ -214,9 +227,7 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				      struct drm_gem_object *gem_obj, int flags)
 {
-	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
-
-	return dma_buf_export(obj, &i915_dmabuf_ops, obj->base.size, flags);
+	return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags);
 }
 
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
@@ -253,7 +264,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 
 	/* is this one of own objects? */
 	if (dma_buf->ops == &i915_dmabuf_ops) {
-		obj = dma_buf->priv;
+		obj = dma_buf_to_obj(dma_buf);
 		/* is it from our device? */
 		if (obj->base.dev == dev) {
 			/*

drivers/gpu/drm/i915/i915_gem_evict.c

@@ -37,7 +37,7 @@ mark_free(struct i915_vma *vma, struct list_head *unwind)
 	if (vma->obj->pin_count)
 		return false;
 
-	list_add(&vma->obj->exec_list, unwind);
+	list_add(&vma->exec_list, unwind);
 	return drm_mm_scan_add_block(&vma->node);
 }
 
@@ -49,7 +49,6 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
 	struct i915_vma *vma;
-	struct drm_i915_gem_object *obj;
 	int ret = 0;
 
 	trace_i915_gem_evict(dev, min_size, alignment, mappable);
@@ -104,14 +103,13 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 none:
 	/* Nothing found, clean up and bail out! */
 	while (!list_empty(&unwind_list)) {
-		obj = list_first_entry(&unwind_list,
-				       struct drm_i915_gem_object,
+		vma = list_first_entry(&unwind_list,
+				       struct i915_vma,
 				       exec_list);
-		vma = i915_gem_obj_to_vma(obj, vm);
 		ret = drm_mm_scan_remove_block(&vma->node);
 		BUG_ON(ret);
 
-		list_del_init(&obj->exec_list);
+		list_del_init(&vma->exec_list);
 	}
 
 	/* We expect the caller to unpin, evict all and try again, or give up.
@@ -125,28 +123,30 @@ found:
 	 * temporary list. */
 	INIT_LIST_HEAD(&eviction_list);
 	while (!list_empty(&unwind_list)) {
-		obj = list_first_entry(&unwind_list,
-				       struct drm_i915_gem_object,
+		vma = list_first_entry(&unwind_list,
+				       struct i915_vma,
 				       exec_list);
-		vma = i915_gem_obj_to_vma(obj, vm);
 		if (drm_mm_scan_remove_block(&vma->node)) {
-			list_move(&obj->exec_list, &eviction_list);
-			drm_gem_object_reference(&obj->base);
+			list_move(&vma->exec_list, &eviction_list);
+			drm_gem_object_reference(&vma->obj->base);
 			continue;
 		}
-		list_del_init(&obj->exec_list);
+		list_del_init(&vma->exec_list);
 	}
 
 	/* Unbinding will emit any required flushes */
 	while (!list_empty(&eviction_list)) {
-		obj = list_first_entry(&eviction_list,
-				       struct drm_i915_gem_object,
+		struct drm_gem_object *obj;
+		vma = list_first_entry(&eviction_list,
+				       struct i915_vma,
 				       exec_list);
+
+		obj =  &vma->obj->base;
+		list_del_init(&vma->exec_list);
 		if (ret == 0)
-			ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm));
+			ret = i915_vma_unbind(vma);
 
-		list_del_init(&obj->exec_list);
-		drm_gem_object_unreference(&obj->base);
+		drm_gem_object_unreference(obj);
 	}
 
 	return ret;

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -171,6 +171,56 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 		obj->cache_level != I915_CACHE_NONE);
 }
 
+static int
+relocate_entry_cpu(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	uint32_t page_offset = offset_in_page(reloc->offset);
+	char *vaddr;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+	if (ret)
+		return ret;
+
+	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+				reloc->offset >> PAGE_SHIFT));
+	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	kunmap_atomic(vaddr);
+
+	return 0;
+}
+
+static int
+relocate_entry_gtt(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t __iomem *reloc_entry;
+	void __iomem *reloc_page;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_object_put_fence(obj);
+	if (ret)
+		return ret;
+
+	/* Map the page containing the relocation we're going to perform.  */
+	reloc->offset += i915_gem_obj_ggtt_offset(obj);
+	reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
+			reloc->offset & PAGE_MASK);
+	reloc_entry = (uint32_t __iomem *)
+		(reloc_page + offset_in_page(reloc->offset));
+	iowrite32(reloc->delta, reloc_entry);
+	io_mapping_unmap_atomic(reloc_page);
+
+	return 0;
+}
+
 static int
 i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 				   struct eb_objects *eb,
@@ -255,40 +305,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -EFAULT;
 
 	reloc->delta += target_offset;
-	if (use_cpu_reloc(obj)) {
-		uint32_t page_offset = offset_in_page(reloc->offset);
-		char *vaddr;
-
-		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
-		if (ret)
-			return ret;
-
-		vaddr = kmap_atomic(i915_gem_object_get_page(obj,
-							     reloc->offset >> PAGE_SHIFT));
-		*(uint32_t *)(vaddr + page_offset) = reloc->delta;
-		kunmap_atomic(vaddr);
-	} else {
-		struct drm_i915_private *dev_priv = dev->dev_private;
-		uint32_t __iomem *reloc_entry;
-		void __iomem *reloc_page;
-
-		ret = i915_gem_object_set_to_gtt_domain(obj, true);
-		if (ret)
-			return ret;
-
-		ret = i915_gem_object_put_fence(obj);
-		if (ret)
-			return ret;
-
-		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += i915_gem_obj_ggtt_offset(obj);
-		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						      reloc->offset & PAGE_MASK);
-		reloc_entry = (uint32_t __iomem *)
-			(reloc_page + offset_in_page(reloc->offset));
-		iowrite32(reloc->delta, reloc_entry);
-		io_mapping_unmap_atomic(reloc_page);
-	}
+	if (use_cpu_reloc(obj))
+		ret = relocate_entry_cpu(obj, reloc);
+	else
+		ret = relocate_entry_gtt(obj, reloc);
 
 	/* and update the user's relocation entry */
 	reloc->presumed_offset = target_offset;
@@ -708,6 +728,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 {
 	struct drm_i915_gem_object *obj;
 	uint32_t flush_domains = 0;
+	bool flush_chipset = false;
 	int ret;
 
 	list_for_each_entry(obj, objects, exec_list) {
@@ -716,12 +737,12 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 			return ret;
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			i915_gem_clflush_object(obj);
+			flush_chipset |= i915_gem_clflush_object(obj, false);
 
 		flush_domains |= obj->base.write_domain;
 	}
 
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
+	if (flush_chipset)
 		i915_gem_chipset_flush(ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -55,6 +55,7 @@
 #define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
 #define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
 #define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level)
@@ -138,8 +139,16 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
-	if (level != I915_CACHE_NONE)
+	switch (level) {
+	case I915_CACHE_NONE:
+		break;
+	case I915_CACHE_WT:
+		pte |= HSW_WT_ELLC_LLC_AGE0;
+		break;
+	default:
 		pte |= HSW_WB_ELLC_LLC_AGE0;
+		break;
+	}
 
 	return pte;
 }
@@ -487,7 +496,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 				       dev_priv->gtt.base.total / PAGE_SIZE);
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, obj->pin_display);
 		i915_gem_gtt_bind_object(obj, obj->cache_level);
 	}
 

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -296,9 +296,8 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
-	obj->base.write_domain = I915_GEM_DOMAIN_GTT;
-	obj->base.read_domains = I915_GEM_DOMAIN_GTT;
-	obj->cache_level = I915_CACHE_NONE;
+	obj->base.read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
+	obj->cache_level = HAS_LLC(dev) ? I915_CACHE_LLC : I915_CACHE_NONE;
 
 	return obj;
 
@@ -410,8 +409,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 		ret = drm_mm_reserve_node(&ggtt->mm, &vma->node);
 		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
-			i915_gem_vma_destroy(vma);
-			goto err_out;
+			goto err_vma;
 		}
 	}
 
@@ -422,6 +420,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 	return obj;
 
+err_vma:
+	i915_gem_vma_destroy(vma);
 err_out:
 	drm_mm_remove_node(stolen);
 	kfree(stolen);

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -243,6 +243,11 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
 			   error->semaphore_mboxes[ring][1],
 			   error->semaphore_seqno[ring][1]);
+		if (HAS_VEBOX(dev)) {
+			err_printf(m, "  SYNC_2: 0x%08x [last synced 0x%08x]\n",
+				   error->semaphore_mboxes[ring][2],
+				   error->semaphore_seqno[ring][2]);
+		}
 	}
 	err_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
 	err_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
@@ -682,6 +687,12 @@ static void i915_record_ring_state(struct drm_device *dev,
 		error->semaphore_seqno[ring->id][1] = ring->sync_seqno[1];
 	}
 
+	if (HAS_VEBOX(dev)) {
+		error->semaphore_mboxes[ring->id][2] =
+			I915_READ(RING_SYNC_2(ring->mmio_base));
+		error->semaphore_seqno[ring->id][2] = ring->sync_seqno[2];
+	}
+
 	if (INTEL_INFO(dev)->gen >= 4) {
 		error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base));
 		error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base));

drivers/gpu/drm/i915/i915_irq.c

@@ -85,6 +85,12 @@ ironlake_enable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr &= ~mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != 0) {
 		dev_priv->irq_mask &= ~mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -97,6 +103,12 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr |= mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != mask) {
 		dev_priv->irq_mask |= mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -104,6 +116,85 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 	}
 }
 
+/**
+ * ilk_update_gt_irq - update GTIMR
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ */
+static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gtimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gtimr |= (~enabled_irq_mask &
+						interrupt_mask);
+		return;
+	}
+
+	dev_priv->gt_irq_mask &= ~interrupt_mask;
+	dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask);
+	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	POSTING_READ(GTIMR);
+}
+
+void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	ilk_update_gt_irq(dev_priv, mask, mask);
+}
+
+void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	ilk_update_gt_irq(dev_priv, mask, 0);
+}
+
+/**
+  * snb_update_pm_irq - update GEN6_PMIMR
+  * @dev_priv: driver private
+  * @interrupt_mask: mask of interrupt bits to update
+  * @enabled_irq_mask: mask of interrupt bits to enable
+  */
+static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	uint32_t new_val;
+
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gen6_pmimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gen6_pmimr |= (~enabled_irq_mask &
+						     interrupt_mask);
+		return;
+	}
+
+	new_val = dev_priv->pm_irq_mask;
+	new_val &= ~interrupt_mask;
+	new_val |= (~enabled_irq_mask & interrupt_mask);
+
+	if (new_val != dev_priv->pm_irq_mask) {
+		dev_priv->pm_irq_mask = new_val;
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask);
+		POSTING_READ(GEN6_PMIMR);
+	}
+}
+
+void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, mask);
+}
+
+void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, 0);
+}
+
 static bool ivb_can_enable_err_int(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -194,6 +285,15 @@ static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled &&
+	    (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.sdeimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.sdeimr |= (~enabled_irq_mask &
+						 interrupt_mask);
+		return;
+	}
+
 	I915_WRITE(SDEIMR, sdeimr);
 	POSTING_READ(SDEIMR);
 }
@@ -711,17 +811,19 @@ static void gen6_pm_rps_work(struct work_struct *work)
 {
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    rps.work);
-	u32 pm_iir, pm_imr;
+	u32 pm_iir;
 	u8 new_delay;
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
-	pm_imr = I915_READ(GEN6_PMIMR);
 	/* Make sure not to corrupt PMIMR state used by ringbuffer code */
-	I915_WRITE(GEN6_PMIMR, pm_imr & ~GEN6_PM_RPS_EVENTS);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
+	/* Make sure we didn't queue anything we're not going to process. */
+	WARN_ON(pm_iir & ~GEN6_PM_RPS_EVENTS);
+
 	if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0)
 		return;
 
@@ -806,8 +908,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	dev_priv->gt_irq_mask &= ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	ilk_enable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	mutex_unlock(&dev_priv->dev->struct_mutex);
@@ -837,8 +938,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	dev_priv->gt_irq_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	ilk_disable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 	spin_unlock(&dev_priv->irq_lock);
 
 	queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work);
@@ -879,29 +979,6 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		ivybridge_parity_error_irq_handler(dev);
 }
 
-/* Legacy way of handling PM interrupts */
-static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv,
-				 u32 pm_iir)
-{
-	/*
-	 * IIR bits should never already be set because IMR should
-	 * prevent an interrupt from being shown in IIR. The warning
-	 * displays a case where we've unsafely cleared
-	 * dev_priv->rps.pm_iir. Although missing an interrupt of the same
-	 * type is not a problem, it displays a problem in the logic.
-	 *
-	 * The mask bit in IMR is cleared by dev_priv->rps.work.
-	 */
-
-	spin_lock(&dev_priv->irq_lock);
-	dev_priv->rps.pm_iir |= pm_iir;
-	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-	POSTING_READ(GEN6_PMIMR);
-	spin_unlock(&dev_priv->irq_lock);
-
-	queue_work(dev_priv->wq, &dev_priv->rps.work);
-}
-
 #define HPD_STORM_DETECT_PERIOD 1000
 #define HPD_STORM_THRESHOLD 5
 
@@ -968,31 +1045,28 @@ static void dp_aux_irq_handler(struct drm_device *dev)
 	wake_up_all(&dev_priv->gmbus_wait_queue);
 }
 
-/* Unlike gen6_rps_irq_handler() from which this function is originally derived,
- * we must be able to deal with other PM interrupts. This is complicated because
- * of the way in which we use the masks to defer the RPS work (which for
- * posterity is necessary because of forcewake).
- */
-static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
-			       u32 pm_iir)
+/* The RPS events need forcewake, so we add them to a work queue and mask their
+ * IMR bits until the work is done. Other interrupts can be processed without
+ * the work queue. */
+static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 {
 	if (pm_iir & GEN6_PM_RPS_EVENTS) {
 		spin_lock(&dev_priv->irq_lock);
 		dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
-		I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-		/* never want to mask useful interrupts. (also posting read) */
-		WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
+		snb_disable_pm_irq(dev_priv, pm_iir & GEN6_PM_RPS_EVENTS);
 		spin_unlock(&dev_priv->irq_lock);
 
 		queue_work(dev_priv->wq, &dev_priv->rps.work);
 	}
 
-	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
+	if (HAS_VEBOX(dev_priv->dev)) {
+		if (pm_iir & PM_VEBOX_USER_INTERRUPT)
+			notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
 
-	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
-		DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
-		i915_handle_error(dev_priv->dev, false);
+		if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
+			DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
+			i915_handle_error(dev_priv->dev, false);
+		}
 	}
 }
 
@@ -1064,7 +1138,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		if (pipe_stats[0] & PIPE_GMBUS_INTERRUPT_STATUS)
 			gmbus_irq_handler(dev);
 
-		if (pm_iir & GEN6_PM_RPS_EVENTS)
+		if (pm_iir)
 			gen6_rps_irq_handler(dev_priv, pm_iir);
 
 		I915_WRITE(GTIIR, gt_iir);
@@ -1309,6 +1383,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
+	bool err_int_reenable = false;
 
 	atomic_inc(&dev_priv->irq_received);
 
@@ -1337,7 +1412,9 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	 * handler. */
 	if (IS_HASWELL(dev)) {
 		spin_lock(&dev_priv->irq_lock);
-		ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
+		err_int_reenable = ~dev_priv->irq_mask & DE_ERR_INT_IVB;
+		if (err_int_reenable)
+			ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
 		spin_unlock(&dev_priv->irq_lock);
 	}
 
@@ -1364,16 +1441,13 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (INTEL_INFO(dev)->gen >= 6) {
 		u32 pm_iir = I915_READ(GEN6_PMIIR);
 		if (pm_iir) {
-			if (IS_HASWELL(dev))
-				hsw_pm_irq_handler(dev_priv, pm_iir);
-			else if (pm_iir & GEN6_PM_RPS_EVENTS)
-				gen6_rps_irq_handler(dev_priv, pm_iir);
+			gen6_rps_irq_handler(dev_priv, pm_iir);
 			I915_WRITE(GEN6_PMIIR, pm_iir);
 			ret = IRQ_HANDLED;
 		}
 	}
 
-	if (IS_HASWELL(dev)) {
+	if (err_int_reenable) {
 		spin_lock(&dev_priv->irq_lock);
 		if (ivb_can_enable_err_int(dev))
 			ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB);
@@ -1826,10 +1900,10 @@ ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
 	u32 tmp;
 
 	if (ring->hangcheck.acthd != acthd)
-		return active;
+		return HANGCHECK_ACTIVE;
 
 	if (IS_GEN2(dev))
-		return hung;
+		return HANGCHECK_HUNG;
 
 	/* Is the chip hanging on a WAIT_FOR_EVENT?
 	 * If so we can simply poke the RB_WAIT bit
@@ -1841,24 +1915,24 @@ ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
 		DRM_ERROR("Kicking stuck wait on %s\n",
 			  ring->name);
 		I915_WRITE_CTL(ring, tmp);
-		return kick;
+		return HANGCHECK_KICK;
 	}
 
 	if (INTEL_INFO(dev)->gen >= 6 && tmp & RING_WAIT_SEMAPHORE) {
 		switch (semaphore_passed(ring)) {
 		default:
-			return hung;
+			return HANGCHECK_HUNG;
 		case 1:
 			DRM_ERROR("Kicking stuck semaphore on %s\n",
 				  ring->name);
 			I915_WRITE_CTL(ring, tmp);
-			return kick;
+			return HANGCHECK_KICK;
 		case 0:
-			return wait;
+			return HANGCHECK_WAIT;
 		}
 	}
 
-	return hung;
+	return HANGCHECK_HUNG;
 }
 
 /**
@@ -1905,8 +1979,6 @@ static void i915_hangcheck_elapsed(unsigned long data)
 				} else
 					busy = false;
 			} else {
-				int score;
-
 				/* We always increment the hangcheck score
 				 * if the ring is busy and still processing
 				 * the same request, so that no single request
@@ -1926,21 +1998,19 @@ static void i915_hangcheck_elapsed(unsigned long data)
 								    acthd);
 
 				switch (ring->hangcheck.action) {
-				case wait:
-					score = 0;
+				case HANGCHECK_WAIT:
 					break;
-				case active:
-					score = BUSY;
+				case HANGCHECK_ACTIVE:
+					ring->hangcheck.score += BUSY;
 					break;
-				case kick:
-					score = KICK;
+				case HANGCHECK_KICK:
+					ring->hangcheck.score += KICK;
 					break;
-				case hung:
-					score = HUNG;
+				case HANGCHECK_HUNG:
+					ring->hangcheck.score += HUNG;
 					stuck[i] = true;
 					break;
 				}
-				ring->hangcheck.score += score;
 			}
 		} else {
 			/* Gradually reduce the count so that we catch DoS
@@ -2158,8 +2228,9 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 		if (HAS_VEBOX(dev))
 			pm_irqs |= PM_VEBOX_USER_INTERRUPT;
 
+		dev_priv->pm_irq_mask = 0xffffffff;
 		I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
-		I915_WRITE(GEN6_PMIMR, 0xffffffff);
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask);
 		I915_WRITE(GEN6_PMIER, pm_irqs);
 		POSTING_READ(GEN6_PMIER);
 	}
@@ -2403,7 +2474,6 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 	u16 iir, new_iir;
 	u32 pipe_stats[2];
 	unsigned long irqflags;
-	int irq_received;
 	int pipe;
 	u16 flip_mask =
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
@@ -2437,7 +2507,6 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 					DRM_DEBUG_DRIVER("pipe %c underrun\n",
 							 pipe_name(pipe));
 				I915_WRITE(reg, pipe_stats[pipe]);
-				irq_received = 1;
 			}
 		}
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
@@ -3081,3 +3150,67 @@ void intel_hpd_init(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
+
+/* Disable interrupts so we can allow Package C8+. */
+void hsw_pc8_disable_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	dev_priv->pc8.regsave.deimr = I915_READ(DEIMR);
+	dev_priv->pc8.regsave.sdeimr = I915_READ(SDEIMR);
+	dev_priv->pc8.regsave.gtimr = I915_READ(GTIMR);
+	dev_priv->pc8.regsave.gtier = I915_READ(GTIER);
+	dev_priv->pc8.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
+
+	ironlake_disable_display_irq(dev_priv, ~DE_PCH_EVENT_IVB);
+	ibx_disable_display_interrupt(dev_priv, ~SDE_HOTPLUG_MASK_CPT);
+	ilk_disable_gt_irq(dev_priv, 0xffffffff);
+	snb_disable_pm_irq(dev_priv, 0xffffffff);
+
+	dev_priv->pc8.irqs_disabled = true;
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
+
+/* Restore interrupts so we can recover from Package C8+. */
+void hsw_pc8_restore_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+	uint32_t val, expected;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	val = I915_READ(DEIMR);
+	expected = ~DE_PCH_EVENT_IVB;
+	WARN(val != expected, "DEIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(SDEIMR) & ~SDE_HOTPLUG_MASK_CPT;
+	expected = ~SDE_HOTPLUG_MASK_CPT;
+	WARN(val != expected, "SDEIMR non-HPD bits are 0x%08x, not 0x%08x\n",
+	     val, expected);
+
+	val = I915_READ(GTIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GTIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(GEN6_PMIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GEN6_PMIMR is 0x%08x, not 0x%08x\n", val,
+	     expected);
+
+	dev_priv->pc8.irqs_disabled = false;
+
+	ironlake_enable_display_irq(dev_priv, ~dev_priv->pc8.regsave.deimr);
+	ibx_enable_display_interrupt(dev_priv,
+				     ~dev_priv->pc8.regsave.sdeimr &
+				     ~SDE_HOTPLUG_MASK_CPT);
+	ilk_enable_gt_irq(dev_priv, ~dev_priv->pc8.regsave.gtimr);
+	snb_enable_pm_irq(dev_priv, ~dev_priv->pc8.regsave.gen6_pmimr);
+	I915_WRITE(GTIER, dev_priv->pc8.regsave.gtier);
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}

drivers/gpu/drm/i915/i915_reg.h

@@ -1447,6 +1447,8 @@
 #define   MCH_SSKPD_WM0_MASK		0x3f
 #define   MCH_SSKPD_WM0_VAL		0xc
 
+#define MCH_SECP_NRG_STTS		(MCHBAR_MIRROR_BASE_SNB + 0x592c)
+
 /* Clocking configuration register */
 #define CLKCFG			0x10c00
 #define CLKCFG_FSB_400					(5 << 0)	/* hrawclk 100 */
@@ -1703,15 +1705,26 @@
  */
 #define CCID			0x2180
 #define   CCID_EN		(1<<0)
+/*
+ * Notes on SNB/IVB/VLV context size:
+ * - Power context is saved elsewhere (LLC or stolen)
+ * - Ring/execlist context is saved on SNB, not on IVB
+ * - Extended context size already includes render context size
+ * - We always need to follow the extended context size.
+ *   SNB BSpec has comments indicating that we should use the
+ *   render context size instead if execlists are disabled, but
+ *   based on empirical testing that's just nonsense.
+ * - Pipelined/VF state is saved on SNB/IVB respectively
+ * - GT1 size just indicates how much of render context
+ *   doesn't need saving on GT1
+ */
 #define CXT_SIZE		0x21a0
 #define GEN6_CXT_POWER_SIZE(cxt_reg)	((cxt_reg >> 24) & 0x3f)
 #define GEN6_CXT_RING_SIZE(cxt_reg)	((cxt_reg >> 18) & 0x3f)
 #define GEN6_CXT_RENDER_SIZE(cxt_reg)	((cxt_reg >> 12) & 0x3f)
 #define GEN6_CXT_EXTENDED_SIZE(cxt_reg)	((cxt_reg >> 6) & 0x3f)
 #define GEN6_CXT_PIPELINE_SIZE(cxt_reg)	((cxt_reg >> 0) & 0x3f)
-#define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_POWER_SIZE(cxt_reg) + \
-					GEN6_CXT_RING_SIZE(cxt_reg) + \
-					GEN6_CXT_RENDER_SIZE(cxt_reg) + \
+#define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_RING_SIZE(cxt_reg) + \
 					GEN6_CXT_EXTENDED_SIZE(cxt_reg) + \
 					GEN6_CXT_PIPELINE_SIZE(cxt_reg))
 #define GEN7_CXT_SIZE		0x21a8
@@ -1721,11 +1734,7 @@
 #define GEN7_CXT_EXTENDED_SIZE(ctx_reg)	((ctx_reg >> 9) & 0x7f)
 #define GEN7_CXT_GT1_SIZE(ctx_reg)	((ctx_reg >> 6) & 0x7)
 #define GEN7_CXT_VFSTATE_SIZE(ctx_reg)	((ctx_reg >> 0) & 0x3f)
-#define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_POWER_SIZE(ctx_reg) + \
-					 GEN7_CXT_RING_SIZE(ctx_reg) + \
-					 GEN7_CXT_RENDER_SIZE(ctx_reg) + \
-					 GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
-					 GEN7_CXT_GT1_SIZE(ctx_reg) + \
+#define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
 					 GEN7_CXT_VFSTATE_SIZE(ctx_reg))
 /* Haswell does have the CXT_SIZE register however it does not appear to be
  * valid. Now, docs explain in dwords what is in the context object. The full
@@ -4827,8 +4836,8 @@
 #define HSW_PWR_WELL_DRIVER			0x45404 /* CTL2 */
 #define HSW_PWR_WELL_KVMR			0x45408 /* CTL3 */
 #define HSW_PWR_WELL_DEBUG			0x4540C /* CTL4 */
-#define   HSW_PWR_WELL_ENABLE			(1<<31)
-#define   HSW_PWR_WELL_STATE			(1<<30)
+#define   HSW_PWR_WELL_ENABLE_REQUEST		(1<<31)
+#define   HSW_PWR_WELL_STATE_ENABLED		(1<<30)
 #define HSW_PWR_WELL_CTL5			0x45410
 #define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1<<31)
 #define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1<<20)

drivers/gpu/drm/i915/intel_ddi.c

@@ -1139,10 +1139,13 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 
 int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
 {
-	if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT)
+	uint32_t lcpll = I915_READ(LCPLL_CTL);
+
+	if (lcpll & LCPLL_CD_SOURCE_FCLK)
+		return 800000;
+	else if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT)
 		return 450000;
-	else if ((I915_READ(LCPLL_CTL) & LCPLL_CLK_FREQ_MASK) ==
-		 LCPLL_CLK_FREQ_450)
+	else if ((lcpll & LCPLL_CLK_FREQ_MASK) == LCPLL_CLK_FREQ_450)
 		return 450000;
 	else if (IS_ULT(dev_priv->dev))
 		return 337500;

drivers/gpu/drm/i915/intel_display.c

@@ -690,7 +690,7 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 {
 	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
 	u32 m, n, fastclk;
-	u32 updrate, minupdate, fracbits, p;
+	u32 updrate, minupdate, p;
 	unsigned long bestppm, ppm, absppm;
 	int dotclk, flag;
 
@@ -701,7 +701,6 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 	fastclk = dotclk / (2*100);
 	updrate = 0;
 	minupdate = 19200;
-	fracbits = 1;
 	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
 	bestm1 = bestm2 = bestp1 = bestp2 = 0;
 
@@ -1877,7 +1876,7 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev,
 	return 0;
 
 err_unpin:
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 err_interruptible:
 	dev_priv->mm.interruptible = true;
 	return ret;
@@ -1886,7 +1885,7 @@ err_interruptible:
 void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_fence(obj);
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 }
 
 /* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel
@@ -2598,7 +2597,7 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	u32 reg, temp, i;
+	u32 reg, temp, i, j;
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -2614,97 +2613,99 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	DRM_DEBUG_KMS("FDI_RX_IIR before link train 0x%x\n",
 		      I915_READ(FDI_RX_IIR(pipe)));
 
-	/* enable CPU FDI TX and PCH FDI RX */
-	reg = FDI_TX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_DP_PORT_WIDTH_MASK;
-	temp |= FDI_DP_PORT_WIDTH(intel_crtc->config.fdi_lanes);
-	temp &= ~(FDI_LINK_TRAIN_AUTO | FDI_LINK_TRAIN_NONE_IVB);
-	temp |= FDI_LINK_TRAIN_PATTERN_1_IVB;
-	temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-	temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B;
-	temp |= FDI_COMPOSITE_SYNC;
-	I915_WRITE(reg, temp | FDI_TX_ENABLE);
-
-	I915_WRITE(FDI_RX_MISC(pipe),
-		   FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90);
-
-	reg = FDI_RX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_AUTO;
-	temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
-	temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
-	temp |= FDI_COMPOSITE_SYNC;
-	I915_WRITE(reg, temp | FDI_RX_ENABLE);
+	/* Try each vswing and preemphasis setting twice before moving on */
+	for (j = 0; j < ARRAY_SIZE(snb_b_fdi_train_param) * 2; j++) {
+		/* disable first in case we need to retry */
+		reg = FDI_TX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~(FDI_LINK_TRAIN_AUTO | FDI_LINK_TRAIN_NONE_IVB);
+		temp &= ~FDI_TX_ENABLE;
+		I915_WRITE(reg, temp);
 
-	POSTING_READ(reg);
-	udelay(150);
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~FDI_LINK_TRAIN_AUTO;
+		temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+		temp &= ~FDI_RX_ENABLE;
+		I915_WRITE(reg, temp);
 
-	for (i = 0; i < 4; i++) {
+		/* enable CPU FDI TX and PCH FDI RX */
 		reg = FDI_TX_CTL(pipe);
 		temp = I915_READ(reg);
+		temp &= ~FDI_DP_PORT_WIDTH_MASK;
+		temp |= FDI_DP_PORT_WIDTH(intel_crtc->config.fdi_lanes);
+		temp |= FDI_LINK_TRAIN_PATTERN_1_IVB;
 		temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-		temp |= snb_b_fdi_train_param[i];
-		I915_WRITE(reg, temp);
+		temp |= snb_b_fdi_train_param[j/2];
+		temp |= FDI_COMPOSITE_SYNC;
+		I915_WRITE(reg, temp | FDI_TX_ENABLE);
 
-		POSTING_READ(reg);
-		udelay(500);
+		I915_WRITE(FDI_RX_MISC(pipe),
+			   FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90);
 
-		reg = FDI_RX_IIR(pipe);
+		reg = FDI_RX_CTL(pipe);
 		temp = I915_READ(reg);
-		DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
-
-		if (temp & FDI_RX_BIT_LOCK ||
-		    (I915_READ(reg) & FDI_RX_BIT_LOCK)) {
-			I915_WRITE(reg, temp | FDI_RX_BIT_LOCK);
-			DRM_DEBUG_KMS("FDI train 1 done, level %i.\n", i);
-			break;
-		}
-	}
-	if (i == 4)
-		DRM_ERROR("FDI train 1 fail!\n");
+		temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+		temp |= FDI_COMPOSITE_SYNC;
+		I915_WRITE(reg, temp | FDI_RX_ENABLE);
 
-	/* Train 2 */
-	reg = FDI_TX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_NONE_IVB;
-	temp |= FDI_LINK_TRAIN_PATTERN_2_IVB;
-	temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-	temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B;
-	I915_WRITE(reg, temp);
+		POSTING_READ(reg);
+		udelay(1); /* should be 0.5us */
 
-	reg = FDI_RX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
-	temp |= FDI_LINK_TRAIN_PATTERN_2_CPT;
-	I915_WRITE(reg, temp);
+		for (i = 0; i < 4; i++) {
+			reg = FDI_RX_IIR(pipe);
+			temp = I915_READ(reg);
+			DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
 
-	POSTING_READ(reg);
-	udelay(150);
+			if (temp & FDI_RX_BIT_LOCK ||
+			    (I915_READ(reg) & FDI_RX_BIT_LOCK)) {
+				I915_WRITE(reg, temp | FDI_RX_BIT_LOCK);
+				DRM_DEBUG_KMS("FDI train 1 done, level %i.\n",
+					      i);
+				break;
+			}
+			udelay(1); /* should be 0.5us */
+		}
+		if (i == 4) {
+			DRM_DEBUG_KMS("FDI train 1 fail on vswing %d\n", j / 2);
+			continue;
+		}
 
-	for (i = 0; i < 4; i++) {
+		/* Train 2 */
 		reg = FDI_TX_CTL(pipe);
 		temp = I915_READ(reg);
-		temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-		temp |= snb_b_fdi_train_param[i];
+		temp &= ~FDI_LINK_TRAIN_NONE_IVB;
+		temp |= FDI_LINK_TRAIN_PATTERN_2_IVB;
+		I915_WRITE(reg, temp);
+
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+		temp |= FDI_LINK_TRAIN_PATTERN_2_CPT;
 		I915_WRITE(reg, temp);
 
 		POSTING_READ(reg);
-		udelay(500);
+		udelay(2); /* should be 1.5us */
 
-		reg = FDI_RX_IIR(pipe);
-		temp = I915_READ(reg);
-		DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
+		for (i = 0; i < 4; i++) {
+			reg = FDI_RX_IIR(pipe);
+			temp = I915_READ(reg);
+			DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
 
-		if (temp & FDI_RX_SYMBOL_LOCK) {
-			I915_WRITE(reg, temp | FDI_RX_SYMBOL_LOCK);
-			DRM_DEBUG_KMS("FDI train 2 done, level %i.\n", i);
-			break;
+			if (temp & FDI_RX_SYMBOL_LOCK ||
+			    (I915_READ(reg) & FDI_RX_SYMBOL_LOCK)) {
+				I915_WRITE(reg, temp | FDI_RX_SYMBOL_LOCK);
+				DRM_DEBUG_KMS("FDI train 2 done, level %i.\n",
+					      i);
+				goto train_done;
+			}
+			udelay(2); /* should be 1.5us */
 		}
+		if (i == 4)
+			DRM_DEBUG_KMS("FDI train 2 fail on vswing %d\n", j / 2);
 	}
-	if (i == 4)
-		DRM_ERROR("FDI train 2 fail!\n");
 
+train_done:
 	DRM_DEBUG_KMS("FDI train done.\n");
 }
 
@@ -4423,13 +4424,10 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	int pipe = crtc->pipe;
 	u32 dpll, mdiv;
 	u32 bestn, bestm1, bestm2, bestp1, bestp2;
-	bool is_hdmi;
 	u32 coreclk, reg_val, dpll_md;
 
 	mutex_lock(&dev_priv->dpio_lock);
 
-	is_hdmi = intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI);
-
 	bestn = crtc->config.dpll.n;
 	bestm1 = crtc->config.dpll.m1;
 	bestm2 = crtc->config.dpll.m2;
@@ -5934,11 +5932,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 	struct intel_ddi_plls *plls = &dev_priv->ddi_plls;
 	struct intel_crtc *crtc;
 	unsigned long irqflags;
-	uint32_t val, pch_hpd_mask;
-
-	pch_hpd_mask = SDE_PORTB_HOTPLUG_CPT | SDE_PORTC_HOTPLUG_CPT;
-	if (!(dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE))
-		pch_hpd_mask |= SDE_PORTD_HOTPLUG_CPT | SDE_CRT_HOTPLUG_CPT;
+	uint32_t val;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
 		WARN(crtc->base.enabled, "CRTC for pipe %c enabled\n",
@@ -5964,7 +5958,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 	WARN((val & ~DE_PCH_EVENT_IVB) != val,
 	     "Unexpected DEIMR bits enabled: 0x%x\n", val);
 	val = I915_READ(SDEIMR);
-	WARN((val & ~pch_hpd_mask) != val,
+	WARN((val | SDE_HOTPLUG_MASK_CPT) != 0xffffffff,
 	     "Unexpected SDEIMR bits enabled: 0x%x\n", val);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
@@ -6035,16 +6029,21 @@ void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 		    LCPLL_POWER_DOWN_ALLOW)) == LCPLL_PLL_LOCK)
 		return;
 
+	/* Make sure we're not on PC8 state before disabling PC8, otherwise
+	 * we'll hang the machine! */
+	dev_priv->uncore.funcs.force_wake_get(dev_priv);
+
 	if (val & LCPLL_POWER_DOWN_ALLOW) {
 		val &= ~LCPLL_POWER_DOWN_ALLOW;
 		I915_WRITE(LCPLL_CTL, val);
+		POSTING_READ(LCPLL_CTL);
 	}
 
 	val = I915_READ(D_COMP);
 	val |= D_COMP_COMP_FORCE;
 	val &= ~D_COMP_COMP_DISABLE;
 	I915_WRITE(D_COMP, val);
-	I915_READ(D_COMP);
+	POSTING_READ(D_COMP);
 
 	val = I915_READ(LCPLL_CTL);
 	val &= ~LCPLL_PLL_DISABLE;
@@ -6062,6 +6061,168 @@ void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 					LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
 			DRM_ERROR("Switching back to LCPLL failed\n");
 	}
+
+	dev_priv->uncore.funcs.force_wake_put(dev_priv);
+}
+
+void hsw_enable_pc8_work(struct work_struct *__work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(to_delayed_work(__work), struct drm_i915_private,
+			     pc8.enable_work);
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	if (dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Enabling package C8+\n");
+
+	dev_priv->pc8.enabled = true;
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	lpt_disable_clkout_dp(dev);
+	hsw_pc8_disable_interrupts(dev);
+	hsw_disable_lcpll(dev_priv, true, true);
+}
+
+static void __hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 1,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count--;
+	if (dev_priv->pc8.disable_count != 0)
+		return;
+
+	schedule_delayed_work(&dev_priv->pc8.enable_work,
+			      msecs_to_jiffies(i915_pc8_timeout));
+}
+
+static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 0,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count++;
+	if (dev_priv->pc8.disable_count != 1)
+		return;
+
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+	if (!dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Disabling package C8+\n");
+
+	hsw_restore_lcpll(dev_priv);
+	hsw_pc8_restore_interrupts(dev);
+	lpt_init_pch_refclk(dev);
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val |= PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	intel_prepare_ddi(dev);
+	i915_gem_init_swizzling(dev);
+	mutex_lock(&dev_priv->rps.hw_lock);
+	gen6_update_ring_freq(dev);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	dev_priv->pc8.enabled = false;
+}
+
+void hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_enable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+void hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_disable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static bool hsw_can_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_crtc *crtc;
+	uint32_t val;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
+		if (crtc->base.enabled)
+			return false;
+
+	/* This case is still possible since we have the i915.disable_power_well
+	 * parameter and also the KVMr or something else might be requesting the
+	 * power well. */
+	val = I915_READ(HSW_PWR_WELL_DRIVER);
+	if (val != 0) {
+		DRM_DEBUG_KMS("Not enabling PC8: power well on\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Since we're called from modeset_global_resources there's no way to
+ * symmetrically increase and decrease the refcount, so we use
+ * dev_priv->pc8.requirements_met to track whether we already have the refcount
+ * or not.
+ */
+static void hsw_update_package_c8(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool allow;
+
+	if (!i915_enable_pc8)
+		return;
+
+	mutex_lock(&dev_priv->pc8.lock);
+
+	allow = hsw_can_enable_package_c8(dev_priv);
+
+	if (allow == dev_priv->pc8.requirements_met)
+		goto done;
+
+	dev_priv->pc8.requirements_met = allow;
+
+	if (allow)
+		__hsw_enable_package_c8(dev_priv);
+	else
+		__hsw_disable_package_c8(dev_priv);
+
+done:
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = true;
+		hsw_enable_package_c8(dev_priv);
+	}
+}
+
+static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
+{
+	if (dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = false;
+		hsw_disable_package_c8(dev_priv);
+	}
 }
 
 static void haswell_modeset_global_resources(struct drm_device *dev)
@@ -6079,6 +6240,8 @@ static void haswell_modeset_global_resources(struct drm_device *dev)
 	}
 
 	intel_set_power_well(dev, enable);
+
+	hsw_update_package_c8(dev);
 }
 
 static int haswell_crtc_mode_set(struct drm_crtc *crtc,
@@ -6759,7 +6922,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			if (intel_crtc->cursor_bo != obj)
 				i915_gem_detach_phys_object(dev, intel_crtc->cursor_bo);
 		} else
-			i915_gem_object_unpin(intel_crtc->cursor_bo);
+			i915_gem_object_unpin_from_display_plane(intel_crtc->cursor_bo);
 		drm_gem_object_unreference(&intel_crtc->cursor_bo->base);
 	}
 
@@ -6774,7 +6937,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 
 	return 0;
 fail_unpin:
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 fail_locked:
 	mutex_unlock(&dev->struct_mutex);
 fail:
@@ -7310,13 +7473,19 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc)
 
 void intel_mark_busy(struct drm_device *dev)
 {
-	i915_update_gfx_val(dev->dev_private);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	hsw_package_c8_gpu_busy(dev_priv);
+	i915_update_gfx_val(dev_priv);
 }
 
 void intel_mark_idle(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 
+	hsw_package_c8_gpu_idle(dev_priv);
+
 	if (!i915_powersave)
 		return;
 
@@ -8891,6 +9060,9 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set,
 		drm_mode_debug_printmodeline(set->mode);
 		config->mode_changed = true;
 	}
+
+	DRM_DEBUG_KMS("computed changes for [CRTC:%d], mode_changed=%d, fb_changed=%d\n",
+			set->crtc->base.id, config->mode_changed, config->fb_changed);
 }
 
 static int
@@ -8901,14 +9073,13 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	struct drm_crtc *new_crtc;
 	struct intel_connector *connector;
 	struct intel_encoder *encoder;
-	int count, ro;
+	int ro;
 
 	/* The upper layers ensure that we either disable a crtc or have a list
 	 * of connectors. For paranoia, double-check this. */
 	WARN_ON(!set->fb && (set->num_connectors != 0));
 	WARN_ON(set->fb && (set->num_connectors == 0));
 
-	count = 0;
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    base.head) {
 		/* Otherwise traverse passed in connector list and get encoders
@@ -8942,7 +9113,6 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	/* connector->new_encoder is now updated for all connectors. */
 
 	/* Update crtc of enabled connectors. */
-	count = 0;
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    base.head) {
 		if (!connector->new_encoder)
@@ -10114,6 +10284,17 @@ void i915_redisable_vga(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 vga_reg = i915_vgacntrl_reg(dev);
 
+	/* This function can be called both from intel_modeset_setup_hw_state or
+	 * at a very early point in our resume sequence, where the power well
+	 * structures are not yet restored. Since this function is at a very
+	 * paranoid "someone might have enabled VGA while we were not looking"
+	 * level, just check if the power well is enabled instead of trying to
+	 * follow the "don't touch the power well if we don't need it" policy
+	 * the rest of the driver uses. */
+	if (HAS_POWER_WELL(dev) &&
+	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
+		return;
+
 	if (I915_READ(vga_reg) != VGA_DISP_DISABLE) {
 		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
 		i915_disable_vga(dev);
@@ -10302,7 +10483,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-	struct intel_crtc *intel_crtc;
 
 	/*
 	 * Interrupts and polling as the first thing to avoid creating havoc.
@@ -10326,7 +10506,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 		if (!crtc->fb)
 			continue;
 
-		intel_crtc = to_intel_crtc(crtc);
 		intel_increase_pllclock(crtc);
 	}
 

drivers/gpu/drm/i915/intel_dp.c

@@ -344,6 +344,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	else
 		precharge = 5;
 
+	intel_aux_display_runtime_get(dev_priv);
+
 	/* Try to wait for any previous AUX channel activity */
 	for (try = 0; try < 3; try++) {
 		status = I915_READ_NOTRACE(ch_ctl);
@@ -434,6 +436,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	ret = recv_bytes;
 out:
 	pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
+	intel_aux_display_runtime_put(dev_priv);
 
 	return ret;
 }
@@ -2326,7 +2329,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	struct drm_device *dev = encoder->dev;
 	int i;
 	uint8_t voltage;
-	bool clock_recovery = false;
 	int voltage_tries, loop_tries;
 	uint32_t DP = intel_dp->DP;
 
@@ -2344,7 +2346,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	voltage = 0xff;
 	voltage_tries = 0;
 	loop_tries = 0;
-	clock_recovery = false;
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
 		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
@@ -2365,7 +2366,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 
 		if (drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			DRM_DEBUG_KMS("clock recovery OK\n");
-			clock_recovery = true;
 			break;
 		}
 

drivers/gpu/drm/i915/intel_drv.h

@@ -745,6 +745,7 @@ extern void intel_set_power_well(struct drm_device *dev, bool enable);
 extern void intel_enable_gt_powersave(struct drm_device *dev);
 extern void intel_disable_gt_powersave(struct drm_device *dev);
 extern void ironlake_teardown_rc6(struct drm_device *dev);
+void gen6_update_ring_freq(struct drm_device *dev);
 
 extern bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe);
@@ -778,5 +779,18 @@ extern void intel_edp_psr_update(struct drm_device *dev);
 extern void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
 			      bool switch_to_fclk, bool allow_power_down);
 extern void hsw_restore_lcpll(struct drm_i915_private *dev_priv);
+extern void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+extern void ilk_disable_gt_irq(struct drm_i915_private *dev_priv,
+			       uint32_t mask);
+extern void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+extern void snb_disable_pm_irq(struct drm_i915_private *dev_priv,
+			       uint32_t mask);
+extern void hsw_enable_pc8_work(struct work_struct *__work);
+extern void hsw_enable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_disable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_pc8_disable_interrupts(struct drm_device *dev);
+extern void hsw_pc8_restore_interrupts(struct drm_device *dev);
+extern void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
+extern void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 
 #endif /* __INTEL_DRV_H__ */

drivers/gpu/drm/i915/intel_hdmi.c

@@ -1273,7 +1273,6 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 {
 	struct intel_digital_port *intel_dig_port;
 	struct intel_encoder *intel_encoder;
-	struct drm_encoder *encoder;
 	struct intel_connector *intel_connector;
 
 	intel_dig_port = kzalloc(sizeof(struct intel_digital_port), GFP_KERNEL);
@@ -1287,7 +1286,6 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 	}
 
 	intel_encoder = &intel_dig_port->base;
-	encoder = &intel_encoder->base;
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_hdmi_enc_funcs,
 			 DRM_MODE_ENCODER_TMDS);

drivers/gpu/drm/i915/intel_i2c.c

@@ -398,6 +398,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 	int i, reg_offset;
 	int ret = 0;
 
+	intel_aux_display_runtime_get(dev_priv);
 	mutex_lock(&dev_priv->gmbus_mutex);
 
 	if (bus->force_bit) {
@@ -497,6 +498,7 @@ timeout:
 
 out:
 	mutex_unlock(&dev_priv->gmbus_mutex);
+	intel_aux_display_runtime_put(dev_priv);
 	return ret;
 }
 

drivers/gpu/drm/i915/intel_pm.c

@@ -3450,11 +3450,11 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	WARN_ON(dev_priv->rps.pm_iir);
-	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
-	/* unmask all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	/* only unmask PM interrupts we need. Mask all others. */
+	I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS);
 }
 
 static void gen6_enable_rps(struct drm_device *dev)
@@ -3508,7 +3508,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
-	I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
+	if (INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev))
+		I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
+	else
+		I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
 	I915_WRITE(GEN6_RC6p_THRESHOLD, 150000);
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
@@ -3604,7 +3607,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_put(dev_priv);
 }
 
-static void gen6_update_ring_freq(struct drm_device *dev)
+void gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
@@ -4861,10 +4864,6 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		   ILK_DPARBUNIT_CLOCK_GATE_ENABLE  |
 		   ILK_DPFDUNIT_CLOCK_GATE_ENABLE);
 
-	/* WaMbcDriverBootEnable:snb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	g4x_disable_trickle_feed(dev);
 
 	/* The default value should be 0x200 according to docs, but the two
@@ -4960,10 +4959,6 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
 
-	/* WaMbcDriverBootEnable:hsw */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -5047,10 +5042,6 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 
 	g4x_disable_trickle_feed(dev);
 
-	/* WaMbcDriverBootEnable:ivb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaVSRefCountFullforceMissDisable:ivb */
 	gen7_setup_fixed_func_scheduler(dev_priv);
 
@@ -5110,11 +5101,6 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	/* WaMbcDriverBootEnable:vlv */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
-
 	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
 	 * gating disable must be set.  Failure to set it results in
 	 * flickering pixels due to Z write ordering failures after
@@ -5282,7 +5268,7 @@ bool intel_display_power_enabled(struct drm_device *dev,
 	case POWER_DOMAIN_TRANSCODER_B:
 	case POWER_DOMAIN_TRANSCODER_C:
 		return I915_READ(HSW_PWR_WELL_DRIVER) ==
-		       (HSW_PWR_WELL_ENABLE | HSW_PWR_WELL_STATE);
+		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
 	default:
 		BUG();
 	}
@@ -5295,17 +5281,18 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 	uint32_t tmp;
 
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
-	is_enabled = tmp & HSW_PWR_WELL_STATE;
-	enable_requested = tmp & HSW_PWR_WELL_ENABLE;
+	is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED;
+	enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST;
 
 	if (enable) {
 		if (!enable_requested)
-			I915_WRITE(HSW_PWR_WELL_DRIVER, HSW_PWR_WELL_ENABLE);
+			I915_WRITE(HSW_PWR_WELL_DRIVER,
+				   HSW_PWR_WELL_ENABLE_REQUEST);
 
 		if (!is_enabled) {
 			DRM_DEBUG_KMS("Enabling power well\n");
 			if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) &
-				      HSW_PWR_WELL_STATE), 20))
+				      HSW_PWR_WELL_STATE_ENABLED), 20))
 				DRM_ERROR("Timeout enabling power well\n");
 		}
 	} else {
@@ -5407,10 +5394,21 @@ void intel_init_power_well(struct drm_device *dev)
 
 	/* We're taking over the BIOS, so clear any requests made by it since
 	 * the driver is in charge now. */
-	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE)
+	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST)
 		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
 }
 
+/* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */
+void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
+{
+	hsw_disable_package_c8(dev_priv);
+}
+
+void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
+{
+	hsw_enable_package_c8(dev_priv);
+}
+
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -836,11 +836,8 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount++ == 0) {
-		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
-	}
+	if (ring->irq_refcount++ == 0)
+		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
@@ -854,11 +851,8 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount == 0) {
-		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
-	}
+	if (--ring->irq_refcount == 0)
+		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
@@ -1028,9 +1022,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
-		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
+		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1051,9 +1043,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 		else
 			I915_WRITE_IMR(ring, ~0);
-		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
+		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1072,10 +1062,8 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
-		I915_WRITE(GEN6_PMIMR, pm_imr & ~ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_enable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1094,10 +1082,8 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~0);
-		I915_WRITE(GEN6_PMIMR, pm_imr | ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_disable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
@@ -1594,6 +1580,8 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 	if (INTEL_INFO(ring->dev)->gen >= 6) {
 		I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
 		I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
+		if (HAS_VEBOX(ring->dev))
+			I915_WRITE(RING_SYNC_2(ring->mmio_base), 0);
 	}
 
 	ring->set_seqno(ring, seqno);

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -33,11 +33,12 @@ struct  intel_hw_status_page {
 #define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
 #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 
-#define I915_READ_NOPID(ring) I915_READ(RING_NOPID((ring)->mmio_base))
-#define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
-#define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
-
-enum intel_ring_hangcheck_action { wait, active, kick, hung };
+enum intel_ring_hangcheck_action {
+	HANGCHECK_WAIT,
+	HANGCHECK_ACTIVE,
+	HANGCHECK_KICK,
+	HANGCHECK_HUNG,
+};
 
 struct intel_ring_hangcheck {
 	bool deadlock;

drivers/gpu/drm/i915/intel_sdvo.c

@@ -538,7 +538,8 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo,
 				  &status))
 		goto log_fail;
 
-	while (status == SDVO_CMD_STATUS_PENDING && --retry) {
+	while ((status == SDVO_CMD_STATUS_PENDING ||
+			status == SDVO_CMD_STATUS_TARGET_NOT_SPECIFIED) && --retry) {
 		if (retry < 10)
 			msleep(15);
 		else

include/uapi/drm/i915_drm.h

@@ -334,6 +334,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_PINNED_BATCHES	 24
 #define I915_PARAM_HAS_EXEC_NO_RELOC	 25
 #define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
+#define I915_PARAM_HAS_WT     	 	 27
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -768,8 +769,32 @@ struct drm_i915_gem_busy {
 	__u32 busy;
 };
 
+/**
+ * I915_CACHING_NONE
+ *
+ * GPU access is not coherent with cpu caches. Default for machines without an
+ * LLC.
+ */
 #define I915_CACHING_NONE		0
+/**
+ * I915_CACHING_CACHED
+ *
+ * GPU access is coherent with cpu caches and furthermore the data is cached in
+ * last-level caches shared between cpu cores and the gpu GT. Default on
+ * machines with HAS_LLC.
+ */
 #define I915_CACHING_CACHED		1
+/**
+ * I915_CACHING_DISPLAY
+ *
+ * Special GPU caching mode which is coherent with the scanout engines.
+ * Transparently falls back to I915_CACHING_NONE on platforms where no special
+ * cache mode (like write-through or gfdt flushing) is available. The kernel
+ * automatically sets this mode when using a buffer as a scanout target.
+ * Userspace can manually set this mode to avoid a costly stall and clflush in
+ * the hotpath of drawing the first frame.
+ */
+#define I915_CACHING_DISPLAY		2
 
 struct drm_i915_gem_caching {
 	/**