Merge tag 'drm-intel-next-2014-06-20' of git://anongit.freedesktop.org/drm-intel into drm-next

- Accurate frontbuffer tracking and frontbuffer rendering invalidate, flush and
  flip events. This is prep work for proper PSR support and should also be
  useful for DRRS&fbc.
- Runtime suspend hardware on system suspend to support the new SOix sleep
  states, from Jesse.
- PSR updates for broadwell (Rodrigo)
- Universal plane support for cursors (Matt Roper), including core drm patches.
- Prefault gtt mappings (Chris)
- baytrail write-enable pte bit support (Akash Goel)
- mmio based flips (Sourab Gupta) instead of blitter ring flips
- interrupt handling race fixes (Oscar Mateo)

And old, not yet merged features from the previous round:
- rps/turbo support for chv (Deepak)
- some other straggling chv patches (Ville)
- proper universal plane conversion for the primary plane (Matt Roper)
- ppgtt on vlv from Jesse
- pile of cleanups, little fixes for insane corner cases and improved debug
  support all over

* tag 'drm-intel-next-2014-06-20' of git://anongit.freedesktop.org/drm-intel: (99 commits)
  drm/i915: Update DRIVER_DATE to 20140620
  drivers/i915: Fix unnoticed failure of init_ring_common()
  drm/i915: Track frontbuffer invalidation/flushing
  drm/i915: Use new frontbuffer bits to increase pll clock
  drm/i915: don't take runtime PM reference around freeze/thaw
  drm/i915: use runtime irq suspend/resume in freeze/thaw
  drm/i915: Properly track domain of the fbcon fb
  drm/i915: Print obj->frontbuffer_bits in debugfs output
  drm/i915: Introduce accurate frontbuffer tracking
  drm/i915: Drop schedule_back from psr_exit
  drm/i915: Ditch intel_edp_psr_update
  drm/i915: Drop unecessary complexity from psr_inactivate
  drm/i915: Remove ctx->last_ring
  drm/i915/chv: Ack interrupts before handling them (CHV)
  drm/i915/bdw: Ack interrupts before handling them (GEN8)
  drm/i915/vlv: Ack interrupts before handling them (VLV)
  drm/i915: Ack interrupts before handling them (GEN5 - GEN7)
  drm/i915: Don't BUG_ON in i915_gem_obj_offset
  drm/i915: Grab dev->struct_mutex in i915_gem_pageflip_info
  drm/i915: Add some L3 registers to the parser whitelist
  ...

Conflicts:
	drivers/gpu/drm/i915/i915_drv.c

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -426,6 +426,9 @@ static const u32 gen7_render_regs[] = {
 	GEN7_SO_WRITE_OFFSET(1),
 	GEN7_SO_WRITE_OFFSET(2),
 	GEN7_SO_WRITE_OFFSET(3),
+	GEN7_L3SQCREG1,
+	GEN7_L3CNTLREG2,
+	GEN7_L3CNTLREG3,
 };
 
 static const u32 gen7_blt_regs[] = {

drivers/gpu/drm/i915/i915_debugfs.c

@@ -170,6 +170,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	}
 	if (obj->ring != NULL)
 		seq_printf(m, " (%s)", obj->ring->name);
+	if (obj->frontbuffer_bits)
+		seq_printf(m, " (frontbuffer: 0x%03x)", obj->frontbuffer_bits);
 }
 
 static void describe_ctx(struct seq_file *m, struct intel_context *ctx)
@@ -515,6 +517,11 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	unsigned long flags;
 	struct intel_crtc *crtc;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for_each_intel_crtc(dev, crtc) {
 		const char pipe = pipe_name(crtc->pipe);
@@ -556,6 +563,8 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -1029,7 +1038,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   MEMSTAT_VID_SHIFT);
 		seq_printf(m, "Current P-state: %d\n",
 			   (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
-	} else if ((IS_GEN6(dev) || IS_GEN7(dev)) && !IS_VALLEYVIEW(dev)) {
+	} else if (IS_GEN6(dev) || (IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) ||
+		   IS_BROADWELL(dev)) {
 		u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 		u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS);
 		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
@@ -1048,7 +1058,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 
 		reqf = I915_READ(GEN6_RPNSWREQ);
 		reqf &= ~GEN6_TURBO_DISABLE;
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 			reqf >>= 24;
 		else
 			reqf >>= 25;
@@ -1065,7 +1075,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI);
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN);
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN);
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 			cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
 		else
 			cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
@@ -1677,9 +1687,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 
 #ifdef CONFIG_DRM_I915_FBDEV
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret = mutex_lock_interruptible(&dev->mode_config.mutex);
-	if (ret)
-		return ret;
 
 	ifbdev = dev_priv->fbdev;
 	fb = to_intel_framebuffer(ifbdev->helper.fb);
@@ -1692,7 +1699,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		   atomic_read(&fb->base.refcount.refcount));
 	describe_obj(m, fb->obj);
 	seq_putc(m, '\n');
-	mutex_unlock(&dev->mode_config.mutex);
 #endif
 
 	mutex_lock(&dev->mode_config.fb_lock);
@@ -1723,7 +1729,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	struct intel_context *ctx;
 	int ret, i;
 
-	ret = mutex_lock_interruptible(&dev->mode_config.mutex);
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
@@ -1753,7 +1759,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_putc(m, '\n');
 	}
 
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -1978,10 +1984,12 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 	seq_printf(m, "Sink_Support: %s\n", yesno(dev_priv->psr.sink_support));
 	seq_printf(m, "Source_OK: %s\n", yesno(dev_priv->psr.source_ok));
+	seq_printf(m, "Enabled: %s\n", yesno(dev_priv->psr.enabled));
+	seq_printf(m, "Active: %s\n", yesno(dev_priv->psr.active));
 
 	enabled = HAS_PSR(dev) &&
 		I915_READ(EDP_PSR_CTL(dev)) & EDP_PSR_ENABLE;
-	seq_printf(m, "Enabled: %s\n", yesno(enabled));
+	seq_printf(m, "HW Enabled & Active bit: %s\n", yesno(enabled));
 
 	if (HAS_PSR(dev))
 		psrperf = I915_READ(EDP_PSR_PERF_CNT(dev)) &
@@ -2223,9 +2231,12 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct intel_encoder *intel_encoder;
 
-	seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
-		   crtc->primary->fb->base.id, crtc->x, crtc->y,
-		   crtc->primary->fb->width, crtc->primary->fb->height);
+	if (crtc->primary->fb)
+		seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
+			   crtc->primary->fb->base.id, crtc->x, crtc->y,
+			   crtc->primary->fb->width, crtc->primary->fb->height);
+	else
+		seq_puts(m, "\tprimary plane disabled\n");
 	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
 		intel_encoder_info(m, intel_crtc, intel_encoder);
 }
@@ -2929,11 +2940,16 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	/* real source -> none transition */
 	if (source == INTEL_PIPE_CRC_SOURCE_NONE) {
 		struct intel_pipe_crc_entry *entries;
+		struct intel_crtc *crtc =
+			to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
 		DRM_DEBUG_DRIVER("stopping CRCs for pipe %c\n",
 				 pipe_name(pipe));
 
-		intel_wait_for_vblank(dev, pipe);
+		drm_modeset_lock(&crtc->base.mutex, NULL);
+		if (crtc->active)
+			intel_wait_for_vblank(dev, pipe);
+		drm_modeset_unlock(&crtc->base.mutex);
 
 		spin_lock_irq(&pipe_crc->lock);
 		entries = pipe_crc->entries;
@@ -3506,7 +3522,7 @@ i915_max_freq_get(void *data, u64 *val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3532,7 +3548,7 @@ i915_max_freq_set(void *data, u64 val)
 	u32 rp_state_cap, hw_max, hw_min;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3587,7 +3603,7 @@ i915_min_freq_get(void *data, u64 *val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3613,7 +3629,7 @@ i915_min_freq_set(void *data, u64 val)
 	u32 rp_state_cap, hw_max, hw_min;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);

drivers/gpu/drm/i915/i915_dma.c

@@ -138,7 +138,7 @@ static void i915_free_hws(struct drm_device *dev)
 	I915_WRITE(HWS_PGA, 0x1ffff000);
 }
 
-void i915_kernel_lost_context(struct drm_device * dev)
+void i915_kernel_lost_context(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv;
@@ -166,7 +166,7 @@ void i915_kernel_lost_context(struct drm_device * dev)
 		master_priv->sarea_priv->perf_boxes |= I915_BOX_RING_EMPTY;
 }
 
-static int i915_dma_cleanup(struct drm_device * dev)
+static int i915_dma_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
@@ -190,7 +190,7 @@ static int i915_dma_cleanup(struct drm_device * dev)
 	return 0;
 }
 
-static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
+static int i915_initialize(struct drm_device *dev, drm_i915_init_t *init)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -235,7 +235,7 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
 	return 0;
 }
 
-static int i915_dma_resume(struct drm_device * dev)
+static int i915_dma_resume(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring = LP_RING(dev_priv);
@@ -359,7 +359,7 @@ static int validate_cmd(int cmd)
 	return 0;
 }
 
-static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords)
+static int i915_emit_cmds(struct drm_device *dev, int *buffer, int dwords)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i, ret;
@@ -369,6 +369,7 @@ static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords)
 
 	for (i = 0; i < dwords;) {
 		int sz = validate_cmd(buffer[i]);
+
 		if (sz == 0 || i + sz > dwords)
 			return -EINVAL;
 		i += sz;
@@ -453,7 +454,7 @@ static void i915_emit_breadcrumb(struct drm_device *dev)
 	}
 }
 
-static int i915_dispatch_cmdbuffer(struct drm_device * dev,
+static int i915_dispatch_cmdbuffer(struct drm_device *dev,
 				   drm_i915_cmdbuffer_t *cmd,
 				   struct drm_clip_rect *cliprects,
 				   void *cmdbuf)
@@ -487,8 +488,8 @@ static int i915_dispatch_cmdbuffer(struct drm_device * dev,
 	return 0;
 }
 
-static int i915_dispatch_batchbuffer(struct drm_device * dev,
-				     drm_i915_batchbuffer_t * batch,
+static int i915_dispatch_batchbuffer(struct drm_device *dev,
+				     drm_i915_batchbuffer_t *batch,
 				     struct drm_clip_rect *cliprects)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -549,7 +550,7 @@ static int i915_dispatch_batchbuffer(struct drm_device * dev,
 	return 0;
 }
 
-static int i915_dispatch_flip(struct drm_device * dev)
+static int i915_dispatch_flip(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv =
@@ -755,7 +756,7 @@ static int i915_cmdbuffer(struct drm_device *dev, void *data,
 	return ret;
 }
 
-static int i915_emit_irq(struct drm_device * dev)
+static int i915_emit_irq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -781,7 +782,7 @@ static int i915_emit_irq(struct drm_device * dev)
 	return dev_priv->dri1.counter;
 }
 
-static int i915_wait_irq(struct drm_device * dev, int irq_nr)
+static int i915_wait_irq(struct drm_device *dev, int irq_nr)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -1266,6 +1267,7 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
 	if (state == VGA_SWITCHEROO_ON) {
 		pr_info("switched on\n");
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
@@ -1488,10 +1490,11 @@ static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 #define SEP_EMPTY
 #define PRINT_FLAG(name) info->name ? #name "," : ""
 #define SEP_COMMA ,
-	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x flags="
+	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x flags="
 			 DEV_INFO_FOR_EACH_FLAG(PRINT_S, SEP_EMPTY),
 			 info->gen,
 			 dev_priv->dev->pdev->device,
+			 dev_priv->dev->pdev->revision,
 			 DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_COMMA));
 #undef PRINT_S
 #undef SEP_EMPTY
@@ -1602,6 +1605,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->backlight_lock);
 	spin_lock_init(&dev_priv->uncore.lock);
 	spin_lock_init(&dev_priv->mm.object_stat_lock);
+	spin_lock_init(&dev_priv->mmio_flip_lock);
 	mutex_init(&dev_priv->dpio_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
@@ -1929,7 +1933,7 @@ int i915_driver_open(struct drm_device *dev, struct drm_file *file)
  * and DMA structures, since the kernel won't be using them, and clea
  * up any GEM state.
  */
-void i915_driver_lastclose(struct drm_device * dev)
+void i915_driver_lastclose(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1950,7 +1954,7 @@ void i915_driver_lastclose(struct drm_device * dev)
 	i915_dma_cleanup(dev);
 }
 
-void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
+void i915_driver_preclose(struct drm_device *dev, struct drm_file *file_priv)
 {
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_close(dev, file_priv);
@@ -2027,7 +2031,7 @@ int i915_max_ioctl = ARRAY_SIZE(i915_ioctls);
  * manage the gtt, we need to claim that all intel devices are agp.  For
  * otherwise the drm core refuses to initialize the agp support code.
  */
-int i915_driver_device_is_agp(struct drm_device * dev)
+int i915_driver_device_is_agp(struct drm_device *dev)
 {
 	return 1;
 }

drivers/gpu/drm/i915/i915_drv.c

@@ -28,6 +28,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/acpi.h>
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -46,8 +47,6 @@ static struct drm_driver driver;
 			  PIPE_C_OFFSET, PIPE_EDP_OFFSET }, \
 	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
 			   TRANSCODER_C_OFFSET, TRANSCODER_EDP_OFFSET }, \
-	.dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET }, \
-	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET }, \
 	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET }
 
 #define GEN_CHV_PIPEOFFSETS \
@@ -55,10 +54,6 @@ static struct drm_driver driver;
 			  CHV_PIPE_C_OFFSET }, \
 	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
 			   CHV_TRANSCODER_C_OFFSET, }, \
-	.dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET, \
-			  CHV_DPLL_C_OFFSET }, \
-	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET, \
-			     CHV_DPLL_C_MD_OFFSET }, \
 	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \
 			     CHV_PALETTE_C_OFFSET }
 
@@ -499,8 +494,7 @@ static int i915_drm_freeze(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-
-	intel_runtime_pm_get(dev_priv);
+	pci_power_t opregion_target_state;
 
 	/* ignore lid events during suspend */
 	mutex_lock(&dev_priv->modeset_restore_lock);
@@ -526,9 +520,9 @@ static int i915_drm_freeze(struct drm_device *dev)
 			return error;
 		}
 
-		drm_irq_uninstall(dev);
+		intel_runtime_pm_disable_interrupts(dev);
 
-		intel_disable_gt_powersave(dev);
+		intel_suspend_gt_powersave(dev);
 
 		/*
 		 * Disable CRTCs directly since we want to preserve sw state
@@ -547,8 +541,14 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	i915_save_state(dev);
 
+	if (acpi_target_system_state() >= ACPI_STATE_S3)
+		opregion_target_state = PCI_D3cold;
+	else
+		opregion_target_state = PCI_D1;
+	intel_opregion_notify_adapter(dev, opregion_target_state);
+
+	intel_uncore_forcewake_reset(dev, false);
 	intel_opregion_fini(dev);
-	intel_uncore_fini(dev);
 
 	console_lock();
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
@@ -556,6 +556,8 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	dev_priv->suspend_count++;
 
+	intel_display_set_init_power(dev_priv, false);
+
 	return 0;
 }
 
@@ -605,7 +607,10 @@ static int i915_drm_thaw_early(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	intel_uncore_early_sanitize(dev);
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		hsw_disable_pc8(dev_priv);
+
+	intel_uncore_early_sanitize(dev, true);
 	intel_uncore_sanitize(dev);
 	intel_power_domains_init_hw(dev_priv);
 
@@ -638,8 +643,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		}
 		mutex_unlock(&dev->struct_mutex);
 
-		/* We need working interrupts for modeset enabling ... */
-		drm_irq_install(dev, dev->pdev->irq);
+		intel_runtime_pm_restore_interrupts(dev);
 
 		intel_modeset_init_hw(dev);
 
@@ -676,7 +680,8 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_opregion_notify_adapter(dev, PCI_D0);
+
 	return 0;
 }
 
@@ -885,6 +890,7 @@ static int i915_pm_suspend_late(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 
 	/*
 	 * We have a suspedn ordering issue with the snd-hda driver also
@@ -898,6 +904,9 @@ static int i915_pm_suspend_late(struct device *dev)
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	if (IS_HASWELL(drm_dev) || IS_BROADWELL(drm_dev))
+		hsw_enable_pc8(dev_priv);
+
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -53,7 +53,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20080730"
+#define DRIVER_DATE		"20140620"
 
 enum pipe {
 	INVALID_PIPE = -1,
@@ -552,8 +552,6 @@ struct intel_device_info {
 	/* Register offsets for the various display pipes and transcoders */
 	int pipe_offsets[I915_MAX_TRANSCODERS];
 	int trans_offsets[I915_MAX_TRANSCODERS];
-	int dpll_offsets[I915_MAX_PIPES];
-	int dpll_md_offsets[I915_MAX_PIPES];
 	int palette_offsets[I915_MAX_PIPES];
 	int cursor_offsets[I915_MAX_PIPES];
 };
@@ -593,7 +591,6 @@ struct intel_context {
 	bool is_initialized;
 	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
-	struct intel_engine_cs *last_ring;
 	struct drm_i915_gem_object *obj;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_address_space *vm;
@@ -638,6 +635,10 @@ struct i915_drrs {
 struct i915_psr {
 	bool sink_support;
 	bool source_ok;
+	bool setup_done;
+	bool enabled;
+	bool active;
+	struct delayed_work work;
 };
 
 enum intel_pch {
@@ -1331,6 +1332,17 @@ struct intel_pipe_crc {
 	wait_queue_head_t wq;
 };
 
+struct i915_frontbuffer_tracking {
+	struct mutex lock;
+
+	/*
+	 * Tracking bits for delayed frontbuffer flushing du to gpu activity or
+	 * scheduled flips.
+	 */
+	unsigned busy_bits;
+	unsigned flip_bits;
+};
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1370,6 +1382,9 @@ struct drm_i915_private {
 	/* protects the irq masks */
 	spinlock_t irq_lock;
 
+	/* protects the mmio flip data */
+	spinlock_t mmio_flip_lock;
+
 	bool display_irqs_enabled;
 
 	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
@@ -1473,6 +1488,9 @@ struct drm_i915_private {
 	bool lvds_downclock_avail;
 	/* indicates the reduced downclock for LVDS*/
 	int lvds_downclock;
+
+	struct i915_frontbuffer_tracking fb_tracking;
+
 	u16 orig_clock;
 
 	bool mchbar_need_disable;
@@ -1590,6 +1608,28 @@ struct drm_i915_gem_object_ops {
 	void (*release)(struct drm_i915_gem_object *);
 };
 
+/*
+ * Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is
+ * considered to be the frontbuffer for the given plane interface-vise. This
+ * doesn't mean that the hw necessarily already scans it out, but that any
+ * rendering (by the cpu or gpu) will land in the frontbuffer eventually.
+ *
+ * We have one bit per pipe and per scanout plane type.
+ */
+#define INTEL_FRONTBUFFER_BITS_PER_PIPE 4
+#define INTEL_FRONTBUFFER_BITS \
+	(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES)
+#define INTEL_FRONTBUFFER_PRIMARY(pipe) \
+	(1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
+#define INTEL_FRONTBUFFER_CURSOR(pipe) \
+	(1 << (1 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_SPRITE(pipe) \
+	(1 << (2 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_OVERLAY(pipe) \
+	(1 << (3 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_ALL_MASK(pipe) \
+	(0xf << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
+
 struct drm_i915_gem_object {
 	struct drm_gem_object base;
 
@@ -1659,6 +1699,12 @@ struct drm_i915_gem_object {
 	unsigned int pin_mappable:1;
 	unsigned int pin_display:1;
 
+	/*
+	 * Is the object to be mapped as read-only to the GPU
+	 * Only honoured if hardware has relevant pte bit
+	 */
+	unsigned long gt_ro:1;
+
 	/*
 	 * Is the GPU currently using a fence to access this buffer,
 	 */
@@ -1671,6 +1717,8 @@ struct drm_i915_gem_object {
 	unsigned int has_global_gtt_mapping:1;
 	unsigned int has_dma_mapping:1;
 
+	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
+
 	struct sg_table *pages;
 	int pages_pin_count;
 
@@ -1717,6 +1765,10 @@ struct drm_i915_gem_object {
 };
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits);
+
 /**
  * Request queue structure.
  *
@@ -1938,10 +1990,8 @@ struct drm_i915_cmd_table {
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
-#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6 && \
-				 (!IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)))
-#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 \
-				 && !IS_GEN8(dev))
+#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6)
+#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 && !IS_GEN8(dev))
 #define USES_PPGTT(dev)		intel_enable_ppgtt(dev, false)
 #define USES_FULL_PPGTT(dev)	intel_enable_ppgtt(dev, true)
 
@@ -2038,6 +2088,7 @@ struct i915_params {
 	bool reset;
 	bool disable_display;
 	bool disable_vtd_wa;
+	int use_mmio_flip;
 };
 extern struct i915_params i915 __read_mostly;
 
@@ -2082,10 +2133,12 @@ extern void intel_irq_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
 
 extern void intel_uncore_sanitize(struct drm_device *dev);
-extern void intel_uncore_early_sanitize(struct drm_device *dev);
+extern void intel_uncore_early_sanitize(struct drm_device *dev,
+					bool restore_forcewake);
 extern void intel_uncore_init(struct drm_device *dev);
 extern void intel_uncore_check_errors(struct drm_device *dev);
 extern void intel_uncore_fini(struct drm_device *dev);
+extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore);
 
 void
 i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
@@ -2233,6 +2286,8 @@ bool i915_gem_retire_requests(struct drm_device *dev);
 void i915_gem_retire_requests_ring(struct intel_engine_cs *ring);
 int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 				      bool interruptible);
+int __must_check i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno);
+
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
 {
 	return unlikely(atomic_read(&error->reset_counter)
@@ -2443,7 +2498,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 					       u32 stolen_offset,
 					       u32 gtt_offset,
 					       u32 size);
-void i915_gem_object_release_stolen(struct drm_i915_gem_object *obj);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
@@ -2603,6 +2657,8 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 
+void intel_notify_mmio_flip(struct intel_engine_cs *ring);
+
 /* overlay */
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
 extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,

drivers/gpu/drm/i915/i915_gem.c

@@ -1095,7 +1095,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
  * Compare seqno against outstanding lazy request. Emit a request if they are
  * equal.
  */
-static int
+int
 i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno)
 {
 	int ret;
@@ -1561,14 +1561,29 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret)
 		goto unpin;
 
-	obj->fault_mappable = true;
-
+	/* Finally, remap it using the new GTT offset */
 	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
 	pfn >>= PAGE_SHIFT;
-	pfn += page_offset;
 
-	/* Finally, remap it using the new GTT offset */
-	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	if (!obj->fault_mappable) {
+		unsigned long size = min_t(unsigned long,
+					   vma->vm_end - vma->vm_start,
+					   obj->base.size);
+		int i;
+
+		for (i = 0; i < size >> PAGE_SHIFT; i++) {
+			ret = vm_insert_pfn(vma,
+					    (unsigned long)vma->vm_start + i * PAGE_SIZE,
+					    pfn + i);
+			if (ret)
+				break;
+		}
+
+		obj->fault_mappable = true;
+	} else
+		ret = vm_insert_pfn(vma,
+				    (unsigned long)vmf->virtual_address,
+				    pfn + page_offset);
 unpin:
 	i915_gem_object_ggtt_unpin(obj);
 unlock:
@@ -1616,22 +1631,6 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
-{
-	struct i915_vma *vma;
-
-	/*
-	 * Only the global gtt is relevant for gtt memory mappings, so restrict
-	 * list traversal to objects bound into the global address space. Note
-	 * that the active list should be empty, but better safe than sorry.
-	 */
-	WARN_ON(!list_empty(&dev_priv->gtt.base.active_list));
-	list_for_each_entry(vma, &dev_priv->gtt.base.active_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-	list_for_each_entry(vma, &dev_priv->gtt.base.inactive_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-}
-
 /**
  * i915_gem_release_mmap - remove physical page mappings
  * @obj: obj in question
@@ -1657,6 +1656,15 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	obj->fault_mappable = false;
 }
 
+void
+i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
+{
+	struct drm_i915_gem_object *obj;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
+		i915_gem_release_mmap(obj);
+}
+
 uint32_t
 i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 {
@@ -2211,6 +2219,8 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 			list_move_tail(&vma->mm_list, &vm->inactive_list);
 	}
 
+	intel_fb_obj_flush(obj, true);
+
 	list_del_init(&obj->ring_list);
 	obj->ring = NULL;
 
@@ -3540,6 +3550,8 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3561,6 +3573,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3614,6 +3628,9 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->dirty = 1;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -3950,6 +3967,9 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -4438,13 +4458,14 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->stolen)
 		i915_gem_object_unpin_pages(obj);
 
+	WARN_ON(obj->frontbuffer_bits);
+
 	if (WARN_ON(obj->pages_pin_count))
 		obj->pages_pin_count = 0;
 	if (discard_backing_storage(obj))
 		obj->madv = I915_MADV_DONTNEED;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
-	i915_gem_object_release_stolen(obj);
 
 	BUG_ON(obj->pages);
 
@@ -4922,6 +4943,8 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
 	register_oom_notifier(&dev_priv->mm.oom_notifier);
+
+	mutex_init(&dev_priv->fb_tracking.lock);
 }
 
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
@@ -4983,6 +5006,23 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file)
 	return ret;
 }
 
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits)
+{
+	if (old) {
+		WARN_ON(!mutex_is_locked(&old->base.dev->struct_mutex));
+		WARN_ON(!(old->frontbuffer_bits & frontbuffer_bits));
+		old->frontbuffer_bits &= ~frontbuffer_bits;
+	}
+
+	if (new) {
+		WARN_ON(!mutex_is_locked(&new->base.dev->struct_mutex));
+		WARN_ON(new->frontbuffer_bits & frontbuffer_bits);
+		new->frontbuffer_bits |= frontbuffer_bits;
+	}
+}
+
 static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 {
 	if (!mutex_is_locked(mutex))
@@ -5065,12 +5105,13 @@ unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
 	    vm == &dev_priv->mm.aliasing_ppgtt->base)
 		vm = &dev_priv->gtt.base;
 
-	BUG_ON(list_empty(&o->vma_list));
 	list_for_each_entry(vma, &o->vma_list, vma_link) {
 		if (vma->vm == vm)
 			return vma->node.start;
 
 	}
+	WARN(1, "%s vma for this object not found.\n",
+	     i915_is_ggtt(vm) ? "global" : "ppgtt");
 	return -1;
 }
 

drivers/gpu/drm/i915/i915_gem_context.c

@@ -606,7 +606,7 @@ static int do_switch(struct intel_engine_cs *ring,
 		BUG_ON(!i915_gem_obj_is_pinned(from->obj));
 	}
 
-	if (from == to && from->last_ring == ring && !to->remap_slice)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	/* Trying to pin first makes error handling easier. */
@@ -703,7 +703,6 @@ static int do_switch(struct intel_engine_cs *ring,
 done:
 	i915_gem_context_reference(to);
 	ring->last_context = to;
-	to->last_ring = ring;
 
 	if (uninitialized) {
 		ret = i915_gem_render_state_init(ring);

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -975,10 +975,8 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
 			obj->last_write_seqno = intel_ring_get_seqno(ring);
-			/* check for potential scanout */
-			if (i915_gem_obj_ggtt_bound(obj) &&
-			    i915_gem_obj_to_ggtt(obj)->pin_count)
-				intel_mark_fb_busy(obj, ring);
+
+			intel_fb_obj_invalidate(obj, ring);
 
 			/* update for the implicit flush after a batch */
 			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
@@ -1525,7 +1523,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
-		struct drm_i915_gem_exec_object2 *user_exec_list =
+		struct drm_i915_gem_exec_object2 __user *user_exec_list =
 				   to_user_ptr(args->buffers_ptr);
 		int i;
 

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -63,6 +63,12 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	}
 #endif
 
+	/* Early VLV doesn't have this */
+	if (IS_VALLEYVIEW(dev) && dev->pdev->revision < 0xb) {
+		DRM_DEBUG_DRIVER("disabling PPGTT on pre-B3 step VLV\n");
+		return 0;
+	}
+
 	return HAS_ALIASING_PPGTT(dev) ? 1 : 0;
 }
 
@@ -110,7 +116,7 @@ static inline gen8_ppgtt_pde_t gen8_pde_encode(struct drm_device *dev,
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -132,7 +138,7 @@ static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -156,7 +162,7 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 flags)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -164,7 +170,8 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 	/* Mark the page as writeable.  Other platforms don't have a
 	 * setting for read-only/writable, so this matches that behavior.
 	 */
-	pte |= BYT_PTE_WRITEABLE;
+	if (!(flags & PTE_READ_ONLY))
+		pte |= BYT_PTE_WRITEABLE;
 
 	if (level != I915_CACHE_NONE)
 		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
@@ -174,7 +181,7 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
@@ -187,7 +194,7 @@ static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 				      enum i915_cache_level level,
-				      bool valid)
+				      bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
@@ -301,7 +308,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
 				      uint64_t start,
-				      enum i915_cache_level cache_level)
+				      enum i915_cache_level cache_level, u32 unused)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
@@ -639,7 +646,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 	uint32_t pd_entry;
 	int pte, pde;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
 	pd_addr = (gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm +
 		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
@@ -941,7 +948,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
@@ -964,7 +971,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
 				      uint64_t start,
-				      enum i915_cache_level cache_level)
+				      enum i915_cache_level cache_level, u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
@@ -981,7 +988,8 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 		pt_vaddr[act_pte] =
 			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
-				       cache_level, true);
+				       cache_level, true, flags);
+
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
@@ -1218,8 +1226,12 @@ ppgtt_bind_vma(struct i915_vma *vma,
 	       enum i915_cache_level cache_level,
 	       u32 flags)
 {
+	/* Currently applicable only to VLV */
+	if (vma->obj->gt_ro)
+		flags |= PTE_READ_ONLY;
+
 	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
-				cache_level);
+				cache_level, flags);
 }
 
 static void ppgtt_unbind_vma(struct i915_vma *vma)
@@ -1394,7 +1406,7 @@ static inline void gen8_set_pte(void __iomem *addr, gen8_gtt_pte_t pte)
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level, u32 unused)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
@@ -1440,7 +1452,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level, u32 flags)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
@@ -1452,7 +1464,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(vm->pte_encode(addr, level, true), &gtt_entries[i]);
+		iowrite32(vm->pte_encode(addr, level, true, flags), &gtt_entries[i]);
 		i++;
 	}
 
@@ -1464,7 +1476,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 	if (i != 0)
 		WARN_ON(readl(&gtt_entries[i-1]) !=
-			vm->pte_encode(addr, level, true));
+			vm->pte_encode(addr, level, true, flags));
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -1518,7 +1530,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch, 0);
 
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
@@ -1567,6 +1579,10 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
 
+	/* Currently applicable only to VLV */
+	if (obj->gt_ro)
+		flags |= PTE_READ_ONLY;
+
 	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
 	 * or we have a global mapping already but the cacheability flags have
 	 * changed, set the global PTEs.
@@ -1583,7 +1599,7 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 		    (cache_level != obj->cache_level)) {
 			vma->vm->insert_entries(vma->vm, obj->pages,
 						vma->node.start,
-						cache_level);
+						cache_level, flags);
 			obj->has_global_gtt_mapping = 1;
 		}
 	}
@@ -1595,7 +1611,7 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 		appgtt->base.insert_entries(&appgtt->base,
 					    vma->obj->pages,
 					    vma->node.start,
-					    cache_level);
+					    cache_level, flags);
 		vma->obj->has_aliasing_ppgtt_mapping = 1;
 	}
 }

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -154,6 +154,7 @@ struct i915_vma {
 	void (*unbind_vma)(struct i915_vma *vma);
 	/* Map an object into an address space with the given cache flags. */
 #define GLOBAL_BIND (1<<0)
+#define PTE_READ_ONLY (1<<1)
 	void (*bind_vma)(struct i915_vma *vma,
 			 enum i915_cache_level cache_level,
 			 u32 flags);
@@ -197,7 +198,7 @@ struct i915_address_space {
 	/* FIXME: Need a more generic return type */
 	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid); /* Create a valid PTE */
+				     bool valid, u32 flags); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
 			    uint64_t start,
 			    uint64_t length,
@@ -205,7 +206,7 @@ struct i915_address_space {
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
 			       uint64_t start,
-			       enum i915_cache_level cache_level);
+			       enum i915_cache_level cache_level, u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
 };
 

drivers/gpu/drm/i915/i915_gem_render_state.c

@@ -28,64 +28,13 @@
 #include "i915_drv.h"
 #include "intel_renderstate.h"
 
-struct i915_render_state {
+struct render_state {
+	const struct intel_renderstate_rodata *rodata;
 	struct drm_i915_gem_object *obj;
-	unsigned long ggtt_offset;
-	void *batch;
-	u32 size;
-	u32 len;
+	u64 ggtt_offset;
+	int gen;
 };
 
-static struct i915_render_state *render_state_alloc(struct drm_device *dev)
-{
-	struct i915_render_state *so;
-	struct page *page;
-	int ret;
-
-	so = kzalloc(sizeof(*so), GFP_KERNEL);
-	if (!so)
-		return ERR_PTR(-ENOMEM);
-
-	so->obj = i915_gem_alloc_object(dev, 4096);
-	if (so->obj == NULL) {
-		ret = -ENOMEM;
-		goto free;
-	}
-	so->size = 4096;
-
-	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
-	if (ret)
-		goto free_gem;
-
-	BUG_ON(so->obj->pages->nents != 1);
-	page = sg_page(so->obj->pages->sgl);
-
-	so->batch = kmap(page);
-	if (!so->batch) {
-		ret = -ENOMEM;
-		goto unpin;
-	}
-
-	so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj);
-
-	return so;
-unpin:
-	i915_gem_object_ggtt_unpin(so->obj);
-free_gem:
-	drm_gem_object_unreference(&so->obj->base);
-free:
-	kfree(so);
-	return ERR_PTR(ret);
-}
-
-static void render_state_free(struct i915_render_state *so)
-{
-	kunmap(so->batch);
-	i915_gem_object_ggtt_unpin(so->obj);
-	drm_gem_object_unreference(&so->obj->base);
-	kfree(so);
-}
-
 static const struct intel_renderstate_rodata *
 render_state_get_rodata(struct drm_device *dev, const int gen)
 {
@@ -101,98 +50,120 @@ render_state_get_rodata(struct drm_device *dev, const int gen)
 	return NULL;
 }
 
-static int render_state_setup(const int gen,
-			      const struct intel_renderstate_rodata *rodata,
-			      struct i915_render_state *so)
+static int render_state_init(struct render_state *so, struct drm_device *dev)
 {
-	const u64 goffset = i915_gem_obj_ggtt_offset(so->obj);
-	u32 reloc_index = 0;
-	u32 * const d = so->batch;
-	unsigned int i = 0;
 	int ret;
 
-	if (!rodata || rodata->batch_items * 4 > so->size)
+	so->gen = INTEL_INFO(dev)->gen;
+	so->rodata = render_state_get_rodata(dev, so->gen);
+	if (so->rodata == NULL)
+		return 0;
+
+	if (so->rodata->batch_items * 4 > 4096)
 		return -EINVAL;
 
+	so->obj = i915_gem_alloc_object(dev, 4096);
+	if (so->obj == NULL)
+		return -ENOMEM;
+
+	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
+	if (ret)
+		goto free_gem;
+
+	so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj);
+	return 0;
+
+free_gem:
+	drm_gem_object_unreference(&so->obj->base);
+	return ret;
+}
+
+static int render_state_setup(struct render_state *so)
+{
+	const struct intel_renderstate_rodata *rodata = so->rodata;
+	unsigned int i = 0, reloc_index = 0;
+	struct page *page;
+	u32 *d;
+	int ret;
+
 	ret = i915_gem_object_set_to_cpu_domain(so->obj, true);
 	if (ret)
 		return ret;
 
+	page = sg_page(so->obj->pages->sgl);
+	d = kmap(page);
+
 	while (i < rodata->batch_items) {
 		u32 s = rodata->batch[i];
 
-		if (reloc_index < rodata->reloc_items &&
-		    i * 4  == rodata->reloc[reloc_index]) {
-
-			s += goffset & 0xffffffff;
-
-			/* We keep batch offsets max 32bit */
-			if (gen >= 8) {
+		if (i * 4  == rodata->reloc[reloc_index]) {
+			u64 r = s + so->ggtt_offset;
+			s = lower_32_bits(r);
+			if (so->gen >= 8) {
 				if (i + 1 >= rodata->batch_items ||
 				    rodata->batch[i + 1] != 0)
 					return -EINVAL;
 
-				d[i] = s;
-				i++;
-				s = (goffset & 0xffffffff00000000ull) >> 32;
+				d[i++] = s;
+				s = upper_32_bits(r);
 			}
 
 			reloc_index++;
 		}
 
-		d[i] = s;
-		i++;
+		d[i++] = s;
 	}
+	kunmap(page);
 
 	ret = i915_gem_object_set_to_gtt_domain(so->obj, false);
 	if (ret)
 		return ret;
 
-	if (rodata->reloc_items != reloc_index) {
-		DRM_ERROR("not all relocs resolved, %d out of %d\n",
-			  reloc_index, rodata->reloc_items);
+	if (rodata->reloc[reloc_index] != -1) {
+		DRM_ERROR("only %d relocs resolved\n", reloc_index);
 		return -EINVAL;
 	}
 
-	so->len = rodata->batch_items * 4;
-
 	return 0;
 }
 
+static void render_state_fini(struct render_state *so)
+{
+	i915_gem_object_ggtt_unpin(so->obj);
+	drm_gem_object_unreference(&so->obj->base);
+}
+
 int i915_gem_render_state_init(struct intel_engine_cs *ring)
 {
-	const int gen = INTEL_INFO(ring->dev)->gen;
-	struct i915_render_state *so;
-	const struct intel_renderstate_rodata *rodata;
+	struct render_state so;
 	int ret;
 
 	if (WARN_ON(ring->id != RCS))
 		return -ENOENT;
 
-	rodata = render_state_get_rodata(ring->dev, gen);
-	if (rodata == NULL)
-		return 0;
+	ret = render_state_init(&so, ring->dev);
+	if (ret)
+		return ret;
 
-	so = render_state_alloc(ring->dev);
-	if (IS_ERR(so))
-		return PTR_ERR(so);
+	if (so.rodata == NULL)
+		return 0;
 
-	ret = render_state_setup(gen, rodata, so);
+	ret = render_state_setup(&so);
 	if (ret)
 		goto out;
 
 	ret = ring->dispatch_execbuffer(ring,
-					i915_gem_obj_ggtt_offset(so->obj),
-					so->len,
+					so.ggtt_offset,
+					so.rodata->batch_items * 4,
 					I915_DISPATCH_SECURE);
 	if (ret)
 		goto out;
 
-	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so->obj), ring);
+	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
 
-	ret = __i915_add_request(ring, NULL, so->obj, NULL);
+	ret = __i915_add_request(ring, NULL, so.obj, NULL);
 	/* __i915_add_request moves object to inactive if it fails */
 out:
-	render_state_free(so);
+	render_state_fini(&so);
 	return ret;
 }

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -292,9 +292,20 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj)
 	kfree(obj->pages);
 }
 
+
+static void
+i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
+{
+	if (obj->stolen) {
+		drm_mm_remove_node(obj->stolen);
+		kfree(obj->stolen);
+		obj->stolen = NULL;
+	}
+}
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
 	.get_pages = i915_gem_object_get_pages_stolen,
 	.put_pages = i915_gem_object_put_pages_stolen,
+	.release = i915_gem_object_release_stolen,
 };
 
 static struct drm_i915_gem_object *
@@ -452,13 +463,3 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	drm_gem_object_unreference(&obj->base);
 	return NULL;
 }
-
-void
-i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
-{
-	if (obj->stolen) {
-		drm_mm_remove_node(obj->stolen);
-		kfree(obj->stolen);
-		obj->stolen = NULL;
-	}
-}

drivers/gpu/drm/i915/i915_params.c

@@ -48,6 +48,7 @@ struct i915_params i915 __read_mostly = {
 	.disable_display = 0,
 	.enable_cmd_parser = 1,
 	.disable_vtd_wa = 0,
+	.use_mmio_flip = 0,
 };
 
 module_param_named(modeset, i915.modeset, int, 0400);
@@ -156,3 +157,7 @@ MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)"
 module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
 MODULE_PARM_DESC(enable_cmd_parser,
 		 "Enable command parsing (1=enabled [default], 0=disabled)");
+
+module_param_named(use_mmio_flip, i915.use_mmio_flip, int, 0600);
+MODULE_PARM_DESC(use_mmio_flip,
+		 "use MMIO flips (-1=never, 0=driver discretion [default], 1=always)");

drivers/gpu/drm/i915/intel_ddi.c

@@ -76,12 +76,12 @@ static const u32 bdw_ddi_translations_edp[] = {
 	0x00FFFFFF, 0x00000012,		/* eDP parameters */
 	0x00EBAFFF, 0x00020011,
 	0x00C71FFF, 0x0006000F,
+	0x00AAAFFF, 0x000E000A,
 	0x00FFFFFF, 0x00020011,
 	0x00DB6FFF, 0x0005000F,
 	0x00BEEFFF, 0x000A000C,
 	0x00FFFFFF, 0x0005000F,
 	0x00DB6FFF, 0x000A000C,
-	0x00FFFFFF, 0x000A000C,
 	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
 };
 
@@ -89,12 +89,12 @@ static const u32 bdw_ddi_translations_dp[] = {
 	0x00FFFFFF, 0x0007000E,		/* DP parameters */
 	0x00D75FFF, 0x000E000A,
 	0x00BEFFFF, 0x00140006,
+	0x80B2CFFF, 0x001B0002,
 	0x00FFFFFF, 0x000E000A,
 	0x00D75FFF, 0x00180004,
 	0x80CB2FFF, 0x001B0002,
 	0x00F7DFFF, 0x00180004,
 	0x80D75FFF, 0x001B0002,
-	0x80FFFFFF, 0x001B0002,
 	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
 };
 

drivers/gpu/drm/i915/intel_drv.h

@@ -358,6 +358,11 @@ struct intel_pipe_wm {
 	bool sprites_scaled;
 };
 
+struct intel_mmio_flip {
+	u32 seqno;
+	u32 ring_id;
+};
+
 struct intel_crtc {
 	struct drm_crtc base;
 	enum pipe pipe;
@@ -384,7 +389,6 @@ struct intel_crtc {
 
 	struct drm_i915_gem_object *cursor_bo;
 	uint32_t cursor_addr;
-	int16_t cursor_x, cursor_y;
 	int16_t cursor_width, cursor_height;
 	uint32_t cursor_cntl;
 	uint32_t cursor_base;
@@ -412,6 +416,7 @@ struct intel_crtc {
 	wait_queue_head_t vbl_wait;
 
 	int scanline_offset;
+	struct intel_mmio_flip mmio_flip;
 };
 
 struct intel_plane_wm_parameters {
@@ -428,7 +433,6 @@ struct intel_plane {
 	struct drm_i915_gem_object *obj;
 	bool can_scale;
 	int max_downscale;
-	u32 lut_r[1024], lut_g[1024], lut_b[1024];
 	int crtc_x, crtc_y;
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y;
@@ -537,7 +541,6 @@ struct intel_dp {
 	unsigned long last_power_cycle;
 	unsigned long last_power_on;
 	unsigned long last_backlight_off;
-	bool psr_setup_done;
 	bool use_tps3;
 	struct intel_connector *attached_connector;
 
@@ -721,8 +724,33 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev);
 int intel_pch_rawclk(struct drm_device *dev);
 int valleyview_cur_cdclk(struct drm_i915_private *dev_priv);
 void intel_mark_busy(struct drm_device *dev);
-void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
-			struct intel_engine_cs *ring);
+void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+			     struct intel_engine_cs *ring);
+void intel_frontbuffer_flip_prepare(struct drm_device *dev,
+				    unsigned frontbuffer_bits);
+void intel_frontbuffer_flip_complete(struct drm_device *dev,
+				     unsigned frontbuffer_bits);
+void intel_frontbuffer_flush(struct drm_device *dev,
+			     unsigned frontbuffer_bits);
+/**
+ * intel_frontbuffer_flip - prepare frontbuffer flip
+ * @dev: DRM device
+ * @frontbuffer_bits: frontbuffer plane tracking bits
+ *
+ * This function gets called after scheduling a flip on @obj. This is for
+ * synchronous plane updates which will happen on the next vblank and which will
+ * not get delayed by pending gpu rendering.
+ *
+ * Can be called without any locks held.
+ */
+static inline
+void intel_frontbuffer_flip(struct drm_device *dev,
+			    unsigned frontbuffer_bits)
+{
+	intel_frontbuffer_flush(dev, frontbuffer_bits);
+}
+
+void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 void intel_mark_idle(struct drm_device *dev);
 void intel_crtc_restore_mode(struct drm_crtc *crtc);
 void intel_crtc_update_dpms(struct drm_crtc *crtc);
@@ -831,11 +859,13 @@ void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
 void intel_edp_psr_enable(struct intel_dp *intel_dp);
 void intel_edp_psr_disable(struct intel_dp *intel_dp);
-void intel_edp_psr_update(struct drm_device *dev);
 void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate);
+void intel_edp_psr_exit(struct drm_device *dev);
+void intel_edp_psr_init(struct drm_device *dev);
+
 
 /* intel_dsi.c */
-bool intel_dsi_init(struct drm_device *dev);
+void intel_dsi_init(struct drm_device *dev);
 
 
 /* intel_dvo.c */
@@ -961,6 +991,7 @@ void intel_init_gt_powersave(struct drm_device *dev);
 void intel_cleanup_gt_powersave(struct drm_device *dev);
 void intel_enable_gt_powersave(struct drm_device *dev);
 void intel_disable_gt_powersave(struct drm_device *dev);
+void intel_suspend_gt_powersave(struct drm_device *dev);
 void intel_reset_gt_powersave(struct drm_device *dev);
 void ironlake_teardown_rc6(struct drm_device *dev);
 void gen6_update_ring_freq(struct drm_device *dev);

drivers/gpu/drm/i915/intel_dsi.c

@@ -657,7 +657,7 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 };
 
-bool intel_dsi_init(struct drm_device *dev)
+void intel_dsi_init(struct drm_device *dev)
 {
 	struct intel_dsi *intel_dsi;
 	struct intel_encoder *intel_encoder;
@@ -673,29 +673,29 @@ bool intel_dsi_init(struct drm_device *dev)
 
 	/* There is no detection method for MIPI so rely on VBT */
 	if (!dev_priv->vbt.has_mipi)
-		return false;
+		return;
+
+	if (IS_VALLEYVIEW(dev)) {
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
+	} else {
+		DRM_ERROR("Unsupported Mipi device to reg base");
+		return;
+	}
 
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
-		return false;
+		return;
 
 	intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
 	if (!intel_connector) {
 		kfree(intel_dsi);
-		return false;
+		return;
 	}
 
 	intel_encoder = &intel_dsi->base;
 	encoder = &intel_encoder->base;
 	intel_dsi->attached_connector = intel_connector;
 
-	if (IS_VALLEYVIEW(dev)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return false;
-	}
-
 	connector = &intel_connector->base;
 
 	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI);
@@ -753,12 +753,10 @@ bool intel_dsi_init(struct drm_device *dev)
 	fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
 	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 
-	return true;
+	return;
 
 err:
 	drm_encoder_cleanup(&intel_encoder->base);
 	kfree(intel_dsi);
 	kfree(intel_connector);
-
-	return false;
 }

drivers/gpu/drm/i915/intel_dsi_panel_vbt.c

@@ -143,7 +143,7 @@ static u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi, u8 *data)
 	case MIPI_DSI_DCS_LONG_WRITE:
 		dsi_vc_dcs_write(intel_dsi, vc, data, len);
 		break;
-	};
+	}
 
 	data += len;
 
@@ -294,7 +294,8 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	intel_dsi->rst_timer_val = mipi_config->device_reset_timer;
 	intel_dsi->init_count = mipi_config->master_init_timer;
 	intel_dsi->bw_timer = mipi_config->dbi_bw_timer;
-	intel_dsi->video_frmt_cfg_bits = mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
+	intel_dsi->video_frmt_cfg_bits =
+		mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
 
 	switch (intel_dsi->escape_clk_div) {
 	case 0:
@@ -351,7 +352,8 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	 *
 	 * prepare count
 	 */
-	ths_prepare_ns = max(mipi_config->ths_prepare, mipi_config->tclk_prepare);
+	ths_prepare_ns = max(mipi_config->ths_prepare,
+			     mipi_config->tclk_prepare);
 	prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * 2);
 
 	/* exit zero count */

drivers/gpu/drm/i915/intel_dvo.c

@@ -112,7 +112,15 @@ static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
 
 static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dvo *intel_dvo = intel_attached_dvo(&connector->base);
+	u32 tmp;
+
+	tmp = I915_READ(intel_dvo->dev.dvo_reg);
+
+	if (!(tmp & DVO_ENABLE))
+		return false;
 
 	return intel_dvo->dev.dev_ops->get_hw_state(&intel_dvo->dev);
 }

drivers/gpu/drm/i915/intel_fbdev.c

@@ -43,10 +43,36 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
+static int intel_fbdev_set_par(struct fb_info *info)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+	struct intel_fbdev *ifbdev =
+		container_of(fb_helper, struct intel_fbdev, helper);
+	int ret;
+
+	ret = drm_fb_helper_set_par(info);
+
+	if (ret == 0) {
+		/*
+		 * FIXME: fbdev presumes that all callbacks also work from
+		 * atomic contexts and relies on that for emergency oops
+		 * printing. KMS totally doesn't do that and the locking here is
+		 * by far not the only place this goes wrong.  Ignore this for
+		 * now until we solve this for real.
+		 */
+		mutex_lock(&fb_helper->dev->struct_mutex);
+		ret = i915_gem_object_set_to_gtt_domain(ifbdev->fb->obj,
+							true);
+		mutex_unlock(&fb_helper->dev->struct_mutex);
+	}
+
+	return ret;
+}
+
 static struct fb_ops intelfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = drm_fb_helper_check_var,
-	.fb_set_par = drm_fb_helper_set_par,
+	.fb_set_par = intel_fbdev_set_par,
 	.fb_fillrect = cfb_fillrect,
 	.fb_copyarea = cfb_copyarea,
 	.fb_imageblit = cfb_imageblit,
@@ -417,7 +443,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		}
 		crtcs[i] = new_crtc;
 
-		DRM_DEBUG_KMS("connector %s on pipe %d [CRTC:%d]: %dx%d%s\n",
+		DRM_DEBUG_KMS("connector %s on pipe %c [CRTC:%d]: %dx%d%s\n",
 			      connector->name,
 			      pipe_name(to_intel_crtc(encoder->crtc)->pipe),
 			      encoder->crtc->base.id,

drivers/gpu/drm/i915/intel_hdmi.c

@@ -1229,6 +1229,70 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* program left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA1_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA1_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA2_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA2_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
+	/* program clock channel usage */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+
+	/*
+	 * This a a bit weird since generally CL
+	 * matches the pipe, but here we need to
+	 * pick the CL based on the port.
+	 */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
+	if (pipe != PIPE_B)
+		val &= ~CHV_CMN_USEDCLKCHANNEL;
+	else
+		val |= CHV_CMN_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
 static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
 {
 	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
@@ -1528,6 +1592,7 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 	intel_encoder->get_hw_state = intel_hdmi_get_hw_state;
 	intel_encoder->get_config = intel_hdmi_get_config;
 	if (IS_CHERRYVIEW(dev)) {
+		intel_encoder->pre_pll_enable = chv_hdmi_pre_pll_enable;
 		intel_encoder->pre_enable = chv_hdmi_pre_enable;
 		intel_encoder->enable = vlv_enable_hdmi;
 		intel_encoder->post_disable = chv_hdmi_post_disable;

drivers/gpu/drm/i915/intel_overlay.c

@@ -415,6 +415,10 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 	}
 
 	intel_overlay_release_old_vid_tail(overlay);
+
+
+	i915_gem_track_fb(overlay->old_vid_bo, NULL,
+			  INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
 	return 0;
 }
 
@@ -686,6 +690,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	bool scale_changed = false;
 	struct drm_device *dev = overlay->dev;
 	u32 swidth, swidthsw, sheight, ostride;
+	enum pipe pipe = overlay->crtc->pipe;
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 	BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
@@ -713,7 +718,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		oconfig = OCONF_CC_OUT_8BIT;
 		if (IS_GEN4(overlay->dev))
 			oconfig |= OCONF_CSC_MODE_BT709;
-		oconfig |= overlay->crtc->pipe == 0 ?
+		oconfig |= pipe == 0 ?
 			OCONF_PIPE_A : OCONF_PIPE_B;
 		iowrite32(oconfig, &regs->OCONFIG);
 		intel_overlay_unmap_regs(overlay, regs);
@@ -776,9 +781,15 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	if (ret)
 		goto out_unpin;
 
+	i915_gem_track_fb(overlay->vid_bo, new_bo,
+			  INTEL_FRONTBUFFER_OVERLAY(pipe));
+
 	overlay->old_vid_bo = overlay->vid_bo;
 	overlay->vid_bo = new_bo;
 
+	intel_frontbuffer_flip(dev,
+			       INTEL_FRONTBUFFER_OVERLAY(pipe));
+
 	return 0;
 
 out_unpin:

drivers/gpu/drm/i915/intel_renderstate.h

@@ -28,7 +28,6 @@
 
 struct intel_renderstate_rodata {
 	const u32 *reloc;
-	const u32 reloc_items;
 	const u32 *batch;
 	const u32 batch_items;
 };
@@ -40,7 +39,6 @@ extern const struct intel_renderstate_rodata gen8_null_state;
 #define RO_RENDERSTATE(_g)						\
 	const struct intel_renderstate_rodata gen ## _g ## _null_state = { \
 		.reloc = gen ## _g ## _null_state_relocs,		\
-		.reloc_items = sizeof(gen ## _g ## _null_state_relocs)/4, \
 		.batch = gen ## _g ## _null_state_batch,		\
 		.batch_items = sizeof(gen ## _g ## _null_state_batch)/4, \
 	}

drivers/gpu/drm/i915/intel_renderstate_gen6.c

@@ -6,6 +6,7 @@ static const u32 gen6_null_state_relocs[] = {
 	0x0000002c,
 	0x000001e0,
 	0x000001e4,
+	-1,
 };
 
 static const u32 gen6_null_state_batch[] = {

drivers/gpu/drm/i915/intel_renderstate_gen7.c

@@ -5,6 +5,7 @@ static const u32 gen7_null_state_relocs[] = {
 	0x00000010,
 	0x00000018,
 	0x000001ec,
+	-1,
 };
 
 static const u32 gen7_null_state_batch[] = {

drivers/gpu/drm/i915/intel_renderstate_gen8.c

@@ -5,6 +5,7 @@ static const u32 gen8_null_state_relocs[] = {
 	0x00000050,
 	0x00000060,
 	0x000003ec,
+	-1,
 };
 
 static const u32 gen8_null_state_batch[] = {