Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Been a bit busy, first week of kids school, and waiting on other trees
  to go in before I could send this, so its a bit later than I'd
  normally like.

  Highlights:
   - core:
      timestamp fixes, lots of misc cleanups
   - new drivers:
      bochs virtual vga
   - vmwgfx:
      major overhaul for their nextgen virt gpu.
   - i915:
      runtime D3 on HSW, watermark fixes, power well work, fbc fixes,
      bdw is no longer prelim.
   - nouveau:
      gk110/208 acceleration, more pm groundwork, old overlay support
   - radeon:
      dpm rework and clockgating for CIK, pci config reset, big endian
      fixes
   - tegra:
      panel support and DSI support, build as module, prime.
   - armada, omap, gma500, rcar, exynos, mgag200, cirrus, ast:
      fixes
   - msm:
      hdmi support for mdp5"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (595 commits)
  drm/nouveau: resume display if any later suspend bits fail
  drm/nouveau: fix lock unbalance in nouveau_crtc_page_flip
  drm/nouveau: implement hooks for needed for drm vblank timestamping support
  drm/nouveau/disp: add a method to fetch info needed by drm vblank timestamping
  drm/nv50: fill in crtc mode struct members from crtc_mode_fixup
  drm/radeon/dce8: workaround for atom BlankCrtc table
  drm/radeon/DCE4+: clear bios scratch dpms bit (v2)
  drm/radeon: set si_notify_smc_display_change properly
  drm/radeon: fix DAC interrupt handling on DCE5+
  drm/radeon: clean up active vram sizing
  drm/radeon: skip async dma init on r6xx
  drm/radeon/runpm: don't runtime suspend non-PX cards
  drm/radeon: add ring to fence trace functions
  drm/radeon: add missing trace point
  drm/radeon: fix VMID use tracking
  drm: ast,cirrus,mgag200: use drm_can_sleep
  drm/gma500: Lock struct_mutex around cursor updates
  drm/i915: Fix the offset issue for the stolen GEM objects
  DRM: armada: fix missing DRM_KMS_FB_HELPER select
  drm/i915: Decouple GPU error reporting from ring initialisation
  ...

44 files changed, 3763 insertions, 2858 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 6199d0b5b958..73ed59eff139 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -1,8 +1,10 @@
 config DRM_I915
 	tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics"
 	depends on DRM
-	depends on AGP
-	depends on AGP_INTEL
+	depends on X86 && PCI
+	depends on (AGP || AGP=n)
+	select INTEL_GTT
+	select AGP_INTEL if AGP
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
 	select SHMEM
@@ -35,15 +37,14 @@ config DRM_I915
 config DRM_I915_KMS
 	bool "Enable modesetting on intel by default"
 	depends on DRM_I915
+	default y
 	help
-	  Choose this option if you want kernel modesetting enabled by default,
-	  and you have a new enough userspace to support this. Running old
-	  userspaces with this enabled will cause pain.  Note that this causes
-	  the driver to bind to PCI devices, which precludes loading things
-	  like intelfb.
+	  Choose this option if you want kernel modesetting enabled by default.
+
+	  If in doubt, say "Y".
 
 config DRM_I915_FBDEV
-	bool "Enable legacy fbdev support for the modesettting intel driver"
+	bool "Enable legacy fbdev support for the modesetting intel driver"
 	depends on DRM_I915
 	select DRM_KMS_FB_HELPER
 	select FB_CFB_FILLRECT
@@ -55,9 +56,12 @@ config DRM_I915_FBDEV
 	  support. Note that this support also provide the linux console
 	  support on top of the intel modesetting driver.
 
+	  If in doubt, say "Y".
+
 config DRM_I915_PRELIMINARY_HW_SUPPORT
 	bool "Enable preliminary support for prerelease Intel hardware by default"
 	depends on DRM_I915
+	default n
 	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
@@ -65,3 +69,15 @@ config DRM_I915_PRELIMINARY_HW_SUPPORT
 	  option changes the default for that module option.
 
 	  If in doubt, say "N".
+
+config DRM_I915_UMS
+	bool "Enable userspace modesetting on Intel hardware (DEPRECATED)"
+	depends on DRM_I915
+	default n
+	help
+	  Choose this option if you still need userspace modesetting.
+
+	  Userspace modesetting is deprecated for quite some time now, so
+	  enable this only if you have ancient versions of the DDX drivers.
+
+	  If in doubt, say "N".
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index d4ae48b04cf2..9fd44f5f3b3b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -4,7 +4,6 @@
 
 ccflags-y := -Iinclude/drm
 i915-y := i915_drv.o i915_dma.o i915_irq.o \
-	  i915_debugfs.o \
 	  i915_gpu_error.o \
           i915_suspend.o \
 	  i915_gem.o \
@@ -54,6 +53,8 @@ i915-$(CONFIG_ACPI)	+= intel_acpi.o intel_opregion.o
 
 i915-$(CONFIG_DRM_I915_FBDEV) += intel_fbdev.o
 
+i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
+
 obj-$(CONFIG_DRM_I915)  += i915.o
 
 CFLAGS_i915_trace_points.o := -I$(src)
diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c
index c4a255be6979..954acb2c7021 100644
--- a/drivers/gpu/drm/i915/dvo_ns2501.c
+++ b/drivers/gpu/drm/i915/dvo_ns2501.c
@@ -87,49 +87,6 @@ struct ns2501_priv {
  * when switching the resolution.
  */
 
-static void enable_dvo(struct intel_dvo_device *dvo)
-{
-	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
-	struct i2c_adapter *adapter = dvo->i2c_bus;
-	struct intel_gmbus *bus = container_of(adapter,
-					       struct intel_gmbus,
-					       adapter);
-	struct drm_i915_private *dev_priv = bus->dev_priv;
-
-	DRM_DEBUG_KMS("%s: Trying to re-enable the DVO\n", __FUNCTION__);
-
-	ns->dvoc = I915_READ(DVO_C);
-	ns->pll_a = I915_READ(_DPLL_A);
-	ns->srcdim = I915_READ(DVOC_SRCDIM);
-	ns->fw_blc = I915_READ(FW_BLC);
-
-	I915_WRITE(DVOC, 0x10004084);
-	I915_WRITE(_DPLL_A, 0xd0820000);
-	I915_WRITE(DVOC_SRCDIM, 0x400300);	// 1024x768
-	I915_WRITE(FW_BLC, 0x1080304);
-
-	I915_WRITE(DVOC, 0x90004084);
-}
-
-/*
- * Restore the I915 registers modified by the above
- * trigger function.
- */
-static void restore_dvo(struct intel_dvo_device *dvo)
-{
-	struct i2c_adapter *adapter = dvo->i2c_bus;
-	struct intel_gmbus *bus = container_of(adapter,
-					       struct intel_gmbus,
-					       adapter);
-	struct drm_i915_private *dev_priv = bus->dev_priv;
-	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
-
-	I915_WRITE(DVOC, ns->dvoc);
-	I915_WRITE(_DPLL_A, ns->pll_a);
-	I915_WRITE(DVOC_SRCDIM, ns->srcdim);
-	I915_WRITE(FW_BLC, ns->fw_blc);
-}
-
 /*
 ** Read a register from the ns2501.
 ** Returns true if successful, false otherwise.
@@ -300,7 +257,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 			    struct drm_display_mode *adjusted_mode)
 {
 	bool ok;
-	bool restore = false;
+	int retries = 10;
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
 
 	DRM_DEBUG_KMS
@@ -476,20 +433,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 			ns->reg_8_shadow |= NS2501_8_BPAS;
 		}
 		ok &= ns2501_writeb(dvo, NS2501_REG8, ns->reg_8_shadow);
-
-		if (!ok) {
-			if (restore)
-				restore_dvo(dvo);
-			enable_dvo(dvo);
-			restore = true;
-		}
-	} while (!ok);
-	/*
-	 * Restore the old i915 registers before
-	 * forcing the ns2501 on.
-	 */
-	if (restore)
-		restore_dvo(dvo);
+	} while (!ok && retries--);
 }
 
 /* set the NS2501 power state */
@@ -510,7 +454,7 @@ static bool ns2501_get_hw_state(struct intel_dvo_device *dvo)
 static void ns2501_dpms(struct intel_dvo_device *dvo, bool enable)
 {
 	bool ok;
-	bool restore = false;
+	int retries = 10;
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
 	unsigned char ch;
 
@@ -537,16 +481,7 @@ static void ns2501_dpms(struct intel_dvo_device *dvo, bool enable)
 			ok &=
 			    ns2501_writeb(dvo, 0x35,
 					  enable ? 0xff : 0x00);
-			if (!ok) {
-				if (restore)
-					restore_dvo(dvo);
-				enable_dvo(dvo);
-				restore = true;
-			}
-		} while (!ok);
-
-		if (restore)
-			restore_dvo(dvo);
+		} while (!ok && retries--);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6ed45a984230..b2b46c52294c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -40,8 +40,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-#if defined(CONFIG_DEBUG_FS)
-
 enum {
 	ACTIVE_LIST,
 	INACTIVE_LIST,
@@ -406,16 +404,26 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	seq_putc(m, '\n');
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct file_stats stats;
+		struct task_struct *task;
 
 		memset(&stats, 0, sizeof(stats));
 		idr_for_each(&file->object_idr, per_file_stats, &stats);
+		/*
+		 * Although we have a valid reference on file->pid, that does
+		 * not guarantee that the task_struct who called get_pid() is
+		 * still alive (e.g. get_pid(current) => fork() => exit()).
+		 * Therefore, we need to protect this ->comm access using RCU.
+		 */
+		rcu_read_lock();
+		task = pid_task(file->pid, PIDTYPE_PID);
 		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu unbound)\n",
-			   get_pid_task(file->pid, PIDTYPE_PID)->comm,
+			   task ? task->comm : "<unknown>",
 			   stats.count,
 			   stats.total,
 			   stats.active,
 			   stats.inactive,
 			   stats.unbound);
+		rcu_read_unlock();
 	}
 
 	mutex_unlock(&dev->struct_mutex);
@@ -564,10 +572,12 @@ static int i915_gem_seqno_info(struct seq_file *m, void *data)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	for_each_ring(ring, dev_priv, i)
 		i915_ring_seqno_info(m, ring);
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -585,6 +595,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		int i;
@@ -711,6 +722,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		}
 		i915_ring_seqno_info(m, ring);
 	}
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -904,9 +916,11 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	crstanddelay = I915_READ16(CRSTANDVID);
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "w/ctx: %d, w/o ctx: %d\n", (crstanddelay >> 8) & 0x3f, (crstanddelay & 0x3f));
@@ -919,7 +933,9 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret = 0;
+
+	intel_runtime_pm_get(dev_priv);
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
 
@@ -945,9 +961,9 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		/* RPSTAT1 is in the GT power well */
 		ret = mutex_lock_interruptible(&dev->struct_mutex);
 		if (ret)
-			return ret;
+			goto out;
 
-		gen6_gt_force_wake_get(dev_priv);
+		gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 		reqf = I915_READ(GEN6_RPNSWREQ);
 		reqf &= ~GEN6_TURBO_DISABLE;
@@ -970,7 +986,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 			cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
 		cagf *= GT_FREQUENCY_MULTIPLIER;
 
-		gen6_gt_force_wake_put(dev_priv);
+		gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 		mutex_unlock(&dev->struct_mutex);
 
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
@@ -1018,23 +1034,24 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts);
 		seq_printf(m, "DDR freq: %d MHz\n", dev_priv->mem_freq);
 
-		val = vlv_punit_read(dev_priv, PUNIT_FUSE_BUS1);
+		val = valleyview_rps_max_freq(dev_priv);
 		seq_printf(m, "max GPU freq: %d MHz\n",
-			   vlv_gpu_freq(dev_priv->mem_freq, val));
+			   vlv_gpu_freq(dev_priv, val));
 
-		val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM);
+		val = valleyview_rps_min_freq(dev_priv);
 		seq_printf(m, "min GPU freq: %d MHz\n",
-			   vlv_gpu_freq(dev_priv->mem_freq, val));
+			   vlv_gpu_freq(dev_priv, val));
 
 		seq_printf(m, "current GPU freq: %d MHz\n",
-			   vlv_gpu_freq(dev_priv->mem_freq,
-					(freq_sts >> 8) & 0xff));
+			   vlv_gpu_freq(dev_priv, (freq_sts >> 8) & 0xff));
 		mutex_unlock(&dev_priv->rps.hw_lock);
 	} else {
 		seq_puts(m, "no P-state info available\n");
 	}
 
-	return 0;
+out:
+	intel_runtime_pm_put(dev_priv);
+	return ret;
 }
 
 static int i915_delayfreq_table(struct seq_file *m, void *unused)
@@ -1048,6 +1065,7 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	for (i = 0; i < 16; i++) {
 		delayfreq = I915_READ(PXVFREQ_BASE + i * 4);
@@ -1055,6 +1073,8 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 			   (delayfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT);
 	}
 
+	intel_runtime_pm_put(dev_priv);
+
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -1076,12 +1096,14 @@ static int i915_inttoext_table(struct seq_file *m, void *unused)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	for (i = 1; i <= 32; i++) {
 		inttoext = I915_READ(INTTOEXT_BASE_ILK + i * 4);
 		seq_printf(m, "INTTOEXT%02d: 0x%08x\n", i, inttoext);
 	}
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -1099,11 +1121,13 @@ static int ironlake_drpc_info(struct seq_file *m)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	rgvmodectl = I915_READ(MEMMODECTL);
 	rstdbyctl = I915_READ(RSTDBYCTL);
 	crstandvid = I915_READ16(CRSTANDVID);
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ?
@@ -1154,6 +1178,50 @@ static int ironlake_drpc_info(struct seq_file *m)
 	return 0;
 }
 
+static int vlv_drpc_info(struct seq_file *m)
+{
+
+	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;
+	u32 rpmodectl1, rcctl1;
+	unsigned fw_rendercount = 0, fw_mediacount = 0;
+
+	rpmodectl1 = I915_READ(GEN6_RP_CONTROL);
+	rcctl1 = I915_READ(GEN6_RC_CONTROL);
+
+	seq_printf(m, "Video Turbo Mode: %s\n",
+		   yesno(rpmodectl1 & GEN6_RP_MEDIA_TURBO));
+	seq_printf(m, "Turbo enabled: %s\n",
+		   yesno(rpmodectl1 & GEN6_RP_ENABLE));
+	seq_printf(m, "HW control enabled: %s\n",
+		   yesno(rpmodectl1 & GEN6_RP_ENABLE));
+	seq_printf(m, "SW control enabled: %s\n",
+		   yesno((rpmodectl1 & GEN6_RP_MEDIA_MODE_MASK) ==
+			  GEN6_RP_MEDIA_SW_MODE));
+	seq_printf(m, "RC6 Enabled: %s\n",
+		   yesno(rcctl1 & (GEN7_RC_CTL_TO_MODE |
+					GEN6_RC_CTL_EI_MODE(1))));
+	seq_printf(m, "Render Power Well: %s\n",
+			(I915_READ(VLV_GTLC_PW_STATUS) &
+				VLV_GTLC_PW_RENDER_STATUS_MASK) ? "Up" : "Down");
+	seq_printf(m, "Media Power Well: %s\n",
+			(I915_READ(VLV_GTLC_PW_STATUS) &
+				VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down");
+
+	spin_lock_irq(&dev_priv->uncore.lock);
+	fw_rendercount = dev_priv->uncore.fw_rendercount;
+	fw_mediacount = dev_priv->uncore.fw_mediacount;
+	spin_unlock_irq(&dev_priv->uncore.lock);
+
+	seq_printf(m, "Forcewake Render Count = %u\n", fw_rendercount);
+	seq_printf(m, "Forcewake Media Count = %u\n", fw_mediacount);
+
+
+	return 0;
+}
+
+
 static int gen6_drpc_info(struct seq_file *m)
 {
 
@@ -1167,6 +1235,7 @@ static int gen6_drpc_info(struct seq_file *m)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irq(&dev_priv->uncore.lock);
 	forcewake_count = dev_priv->uncore.forcewake_count;
@@ -1192,6 +1261,8 @@ static int gen6_drpc_info(struct seq_file *m)
 	sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
+	intel_runtime_pm_put(dev_priv);
+
 	seq_printf(m, "Video Turbo Mode: %s\n",
 		   yesno(rpmodectl1 & GEN6_RP_MEDIA_TURBO));
 	seq_printf(m, "HW control enabled: %s\n",
@@ -1256,7 +1327,9 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 
-	if (IS_GEN6(dev) || IS_GEN7(dev))
+	if (IS_VALLEYVIEW(dev))
+		return vlv_drpc_info(m);
+	else if (IS_GEN6(dev) || IS_GEN7(dev))
 		return gen6_drpc_info(m);
 	else
 		return ironlake_drpc_info(m);
@@ -1268,7 +1341,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 
-	if (!I915_HAS_FBC(dev)) {
+	if (!HAS_FBC(dev)) {
 		seq_puts(m, "FBC unsupported on this chipset\n");
 		return 0;
 	}
@@ -1330,7 +1403,7 @@ static int i915_ips_status(struct seq_file *m, void *unused)
 		return 0;
 	}
 
-	if (I915_READ(IPS_CTL) & IPS_ENABLE)
+	if (IS_BROADWELL(dev) || I915_READ(IPS_CTL) & IPS_ENABLE)
 		seq_puts(m, "enabled\n");
 	else
 		seq_puts(m, "disabled\n");
@@ -1406,6 +1479,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	ret = mutex_lock_interruptible(&dev_priv->rps.hw_lock);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
@@ -1422,6 +1496,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 			   ((ia_freq >> 8) & 0xff) * 100);
 	}
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return 0;
@@ -1437,8 +1512,10 @@ static int i915_gfxec(struct seq_file *m, void *unused)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "GFXEC: %ld\n", (unsigned long)I915_READ(0x112f4));
+	intel_runtime_pm_put(dev_priv);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1565,13 +1642,21 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	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;
-	unsigned forcewake_count;
+	unsigned forcewake_count = 0, fw_rendercount = 0, fw_mediacount = 0;
 
 	spin_lock_irq(&dev_priv->uncore.lock);
-	forcewake_count = dev_priv->uncore.forcewake_count;
+	if (IS_VALLEYVIEW(dev)) {
+		fw_rendercount = dev_priv->uncore.fw_rendercount;
+		fw_mediacount = dev_priv->uncore.fw_mediacount;
+	} else
+		forcewake_count = dev_priv->uncore.forcewake_count;
 	spin_unlock_irq(&dev_priv->uncore.lock);
 
-	seq_printf(m, "forcewake count = %u\n", forcewake_count);
+	if (IS_VALLEYVIEW(dev)) {
+		seq_printf(m, "fw_rendercount = %u\n", fw_rendercount);
+		seq_printf(m, "fw_mediacount = %u\n", fw_mediacount);
+	} else
+		seq_printf(m, "forcewake count = %u\n", forcewake_count);
 
 	return 0;
 }
@@ -1610,6 +1695,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "bit6 swizzle for X-tiling = %s\n",
 		   swizzle_string(dev_priv->mm.bit_6_swizzle_x));
@@ -1641,6 +1727,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 		seq_printf(m, "DISP_ARB_CTL = 0x%08x\n",
 			   I915_READ(DISP_ARB_CTL));
 	}
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -1701,16 +1788,19 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 {
 	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;
 
 	int ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	if (INTEL_INFO(dev)->gen >= 8)
 		gen8_ppgtt_info(m, dev);
 	else if (INTEL_INFO(dev)->gen >= 6)
 		gen6_ppgtt_info(m, dev);
 
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -1735,28 +1825,28 @@ static int i915_dpio_info(struct seq_file *m, void *data)
 
 	seq_printf(m, "DPIO_CTL: 0x%08x\n", I915_READ(DPIO_CTL));
 
-	seq_printf(m, "DPIO_DIV_A: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_DIV_A));
-	seq_printf(m, "DPIO_DIV_B: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_DIV_B));
+	seq_printf(m, "DPIO PLL DW3 CH0 : 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(0)));
+	seq_printf(m, "DPIO PLL DW3 CH1: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(1)));
 
-	seq_printf(m, "DPIO_REFSFR_A: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_REFSFR_A));
-	seq_printf(m, "DPIO_REFSFR_B: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_REFSFR_B));
+	seq_printf(m, "DPIO PLL DW5 CH0: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(0)));
+	seq_printf(m, "DPIO PLL DW5 CH1: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(1)));
 
-	seq_printf(m, "DPIO_CORE_CLK_A: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_CORE_CLK_A));
-	seq_printf(m, "DPIO_CORE_CLK_B: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_CORE_CLK_B));
+	seq_printf(m, "DPIO PLL DW7 CH0: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(0)));
+	seq_printf(m, "DPIO PLL DW7 CH1: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(1)));
 
-	seq_printf(m, "DPIO_LPF_COEFF_A: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_LPF_COEFF_A));
-	seq_printf(m, "DPIO_LPF_COEFF_B: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, _DPIO_LPF_COEFF_B));
+	seq_printf(m, "DPIO PLL DW10 CH0: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(0)));
+	seq_printf(m, "DPIO PLL DW10 CH1: 0x%08x\n",
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(1)));
 
 	seq_printf(m, "DPIO_FASTCLK_DISABLE: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, DPIO_FASTCLK_DISABLE));
+		   vlv_dpio_read(dev_priv, PIPE_A, VLV_CMN_DW0));
 
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -1784,6 +1874,8 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	u32 psrperf = 0;
 	bool enabled = false;
 
+	intel_runtime_pm_get(dev_priv);
+
 	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));
 
@@ -1796,6 +1888,7 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 			EDP_PSR_PERF_CNT_MASK;
 	seq_printf(m, "Performance_Counter: %u\n", psrperf);
 
+	intel_runtime_pm_put(dev_priv);
 	return 0;
 }
 
@@ -1845,6 +1938,76 @@ static int i915_pc8_status(struct seq_file *m, void *unused)
 	return 0;
 }
 
+static const char *power_domain_str(enum intel_display_power_domain domain)
+{
+	switch (domain) {
+	case POWER_DOMAIN_PIPE_A:
+		return "PIPE_A";
+	case POWER_DOMAIN_PIPE_B:
+		return "PIPE_B";
+	case POWER_DOMAIN_PIPE_C:
+		return "PIPE_C";
+	case POWER_DOMAIN_PIPE_A_PANEL_FITTER:
+		return "PIPE_A_PANEL_FITTER";
+	case POWER_DOMAIN_PIPE_B_PANEL_FITTER:
+		return "PIPE_B_PANEL_FITTER";
+	case POWER_DOMAIN_PIPE_C_PANEL_FITTER:
+		return "PIPE_C_PANEL_FITTER";
+	case POWER_DOMAIN_TRANSCODER_A:
+		return "TRANSCODER_A";
+	case POWER_DOMAIN_TRANSCODER_B:
+		return "TRANSCODER_B";
+	case POWER_DOMAIN_TRANSCODER_C:
+		return "TRANSCODER_C";
+	case POWER_DOMAIN_TRANSCODER_EDP:
+		return "TRANSCODER_EDP";
+	case POWER_DOMAIN_VGA:
+		return "VGA";
+	case POWER_DOMAIN_AUDIO:
+		return "AUDIO";
+	case POWER_DOMAIN_INIT:
+		return "INIT";
+	default:
+		WARN_ON(1);
+		return "?";
+	}
+}
+
+static int i915_power_domain_info(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;
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	int i;
+
+	mutex_lock(&power_domains->lock);
+
+	seq_printf(m, "%-25s %s\n", "Power well/domain", "Use count");
+	for (i = 0; i < power_domains->power_well_count; i++) {
+		struct i915_power_well *power_well;
+		enum intel_display_power_domain power_domain;
+
+		power_well = &power_domains->power_wells[i];
+		seq_printf(m, "%-25s %d\n", power_well->name,
+			   power_well->count);
+
+		for (power_domain = 0; power_domain < POWER_DOMAIN_NUM;
+		     power_domain++) {
+			if (!(BIT(power_domain) & power_well->domains))
+				continue;
+
+			seq_printf(m, "  %-23s %d\n",
+				 power_domain_str(power_domain),
+				 power_domains->domain_use_count[power_domain]);
+		}
+	}
+
+	mutex_unlock(&power_domains->lock);
+
+	return 0;
+}
+
 struct pipe_crc_info {
 	const char *name;
 	struct drm_device *dev;
@@ -1857,6 +2020,9 @@ static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
 	struct drm_i915_private *dev_priv = info->dev->dev_private;
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
 
+	if (info->pipe >= INTEL_INFO(info->dev)->num_pipes)
+		return -ENODEV;
+
 	spin_lock_irq(&pipe_crc->lock);
 
 	if (pipe_crc->opened) {
@@ -2005,8 +2171,8 @@ static int i915_pipe_crc_create(struct dentry *root, struct drm_minor *minor,
 	info->dev = dev;
 	ent = debugfs_create_file(info->name, S_IRUGO, root, info,
 				  &i915_pipe_crc_fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
+	if (!ent)
+		return -ENOMEM;
 
 	return drm_add_fake_info_node(minor, ent, info);
 }
@@ -2347,7 +2513,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	u32 val;
+	u32 val = 0; /* shut up gcc */
 	int ret;
 
 	if (pipe_crc->source == source)
@@ -2742,7 +2908,7 @@ i915_drop_caches_set(void *data, u64 val)
 	struct i915_vma *vma, *x;
 	int ret;
 
-	DRM_DEBUG_DRIVER("Dropping caches: 0x%08llx\n", val);
+	DRM_DEBUG("Dropping caches: 0x%08llx\n", val);
 
 	/* No need to check and wait for gpu resets, only libdrm auto-restarts
 	 * on ioctls on -EAGAIN. */
@@ -2810,8 +2976,7 @@ i915_max_freq_get(void *data, u64 *val)
 		return ret;
 
 	if (IS_VALLEYVIEW(dev))
-		*val = vlv_gpu_freq(dev_priv->mem_freq,
-				    dev_priv->rps.max_delay);
+		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
 	else
 		*val = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -2841,9 +3006,9 @@ i915_max_freq_set(void *data, u64 val)
 	 * Turbo will still be enabled, but won't go above the set value.
 	 */
 	if (IS_VALLEYVIEW(dev)) {
-		val = vlv_freq_opcode(dev_priv->mem_freq, val);
+		val = vlv_freq_opcode(dev_priv, val);
 		dev_priv->rps.max_delay = val;
-		gen6_set_rps(dev, val);
+		valleyview_set_rps(dev, val);
 	} else {
 		do_div(val, GT_FREQUENCY_MULTIPLIER);
 		dev_priv->rps.max_delay = val;
@@ -2876,8 +3041,7 @@ i915_min_freq_get(void *data, u64 *val)
 		return ret;
 
 	if (IS_VALLEYVIEW(dev))
-		*val = vlv_gpu_freq(dev_priv->mem_freq,
-				    dev_priv->rps.min_delay);
+		*val = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
 	else
 		*val = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -2907,7 +3071,7 @@ i915_min_freq_set(void *data, u64 val)
 	 * Turbo will still be enabled, but won't go below the set value.
 	 */
 	if (IS_VALLEYVIEW(dev)) {
-		val = vlv_freq_opcode(dev_priv->mem_freq, val);
+		val = vlv_freq_opcode(dev_priv, val);
 		dev_priv->rps.min_delay = val;
 		valleyview_set_rps(dev, val);
 	} else {
@@ -2938,8 +3102,11 @@ i915_cache_sharing_get(void *data, u64 *val)
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
+
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev_priv->dev->struct_mutex);
 
 	*val = (snpcr & GEN6_MBC_SNPCR_MASK) >> GEN6_MBC_SNPCR_SHIFT;
@@ -2960,6 +3127,7 @@ i915_cache_sharing_set(void *data, u64 val)
 	if (val > 3)
 		return -EINVAL;
 
+	intel_runtime_pm_get(dev_priv);
 	DRM_DEBUG_DRIVER("Manually setting uncore sharing to %llu\n", val);
 
 	/* Update the cache sharing policy here as well */
@@ -2968,6 +3136,7 @@ i915_cache_sharing_set(void *data, u64 val)
 	snpcr |= (val << GEN6_MBC_SNPCR_SHIFT);
 	I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
 
+	intel_runtime_pm_put(dev_priv);
 	return 0;
 }
 
@@ -2983,7 +3152,8 @@ static int i915_forcewake_open(struct inode *inode, struct file *file)
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
 
-	gen6_gt_force_wake_get(dev_priv);
+	intel_runtime_pm_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	return 0;
 }
@@ -2996,7 +3166,8 @@ static int i915_forcewake_release(struct inode *inode, struct file *file)
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
 
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+	intel_runtime_pm_put(dev_priv);
 
 	return 0;
 }
@@ -3016,8 +3187,8 @@ static int i915_forcewake_create(struct dentry *root, struct drm_minor *minor)
 				  S_IRUSR,
 				  root, dev,
 				  &i915_forcewake_fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
+	if (!ent)
+		return -ENOMEM;
 
 	return drm_add_fake_info_node(minor, ent, &i915_forcewake_fops);
 }
@@ -3034,8 +3205,8 @@ static int i915_debugfs_create(struct dentry *root,
 				  S_IRUGO | S_IWUSR,
 				  root, dev,
 				  fops);
-	if (IS_ERR(ent))
-		return PTR_ERR(ent);
+	if (!ent)
+		return -ENOMEM;
 
 	return drm_add_fake_info_node(minor, ent, fops);
 }
@@ -3079,6 +3250,7 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
 	{"i915_energy_uJ", i915_energy_uJ, 0},
 	{"i915_pc8_status", i915_pc8_status, 0},
+	{"i915_power_domain_info", i915_power_domain_info, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 
@@ -3102,10 +3274,10 @@ static const struct i915_debugfs_files {
 void intel_display_crc_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int i;
+	enum pipe pipe;
 
-	for (i = 0; i < INTEL_INFO(dev)->num_pipes; i++) {
-		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[i];
+	for_each_pipe(pipe) {
+		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 
 		pipe_crc->opened = false;
 		spin_lock_init(&pipe_crc->lock);
@@ -3164,5 +3336,3 @@ void i915_debugfs_cleanup(struct drm_minor *minor)
 		drm_debugfs_remove_files(info_list, 1, minor);
 	}
 }
-
-#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 5c648425c1e0..15a74f979b4b 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -42,6 +42,8 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
 #include <acpi/video.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
 
 #define LP_RING(d) (&((struct drm_i915_private *)(d))->ring[RCS])
 
@@ -791,7 +793,7 @@ static int i915_wait_irq(struct drm_device * dev, int irq_nr)
 		master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
 
 	if (ring->irq_get(ring)) {
-		DRM_WAIT_ON(ret, ring->irq_queue, 3 * DRM_HZ,
+		DRM_WAIT_ON(ret, ring->irq_queue, 3 * HZ,
 			    READ_BREADCRUMB(dev_priv) >= irq_nr);
 		ring->irq_put(ring);
 	} else if (wait_for(READ_BREADCRUMB(dev_priv) >= irq_nr, 3000))
@@ -828,7 +830,7 @@ static int i915_irq_emit(struct drm_device *dev, void *data,
 	result = i915_emit_irq(dev);
 	mutex_unlock(&dev->struct_mutex);
 
-	if (DRM_COPY_TO_USER(emit->irq_seq, &result, sizeof(int))) {
+	if (copy_to_user(emit->irq_seq, &result, sizeof(int))) {
 		DRM_ERROR("copy_to_user\n");
 		return -EFAULT;
 	}
@@ -1016,8 +1018,8 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (DRM_COPY_TO_USER(param->value, &value, sizeof(int))) {
-		DRM_ERROR("DRM_COPY_TO_USER failed\n");
+	if (copy_to_user(param->value, &value, sizeof(int))) {
+		DRM_ERROR("copy_to_user failed\n");
 		return -EFAULT;
 	}
 
@@ -1411,7 +1413,7 @@ void i915_master_destroy(struct drm_device *dev, struct drm_master *master)
 	master->driver_priv = NULL;
 }
 
-#ifdef CONFIG_DRM_I915_FBDEV
+#if IS_ENABLED(CONFIG_FB)
 static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 {
 	struct apertures_struct *ap;
@@ -1484,6 +1486,10 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		return -ENODEV;
 	}
 
+	/* UMS needs agp support. */
+	if (!drm_core_check_feature(dev, DRIVER_MODESET) && !dev->agp)
+		return -EINVAL;
+
 	dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
 	if (dev_priv == NULL)
 		return -ENOMEM;
@@ -1494,7 +1500,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
-	spin_lock_init(&dev_priv->backlight.lock);
+	spin_lock_init(&dev_priv->backlight_lock);
 	spin_lock_init(&dev_priv->uncore.lock);
 	spin_lock_init(&dev_priv->mm.object_stat_lock);
 	mutex_init(&dev_priv->dpio_lock);
@@ -1639,8 +1645,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 			goto out_gem_unload;
 	}
 
-	if (HAS_POWER_WELL(dev))
-		intel_power_domains_init(dev);
+	intel_power_domains_init(dev);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		ret = i915_load_modeset_init(dev);
@@ -1664,11 +1669,12 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (IS_GEN5(dev))
 		intel_gpu_ips_init(dev_priv);
 
+	intel_init_runtime_pm(dev_priv);
+
 	return 0;
 
 out_power_well:
-	if (HAS_POWER_WELL(dev))
-		intel_power_domains_remove(dev);
+	intel_power_domains_remove(dev);
 	drm_vblank_cleanup(dev);
 out_gem_unload:
 	if (dev_priv->mm.inactive_shrinker.scan_objects)
@@ -1679,6 +1685,7 @@ out_gem_unload:
 
 	intel_teardown_gmbus(dev);
 	intel_teardown_mchbar(dev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 	destroy_workqueue(dev_priv->wq);
 out_mtrrfree:
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
@@ -1704,25 +1711,27 @@ int i915_driver_unload(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	ret = i915_gem_suspend(dev);
+	if (ret) {
+		DRM_ERROR("failed to idle hardware: %d\n", ret);
+		return ret;
+	}
+
+	intel_fini_runtime_pm(dev_priv);
+
 	intel_gpu_ips_teardown();
 
-	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_display_set_init_power(dev, true);
-		intel_power_domains_remove(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_display_set_init_power(dev, true);
+	intel_power_domains_remove(dev);
 
 	i915_teardown_sysfs(dev);
 
 	if (dev_priv->mm.inactive_shrinker.scan_objects)
 		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
 
-	ret = i915_gem_suspend(dev);
-	if (ret)
-		DRM_ERROR("failed to idle hardware: %d\n", ret);
-
 	io_mapping_free(dev_priv->gtt.mappable);
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
 
@@ -1777,7 +1786,6 @@ int i915_driver_unload(struct drm_device *dev)
 
 	list_del(&dev_priv->gtt.base.global_link);
 	WARN_ON(!list_empty(&dev_priv->vm_list));
-	drm_mm_takedown(&dev_priv->gtt.base.mm);
 
 	drm_vblank_cleanup(dev);
 
@@ -1910,6 +1918,7 @@ const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5b7b7e06cb3a..04f1f02c4019 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -59,7 +59,7 @@ MODULE_PARM_DESC(powersave,
 		"Enable powersavings, fbc, downclocking, etc. (default: true)");
 
 int i915_semaphores __read_mostly = -1;
-module_param_named(semaphores, i915_semaphores, int, 0600);
+module_param_named(semaphores, i915_semaphores, int, 0400);
 MODULE_PARM_DESC(semaphores,
 		"Use semaphores for inter-ring sync (default: -1 (use per-chip defaults))");
 
@@ -114,7 +114,7 @@ MODULE_PARM_DESC(enable_hangcheck,
 		"(default: true)");
 
 int i915_enable_ppgtt __read_mostly = -1;
-module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0600);
+module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0400);
 MODULE_PARM_DESC(i915_enable_ppgtt,
 		"Enable PPGTT (default: true)");
 
@@ -155,7 +155,6 @@ MODULE_PARM_DESC(prefault_disable,
 		"Disable page prefaulting for pread/pwrite/reloc (default:false). For developers only.");
 
 static struct drm_driver driver;
-extern int intel_agp_enabled;
 
 static const struct intel_device_info intel_i830_info = {
 	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
@@ -173,6 +172,7 @@ static const struct intel_device_info intel_i85x_info = {
 	.gen = 2, .is_i85x = 1, .is_mobile = 1, .num_pipes = 2,
 	.cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
+	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 };
 
@@ -192,6 +192,7 @@ static const struct intel_device_info intel_i915gm_info = {
 	.cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.supports_tv = 1,
+	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 };
 static const struct intel_device_info intel_i945g_info = {
@@ -204,6 +205,7 @@ static const struct intel_device_info intel_i945gm_info = {
 	.has_hotplug = 1, .cursor_needs_physical = 1,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.supports_tv = 1,
+	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 };
 
@@ -265,6 +267,7 @@ static const struct intel_device_info intel_ironlake_m_info = {
 static const struct intel_device_info intel_sandybridge_d_info = {
 	.gen = 6, .num_pipes = 2,
 	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_fbc = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
 	.has_llc = 1,
 };
@@ -280,6 +283,7 @@ static const struct intel_device_info intel_sandybridge_m_info = {
 #define GEN7_FEATURES  \
 	.gen = 7, .num_pipes = 3, \
 	.need_gfx_hws = 1, .has_hotplug = 1, \
+	.has_fbc = 1, \
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING, \
 	.has_llc = 1
 
@@ -292,7 +296,6 @@ static const struct intel_device_info intel_ivybridge_m_info = {
 	GEN7_FEATURES,
 	.is_ivybridge = 1,
 	.is_mobile = 1,
-	.has_fbc = 1,
 };
 
 static const struct intel_device_info intel_ivybridge_q_info = {
@@ -307,6 +310,7 @@ static const struct intel_device_info intel_valleyview_m_info = {
 	.num_pipes = 2,
 	.is_valleyview = 1,
 	.display_mmio_offset = VLV_DISPLAY_BASE,
+	.has_fbc = 0, /* legal, last one wins */
 	.has_llc = 0, /* legal, last one wins */
 };
 
@@ -315,6 +319,7 @@ static const struct intel_device_info intel_valleyview_d_info = {
 	.num_pipes = 2,
 	.is_valleyview = 1,
 	.display_mmio_offset = VLV_DISPLAY_BASE,
+	.has_fbc = 0, /* legal, last one wins */
 	.has_llc = 0, /* legal, last one wins */
 };
 
@@ -332,12 +337,10 @@ static const struct intel_device_info intel_haswell_m_info = {
 	.is_mobile = 1,
 	.has_ddi = 1,
 	.has_fpga_dbg = 1,
-	.has_fbc = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 };
 
 static const struct intel_device_info intel_broadwell_d_info = {
-	.is_preliminary = 1,
 	.gen = 8, .num_pipes = 3,
 	.need_gfx_hws = 1, .has_hotplug = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
@@ -346,7 +349,6 @@ static const struct intel_device_info intel_broadwell_d_info = {
 };
 
 static const struct intel_device_info intel_broadwell_m_info = {
-	.is_preliminary = 1,
 	.gen = 8, .is_mobile = 1, .num_pipes = 3,
 	.need_gfx_hws = 1, .has_hotplug = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
@@ -476,12 +478,12 @@ check_next:
 bool i915_semaphore_is_enabled(struct drm_device *dev)
 {
 	if (INTEL_INFO(dev)->gen < 6)
-		return 0;
+		return false;
 
 	/* Until we get further testing... */
 	if (IS_GEN8(dev)) {
 		WARN_ON(!i915_preliminary_hw_support);
-		return 0;
+		return false;
 	}
 
 	if (i915_semaphores >= 0)
@@ -493,7 +495,7 @@ bool i915_semaphore_is_enabled(struct drm_device *dev)
 		return false;
 #endif
 
-	return 1;
+	return true;
 }
 
 static int i915_drm_freeze(struct drm_device *dev)
@@ -501,6 +503,8 @@ 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);
+
 	/* ignore lid events during suspend */
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_SUSPENDED;
@@ -688,6 +692,8 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
+
+	intel_runtime_pm_put(dev_priv);
 	return error;
 }
 
@@ -762,14 +768,14 @@ int i915_reset(struct drm_device *dev)
 		DRM_INFO("Simulated gpu hang, resetting stop_rings\n");
 		dev_priv->gpu_error.stop_rings = 0;
 		if (ret == -ENODEV) {
-			DRM_ERROR("Reset not implemented, but ignoring "
-				  "error for simulated gpu hangs\n");
+			DRM_INFO("Reset not implemented, but ignoring "
+				 "error for simulated gpu hangs\n");
 			ret = 0;
 		}
 	}
 
 	if (ret) {
-		DRM_ERROR("Failed to reset chip.\n");
+		DRM_ERROR("Failed to reset chip: %i\n", ret);
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
 	}
@@ -790,12 +796,9 @@ int i915_reset(struct drm_device *dev)
 	 */
 	if (drm_core_check_feature(dev, DRIVER_MODESET) ||
 			!dev_priv->ums.mm_suspended) {
-		bool hw_contexts_disabled = dev_priv->hw_contexts_disabled;
 		dev_priv->ums.mm_suspended = 0;
 
 		ret = i915_gem_init_hw(dev);
-		if (!hw_contexts_disabled && dev_priv->hw_contexts_disabled)
-			DRM_ERROR("HW contexts didn't survive reset\n");
 		mutex_unlock(&dev->struct_mutex);
 		if (ret) {
 			DRM_ERROR("Failed hw init on reset %d\n", ret);
@@ -831,17 +834,7 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (PCI_FUNC(pdev->devfn))
 		return -ENODEV;
 
-	/* We've managed to ship a kms-enabled ddx that shipped with an XvMC
-	 * implementation for gen3 (and only gen3) that used legacy drm maps
-	 * (gasp!) to share buffers between X and the client. Hence we need to
-	 * keep around the fake agp stuff for gen3, even when kms is enabled. */
-	if (intel_info->gen != 3) {
-		driver.driver_features &=
-			~(DRIVER_USE_AGP | DRIVER_REQUIRE_AGP);
-	} else if (!intel_agp_enabled) {
-		DRM_ERROR("drm/i915 can't work without intel_agp module!\n");
-		return -ENODEV;
-	}
+	driver.driver_features &= ~(DRIVER_USE_AGP);
 
 	return drm_get_pci_dev(pdev, ent, &driver);
 }
@@ -915,6 +908,49 @@ static int i915_pm_poweroff(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
+static int i915_runtime_suspend(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WARN_ON(!HAS_RUNTIME_PM(dev));
+
+	DRM_DEBUG_KMS("Suspending device\n");
+
+	i915_gem_release_all_mmaps(dev_priv);
+
+	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
+	dev_priv->pm.suspended = true;
+
+	/*
+	 * current versions of firmware which depend on this opregion
+	 * notification have repurposed the D1 definition to mean
+	 * "runtime suspended" vs. what you would normally expect (D3)
+	 * to distinguish it from notifications that might be sent
+	 * via the suspend path.
+	 */
+	intel_opregion_notify_adapter(dev, PCI_D1);
+
+	return 0;
+}
+
+static int i915_runtime_resume(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WARN_ON(!HAS_RUNTIME_PM(dev));
+
+	DRM_DEBUG_KMS("Resuming device\n");
+
+	intel_opregion_notify_adapter(dev, PCI_D0);
+	dev_priv->pm.suspended = false;
+
+	return 0;
+}
+
 static const struct dev_pm_ops i915_pm_ops = {
 	.suspend = i915_pm_suspend,
 	.resume = i915_pm_resume,
@@ -922,6 +958,8 @@ static const struct dev_pm_ops i915_pm_ops = {
 	.thaw = i915_pm_thaw,
 	.poweroff = i915_pm_poweroff,
 	.restore = i915_pm_resume,
+	.runtime_suspend = i915_runtime_suspend,
+	.runtime_resume = i915_runtime_resume,
 };
 
 static const struct vm_operations_struct i915_gem_vm_ops = {
@@ -949,7 +987,7 @@ static struct drm_driver driver = {
 	 * deal with them for Intel hardware.
 	 */
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
+	    DRIVER_USE_AGP |
 	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME |
 	    DRIVER_RENDER,
 	.load = i915_driver_load,
@@ -1024,14 +1062,24 @@ static int __init i915_init(void)
 		driver.driver_features &= ~DRIVER_MODESET;
 #endif
 
-	if (!(driver.driver_features & DRIVER_MODESET))
+	if (!(driver.driver_features & DRIVER_MODESET)) {
 		driver.get_vblank_timestamp = NULL;
+#ifndef CONFIG_DRM_I915_UMS
+		/* Silently fail loading to not upset userspace. */
+		return 0;
+#endif
+	}
 
 	return drm_pci_init(&driver, &i915_pci_driver);
 }
 
 static void __exit i915_exit(void)
 {
+#ifndef CONFIG_DRM_I915_UMS
+	if (!(driver.driver_features & DRIVER_MODESET))
+		return; /* Never loaded a driver. */
+#endif
+
 	drm_pci_exit(&driver, &i915_pci_driver);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1caa5e34fbe3..4a2bf8e3f739 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -89,6 +89,18 @@ enum port {
 };
 #define port_name(p) ((p) + 'A')
 
+#define I915_NUM_PHYS_VLV 1
+
+enum dpio_channel {
+	DPIO_CH0,
+	DPIO_CH1
+};
+
+enum dpio_phy {
+	DPIO_PHY0,
+	DPIO_PHY1
+};
+
 enum intel_display_power_domain {
 	POWER_DOMAIN_PIPE_A,
 	POWER_DOMAIN_PIPE_B,
@@ -101,6 +113,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_TRANSCODER_C,
 	POWER_DOMAIN_TRANSCODER_EDP,
 	POWER_DOMAIN_VGA,
+	POWER_DOMAIN_AUDIO,
 	POWER_DOMAIN_INIT,
 
 	POWER_DOMAIN_NUM,
@@ -310,13 +323,14 @@ struct drm_i915_error_state {
 	u32 instps[I915_NUM_RINGS];
 	u32 extra_instdone[I915_NUM_INSTDONE_REG];
 	u32 seqno[I915_NUM_RINGS];
-	u64 bbaddr;
+	u64 bbaddr[I915_NUM_RINGS];
 	u32 fault_reg[I915_NUM_RINGS];
 	u32 done_reg;
 	u32 faddr[I915_NUM_RINGS];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
 	struct drm_i915_error_ring {
+		bool valid;
 		struct drm_i915_error_object {
 			int page_count;
 			u32 gtt_offset;
@@ -351,6 +365,7 @@ struct drm_i915_error_state {
 	enum intel_ring_hangcheck_action hangcheck_action[I915_NUM_RINGS];
 };
 
+struct intel_connector;
 struct intel_crtc_config;
 struct intel_crtc;
 struct intel_limit;
@@ -358,7 +373,7 @@ struct dpll;
 
 struct drm_i915_display_funcs {
 	bool (*fbc_enabled)(struct drm_device *dev);
-	void (*enable_fbc)(struct drm_crtc *crtc, unsigned long interval);
+	void (*enable_fbc)(struct drm_crtc *crtc);
 	void (*disable_fbc)(struct drm_device *dev);
 	int (*get_display_clock_speed)(struct drm_device *dev);
 	int (*get_fifo_size)(struct drm_device *dev, int plane);
@@ -413,11 +428,20 @@ struct drm_i915_display_funcs {
 	/* render clock increase/decrease */
 	/* display clock increase/decrease */
 	/* pll clock increase/decrease */
+
+	int (*setup_backlight)(struct intel_connector *connector);
+	uint32_t (*get_backlight)(struct intel_connector *connector);
+	void (*set_backlight)(struct intel_connector *connector,
+			      uint32_t level);
+	void (*disable_backlight)(struct intel_connector *connector);
+	void (*enable_backlight)(struct intel_connector *connector);
 };
 
 struct intel_uncore_funcs {
-	void (*force_wake_get)(struct drm_i915_private *dev_priv);
-	void (*force_wake_put)(struct drm_i915_private *dev_priv);
+	void (*force_wake_get)(struct drm_i915_private *dev_priv,
+							int fw_engine);
+	void (*force_wake_put)(struct drm_i915_private *dev_priv,
+							int fw_engine);
 
 	uint8_t  (*mmio_readb)(struct drm_i915_private *dev_priv, off_t offset, bool trace);
 	uint16_t (*mmio_readw)(struct drm_i915_private *dev_priv, off_t offset, bool trace);
@@ -442,6 +466,9 @@ struct intel_uncore {
 	unsigned fifo_count;
 	unsigned forcewake_count;
 
+	unsigned fw_rendercount;
+	unsigned fw_mediacount;
+
 	struct delayed_work force_wake_work;
 };
 
@@ -669,7 +696,6 @@ struct i915_fbc {
 		struct delayed_work work;
 		struct drm_crtc *crtc;
 		struct drm_framebuffer *fb;
-		int interval;
 	} *fbc_work;
 
 	enum no_fbc_reason {
@@ -708,7 +734,6 @@ enum intel_sbi_destination {
 #define QUIRK_PIPEA_FORCE (1<<0)
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
 #define QUIRK_INVERT_BRIGHTNESS (1<<2)
-#define QUIRK_NO_PCH_PWM_ENABLE (1<<3)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -761,8 +786,6 @@ struct i915_suspend_saved_registers {
 	u32 saveBLC_PWM_CTL;
 	u32 saveBLC_PWM_CTL2;
 	u32 saveBLC_HIST_CTL_B;
-	u32 saveBLC_PWM_CTL_B;
-	u32 saveBLC_PWM_CTL2_B;
 	u32 saveBLC_CPU_PWM_CTL;
 	u32 saveBLC_CPU_PWM_CTL2;
 	u32 saveFPB0;
@@ -932,21 +955,29 @@ struct intel_ilk_power_mgmt {
 
 /* Power well structure for haswell */
 struct i915_power_well {
+	const char *name;
+	bool always_on;
 	/* power well enable/disable usage count */
 	int count;
+	unsigned long domains;
+	void *data;
+	void (*set)(struct drm_device *dev, struct i915_power_well *power_well,
+		    bool enable);
+	bool (*is_enabled)(struct drm_device *dev,
+			   struct i915_power_well *power_well);
 };
 
-#define I915_MAX_POWER_WELLS 1
-
 struct i915_power_domains {
 	/*
 	 * Power wells needed for initialization at driver init and suspend
 	 * time are on. They are kept on until after the first modeset.
 	 */
 	bool init_power_on;
+	int power_well_count;
 
 	struct mutex lock;
-	struct i915_power_well power_wells[I915_MAX_POWER_WELLS];
+	int domain_use_count[POWER_DOMAIN_NUM];
+	struct i915_power_well *power_wells;
 };
 
 struct i915_dri1_state {
@@ -1077,34 +1108,30 @@ struct i915_gpu_error {
 	unsigned long missed_irq_rings;
 
 	/**
-	 * State variable and reset counter controlling the reset flow
+	 * State variable controlling the reset flow and count
 	 *
-	 * Upper bits are for the reset counter.  This counter is used by the
-	 * wait_seqno code to race-free noticed that a reset event happened and
-	 * that it needs to restart the entire ioctl (since most likely the
-	 * seqno it waited for won't ever signal anytime soon).
+	 * This is a counter which gets incremented when reset is triggered,
+	 * and again when reset has been handled. So odd values (lowest bit set)
+	 * means that reset is in progress and even values that
+	 * (reset_counter >> 1):th reset was successfully completed.
+	 *
+	 * If reset is not completed succesfully, the I915_WEDGE bit is
+	 * set meaning that hardware is terminally sour and there is no
+	 * recovery. All waiters on the reset_queue will be woken when
+	 * that happens.
+	 *
+	 * This counter is used by the wait_seqno code to notice that reset
+	 * event happened and it needs to restart the entire ioctl (since most
+	 * likely the seqno it waited for won't ever signal anytime soon).
 	 *
 	 * This is important for lock-free wait paths, where no contended lock
 	 * naturally enforces the correct ordering between the bail-out of the
 	 * waiter and the gpu reset work code.
-	 *
-	 * Lowest bit controls the reset state machine: Set means a reset is in
-	 * progress. This state will (presuming we don't have any bugs) decay
-	 * into either unset (successful reset) or the special WEDGED value (hw
-	 * terminally sour). All waiters on the reset_queue will be woken when
-	 * that happens.
 	 */
 	atomic_t reset_counter;
 
-	/**
-	 * Special values/flags for reset_counter
-	 *
-	 * Note that the code relies on
-	 * 	I915_WEDGED & I915_RESET_IN_PROGRESS_FLAG
-	 * being true.
-	 */
 #define I915_RESET_IN_PROGRESS_FLAG	1
-#define I915_WEDGED			0xffffffff
+#define I915_WEDGED			(1 << 31)
 
 	/**
 	 * Waitqueue to signal when the reset has completed. Used by clients
@@ -1158,6 +1185,11 @@ struct intel_vbt_data {
 	int edp_bpp;
 	struct edp_power_seq edp_pps;
 
+	struct {
+		u16 pwm_freq_hz;
+		bool active_low_pwm;
+	} backlight;
+
 	/* MIPI DSI */
 	struct {
 		u16 panel_id;
@@ -1184,7 +1216,7 @@ struct intel_wm_level {
 	uint32_t fbc_val;
 };
 
-struct hsw_wm_values {
+struct ilk_wm_values {
 	uint32_t wm_pipe[3];
 	uint32_t wm_lp[3];
 	uint32_t wm_lp_spr[3];
@@ -1262,6 +1294,10 @@ struct i915_package_c8 {
 	} regsave;
 };
 
+struct i915_runtime_pm {
+	bool suspended;
+};
+
 enum intel_pipe_crc_source {
 	INTEL_PIPE_CRC_SOURCE_NONE,
 	INTEL_PIPE_CRC_SOURCE_PLANE1,
@@ -1366,15 +1402,9 @@ typedef struct drm_i915_private {
 
 	/* overlay */
 	struct intel_overlay *overlay;
-	unsigned int sprite_scaling_enabled;
 
-	/* backlight */
-	struct {
-		int level;
-		bool enabled;
-		spinlock_t lock; /* bl registers and the above bl fields */
-		struct backlight_device *device;
-	} backlight;
+	/* backlight registers and fields in struct intel_panel */
+	spinlock_t backlight_lock;
 
 	/* LVDS info */
 	bool no_aux_handshake;
@@ -1426,6 +1456,7 @@ typedef struct drm_i915_private {
 	int num_shared_dpll;
 	struct intel_shared_dpll shared_dplls[I915_NUM_PLLS];
 	struct intel_ddi_plls ddi_plls;
+	int dpio_phy_iosf_port[I915_NUM_PHYS_VLV];
 
 	/* Reclocking support */
 	bool render_reclock_avail;
@@ -1470,7 +1501,6 @@ typedef struct drm_i915_private {
 	struct drm_property *broadcast_rgb_property;
 	struct drm_property *force_audio_property;
 
-	bool hw_contexts_disabled;
 	uint32_t hw_context_size;
 	struct list_head context_list;
 
@@ -1492,11 +1522,13 @@ typedef struct drm_i915_private {
 		uint16_t cur_latency[5];
 
 		/* current hardware state */
-		struct hsw_wm_values hw;
+		struct ilk_wm_values hw;
 	} wm;
 
 	struct i915_package_c8 pc8;
 
+	struct i915_runtime_pm pm;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
@@ -1813,15 +1845,15 @@ struct drm_i915_file_private {
 
 #define HAS_FW_BLC(dev) (INTEL_INFO(dev)->gen > 2)
 #define HAS_PIPE_CXSR(dev) (INTEL_INFO(dev)->has_pipe_cxsr)
-#define I915_HAS_FBC(dev) (INTEL_INFO(dev)->has_fbc)
+#define HAS_FBC(dev) (INTEL_INFO(dev)->has_fbc)
 
 #define HAS_IPS(dev)		(IS_ULT(dev) || IS_BROADWELL(dev))
 
 #define HAS_DDI(dev)		(INTEL_INFO(dev)->has_ddi)
-#define HAS_POWER_WELL(dev)	(IS_HASWELL(dev) || IS_BROADWELL(dev))
 #define HAS_FPGA_DBG_UNCLAIMED(dev)	(INTEL_INFO(dev)->has_fpga_dbg)
 #define HAS_PSR(dev)		(IS_HASWELL(dev) || IS_BROADWELL(dev))
 #define HAS_PC8(dev)		(IS_HASWELL(dev)) /* XXX HSW:ULX */
+#define HAS_RUNTIME_PM(dev)	(IS_HASWELL(dev))
 
 #define INTEL_PCH_DEVICE_ID_MASK		0xff00
 #define INTEL_PCH_IBX_DEVICE_ID_TYPE		0x3b00
@@ -1911,7 +1943,6 @@ 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_init(struct drm_device *dev);
-extern void intel_uncore_clear_errors(struct drm_device *dev);
 extern void intel_uncore_check_errors(struct drm_device *dev);
 extern void intel_uncore_fini(struct drm_device *dev);
 
@@ -1987,6 +2018,7 @@ void i915_gem_object_unpin(struct drm_i915_gem_object *obj);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
 int __must_check i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj);
 int i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
+void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
 void i915_gem_lastclose(struct drm_device *dev);
 
@@ -2063,12 +2095,17 @@ int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
 {
 	return unlikely(atomic_read(&error->reset_counter)
-			& I915_RESET_IN_PROGRESS_FLAG);
+			& (I915_RESET_IN_PROGRESS_FLAG | I915_WEDGED));
 }
 
 static inline bool i915_terminally_wedged(struct i915_gpu_error *error)
 {
-	return atomic_read(&error->reset_counter) == I915_WEDGED;
+	return atomic_read(&error->reset_counter) & I915_WEDGED;
+}
+
+static inline u32 i915_reset_count(struct i915_gpu_error *error)
+{
+	return ((atomic_read(&error->reset_counter) & ~I915_WEDGED) + 1) / 2;
 }
 
 void i915_gem_reset(struct drm_device *dev);
@@ -2180,7 +2217,7 @@ i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
 }
 
 /* i915_gem_context.c */
-void i915_gem_context_init(struct drm_device *dev);
+int __must_check i915_gem_context_init(struct drm_device *dev);
 void i915_gem_context_fini(struct drm_device *dev);
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
 int i915_switch_context(struct intel_ring_buffer *ring,
@@ -2399,6 +2436,8 @@ extern int intel_enable_rc6(const struct drm_device *dev);
 extern bool i915_semaphore_is_enabled(struct drm_device *dev);
 int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
+int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file);
 
 /* overlay */
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
@@ -2414,8 +2453,8 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
  * must be set to prevent GT core from power down and stale values being
  * returned.
  */
-void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
-void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine);
+void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val);
@@ -2430,6 +2469,8 @@ u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
+u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg);
+void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg);
@@ -2438,9 +2479,30 @@ u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
 		   enum intel_sbi_destination destination);
 void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 		     enum intel_sbi_destination destination);
+u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg);
+void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
+
+int vlv_gpu_freq(struct drm_i915_private *dev_priv, int val);
+int vlv_freq_opcode(struct drm_i915_private *dev_priv, int val);
+
+void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine);
+void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
+
+#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
+	(((reg) >= 0x2000 && (reg) < 0x4000) ||\
+	((reg) >= 0x5000 && (reg) < 0x8000) ||\
+	((reg) >= 0xB000 && (reg) < 0x12000) ||\
+	((reg) >= 0x2E000 && (reg) < 0x30000))
+
+#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\
+	(((reg) >= 0x12000 && (reg) < 0x14000) ||\
+	((reg) >= 0x22000 && (reg) < 0x24000) ||\
+	((reg) >= 0x30000 && (reg) < 0x40000))
+
+#define FORCEWAKE_RENDER	(1 << 0)
+#define FORCEWAKE_MEDIA		(1 << 1)
+#define FORCEWAKE_ALL		(FORCEWAKE_RENDER | FORCEWAKE_MEDIA)
 
-int vlv_gpu_freq(int ddr_freq, int val);
-int vlv_freq_opcode(int ddr_freq, int val);
 
 #define I915_READ8(reg)		dev_priv->uncore.funcs.mmio_readb(dev_priv, (reg), true)
 #define I915_WRITE8(reg, val)	dev_priv->uncore.funcs.mmio_writeb(dev_priv, (reg), (val), true)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 76d3d1ab73c6..00c836154725 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1015,9 +1015,11 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 			struct drm_i915_file_private *file_priv)
 {
 	drm_i915_private_t *dev_priv = ring->dev->dev_private;
+	const bool irq_test_in_progress =
+		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
 	struct timespec before, now;
 	DEFINE_WAIT(wait);
-	long timeout_jiffies;
+	unsigned long timeout_expire;
 	int ret;
 
 	WARN(dev_priv->pc8.irqs_disabled, "IRQs disabled\n");
@@ -1025,7 +1027,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
 
-	timeout_jiffies = timeout ? timespec_to_jiffies_timeout(timeout) : 1;
+	timeout_expire = timeout ? jiffies + timespec_to_jiffies_timeout(timeout) : 0;
 
 	if (dev_priv->info->gen >= 6 && can_wait_boost(file_priv)) {
 		gen6_rps_boost(dev_priv);
@@ -1035,8 +1037,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 					 msecs_to_jiffies(100));
 	}
 
-	if (!(dev_priv->gpu_error.test_irq_rings & intel_ring_flag(ring)) &&
-	    WARN_ON(!ring->irq_get(ring)))
+	if (!irq_test_in_progress && WARN_ON(!ring->irq_get(ring)))
 		return -ENODEV;
 
 	/* Record current time in case interrupted by signal, or wedged */
@@ -1044,7 +1045,6 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	getrawmonotonic(&before);
 	for (;;) {
 		struct timer_list timer;
-		unsigned long expire;
 
 		prepare_to_wait(&ring->irq_queue, &wait,
 				interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
@@ -1070,23 +1070,22 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 			break;
 		}
 
-		if (timeout_jiffies <= 0) {
+		if (timeout && time_after_eq(jiffies, timeout_expire)) {
 			ret = -ETIME;
 			break;
 		}
 
 		timer.function = NULL;
 		if (timeout || missed_irq(dev_priv, ring)) {
+			unsigned long expire;
+
 			setup_timer_on_stack(&timer, fake_irq, (unsigned long)current);
-			expire = jiffies + (missed_irq(dev_priv, ring) ? 1: timeout_jiffies);
+			expire = missed_irq(dev_priv, ring) ? jiffies + 1 : timeout_expire;
 			mod_timer(&timer, expire);
 		}
 
 		io_schedule();
 
-		if (timeout)
-			timeout_jiffies = expire - jiffies;
-
 		if (timer.function) {
 			del_singleshot_timer_sync(&timer);
 			destroy_timer_on_stack(&timer);
@@ -1095,7 +1094,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	getrawmonotonic(&now);
 	trace_i915_gem_request_wait_end(ring, seqno);
 
-	ring->irq_put(ring);
+	if (!irq_test_in_progress)
+		ring->irq_put(ring);
 
 	finish_wait(&ring->irq_queue, &wait);
 
@@ -1380,6 +1380,8 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	int ret = 0;
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
 
+	intel_runtime_pm_get(dev_priv);
+
 	/* We don't use vmf->pgoff since that has the fake offset */
 	page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >>
 		PAGE_SHIFT;
@@ -1427,8 +1429,10 @@ out:
 		/* If this -EIO is due to a gpu hang, give the reset code a
 		 * chance to clean up the mess. Otherwise return the proper
 		 * SIGBUS. */
-		if (i915_terminally_wedged(&dev_priv->gpu_error))
-			return VM_FAULT_SIGBUS;
+		if (i915_terminally_wedged(&dev_priv->gpu_error)) {
+			ret = VM_FAULT_SIGBUS;
+			break;
+		}
 	case -EAGAIN:
 		/*
 		 * EAGAIN means the gpu is hung and we'll wait for the error
@@ -1443,15 +1447,38 @@ out:
 		 * EBUSY is ok: this just means that another thread
 		 * already did the job.
 		 */
-		return VM_FAULT_NOPAGE;
+		ret = VM_FAULT_NOPAGE;
+		break;
 	case -ENOMEM:
-		return VM_FAULT_OOM;
+		ret = VM_FAULT_OOM;
+		break;
 	case -ENOSPC:
-		return VM_FAULT_SIGBUS;
+		ret = VM_FAULT_SIGBUS;
+		break;
 	default:
 		WARN_ONCE(ret, "unhandled error in i915_gem_fault: %i\n", ret);
-		return VM_FAULT_SIGBUS;
+		ret = VM_FAULT_SIGBUS;
+		break;
 	}
+
+	intel_runtime_pm_put(dev_priv);
+	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);
 }
 
 /**
@@ -2303,7 +2330,7 @@ static void i915_set_reset_status(struct intel_ring_buffer *ring,
 
 	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",
+		DRM_DEBUG("%s hung %s bo (0x%lx ctx %d) at 0x%x\n",
 			  ring->name,
 			  inside ? "inside" : "flushing",
 			  offset,
@@ -2361,16 +2388,6 @@ static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
 static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 					struct intel_ring_buffer *ring)
 {
-	while (!list_empty(&ring->request_list)) {
-		struct drm_i915_gem_request *request;
-
-		request = list_first_entry(&ring->request_list,
-					   struct drm_i915_gem_request,
-					   list);
-
-		i915_gem_free_request(request);
-	}
-
 	while (!list_empty(&ring->active_list)) {
 		struct drm_i915_gem_object *obj;
 
@@ -2380,6 +2397,23 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 
 		i915_gem_object_move_to_inactive(obj);
 	}
+
+	/*
+	 * We must free the requests after all the corresponding objects have
+	 * been moved off active lists. Which is the same order as the normal
+	 * retire_requests function does. This is important if object hold
+	 * implicit references on things like e.g. ppgtt address spaces through
+	 * the request.
+	 */
+	while (!list_empty(&ring->request_list)) {
+		struct drm_i915_gem_request *request;
+
+		request = list_first_entry(&ring->request_list,
+					   struct drm_i915_gem_request,
+					   list);
+
+		i915_gem_free_request(request);
+	}
 }
 
 void i915_gem_restore_fences(struct drm_device *dev)
@@ -2760,7 +2794,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 		obj->has_aliasing_ppgtt_mapping = 0;
 	}
 	i915_gem_gtt_finish_object(obj);
-	i915_gem_object_unpin_pages(obj);
 
 	list_del(&vma->mm_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
@@ -2768,7 +2801,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 		obj->map_and_fenceable = true;
 
 	drm_mm_remove_node(&vma->node);
-
 	i915_gem_vma_destroy(vma);
 
 	/* Since the unbound list is global, only move to that list if
@@ -2776,6 +2808,12 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (list_empty(&obj->vma_list))
 		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 
+	/* And finally now the object is completely decoupled from this vma,
+	 * we can drop its hold on the backing storage and allow it to be
+	 * reaped by the shrinker.
+	 */
+	i915_gem_object_unpin_pages(obj);
+
 	return 0;
 }
 
@@ -3068,7 +3106,7 @@ i915_find_fence_reg(struct drm_device *dev)
 	}
 
 	if (avail == NULL)
-		return NULL;
+		goto deadlock;
 
 	/* None available, try to steal one or wait for a user to finish */
 	list_for_each_entry(reg, &dev_priv->mm.fence_list, lru_list) {
@@ -3078,7 +3116,12 @@ i915_find_fence_reg(struct drm_device *dev)
 		return reg;
 	}
 
-	return NULL;
+deadlock:
+	/* Wait for completion of pending flips which consume fences */
+	if (intel_has_pending_fb_unpin(dev))
+		return ERR_PTR(-EAGAIN);
+
+	return ERR_PTR(-EDEADLK);
 }
 
 /**
@@ -3123,8 +3166,8 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 		}
 	} else if (enable) {
 		reg = i915_find_fence_reg(dev);
-		if (reg == NULL)
-			return -EDEADLK;
+		if (IS_ERR(reg))
+			return PTR_ERR(reg);
 
 		if (reg->obj) {
 			struct drm_i915_gem_object *old = reg->obj;
@@ -4179,6 +4222,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct i915_vma *vma, *next;
 
+	intel_runtime_pm_get(dev_priv);
+
 	trace_i915_gem_object_destroy(obj);
 
 	if (obj->phys_obj)
@@ -4223,6 +4268,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 
 	kfree(obj->bit_17);
 	i915_gem_object_free(obj);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
@@ -4479,7 +4526,13 @@ i915_gem_init_hw(struct drm_device *dev)
 	 * XXX: There was some w/a described somewhere suggesting loading
 	 * contexts before PPGTT.
 	 */
-	i915_gem_context_init(dev);
+	ret = i915_gem_context_init(dev);
+	if (ret) {
+		i915_gem_cleanup_ringbuffer(dev);
+		DRM_ERROR("Context initialization failed %d\n", ret);
+		return ret;
+	}
+
 	if (dev_priv->mm.aliasing_ppgtt) {
 		ret = dev_priv->mm.aliasing_ppgtt->enable(dev);
 		if (ret) {
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b0f42b9ca037..e08acaba5402 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -247,36 +247,34 @@ err_destroy:
 	return ret;
 }
 
-void i915_gem_context_init(struct drm_device *dev)
+int i915_gem_context_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
 
-	if (!HAS_HW_CONTEXTS(dev)) {
-		dev_priv->hw_contexts_disabled = true;
-		DRM_DEBUG_DRIVER("Disabling HW Contexts; old hardware\n");
-		return;
-	}
+	if (!HAS_HW_CONTEXTS(dev))
+		return 0;
 
 	/* If called from reset, or thaw... we've been here already */
-	if (dev_priv->hw_contexts_disabled ||
-	    dev_priv->ring[RCS].default_context)
-		return;
+	if (dev_priv->ring[RCS].default_context)
+		return 0;
 
 	dev_priv->hw_context_size = round_up(get_context_size(dev), 4096);
 
 	if (dev_priv->hw_context_size > (1<<20)) {
-		dev_priv->hw_contexts_disabled = true;
 		DRM_DEBUG_DRIVER("Disabling HW Contexts; invalid size\n");
-		return;
+		return -E2BIG;
 	}
 
-	if (create_default_context(dev_priv)) {
-		dev_priv->hw_contexts_disabled = true;
-		DRM_DEBUG_DRIVER("Disabling HW Contexts; create failed\n");
-		return;
+	ret = create_default_context(dev_priv);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Disabling HW Contexts; create failed %d\n",
+				 ret);
+		return ret;
 	}
 
 	DRM_DEBUG_DRIVER("HW context support initialized\n");
+	return 0;
 }
 
 void i915_gem_context_fini(struct drm_device *dev)
@@ -284,7 +282,7 @@ void i915_gem_context_fini(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_context *dctx = dev_priv->ring[RCS].default_context;
 
-	if (dev_priv->hw_contexts_disabled)
+	if (!HAS_HW_CONTEXTS(dev))
 		return;
 
 	/* The only known way to stop the gpu from accessing the hw context is
@@ -327,16 +325,16 @@ i915_gem_context_get_hang_stats(struct drm_device *dev,
 				struct drm_file *file,
 				u32 id)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct i915_hw_context *ctx;
 
 	if (id == DEFAULT_CONTEXT_ID)
 		return &file_priv->hang_stats;
 
-	ctx = NULL;
-	if (!dev_priv->hw_contexts_disabled)
-		ctx = i915_gem_context_get(file->driver_priv, id);
+	if (!HAS_HW_CONTEXTS(dev))
+		return ERR_PTR(-ENOENT);
+
+	ctx = i915_gem_context_get(file->driver_priv, id);
 	if (ctx == NULL)
 		return ERR_PTR(-ENOENT);
 
@@ -502,8 +500,6 @@ static int do_switch(struct i915_hw_context *to)
  * @ring: ring for which we'll execute the context switch
  * @file_priv: file_priv associated with the context, may be NULL
  * @id: context id number
- * @seqno: sequence number by which the new context will be switched to
- * @flags:
  *
  * The context life cycle is simple. The context refcount is incremented and
  * decremented by 1 and create and destroy. If the context is in use by the GPU,
@@ -517,7 +513,7 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct i915_hw_context *to;
 
-	if (dev_priv->hw_contexts_disabled)
+	if (!HAS_HW_CONTEXTS(ring->dev))
 		return 0;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
@@ -542,7 +538,6 @@ int i915_switch_context(struct intel_ring_buffer *ring,
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_context_create *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct i915_hw_context *ctx;
@@ -551,7 +546,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	if (!(dev->driver->driver_features & DRIVER_GEM))
 		return -ENODEV;
 
-	if (dev_priv->hw_contexts_disabled)
+	if (!HAS_HW_CONTEXTS(dev))
 		return -ENODEV;
 
 	ret = i915_mutex_lock_interruptible(dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 8f3adc7d0dc8..2ca280f9ee53 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -27,8 +27,10 @@
  */
 
 #include <drm/drmP.h>
-#include "i915_drv.h"
 #include <drm/i915_drm.h>
+
+#include "i915_drv.h"
+#include "intel_drv.h"
 #include "i915_trace.h"
 
 static bool
@@ -53,6 +55,7 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 	struct list_head eviction_list, unwind_list;
 	struct i915_vma *vma;
 	int ret = 0;
+	int pass = 0;
 
 	trace_i915_gem_evict(dev, min_size, alignment, mappable);
 
@@ -119,14 +122,24 @@ none:
 	/* Can we unpin some objects such as idle hw contents,
 	 * or pending flips?
 	 */
-	ret = nonblocking ? -ENOSPC : i915_gpu_idle(dev);
-	if (ret)
-		return ret;
+	if (nonblocking)
+		return -ENOSPC;
 
 	/* Only idle the GPU and repeat the search once */
-	i915_gem_retire_requests(dev);
-	nonblocking = true;
-	goto search_again;
+	if (pass++ == 0) {
+		ret = i915_gpu_idle(dev);
+		if (ret)
+			return ret;
+
+		i915_gem_retire_requests(dev);
+		goto search_again;
+	}
+
+	/* If we still have pending pageflip completions, drop
+	 * back to userspace to give our workqueues time to
+	 * acquire our locks and unpin the old scanouts.
+	 */
+	return intel_has_pending_fb_unpin(dev) ? -EAGAIN : -ENOSPC;
 
 found:
 	/* drm_mm doesn't allow any other other operations while
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a3ba9a8cd687..d269ecf46e26 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -46,7 +46,7 @@ struct eb_vmas {
 };
 
 static struct eb_vmas *
-eb_create(struct drm_i915_gem_execbuffer2 *args, struct i915_address_space *vm)
+eb_create(struct drm_i915_gem_execbuffer2 *args)
 {
 	struct eb_vmas *eb = NULL;
 
@@ -252,7 +252,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
 	char *vaddr;
-	int ret = -EINVAL;
+	int ret;
 
 	ret = i915_gem_object_set_to_cpu_domain(obj, true);
 	if (ret)
@@ -287,7 +287,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t __iomem *reloc_entry;
 	void __iomem *reloc_page;
-	int ret = -EINVAL;
+	int ret;
 
 	ret = i915_gem_object_set_to_gtt_domain(obj, true);
 	if (ret)
@@ -335,7 +335,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	struct drm_i915_gem_object *target_i915_obj;
 	struct i915_vma *target_vma;
 	uint32_t target_offset;
-	int ret = -EINVAL;
+	int ret;
 
 	/* we've already hold a reference to all valid objects */
 	target_vma = eb_get_vma(eb, reloc->target_handle);
@@ -344,7 +344,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	target_i915_obj = target_vma->obj;
 	target_obj = &target_vma->obj->base;
 
-	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
+	target_offset = target_vma->node.start;
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -365,7 +365,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			  (int) reloc->offset,
 			  reloc->read_domains,
 			  reloc->write_domain);
-		return ret;
+		return -EINVAL;
 	}
 	if (unlikely((reloc->write_domain | reloc->read_domains)
 		     & ~I915_GEM_GPU_DOMAINS)) {
@@ -376,7 +376,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			  (int) reloc->offset,
 			  reloc->read_domains,
 			  reloc->write_domain);
-		return ret;
+		return -EINVAL;
 	}
 
 	target_obj->pending_read_domains |= reloc->read_domains;
@@ -396,14 +396,14 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			  obj, reloc->target_handle,
 			  (int) reloc->offset,
 			  (int) obj->base.size);
-		return ret;
+		return -EINVAL;
 	}
 	if (unlikely(reloc->offset & 3)) {
 		DRM_DEBUG("Relocation not 4-byte aligned: "
 			  "obj %p target %d offset %d.\n",
 			  obj, reloc->target_handle,
 			  (int) reloc->offset);
-		return ret;
+		return -EINVAL;
 	}
 
 	/* We can't wait for rendering with pagefaults disabled */
@@ -491,8 +491,7 @@ i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma,
 }
 
 static int
-i915_gem_execbuffer_relocate(struct eb_vmas *eb,
-			     struct i915_address_space *vm)
+i915_gem_execbuffer_relocate(struct eb_vmas *eb)
 {
 	struct i915_vma *vma;
 	int ret = 0;
@@ -901,6 +900,24 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 	return 0;
 }
 
+static int
+i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
+			  const u32 ctx_id)
+{
+	struct i915_ctx_hang_stats *hs;
+
+	hs = i915_gem_context_get_hang_stats(dev, file, ctx_id);
+	if (IS_ERR(hs))
+		return PTR_ERR(hs);
+
+	if (hs->banned) {
+		DRM_DEBUG("Context %u tried to submit while banned\n", ctx_id);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static void
 i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 				   struct intel_ring_buffer *ring)
@@ -980,8 +997,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *batch_obj;
 	struct drm_clip_rect *cliprects = NULL;
 	struct intel_ring_buffer *ring;
-	struct i915_ctx_hang_stats *hs;
-	u32 ctx_id = i915_execbuffer2_get_context_id(*args);
+	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
 	u32 exec_start, exec_len;
 	u32 mask, flags;
 	int ret, mode, i;
@@ -1108,6 +1124,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		}
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		goto pre_mutex_err;
@@ -1118,7 +1136,13 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		goto pre_mutex_err;
 	}
 
-	eb = eb_create(args, vm);
+	ret = i915_gem_validate_context(dev, file, ctx_id);
+	if (ret) {
+		mutex_unlock(&dev->struct_mutex);
+		goto pre_mutex_err;
+	}
+
+	eb = eb_create(args);
 	if (eb == NULL) {
 		mutex_unlock(&dev->struct_mutex);
 		ret = -ENOMEM;
@@ -1141,7 +1165,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	/* The objects are in their final locations, apply the relocations. */
 	if (need_relocs)
-		ret = i915_gem_execbuffer_relocate(eb, vm);
+		ret = i915_gem_execbuffer_relocate(eb);
 	if (ret) {
 		if (ret == -EFAULT) {
 			ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
@@ -1170,17 +1194,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret)
 		goto err;
 
-	hs = i915_gem_context_get_hang_stats(dev, file, ctx_id);
-	if (IS_ERR(hs)) {
-		ret = PTR_ERR(hs);
-		goto err;
-	}
-
-	if (hs->banned) {
-		ret = -EIO;
-		goto err;
-	}
-
 	ret = i915_switch_context(ring, file, ctx_id);
 	if (ret)
 		goto err;
@@ -1242,6 +1255,10 @@ err:
 
 pre_mutex_err:
 	kfree(cliprects);
+
+	/* intel_gpu_busy should also get a ref, so it will free when the device
+	 * is really idle. */
+	intel_runtime_pm_put(dev_priv);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3540569948db..40a2b36b276b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -240,10 +240,16 @@ static int gen8_ppgtt_enable(struct drm_device *dev)
 		for_each_ring(ring, dev_priv, j) {
 			ret = gen8_write_pdp(ring, i, addr);
 			if (ret)
-				return ret;
+				goto err_out;
 		}
 	}
 	return 0;
+
+err_out:
+	for_each_ring(ring, dev_priv, j)
+		I915_WRITE(RING_MODE_GEN7(ring),
+			   _MASKED_BIT_DISABLE(GFX_PPGTT_ENABLE));
+	return ret;
 }
 
 static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
@@ -293,23 +299,23 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 	unsigned act_pte = first_entry % GEN8_PTES_PER_PAGE;
 	struct sg_page_iter sg_iter;
 
-	pt_vaddr = kmap_atomic(&ppgtt->gen8_pt_pages[act_pt]);
+	pt_vaddr = NULL;
 	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
-		dma_addr_t page_addr;
+		if (pt_vaddr == NULL)
+			pt_vaddr = kmap_atomic(&ppgtt->gen8_pt_pages[act_pt]);
 
-		page_addr = sg_dma_address(sg_iter.sg) +
-				(sg_iter.sg_pgoffset << PAGE_SHIFT);
-		pt_vaddr[act_pte] = gen8_pte_encode(page_addr, cache_level,
-						    true);
+		pt_vaddr[act_pte] =
+			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
+					cache_level, true);
 		if (++act_pte == GEN8_PTES_PER_PAGE) {
 			kunmap_atomic(pt_vaddr);
+			pt_vaddr = NULL;
 			act_pt++;
-			pt_vaddr = kmap_atomic(&ppgtt->gen8_pt_pages[act_pt]);
 			act_pte = 0;
-
 		}
 	}
-	kunmap_atomic(pt_vaddr);
+	if (pt_vaddr)
+		kunmap_atomic(pt_vaddr);
 }
 
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
@@ -318,6 +324,8 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 		container_of(vm, struct i915_hw_ppgtt, base);
 	int i, j;
 
+	drm_mm_takedown(&vm->mm);
+
 	for (i = 0; i < ppgtt->num_pd_pages ; i++) {
 		if (ppgtt->pd_dma_addr[i]) {
 			pci_unmap_page(ppgtt->base.dev->pdev,
@@ -381,6 +389,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+	ppgtt->base.start = 0;
+	ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE;
 
 	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
 
@@ -573,21 +583,23 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	struct sg_page_iter sg_iter;
 
-	pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
+	pt_vaddr = NULL;
 	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
-		dma_addr_t page_addr;
+		if (pt_vaddr == NULL)
+			pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
 
-		page_addr = sg_page_iter_dma_address(&sg_iter);
-		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level, true);
+		pt_vaddr[act_pte] =
+			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
+				       cache_level, true);
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
+			pt_vaddr = NULL;
 			act_pt++;
-			pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);
 			act_pte = 0;
-
 		}
 	}
-	kunmap_atomic(pt_vaddr);
+	if (pt_vaddr)
+		kunmap_atomic(pt_vaddr);
 }
 
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
@@ -632,6 +644,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
+	ppgtt->base.start = 0;
+	ppgtt->base.total = GEN6_PPGTT_PD_ENTRIES * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
 	ppgtt->pt_pages = kcalloc(ppgtt->num_pd_entries, sizeof(struct page *),
 				  GFP_KERNEL);
 	if (!ppgtt->pt_pages)
@@ -1124,7 +1138,6 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 		if (ret)
 			DRM_DEBUG_KMS("Reservation failed\n");
 		obj->has_global_gtt_mapping = 1;
-		list_add(&vma->vma_link, &obj->vma_list);
 	}
 
 	dev_priv->gtt.base.start = start;
@@ -1400,6 +1413,8 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 {
 
 	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
+
+	drm_mm_takedown(&vm->mm);
 	iounmap(gtt->gsm);
 	teardown_scratch_page(vm->dev);
 }
@@ -1425,6 +1440,9 @@ static int i915_gmch_probe(struct drm_device *dev,
 	dev_priv->gtt.base.clear_range = i915_ggtt_clear_range;
 	dev_priv->gtt.base.insert_entries = i915_ggtt_insert_entries;
 
+	if (unlikely(dev_priv->gtt.do_idle_maps))
+		DRM_INFO("applying Ironlake quirks for intel_iommu\n");
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index d284d892ed94..1a24e84f2315 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -250,7 +250,7 @@ i915_pages_create_for_stolen(struct drm_device *dev,
 	}
 
 	sg = st->sgl;
-	sg->offset = offset;
+	sg->offset = 0;
 	sg->length = size;
 
 	sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset;
@@ -420,6 +420,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&vma->mm_list, &ggtt->inactive_list);
+	i915_gem_object_pin_pages(obj);
 
 	return obj;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 79dcb8f896c6..d7fd2fd2f0a5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -239,6 +239,9 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 				  unsigned ring)
 {
 	BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
+	if (!error->ring[ring].valid)
+		return;
+
 	err_printf(m, "%s command stream:\n", ring_str(ring));
 	err_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
 	err_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
@@ -247,12 +250,11 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
 	err_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
 	err_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
-	if (ring == RCS && INTEL_INFO(dev)->gen >= 4)
-		err_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
-	if (INTEL_INFO(dev)->gen >= 4)
+	if (INTEL_INFO(dev)->gen >= 4) {
+		err_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr[ring]);
 		err_printf(m, "  BB_STATE: 0x%08x\n", error->bbstate[ring]);
-	if (INTEL_INFO(dev)->gen >= 4)
 		err_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
+	}
 	err_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
 	err_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
 	if (INTEL_INFO(dev)->gen >= 6) {
@@ -294,7 +296,6 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	struct drm_device *dev = error_priv->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error = error_priv->error;
-	struct intel_ring_buffer *ring;
 	int i, j, page, offset, elt;
 
 	if (!error) {
@@ -329,7 +330,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	if (INTEL_INFO(dev)->gen == 7)
 		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
 
-	for_each_ring(ring, dev_priv, i)
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++)
 		i915_ring_error_state(m, dev, error, i);
 
 	if (error->active_bo)
@@ -386,8 +387,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
-		obj = error->ring[i].ctx;
-		if (obj) {
+		if ((obj = error->ring[i].ctx)) {
 			err_printf(m, "%s --- HW Context = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
@@ -668,7 +668,8 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			return NULL;
 
 		obj = ring->scratch.obj;
-		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+		if (obj != NULL &&
+		    acthd >= i915_gem_obj_ggtt_offset(obj) &&
 		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
 			return i915_error_object_create(dev_priv, obj);
 	}
@@ -725,8 +726,9 @@ static void i915_record_ring_state(struct drm_device *dev,
 		error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base));
 		error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base));
 		error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base));
-		if (ring->id == RCS)
-			error->bbaddr = I915_READ64(BB_ADDR);
+		error->bbaddr[ring->id] = I915_READ(RING_BBADDR(ring->mmio_base));
+		if (INTEL_INFO(dev)->gen >= 8)
+			error->bbaddr[ring->id] |= (u64) I915_READ(RING_BBADDR_UDW(ring->mmio_base)) << 32;
 		error->bbstate[ring->id] = I915_READ(RING_BBSTATE(ring->mmio_base));
 	} else {
 		error->faddr[ring->id] = I915_READ(DMA_FADD_I8XX);
@@ -775,11 +777,17 @@ static void i915_gem_record_rings(struct drm_device *dev,
 				  struct drm_i915_error_state *error)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_request *request;
 	int i, count;
 
-	for_each_ring(ring, dev_priv, i) {
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct intel_ring_buffer *ring = &dev_priv->ring[i];
+
+		if (ring->dev == NULL)
+			continue;
+
+		error->ring[i].valid = true;
+
 		i915_record_ring_state(dev, error, ring);
 
 		error->ring[i].batchbuffer =
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f13d5edc39d5..17d8fcb1b6f7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -62,7 +62,7 @@ static const u32 hpd_mask_i915[] = {
 	[HPD_PORT_D] = PORTD_HOTPLUG_INT_EN
 };
 
-static const u32 hpd_status_gen4[] = {
+static const u32 hpd_status_g4x[] = {
 	[HPD_CRT] = CRT_HOTPLUG_INT_STATUS,
 	[HPD_SDVO_B] = SDVOB_HOTPLUG_INT_STATUS_G4X,
 	[HPD_SDVO_C] = SDVOC_HOTPLUG_INT_STATUS_G4X,
@@ -600,7 +600,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe)
 	 * Cook up a vblank counter by also checking the pixel
 	 * counter against vblank start.
 	 */
-	return ((high1 << 8) | low) + (pixel >= vbl_start);
+	return (((high1 << 8) | low) + (pixel >= vbl_start)) & 0xffffff;
 }
 
 static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe)
@@ -621,36 +621,15 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe)
 #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
 #define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__))
 
-static bool intel_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
+static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t status;
-	int reg;
 
-	if (IS_VALLEYVIEW(dev)) {
-		status = pipe == PIPE_A ?
-			I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT :
-			I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
-		reg = VLV_ISR;
-	} else if (IS_GEN2(dev)) {
-		status = pipe == PIPE_A ?
-			I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT :
-			I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
-		reg = ISR;
-	} else if (INTEL_INFO(dev)->gen < 5) {
-		status = pipe == PIPE_A ?
-			I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT :
-			I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
-		reg = ISR;
-	} else if (INTEL_INFO(dev)->gen < 7) {
+	if (INTEL_INFO(dev)->gen < 7) {
 		status = pipe == PIPE_A ?
 			DE_PIPEA_VBLANK :
 			DE_PIPEB_VBLANK;
-
-		reg = DEISR;
 	} else {
 		switch (pipe) {
 		default:
@@ -664,18 +643,14 @@ static bool intel_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
 			status = DE_PIPEC_VBLANK_IVB;
 			break;
 		}
-
-		reg = DEISR;
 	}
 
-	if (IS_GEN2(dev))
-		return __raw_i915_read16(dev_priv, reg) & status;
-	else
-		return __raw_i915_read32(dev_priv, reg) & status;
+	return __raw_i915_read32(dev_priv, DEISR) & status;
 }
 
 static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
-			     int *vpos, int *hpos, ktime_t *stime, ktime_t *etime)
+				    unsigned int flags, int *vpos, int *hpos,
+				    ktime_t *stime, ktime_t *etime)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
@@ -698,6 +673,12 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	vbl_start = mode->crtc_vblank_start;
 	vbl_end = mode->crtc_vblank_end;
 
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		vbl_start = DIV_ROUND_UP(vbl_start, 2);
+		vbl_end /= 2;
+		vtotal /= 2;
+	}
+
 	ret |= DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE;
 
 	/*
@@ -722,17 +703,42 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 		else
 			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
-		/*
-		 * The scanline counter increments at the leading edge
-		 * of hsync, ie. it completely misses the active portion
-		 * of the line. Fix up the counter at both edges of vblank
-		 * to get a more accurate picture whether we're in vblank
-		 * or not.
-		 */
-		in_vbl = intel_pipe_in_vblank_locked(dev, pipe);
-		if ((in_vbl && position == vbl_start - 1) ||
-		    (!in_vbl && position == vbl_end - 1))
-			position = (position + 1) % vtotal;
+		if (HAS_PCH_SPLIT(dev)) {
+			/*
+			 * The scanline counter increments at the leading edge
+			 * of hsync, ie. it completely misses the active portion
+			 * of the line. Fix up the counter at both edges of vblank
+			 * to get a more accurate picture whether we're in vblank
+			 * or not.
+			 */
+			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
+			if ((in_vbl && position == vbl_start - 1) ||
+			    (!in_vbl && position == vbl_end - 1))
+				position = (position + 1) % vtotal;
+		} else {
+			/*
+			 * ISR vblank status bits don't work the way we'd want
+			 * them to work on non-PCH platforms (for
+			 * ilk_pipe_in_vblank_locked()), and there doesn't
+			 * appear any other way to determine if we're currently
+			 * in vblank.
+			 *
+			 * Instead let's assume that we're already in vblank if
+			 * we got called from the vblank interrupt and the
+			 * scanline counter value indicates that we're on the
+			 * line just prior to vblank start. This should result
+			 * in the correct answer, unless the vblank interrupt
+			 * delivery really got delayed for almost exactly one
+			 * full frame/field.
+			 */
+			if (flags & DRM_CALLED_FROM_VBLIRQ &&
+			    position == vbl_start - 1) {
+				position = (position + 1) % vtotal;
+
+				/* Signal this correction as "applied". */
+				ret |= 0x8;
+			}
+		}
 	} else {
 		/* Have access to pixelcount since start of frame.
 		 * We can split this into vertical and horizontal
@@ -809,7 +815,8 @@ static int i915_get_vblank_timestamp(struct drm_device *dev, int pipe,
 	/* Helper routine in DRM core does all the work: */
 	return drm_calc_vbltimestamp_from_scanoutpos(dev, pipe, max_error,
 						     vblank_time, flags,
-						     crtc);
+						     crtc,
+						     &to_intel_crtc(crtc)->config.adjusted_mode);
 }
 
 static bool intel_hpd_irq_event(struct drm_device *dev,
@@ -1015,10 +1022,8 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	/* sysfs frequency interfaces may have snuck in while servicing the
 	 * interrupt
 	 */
-	if (new_delay < (int)dev_priv->rps.min_delay)
-		new_delay = dev_priv->rps.min_delay;
-	if (new_delay > (int)dev_priv->rps.max_delay)
-		new_delay = dev_priv->rps.max_delay;
+	new_delay = clamp_t(int, new_delay,
+			    dev_priv->rps.min_delay, dev_priv->rps.max_delay);
 	dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_delay;
 
 	if (IS_VALLEYVIEW(dev_priv->dev))
@@ -1235,9 +1240,10 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 	spin_lock(&dev_priv->irq_lock);
 	for (i = 1; i < HPD_NUM_PINS; i++) {
 
-		WARN(((hpd[i] & hotplug_trigger) &&
-		      dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED),
-		     "Received HPD interrupt although disabled\n");
+		WARN_ONCE(hpd[i] & hotplug_trigger &&
+			  dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED,
+			  "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
+			  hotplug_trigger, i, hpd[i]);
 
 		if (!(hpd[i] & hotplug_trigger) ||
 		    dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED)
@@ -1474,6 +1480,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 
 			intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
 
+			if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
+				dp_aux_irq_handler(dev);
+
 			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
 			I915_READ(PORT_HOTPLUG_STAT);
 		}
@@ -1993,7 +2002,7 @@ static void i915_error_work_func(struct work_struct *work)
 			kobject_uevent_env(&dev->primary->kdev->kobj,
 					   KOBJ_CHANGE, reset_done_event);
 		} else {
-			atomic_set(&error->reset_counter, I915_WEDGED);
+			atomic_set_mask(I915_WEDGED, &error->reset_counter);
 		}
 
 		/*
@@ -3140,10 +3149,10 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
  * Returns true when a page flip has completed.
  */
 static bool i8xx_handle_vblank(struct drm_device *dev,
-			       int pipe, u16 iir)
+			       int plane, int pipe, u32 iir)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(pipe);
+	u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
 	if (!drm_handle_vblank(dev, pipe))
 		return false;
@@ -3151,7 +3160,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		return false;
 
-	intel_prepare_page_flip(dev, pipe);
+	intel_prepare_page_flip(dev, plane);
 
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
@@ -3220,9 +3229,13 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 			notify_ring(dev, &dev_priv->ring[RCS]);
 
 		for_each_pipe(pipe) {
+			int plane = pipe;
+			if (HAS_FBC(dev))
+				plane = !plane;
+
 			if (pipe_stats[pipe] & PIPE_VBLANK_INTERRUPT_STATUS &&
-			    i8xx_handle_vblank(dev, pipe, iir))
-				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(pipe);
+			    i8xx_handle_vblank(dev, plane, pipe, iir))
+				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(plane);
 
 			if (pipe_stats[pipe] & PIPE_CRC_DONE_INTERRUPT_STATUS)
 				i9xx_pipe_crc_irq_handler(dev, pipe);
@@ -3418,7 +3431,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 		for_each_pipe(pipe) {
 			int plane = pipe;
-			if (IS_MOBILE(dev))
+			if (HAS_FBC(dev))
 				plane = !plane;
 
 			if (pipe_stats[pipe] & PIPE_VBLANK_INTERRUPT_STATUS &&
@@ -3655,7 +3668,11 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 				  hotplug_status);
 
 			intel_hpd_irq_handler(dev, hotplug_trigger,
-					      IS_G4X(dev) ? hpd_status_gen4 : hpd_status_i915);
+					      IS_G4X(dev) ? hpd_status_g4x : hpd_status_i915);
+
+			if (IS_G4X(dev) &&
+			    (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X))
+				dp_aux_irq_handler(dev);
 
 			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
 			I915_READ(PORT_HOTPLUG_STAT);
@@ -3893,8 +3910,8 @@ void hsw_pc8_disable_interrupts(struct drm_device *dev)
 	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);
+	ironlake_disable_display_irq(dev_priv, 0xffffffff);
+	ibx_disable_display_interrupt(dev_priv, 0xffffffff);
 	ilk_disable_gt_irq(dev_priv, 0xffffffff);
 	snb_disable_pm_irq(dev_priv, 0xffffffff);
 
@@ -3908,34 +3925,26 @@ 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;
+	uint32_t val;
 
 	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);
+	WARN(val != 0xffffffff, "DEIMR is 0x%08x\n", val);
 
-	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(SDEIMR);
+	WARN(val != 0xffffffff, "SDEIMR is 0x%08x\n", val);
 
 	val = I915_READ(GTIMR);
-	expected = 0xffffffff;
-	WARN(val != expected, "GTIMR is 0x%08x, not 0x%08x\n", val, expected);
+	WARN(val != 0xffffffff, "GTIMR is 0x%08x\n", val);
 
 	val = I915_READ(GEN6_PMIMR);
-	expected = 0xffffffff;
-	WARN(val != expected, "GEN6_PMIMR is 0x%08x, not 0x%08x\n", val,
-	     expected);
+	WARN(val != 0xffffffff, "GEN6_PMIMR is 0x%08x\n", val);
 
 	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);
+	ibx_enable_display_interrupt(dev_priv, ~dev_priv->pc8.regsave.sdeimr);
 	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);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ee2742122a02..a48b7cad6f11 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -193,10 +193,13 @@
 #define   MI_SCENE_COUNT	(1 << 3) /* just increment scene count */
 #define   MI_END_SCENE		(1 << 4) /* flush binner and incr scene count */
 #define   MI_INVALIDATE_ISP	(1 << 5) /* invalidate indirect state pointers */
+#define MI_REPORT_HEAD		MI_INSTR(0x07, 0)
+#define MI_ARB_ON_OFF		MI_INSTR(0x08, 0)
+#define   MI_ARB_ENABLE			(1<<0)
+#define   MI_ARB_DISABLE		(0<<0)
 #define MI_BATCH_BUFFER_END	MI_INSTR(0x0a, 0)
 #define MI_SUSPEND_FLUSH	MI_INSTR(0x0b, 0)
 #define   MI_SUSPEND_FLUSH_EN	(1<<0)
-#define MI_REPORT_HEAD		MI_INSTR(0x07, 0)
 #define MI_OVERLAY_FLIP		MI_INSTR(0x11, 0)
 #define   MI_OVERLAY_CONTINUE	(0x0<<21)
 #define   MI_OVERLAY_ON		(0x1<<21)
@@ -212,10 +215,24 @@
 #define   MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19)
 #define   MI_DISPLAY_FLIP_IVB_PLANE_C  (4 << 19)
 #define   MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19)
-#define MI_ARB_ON_OFF		MI_INSTR(0x08, 0)
-#define   MI_ARB_ENABLE			(1<<0)
-#define   MI_ARB_DISABLE		(0<<0)
-
+#define MI_SEMAPHORE_MBOX	MI_INSTR(0x16, 1) /* gen6+ */
+#define   MI_SEMAPHORE_GLOBAL_GTT    (1<<22)
+#define   MI_SEMAPHORE_UPDATE	    (1<<21)
+#define   MI_SEMAPHORE_COMPARE	    (1<<20)
+#define   MI_SEMAPHORE_REGISTER	    (1<<18)
+#define   MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS  wait for VCS  (RVSYNC) */
+#define   MI_SEMAPHORE_SYNC_VER	    (1<<16) /* RCS  wait for VECS (RVESYNC) */
+#define   MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS  wait for BCS  (RBSYNC) */
+#define   MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS  wait for BCS  (VBSYNC) */
+#define   MI_SEMAPHORE_SYNC_VEV	    (1<<16) /* VCS  wait for VECS (VVESYNC) */
+#define   MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS  wait for RCS  (VRSYNC) */
+#define   MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS  wait for RCS  (BRSYNC) */
+#define   MI_SEMAPHORE_SYNC_VEB	    (1<<16) /* BCS  wait for VECS (BVESYNC) */
+#define   MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS  wait for VCS  (BVSYNC) */
+#define   MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
+#define   MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
+#define   MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
+#define   MI_SEMAPHORE_SYNC_INVALID  (3<<16)
 #define MI_SET_CONTEXT		MI_INSTR(0x18, 0)
 #define   MI_MM_SPACE_GTT		(1<<8)
 #define   MI_MM_SPACE_PHYSICAL		(0<<8)
@@ -235,7 +252,7 @@
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*x-1)
 #define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*x-1)
-#define  MI_SRM_LRM_GLOBAL_GTT		(1<<22)
+#define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
 #define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
 #define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
 #define   MI_INVALIDATE_TLB		(1<<18)
@@ -246,30 +263,13 @@
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
-#define   MI_BATCH_NON_SECURE_I965 	(1<<8)
+#define   MI_BATCH_NON_SECURE_I965	(1<<8)
 #define   MI_BATCH_PPGTT_HSW		(1<<8)
-#define   MI_BATCH_NON_SECURE_HSW 	(1<<13)
+#define   MI_BATCH_NON_SECURE_HSW	(1<<13)
 #define MI_BATCH_BUFFER_START	MI_INSTR(0x31, 0)
 #define   MI_BATCH_GTT		    (2<<6) /* aliased with (1<<7) on gen4 */
 #define MI_BATCH_BUFFER_START_GEN8	MI_INSTR(0x31, 1)
-#define MI_SEMAPHORE_MBOX	MI_INSTR(0x16, 1) /* gen6+ */
-#define  MI_SEMAPHORE_GLOBAL_GTT    (1<<22)
-#define  MI_SEMAPHORE_UPDATE	    (1<<21)
-#define  MI_SEMAPHORE_COMPARE	    (1<<20)
-#define  MI_SEMAPHORE_REGISTER	    (1<<18)
-#define  MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS  wait for VCS  (RVSYNC) */
-#define  MI_SEMAPHORE_SYNC_VER	    (1<<16) /* RCS  wait for VECS (RVESYNC) */
-#define  MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS  wait for BCS  (RBSYNC) */
-#define  MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS  wait for BCS  (VBSYNC) */
-#define  MI_SEMAPHORE_SYNC_VEV	    (1<<16) /* VCS  wait for VECS (VVESYNC) */
-#define  MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS  wait for RCS  (VRSYNC) */
-#define  MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS  wait for RCS  (BRSYNC) */
-#define  MI_SEMAPHORE_SYNC_VEB	    (1<<16) /* BCS  wait for VECS (BVESYNC) */
-#define  MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS  wait for VCS  (BVSYNC) */
-#define  MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
-#define  MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
-#define  MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
-#define  MI_SEMAPHORE_SYNC_INVALID  (3<<16)
+
 
 #define MI_PREDICATE_RESULT_2	(0x2214)
 #define  LOWER_SLICE_ENABLED	(1<<0)
@@ -354,6 +354,7 @@
 #define   IOSF_BYTE_ENABLES_SHIFT		4
 #define   IOSF_BAR_SHIFT			1
 #define   IOSF_SB_BUSY				(1<<0)
+#define   IOSF_PORT_BUNIT			0x3
 #define   IOSF_PORT_PUNIT			0x4
 #define   IOSF_PORT_NC				0x11
 #define   IOSF_PORT_DPIO			0x12
@@ -361,12 +362,21 @@
 #define   IOSF_PORT_CCK				0x14
 #define   IOSF_PORT_CCU				0xA9
 #define   IOSF_PORT_GPS_CORE			0x48
+#define   IOSF_PORT_FLISDSI			0x1B
 #define VLV_IOSF_DATA				(VLV_DISPLAY_BASE + 0x2104)
 #define VLV_IOSF_ADDR				(VLV_DISPLAY_BASE + 0x2108)
 
+/* See configdb bunit SB addr map */
+#define BUNIT_REG_BISOC				0x11
+
 #define PUNIT_OPCODE_REG_READ			6
 #define PUNIT_OPCODE_REG_WRITE			7
 
+#define PUNIT_REG_DSPFREQ			0x36
+#define   DSPFREQSTAT_SHIFT			30
+#define   DSPFREQSTAT_MASK			(0x3 << DSPFREQSTAT_SHIFT)
+#define   DSPFREQGUAR_SHIFT			14
+#define   DSPFREQGUAR_MASK			(0x3 << DSPFREQGUAR_SHIFT)
 #define PUNIT_REG_PWRGT_CTRL			0x60
 #define PUNIT_REG_PWRGT_STATUS			0x61
 #define	  PUNIT_CLK_GATE			1
@@ -429,6 +439,7 @@
 #define  DSI_PLL_N1_DIV_MASK			(3 << 16)
 #define  DSI_PLL_M1_DIV_SHIFT			0
 #define  DSI_PLL_M1_DIV_MASK			(0x1ff << 0)
+#define CCK_DISPLAY_CLOCK_CONTROL		0x6b
 
 /*
  * DPIO - a special bus for various display related registers to hide behind
@@ -447,15 +458,13 @@
 #define  DPIO_SFR_BYPASS		(1<<1)
 #define  DPIO_CMNRST			(1<<0)
 
-#define _DPIO_TX3_SWING_CTL4_A		0x690
-#define _DPIO_TX3_SWING_CTL4_B		0x2a90
-#define DPIO_TX3_SWING_CTL4(pipe) _PIPE(pipe, _DPIO_TX3_SWING_CTL4_A, \
-					_DPIO_TX3_SWING_CTL4_B)
+#define DPIO_PHY(pipe)			((pipe) >> 1)
+#define DPIO_PHY_IOSF_PORT(phy)		(dev_priv->dpio_phy_iosf_port[phy])
 
 /*
  * Per pipe/PLL DPIO regs
  */
-#define _DPIO_DIV_A			0x800c
+#define _VLV_PLL_DW3_CH0		0x800c
 #define   DPIO_POST_DIV_SHIFT		(28) /* 3 bits */
 #define   DPIO_POST_DIV_DAC		0
 #define   DPIO_POST_DIV_HDMIDP		1 /* DAC 225-400M rate */
@@ -468,10 +477,10 @@
 #define   DPIO_ENABLE_CALIBRATION	(1<<11)
 #define   DPIO_M1DIV_SHIFT		(8) /* 3 bits */
 #define   DPIO_M2DIV_MASK		0xff
-#define _DPIO_DIV_B			0x802c
-#define DPIO_DIV(pipe) _PIPE(pipe, _DPIO_DIV_A, _DPIO_DIV_B)
+#define _VLV_PLL_DW3_CH1		0x802c
+#define VLV_PLL_DW3(ch) _PIPE(ch, _VLV_PLL_DW3_CH0, _VLV_PLL_DW3_CH1)
 
-#define _DPIO_REFSFR_A			0x8014
+#define _VLV_PLL_DW5_CH0		0x8014
 #define   DPIO_REFSEL_OVERRIDE		27
 #define   DPIO_PLL_MODESEL_SHIFT	24 /* 3 bits */
 #define   DPIO_BIAS_CURRENT_CTL_SHIFT	21 /* 3 bits, always 0x7 */
@@ -479,118 +488,112 @@
 #define   DPIO_PLL_REFCLK_SEL_MASK	3
 #define   DPIO_DRIVER_CTL_SHIFT		12 /* always set to 0x8 */
 #define   DPIO_CLK_BIAS_CTL_SHIFT	8 /* always set to 0x5 */
-#define _DPIO_REFSFR_B			0x8034
-#define DPIO_REFSFR(pipe) _PIPE(pipe, _DPIO_REFSFR_A, _DPIO_REFSFR_B)
+#define _VLV_PLL_DW5_CH1		0x8034
+#define VLV_PLL_DW5(ch) _PIPE(ch, _VLV_PLL_DW5_CH0, _VLV_PLL_DW5_CH1)
 
-#define _DPIO_CORE_CLK_A		0x801c
-#define _DPIO_CORE_CLK_B		0x803c
-#define DPIO_CORE_CLK(pipe) _PIPE(pipe, _DPIO_CORE_CLK_A, _DPIO_CORE_CLK_B)
+#define _VLV_PLL_DW7_CH0		0x801c
+#define _VLV_PLL_DW7_CH1		0x803c
+#define VLV_PLL_DW7(ch) _PIPE(ch, _VLV_PLL_DW7_CH0, _VLV_PLL_DW7_CH1)
 
-#define _DPIO_IREF_CTL_A		0x8040
-#define _DPIO_IREF_CTL_B		0x8060
-#define DPIO_IREF_CTL(pipe) _PIPE(pipe, _DPIO_IREF_CTL_A, _DPIO_IREF_CTL_B)
+#define _VLV_PLL_DW8_CH0		0x8040
+#define _VLV_PLL_DW8_CH1		0x8060
+#define VLV_PLL_DW8(ch) _PIPE(ch, _VLV_PLL_DW8_CH0, _VLV_PLL_DW8_CH1)
 
-#define DPIO_IREF_BCAST			0xc044
-#define _DPIO_IREF_A			0x8044
-#define _DPIO_IREF_B			0x8064
-#define DPIO_IREF(pipe) _PIPE(pipe, _DPIO_IREF_A, _DPIO_IREF_B)
+#define VLV_PLL_DW9_BCAST		0xc044
+#define _VLV_PLL_DW9_CH0		0x8044
+#define _VLV_PLL_DW9_CH1		0x8064
+#define VLV_PLL_DW9(ch) _PIPE(ch, _VLV_PLL_DW9_CH0, _VLV_PLL_DW9_CH1)
 
-#define _DPIO_PLL_CML_A			0x804c
-#define _DPIO_PLL_CML_B			0x806c
-#define DPIO_PLL_CML(pipe) _PIPE(pipe, _DPIO_PLL_CML_A, _DPIO_PLL_CML_B)
+#define _VLV_PLL_DW10_CH0		0x8048
+#define _VLV_PLL_DW10_CH1		0x8068
+#define VLV_PLL_DW10(ch) _PIPE(ch, _VLV_PLL_DW10_CH0, _VLV_PLL_DW10_CH1)
 
-#define _DPIO_LPF_COEFF_A		0x8048
-#define _DPIO_LPF_COEFF_B		0x8068
-#define DPIO_LPF_COEFF(pipe) _PIPE(pipe, _DPIO_LPF_COEFF_A, _DPIO_LPF_COEFF_B)
+#define _VLV_PLL_DW11_CH0		0x804c
+#define _VLV_PLL_DW11_CH1		0x806c
+#define VLV_PLL_DW11(ch) _PIPE(ch, _VLV_PLL_DW11_CH0, _VLV_PLL_DW11_CH1)
 
-#define DPIO_CALIBRATION		0x80ac
+/* Spec for ref block start counts at DW10 */
+#define VLV_REF_DW13			0x80ac
 
-#define DPIO_FASTCLK_DISABLE		0x8100
+#define VLV_CMN_DW0			0x8100
 
 /*
  * Per DDI channel DPIO regs
  */
 
-#define _DPIO_PCS_TX_0			0x8200
-#define _DPIO_PCS_TX_1			0x8400
+#define _VLV_PCS_DW0_CH0		0x8200
+#define _VLV_PCS_DW0_CH1		0x8400
 #define   DPIO_PCS_TX_LANE2_RESET	(1<<16)
 #define   DPIO_PCS_TX_LANE1_RESET	(1<<7)
-#define DPIO_PCS_TX(port) _PORT(port, _DPIO_PCS_TX_0, _DPIO_PCS_TX_1)
+#define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1)
 
-#define _DPIO_PCS_CLK_0			0x8204
-#define _DPIO_PCS_CLK_1			0x8404
+#define _VLV_PCS_DW1_CH0		0x8204
+#define _VLV_PCS_DW1_CH1		0x8404
 #define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1<<22)
 #define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21)
 #define   DPIO_PCS_CLK_DATAWIDTH_SHIFT	(6)
 #define   DPIO_PCS_CLK_SOFT_RESET	(1<<5)
-#define DPIO_PCS_CLK(port) _PORT(port, _DPIO_PCS_CLK_0, _DPIO_PCS_CLK_1)
-
-#define _DPIO_PCS_CTL_OVR1_A		0x8224
-#define _DPIO_PCS_CTL_OVR1_B		0x8424
-#define DPIO_PCS_CTL_OVER1(port) _PORT(port, _DPIO_PCS_CTL_OVR1_A, \
-				       _DPIO_PCS_CTL_OVR1_B)
-
-#define _DPIO_PCS_STAGGER0_A		0x822c
-#define _DPIO_PCS_STAGGER0_B		0x842c
-#define DPIO_PCS_STAGGER0(port) _PORT(port, _DPIO_PCS_STAGGER0_A, \
-				      _DPIO_PCS_STAGGER0_B)
-
-#define _DPIO_PCS_STAGGER1_A		0x8230
-#define _DPIO_PCS_STAGGER1_B		0x8430
-#define DPIO_PCS_STAGGER1(port) _PORT(port, _DPIO_PCS_STAGGER1_A, \
-				      _DPIO_PCS_STAGGER1_B)
-
-#define _DPIO_PCS_CLOCKBUF0_A		0x8238
-#define _DPIO_PCS_CLOCKBUF0_B		0x8438
-#define DPIO_PCS_CLOCKBUF0(port) _PORT(port, _DPIO_PCS_CLOCKBUF0_A, \
-				       _DPIO_PCS_CLOCKBUF0_B)
-
-#define _DPIO_PCS_CLOCKBUF8_A		0x825c
-#define _DPIO_PCS_CLOCKBUF8_B		0x845c
-#define DPIO_PCS_CLOCKBUF8(port) _PORT(port, _DPIO_PCS_CLOCKBUF8_A, \
-				       _DPIO_PCS_CLOCKBUF8_B)
-
-#define _DPIO_TX_SWING_CTL2_A		0x8288
-#define _DPIO_TX_SWING_CTL2_B		0x8488
-#define DPIO_TX_SWING_CTL2(port) _PORT(port, _DPIO_TX_SWING_CTL2_A, \
-				       _DPIO_TX_SWING_CTL2_B)
-
-#define _DPIO_TX_SWING_CTL3_A		0x828c
-#define _DPIO_TX_SWING_CTL3_B		0x848c
-#define DPIO_TX_SWING_CTL3(port) _PORT(port, _DPIO_TX_SWING_CTL3_A, \
-				       _DPIO_TX_SWING_CTL3_B)
-
-#define _DPIO_TX_SWING_CTL4_A		0x8290
-#define _DPIO_TX_SWING_CTL4_B		0x8490
-#define DPIO_TX_SWING_CTL4(port) _PORT(port, _DPIO_TX_SWING_CTL4_A, \
-				       _DPIO_TX_SWING_CTL4_B)
-
-#define _DPIO_TX_OCALINIT_0		0x8294
-#define _DPIO_TX_OCALINIT_1		0x8494
+#define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1)
+
+#define _VLV_PCS_DW8_CH0		0x8220
+#define _VLV_PCS_DW8_CH1		0x8420
+#define VLV_PCS_DW8(ch) _PORT(ch, _VLV_PCS_DW8_CH0, _VLV_PCS_DW8_CH1)
+
+#define _VLV_PCS01_DW8_CH0		0x0220
+#define _VLV_PCS23_DW8_CH0		0x0420
+#define _VLV_PCS01_DW8_CH1		0x2620
+#define _VLV_PCS23_DW8_CH1		0x2820
+#define VLV_PCS01_DW8(port) _PORT(port, _VLV_PCS01_DW8_CH0, _VLV_PCS01_DW8_CH1)
+#define VLV_PCS23_DW8(port) _PORT(port, _VLV_PCS23_DW8_CH0, _VLV_PCS23_DW8_CH1)
+
+#define _VLV_PCS_DW9_CH0		0x8224
+#define _VLV_PCS_DW9_CH1		0x8424
+#define	VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1)
+
+#define _VLV_PCS_DW11_CH0		0x822c
+#define _VLV_PCS_DW11_CH1		0x842c
+#define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1)
+
+#define _VLV_PCS_DW12_CH0		0x8230
+#define _VLV_PCS_DW12_CH1		0x8430
+#define VLV_PCS_DW12(ch) _PORT(ch, _VLV_PCS_DW12_CH0, _VLV_PCS_DW12_CH1)
+
+#define _VLV_PCS_DW14_CH0		0x8238
+#define _VLV_PCS_DW14_CH1		0x8438
+#define	VLV_PCS_DW14(ch) _PORT(ch, _VLV_PCS_DW14_CH0, _VLV_PCS_DW14_CH1)
+
+#define _VLV_PCS_DW23_CH0		0x825c
+#define _VLV_PCS_DW23_CH1		0x845c
+#define VLV_PCS_DW23(ch) _PORT(ch, _VLV_PCS_DW23_CH0, _VLV_PCS_DW23_CH1)
+
+#define _VLV_TX_DW2_CH0			0x8288
+#define _VLV_TX_DW2_CH1			0x8488
+#define VLV_TX_DW2(ch) _PORT(ch, _VLV_TX_DW2_CH0, _VLV_TX_DW2_CH1)
+
+#define _VLV_TX_DW3_CH0			0x828c
+#define _VLV_TX_DW3_CH1			0x848c
+#define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1)
+
+#define _VLV_TX_DW4_CH0			0x8290
+#define _VLV_TX_DW4_CH1			0x8490
+#define VLV_TX_DW4(ch) _PORT(ch, _VLV_TX_DW4_CH0, _VLV_TX_DW4_CH1)
+
+#define _VLV_TX3_DW4_CH0		0x690
+#define _VLV_TX3_DW4_CH1		0x2a90
+#define VLV_TX3_DW4(ch) _PORT(ch, _VLV_TX3_DW4_CH0, _VLV_TX3_DW4_CH1)
+
+#define _VLV_TX_DW5_CH0			0x8294
+#define _VLV_TX_DW5_CH1			0x8494
 #define   DPIO_TX_OCALINIT_EN		(1<<31)
-#define DPIO_TX_OCALINIT(port) _PORT(port, _DPIO_TX_OCALINIT_0, \
-				     _DPIO_TX_OCALINIT_1)
-
-#define _DPIO_TX_CTL_0			0x82ac
-#define _DPIO_TX_CTL_1			0x84ac
-#define DPIO_TX_CTL(port) _PORT(port, _DPIO_TX_CTL_0, _DPIO_TX_CTL_1)
-
-#define _DPIO_TX_LANE_0			0x82b8
-#define _DPIO_TX_LANE_1			0x84b8
-#define DPIO_TX_LANE(port) _PORT(port, _DPIO_TX_LANE_0, _DPIO_TX_LANE_1)
-
-#define _DPIO_DATA_CHANNEL1		0x8220
-#define _DPIO_DATA_CHANNEL2		0x8420
-#define DPIO_DATA_CHANNEL(port) _PORT(port, _DPIO_DATA_CHANNEL1, _DPIO_DATA_CHANNEL2)
-
-#define _DPIO_PORT0_PCS0		0x0220
-#define _DPIO_PORT0_PCS1		0x0420
-#define _DPIO_PORT1_PCS2		0x2620
-#define _DPIO_PORT1_PCS3		0x2820
-#define DPIO_DATA_LANE_A(port) _PORT(port, _DPIO_PORT0_PCS0, _DPIO_PORT1_PCS2)
-#define DPIO_DATA_LANE_B(port) _PORT(port, _DPIO_PORT0_PCS1, _DPIO_PORT1_PCS3)
-#define DPIO_DATA_CHANNEL1              0x8220
-#define DPIO_DATA_CHANNEL2              0x8420
+#define VLV_TX_DW5(ch) _PORT(ch, _VLV_TX_DW5_CH0, _VLV_TX_DW5_CH1)
+
+#define _VLV_TX_DW11_CH0		0x82ac
+#define _VLV_TX_DW11_CH1		0x84ac
+#define VLV_TX_DW11(ch) _PORT(ch, _VLV_TX_DW11_CH0, _VLV_TX_DW11_CH1)
+
+#define _VLV_TX_DW14_CH0		0x82b8
+#define _VLV_TX_DW14_CH1		0x84b8
+#define VLV_TX_DW14(ch) _PORT(ch, _VLV_TX_DW14_CH0, _VLV_TX_DW14_CH1)
 
 /*
  * Fence registers
@@ -732,6 +735,8 @@
 #define HWSTAM		0x02098
 #define DMA_FADD_I8XX	0x020d0
 #define RING_BBSTATE(base)	((base)+0x110)
+#define RING_BBADDR(base)	((base)+0x140)
+#define RING_BBADDR_UDW(base)	((base)+0x168) /* gen8+ */
 
 #define ERROR_GEN6	0x040a0
 #define GEN7_ERR_INT	0x44040
@@ -922,7 +927,6 @@
 #define   CM0_COLOR_EVICT_DISABLE (1<<3)
 #define   CM0_DEPTH_WRITE_DISABLE (1<<1)
 #define   CM0_RC_OP_FLUSH_DISABLE (1<<0)
-#define BB_ADDR		0x02140 /* 8 bytes */
 #define GFX_FLSH_CNTL	0x02170 /* 915+ only */
 #define GFX_FLSH_CNTL_GEN6	0x101008
 #define   GFX_FLSH_CNTL_EN	(1<<0)
@@ -999,6 +1003,7 @@
 
 #define GEN7_FF_THREAD_MODE		0x20a0
 #define   GEN7_FF_SCHED_MASK		0x0077070
+#define   GEN8_FF_DS_REF_CNT_FFME	(1 << 19)
 #define   GEN7_FF_TS_SCHED_HS1		(0x5<<16)
 #define   GEN7_FF_TS_SCHED_HS0		(0x3<<16)
 #define   GEN7_FF_TS_SCHED_LOAD_BALANCE	(0x1<<16)
@@ -1026,14 +1031,14 @@
 #define   FBC_CTL_UNCOMPRESSIBLE (1<<14)
 #define   FBC_CTL_C3_IDLE	(1<<13)
 #define   FBC_CTL_STRIDE_SHIFT	(5)
-#define   FBC_CTL_FENCENO	(1<<0)
+#define   FBC_CTL_FENCENO_SHIFT	(0)
 #define FBC_COMMAND		0x0320c
 #define   FBC_CMD_COMPRESS	(1<<0)
 #define FBC_STATUS		0x03210
 #define   FBC_STAT_COMPRESSING	(1<<31)
 #define   FBC_STAT_COMPRESSED	(1<<30)
 #define   FBC_STAT_MODIFIED	(1<<29)
-#define   FBC_STAT_CURRENT_LINE	(1<<0)
+#define   FBC_STAT_CURRENT_LINE_SHIFT	(0)
 #define FBC_CONTROL2		0x03214
 #define   FBC_CTL_FENCE_DBL	(0<<4)
 #define   FBC_CTL_IDLE_IMM	(0<<2)
@@ -2117,9 +2122,13 @@
  * Please check the detailed lore in the commit message for for experimental
  * evidence.
  */
-#define   PORTD_HOTPLUG_LIVE_STATUS               (1 << 29)
-#define   PORTC_HOTPLUG_LIVE_STATUS               (1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS               (1 << 27)
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
+/* VLV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
+#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTC_HOTPLUG_INT_STATUS		(3 << 19)
 #define   PORTB_HOTPLUG_INT_STATUS		(3 << 17)
@@ -2130,6 +2139,11 @@
 #define   CRT_HOTPLUG_MONITOR_COLOR		(3 << 8)
 #define   CRT_HOTPLUG_MONITOR_MONO		(2 << 8)
 #define   CRT_HOTPLUG_MONITOR_NONE		(0 << 8)
+#define   DP_AUX_CHANNEL_D_INT_STATUS_G4X	(1 << 6)
+#define   DP_AUX_CHANNEL_C_INT_STATUS_G4X	(1 << 5)
+#define   DP_AUX_CHANNEL_B_INT_STATUS_G4X	(1 << 4)
+#define   DP_AUX_CHANNEL_MASK_INT_STATUS_G4X	(7 << 4)
+
 /* SDVO is different across gen3/4 */
 #define   SDVOC_HOTPLUG_INT_STATUS_G4X		(1 << 3)
 #define   SDVOB_HOTPLUG_INT_STATUS_G4X		(1 << 2)
@@ -3421,42 +3435,6 @@
 /* the unit of memory self-refresh latency time is 0.5us */
 #define  ILK_SRLT_MASK		0x3f
 
-/* define the fifo size on Ironlake */
-#define ILK_DISPLAY_FIFO	128
-#define ILK_DISPLAY_MAXWM	64
-#define ILK_DISPLAY_DFTWM	8
-#define ILK_CURSOR_FIFO		32
-#define ILK_CURSOR_MAXWM	16
-#define ILK_CURSOR_DFTWM	8
-
-#define ILK_DISPLAY_SR_FIFO	512
-#define ILK_DISPLAY_MAX_SRWM	0x1ff
-#define ILK_DISPLAY_DFT_SRWM	0x3f
-#define ILK_CURSOR_SR_FIFO	64
-#define ILK_CURSOR_MAX_SRWM	0x3f
-#define ILK_CURSOR_DFT_SRWM	8
-
-#define ILK_FIFO_LINE_SIZE	64
-
-/* define the WM info on Sandybridge */
-#define SNB_DISPLAY_FIFO	128
-#define SNB_DISPLAY_MAXWM	0x7f	/* bit 16:22 */
-#define SNB_DISPLAY_DFTWM	8
-#define SNB_CURSOR_FIFO		32
-#define SNB_CURSOR_MAXWM	0x1f	/* bit 4:0 */
-#define SNB_CURSOR_DFTWM	8
-
-#define SNB_DISPLAY_SR_FIFO	512
-#define SNB_DISPLAY_MAX_SRWM	0x1ff	/* bit 16:8 */
-#define SNB_DISPLAY_DFT_SRWM	0x3f
-#define SNB_CURSOR_SR_FIFO	64
-#define SNB_CURSOR_MAX_SRWM	0x3f	/* bit 5:0 */
-#define SNB_CURSOR_DFT_SRWM	8
-
-#define SNB_FBC_MAX_SRWM	0xf	/* bit 23:20 */
-
-#define SNB_FIFO_LINE_SIZE	64
-
 
 /* the address where we get all kinds of latency value */
 #define SSKPD			0x5d10
@@ -3600,8 +3578,6 @@
 #define DISP_BASEADDR_MASK	(0xfffff000)
 #define I915_LO_DISPBASE(val)	(val & ~DISP_BASEADDR_MASK)
 #define I915_HI_DISPBASE(val)	(val & DISP_BASEADDR_MASK)
-#define I915_MODIFY_DISPBASE(reg, gfx_addr) \
-		(I915_WRITE((reg), (gfx_addr) | I915_LO_DISPBASE(I915_READ(reg))))
 
 /* VBIOS flags */
 #define SWF00			(dev_priv->info->display_mmio_offset + 0x71410)
@@ -3787,7 +3763,7 @@
 
 #define _SPACNTR		(VLV_DISPLAY_BASE + 0x72180)
 #define   SP_ENABLE			(1<<31)
-#define   SP_GEAMMA_ENABLE		(1<<30)
+#define   SP_GAMMA_ENABLE		(1<<30)
 #define   SP_PIXFORMAT_MASK		(0xf<<26)
 #define   SP_FORMAT_YUV422		(0<<26)
 #define   SP_FORMAT_BGR565		(5<<26)
@@ -4139,6 +4115,8 @@
 #define DISP_ARB_CTL	0x45000
 #define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
 #define  DISP_FBC_WM_DIS		(1<<15)
+#define DISP_ARB_CTL2	0x45004
+#define  DISP_DATA_PARTITION_5_6	(1<<6)
 #define GEN7_MSG_CTL	0x45010
 #define  WAIT_FOR_PCH_RESET_ACK		(1<<1)
 #define  WAIT_FOR_PCH_FLR_ACK		(1<<0)
@@ -4159,6 +4137,10 @@
 #define GEN7_L3SQCREG4				0xb034
 #define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1<<27)
 
+/* GEN8 chicken */
+#define HDC_CHICKEN0				0x7300
+#define  HDC_FORCE_NON_COHERENT			(1<<4)
+
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
@@ -4843,6 +4825,8 @@
 #define  FORCEWAKE_ACK				0x130090
 #define  VLV_GTLC_WAKE_CTRL			0x130090
 #define  VLV_GTLC_PW_STATUS			0x130094
+#define VLV_GTLC_PW_RENDER_STATUS_MASK		0x80
+#define VLV_GTLC_PW_MEDIA_STATUS_MASK		0x20
 #define  FORCEWAKE_MT				0xa188 /* multi-threaded */
 #define   FORCEWAKE_KERNEL			0x1
 #define   FORCEWAKE_USER			0x2
@@ -4851,12 +4835,16 @@
 #define    FORCEWAKE_MT_ENABLE			(1<<5)
 
 #define  GTFIFODBG				0x120000
-#define    GT_FIFO_CPU_ERROR_MASK		7
+#define    GT_FIFO_SBDROPERR			(1<<6)
+#define    GT_FIFO_BLOBDROPERR			(1<<5)
+#define    GT_FIFO_SB_READ_ABORTERR		(1<<4)
+#define    GT_FIFO_DROPERR			(1<<3)
 #define    GT_FIFO_OVFERR			(1<<2)
 #define    GT_FIFO_IAWRERR			(1<<1)
 #define    GT_FIFO_IARDERR			(1<<0)
 
-#define  GT_FIFO_FREE_ENTRIES			0x120008
+#define  GTFIFOCTL				0x120008
+#define    GT_FIFO_FREE_ENTRIES_MASK		0x7f
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
 
 #define  HSW_IDICR				0x9008
@@ -4890,6 +4878,7 @@
 #define   GEN6_RC_CTL_RC6_ENABLE		(1<<18)
 #define   GEN6_RC_CTL_RC1e_ENABLE		(1<<20)
 #define   GEN6_RC_CTL_RC7_ENABLE		(1<<22)
+#define   VLV_RC_CTL_CTX_RST_PARALLEL		(1<<24)
 #define   GEN7_RC_CTL_TO_MODE			(1<<28)
 #define   GEN6_RC_CTL_EI_MODE(x)		((x)<<27)
 #define   GEN6_RC_CTL_HW_ENABLE			(1<<31)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 98790c7cccb1..8150fdc08d49 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -192,7 +192,6 @@ static void i915_restore_vga(struct drm_device *dev)
 static void i915_save_display(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
 
 	/* Display arbitration control */
 	if (INTEL_INFO(dev)->gen <= 4)
@@ -203,46 +202,27 @@ static void i915_save_display(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		i915_save_display_reg(dev);
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
-
 	/* LVDS state */
 	if (HAS_PCH_SPLIT(dev)) {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PCH_PP_CONTROL);
-		dev_priv->regfile.saveBLC_PWM_CTL = I915_READ(BLC_PWM_PCH_CTL1);
-		dev_priv->regfile.saveBLC_PWM_CTL2 = I915_READ(BLC_PWM_PCH_CTL2);
-		dev_priv->regfile.saveBLC_CPU_PWM_CTL = I915_READ(BLC_PWM_CPU_CTL);
-		dev_priv->regfile.saveBLC_CPU_PWM_CTL2 = I915_READ(BLC_PWM_CPU_CTL2);
 		if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev))
 			dev_priv->regfile.saveLVDS = I915_READ(PCH_LVDS);
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PP_CONTROL);
 		dev_priv->regfile.savePFIT_PGM_RATIOS = I915_READ(PFIT_PGM_RATIOS);
 
-		dev_priv->regfile.saveBLC_PWM_CTL =
-			I915_READ(VLV_BLC_PWM_CTL(PIPE_A));
 		dev_priv->regfile.saveBLC_HIST_CTL =
 			I915_READ(VLV_BLC_HIST_CTL(PIPE_A));
-		dev_priv->regfile.saveBLC_PWM_CTL2 =
-			I915_READ(VLV_BLC_PWM_CTL2(PIPE_A));
-		dev_priv->regfile.saveBLC_PWM_CTL_B =
-			I915_READ(VLV_BLC_PWM_CTL(PIPE_B));
 		dev_priv->regfile.saveBLC_HIST_CTL_B =
 			I915_READ(VLV_BLC_HIST_CTL(PIPE_B));
-		dev_priv->regfile.saveBLC_PWM_CTL2_B =
-			I915_READ(VLV_BLC_PWM_CTL2(PIPE_B));
 	} else {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PP_CONTROL);
 		dev_priv->regfile.savePFIT_PGM_RATIOS = I915_READ(PFIT_PGM_RATIOS);
-		dev_priv->regfile.saveBLC_PWM_CTL = I915_READ(BLC_PWM_CTL);
 		dev_priv->regfile.saveBLC_HIST_CTL = I915_READ(BLC_HIST_CTL);
-		if (INTEL_INFO(dev)->gen >= 4)
-			dev_priv->regfile.saveBLC_PWM_CTL2 = I915_READ(BLC_PWM_CTL2);
 		if (IS_MOBILE(dev) && !IS_I830(dev))
 			dev_priv->regfile.saveLVDS = I915_READ(LVDS);
 	}
 
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
-
 	if (!IS_I830(dev) && !IS_845G(dev) && !HAS_PCH_SPLIT(dev))
 		dev_priv->regfile.savePFIT_CONTROL = I915_READ(PFIT_CONTROL);
 
@@ -257,7 +237,7 @@ static void i915_save_display(struct drm_device *dev)
 	}
 
 	/* Only regfile.save FBC state on the platform that supports FBC */
-	if (I915_HAS_FBC(dev)) {
+	if (HAS_FBC(dev)) {
 		if (HAS_PCH_SPLIT(dev)) {
 			dev_priv->regfile.saveDPFC_CB_BASE = I915_READ(ILK_DPFC_CB_BASE);
 		} else if (IS_GM45(dev)) {
@@ -278,7 +258,6 @@ static void i915_restore_display(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 mask = 0xffffffff;
-	unsigned long flags;
 
 	/* Display arbitration */
 	if (INTEL_INFO(dev)->gen <= 4)
@@ -287,12 +266,6 @@ static void i915_restore_display(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		i915_restore_display_reg(dev);
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
-
-	/* LVDS state */
-	if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev))
-		I915_WRITE(BLC_PWM_CTL2, dev_priv->regfile.saveBLC_PWM_CTL2);
-
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		mask = ~LVDS_PORT_EN;
 
@@ -305,13 +278,6 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(PFIT_CONTROL, dev_priv->regfile.savePFIT_CONTROL);
 
 	if (HAS_PCH_SPLIT(dev)) {
-		I915_WRITE(BLC_PWM_PCH_CTL1, dev_priv->regfile.saveBLC_PWM_CTL);
-		I915_WRITE(BLC_PWM_PCH_CTL2, dev_priv->regfile.saveBLC_PWM_CTL2);
-		/* NOTE: BLC_PWM_CPU_CTL must be written after BLC_PWM_CPU_CTL2;
-		 * otherwise we get blank eDP screen after S3 on some machines
-		 */
-		I915_WRITE(BLC_PWM_CPU_CTL2, dev_priv->regfile.saveBLC_CPU_PWM_CTL2);
-		I915_WRITE(BLC_PWM_CPU_CTL, dev_priv->regfile.saveBLC_CPU_PWM_CTL);
 		I915_WRITE(PCH_PP_ON_DELAYS, dev_priv->regfile.savePP_ON_DELAYS);
 		I915_WRITE(PCH_PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PCH_PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
@@ -319,21 +285,12 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(RSTDBYCTL,
 			   dev_priv->regfile.saveMCHBAR_RENDER_STANDBY);
 	} else if (IS_VALLEYVIEW(dev)) {
-		I915_WRITE(VLV_BLC_PWM_CTL(PIPE_A),
-			   dev_priv->regfile.saveBLC_PWM_CTL);
 		I915_WRITE(VLV_BLC_HIST_CTL(PIPE_A),
 			   dev_priv->regfile.saveBLC_HIST_CTL);
-		I915_WRITE(VLV_BLC_PWM_CTL2(PIPE_A),
-			   dev_priv->regfile.saveBLC_PWM_CTL2);
-		I915_WRITE(VLV_BLC_PWM_CTL(PIPE_B),
-			   dev_priv->regfile.saveBLC_PWM_CTL);
 		I915_WRITE(VLV_BLC_HIST_CTL(PIPE_B),
 			   dev_priv->regfile.saveBLC_HIST_CTL);
-		I915_WRITE(VLV_BLC_PWM_CTL2(PIPE_B),
-			   dev_priv->regfile.saveBLC_PWM_CTL2);
 	} else {
 		I915_WRITE(PFIT_PGM_RATIOS, dev_priv->regfile.savePFIT_PGM_RATIOS);
-		I915_WRITE(BLC_PWM_CTL, dev_priv->regfile.saveBLC_PWM_CTL);
 		I915_WRITE(BLC_HIST_CTL, dev_priv->regfile.saveBLC_HIST_CTL);
 		I915_WRITE(PP_ON_DELAYS, dev_priv->regfile.savePP_ON_DELAYS);
 		I915_WRITE(PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
@@ -341,11 +298,9 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(PP_CONTROL, dev_priv->regfile.savePP_CONTROL);
 	}
 
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
-
 	/* only restore FBC info on the platform that supports FBC*/
 	intel_disable_fbc(dev);
-	if (I915_HAS_FBC(dev)) {
+	if (HAS_FBC(dev)) {
 		if (HAS_PCH_SPLIT(dev)) {
 			I915_WRITE(ILK_DPFC_CB_BASE, dev_priv->regfile.saveDPFC_CB_BASE);
 		} else if (IS_GM45(dev)) {
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index cef38fd320a7..33bcae314bf8 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -40,10 +40,13 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u64 raw_time; /* 32b value may overflow during fixed point math */
 	u64 units = 128ULL, div = 100000ULL, bias = 100ULL;
+	u32 ret;
 
 	if (!intel_enable_rc6(dev))
 		return 0;
 
+	intel_runtime_pm_get(dev_priv);
+
 	/* On VLV, residency time is in CZ units rather than 1.28us */
 	if (IS_VALLEYVIEW(dev)) {
 		u32 clkctl2;
@@ -52,7 +55,8 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg)
 			CLK_CTL2_CZCOUNT_30NS_SHIFT;
 		if (!clkctl2) {
 			WARN(!clkctl2, "bogus CZ count value");
-			return 0;
+			ret = 0;
+			goto out;
 		}
 		units = DIV_ROUND_UP_ULL(30ULL * bias, (u64)clkctl2);
 		if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
@@ -62,7 +66,11 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg)
 	}
 
 	raw_time = I915_READ(reg) * units;
-	return DIV_ROUND_UP_ULL(raw_time, div);
+	ret = DIV_ROUND_UP_ULL(raw_time, div);
+
+out:
+	intel_runtime_pm_put(dev_priv);
+	return ret;
 }
 
 static ssize_t
@@ -183,13 +191,13 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
+	if (!HAS_HW_CONTEXTS(drm_dev))
+		return -ENXIO;
+
 	ret = l3_access_valid(drm_dev, offset);
 	if (ret)
 		return ret;
 
-	if (dev_priv->hw_contexts_disabled)
-		return -ENXIO;
-
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -259,7 +267,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
 		u32 freq;
 		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-		ret = vlv_gpu_freq(dev_priv->mem_freq, (freq >> 8) & 0xff);
+		ret = vlv_gpu_freq(dev_priv, (freq >> 8) & 0xff);
 	} else {
 		ret = dev_priv->rps.cur_delay * GT_FREQUENCY_MULTIPLIER;
 	}
@@ -276,8 +284,7 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			vlv_gpu_freq(dev_priv->mem_freq,
-				     dev_priv->rps.rpe_delay));
+			vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay));
 }
 
 static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
@@ -291,7 +298,7 @@ static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev))
-		ret = vlv_gpu_freq(dev_priv->mem_freq, dev_priv->rps.max_delay);
+		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay);
 	else
 		ret = dev_priv->rps.max_delay * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -318,7 +325,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
-		val = vlv_freq_opcode(dev_priv->mem_freq, val);
+		val = vlv_freq_opcode(dev_priv, val);
 
 		hw_max = valleyview_rps_max_freq(dev_priv);
 		hw_min = valleyview_rps_min_freq(dev_priv);
@@ -342,15 +349,15 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 		DRM_DEBUG("User requested overclocking to %d\n",
 			  val * GT_FREQUENCY_MULTIPLIER);
 
+	dev_priv->rps.max_delay = val;
+
 	if (dev_priv->rps.cur_delay > val) {
-		if (IS_VALLEYVIEW(dev_priv->dev))
-			valleyview_set_rps(dev_priv->dev, val);
+		if (IS_VALLEYVIEW(dev))
+			valleyview_set_rps(dev, val);
 		else
-			gen6_set_rps(dev_priv->dev, val);
+			gen6_set_rps(dev, val);
 	}
 
-	dev_priv->rps.max_delay = val;
-
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return count;
@@ -367,7 +374,7 @@ static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev))
-		ret = vlv_gpu_freq(dev_priv->mem_freq, dev_priv->rps.min_delay);
+		ret = vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay);
 	else
 		ret = dev_priv->rps.min_delay * GT_FREQUENCY_MULTIPLIER;
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -394,7 +401,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	if (IS_VALLEYVIEW(dev)) {
-		val = vlv_freq_opcode(dev_priv->mem_freq, val);
+		val = vlv_freq_opcode(dev_priv, val);
 
 		hw_max = valleyview_rps_max_freq(dev_priv);
 		hw_min = valleyview_rps_min_freq(dev_priv);
@@ -411,15 +418,15 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 		return -EINVAL;
 	}
 
+	dev_priv->rps.min_delay = val;
+
 	if (dev_priv->rps.cur_delay < val) {
 		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev, val);
 		else
-			gen6_set_rps(dev_priv->dev, val);
+			gen6_set_rps(dev, val);
 	}
 
-	dev_priv->rps.min_delay = val;
-
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	return count;
@@ -449,7 +456,9 @@ static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
+	intel_runtime_pm_get(dev_priv);
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	if (attr == &dev_attr_gt_RP0_freq_mhz) {
diff --git a/drivers/gpu/drm/i915/i915_ums.c b/drivers/gpu/drm/i915/i915_ums.c
index 967da4772c44..caa18e855815 100644
--- a/drivers/gpu/drm/i915/i915_ums.c
+++ b/drivers/gpu/drm/i915/i915_ums.c
@@ -270,6 +270,18 @@ void i915_save_display_reg(struct drm_device *dev)
 	}
 	/* FIXME: regfile.save TV & SDVO state */
 
+	/* Backlight */
+	if (HAS_PCH_SPLIT(dev)) {
+		dev_priv->regfile.saveBLC_PWM_CTL = I915_READ(BLC_PWM_PCH_CTL1);
+		dev_priv->regfile.saveBLC_PWM_CTL2 = I915_READ(BLC_PWM_PCH_CTL2);
+		dev_priv->regfile.saveBLC_CPU_PWM_CTL = I915_READ(BLC_PWM_CPU_CTL);
+		dev_priv->regfile.saveBLC_CPU_PWM_CTL2 = I915_READ(BLC_PWM_CPU_CTL2);
+	} else {
+		dev_priv->regfile.saveBLC_PWM_CTL = I915_READ(BLC_PWM_CTL);
+		if (INTEL_INFO(dev)->gen >= 4)
+			dev_priv->regfile.saveBLC_PWM_CTL2 = I915_READ(BLC_PWM_CTL2);
+	}
+
 	return;
 }
 
@@ -280,6 +292,21 @@ void i915_restore_display_reg(struct drm_device *dev)
 	int dpll_b_reg, fpb0_reg, fpb1_reg;
 	int i;
 
+	/* Backlight */
+	if (HAS_PCH_SPLIT(dev)) {
+		I915_WRITE(BLC_PWM_PCH_CTL1, dev_priv->regfile.saveBLC_PWM_CTL);
+		I915_WRITE(BLC_PWM_PCH_CTL2, dev_priv->regfile.saveBLC_PWM_CTL2);
+		/* NOTE: BLC_PWM_CPU_CTL must be written after BLC_PWM_CPU_CTL2;
+		 * otherwise we get blank eDP screen after S3 on some machines
+		 */
+		I915_WRITE(BLC_PWM_CPU_CTL2, dev_priv->regfile.saveBLC_CPU_PWM_CTL2);
+		I915_WRITE(BLC_PWM_CPU_CTL, dev_priv->regfile.saveBLC_CPU_PWM_CTL);
+	} else {
+		if (INTEL_INFO(dev)->gen >= 4)
+			I915_WRITE(BLC_PWM_CTL2, dev_priv->regfile.saveBLC_PWM_CTL2);
+		I915_WRITE(BLC_PWM_CTL, dev_priv->regfile.saveBLC_PWM_CTL);
+	}
+
 	/* Display port ratios (must be done before clock is set) */
 	if (SUPPORTS_INTEGRATED_DP(dev)) {
 		I915_WRITE(_PIPEA_DATA_M_G4X, dev_priv->regfile.savePIPEA_GMCH_DATA_M);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index e4fba39631a5..f22041973f3a 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -281,6 +281,34 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 	}
 }
 
+static void
+parse_lfp_backlight(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
+{
+	const struct bdb_lfp_backlight_data *backlight_data;
+	const struct bdb_lfp_backlight_data_entry *entry;
+
+	backlight_data = find_section(bdb, BDB_LVDS_BACKLIGHT);
+	if (!backlight_data)
+		return;
+
+	if (backlight_data->entry_size != sizeof(backlight_data->data[0])) {
+		DRM_DEBUG_KMS("Unsupported backlight data entry size %u\n",
+			      backlight_data->entry_size);
+		return;
+	}
+
+	entry = &backlight_data->data[panel_type];
+
+	dev_priv->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz;
+	dev_priv->vbt.backlight.active_low_pwm = entry->active_low_pwm;
+	DRM_DEBUG_KMS("VBT backlight PWM modulation frequency %u Hz, "
+		      "active %s, min brightness %u, level %u\n",
+		      dev_priv->vbt.backlight.pwm_freq_hz,
+		      dev_priv->vbt.backlight.active_low_pwm ? "low" : "high",
+		      entry->min_brightness,
+		      backlight_data->level[panel_type]);
+}
+
 /* Try to find sdvo panel data */
 static void
 parse_sdvo_panel_data(struct drm_i915_private *dev_priv,
@@ -327,12 +355,12 @@ static int intel_bios_ssc_frequency(struct drm_device *dev,
 {
 	switch (INTEL_INFO(dev)->gen) {
 	case 2:
-		return alternate ? 66 : 48;
+		return alternate ? 66667 : 48000;
 	case 3:
 	case 4:
-		return alternate ? 100 : 96;
+		return alternate ? 100000 : 96000;
 	default:
-		return alternate ? 100 : 120;
+		return alternate ? 100000 : 120000;
 	}
 }
 
@@ -796,7 +824,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	 */
 	dev_priv->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(dev,
 			!HAS_PCH_SPLIT(dev));
-	DRM_DEBUG_KMS("Set default to SSC at %dMHz\n", dev_priv->vbt.lvds_ssc_freq);
+	DRM_DEBUG_KMS("Set default to SSC at %d kHz\n", dev_priv->vbt.lvds_ssc_freq);
 
 	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
 		struct ddi_vbt_port_info *info =
@@ -894,6 +922,7 @@ intel_parse_bios(struct drm_device *dev)
 	parse_general_features(dev_priv, bdb);
 	parse_general_definitions(dev_priv, bdb);
 	parse_lfp_panel_data(dev_priv, bdb);
+	parse_lfp_backlight(dev_priv, bdb);
 	parse_sdvo_panel_data(dev_priv, bdb);
 	parse_sdvo_device_mapping(dev_priv, bdb);
 	parse_device_mapping(dev_priv, bdb);
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index f580a2b0ddd3..282de5e9f39d 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -39,7 +39,7 @@ struct vbt_header {
 	u8 reserved0;
 	u32 bdb_offset;			/**< from beginning of VBT */
 	u32 aim_offset[4];		/**< from beginning of VBT */
-} __attribute__((packed));
+} __packed;
 
 struct bdb_header {
 	u8 signature[16];		/**< Always 'BIOS_DATA_BLOCK' */
@@ -65,7 +65,7 @@ struct vbios_data {
 	u8 rsvd4; /* popup memory size */
 	u8 resize_pci_bios;
 	u8 rsvd5; /* is crt already on ddc2 */
-} __attribute__((packed));
+} __packed;
 
 /*
  * There are several types of BIOS data blocks (BDBs), each block has
@@ -142,7 +142,7 @@ struct bdb_general_features {
 	u8 dp_ssc_enb:1;	/* PCH attached eDP supports SSC */
 	u8 dp_ssc_freq:1;	/* SSC freq for PCH attached eDP */
 	u8 rsvd11:3; /* finish byte */
-} __attribute__((packed));
+} __packed;
 
 /* pre-915 */
 #define GPIO_PIN_DVI_LVDS	0x03 /* "DVI/LVDS DDC GPIO pins" */
@@ -225,7 +225,7 @@ struct old_child_dev_config {
 	u8  dvo2_wiring;
 	u16 extended_type;
 	u8  dvo_function;
-} __attribute__((packed));
+} __packed;
 
 /* This one contains field offsets that are known to be common for all BDB
  * versions. Notice that the meaning of the contents contents may still change,
@@ -238,7 +238,7 @@ struct common_child_dev_config {
 	u8 not_common2[2];
 	u8 ddc_pin;
 	u16 edid_ptr;
-} __attribute__((packed));
+} __packed;
 
 /* This field changes depending on the BDB version, so the most reliable way to
  * read it is by checking the BDB version and reading the raw pointer. */
@@ -279,7 +279,7 @@ struct bdb_general_definitions {
 	 *	     sizeof(child_device_config);
 	 */
 	union child_device_config devices[0];
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_options {
 	u8 panel_type;
@@ -293,7 +293,7 @@ struct bdb_lvds_options {
 	u8 lvds_edid:1;
 	u8 rsvd2:1;
 	u8 rsvd4;
-} __attribute__((packed));
+} __packed;
 
 /* LFP pointer table contains entries to the struct below */
 struct bdb_lvds_lfp_data_ptr {
@@ -303,12 +303,12 @@ struct bdb_lvds_lfp_data_ptr {
 	u8 dvo_table_size;
 	u16 panel_pnp_id_offset;
 	u8 pnp_table_size;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_ptrs {
 	u8 lvds_entries; /* followed by one or more lvds_data_ptr structs */
 	struct bdb_lvds_lfp_data_ptr ptr[16];
-} __attribute__((packed));
+} __packed;
 
 /* LFP data has 3 blocks per entry */
 struct lvds_fp_timing {
@@ -325,7 +325,7 @@ struct lvds_fp_timing {
 	u32 pfit_reg;
 	u32 pfit_reg_val;
 	u16 terminator;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_dvo_timing {
 	u16 clock;		/**< In 10khz */
@@ -353,7 +353,7 @@ struct lvds_dvo_timing {
 	u8 vsync_positive:1;
 	u8 hsync_positive:1;
 	u8 rsvd2:1;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_pnp_id {
 	u16 mfg_name;
@@ -361,17 +361,33 @@ struct lvds_pnp_id {
 	u32 serial;
 	u8 mfg_week;
 	u8 mfg_year;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_entry {
 	struct lvds_fp_timing fp_timing;
 	struct lvds_dvo_timing dvo_timing;
 	struct lvds_pnp_id pnp_id;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data {
 	struct bdb_lvds_lfp_data_entry data[16];
-} __attribute__((packed));
+} __packed;
+
+struct bdb_lfp_backlight_data_entry {
+	u8 type:2;
+	u8 active_low_pwm:1;
+	u8 obsolete1:5;
+	u16 pwm_freq_hz;
+	u8 min_brightness;
+	u8 obsolete2;
+	u8 obsolete3;
+} __packed;
+
+struct bdb_lfp_backlight_data {
+	u8 entry_size;
+	struct bdb_lfp_backlight_data_entry data[16];
+	u8 level[16];
+} __packed;
 
 struct aimdb_header {
 	char signature[16];
@@ -379,12 +395,12 @@ struct aimdb_header {
 	u16 aimdb_version;
 	u16 aimdb_header_size;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_block {
 	u8 aimdb_id;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_panel_data {
 	u16 fp_timing_offset;
@@ -395,12 +411,12 @@ struct vch_panel_data {
 	u8 text_fitting_size;
 	u16 graphics_fitting_offset;
 	u8 graphics_fitting_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_bdb_22 {
 	struct aimdb_block aimdb_block;
 	struct vch_panel_data panels[16];
-} __attribute__((packed));
+} __packed;
 
 struct bdb_sdvo_lvds_options {
 	u8 panel_backlight;
@@ -416,7 +432,7 @@ struct bdb_sdvo_lvds_options {
 	u8 panel_misc_bits_2;
 	u8 panel_misc_bits_3;
 	u8 panel_misc_bits_4;
-} __attribute__((packed));
+} __packed;
 
 
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
@@ -462,7 +478,7 @@ struct bdb_driver_features {
 
 	u8 hdmi_termination;
 	u8 custom_vbt_version;
-} __attribute__((packed));
+} __packed;
 
 #define EDP_18BPP	0
 #define EDP_24BPP	1
@@ -487,14 +503,14 @@ struct edp_power_seq {
 	u16 t9;
 	u16 t10;
 	u16 t11_t12;
-} __attribute__ ((packed));
+} __packed;
 
 struct edp_link_params {
 	u8 rate:4;
 	u8 lanes:4;
 	u8 preemphasis:4;
 	u8 vswing:4;
-} __attribute__ ((packed));
+} __packed;
 
 struct bdb_edp {
 	struct edp_power_seq power_seqs[16];
@@ -505,7 +521,7 @@ struct bdb_edp {
 	/* ith bit indicates enabled/disabled for (i+1)th panel */
 	u16 edp_s3d_feature;
 	u16 edp_t3_optimization;
-} __attribute__ ((packed));
+} __packed;
 
 void intel_setup_bios(struct drm_device *dev);
 int intel_parse_bios(struct drm_device *dev);
@@ -733,6 +749,6 @@ struct bdb_mipi {
 	u32 hl_switch_cnt;
 	u32 lp_byte_clk;
 	u32 clk_lane_switch_cnt;
-} __attribute__((packed));
+} __packed;
 
 #endif /* _I830_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index b5b1b9b23adf..e2e39e65f109 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -222,8 +222,9 @@ static void intel_crt_dpms(struct drm_connector *connector, int mode)
 	intel_modeset_check_state(connector->dev);
 }
 
-static int intel_crt_mode_valid(struct drm_connector *connector,
-				struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_crt_mode_valid(struct drm_connector *connector,
+		     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b69dc3e66c16..e06b9e017d6b 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -73,7 +73,7 @@ static const u32 hsw_ddi_translations_hdmi[] = {
 };
 
 static const u32 bdw_ddi_translations_edp[] = {
-	0x00FFFFFF, 0x00000012,		/* DP parameters */
+	0x00FFFFFF, 0x00000012,		/* eDP parameters */
 	0x00EBAFFF, 0x00020011,
 	0x00C71FFF, 0x0006000F,
 	0x00FFFFFF, 0x00020011,
@@ -696,25 +696,25 @@ intel_ddi_calculate_wrpll(int clock /* in Hz */,
 	*n2_out = best.n2;
 	*p_out = best.p;
 	*r2_out = best.r2;
-
-	DRM_DEBUG_KMS("WRPLL: %dHz refresh rate with p=%d, n2=%d r2=%d\n",
-		      clock, *p_out, *n2_out, *r2_out);
 }
 
-bool intel_ddi_pll_mode_set(struct drm_crtc *crtc)
+/*
+ * Tries to find a PLL for the CRTC. If it finds, it increases the refcount and
+ * stores it in intel_crtc->ddi_pll_sel, so other mode sets won't be able to
+ * steal the selected PLL. You need to call intel_ddi_pll_enable to actually
+ * enable the PLL.
+ */
+bool intel_ddi_pll_select(struct intel_crtc *intel_crtc)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_crtc *crtc = &intel_crtc->base;
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
 	struct intel_ddi_plls *plls = &dev_priv->ddi_plls;
 	int type = intel_encoder->type;
 	enum pipe pipe = intel_crtc->pipe;
-	uint32_t reg, val;
 	int clock = intel_crtc->config.port_clock;
 
-	/* TODO: reuse PLLs when possible (compare values) */
-
 	intel_ddi_put_crtc_pll(crtc);
 
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
@@ -736,66 +736,145 @@ bool intel_ddi_pll_mode_set(struct drm_crtc *crtc)
 			return false;
 		}
 
-		/* We don't need to turn any PLL on because we'll use LCPLL. */
-		return true;
-
 	} else if (type == INTEL_OUTPUT_HDMI) {
+		uint32_t reg, val;
 		unsigned p, n2, r2;
 
-		if (plls->wrpll1_refcount == 0) {
+		intel_ddi_calculate_wrpll(clock * 1000, &r2, &n2, &p);
+
+		val = WRPLL_PLL_ENABLE | WRPLL_PLL_SELECT_LCPLL_2700 |
+		      WRPLL_DIVIDER_REFERENCE(r2) | WRPLL_DIVIDER_FEEDBACK(n2) |
+		      WRPLL_DIVIDER_POST(p);
+
+		if (val == I915_READ(WRPLL_CTL1)) {
+			DRM_DEBUG_KMS("Reusing WRPLL 1 on pipe %c\n",
+				      pipe_name(pipe));
+			reg = WRPLL_CTL1;
+		} else if (val == I915_READ(WRPLL_CTL2)) {
+			DRM_DEBUG_KMS("Reusing WRPLL 2 on pipe %c\n",
+				      pipe_name(pipe));
+			reg = WRPLL_CTL2;
+		} else if (plls->wrpll1_refcount == 0) {
 			DRM_DEBUG_KMS("Using WRPLL 1 on pipe %c\n",
 				      pipe_name(pipe));
-			plls->wrpll1_refcount++;
 			reg = WRPLL_CTL1;
-			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_WRPLL1;
 		} else if (plls->wrpll2_refcount == 0) {
 			DRM_DEBUG_KMS("Using WRPLL 2 on pipe %c\n",
 				      pipe_name(pipe));
-			plls->wrpll2_refcount++;
 			reg = WRPLL_CTL2;
-			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_WRPLL2;
 		} else {
 			DRM_ERROR("No WRPLLs available!\n");
 			return false;
 		}
 
-		WARN(I915_READ(reg) & WRPLL_PLL_ENABLE,
-		     "WRPLL already enabled\n");
+		DRM_DEBUG_KMS("WRPLL: %dKHz refresh rate with p=%d, n2=%d r2=%d\n",
+			      clock, p, n2, r2);
 
-		intel_ddi_calculate_wrpll(clock * 1000, &r2, &n2, &p);
-
-		val = WRPLL_PLL_ENABLE | WRPLL_PLL_SELECT_LCPLL_2700 |
-		      WRPLL_DIVIDER_REFERENCE(r2) | WRPLL_DIVIDER_FEEDBACK(n2) |
-		      WRPLL_DIVIDER_POST(p);
+		if (reg == WRPLL_CTL1) {
+			plls->wrpll1_refcount++;
+			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_WRPLL1;
+		} else {
+			plls->wrpll2_refcount++;
+			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_WRPLL2;
+		}
 
 	} else if (type == INTEL_OUTPUT_ANALOG) {
 		if (plls->spll_refcount == 0) {
 			DRM_DEBUG_KMS("Using SPLL on pipe %c\n",
 				      pipe_name(pipe));
 			plls->spll_refcount++;
-			reg = SPLL_CTL;
 			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_SPLL;
 		} else {
 			DRM_ERROR("SPLL already in use\n");
 			return false;
 		}
 
-		WARN(I915_READ(reg) & SPLL_PLL_ENABLE,
-		     "SPLL already enabled\n");
-
-		val = SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC;
-
 	} else {
 		WARN(1, "Invalid DDI encoder type %d\n", type);
 		return false;
 	}
 
-	I915_WRITE(reg, val);
-	udelay(20);
-
 	return true;
 }
 
+/*
+ * To be called after intel_ddi_pll_select(). That one selects the PLL to be
+ * used, this one actually enables the PLL.
+ */
+void intel_ddi_pll_enable(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ddi_plls *plls = &dev_priv->ddi_plls;
+	int clock = crtc->config.port_clock;
+	uint32_t reg, cur_val, new_val;
+	int refcount;
+	const char *pll_name;
+	uint32_t enable_bit = (1 << 31);
+	unsigned int p, n2, r2;
+
+	BUILD_BUG_ON(enable_bit != SPLL_PLL_ENABLE);
+	BUILD_BUG_ON(enable_bit != WRPLL_PLL_ENABLE);
+
+	switch (crtc->ddi_pll_sel) {
+	case PORT_CLK_SEL_LCPLL_2700:
+	case PORT_CLK_SEL_LCPLL_1350:
+	case PORT_CLK_SEL_LCPLL_810:
+		/*
+		 * LCPLL should always be enabled at this point of the mode set
+		 * sequence, so nothing to do.
+		 */
+		return;
+
+	case PORT_CLK_SEL_SPLL:
+		pll_name = "SPLL";
+		reg = SPLL_CTL;
+		refcount = plls->spll_refcount;
+		new_val = SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz |
+			  SPLL_PLL_SSC;
+		break;
+
+	case PORT_CLK_SEL_WRPLL1:
+	case PORT_CLK_SEL_WRPLL2:
+		if (crtc->ddi_pll_sel == PORT_CLK_SEL_WRPLL1) {
+			pll_name = "WRPLL1";
+			reg = WRPLL_CTL1;
+			refcount = plls->wrpll1_refcount;
+		} else {
+			pll_name = "WRPLL2";
+			reg = WRPLL_CTL2;
+			refcount = plls->wrpll2_refcount;
+		}
+
+		intel_ddi_calculate_wrpll(clock * 1000, &r2, &n2, &p);
+
+		new_val = WRPLL_PLL_ENABLE | WRPLL_PLL_SELECT_LCPLL_2700 |
+			  WRPLL_DIVIDER_REFERENCE(r2) |
+			  WRPLL_DIVIDER_FEEDBACK(n2) | WRPLL_DIVIDER_POST(p);
+
+		break;
+
+	case PORT_CLK_SEL_NONE:
+		WARN(1, "Bad selected pll: PORT_CLK_SEL_NONE\n");
+		return;
+	default:
+		WARN(1, "Bad selected pll: 0x%08x\n", crtc->ddi_pll_sel);
+		return;
+	}
+
+	cur_val = I915_READ(reg);
+
+	WARN(refcount < 1, "Bad %s refcount: %d\n", pll_name, refcount);
+	if (refcount == 1) {
+		WARN(cur_val & enable_bit, "%s already enabled\n", pll_name);
+		I915_WRITE(reg, new_val);
+		POSTING_READ(reg);
+		udelay(20);
+	} else {
+		WARN((cur_val & enable_bit) == 0, "%s disabled\n", pll_name);
+	}
+}
+
 void intel_ddi_set_pipe_settings(struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
@@ -1121,9 +1200,7 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 
 	if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
-		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_panel_on(intel_dp);
-		ironlake_edp_panel_vdd_off(intel_dp, true);
 	}
 
 	WARN_ON(intel_crtc->ddi_pll_sel == PORT_CLK_SEL_NONE);
@@ -1166,7 +1243,6 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
 
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
-		ironlake_edp_panel_vdd_on(intel_dp);
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 		ironlake_edp_panel_off(intel_dp);
 	}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2bde35d34eb9..9fa24347963a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -90,8 +90,8 @@ intel_fdi_link_freq(struct drm_device *dev)
 
 static const intel_limit_t intel_limits_i8xx_dac = {
 	.dot = { .min = 25000, .max = 350000 },
-	.vco = { .min = 930000, .max = 1400000 },
-	.n = { .min = 3, .max = 16 },
+	.vco = { .min = 908000, .max = 1512000 },
+	.n = { .min = 2, .max = 16 },
 	.m = { .min = 96, .max = 140 },
 	.m1 = { .min = 18, .max = 26 },
 	.m2 = { .min = 6, .max = 16 },
@@ -103,8 +103,8 @@ static const intel_limit_t intel_limits_i8xx_dac = {
 
 static const intel_limit_t intel_limits_i8xx_dvo = {
 	.dot = { .min = 25000, .max = 350000 },
-	.vco = { .min = 930000, .max = 1400000 },
-	.n = { .min = 3, .max = 16 },
+	.vco = { .min = 908000, .max = 1512000 },
+	.n = { .min = 2, .max = 16 },
 	.m = { .min = 96, .max = 140 },
 	.m1 = { .min = 18, .max = 26 },
 	.m2 = { .min = 6, .max = 16 },
@@ -116,8 +116,8 @@ static const intel_limit_t intel_limits_i8xx_dvo = {
 
 static const intel_limit_t intel_limits_i8xx_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
-	.vco = { .min = 930000, .max = 1400000 },
-	.n = { .min = 3, .max = 16 },
+	.vco = { .min = 908000, .max = 1512000 },
+	.n = { .min = 2, .max = 16 },
 	.m = { .min = 96, .max = 140 },
 	.m1 = { .min = 18, .max = 26 },
 	.m2 = { .min = 6, .max = 16 },
@@ -329,6 +329,8 @@ static void vlv_clock(int refclk, intel_clock_t *clock)
 {
 	clock->m = clock->m1 * clock->m2;
 	clock->p = clock->p1 * clock->p2;
+	if (WARN_ON(clock->n == 0 || clock->p == 0))
+		return;
 	clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n);
 	clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
 }
@@ -430,6 +432,8 @@ static void pineview_clock(int refclk, intel_clock_t *clock)
 {
 	clock->m = clock->m2 + 2;
 	clock->p = clock->p1 * clock->p2;
+	if (WARN_ON(clock->n == 0 || clock->p == 0))
+		return;
 	clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n);
 	clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
 }
@@ -443,6 +447,8 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
 {
 	clock->m = i9xx_dpll_compute_m(clock);
 	clock->p = clock->p1 * clock->p2;
+	if (WARN_ON(clock->n + 2 == 0 || clock->p == 0))
+		return;
 	clock->vco = DIV_ROUND_CLOSEST(refclk * clock->m, clock->n + 2);
 	clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
 }
@@ -748,10 +754,10 @@ enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
 	return intel_crtc->config.cpu_transcoder;
 }
 
-static void ironlake_wait_for_vblank(struct drm_device *dev, int pipe)
+static void g4x_wait_for_vblank(struct drm_device *dev, int pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 frame, frame_reg = PIPEFRAME(pipe);
+	u32 frame, frame_reg = PIPE_FRMCOUNT_GM45(pipe);
 
 	frame = I915_READ(frame_reg);
 
@@ -772,8 +778,8 @@ void intel_wait_for_vblank(struct drm_device *dev, int pipe)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipestat_reg = PIPESTAT(pipe);
 
-	if (INTEL_INFO(dev)->gen >= 5) {
-		ironlake_wait_for_vblank(dev, pipe);
+	if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
+		g4x_wait_for_vblank(dev, pipe);
 		return;
 	}
 
@@ -1205,15 +1211,12 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
+static void ibx_assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
 {
 	u32 val;
 	bool enabled;
 
-	if (HAS_PCH_LPT(dev_priv->dev)) {
-		DRM_DEBUG_DRIVER("LPT does not has PCH refclk, skipping check\n");
-		return;
-	}
+	WARN_ON(!(HAS_PCH_IBX(dev_priv->dev) || HAS_PCH_CPT(dev_priv->dev)));
 
 	val = I915_READ(PCH_DREF_CONTROL);
 	enabled = !!(val & (DREF_SSC_SOURCE_MASK | DREF_NONSPREAD_SOURCE_MASK |
@@ -1361,6 +1364,24 @@ static void intel_init_dpio(struct drm_device *dev)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
+	DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
+}
+
+static void intel_reset_dpio(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_VALLEYVIEW(dev))
+		return;
+
+	/*
+	 * Enable the CRI clock source so we can get at the display and the
+	 * reference clock for VGA hotplug / manual detection.
+	 */
+	I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+		   DPLL_REFA_CLK_ENABLE_VLV |
+		   DPLL_INTEGRATED_CRI_CLK_VLV);
+
 	/*
 	 * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx -
 	 *  6.	De-assert cmn_reset/side_reset. Same as VLV X0.
@@ -1487,25 +1508,35 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	/* Make sure the pipe isn't still relying on us */
 	assert_pipe_disabled(dev_priv, pipe);
 
-	/* Leave integrated clock source enabled */
+	/*
+	 * Leave integrated clock source and reference clock enabled for pipe B.
+	 * The latter is needed for VGA hotplug / manual detection.
+	 */
 	if (pipe == PIPE_B)
-		val = DPLL_INTEGRATED_CRI_CLK_VLV;
+		val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REFA_CLK_ENABLE_VLV;
 	I915_WRITE(DPLL(pipe), val);
 	POSTING_READ(DPLL(pipe));
 }
 
-void vlv_wait_port_ready(struct drm_i915_private *dev_priv, int port)
+void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
+		struct intel_digital_port *dport)
 {
 	u32 port_mask;
 
-	if (!port)
+	switch (dport->port) {
+	case PORT_B:
 		port_mask = DPLL_PORTB_READY_MASK;
-	else
+		break;
+	case PORT_C:
 		port_mask = DPLL_PORTC_READY_MASK;
+		break;
+	default:
+		BUG();
+	}
 
 	if (wait_for((I915_READ(DPLL(0)) & port_mask) == 0, 1000))
 		WARN(1, "timed out waiting for port %c ready: 0x%08x\n",
-		     'B' + port, I915_READ(DPLL(0)));
+		     port_name(dport->port), I915_READ(DPLL(0)));
 }
 
 /**
@@ -2083,8 +2114,8 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_INFO(dev)->gen >= 4) {
-		I915_MODIFY_DISPBASE(DSPSURF(plane),
-				     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+		I915_WRITE(DSPSURF(plane),
+			   i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
@@ -2174,8 +2205,8 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
 		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
-	I915_MODIFY_DISPBASE(DSPSURF(plane),
-			     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	I915_WRITE(DSPSURF(plane),
+		   i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
 	} else {
@@ -2233,7 +2264,12 @@ void intel_display_handle_reset(struct drm_device *dev)
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 		mutex_lock(&crtc->mutex);
-		if (intel_crtc->active)
+		/*
+		 * FIXME: Once we have proper support for primary planes (and
+		 * disabling them without disabling the entire crtc) allow again
+		 * a NULL crtc->fb.
+		 */
+		if (intel_crtc->active && crtc->fb)
 			dev_priv->display.update_plane(crtc, crtc->fb,
 						       crtc->x, crtc->y);
 		mutex_unlock(&crtc->mutex);
@@ -2350,6 +2386,8 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 			I915_WRITE(PF_WIN_POS(intel_crtc->pipe), 0);
 			I915_WRITE(PF_WIN_SZ(intel_crtc->pipe), 0);
 		}
+		intel_crtc->config.pipe_src_w = adjusted_mode->crtc_hdisplay;
+		intel_crtc->config.pipe_src_h = adjusted_mode->crtc_vdisplay;
 	}
 
 	ret = dev_priv->display.update_plane(crtc, fb, x, y);
@@ -2944,6 +2982,30 @@ static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
 	return pending;
 }
 
+bool intel_has_pending_fb_unpin(struct drm_device *dev)
+{
+	struct intel_crtc *crtc;
+
+	/* Note that we don't need to be called with mode_config.lock here
+	 * as our list of CRTC objects is static for the lifetime of the
+	 * device and so cannot disappear as we iterate. Similarly, we can
+	 * happily treat the predicates as racy, atomic checks as userspace
+	 * cannot claim and pin a new fb without at least acquring the
+	 * struct_mutex and so serialising with us.
+	 */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+		if (atomic_read(&crtc->unpin_work_count) == 0)
+			continue;
+
+		if (crtc->unpin_work)
+			intel_wait_for_vblank(dev, crtc->pipe);
+
+		return true;
+	}
+
+	return false;
+}
+
 static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -3399,9 +3461,8 @@ void hsw_enable_ips(struct intel_crtc *crtc)
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		/* Quoting Art Runyan: "its not safe to expect any particular
 		 * value in IPS_CTL bit 31 after enabling IPS through the
-		 * mailbox." Therefore we need to defer waiting on the state
-		 * change.
-		 * TODO: need to fix this for state checker
+		 * mailbox." Moreover, the mailbox may return a bogus state,
+		 * so we need to just enable it and continue on.
 		 */
 	} else {
 		I915_WRITE(IPS_CTL, IPS_ENABLE);
@@ -3428,9 +3489,10 @@ void hsw_disable_ips(struct intel_crtc *crtc)
 		mutex_lock(&dev_priv->rps.hw_lock);
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0));
 		mutex_unlock(&dev_priv->rps.hw_lock);
-	} else
+	} else {
 		I915_WRITE(IPS_CTL, 0);
-	POSTING_READ(IPS_CTL);
+		POSTING_READ(IPS_CTL);
+	}
 
 	/* We need to wait for a vblank before we can disable the plane. */
 	intel_wait_for_vblank(dev, crtc->pipe);
@@ -3465,7 +3527,7 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc)
 	/* Workaround : Do not read or write the pipe palette/gamma data while
 	 * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled.
 	 */
-	if (intel_crtc->config.ips_enabled &&
+	if (IS_HASWELL(dev) && intel_crtc->config.ips_enabled &&
 	    ((I915_READ(GAMMA_MODE(pipe)) & GAMMA_MODE_MODE_MASK) ==
 	     GAMMA_MODE_MODE_SPLIT)) {
 		hsw_disable_ips(intel_crtc);
@@ -3910,6 +3972,174 @@ static void i9xx_pfit_enable(struct intel_crtc *crtc)
 	I915_WRITE(BCLRPAT(crtc->pipe), 0);
 }
 
+int valleyview_get_vco(struct drm_i915_private *dev_priv)
+{
+	int hpll_freq, vco_freq[] = { 800, 1600, 2000, 2400 };
+
+	/* Obtain SKU information */
+	mutex_lock(&dev_priv->dpio_lock);
+	hpll_freq = vlv_cck_read(dev_priv, CCK_FUSE_REG) &
+		CCK_FUSE_HPLL_FREQ_MASK;
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return vco_freq[hpll_freq];
+}
+
+/* Adjust CDclk dividers to allow high res or save power if possible */
+static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val, cmd;
+
+	if (cdclk >= 320) /* jump to highest voltage for 400MHz too */
+		cmd = 2;
+	else if (cdclk == 266)
+		cmd = 1;
+	else
+		cmd = 0;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+	val &= ~DSPFREQGUAR_MASK;
+	val |= (cmd << DSPFREQGUAR_SHIFT);
+	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val);
+	if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) &
+		      DSPFREQSTAT_MASK) == (cmd << DSPFREQSTAT_SHIFT),
+		     50)) {
+		DRM_ERROR("timed out waiting for CDclk change\n");
+	}
+	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	if (cdclk == 400) {
+		u32 divider, vco;
+
+		vco = valleyview_get_vco(dev_priv);
+		divider = ((vco << 1) / cdclk) - 1;
+
+		mutex_lock(&dev_priv->dpio_lock);
+		/* adjust cdclk divider */
+		val = vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL);
+		val &= ~0xf;
+		val |= divider;
+		vlv_cck_write(dev_priv, CCK_DISPLAY_CLOCK_CONTROL, val);
+		mutex_unlock(&dev_priv->dpio_lock);
+	}
+
+	mutex_lock(&dev_priv->dpio_lock);
+	/* adjust self-refresh exit latency value */
+	val = vlv_bunit_read(dev_priv, BUNIT_REG_BISOC);
+	val &= ~0x7f;
+
+	/*
+	 * For high bandwidth configs, we set a higher latency in the bunit
+	 * so that the core display fetch happens in time to avoid underruns.
+	 */
+	if (cdclk == 400)
+		val |= 4500 / 250; /* 4.5 usec */
+	else
+		val |= 3000 / 250; /* 3.0 usec */
+	vlv_bunit_write(dev_priv, BUNIT_REG_BISOC, val);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	/* Since we changed the CDclk, we need to update the GMBUSFREQ too */
+	intel_i2c_reset(dev);
+}
+
+static int valleyview_cur_cdclk(struct drm_i915_private *dev_priv)
+{
+	int cur_cdclk, vco;
+	int divider;
+
+	vco = valleyview_get_vco(dev_priv);
+
+	mutex_lock(&dev_priv->dpio_lock);
+	divider = vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	divider &= 0xf;
+
+	cur_cdclk = (vco << 1) / (divider + 1);
+
+	return cur_cdclk;
+}
+
+static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv,
+				 int max_pixclk)
+{
+	int cur_cdclk;
+
+	cur_cdclk = valleyview_cur_cdclk(dev_priv);
+
+	/*
+	 * Really only a few cases to deal with, as only 4 CDclks are supported:
+	 *   200MHz
+	 *   267MHz
+	 *   320MHz
+	 *   400MHz
+	 * So we check to see whether we're above 90% of the lower bin and
+	 * adjust if needed.
+	 */
+	if (max_pixclk > 288000) {
+		return 400;
+	} else if (max_pixclk > 240000) {
+		return 320;
+	} else
+		return 266;
+	/* Looks like the 200MHz CDclk freq doesn't work on some configs */
+}
+
+static int intel_mode_max_pixclk(struct drm_i915_private *dev_priv,
+				 unsigned modeset_pipes,
+				 struct intel_crtc_config *pipe_config)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_crtc *intel_crtc;
+	int max_pixclk = 0;
+
+	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
+			    base.head) {
+		if (modeset_pipes & (1 << intel_crtc->pipe))
+			max_pixclk = max(max_pixclk,
+					 pipe_config->adjusted_mode.crtc_clock);
+		else if (intel_crtc->base.enabled)
+			max_pixclk = max(max_pixclk,
+					 intel_crtc->config.adjusted_mode.crtc_clock);
+	}
+
+	return max_pixclk;
+}
+
+static void valleyview_modeset_global_pipes(struct drm_device *dev,
+					    unsigned *prepare_pipes,
+					    unsigned modeset_pipes,
+					    struct intel_crtc_config *pipe_config)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc;
+	int max_pixclk = intel_mode_max_pixclk(dev_priv, modeset_pipes,
+					       pipe_config);
+	int cur_cdclk = valleyview_cur_cdclk(dev_priv);
+
+	if (valleyview_calc_cdclk(dev_priv, max_pixclk) == cur_cdclk)
+		return;
+
+	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
+			    base.head)
+		if (intel_crtc->base.enabled)
+			*prepare_pipes |= (1 << intel_crtc->pipe);
+}
+
+static void valleyview_modeset_global_resources(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int max_pixclk = intel_mode_max_pixclk(dev_priv, 0, NULL);
+	int cur_cdclk = valleyview_cur_cdclk(dev_priv);
+	int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
+
+	if (req_cdclk != cur_cdclk)
+		valleyview_set_cdclk(dev, req_cdclk);
+}
+
 static void valleyview_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -4570,9 +4800,8 @@ static int i9xx_get_refclk(struct drm_crtc *crtc, int num_connectors)
 		refclk = 100000;
 	} else if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) &&
 	    intel_panel_use_ssc(dev_priv) && num_connectors < 2) {
-		refclk = dev_priv->vbt.lvds_ssc_freq * 1000;
-		DRM_DEBUG_KMS("using SSC reference clock of %d MHz\n",
-			      refclk / 1000);
+		refclk = dev_priv->vbt.lvds_ssc_freq;
+		DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
 	} else if (!IS_GEN2(dev)) {
 		refclk = 96000;
 	} else {
@@ -4634,24 +4863,24 @@ static void vlv_pllb_recal_opamp(struct drm_i915_private *dev_priv, enum pipe
 	 * PLLB opamp always calibrates to max value of 0x3f, force enable it
 	 * and set it to a reasonable value instead.
 	 */
-	reg_val = vlv_dpio_read(dev_priv, pipe, DPIO_IREF(1));
+	reg_val = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW9(1));
 	reg_val &= 0xffffff00;
 	reg_val |= 0x00000030;
-	vlv_dpio_write(dev_priv, pipe, DPIO_IREF(1), reg_val);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW9(1), reg_val);
 
-	reg_val = vlv_dpio_read(dev_priv, pipe, DPIO_CALIBRATION);
+	reg_val = vlv_dpio_read(dev_priv, pipe, VLV_REF_DW13);
 	reg_val &= 0x8cffffff;
 	reg_val = 0x8c000000;
-	vlv_dpio_write(dev_priv, pipe, DPIO_CALIBRATION, reg_val);
+	vlv_dpio_write(dev_priv, pipe, VLV_REF_DW13, reg_val);
 
-	reg_val = vlv_dpio_read(dev_priv, pipe, DPIO_IREF(1));
+	reg_val = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW9(1));
 	reg_val &= 0xffffff00;
-	vlv_dpio_write(dev_priv, pipe, DPIO_IREF(1), reg_val);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW9(1), reg_val);
 
-	reg_val = vlv_dpio_read(dev_priv, pipe, DPIO_CALIBRATION);
+	reg_val = vlv_dpio_read(dev_priv, pipe, VLV_REF_DW13);
 	reg_val &= 0x00ffffff;
 	reg_val |= 0xb0000000;
-	vlv_dpio_write(dev_priv, pipe, DPIO_CALIBRATION, reg_val);
+	vlv_dpio_write(dev_priv, pipe, VLV_REF_DW13, reg_val);
 }
 
 static void intel_pch_transcoder_set_m_n(struct intel_crtc *crtc,
@@ -4720,15 +4949,15 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 		vlv_pllb_recal_opamp(dev_priv, pipe);
 
 	/* Set up Tx target for periodic Rcomp update */
-	vlv_dpio_write(dev_priv, pipe, DPIO_IREF_BCAST, 0x0100000f);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW9_BCAST, 0x0100000f);
 
 	/* Disable target IRef on PLL */
-	reg_val = vlv_dpio_read(dev_priv, pipe, DPIO_IREF_CTL(pipe));
+	reg_val = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW8(pipe));
 	reg_val &= 0x00ffffff;
-	vlv_dpio_write(dev_priv, pipe, DPIO_IREF_CTL(pipe), reg_val);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW8(pipe), reg_val);
 
 	/* Disable fast lock */
-	vlv_dpio_write(dev_priv, pipe, DPIO_FASTCLK_DISABLE, 0x610);
+	vlv_dpio_write(dev_priv, pipe, VLV_CMN_DW0, 0x610);
 
 	/* Set idtafcrecal before PLL is enabled */
 	mdiv = ((bestm1 << DPIO_M1DIV_SHIFT) | (bestm2 & DPIO_M2DIV_MASK));
@@ -4742,50 +4971,54 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	 * Note: don't use the DAC post divider as it seems unstable.
 	 */
 	mdiv |= (DPIO_POST_DIV_HDMIDP << DPIO_POST_DIV_SHIFT);
-	vlv_dpio_write(dev_priv, pipe, DPIO_DIV(pipe), mdiv);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW3(pipe), mdiv);
 
 	mdiv |= DPIO_ENABLE_CALIBRATION;
-	vlv_dpio_write(dev_priv, pipe, DPIO_DIV(pipe), mdiv);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW3(pipe), mdiv);
 
 	/* Set HBR and RBR LPF coefficients */
 	if (crtc->config.port_clock == 162000 ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_ANALOG) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI))
-		vlv_dpio_write(dev_priv, pipe, DPIO_LPF_COEFF(pipe),
+		vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW10(pipe),
 				 0x009f0003);
 	else
-		vlv_dpio_write(dev_priv, pipe, DPIO_LPF_COEFF(pipe),
+		vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW10(pipe),
 				 0x00d0000f);
 
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) {
 		/* Use SSC source */
 		if (!pipe)
-			vlv_dpio_write(dev_priv, pipe, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df40000);
 		else
-			vlv_dpio_write(dev_priv, pipe, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df70000);
 	} else { /* HDMI or VGA */
 		/* Use bend source */
 		if (!pipe)
-			vlv_dpio_write(dev_priv, pipe, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df70000);
 		else
-			vlv_dpio_write(dev_priv, pipe, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df40000);
 	}
 
-	coreclk = vlv_dpio_read(dev_priv, pipe, DPIO_CORE_CLK(pipe));
+	coreclk = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW7(pipe));
 	coreclk = (coreclk & 0x0000ff00) | 0x01c00000;
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP))
 		coreclk |= 0x01000000;
-	vlv_dpio_write(dev_priv, pipe, DPIO_CORE_CLK(pipe), coreclk);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW7(pipe), coreclk);
 
-	vlv_dpio_write(dev_priv, pipe, DPIO_PLL_CML(pipe), 0x87871000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW11(pipe), 0x87871000);
 
-	/* Enable DPIO clock input */
+	/*
+	 * Enable DPIO clock input. We should never disable the reference
+	 * clock for pipe B, since VGA hotplug / manual detection depends
+	 * on it.
+	 */
 	dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV |
 		DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV;
 	/* We should never disable this, set it here for state tracking */
@@ -5230,6 +5463,9 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
+	if (INTEL_INFO(dev)->gen <= 3 && (IS_I830(dev) || !IS_MOBILE(dev)))
+		return;
+
 	tmp = I915_READ(PFIT_CONTROL);
 	if (!(tmp & PFIT_ENABLE))
 		return;
@@ -5261,7 +5497,7 @@ static void vlv_crtc_clock_get(struct intel_crtc *crtc,
 	int refclk = 100000;
 
 	mutex_lock(&dev_priv->dpio_lock);
-	mdiv = vlv_dpio_read(dev_priv, pipe, DPIO_DIV(pipe));
+	mdiv = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW3(pipe));
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	clock.m1 = (mdiv >> DPIO_M1DIV_SHIFT) & 7;
@@ -5718,9 +5954,9 @@ static int ironlake_get_refclk(struct drm_crtc *crtc)
 	}
 
 	if (is_lvds && intel_panel_use_ssc(dev_priv) && num_connectors < 2) {
-		DRM_DEBUG_KMS("using SSC reference clock of %d MHz\n",
+		DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n",
 			      dev_priv->vbt.lvds_ssc_freq);
-		return dev_priv->vbt.lvds_ssc_freq * 1000;
+		return dev_priv->vbt.lvds_ssc_freq;
 	}
 
 	return 120000;
@@ -5982,7 +6218,7 @@ static uint32_t ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 	factor = 21;
 	if (is_lvds) {
 		if ((intel_panel_use_ssc(dev_priv) &&
-		     dev_priv->vbt.lvds_ssc_freq == 100) ||
+		     dev_priv->vbt.lvds_ssc_freq == 100000) ||
 		    (HAS_PCH_IBX(dev) && intel_is_dual_link_lvds(dev)))
 			factor = 25;
 	} else if (intel_crtc->config.sdvo_tv_clock)
@@ -6323,7 +6559,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	val = I915_READ(DEIMR);
-	WARN((val & ~DE_PCH_EVENT_IVB) != val,
+	WARN((val | DE_PCH_EVENT_IVB) != 0xffffffff,
 	     "Unexpected DEIMR bits enabled: 0x%x\n", val);
 	val = I915_READ(SDEIMR);
 	WARN((val | SDE_HOTPLUG_MASK_CPT) != 0xffffffff,
@@ -6402,7 +6638,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 
 	/* Make sure we're not on PC8 state before disabling PC8, otherwise
 	 * we'll hang the machine! */
-	gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	if (val & LCPLL_POWER_DOWN_ALLOW) {
 		val &= ~LCPLL_POWER_DOWN_ALLOW;
@@ -6436,7 +6672,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 			DRM_ERROR("Switching back to LCPLL failed\n");
 	}
 
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
 void hsw_enable_pc8_work(struct work_struct *__work)
@@ -6447,6 +6683,8 @@ void hsw_enable_pc8_work(struct work_struct *__work)
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t val;
 
+	WARN_ON(!HAS_PC8(dev));
+
 	if (dev_priv->pc8.enabled)
 		return;
 
@@ -6463,6 +6701,8 @@ void hsw_enable_pc8_work(struct work_struct *__work)
 	lpt_disable_clkout_dp(dev);
 	hsw_pc8_disable_interrupts(dev);
 	hsw_disable_lcpll(dev_priv, true, true);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 static void __hsw_enable_package_c8(struct drm_i915_private *dev_priv)
@@ -6492,12 +6732,16 @@ static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
 	if (dev_priv->pc8.disable_count != 1)
 		return;
 
+	WARN_ON(!HAS_PC8(dev));
+
 	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
 	if (!dev_priv->pc8.enabled)
 		return;
 
 	DRM_DEBUG_KMS("Disabling package C8+\n");
 
+	intel_runtime_pm_get(dev_priv);
+
 	hsw_restore_lcpll(dev_priv);
 	hsw_pc8_restore_interrupts(dev);
 	lpt_init_pch_refclk(dev);
@@ -6704,8 +6948,9 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 	int plane = intel_crtc->plane;
 	int ret;
 
-	if (!intel_ddi_pll_mode_set(crtc))
+	if (!intel_ddi_pll_select(intel_crtc))
 		return -EINVAL;
+	intel_ddi_pll_enable(intel_crtc);
 
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
@@ -6796,8 +7041,9 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	if (intel_display_power_enabled(dev, pfit_domain))
 		ironlake_get_pfit_config(crtc, pipe_config);
 
-	pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
-				   (I915_READ(IPS_CTL) & IPS_ENABLE);
+	if (IS_HASWELL(dev))
+		pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
+			(I915_READ(IPS_CTL) & IPS_ENABLE);
 
 	pipe_config->pixel_multiplier = 1;
 
@@ -7689,7 +7935,7 @@ static int i9xx_pll_refclk(struct drm_device *dev,
 	u32 dpll = pipe_config->dpll_hw_state.dpll;
 
 	if ((dpll & PLL_REF_INPUT_MASK) == PLLB_REF_INPUT_SPREADSPECTRUMIN)
-		return dev_priv->vbt.lvds_ssc_freq * 1000;
+		return dev_priv->vbt.lvds_ssc_freq;
 	else if (HAS_PCH_SPLIT(dev))
 		return 120000;
 	else if (!IS_GEN2(dev))
@@ -7752,12 +7998,17 @@ static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 		else
 			i9xx_clock(refclk, &clock);
 	} else {
-		bool is_lvds = (pipe == 1) && (I915_READ(LVDS) & LVDS_PORT_EN);
+		u32 lvds = IS_I830(dev) ? 0 : I915_READ(LVDS);
+		bool is_lvds = (pipe == 1) && (lvds & LVDS_PORT_EN);
 
 		if (is_lvds) {
 			clock.p1 = ffs((dpll & DPLL_FPA01_P1_POST_DIV_MASK_I830_LVDS) >>
 				       DPLL_FPA01_P1_POST_DIV_SHIFT);
-			clock.p2 = 14;
+
+			if (lvds & LVDS_CLKB_POWER_UP)
+				clock.p2 = 7;
+			else
+				clock.p2 = 14;
 		} else {
 			if (dpll & PLL_P1_DIVIDE_BY_TWO)
 				clock.p1 = 2;
@@ -8493,28 +8744,6 @@ static struct drm_crtc_helper_funcs intel_helper_funcs = {
 	.load_lut = intel_crtc_load_lut,
 };
 
-static bool intel_encoder_crtc_ok(struct drm_encoder *encoder,
-				  struct drm_crtc *crtc)
-{
-	struct drm_device *dev;
-	struct drm_crtc *tmp;
-	int crtc_mask = 1;
-
-	WARN(!crtc, "checking null crtc?\n");
-
-	dev = crtc->dev;
-
-	list_for_each_entry(tmp, &dev->mode_config.crtc_list, head) {
-		if (tmp == crtc)
-			break;
-		crtc_mask <<= 1;
-	}
-
-	if (encoder->possible_crtcs & crtc_mask)
-		return true;
-	return false;
-}
-
 /**
  * intel_modeset_update_staged_output_state
  *
@@ -9122,7 +9351,9 @@ intel_pipe_config_compare(struct drm_device *dev,
 		PIPE_CONF_CHECK_I(pch_pfit.size);
 	}
 
-	PIPE_CONF_CHECK_I(ips_enabled);
+	/* BDW+ don't expose a synchronous way to read the state */
+	if (IS_HASWELL(dev))
+		PIPE_CONF_CHECK_I(ips_enabled);
 
 	PIPE_CONF_CHECK_I(double_wide);
 
@@ -9368,21 +9599,19 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_display_mode *saved_mode, *saved_hwmode;
+	struct drm_display_mode *saved_mode;
 	struct intel_crtc_config *pipe_config = NULL;
 	struct intel_crtc *intel_crtc;
 	unsigned disable_pipes, prepare_pipes, modeset_pipes;
 	int ret = 0;
 
-	saved_mode = kcalloc(2, sizeof(*saved_mode), GFP_KERNEL);
+	saved_mode = kmalloc(sizeof(*saved_mode), GFP_KERNEL);
 	if (!saved_mode)
 		return -ENOMEM;
-	saved_hwmode = saved_mode + 1;
 
 	intel_modeset_affected_pipes(crtc, &modeset_pipes,
 				     &prepare_pipes, &disable_pipes);
 
-	*saved_hwmode = crtc->hwmode;
 	*saved_mode = crtc->mode;
 
 	/* Hack: Because we don't (yet) support global modeset on multiple
@@ -9402,6 +9631,21 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 				       "[modeset]");
 	}
 
+	/*
+	 * See if the config requires any additional preparation, e.g.
+	 * to adjust global state with pipes off.  We need to do this
+	 * here so we can get the modeset_pipe updated config for the new
+	 * mode set on this crtc.  For other crtcs we need to use the
+	 * adjusted_mode bits in the crtc directly.
+	 */
+	if (IS_VALLEYVIEW(dev)) {
+		valleyview_modeset_global_pipes(dev, &prepare_pipes,
+						modeset_pipes, pipe_config);
+
+		/* may have added more to prepare_pipes than we should */
+		prepare_pipes &= ~disable_pipes;
+	}
+
 	for_each_intel_crtc_masked(dev, disable_pipes, intel_crtc)
 		intel_crtc_disable(&intel_crtc->base);
 
@@ -9418,6 +9662,14 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 		/* mode_set/enable/disable functions rely on a correct pipe
 		 * config. */
 		to_intel_crtc(crtc)->config = *pipe_config;
+
+		/*
+		 * Calculate and store various constants which
+		 * are later needed by vblank and swap-completion
+		 * timestamping. They are derived from true hwmode.
+		 */
+		drm_calc_timestamping_constants(crtc,
+						&pipe_config->adjusted_mode);
 	}
 
 	/* Only after disabling all output pipelines that will be changed can we
@@ -9441,23 +9693,10 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 	for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc)
 		dev_priv->display.crtc_enable(&intel_crtc->base);
 
-	if (modeset_pipes) {
-		/* Store real post-adjustment hardware mode. */
-		crtc->hwmode = pipe_config->adjusted_mode;
-
-		/* Calculate and store various constants which
-		 * are later needed by vblank and swap-completion
-		 * timestamping. They are derived from true hwmode.
-		 */
-		drm_calc_timestamping_constants(crtc);
-	}
-
 	/* FIXME: add subpixel order */
 done:
-	if (ret && crtc->enabled) {
-		crtc->hwmode = *saved_hwmode;
+	if (ret && crtc->enabled)
 		crtc->mode = *saved_mode;
-	}
 
 out:
 	kfree(pipe_config);
@@ -9679,8 +9918,8 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 		}
 
 		/* Make sure the new CRTC will work with the encoder */
-		if (!intel_encoder_crtc_ok(&connector->new_encoder->base,
-					   new_crtc)) {
+		if (!drm_encoder_crtc_ok(&connector->new_encoder->base,
+					 new_crtc)) {
 			return -EINVAL;
 		}
 		connector->encoder->new_crtc = to_intel_crtc(new_crtc);
@@ -9694,17 +9933,21 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	/* Check for any encoders that needs to be disabled. */
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
 			    base.head) {
+		int num_connectors = 0;
 		list_for_each_entry(connector,
 				    &dev->mode_config.connector_list,
 				    base.head) {
 			if (connector->new_encoder == encoder) {
 				WARN_ON(!connector->new_encoder->new_crtc);
-
-				goto next_encoder;
+				num_connectors++;
 			}
 		}
-		encoder->new_crtc = NULL;
-next_encoder:
+
+		if (num_connectors == 0)
+			encoder->new_crtc = NULL;
+		else if (num_connectors > 1)
+			return -EINVAL;
+
 		/* Only now check for crtc changes so we don't miss encoders
 		 * that will be disabled. */
 		if (&encoder->new_crtc->base != encoder->base.crtc) {
@@ -9775,6 +10018,16 @@ static int intel_crtc_set_config(struct drm_mode_set *set)
 
 		ret = intel_pipe_set_base(set->crtc,
 					  set->x, set->y, set->fb);
+		/*
+		 * In the fastboot case this may be our only check of the
+		 * state after boot.  It would be better to only do it on
+		 * the first update, but we don't have a nice way of doing that
+		 * (and really, set_config isn't used much for high freq page
+		 * flipping, so increasing its cost here shouldn't be a big
+		 * deal).
+		 */
+		if (i915_fastboot && ret == 0)
+			intel_modeset_check_state(set->crtc->dev);
 	}
 
 	if (ret) {
@@ -9835,7 +10088,7 @@ static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
 	/* PCH refclock must be enabled first */
-	assert_pch_refclk_enabled(dev_priv);
+	ibx_assert_pch_refclk_enabled(dev_priv);
 
 	I915_WRITE(PCH_DPLL(pll->id), pll->hw_state.dpll);
 
@@ -9903,8 +10156,6 @@ static void intel_shared_dpll_init(struct drm_device *dev)
 		dev_priv->num_shared_dpll = 0;
 
 	BUG_ON(dev_priv->num_shared_dpll > I915_NUM_PLLS);
-	DRM_DEBUG_KMS("%i shared PLLs initialized\n",
-		      dev_priv->num_shared_dpll);
 }
 
 static void intel_crtc_init(struct drm_device *dev, int pipe)
@@ -9926,10 +10177,13 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 		intel_crtc->lut_b[i] = i;
 	}
 
-	/* Swap pipes & planes for FBC on pre-965 */
+	/*
+	 * On gen2/3 only plane A can do fbc, but the panel fitter and lvds port
+	 * is hooked to plane B. Hence we want plane A feeding pipe B.
+	 */
 	intel_crtc->pipe = pipe;
 	intel_crtc->plane = pipe;
-	if (IS_MOBILE(dev) && IS_GEN3(dev)) {
+	if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4) {
 		DRM_DEBUG_KMS("swapping pipes & planes for FBC\n");
 		intel_crtc->plane = !pipe;
 	}
@@ -10018,6 +10272,28 @@ static bool has_edp_a(struct drm_device *dev)
 	return true;
 }
 
+const char *intel_output_name(int output)
+{
+	static const char *names[] = {
+		[INTEL_OUTPUT_UNUSED] = "Unused",
+		[INTEL_OUTPUT_ANALOG] = "Analog",
+		[INTEL_OUTPUT_DVO] = "DVO",
+		[INTEL_OUTPUT_SDVO] = "SDVO",
+		[INTEL_OUTPUT_LVDS] = "LVDS",
+		[INTEL_OUTPUT_TVOUT] = "TV",
+		[INTEL_OUTPUT_HDMI] = "HDMI",
+		[INTEL_OUTPUT_DISPLAYPORT] = "DisplayPort",
+		[INTEL_OUTPUT_EDP] = "eDP",
+		[INTEL_OUTPUT_DSI] = "DSI",
+		[INTEL_OUTPUT_UNKNOWN] = "Unknown",
+	};
+
+	if (output < 0 || output >= ARRAY_SIZE(names) || !names[output])
+		return "Invalid";
+
+	return names[output];
+}
+
 static void intel_setup_outputs(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -10412,8 +10688,11 @@ static void intel_init_display(struct drm_device *dev)
 		}
 	} else if (IS_G4X(dev)) {
 		dev_priv->display.write_eld = g4x_write_eld;
-	} else if (IS_VALLEYVIEW(dev))
+	} else if (IS_VALLEYVIEW(dev)) {
+		dev_priv->display.modeset_global_resources =
+			valleyview_modeset_global_resources;
 		dev_priv->display.write_eld = ironlake_write_eld;
+	}
 
 	/* Default just returns -ENODEV to indicate unsupported */
 	dev_priv->display.queue_flip = intel_default_queue_flip;
@@ -10440,6 +10719,8 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.queue_flip = intel_gen7_queue_flip;
 		break;
 	}
+
+	intel_panel_init_backlight_funcs(dev);
 }
 
 /*
@@ -10476,17 +10757,6 @@ static void quirk_invert_brightness(struct drm_device *dev)
 	DRM_INFO("applying inverted panel brightness quirk\n");
 }
 
-/*
- * Some machines (Dell XPS13) suffer broken backlight controls if
- * BLM_PCH_PWM_ENABLE is set.
- */
-static void quirk_no_pcm_pwm_enable(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE;
-	DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n");
-}
-
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -10555,11 +10825,6 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Acer Aspire 4736Z */
 	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
-
-	/* Dell XPS13 HD Sandy Bridge */
-	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
-	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */
-	{ 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -10603,18 +10868,11 @@ static void i915_disable_vga(struct drm_device *dev)
 
 void intel_modeset_init_hw(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	intel_prepare_ddi(dev);
 
 	intel_init_clock_gating(dev);
 
-	/* Enable the CRI clock source so we can get at the display */
-	if (IS_VALLEYVIEW(dev))
-		I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
-			   DPLL_INTEGRATED_CRI_CLK_VLV);
-
-	intel_init_dpio(dev);
+	intel_reset_dpio(dev);
 
 	mutex_lock(&dev->struct_mutex);
 	intel_enable_gt_powersave(dev);
@@ -10676,6 +10934,9 @@ void intel_modeset_init(struct drm_device *dev)
 		}
 	}
 
+	intel_init_dpio(dev);
+	intel_reset_dpio(dev);
+
 	intel_cpu_pll_init(dev);
 	intel_shared_dpll_init(dev);
 
@@ -10879,7 +11140,7 @@ void i915_redisable_vga(struct drm_device *dev)
 	 * 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) &&
+	if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
 	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
 		return;
 
@@ -11023,7 +11284,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 		pll->on = false;
 	}
 
-	if (IS_HASWELL(dev))
+	if (HAS_PCH_SPLIT(dev))
 		ilk_wm_get_hw_state(dev);
 
 	if (force_restore) {
@@ -11101,12 +11362,11 @@ void intel_modeset_cleanup(struct drm_device *dev)
 	/* flush any delayed tasks or pending work */
 	flush_scheduled_work();
 
-	/* destroy backlight, if any, before the connectors */
-	intel_panel_destroy_backlight(dev);
-
-	/* destroy the sysfs files before encoders/connectors */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
+	/* destroy the backlight and sysfs files before encoders/connectors */
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+		intel_panel_destroy_backlight(connector);
 		drm_sysfs_connector_remove(connector);
+	}
 
 	drm_mode_config_cleanup(dev);
 
@@ -11161,6 +11421,7 @@ struct intel_display_error_state {
 	} cursor[I915_MAX_PIPES];
 
 	struct intel_pipe_error_state {
+		bool power_domain_on;
 		u32 source;
 	} pipe[I915_MAX_PIPES];
 
@@ -11175,6 +11436,7 @@ struct intel_display_error_state {
 	} plane[I915_MAX_PIPES];
 
 	struct intel_transcoder_error_state {
+		bool power_domain_on;
 		enum transcoder cpu_transcoder;
 
 		u32 conf;
@@ -11208,11 +11470,13 @@ intel_display_capture_error_state(struct drm_device *dev)
 	if (error == NULL)
 		return NULL;
 
-	if (HAS_POWER_WELL(dev))
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		error->power_well_driver = I915_READ(HSW_PWR_WELL_DRIVER);
 
 	for_each_pipe(i) {
-		if (!intel_display_power_enabled(dev, POWER_DOMAIN_PIPE(i)))
+		error->pipe[i].power_domain_on =
+			intel_display_power_enabled_sw(dev, POWER_DOMAIN_PIPE(i));
+		if (!error->pipe[i].power_domain_on)
 			continue;
 
 		if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) {
@@ -11248,8 +11512,10 @@ intel_display_capture_error_state(struct drm_device *dev)
 	for (i = 0; i < error->num_transcoders; i++) {
 		enum transcoder cpu_transcoder = transcoders[i];
 
-		if (!intel_display_power_enabled(dev,
-				POWER_DOMAIN_TRANSCODER(cpu_transcoder)))
+		error->transcoder[i].power_domain_on =
+			intel_display_power_enabled_sw(dev,
+				POWER_DOMAIN_TRANSCODER(cpu_transcoder));
+		if (!error->transcoder[i].power_domain_on)
 			continue;
 
 		error->transcoder[i].cpu_transcoder = cpu_transcoder;
@@ -11279,11 +11545,13 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		return;
 
 	err_printf(m, "Num Pipes: %d\n", INTEL_INFO(dev)->num_pipes);
-	if (HAS_POWER_WELL(dev))
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		err_printf(m, "PWR_WELL_CTL2: %08x\n",
 			   error->power_well_driver);
 	for_each_pipe(i) {
 		err_printf(m, "Pipe [%d]:\n", i);
+		err_printf(m, "  Power: %s\n",
+			   error->pipe[i].power_domain_on ? "on" : "off");
 		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
 
 		err_printf(m, "Plane [%d]:\n", i);
@@ -11309,6 +11577,8 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 	for (i = 0; i < error->num_transcoders; i++) {
 		err_printf(m, "CPU transcoder: %c\n",
 			   transcoder_name(error->transcoder[i].cpu_transcoder));
+		err_printf(m, "  Power: %s\n",
+			   error->transcoder[i].power_domain_on ? "on" : "off");
 		err_printf(m, "  CONF: %08x\n", error->transcoder[i].conf);
 		err_printf(m, "  HTOTAL: %08x\n", error->transcoder[i].htotal);
 		err_printf(m, "  HBLANK: %08x\n", error->transcoder[i].hblank);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 30c627c7b7ba..5ede4e8e290d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -142,7 +142,7 @@ intel_dp_max_data_rate(int max_link_clock, int max_lanes)
 	return (max_link_clock * max_lanes * 8) / 10;
 }
 
-static int
+static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
@@ -404,7 +404,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, precharge, clock = 0;
-	bool has_aux_irq = INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev);
+	bool has_aux_irq = true;
 	uint32_t timeout;
 
 	/* dp aux is extremely sensitive to irq latency, hence request the
@@ -542,7 +542,7 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp,
 		return -E2BIG;
 
 	intel_dp_check_edp(intel_dp);
-	msg[0] = AUX_NATIVE_WRITE << 4;
+	msg[0] = DP_AUX_NATIVE_WRITE << 4;
 	msg[1] = address >> 8;
 	msg[2] = address & 0xff;
 	msg[3] = send_bytes - 1;
@@ -552,9 +552,10 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp,
 		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
 		if (ret < 0)
 			return ret;
-		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK)
+		ack >>= 4;
+		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
 			break;
-		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
+		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
 			udelay(100);
 		else
 			return -EIO;
@@ -586,7 +587,7 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp,
 		return -E2BIG;
 
 	intel_dp_check_edp(intel_dp);
-	msg[0] = AUX_NATIVE_READ << 4;
+	msg[0] = DP_AUX_NATIVE_READ << 4;
 	msg[1] = address >> 8;
 	msg[2] = address & 0xff;
 	msg[3] = recv_bytes - 1;
@@ -601,12 +602,12 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp,
 			return -EPROTO;
 		if (ret < 0)
 			return ret;
-		ack = reply[0];
-		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK) {
+		ack = reply[0] >> 4;
+		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK) {
 			memcpy(recv, reply + 1, ret - 1);
 			return ret - 1;
 		}
-		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
+		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
 			udelay(100);
 		else
 			return -EIO;
@@ -633,12 +634,12 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 	intel_dp_check_edp(intel_dp);
 	/* Set up the command byte */
 	if (mode & MODE_I2C_READ)
-		msg[0] = AUX_I2C_READ << 4;
+		msg[0] = DP_AUX_I2C_READ << 4;
 	else
-		msg[0] = AUX_I2C_WRITE << 4;
+		msg[0] = DP_AUX_I2C_WRITE << 4;
 
 	if (!(mode & MODE_I2C_STOP))
-		msg[0] |= AUX_I2C_MOT << 4;
+		msg[0] |= DP_AUX_I2C_MOT << 4;
 
 	msg[1] = address >> 8;
 	msg[2] = address;
@@ -675,17 +676,17 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 			goto out;
 		}
 
-		switch (reply[0] & AUX_NATIVE_REPLY_MASK) {
-		case AUX_NATIVE_REPLY_ACK:
+		switch ((reply[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK) {
+		case DP_AUX_NATIVE_REPLY_ACK:
 			/* I2C-over-AUX Reply field is only valid
 			 * when paired with AUX ACK.
 			 */
 			break;
-		case AUX_NATIVE_REPLY_NACK:
+		case DP_AUX_NATIVE_REPLY_NACK:
 			DRM_DEBUG_KMS("aux_ch native nack\n");
 			ret = -EREMOTEIO;
 			goto out;
-		case AUX_NATIVE_REPLY_DEFER:
+		case DP_AUX_NATIVE_REPLY_DEFER:
 			/*
 			 * For now, just give more slack to branch devices. We
 			 * could check the DPCD for I2C bit rate capabilities,
@@ -706,18 +707,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 			goto out;
 		}
 
-		switch (reply[0] & AUX_I2C_REPLY_MASK) {
-		case AUX_I2C_REPLY_ACK:
+		switch ((reply[0] >> 4) & DP_AUX_I2C_REPLY_MASK) {
+		case DP_AUX_I2C_REPLY_ACK:
 			if (mode == MODE_I2C_READ) {
 				*read_byte = reply[1];
 			}
 			ret = reply_bytes - 1;
 			goto out;
-		case AUX_I2C_REPLY_NACK:
+		case DP_AUX_I2C_REPLY_NACK:
 			DRM_DEBUG_KMS("aux_i2c nack\n");
 			ret = -EREMOTEIO;
 			goto out;
-		case AUX_I2C_REPLY_DEFER:
+		case DP_AUX_I2C_REPLY_DEFER:
 			DRM_DEBUG_KMS("aux_i2c defer\n");
 			udelay(100);
 			break;
@@ -1037,6 +1038,8 @@ static void ironlake_wait_panel_status(struct intel_dp *intel_dp,
 				I915_READ(pp_stat_reg),
 				I915_READ(pp_ctrl_reg));
 	}
+
+	DRM_DEBUG_KMS("Wait complete\n");
 }
 
 static void ironlake_wait_panel_on(struct intel_dp *intel_dp)
@@ -1092,6 +1095,8 @@ void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
 	if (ironlake_edp_have_panel_vdd(intel_dp))
 		return;
 
+	intel_runtime_pm_get(dev_priv);
+
 	DRM_DEBUG_KMS("Turning eDP VDD on\n");
 
 	if (!ironlake_edp_have_panel_power(intel_dp))
@@ -1140,7 +1145,11 @@ static void ironlake_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		/* Make sure sequencer is idle before allowing subsequent activity */
 		DRM_DEBUG_KMS("PP_STATUS: 0x%08x PP_CONTROL: 0x%08x\n",
 		I915_READ(pp_stat_reg), I915_READ(pp_ctrl_reg));
-		msleep(intel_dp->panel_power_down_delay);
+
+		if ((pp & POWER_TARGET_ON) == 0)
+			msleep(intel_dp->panel_power_cycle_delay);
+
+		intel_runtime_pm_put(dev_priv);
 	}
 }
 
@@ -1233,20 +1242,16 @@ void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 
 	DRM_DEBUG_KMS("Turn eDP power off\n");
 
-	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
-
 	pp = ironlake_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
-	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
-	intel_dp->want_panel_vdd = false;
-
 	ironlake_wait_panel_off(intel_dp);
 }
 
@@ -1772,7 +1777,6 @@ static void intel_disable_dp(struct intel_encoder *encoder)
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
-	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	ironlake_edp_panel_off(intel_dp);
@@ -1845,23 +1849,23 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 	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);
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 	struct edp_power_seq power_seq;
 	u32 val;
 
 	mutex_lock(&dev_priv->dpio_lock);
 
-	val = vlv_dpio_read(dev_priv, pipe, DPIO_DATA_LANE_A(port));
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
 	val = 0;
 	if (pipe)
 		val |= (1<<21);
 	else
 		val &= ~(1<<21);
 	val |= 0x001000c4;
-	vlv_dpio_write(dev_priv, pipe, DPIO_DATA_CHANNEL(port), val);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLOCKBUF0(port), 0x00760018);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLOCKBUF8(port), 0x00400888);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW8(port), val);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW14(port), 0x00760018);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
 
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -1872,7 +1876,7 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 
 	intel_enable_dp(encoder);
 
-	vlv_wait_port_ready(dev_priv, port);
+	vlv_wait_port_ready(dev_priv, dport);
 }
 
 static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
@@ -1882,24 +1886,24 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
 	/* Program Tx lane resets to default */
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_TX(port),
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLK(port),
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port),
 			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
 			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
 			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
 				 DPIO_PCS_CLK_SOFT_RESET);
 
 	/* Fix up inter-pair skew failure */
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_STAGGER1(port), 0x00750f00);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_CTL(port), 0x00001500);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_LANE(port), 0x40400000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW12(port), 0x00750f00);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW11(port), 0x00001500);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW14(port), 0x40400000);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
@@ -1941,18 +1945,6 @@ intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_
 					      DP_LINK_STATUS_SIZE);
 }
 
-#if 0
-static char	*voltage_names[] = {
-	"0.4V", "0.6V", "0.8V", "1.2V"
-};
-static char	*pre_emph_names[] = {
-	"0dB", "3.5dB", "6dB", "9.5dB"
-};
-static char	*link_train_names[] = {
-	"pattern 1", "pattern 2", "idle", "off"
-};
-#endif
-
 /*
  * These are source-specific values; current Intel hardware supports
  * a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
@@ -2050,7 +2042,7 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	unsigned long demph_reg_value, preemph_reg_value,
 		uniqtranscale_reg_value;
 	uint8_t train_set = intel_dp->train_set[0];
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
@@ -2127,14 +2119,14 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	}
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_OCALINIT(port), 0x00000000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL4(port), demph_reg_value);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL2(port),
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0x00000000);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW4(port), demph_reg_value);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(port),
 			 uniqtranscale_reg_value);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL3(port), 0x0C782040);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_STAGGER0(port), 0x00030000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CTL_OVER1(port), preemph_reg_value);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_OCALINIT(port), 0x80000000);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(port), 0x0C782040);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW11(port), 0x00030000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), preemph_reg_value);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0x80000000);
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	return 0;
@@ -2646,7 +2638,6 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 
 		if (cr_tries > 5) {
 			DRM_ERROR("failed to train DP, aborting\n");
-			intel_dp_link_down(intel_dp);
 			break;
 		}
 
@@ -2899,13 +2890,11 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 
 	/* Try to read receiver status if the link appears to be up */
 	if (!intel_dp_get_link_status(intel_dp, link_status)) {
-		intel_dp_link_down(intel_dp);
 		return;
 	}
 
 	/* Now read the DPCD to see if it's actually running */
 	if (!intel_dp_get_dpcd(intel_dp)) {
-		intel_dp_link_down(intel_dp);
 		return;
 	}
 
@@ -3020,18 +3009,34 @@ g4x_dp_detect(struct intel_dp *intel_dp)
 		return status;
 	}
 
-	switch (intel_dig_port->port) {
-	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS;
-		break;
-	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS;
-		break;
-	default:
-		return connector_status_unknown;
+	if (IS_VALLEYVIEW(dev)) {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+			break;
+		default:
+			return connector_status_unknown;
+		}
+	} else {
+		switch (intel_dig_port->port) {
+		case PORT_B:
+			bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_C:
+			bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		case PORT_D:
+			bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
+			break;
+		default:
+			return connector_status_unknown;
+		}
 	}
 
 	if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0)
@@ -3082,9 +3087,12 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum drm_connector_status status;
 	struct edid *edid = NULL;
 
+	intel_runtime_pm_get(dev_priv);
+
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, drm_get_connector_name(connector));
 
@@ -3096,7 +3104,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 		status = g4x_dp_detect(intel_dp);
 
 	if (status != connector_status_connected)
-		return status;
+		goto out;
 
 	intel_dp_probe_oui(intel_dp);
 
@@ -3112,7 +3120,11 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 
 	if (intel_encoder->type != INTEL_OUTPUT_EDP)
 		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
-	return connector_status_connected;
+	status = connector_status_connected;
+
+out:
+	intel_runtime_pm_put(dev_priv);
+	return status;
 }
 
 static int intel_dp_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 79f91f26e288..fbfaaba5cc3b 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -65,8 +65,8 @@
 #define wait_for_atomic_us(COND, US) _wait_for((COND), \
 					       DIV_ROUND_UP((US), 1000), 0)
 
-#define KHz(x) (1000*x)
-#define MHz(x) KHz(1000*x)
+#define KHz(x) (1000 * (x))
+#define MHz(x) KHz(1000 * (x))
 
 /*
  * Display related stuff
@@ -155,7 +155,19 @@ struct intel_encoder {
 
 struct intel_panel {
 	struct drm_display_mode *fixed_mode;
+	struct drm_display_mode *downclock_mode;
 	int fitting_mode;
+
+	/* backlight */
+	struct {
+		bool present;
+		u32 level;
+		u32 max;
+		bool enabled;
+		bool combination_mode;	/* gen 2/4 only */
+		bool active_low_pwm;
+		struct backlight_device *device;
+	} backlight;
 };
 
 struct intel_connector {
@@ -443,7 +455,7 @@ struct intel_hdmi {
 	bool rgb_quant_range_selectable;
 	void (*write_infoframe)(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len);
+				const void *frame, ssize_t len);
 	void (*set_infoframes)(struct drm_encoder *encoder,
 			       struct drm_display_mode *adjusted_mode);
 };
@@ -490,9 +502,9 @@ vlv_dport_to_channel(struct intel_digital_port *dport)
 {
 	switch (dport->port) {
 	case PORT_B:
-		return 0;
+		return DPIO_CH0;
 	case PORT_C:
-		return 1;
+		return DPIO_CH1;
 	default:
 		BUG();
 	}
@@ -601,7 +613,8 @@ void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
 void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc);
 void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc);
 void intel_ddi_setup_hw_pll_state(struct drm_device *dev);
-bool intel_ddi_pll_mode_set(struct drm_crtc *crtc);
+bool intel_ddi_pll_select(struct intel_crtc *crtc);
+void intel_ddi_pll_enable(struct intel_crtc *crtc);
 void intel_ddi_put_crtc_pll(struct drm_crtc *crtc);
 void intel_ddi_set_pipe_settings(struct drm_crtc *crtc);
 void intel_ddi_prepare_link_retrain(struct drm_encoder *encoder);
@@ -612,6 +625,8 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 
 
 /* intel_display.c */
+const char *intel_output_name(int output);
+bool intel_has_pending_fb_unpin(struct drm_device *dev);
 int intel_pch_rawclk(struct drm_device *dev);
 void intel_mark_busy(struct drm_device *dev);
 void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
@@ -638,7 +653,8 @@ enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
 void intel_wait_for_vblank(struct drm_device *dev, int pipe);
 void intel_wait_for_pipe_off(struct drm_device *dev, int pipe);
 int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp);
-void vlv_wait_port_ready(struct drm_i915_private *dev_priv, int port);
+void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
+			 struct intel_digital_port *dport);
 bool intel_get_load_detect_pipe(struct drm_connector *connector,
 				struct drm_display_mode *mode,
 				struct intel_load_detect_pipe *old);
@@ -690,11 +706,10 @@ void
 ironlake_check_encoder_dotclock(const struct intel_crtc_config *pipe_config,
 				int dotclock);
 bool intel_crtc_active(struct drm_crtc *crtc);
-void i915_disable_vga_mem(struct drm_device *dev);
 void hsw_enable_ips(struct intel_crtc *crtc);
 void hsw_disable_ips(struct intel_crtc *crtc);
 void intel_display_set_init_power(struct drm_device *dev, bool enable);
-
+int valleyview_get_vco(struct drm_i915_private *dev_priv);
 
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
@@ -808,9 +823,13 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 int intel_panel_setup_backlight(struct drm_connector *connector);
 void intel_panel_enable_backlight(struct intel_connector *connector);
 void intel_panel_disable_backlight(struct intel_connector *connector);
-void intel_panel_destroy_backlight(struct drm_device *dev);
+void intel_panel_destroy_backlight(struct drm_connector *connector);
+void intel_panel_init_backlight_funcs(struct drm_device *dev);
 enum drm_connector_status intel_panel_detect(struct drm_device *dev);
-
+extern struct drm_display_mode *intel_find_panel_downclock(
+				struct drm_device *dev,
+				struct drm_display_mode *fixed_mode,
+				struct drm_connector *connector);
 
 /* intel_pm.c */
 void intel_init_clock_gating(struct drm_device *dev);
@@ -830,6 +849,8 @@ int intel_power_domains_init(struct drm_device *dev);
 void intel_power_domains_remove(struct drm_device *dev);
 bool intel_display_power_enabled(struct drm_device *dev,
 				 enum intel_display_power_domain domain);
+bool intel_display_power_enabled_sw(struct drm_device *dev,
+				    enum intel_display_power_domain domain);
 void intel_display_power_get(struct drm_device *dev,
 			     enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_device *dev,
@@ -844,6 +865,10 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv);
 void gen6_rps_boost(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
+void intel_init_runtime_pm(struct drm_i915_private *dev_priv);
+void intel_fini_runtime_pm(struct drm_i915_private *dev_priv);
 void ilk_wm_get_hw_state(struct drm_device *dev);
 
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index d257b093ca68..fabbf0d895cf 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -37,49 +37,18 @@
 static const struct intel_dsi_device intel_dsi_devices[] = {
 };
 
-
-static void vlv_cck_modify(struct drm_i915_private *dev_priv, u32 reg, u32 val,
-			   u32 mask)
-{
-	u32 tmp = vlv_cck_read(dev_priv, reg);
-	tmp &= ~mask;
-	tmp |= val;
-	vlv_cck_write(dev_priv, reg, tmp);
-}
-
-static void band_gap_wa(struct drm_i915_private *dev_priv)
+static void band_gap_reset(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->dpio_lock);
 
-	/* Enable bandgap fix in GOP driver */
-	vlv_cck_modify(dev_priv, 0x6D, 0x00010000, 0x00030000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x6E, 0x00010000, 0x00030000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x6F, 0x00010000, 0x00030000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x00, 0x00008000, 0x00008000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x00, 0x00000000, 0x00008000);
-	msleep(20);
-
-	/* Turn Display Trunk on */
-	vlv_cck_modify(dev_priv, 0x6B, 0x00020000, 0x00030000);
-	msleep(20);
-
-	vlv_cck_modify(dev_priv, 0x6C, 0x00020000, 0x00030000);
-	msleep(20);
-
-	vlv_cck_modify(dev_priv, 0x6D, 0x00020000, 0x00030000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x6E, 0x00020000, 0x00030000);
-	msleep(20);
-	vlv_cck_modify(dev_priv, 0x6F, 0x00020000, 0x00030000);
+	vlv_flisdsi_write(dev_priv, 0x08, 0x0001);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0005);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0025);
+	udelay(150);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0000);
+	vlv_flisdsi_write(dev_priv, 0x08, 0x0000);
 
 	mutex_unlock(&dev_priv->dpio_lock);
-
-	/* Need huge delay, otherwise clock is not stable */
-	msleep(100);
 }
 
 static struct intel_dsi *intel_attached_dsi(struct drm_connector *connector)
@@ -132,14 +101,47 @@ static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder)
 	vlv_enable_dsi_pll(encoder);
 }
 
+static void intel_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	int pipe = intel_crtc->pipe;
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	val = I915_READ(MIPI_PORT_CTRL(pipe));
+	I915_WRITE(MIPI_PORT_CTRL(pipe), val | LP_OUTPUT_HOLD);
+	usleep_range(1000, 1500);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY | ULPS_STATE_EXIT);
+	usleep_range(2000, 2500);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY);
+	usleep_range(2000, 2500);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x00);
+	usleep_range(2000, 2500);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY);
+	usleep_range(2000, 2500);
+}
 static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 {
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+
 	DRM_DEBUG_KMS("\n");
+
+	if (intel_dsi->dev.dev_ops->panel_reset)
+		intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev);
+
+	/* put device in ready state */
+	intel_dsi_device_ready(encoder);
+
+	if (intel_dsi->dev.dev_ops->send_otp_cmds)
+		intel_dsi->dev.dev_ops->send_otp_cmds(&intel_dsi->dev);
 }
 
 static void intel_dsi_enable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	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);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	int pipe = intel_crtc->pipe;
@@ -147,41 +149,28 @@ static void intel_dsi_enable(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("\n");
 
-	temp = I915_READ(MIPI_DEVICE_READY(pipe));
-	if ((temp & DEVICE_READY) == 0) {
-		temp &= ~ULPS_STATE_MASK;
-		I915_WRITE(MIPI_DEVICE_READY(pipe), temp | DEVICE_READY);
-	} else if (temp & ULPS_STATE_MASK) {
-		temp &= ~ULPS_STATE_MASK;
-		I915_WRITE(MIPI_DEVICE_READY(pipe), temp | ULPS_STATE_EXIT);
-		/*
-		 * We need to ensure that there is a minimum of 1 ms time
-		 * available before clearing the UPLS exit state.
-		 */
-		msleep(2);
-		I915_WRITE(MIPI_DEVICE_READY(pipe), temp);
-	}
-
 	if (is_cmd_mode(intel_dsi))
 		I915_WRITE(MIPI_MAX_RETURN_PKT_SIZE(pipe), 8 * 4);
-
-	if (is_vid_mode(intel_dsi)) {
+	else {
 		msleep(20); /* XXX */
 		dpi_send_cmd(intel_dsi, TURN_ON);
 		msleep(100);
 
 		/* assert ip_tg_enable signal */
-		temp = I915_READ(MIPI_PORT_CTRL(pipe));
+		temp = I915_READ(MIPI_PORT_CTRL(pipe)) & ~LANE_CONFIGURATION_MASK;
+		temp = temp | intel_dsi->port_bits;
 		I915_WRITE(MIPI_PORT_CTRL(pipe), temp | DPI_ENABLE);
 		POSTING_READ(MIPI_PORT_CTRL(pipe));
 	}
 
-	intel_dsi->dev.dev_ops->enable(&intel_dsi->dev);
+	if (intel_dsi->dev.dev_ops->enable)
+		intel_dsi->dev.dev_ops->enable(&intel_dsi->dev);
 }
 
 static void intel_dsi_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	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);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	int pipe = intel_crtc->pipe;
@@ -189,8 +178,6 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("\n");
 
-	intel_dsi->dev.dev_ops->disable(&intel_dsi->dev);
-
 	if (is_vid_mode(intel_dsi)) {
 		dpi_send_cmd(intel_dsi, SHUTDOWN);
 		msleep(10);
@@ -203,20 +190,54 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 		msleep(2);
 	}
 
-	temp = I915_READ(MIPI_DEVICE_READY(pipe));
-	if (temp & DEVICE_READY) {
-		temp &= ~DEVICE_READY;
-		temp &= ~ULPS_STATE_MASK;
-		I915_WRITE(MIPI_DEVICE_READY(pipe), temp);
-	}
+	/* if disable packets are sent before sending shutdown packet then in
+	 * some next enable sequence send turn on packet error is observed */
+	if (intel_dsi->dev.dev_ops->disable)
+		intel_dsi->dev.dev_ops->disable(&intel_dsi->dev);
 }
 
-static void intel_dsi_post_disable(struct intel_encoder *encoder)
+static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	int pipe = intel_crtc->pipe;
+	u32 val;
+
 	DRM_DEBUG_KMS("\n");
 
+	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_ENTER);
+	usleep_range(2000, 2500);
+
+	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_EXIT);
+	usleep_range(2000, 2500);
+
+	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_ENTER);
+	usleep_range(2000, 2500);
+
+	val = I915_READ(MIPI_PORT_CTRL(pipe));
+	I915_WRITE(MIPI_PORT_CTRL(pipe), val & ~LP_OUTPUT_HOLD);
+	usleep_range(1000, 1500);
+
+	if (wait_for(((I915_READ(MIPI_PORT_CTRL(pipe)) & AFE_LATCHOUT)
+					== 0x00000), 30))
+		DRM_ERROR("DSI LP not going Low\n");
+
+	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x00);
+	usleep_range(2000, 2500);
+
 	vlv_disable_dsi_pll(encoder);
 }
+static void intel_dsi_post_disable(struct intel_encoder *encoder)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+
+	DRM_DEBUG_KMS("\n");
+
+	intel_dsi_clear_device_ready(encoder);
+
+	if (intel_dsi->dev.dev_ops->disable_panel_power)
+		intel_dsi->dev.dev_ops->disable_panel_power(&intel_dsi->dev);
+}
 
 static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
@@ -251,8 +272,9 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	/* XXX: read flags, set to adjusted_mode */
 }
 
-static int intel_dsi_mode_valid(struct drm_connector *connector,
-				struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_dsi_mode_valid(struct drm_connector *connector,
+		     struct drm_display_mode *mode)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
@@ -352,11 +374,8 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 
 	DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe));
 
-	/* Update the DSI PLL */
-	vlv_enable_dsi_pll(intel_encoder);
-
 	/* XXX: Location of the call */
-	band_gap_wa(dev_priv);
+	band_gap_reset(dev_priv);
 
 	/* escape clock divider, 20MHz, shared for A and C. device ready must be
 	 * off when doing this! txclkesc? */
@@ -373,11 +392,7 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 	I915_WRITE(MIPI_INTR_STAT(pipe), 0xffffffff);
 	I915_WRITE(MIPI_INTR_EN(pipe), 0xffffffff);
 
-	I915_WRITE(MIPI_DPHY_PARAM(pipe),
-		   0x3c << EXIT_ZERO_COUNT_SHIFT |
-		   0x1f << TRAIL_COUNT_SHIFT |
-		   0xc5 << CLK_ZERO_COUNT_SHIFT |
-		   0x1f << PREPARE_COUNT_SHIFT);
+	I915_WRITE(MIPI_DPHY_PARAM(pipe), intel_dsi->dphy_reg);
 
 	I915_WRITE(MIPI_DPI_RESOLUTION(pipe),
 		   adjusted_mode->vdisplay << VERTICAL_ADDRESS_SHIFT |
@@ -425,9 +440,9 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 				       adjusted_mode->htotal,
 				       bpp, intel_dsi->lane_count) + 1);
 	}
-	I915_WRITE(MIPI_LP_RX_TIMEOUT(pipe), 8309); /* max */
-	I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(pipe), 0x14); /* max */
-	I915_WRITE(MIPI_DEVICE_RESET_TIMER(pipe), 0xffff); /* max */
+	I915_WRITE(MIPI_LP_RX_TIMEOUT(pipe), intel_dsi->lp_rx_timeout);
+	I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(pipe), intel_dsi->turn_arnd_val);
+	I915_WRITE(MIPI_DEVICE_RESET_TIMER(pipe), intel_dsi->rst_timer_val);
 
 	/* dphy stuff */
 
@@ -442,29 +457,31 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 	 *
 	 * XXX: write MIPI_STOP_STATE_STALL?
 	 */
-	I915_WRITE(MIPI_HIGH_LOW_SWITCH_COUNT(pipe), 0x46);
+	I915_WRITE(MIPI_HIGH_LOW_SWITCH_COUNT(pipe),
+						intel_dsi->hs_to_lp_count);
 
 	/* XXX: low power clock equivalence in terms of byte clock. the number
 	 * of byte clocks occupied in one low power clock. based on txbyteclkhs
 	 * and txclkesc. txclkesc time / txbyteclk time * (105 +
 	 * MIPI_STOP_STATE_STALL) / 105.???
 	 */
-	I915_WRITE(MIPI_LP_BYTECLK(pipe), 4);
+	I915_WRITE(MIPI_LP_BYTECLK(pipe), intel_dsi->lp_byte_clk);
 
 	/* the bw essential for transmitting 16 long packets containing 252
 	 * bytes meant for dcs write memory command is programmed in this
 	 * register in terms of byte clocks. based on dsi transfer rate and the
 	 * number of lanes configured the time taken to transmit 16 long packets
 	 * in a dsi stream varies. */
-	I915_WRITE(MIPI_DBI_BW_CTRL(pipe), 0x820);
+	I915_WRITE(MIPI_DBI_BW_CTRL(pipe), intel_dsi->bw_timer);
 
 	I915_WRITE(MIPI_CLK_LANE_SWITCH_TIME_CNT(pipe),
-		   0xa << LP_HS_SSW_CNT_SHIFT |
-		   0x14 << HS_LP_PWR_SW_CNT_SHIFT);
+		   intel_dsi->clk_lp_to_hs_count << LP_HS_SSW_CNT_SHIFT |
+		   intel_dsi->clk_hs_to_lp_count << HS_LP_PWR_SW_CNT_SHIFT);
 
 	if (is_vid_mode(intel_dsi))
 		I915_WRITE(MIPI_VIDEO_MODE_FORMAT(pipe),
-			   intel_dsi->video_mode_format);
+				intel_dsi->video_frmt_cfg_bits |
+				intel_dsi->video_mode_format);
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index c7765f33d524..b4a27cec882f 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -39,6 +39,13 @@ struct intel_dsi_device {
 struct intel_dsi_dev_ops {
 	bool (*init)(struct intel_dsi_device *dsi);
 
+	void (*panel_reset)(struct intel_dsi_device *dsi);
+
+	void (*disable_panel_power)(struct intel_dsi_device *dsi);
+
+	/* one time programmable commands if needed */
+	void (*send_otp_cmds)(struct intel_dsi_device *dsi);
+
 	/* This callback must be able to assume DSI commands can be sent */
 	void (*enable)(struct intel_dsi_device *dsi);
 
@@ -89,6 +96,20 @@ struct intel_dsi {
 
 	/* eot for MIPI_EOT_DISABLE register */
 	u32 eot_disable;
+
+	u32 port_bits;
+	u32 bw_timer;
+	u32 dphy_reg;
+	u32 video_frmt_cfg_bits;
+	u16 lp_byte_clk;
+
+	/* timeouts in byte clocks */
+	u16 lp_rx_timeout;
+	u16 turn_arnd_val;
+	u16 rst_timer_val;
+	u16 hs_to_lp_count;
+	u16 clk_lp_to_hs_count;
+	u16 clk_hs_to_lp_count;
 };
 
 static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
index 44279b2ade88..ba79ec19da3b 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/intel_dsi_pll.c
@@ -50,6 +50,8 @@ static const u32 lfsr_converts[] = {
 	71, 35							/* 91 - 92 */
 };
 
+#ifdef DSI_CLK_FROM_RR
+
 static u32 dsi_rr_formula(const struct drm_display_mode *mode,
 			  int pixel_format, int video_mode_format,
 			  int lane_count, bool eotp)
@@ -121,7 +123,7 @@ static u32 dsi_rr_formula(const struct drm_display_mode *mode,
 
 	/* the dsi clock is divided by 2 in the hardware to get dsi ddr clock */
 	dsi_bit_clock_hz = bytes_per_x_frames_x_lanes * 8;
-	dsi_clk = dsi_bit_clock_hz / (1000 * 1000);
+	dsi_clk = dsi_bit_clock_hz / 1000;
 
 	if (eotp && video_mode_format == VIDEO_MODE_BURST)
 		dsi_clk *= 2;
@@ -129,64 +131,37 @@ static u32 dsi_rr_formula(const struct drm_display_mode *mode,
 	return dsi_clk;
 }
 
-#ifdef MNP_FROM_TABLE
-
-struct dsi_clock_table {
-	u32 freq;
-	u8 m;
-	u8 p;
-};
-
-static const struct dsi_clock_table dsi_clk_tbl[] = {
-	{300, 72, 6}, {313, 75, 6}, {323, 78, 6}, {333, 80, 6},
-	{343, 82, 6}, {353, 85, 6}, {363, 87, 6}, {373, 90, 6},
-	{383, 92, 6}, {390, 78, 5}, {393, 79, 5}, {400, 80, 5},
-	{401, 80, 5}, {402, 80, 5}, {403, 81, 5}, {404, 81, 5},
-	{405, 81, 5}, {406, 81, 5}, {407, 81, 5}, {408, 82, 5},
-	{409, 82, 5}, {410, 82, 5}, {411, 82, 5}, {412, 82, 5},
-	{413, 83, 5}, {414, 83, 5}, {415, 83, 5}, {416, 83, 5},
-	{417, 83, 5}, {418, 84, 5}, {419, 84, 5}, {420, 84, 5},
-	{430, 86, 5}, {440, 88, 5}, {450, 90, 5}, {460, 92, 5},
-	{470, 75, 4}, {480, 77, 4}, {490, 78, 4}, {500, 80, 4},
-	{510, 82, 4}, {520, 83, 4}, {530, 85, 4}, {540, 86, 4},
-	{550, 88, 4}, {560, 90, 4}, {570, 91, 4}, {580, 70, 3},
-	{590, 71, 3}, {600, 72, 3}, {610, 73, 3}, {620, 74, 3},
-	{630, 76, 3}, {640, 77, 3}, {650, 78, 3}, {660, 79, 3},
-	{670, 80, 3}, {680, 82, 3}, {690, 83, 3}, {700, 84, 3},
-	{710, 85, 3}, {720, 86, 3}, {730, 88, 3}, {740, 89, 3},
-	{750, 90, 3}, {760, 91, 3}, {770, 92, 3}, {780, 62, 2},
-	{790, 63, 2}, {800, 64, 2}, {880, 70, 2}, {900, 72, 2},
-	{1000, 80, 2},		/* dsi clock frequency in Mhz*/
-};
+#else
 
-static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
+/* Get DSI clock from pixel clock */
+static u32 dsi_clk_from_pclk(const struct drm_display_mode *mode,
+			  int pixel_format, int lane_count)
 {
-	unsigned int i;
-	u8 m;
-	u8 n;
-	u8 p;
-	u32 m_seed;
-
-	if (dsi_clk < 300 || dsi_clk > 1000)
-		return -ECHRNG;
+	u32 dsi_clk_khz;
+	u32 bpp;
 
-	for (i = 0; i <= ARRAY_SIZE(dsi_clk_tbl); i++) {
-		if (dsi_clk_tbl[i].freq > dsi_clk)
-			break;
+	switch (pixel_format) {
+	default:
+	case VID_MODE_FORMAT_RGB888:
+	case VID_MODE_FORMAT_RGB666_LOOSE:
+		bpp = 24;
+		break;
+	case VID_MODE_FORMAT_RGB666:
+		bpp = 18;
+		break;
+	case VID_MODE_FORMAT_RGB565:
+		bpp = 16;
+		break;
 	}
 
-	m = dsi_clk_tbl[i].m;
-	p = dsi_clk_tbl[i].p;
-	m_seed = lfsr_converts[m - 62];
-	n = 1;
-	dsi_mnp->dsi_pll_ctrl = 1 << (DSI_PLL_P1_POST_DIV_SHIFT + p - 2);
-	dsi_mnp->dsi_pll_div = (n - 1) << DSI_PLL_N1_DIV_SHIFT |
-		m_seed << DSI_PLL_M1_DIV_SHIFT;
+	/* DSI data rate = pixel clock * bits per pixel / lane count
+	   pixel clock is converted from KHz to Hz */
+	dsi_clk_khz = DIV_ROUND_CLOSEST(mode->clock * bpp, lane_count);
 
-	return 0;
+	return dsi_clk_khz;
 }
 
-#else
+#endif
 
 static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
 {
@@ -194,36 +169,47 @@ static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
 	u32 ref_clk;
 	u32 error;
 	u32 tmp_error;
-	u32 target_dsi_clk;
-	u32 calc_dsi_clk;
+	int target_dsi_clk;
+	int calc_dsi_clk;
 	u32 calc_m;
 	u32 calc_p;
 	u32 m_seed;
 
-	if (dsi_clk < 300 || dsi_clk > 1150) {
+	/* dsi_clk is expected in KHZ */
+	if (dsi_clk < 300000 || dsi_clk > 1150000) {
 		DRM_ERROR("DSI CLK Out of Range\n");
 		return -ECHRNG;
 	}
 
 	ref_clk = 25000;
-	target_dsi_clk = dsi_clk * 1000;
+	target_dsi_clk = dsi_clk;
 	error = 0xFFFFFFFF;
+	tmp_error = 0xFFFFFFFF;
 	calc_m = 0;
 	calc_p = 0;
 
 	for (m = 62; m <= 92; m++) {
 		for (p = 2; p <= 6; p++) {
-
+			/* Find the optimal m and p divisors
+			with minimal error +/- the required clock */
 			calc_dsi_clk = (m * ref_clk) / p;
-			if (calc_dsi_clk >= target_dsi_clk) {
-				tmp_error = calc_dsi_clk - target_dsi_clk;
-				if (tmp_error < error) {
-					error = tmp_error;
-					calc_m = m;
-					calc_p = p;
-				}
+			if (calc_dsi_clk == target_dsi_clk) {
+				calc_m = m;
+				calc_p = p;
+				error = 0;
+				break;
+			} else
+				tmp_error = abs(target_dsi_clk - calc_dsi_clk);
+
+			if (tmp_error < error) {
+				error = tmp_error;
+				calc_m = m;
+				calc_p = p;
 			}
 		}
+
+		if (error == 0)
+			break;
 	}
 
 	m_seed = lfsr_converts[calc_m - 62];
@@ -235,8 +221,6 @@ static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
 	return 0;
 }
 
-#endif
-
 /*
  * XXX: The muxing and gating is hard coded for now. Need to add support for
  * sharing PLLs with two DSI outputs.
@@ -251,9 +235,8 @@ static void vlv_configure_dsi_pll(struct intel_encoder *encoder)
 	struct dsi_mnp dsi_mnp;
 	u32 dsi_clk;
 
-	dsi_clk = dsi_rr_formula(mode, intel_dsi->pixel_format,
-				 intel_dsi->video_mode_format,
-				 intel_dsi->lane_count, !intel_dsi->eot_disable);
+	dsi_clk = dsi_clk_from_pclk(mode, intel_dsi->pixel_format,
+						intel_dsi->lane_count);
 
 	ret = dsi_calc_mnp(dsi_clk, &dsi_mnp);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 3c7736546856..eeff998e52ef 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -234,8 +234,9 @@ static void intel_dvo_dpms(struct drm_connector *connector, int mode)
 	intel_modeset_check_state(connector->dev);
 }
 
-static int intel_dvo_mode_valid(struct drm_connector *connector,
-				struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_dvo_mode_valid(struct drm_connector *connector,
+		     struct drm_display_mode *mode)
 {
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 895fcb4fbd94..39eac9937a4a 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -57,18 +57,14 @@ static struct fb_ops intelfb_ops = {
 	.fb_debug_leave = drm_fb_helper_debug_leave,
 };
 
-static int intelfb_create(struct drm_fb_helper *helper,
-			  struct drm_fb_helper_surface_size *sizes)
+static int intelfb_alloc(struct drm_fb_helper *helper,
+			 struct drm_fb_helper_surface_size *sizes)
 {
 	struct intel_fbdev *ifbdev =
 		container_of(helper, struct intel_fbdev, helper);
 	struct drm_device *dev = helper->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct fb_info *info;
-	struct drm_framebuffer *fb;
 	struct drm_mode_fb_cmd2 mode_cmd = {};
 	struct drm_i915_gem_object *obj;
-	struct device *device = &dev->pdev->dev;
 	int size, ret;
 
 	/* we don't do packed 24bpp */
@@ -94,8 +90,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out;
 	}
 
-	mutex_lock(&dev->struct_mutex);
-
 	/* Flush everything out, we'll be doing GTT only from now on */
 	ret = intel_pin_and_fence_fb_obj(dev, obj, NULL);
 	if (ret) {
@@ -103,7 +97,50 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unref;
 	}
 
-	info = framebuffer_alloc(0, device);
+	ret = intel_framebuffer_init(dev, &ifbdev->ifb, &mode_cmd, obj);
+	if (ret)
+		goto out_unpin;
+
+	return 0;
+
+out_unpin:
+	i915_gem_object_unpin(obj);
+out_unref:
+	drm_gem_object_unreference(&obj->base);
+out:
+	return ret;
+}
+
+static int intelfb_create(struct drm_fb_helper *helper,
+			  struct drm_fb_helper_surface_size *sizes)
+{
+	struct intel_fbdev *ifbdev =
+		container_of(helper, struct intel_fbdev, helper);
+	struct intel_framebuffer *intel_fb = &ifbdev->ifb;
+	struct drm_device *dev = helper->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct fb_info *info;
+	struct drm_framebuffer *fb;
+	struct drm_i915_gem_object *obj;
+	int size, ret;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (!intel_fb->obj) {
+		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
+		ret = intelfb_alloc(helper, sizes);
+		if (ret)
+			goto out_unlock;
+	} else {
+		DRM_DEBUG_KMS("re-using BIOS fb\n");
+		sizes->fb_width = intel_fb->base.width;
+		sizes->fb_height = intel_fb->base.height;
+	}
+
+	obj = intel_fb->obj;
+	size = obj->base.size;
+
+	info = framebuffer_alloc(0, &dev->pdev->dev);
 	if (!info) {
 		ret = -ENOMEM;
 		goto out_unpin;
@@ -111,10 +148,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	info->par = helper;
 
-	ret = intel_framebuffer_init(dev, &ifbdev->ifb, &mode_cmd, obj);
-	if (ret)
-		goto out_unpin;
-
 	fb = &ifbdev->ifb.base;
 
 	ifbdev->helper.fb = fb;
@@ -170,17 +203,15 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		      fb->width, fb->height,
 		      i915_gem_obj_ggtt_offset(obj), obj);
 
-
 	mutex_unlock(&dev->struct_mutex);
 	vga_switcheroo_client_fb_set(dev->pdev, info);
 	return 0;
 
 out_unpin:
 	i915_gem_object_unpin(obj);
-out_unref:
 	drm_gem_object_unreference(&obj->base);
+out_unlock:
 	mutex_unlock(&dev->struct_mutex);
-out:
 	return ret;
 }
 
@@ -297,8 +328,6 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 	fb_set_suspend(info, state);
 }
 
-MODULE_LICENSE("GPL and additional rights");
-
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 03f9ca70530c..6db0d9d17f47 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -130,9 +130,9 @@ static u32 hsw_infoframe_data_reg(enum hdmi_infoframe_type type,
 
 static void g4x_write_infoframe(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len)
+				const void *frame, ssize_t len)
 {
-	uint32_t *data = (uint32_t *)frame;
+	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val = I915_READ(VIDEO_DIP_CTL);
@@ -167,9 +167,9 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 
 static void ibx_write_infoframe(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len)
+				const void *frame, ssize_t len)
 {
-	uint32_t *data = (uint32_t *)frame;
+	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
@@ -205,9 +205,9 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 
 static void cpt_write_infoframe(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len)
+				const void *frame, ssize_t len)
 {
-	uint32_t *data = (uint32_t *)frame;
+	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
@@ -246,9 +246,9 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 
 static void vlv_write_infoframe(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len)
+				const void *frame, ssize_t len)
 {
-	uint32_t *data = (uint32_t *)frame;
+	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
@@ -284,9 +284,9 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 
 static void hsw_write_infoframe(struct drm_encoder *encoder,
 				enum hdmi_infoframe_type type,
-				const uint8_t *frame, ssize_t len)
+				const void *frame, ssize_t len)
 {
-	uint32_t *data = (uint32_t *)frame;
+	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
@@ -853,8 +853,9 @@ static int hdmi_portclock_limit(struct intel_hdmi *hdmi)
 		return 225000;
 }
 
-static int intel_hdmi_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_hdmi_mode_valid(struct drm_connector *connector,
+		      struct drm_display_mode *mode)
 {
 	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector)))
 		return MODE_CLOCK_HIGH;
@@ -1081,7 +1082,7 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 	u32 val;
 
@@ -1090,41 +1091,33 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 
 	/* Enable clock channels for this port */
 	mutex_lock(&dev_priv->dpio_lock);
-	val = vlv_dpio_read(dev_priv, pipe, DPIO_DATA_LANE_A(port));
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
 	val = 0;
 	if (pipe)
 		val |= (1<<21);
 	else
 		val &= ~(1<<21);
 	val |= 0x001000c4;
-	vlv_dpio_write(dev_priv, pipe, DPIO_DATA_CHANNEL(port), val);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW8(port), val);
 
 	/* HDMI 1.0V-2dB */
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_OCALINIT(port), 0);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL4(port),
-			 0x2b245f5f);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL2(port),
-			 0x5578b83a);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_SWING_CTL3(port),
-			 0x0c782040);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX3_SWING_CTL4(port),
-			 0x2b247878);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_STAGGER0(port), 0x00030000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CTL_OVER1(port),
-			 0x00002000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_OCALINIT(port),
-			 DPIO_TX_OCALINIT_EN);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW4(port), 0x2b245f5f);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(port), 0x5578b83a);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(port), 0x0c782040);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX3_DW4(port), 0x2b247878);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW11(port), 0x00030000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), 0x00002000);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), DPIO_TX_OCALINIT_EN);
 
 	/* Program lane clock */
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLOCKBUF0(port),
-			 0x00760018);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLOCKBUF8(port),
-			 0x00400888);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW14(port), 0x00760018);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	intel_enable_hdmi(encoder);
 
-	vlv_wait_port_ready(dev_priv, port);
+	vlv_wait_port_ready(dev_priv, dport);
 }
 
 static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
@@ -1134,7 +1127,7 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
 	if (!IS_VALLEYVIEW(dev))
@@ -1142,24 +1135,22 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 
 	/* Program Tx lane resets to default */
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_TX(port),
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLK(port),
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port),
 			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
 			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
 			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
 			 DPIO_PCS_CLK_SOFT_RESET);
 
 	/* Fix up inter-pair skew failure */
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_STAGGER1(port), 0x00750f00);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_CTL(port), 0x00001500);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_LANE(port), 0x40400000);
-
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CTL_OVER1(port),
-			 0x00002000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_TX_OCALINIT(port),
-			 DPIO_TX_OCALINIT_EN);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW12(port), 0x00750f00);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW11(port), 0x00001500);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW14(port), 0x40400000);
+
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), 0x00002000);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), DPIO_TX_OCALINIT_EN);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
@@ -1169,13 +1160,13 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
-	int port = vlv_dport_to_channel(dport);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
 	/* Reset lanes to avoid HDMI flicker (VLV w/a) */
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_TX(port), 0x00000000);
-	vlv_dpio_write(dev_priv, pipe, DPIO_PCS_CLK(port), 0x00e00060);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port), 0x00000000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port), 0x00e00060);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 2ca17b14b6c1..b1dc33f47899 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -82,20 +82,11 @@ static int get_disp_clk_div(struct drm_i915_private *dev_priv,
 
 static void gmbus_set_freq(struct drm_i915_private *dev_priv)
 {
-	int vco_freq[] = { 800, 1600, 2000, 2400 };
-	int gmbus_freq = 0, cdclk_div, hpll_freq;
+	int vco, gmbus_freq = 0, cdclk_div;
 
 	BUG_ON(!IS_VALLEYVIEW(dev_priv->dev));
 
-	/* Skip setting the gmbus freq if BIOS has already programmed it */
-	if (I915_READ(GMBUSFREQ_VLV) != 0xA0)
-		return;
-
-	/* Obtain SKU information */
-	mutex_lock(&dev_priv->dpio_lock);
-	hpll_freq =
-		vlv_cck_read(dev_priv, CCK_FUSE_REG) & CCK_FUSE_HPLL_FREQ_MASK;
-	mutex_unlock(&dev_priv->dpio_lock);
+	vco = valleyview_get_vco(dev_priv);
 
 	/* Get the CDCLK divide ratio */
 	cdclk_div = get_disp_clk_div(dev_priv, CDCLK);
@@ -106,7 +97,7 @@ static void gmbus_set_freq(struct drm_i915_private *dev_priv)
 	 * in fact 1MHz is the correct frequency.
 	 */
 	if (cdclk_div)
-		gmbus_freq = (vco_freq[hpll_freq] << 1) / cdclk_div;
+		gmbus_freq = (vco << 1) / cdclk_div;
 
 	if (WARN_ON(gmbus_freq == 0))
 		return;
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index c3b4da7895ed..8bcb93a2a9f6 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -256,8 +256,9 @@ static void intel_disable_lvds(struct intel_encoder *encoder)
 	POSTING_READ(lvds_encoder->reg);
 }
 
-static int intel_lvds_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_lvds_mode_valid(struct drm_connector *connector,
+		      struct drm_display_mode *mode)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
@@ -446,9 +447,19 @@ static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
 	if (dev_priv->modeset_restore == MODESET_DONE)
 		goto exit;
 
-	drm_modeset_lock_all(dev);
-	intel_modeset_setup_hw_state(dev, true);
-	drm_modeset_unlock_all(dev);
+	/*
+	 * Some old platform's BIOS love to wreak havoc while the lid is closed.
+	 * We try to detect this here and undo any damage. The split for PCH
+	 * platforms is rather conservative and a bit arbitrary expect that on
+	 * those platforms VGA disabling requires actual legacy VGA I/O access,
+	 * and as part of the cleanup in the hw state restore we also redisable
+	 * the vga plane.
+	 */
+	if (!HAS_PCH_SPLIT(dev)) {
+		drm_modeset_lock_all(dev);
+		intel_modeset_setup_hw_state(dev, true);
+		drm_modeset_unlock_all(dev);
+	}
 
 	dev_priv->modeset_restore = MODESET_DONE;
 
@@ -744,57 +755,6 @@ static const struct dmi_system_id intel_no_lvds[] = {
 	{ }	/* terminating entry */
 };
 
-/**
- * intel_find_lvds_downclock - find the reduced downclock for LVDS in EDID
- * @dev: drm device
- * @connector: LVDS connector
- *
- * Find the reduced downclock for LVDS in EDID.
- */
-static void intel_find_lvds_downclock(struct drm_device *dev,
-				      struct drm_display_mode *fixed_mode,
-				      struct drm_connector *connector)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_display_mode *scan;
-	int temp_downclock;
-
-	temp_downclock = fixed_mode->clock;
-	list_for_each_entry(scan, &connector->probed_modes, head) {
-		/*
-		 * If one mode has the same resolution with the fixed_panel
-		 * mode while they have the different refresh rate, it means
-		 * that the reduced downclock is found for the LVDS. In such
-		 * case we can set the different FPx0/1 to dynamically select
-		 * between low and high frequency.
-		 */
-		if (scan->hdisplay == fixed_mode->hdisplay &&
-		    scan->hsync_start == fixed_mode->hsync_start &&
-		    scan->hsync_end == fixed_mode->hsync_end &&
-		    scan->htotal == fixed_mode->htotal &&
-		    scan->vdisplay == fixed_mode->vdisplay &&
-		    scan->vsync_start == fixed_mode->vsync_start &&
-		    scan->vsync_end == fixed_mode->vsync_end &&
-		    scan->vtotal == fixed_mode->vtotal) {
-			if (scan->clock < temp_downclock) {
-				/*
-				 * The downclock is already found. But we
-				 * expect to find the lower downclock.
-				 */
-				temp_downclock = scan->clock;
-			}
-		}
-	}
-	if (temp_downclock < fixed_mode->clock && i915_lvds_downclock) {
-		/* We found the downclock for LVDS. */
-		dev_priv->lvds_downclock_avail = 1;
-		dev_priv->lvds_downclock = temp_downclock;
-		DRM_DEBUG_KMS("LVDS downclock is found in EDID. "
-			      "Normal clock %dKhz, downclock %dKhz\n",
-			      fixed_mode->clock, temp_downclock);
-	}
-}
-
 /*
  * Enumerate the child dev array parsed from VBT to check whether
  * the LVDS is present.
@@ -1072,8 +1032,22 @@ void intel_lvds_init(struct drm_device *dev)
 
 			fixed_mode = drm_mode_duplicate(dev, scan);
 			if (fixed_mode) {
-				intel_find_lvds_downclock(dev, fixed_mode,
-							  connector);
+				intel_connector->panel.downclock_mode =
+					intel_find_panel_downclock(dev,
+					fixed_mode, connector);
+				if (intel_connector->panel.downclock_mode !=
+					NULL &&	i915_lvds_downclock) {
+					/* We found the downclock for LVDS. */
+					dev_priv->lvds_downclock_avail = true;
+					dev_priv->lvds_downclock =
+						intel_connector->panel.
+						downclock_mode->clock;
+					DRM_DEBUG_KMS("LVDS downclock is found"
+					" in EDID. Normal clock %dKhz, "
+					"downclock %dKhz\n",
+					fixed_mode->clock,
+					dev_priv->lvds_downclock);
+				}
 				goto out;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 9a8804bee5cd..4e960ec7419f 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -63,7 +63,7 @@ struct opregion_header {
 	u8 driver_ver[16];
 	u32 mboxes;
 	u8 reserved[164];
-} __attribute__((packed));
+} __packed;
 
 /* OpRegion mailbox #1: public ACPI methods */
 struct opregion_acpi {
@@ -85,7 +85,7 @@ struct opregion_acpi {
 	u32 cnot;       /* current OS notification */
 	u32 nrdy;       /* driver status */
 	u8 rsvd2[60];
-} __attribute__((packed));
+} __packed;
 
 /* OpRegion mailbox #2: SWSCI */
 struct opregion_swsci {
@@ -93,7 +93,7 @@ struct opregion_swsci {
 	u32 parm;       /* command parameters */
 	u32 dslp;       /* driver sleep time-out */
 	u8 rsvd[244];
-} __attribute__((packed));
+} __packed;
 
 /* OpRegion mailbox #3: ASLE */
 struct opregion_asle {
@@ -114,7 +114,7 @@ struct opregion_asle {
 	u32 srot;       /* supported rotation angles */
 	u32 iuer;       /* IUER events */
 	u8 rsvd[86];
-} __attribute__((packed));
+} __packed;
 
 /* Driver readiness indicator */
 #define ASLE_ARDY_READY		(1 << 0)
@@ -395,13 +395,8 @@ int intel_opregion_notify_adapter(struct drm_device *dev, pci_power_t state)
 static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_encoder *encoder;
-	struct drm_connector *connector;
-	struct intel_connector *intel_connector = NULL;
-	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[0];
+	struct intel_connector *intel_connector;
 	struct opregion_asle __iomem *asle = dev_priv->opregion.asle;
-	u32 ret = 0;
-	bool found = false;
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
@@ -413,38 +408,20 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 		return ASLC_BACKLIGHT_FAILED;
 
 	mutex_lock(&dev->mode_config.mutex);
+
 	/*
-	 * Could match the OpRegion connector here instead, but we'd also need
-	 * to verify the connector could handle a backlight call.
+	 * Update backlight on all connectors that support backlight (usually
+	 * only one).
 	 */
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
-		if (encoder->crtc == crtc) {
-			found = true;
-			break;
-		}
-
-	if (!found) {
-		ret = ASLC_BACKLIGHT_FAILED;
-		goto out;
-	}
-
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
-		if (connector->encoder == encoder)
-			intel_connector = to_intel_connector(connector);
-
-	if (!intel_connector) {
-		ret = ASLC_BACKLIGHT_FAILED;
-		goto out;
-	}
-
 	DRM_DEBUG_KMS("updating opregion backlight %d/255\n", bclp);
-	intel_panel_set_backlight(intel_connector, bclp, 255);
+	list_for_each_entry(intel_connector, &dev->mode_config.connector_list, base.head)
+		intel_panel_set_backlight(intel_connector, bclp, 255);
 	iowrite32(DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID, &asle->cblv);
 
-out:
 	mutex_unlock(&dev->mode_config.mutex);
 
-	return ret;
+
+	return 0;
 }
 
 static u32 asle_set_als_illum(struct drm_device *dev, u32 alsi)
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index a98a990fbab3..a759ecdb7a6e 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1005,7 +1005,7 @@ static int intel_panel_fitter_pipe(struct drm_device *dev)
 	u32  pfit_control;
 
 	/* i830 doesn't have a panel fitter */
-	if (IS_I830(dev))
+	if (INTEL_INFO(dev)->gen <= 3 && (IS_I830(dev) || !IS_MOBILE(dev)))
 		return -1;
 
 	pfit_control = I915_READ(PFIT_CONTROL);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index e6f782d1c669..350de359123a 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -325,214 +325,170 @@ out:
 	pipe_config->gmch_pfit.lvds_border_bits = border;
 }
 
-static int is_backlight_combination_mode(struct drm_device *dev)
+static int i915_panel_invert_brightness;
+MODULE_PARM_DESC(invert_brightness, "Invert backlight brightness "
+	"(-1 force normal, 0 machine defaults, 1 force inversion), please "
+	"report PCI device ID, subsystem vendor and subsystem device ID "
+	"to dri-devel@lists.freedesktop.org, if your machine needs it. "
+	"It will then be included in an upcoming module version.");
+module_param_named(invert_brightness, i915_panel_invert_brightness, int, 0600);
+static u32 intel_panel_compute_brightness(struct intel_connector *connector,
+					  u32 val)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
 
-	if (IS_GEN4(dev))
-		return I915_READ(BLC_PWM_CTL2) & BLM_COMBINATION_MODE;
+	WARN_ON(panel->backlight.max == 0);
 
-	if (IS_GEN2(dev))
-		return I915_READ(BLC_PWM_CTL) & BLM_LEGACY_MODE;
+	if (i915_panel_invert_brightness < 0)
+		return val;
 
-	return 0;
+	if (i915_panel_invert_brightness > 0 ||
+	    dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) {
+		return panel->backlight.max - val;
+	}
+
+	return val;
 }
 
-/* XXX: query mode clock or hardware clock and program max PWM appropriately
- * when it's 0.
- */
-static u32 i915_read_blc_pwm_ctl(struct drm_device *dev, enum pipe pipe)
+static u32 bdw_get_backlight(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val;
 
-	WARN_ON_SMP(!spin_is_locked(&dev_priv->backlight.lock));
-
-	/* Restore the CTL value if it lost, e.g. GPU reset */
-
-	if (HAS_PCH_SPLIT(dev_priv->dev)) {
-		val = I915_READ(BLC_PWM_PCH_CTL2);
-		if (dev_priv->regfile.saveBLC_PWM_CTL2 == 0) {
-			dev_priv->regfile.saveBLC_PWM_CTL2 = val;
-		} else if (val == 0) {
-			val = dev_priv->regfile.saveBLC_PWM_CTL2;
-			I915_WRITE(BLC_PWM_PCH_CTL2, val);
-		}
-	} else if (IS_VALLEYVIEW(dev)) {
-		val = I915_READ(VLV_BLC_PWM_CTL(pipe));
-		if (dev_priv->regfile.saveBLC_PWM_CTL == 0) {
-			dev_priv->regfile.saveBLC_PWM_CTL = val;
-			dev_priv->regfile.saveBLC_PWM_CTL2 =
-				I915_READ(VLV_BLC_PWM_CTL2(pipe));
-		} else if (val == 0) {
-			val = dev_priv->regfile.saveBLC_PWM_CTL;
-			I915_WRITE(VLV_BLC_PWM_CTL(pipe), val);
-			I915_WRITE(VLV_BLC_PWM_CTL2(pipe),
-				   dev_priv->regfile.saveBLC_PWM_CTL2);
-		}
+	return I915_READ(BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
+}
 
-		if (!val)
-			val = 0x0f42ffff;
-	} else {
-		val = I915_READ(BLC_PWM_CTL);
-		if (dev_priv->regfile.saveBLC_PWM_CTL == 0) {
-			dev_priv->regfile.saveBLC_PWM_CTL = val;
-			if (INTEL_INFO(dev)->gen >= 4)
-				dev_priv->regfile.saveBLC_PWM_CTL2 =
-					I915_READ(BLC_PWM_CTL2);
-		} else if (val == 0) {
-			val = dev_priv->regfile.saveBLC_PWM_CTL;
-			I915_WRITE(BLC_PWM_CTL, val);
-			if (INTEL_INFO(dev)->gen >= 4)
-				I915_WRITE(BLC_PWM_CTL2,
-					   dev_priv->regfile.saveBLC_PWM_CTL2);
-		}
-	}
+static u32 pch_get_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	return val;
+	return I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
 }
 
-static u32 intel_panel_get_max_backlight(struct drm_device *dev,
-					 enum pipe pipe)
+static u32 i9xx_get_backlight(struct intel_connector *connector)
 {
-	u32 max;
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 val;
 
-	max = i915_read_blc_pwm_ctl(dev, pipe);
+	val = I915_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
+	if (INTEL_INFO(dev)->gen < 4)
+		val >>= 1;
 
-	if (HAS_PCH_SPLIT(dev)) {
-		max >>= 16;
-	} else {
-		if (INTEL_INFO(dev)->gen < 4)
-			max >>= 17;
-		else
-			max >>= 16;
+	if (panel->backlight.combination_mode) {
+		u8 lbpc;
 
-		if (is_backlight_combination_mode(dev))
-			max *= 0xff;
+		pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc);
+		val *= lbpc;
 	}
 
-	DRM_DEBUG_DRIVER("max backlight PWM = %d\n", max);
-
-	return max;
+	return val;
 }
 
-static int i915_panel_invert_brightness;
-MODULE_PARM_DESC(invert_brightness, "Invert backlight brightness "
-	"(-1 force normal, 0 machine defaults, 1 force inversion), please "
-	"report PCI device ID, subsystem vendor and subsystem device ID "
-	"to dri-devel@lists.freedesktop.org, if your machine needs it. "
-	"It will then be included in an upcoming module version.");
-module_param_named(invert_brightness, i915_panel_invert_brightness, int, 0600);
-static u32 intel_panel_compute_brightness(struct drm_device *dev,
-					  enum pipe pipe, u32 val)
+static u32 _vlv_get_backlight(struct drm_device *dev, enum pipe pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (i915_panel_invert_brightness < 0)
-		return val;
+	return I915_READ(VLV_BLC_PWM_CTL(pipe)) & BACKLIGHT_DUTY_CYCLE_MASK;
+}
 
-	if (i915_panel_invert_brightness > 0 ||
-	    dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) {
-		u32 max = intel_panel_get_max_backlight(dev, pipe);
-		if (max)
-			return max - val;
-	}
+static u32 vlv_get_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
 
-	return val;
+	return _vlv_get_backlight(dev, pipe);
 }
 
-static u32 intel_panel_get_backlight(struct drm_device *dev,
-				     enum pipe pipe)
+static u32 intel_panel_get_backlight(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
 	unsigned long flags;
-	int reg;
-
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
-
-	if (IS_BROADWELL(dev)) {
-		val = I915_READ(BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
-	} else if (HAS_PCH_SPLIT(dev)) {
-		val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
-	} else {
-		if (IS_VALLEYVIEW(dev))
-			reg = VLV_BLC_PWM_CTL(pipe);
-		else
-			reg = BLC_PWM_CTL;
-
-		val = I915_READ(reg) & BACKLIGHT_DUTY_CYCLE_MASK;
-		if (INTEL_INFO(dev)->gen < 4)
-			val >>= 1;
-
-		if (is_backlight_combination_mode(dev)) {
-			u8 lbpc;
 
-			pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc);
-			val *= lbpc;
-		}
-	}
+	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
 
-	val = intel_panel_compute_brightness(dev, pipe, val);
+	val = dev_priv->display.get_backlight(connector);
+	val = intel_panel_compute_brightness(connector, val);
 
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
+	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
 
 	DRM_DEBUG_DRIVER("get backlight PWM = %d\n", val);
 	return val;
 }
 
-static void intel_bdw_panel_set_backlight(struct drm_device *dev, u32 level)
+static void bdw_set_backlight(struct intel_connector *connector, u32 level)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val = I915_READ(BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK;
 	I915_WRITE(BLC_PWM_PCH_CTL2, val | level);
 }
 
-static void intel_pch_panel_set_backlight(struct drm_device *dev, u32 level)
+static void pch_set_backlight(struct intel_connector *connector, u32 level)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val = I915_READ(BLC_PWM_CPU_CTL) & ~BACKLIGHT_DUTY_CYCLE_MASK;
-	I915_WRITE(BLC_PWM_CPU_CTL, val | level);
+	u32 tmp;
+
+	tmp = I915_READ(BLC_PWM_CPU_CTL) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	I915_WRITE(BLC_PWM_CPU_CTL, tmp | level);
 }
 
-static void intel_panel_actually_set_backlight(struct drm_device *dev,
-					       enum pipe pipe, u32 level)
+static void i9xx_set_backlight(struct intel_connector *connector, u32 level)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 tmp;
-	int reg;
-
-	DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level);
-	level = intel_panel_compute_brightness(dev, pipe, level);
+	struct intel_panel *panel = &connector->panel;
+	u32 tmp, mask;
 
-	if (IS_BROADWELL(dev))
-		return intel_bdw_panel_set_backlight(dev, level);
-	else if (HAS_PCH_SPLIT(dev))
-		return intel_pch_panel_set_backlight(dev, level);
+	WARN_ON(panel->backlight.max == 0);
 
-	if (is_backlight_combination_mode(dev)) {
-		u32 max = intel_panel_get_max_backlight(dev, pipe);
+	if (panel->backlight.combination_mode) {
 		u8 lbpc;
 
-		/* we're screwed, but keep behaviour backwards compatible */
-		if (!max)
-			max = 1;
-
-		lbpc = level * 0xfe / max + 1;
+		lbpc = level * 0xfe / panel->backlight.max + 1;
 		level /= lbpc;
 		pci_write_config_byte(dev->pdev, PCI_LBPC, lbpc);
 	}
 
-	if (IS_VALLEYVIEW(dev))
-		reg = VLV_BLC_PWM_CTL(pipe);
-	else
-		reg = BLC_PWM_CTL;
-
-	tmp = I915_READ(reg);
-	if (INTEL_INFO(dev)->gen < 4)
+	if (IS_GEN4(dev)) {
+		mask = BACKLIGHT_DUTY_CYCLE_MASK;
+	} else {
 		level <<= 1;
-	tmp &= ~BACKLIGHT_DUTY_CYCLE_MASK;
-	I915_WRITE(reg, tmp | level);
+		mask = BACKLIGHT_DUTY_CYCLE_MASK_PNV;
+	}
+
+	tmp = I915_READ(BLC_PWM_CTL) & ~mask;
+	I915_WRITE(BLC_PWM_CTL, tmp | level);
+}
+
+static void vlv_set_backlight(struct intel_connector *connector, u32 level)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
+	u32 tmp;
+
+	tmp = I915_READ(VLV_BLC_PWM_CTL(pipe)) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	I915_WRITE(VLV_BLC_PWM_CTL(pipe), tmp | level);
+}
+
+static void
+intel_panel_actually_set_backlight(struct intel_connector *connector, u32 level)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level);
+
+	level = intel_panel_compute_brightness(connector, level);
+	dev_priv->display.set_backlight(connector, level);
 }
 
 /* set backlight brightness to level in range [0..max] */
@@ -541,45 +497,89 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 {
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
 	enum pipe pipe = intel_get_pipe_from_connector(connector);
 	u32 freq;
 	unsigned long flags;
 
-	if (pipe == INVALID_PIPE)
+	if (!panel->backlight.present || pipe == INVALID_PIPE)
 		return;
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
+	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
 
-	freq = intel_panel_get_max_backlight(dev, pipe);
-	if (!freq) {
-		/* we are screwed, bail out */
-		goto out;
-	}
+	WARN_ON(panel->backlight.max == 0);
 
-	/* scale to hardware, but be careful to not overflow */
+	/* scale to hardware max, but be careful to not overflow */
+	freq = panel->backlight.max;
 	if (freq < max)
 		level = level * freq / max;
 	else
 		level = freq / max * level;
 
-	dev_priv->backlight.level = level;
-	if (dev_priv->backlight.device)
-		dev_priv->backlight.device->props.brightness = level;
+	panel->backlight.level = level;
+	if (panel->backlight.device)
+		panel->backlight.device->props.brightness = level;
 
-	if (dev_priv->backlight.enabled)
-		intel_panel_actually_set_backlight(dev, pipe, level);
-out:
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
+	if (panel->backlight.enabled)
+		intel_panel_actually_set_backlight(connector, level);
+
+	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
+}
+
+static void pch_disable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 tmp;
+
+	intel_panel_actually_set_backlight(connector, 0);
+
+	tmp = I915_READ(BLC_PWM_CPU_CTL2);
+	I915_WRITE(BLC_PWM_CPU_CTL2, tmp & ~BLM_PWM_ENABLE);
+
+	tmp = I915_READ(BLC_PWM_PCH_CTL1);
+	I915_WRITE(BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
+}
+
+static void i9xx_disable_backlight(struct intel_connector *connector)
+{
+	intel_panel_actually_set_backlight(connector, 0);
+}
+
+static void i965_disable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 tmp;
+
+	intel_panel_actually_set_backlight(connector, 0);
+
+	tmp = I915_READ(BLC_PWM_CTL2);
+	I915_WRITE(BLC_PWM_CTL2, tmp & ~BLM_PWM_ENABLE);
+}
+
+static void vlv_disable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
+	u32 tmp;
+
+	intel_panel_actually_set_backlight(connector, 0);
+
+	tmp = I915_READ(VLV_BLC_PWM_CTL2(pipe));
+	I915_WRITE(VLV_BLC_PWM_CTL2(pipe), tmp & ~BLM_PWM_ENABLE);
 }
 
 void intel_panel_disable_backlight(struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
 	enum pipe pipe = intel_get_pipe_from_connector(connector);
 	unsigned long flags;
 
-	if (pipe == INVALID_PIPE)
+	if (!panel->backlight.present || pipe == INVALID_PIPE)
 		return;
 
 	/*
@@ -593,150 +593,215 @@ void intel_panel_disable_backlight(struct intel_connector *connector)
 		return;
 	}
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
+	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
 
-	dev_priv->backlight.enabled = false;
-	intel_panel_actually_set_backlight(dev, pipe, 0);
+	panel->backlight.enabled = false;
+	dev_priv->display.disable_backlight(connector);
 
-	if (INTEL_INFO(dev)->gen >= 4) {
-		uint32_t reg, tmp;
+	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
+}
 
-		if (HAS_PCH_SPLIT(dev))
-			reg = BLC_PWM_CPU_CTL2;
-		else if (IS_VALLEYVIEW(dev))
-			reg = VLV_BLC_PWM_CTL2(pipe);
-		else
-			reg = BLC_PWM_CTL2;
+static void bdw_enable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 pch_ctl1, pch_ctl2;
+
+	pch_ctl1 = I915_READ(BLC_PWM_PCH_CTL1);
+	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
+		DRM_DEBUG_KMS("pch backlight already enabled\n");
+		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
+		I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1);
+	}
 
-		I915_WRITE(reg, I915_READ(reg) & ~BLM_PWM_ENABLE);
+	pch_ctl2 = panel->backlight.max << 16;
+	I915_WRITE(BLC_PWM_PCH_CTL2, pch_ctl2);
 
-		if (HAS_PCH_SPLIT(dev)) {
-			tmp = I915_READ(BLC_PWM_PCH_CTL1);
-			tmp &= ~BLM_PCH_PWM_ENABLE;
-			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
-		}
-	}
+	pch_ctl1 = 0;
+	if (panel->backlight.active_low_pwm)
+		pch_ctl1 |= BLM_PCH_POLARITY;
 
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
+	/* BDW always uses the pch pwm controls. */
+	pch_ctl1 |= BLM_PCH_OVERRIDE_ENABLE;
+
+	I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1);
+	POSTING_READ(BLC_PWM_PCH_CTL1);
+	I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1 | BLM_PCH_PWM_ENABLE);
+
+	/* This won't stick until the above enable. */
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 }
 
-void intel_panel_enable_backlight(struct intel_connector *connector)
+static void pch_enable_backlight(struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
 	enum pipe pipe = intel_get_pipe_from_connector(connector);
 	enum transcoder cpu_transcoder =
 		intel_pipe_to_cpu_transcoder(dev_priv, pipe);
-	unsigned long flags;
+	u32 cpu_ctl2, pch_ctl1, pch_ctl2;
 
-	if (pipe == INVALID_PIPE)
-		return;
+	cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2);
+	if (cpu_ctl2 & BLM_PWM_ENABLE) {
+		WARN(1, "cpu backlight already enabled\n");
+		cpu_ctl2 &= ~BLM_PWM_ENABLE;
+		I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2);
+	}
 
-	DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe));
+	pch_ctl1 = I915_READ(BLC_PWM_PCH_CTL1);
+	if (pch_ctl1 & BLM_PCH_PWM_ENABLE) {
+		DRM_DEBUG_KMS("pch backlight already enabled\n");
+		pch_ctl1 &= ~BLM_PCH_PWM_ENABLE;
+		I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1);
+	}
+
+	if (cpu_transcoder == TRANSCODER_EDP)
+		cpu_ctl2 = BLM_TRANSCODER_EDP;
+	else
+		cpu_ctl2 = BLM_PIPE(cpu_transcoder);
+	I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2);
+	POSTING_READ(BLC_PWM_CPU_CTL2);
+	I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2 | BLM_PWM_ENABLE);
+
+	/* This won't stick until the above enable. */
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
+
+	pch_ctl2 = panel->backlight.max << 16;
+	I915_WRITE(BLC_PWM_PCH_CTL2, pch_ctl2);
+
+	pch_ctl1 = 0;
+	if (panel->backlight.active_low_pwm)
+		pch_ctl1 |= BLM_PCH_POLARITY;
+
+	I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1);
+	POSTING_READ(BLC_PWM_PCH_CTL1);
+	I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1 | BLM_PCH_PWM_ENABLE);
+}
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
+static void i9xx_enable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, freq;
 
-	if (dev_priv->backlight.level == 0) {
-		dev_priv->backlight.level = intel_panel_get_max_backlight(dev,
-									  pipe);
-		if (dev_priv->backlight.device)
-			dev_priv->backlight.device->props.brightness =
-				dev_priv->backlight.level;
+	ctl = I915_READ(BLC_PWM_CTL);
+	if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) {
+		WARN(1, "backlight already enabled\n");
+		I915_WRITE(BLC_PWM_CTL, 0);
 	}
 
-	if (INTEL_INFO(dev)->gen >= 4) {
-		uint32_t reg, tmp;
+	freq = panel->backlight.max;
+	if (panel->backlight.combination_mode)
+		freq /= 0xff;
 
-		if (HAS_PCH_SPLIT(dev))
-			reg = BLC_PWM_CPU_CTL2;
-		else if (IS_VALLEYVIEW(dev))
-			reg = VLV_BLC_PWM_CTL2(pipe);
-		else
-			reg = BLC_PWM_CTL2;
+	ctl = freq << 17;
+	if (IS_GEN2(dev) && panel->backlight.combination_mode)
+		ctl |= BLM_LEGACY_MODE;
+	if (IS_PINEVIEW(dev) && panel->backlight.active_low_pwm)
+		ctl |= BLM_POLARITY_PNV;
 
-		tmp = I915_READ(reg);
+	I915_WRITE(BLC_PWM_CTL, ctl);
+	POSTING_READ(BLC_PWM_CTL);
 
-		/* Note that this can also get called through dpms changes. And
-		 * we don't track the backlight dpms state, hence check whether
-		 * we have to do anything first. */
-		if (tmp & BLM_PWM_ENABLE)
-			goto set_level;
+	/* XXX: combine this into above write? */
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
+}
 
-		if (INTEL_INFO(dev)->num_pipes == 3)
-			tmp &= ~BLM_PIPE_SELECT_IVB;
-		else
-			tmp &= ~BLM_PIPE_SELECT;
+static void i965_enable_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
+	u32 ctl, ctl2, freq;
 
-		if (cpu_transcoder == TRANSCODER_EDP)
-			tmp |= BLM_TRANSCODER_EDP;
-		else
-			tmp |= BLM_PIPE(cpu_transcoder);
-		tmp &= ~BLM_PWM_ENABLE;
-
-		I915_WRITE(reg, tmp);
-		POSTING_READ(reg);
-		I915_WRITE(reg, tmp | BLM_PWM_ENABLE);
-
-		if (IS_BROADWELL(dev)) {
-			/*
-			 * Broadwell requires PCH override to drive the PCH
-			 * backlight pin. The above will configure the CPU
-			 * backlight pin, which we don't plan to use.
-			 */
-			tmp = I915_READ(BLC_PWM_PCH_CTL1);
-			tmp |= BLM_PCH_OVERRIDE_ENABLE | BLM_PCH_PWM_ENABLE;
-			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
-		} else if (HAS_PCH_SPLIT(dev) &&
-		    !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) {
-			tmp = I915_READ(BLC_PWM_PCH_CTL1);
-			tmp |= BLM_PCH_PWM_ENABLE;
-			tmp &= ~BLM_PCH_OVERRIDE_ENABLE;
-			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
-		}
+	ctl2 = I915_READ(BLC_PWM_CTL2);
+	if (ctl2 & BLM_PWM_ENABLE) {
+		WARN(1, "backlight already enabled\n");
+		ctl2 &= ~BLM_PWM_ENABLE;
+		I915_WRITE(BLC_PWM_CTL2, ctl2);
 	}
 
-set_level:
-	/* Call below after setting BLC_PWM_CPU_CTL2 and BLC_PWM_PCH_CTL1.
-	 * BLC_PWM_CPU_CTL may be cleared to zero automatically when these
-	 * registers are set.
-	 */
-	dev_priv->backlight.enabled = true;
-	intel_panel_actually_set_backlight(dev, pipe,
-					   dev_priv->backlight.level);
+	freq = panel->backlight.max;
+	if (panel->backlight.combination_mode)
+		freq /= 0xff;
+
+	ctl = freq << 16;
+	I915_WRITE(BLC_PWM_CTL, ctl);
+
+	/* XXX: combine this into above write? */
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
+	ctl2 = BLM_PIPE(pipe);
+	if (panel->backlight.combination_mode)
+		ctl2 |= BLM_COMBINATION_MODE;
+	if (panel->backlight.active_low_pwm)
+		ctl2 |= BLM_POLARITY_I965;
+	I915_WRITE(BLC_PWM_CTL2, ctl2);
+	POSTING_READ(BLC_PWM_CTL2);
+	I915_WRITE(BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
 }
 
-/* FIXME: use VBT vals to init PWM_CTL and PWM_CTL2 correctly */
-static void intel_panel_init_backlight_regs(struct drm_device *dev)
+static void vlv_enable_backlight(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
+	u32 ctl, ctl2;
 
-	if (IS_VALLEYVIEW(dev)) {
-		enum pipe pipe;
+	ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe));
+	if (ctl2 & BLM_PWM_ENABLE) {
+		WARN(1, "backlight already enabled\n");
+		ctl2 &= ~BLM_PWM_ENABLE;
+		I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2);
+	}
 
-		for_each_pipe(pipe) {
-			u32 cur_val = I915_READ(VLV_BLC_PWM_CTL(pipe));
+	ctl = panel->backlight.max << 16;
+	I915_WRITE(VLV_BLC_PWM_CTL(pipe), ctl);
 
-			/* Skip if the modulation freq is already set */
-			if (cur_val & ~BACKLIGHT_DUTY_CYCLE_MASK)
-				continue;
+	/* XXX: combine this into above write? */
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 
-			cur_val &= BACKLIGHT_DUTY_CYCLE_MASK;
-			I915_WRITE(VLV_BLC_PWM_CTL(pipe), (0xf42 << 16) |
-				   cur_val);
-		}
-	}
+	ctl2 = 0;
+	if (panel->backlight.active_low_pwm)
+		ctl2 |= BLM_POLARITY_I965;
+	I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2);
+	POSTING_READ(VLV_BLC_PWM_CTL2(pipe));
+	I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2 | BLM_PWM_ENABLE);
 }
 
-static void intel_panel_init_backlight(struct drm_device *dev)
+void intel_panel_enable_backlight(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe = intel_get_pipe_from_connector(connector);
+	unsigned long flags;
+
+	if (!panel->backlight.present || pipe == INVALID_PIPE)
+		return;
+
+	DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe));
+
+	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
+
+	WARN_ON(panel->backlight.max == 0);
 
-	intel_panel_init_backlight_regs(dev);
+	if (panel->backlight.level == 0) {
+		panel->backlight.level = panel->backlight.max;
+		if (panel->backlight.device)
+			panel->backlight.device->props.brightness =
+				panel->backlight.level;
+	}
+
+	dev_priv->display.enable_backlight(connector);
+	panel->backlight.enabled = true;
 
-	dev_priv->backlight.level = intel_panel_get_backlight(dev, 0);
-	dev_priv->backlight.enabled = dev_priv->backlight.level != 0;
+	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
 }
 
 enum drm_connector_status
@@ -762,7 +827,7 @@ intel_panel_detect(struct drm_device *dev)
 }
 
 #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
-static int intel_panel_update_status(struct backlight_device *bd)
+static int intel_backlight_device_update_status(struct backlight_device *bd)
 {
 	struct intel_connector *connector = bl_get_data(bd);
 	struct drm_device *dev = connector->base.dev;
@@ -776,85 +841,362 @@ static int intel_panel_update_status(struct backlight_device *bd)
 	return 0;
 }
 
-static int intel_panel_get_brightness(struct backlight_device *bd)
+static int intel_backlight_device_get_brightness(struct backlight_device *bd)
 {
 	struct intel_connector *connector = bl_get_data(bd);
 	struct drm_device *dev = connector->base.dev;
-	enum pipe pipe;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
 
+	intel_runtime_pm_get(dev_priv);
 	mutex_lock(&dev->mode_config.mutex);
-	pipe = intel_get_pipe_from_connector(connector);
+	ret = intel_panel_get_backlight(connector);
 	mutex_unlock(&dev->mode_config.mutex);
-	if (pipe == INVALID_PIPE)
-		return 0;
+	intel_runtime_pm_put(dev_priv);
 
-	return intel_panel_get_backlight(connector->base.dev, pipe);
+	return ret;
 }
 
-static const struct backlight_ops intel_panel_bl_ops = {
-	.update_status = intel_panel_update_status,
-	.get_brightness = intel_panel_get_brightness,
+static const struct backlight_ops intel_backlight_device_ops = {
+	.update_status = intel_backlight_device_update_status,
+	.get_brightness = intel_backlight_device_get_brightness,
 };
 
-int intel_panel_setup_backlight(struct drm_connector *connector)
+static int intel_backlight_device_register(struct intel_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
 	struct backlight_properties props;
-	unsigned long flags;
 
-	intel_panel_init_backlight(dev);
-
-	if (WARN_ON(dev_priv->backlight.device))
+	if (WARN_ON(panel->backlight.device))
 		return -ENODEV;
 
+	BUG_ON(panel->backlight.max == 0);
+
 	memset(&props, 0, sizeof(props));
 	props.type = BACKLIGHT_RAW;
-	props.brightness = dev_priv->backlight.level;
+	props.brightness = panel->backlight.level;
+	props.max_brightness = panel->backlight.max;
 
-	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
-	props.max_brightness = intel_panel_get_max_backlight(dev, 0);
-	spin_unlock_irqrestore(&dev_priv->backlight.lock, flags);
-
-	if (props.max_brightness == 0) {
-		DRM_DEBUG_DRIVER("Failed to get maximum backlight value\n");
-		return -ENODEV;
-	}
-	dev_priv->backlight.device =
+	/*
+	 * Note: using the same name independent of the connector prevents
+	 * registration of multiple backlight devices in the driver.
+	 */
+	panel->backlight.device =
 		backlight_device_register("intel_backlight",
-					  connector->kdev,
-					  to_intel_connector(connector),
-					  &intel_panel_bl_ops, &props);
+					  connector->base.kdev,
+					  connector,
+					  &intel_backlight_device_ops, &props);
 
-	if (IS_ERR(dev_priv->backlight.device)) {
+	if (IS_ERR(panel->backlight.device)) {
 		DRM_ERROR("Failed to register backlight: %ld\n",
-			  PTR_ERR(dev_priv->backlight.device));
-		dev_priv->backlight.device = NULL;
+			  PTR_ERR(panel->backlight.device));
+		panel->backlight.device = NULL;
 		return -ENODEV;
 	}
 	return 0;
 }
 
-void intel_panel_destroy_backlight(struct drm_device *dev)
+static void intel_backlight_device_unregister(struct intel_connector *connector)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	if (panel->backlight.device) {
+		backlight_device_unregister(panel->backlight.device);
+		panel->backlight.device = NULL;
+	}
+}
+#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+static int intel_backlight_device_register(struct intel_connector *connector)
+{
+	return 0;
+}
+static void intel_backlight_device_unregister(struct intel_connector *connector)
+{
+}
+#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+
+/*
+ * Note: The setup hooks can't assume pipe is set!
+ *
+ * XXX: Query mode clock or hardware clock and program PWM modulation frequency
+ * appropriately when it's 0. Use VBT and/or sane defaults.
+ */
+static int bdw_setup_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 pch_ctl1, pch_ctl2, val;
+
+	pch_ctl1 = I915_READ(BLC_PWM_PCH_CTL1);
+	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
+
+	pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2);
+	panel->backlight.max = pch_ctl2 >> 16;
+	if (!panel->backlight.max)
+		return -ENODEV;
+
+	val = bdw_get_backlight(connector);
+	panel->backlight.level = intel_panel_compute_brightness(connector, val);
+
+	panel->backlight.enabled = (pch_ctl1 & BLM_PCH_PWM_ENABLE) &&
+		panel->backlight.level != 0;
+
+	return 0;
+}
+
+static int pch_setup_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 cpu_ctl2, pch_ctl1, pch_ctl2, val;
+
+	pch_ctl1 = I915_READ(BLC_PWM_PCH_CTL1);
+	panel->backlight.active_low_pwm = pch_ctl1 & BLM_PCH_POLARITY;
+
+	pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2);
+	panel->backlight.max = pch_ctl2 >> 16;
+	if (!panel->backlight.max)
+		return -ENODEV;
+
+	val = pch_get_backlight(connector);
+	panel->backlight.level = intel_panel_compute_brightness(connector, val);
+
+	cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2);
+	panel->backlight.enabled = (cpu_ctl2 & BLM_PWM_ENABLE) &&
+		(pch_ctl1 & BLM_PCH_PWM_ENABLE) && panel->backlight.level != 0;
+
+	return 0;
+}
+
+static int i9xx_setup_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, val;
+
+	ctl = I915_READ(BLC_PWM_CTL);
+
+	if (IS_GEN2(dev))
+		panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
+
+	if (IS_PINEVIEW(dev))
+		panel->backlight.active_low_pwm = ctl & BLM_POLARITY_PNV;
+
+	panel->backlight.max = ctl >> 17;
+	if (panel->backlight.combination_mode)
+		panel->backlight.max *= 0xff;
+
+	if (!panel->backlight.max)
+		return -ENODEV;
+
+	val = i9xx_get_backlight(connector);
+	panel->backlight.level = intel_panel_compute_brightness(connector, val);
+
+	panel->backlight.enabled = panel->backlight.level != 0;
+
+	return 0;
+}
+
+static int i965_setup_backlight(struct intel_connector *connector)
+{
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_panel *panel = &connector->panel;
+	u32 ctl, ctl2, val;
+
+	ctl2 = I915_READ(BLC_PWM_CTL2);
+	panel->backlight.combination_mode = ctl2 & BLM_COMBINATION_MODE;
+	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
+
+	ctl = I915_READ(BLC_PWM_CTL);
+	panel->backlight.max = ctl >> 16;
+	if (panel->backlight.combination_mode)
+		panel->backlight.max *= 0xff;
+
+	if (!panel->backlight.max)
+		return -ENODEV;
+
+	val = i9xx_get_backlight(connector);
+	panel->backlight.level = intel_panel_compute_brightness(connector, val);
+
+	panel->backlight.enabled = (ctl2 & BLM_PWM_ENABLE) &&
+		panel->backlight.level != 0;
+
+	return 0;
+}
+
+static int vlv_setup_backlight(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	if (dev_priv->backlight.device) {
-		backlight_device_unregister(dev_priv->backlight.device);
-		dev_priv->backlight.device = NULL;
+	struct intel_panel *panel = &connector->panel;
+	enum pipe pipe;
+	u32 ctl, ctl2, val;
+
+	for_each_pipe(pipe) {
+		u32 cur_val = I915_READ(VLV_BLC_PWM_CTL(pipe));
+
+		/* Skip if the modulation freq is already set */
+		if (cur_val & ~BACKLIGHT_DUTY_CYCLE_MASK)
+			continue;
+
+		cur_val &= BACKLIGHT_DUTY_CYCLE_MASK;
+		I915_WRITE(VLV_BLC_PWM_CTL(pipe), (0xf42 << 16) |
+			   cur_val);
 	}
+
+	ctl2 = I915_READ(VLV_BLC_PWM_CTL2(PIPE_A));
+	panel->backlight.active_low_pwm = ctl2 & BLM_POLARITY_I965;
+
+	ctl = I915_READ(VLV_BLC_PWM_CTL(PIPE_A));
+	panel->backlight.max = ctl >> 16;
+	if (!panel->backlight.max)
+		return -ENODEV;
+
+	val = _vlv_get_backlight(dev, PIPE_A);
+	panel->backlight.level = intel_panel_compute_brightness(connector, val);
+
+	panel->backlight.enabled = (ctl2 & BLM_PWM_ENABLE) &&
+		panel->backlight.level != 0;
+
+	return 0;
 }
-#else
+
 int intel_panel_setup_backlight(struct drm_connector *connector)
 {
-	intel_panel_init_backlight(connector->dev);
+	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_panel *panel = &intel_connector->panel;
+	unsigned long flags;
+	int ret;
+
+	/* set level and max in panel struct */
+	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
+	ret = dev_priv->display.setup_backlight(intel_connector);
+	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
+
+	if (ret) {
+		DRM_DEBUG_KMS("failed to setup backlight for connector %s\n",
+			      drm_get_connector_name(connector));
+		return ret;
+	}
+
+	intel_backlight_device_register(intel_connector);
+
+	panel->backlight.present = true;
+
+	DRM_DEBUG_KMS("backlight initialized, %s, brightness %u/%u, "
+		      "sysfs interface %sregistered\n",
+		      panel->backlight.enabled ? "enabled" : "disabled",
+		      panel->backlight.level, panel->backlight.max,
+		      panel->backlight.device ? "" : "not ");
+
 	return 0;
 }
 
-void intel_panel_destroy_backlight(struct drm_device *dev)
+void intel_panel_destroy_backlight(struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_panel *panel = &intel_connector->panel;
+
+	panel->backlight.present = false;
+	intel_backlight_device_unregister(intel_connector);
+}
+
+/**
+ * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID
+ * @dev: drm device
+ * @fixed_mode : panel native mode
+ * @connector: LVDS/eDP connector
+ *
+ * Return downclock_avail
+ * Find the reduced downclock for LVDS/eDP in EDID.
+ */
+struct drm_display_mode *
+intel_find_panel_downclock(struct drm_device *dev,
+			struct drm_display_mode *fixed_mode,
+			struct drm_connector *connector)
+{
+	struct drm_display_mode *scan, *tmp_mode;
+	int temp_downclock;
+
+	temp_downclock = fixed_mode->clock;
+	tmp_mode = NULL;
+
+	list_for_each_entry(scan, &connector->probed_modes, head) {
+		/*
+		 * If one mode has the same resolution with the fixed_panel
+		 * mode while they have the different refresh rate, it means
+		 * that the reduced downclock is found. In such
+		 * case we can set the different FPx0/1 to dynamically select
+		 * between low and high frequency.
+		 */
+		if (scan->hdisplay == fixed_mode->hdisplay &&
+		    scan->hsync_start == fixed_mode->hsync_start &&
+		    scan->hsync_end == fixed_mode->hsync_end &&
+		    scan->htotal == fixed_mode->htotal &&
+		    scan->vdisplay == fixed_mode->vdisplay &&
+		    scan->vsync_start == fixed_mode->vsync_start &&
+		    scan->vsync_end == fixed_mode->vsync_end &&
+		    scan->vtotal == fixed_mode->vtotal) {
+			if (scan->clock < temp_downclock) {
+				/*
+				 * The downclock is already found. But we
+				 * expect to find the lower downclock.
+				 */
+				temp_downclock = scan->clock;
+				tmp_mode = scan;
+			}
+		}
+	}
+
+	if (temp_downclock < fixed_mode->clock)
+		return drm_mode_duplicate(dev, tmp_mode);
+	else
+		return NULL;
+}
+
+/* Set up chip specific backlight functions */
+void intel_panel_init_backlight_funcs(struct drm_device *dev)
 {
-	return;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_BROADWELL(dev)) {
+		dev_priv->display.setup_backlight = bdw_setup_backlight;
+		dev_priv->display.enable_backlight = bdw_enable_backlight;
+		dev_priv->display.disable_backlight = pch_disable_backlight;
+		dev_priv->display.set_backlight = bdw_set_backlight;
+		dev_priv->display.get_backlight = bdw_get_backlight;
+	} else if (HAS_PCH_SPLIT(dev)) {
+		dev_priv->display.setup_backlight = pch_setup_backlight;
+		dev_priv->display.enable_backlight = pch_enable_backlight;
+		dev_priv->display.disable_backlight = pch_disable_backlight;
+		dev_priv->display.set_backlight = pch_set_backlight;
+		dev_priv->display.get_backlight = pch_get_backlight;
+	} else if (IS_VALLEYVIEW(dev)) {
+		dev_priv->display.setup_backlight = vlv_setup_backlight;
+		dev_priv->display.enable_backlight = vlv_enable_backlight;
+		dev_priv->display.disable_backlight = vlv_disable_backlight;
+		dev_priv->display.set_backlight = vlv_set_backlight;
+		dev_priv->display.get_backlight = vlv_get_backlight;
+	} else if (IS_GEN4(dev)) {
+		dev_priv->display.setup_backlight = i965_setup_backlight;
+		dev_priv->display.enable_backlight = i965_enable_backlight;
+		dev_priv->display.disable_backlight = i965_disable_backlight;
+		dev_priv->display.set_backlight = i9xx_set_backlight;
+		dev_priv->display.get_backlight = i9xx_get_backlight;
+	} else {
+		dev_priv->display.setup_backlight = i9xx_setup_backlight;
+		dev_priv->display.enable_backlight = i9xx_enable_backlight;
+		dev_priv->display.disable_backlight = i9xx_disable_backlight;
+		dev_priv->display.set_backlight = i9xx_set_backlight;
+		dev_priv->display.get_backlight = i9xx_get_backlight;
+	}
 }
-#endif
 
 int intel_panel_init(struct intel_panel *panel,
 		     struct drm_display_mode *fixed_mode)
@@ -871,4 +1213,8 @@ void intel_panel_fini(struct intel_panel *panel)
 
 	if (panel->fixed_mode)
 		drm_mode_destroy(intel_connector->base.dev, panel->fixed_mode);
+
+	if (panel->downclock_mode)
+		drm_mode_destroy(intel_connector->base.dev,
+				panel->downclock_mode);
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 26c29c173221..d77cc81900f9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -30,7 +30,9 @@
 #include "intel_drv.h"
 #include "../../../platform/x86/intel_ips.h"
 #include <linux/module.h>
+#include <linux/vgaarb.h>
 #include <drm/i915_powerwell.h>
+#include <linux/pm_runtime.h>
 
 /**
  * RC6 is a special power stage which allows the GPU to enter an very
@@ -86,7 +88,7 @@ static void i8xx_disable_fbc(struct drm_device *dev)
 	DRM_DEBUG_KMS("disabled FBC\n");
 }
 
-static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void i8xx_enable_fbc(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -96,32 +98,40 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int cfb_pitch;
 	int plane, i;
-	u32 fbc_ctl, fbc_ctl2;
+	u32 fbc_ctl;
 
 	cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE;
 	if (fb->pitches[0] < cfb_pitch)
 		cfb_pitch = fb->pitches[0];
 
-	/* FBC_CTL wants 64B units */
-	cfb_pitch = (cfb_pitch / 64) - 1;
+	/* FBC_CTL wants 32B or 64B units */
+	if (IS_GEN2(dev))
+		cfb_pitch = (cfb_pitch / 32) - 1;
+	else
+		cfb_pitch = (cfb_pitch / 64) - 1;
 	plane = intel_crtc->plane == 0 ? FBC_CTL_PLANEA : FBC_CTL_PLANEB;
 
 	/* Clear old tags */
 	for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++)
 		I915_WRITE(FBC_TAG + (i * 4), 0);
 
-	/* Set it up... */
-	fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
-	fbc_ctl2 |= plane;
-	I915_WRITE(FBC_CONTROL2, fbc_ctl2);
-	I915_WRITE(FBC_FENCE_OFF, crtc->y);
+	if (IS_GEN4(dev)) {
+		u32 fbc_ctl2;
+
+		/* Set it up... */
+		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
+		fbc_ctl2 |= plane;
+		I915_WRITE(FBC_CONTROL2, fbc_ctl2);
+		I915_WRITE(FBC_FENCE_OFF, crtc->y);
+	}
 
 	/* enable it... */
-	fbc_ctl = FBC_CTL_EN | FBC_CTL_PERIODIC;
+	fbc_ctl = I915_READ(FBC_CONTROL);
+	fbc_ctl &= 0x3fff << FBC_CTL_INTERVAL_SHIFT;
+	fbc_ctl |= FBC_CTL_EN | FBC_CTL_PERIODIC;
 	if (IS_I945GM(dev))
 		fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
 	fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
-	fbc_ctl |= (interval & 0x2fff) << FBC_CTL_INTERVAL_SHIFT;
 	fbc_ctl |= obj->fence_reg;
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 
@@ -136,7 +146,7 @@ static bool i8xx_fbc_enabled(struct drm_device *dev)
 	return I915_READ(FBC_CONTROL) & FBC_CTL_EN;
 }
 
-static void g4x_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void g4x_enable_fbc(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -145,16 +155,12 @@ static void g4x_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int plane = intel_crtc->plane == 0 ? DPFC_CTL_PLANEA : DPFC_CTL_PLANEB;
-	unsigned long stall_watermark = 200;
 	u32 dpfc_ctl;
 
 	dpfc_ctl = plane | DPFC_SR_EN | DPFC_CTL_LIMIT_1X;
 	dpfc_ctl |= DPFC_CTL_FENCE_EN | obj->fence_reg;
 	I915_WRITE(DPFC_CHICKEN, DPFC_HT_MODIFY);
 
-	I915_WRITE(DPFC_RECOMP_CTL, DPFC_RECOMP_STALL_EN |
-		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
-		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(DPFC_FENCE_YOFF, crtc->y);
 
 	/* enable it... */
@@ -191,7 +197,11 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 	u32 blt_ecoskpd;
 
 	/* Make sure blitter notifies FBC of writes */
-	gen6_gt_force_wake_get(dev_priv);
+
+	/* Blitter is part of Media powerwell on VLV. No impact of
+	 * his param in other platforms for now */
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_MEDIA);
+
 	blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
 	blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
 		GEN6_BLITTER_LOCK_SHIFT;
@@ -202,10 +212,11 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
 			 GEN6_BLITTER_LOCK_SHIFT);
 	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
 	POSTING_READ(GEN6_BLITTER_ECOSKPD);
-	gen6_gt_force_wake_put(dev_priv);
+
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_MEDIA);
 }
 
-static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void ironlake_enable_fbc(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -214,7 +225,6 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int plane = intel_crtc->plane == 0 ? DPFC_CTL_PLANEA : DPFC_CTL_PLANEB;
-	unsigned long stall_watermark = 200;
 	u32 dpfc_ctl;
 
 	dpfc_ctl = I915_READ(ILK_DPFC_CONTROL);
@@ -222,12 +232,11 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	dpfc_ctl |= (plane | DPFC_CTL_LIMIT_1X);
 	/* Set persistent mode for front-buffer rendering, ala X. */
 	dpfc_ctl |= DPFC_CTL_PERSISTENT_MODE;
-	dpfc_ctl |= (DPFC_CTL_FENCE_EN | obj->fence_reg);
+	dpfc_ctl |= DPFC_CTL_FENCE_EN;
+	if (IS_GEN5(dev))
+		dpfc_ctl |= obj->fence_reg;
 	I915_WRITE(ILK_DPFC_CHICKEN, DPFC_HT_MODIFY);
 
-	I915_WRITE(ILK_DPFC_RECOMP_CTL, DPFC_RECOMP_STALL_EN |
-		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
-		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y);
 	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
 	/* enable it... */
@@ -265,7 +274,7 @@ static bool ironlake_fbc_enabled(struct drm_device *dev)
 	return I915_READ(ILK_DPFC_CONTROL) & DPFC_CTL_EN;
 }
 
-static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void gen7_enable_fbc(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -295,7 +304,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 
 	sandybridge_blit_fbc_update(dev);
 
-	DRM_DEBUG_KMS("enabled fbc on plane %d\n", intel_crtc->plane);
+	DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane));
 }
 
 bool intel_fbc_enabled(struct drm_device *dev)
@@ -322,8 +331,7 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 		 * the prior work.
 		 */
 		if (work->crtc->fb == work->fb) {
-			dev_priv->display.enable_fbc(work->crtc,
-						     work->interval);
+			dev_priv->display.enable_fbc(work->crtc);
 
 			dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane;
 			dev_priv->fbc.fb_id = work->crtc->fb->base.id;
@@ -360,7 +368,7 @@ static void intel_cancel_fbc_work(struct drm_i915_private *dev_priv)
 	dev_priv->fbc.fbc_work = NULL;
 }
 
-static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void intel_enable_fbc(struct drm_crtc *crtc)
 {
 	struct intel_fbc_work *work;
 	struct drm_device *dev = crtc->dev;
@@ -374,13 +382,12 @@ static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	work = kzalloc(sizeof(*work), GFP_KERNEL);
 	if (work == NULL) {
 		DRM_ERROR("Failed to allocate FBC work structure\n");
-		dev_priv->display.enable_fbc(crtc, interval);
+		dev_priv->display.enable_fbc(crtc);
 		return;
 	}
 
 	work->crtc = crtc;
 	work->fb = crtc->fb;
-	work->interval = interval;
 	INIT_DELAYED_WORK(&work->work, intel_fbc_work_fn);
 
 	dev_priv->fbc.fbc_work = work;
@@ -454,7 +461,7 @@ void intel_update_fbc(struct drm_device *dev)
 	const struct drm_display_mode *adjusted_mode;
 	unsigned int max_width, max_height;
 
-	if (!I915_HAS_FBC(dev)) {
+	if (!HAS_FBC(dev)) {
 		set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED);
 		return;
 	}
@@ -530,10 +537,10 @@ void intel_update_fbc(struct drm_device *dev)
 			DRM_DEBUG_KMS("mode too large for compression, disabling\n");
 		goto out_disable;
 	}
-	if ((IS_I915GM(dev) || IS_I945GM(dev) || IS_HASWELL(dev)) &&
-	    intel_crtc->plane != 0) {
+	if ((INTEL_INFO(dev)->gen < 4 || IS_HASWELL(dev)) &&
+	    intel_crtc->plane != PLANE_A) {
 		if (set_no_fbc_reason(dev_priv, FBC_BAD_PLANE))
-			DRM_DEBUG_KMS("plane not 0, disabling compression\n");
+			DRM_DEBUG_KMS("plane not A, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -595,7 +602,7 @@ void intel_update_fbc(struct drm_device *dev)
 		intel_disable_fbc(dev);
 	}
 
-	intel_enable_fbc(crtc, 500);
+	intel_enable_fbc(crtc);
 	dev_priv->fbc.no_fbc_reason = FBC_OK;
 	return;
 
@@ -817,7 +824,7 @@ static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
 	return size;
 }
 
-static int i85x_get_fifo_size(struct drm_device *dev, int plane)
+static int i830_get_fifo_size(struct drm_device *dev, int plane)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t dsparb = I915_READ(DSPARB);
@@ -850,21 +857,6 @@ static int i845_get_fifo_size(struct drm_device *dev, int plane)
 	return size;
 }
 
-static int i830_get_fifo_size(struct drm_device *dev, int plane)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t dsparb = I915_READ(DSPARB);
-	int size;
-
-	size = dsparb & 0x7f;
-	size >>= 1; /* Convert to cachelines */
-
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb,
-		      plane ? "B" : "A", size);
-
-	return size;
-}
-
 /* Pineview has different values for various configs */
 static const struct intel_watermark_params pineview_display_wm = {
 	PINEVIEW_DISPLAY_FIFO,
@@ -943,14 +935,14 @@ static const struct intel_watermark_params i915_wm_info = {
 	2,
 	I915_FIFO_LINE_SIZE
 };
-static const struct intel_watermark_params i855_wm_info = {
+static const struct intel_watermark_params i830_wm_info = {
 	I855GM_FIFO_SIZE,
 	I915_MAX_WM,
 	1,
 	2,
 	I830_FIFO_LINE_SIZE
 };
-static const struct intel_watermark_params i830_wm_info = {
+static const struct intel_watermark_params i845_wm_info = {
 	I830_FIFO_SIZE,
 	I915_MAX_WM,
 	1,
@@ -958,65 +950,6 @@ static const struct intel_watermark_params i830_wm_info = {
 	I830_FIFO_LINE_SIZE
 };
 
-static const struct intel_watermark_params ironlake_display_wm_info = {
-	ILK_DISPLAY_FIFO,
-	ILK_DISPLAY_MAXWM,
-	ILK_DISPLAY_DFTWM,
-	2,
-	ILK_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params ironlake_cursor_wm_info = {
-	ILK_CURSOR_FIFO,
-	ILK_CURSOR_MAXWM,
-	ILK_CURSOR_DFTWM,
-	2,
-	ILK_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params ironlake_display_srwm_info = {
-	ILK_DISPLAY_SR_FIFO,
-	ILK_DISPLAY_MAX_SRWM,
-	ILK_DISPLAY_DFT_SRWM,
-	2,
-	ILK_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params ironlake_cursor_srwm_info = {
-	ILK_CURSOR_SR_FIFO,
-	ILK_CURSOR_MAX_SRWM,
-	ILK_CURSOR_DFT_SRWM,
-	2,
-	ILK_FIFO_LINE_SIZE
-};
-
-static const struct intel_watermark_params sandybridge_display_wm_info = {
-	SNB_DISPLAY_FIFO,
-	SNB_DISPLAY_MAXWM,
-	SNB_DISPLAY_DFTWM,
-	2,
-	SNB_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params sandybridge_cursor_wm_info = {
-	SNB_CURSOR_FIFO,
-	SNB_CURSOR_MAXWM,
-	SNB_CURSOR_DFTWM,
-	2,
-	SNB_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params sandybridge_display_srwm_info = {
-	SNB_DISPLAY_SR_FIFO,
-	SNB_DISPLAY_MAX_SRWM,
-	SNB_DISPLAY_DFT_SRWM,
-	2,
-	SNB_FIFO_LINE_SIZE
-};
-static const struct intel_watermark_params sandybridge_cursor_srwm_info = {
-	SNB_CURSOR_SR_FIFO,
-	SNB_CURSOR_MAX_SRWM,
-	SNB_CURSOR_DFT_SRWM,
-	2,
-	SNB_FIFO_LINE_SIZE
-};
-
-
 /**
  * intel_calculate_wm - calculate watermark level
  * @clock_in_khz: pixel clock
@@ -1567,7 +1500,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	else if (!IS_GEN2(dev))
 		wm_info = &i915_wm_info;
 	else
-		wm_info = &i855_wm_info;
+		wm_info = &i830_wm_info;
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 0);
 	crtc = intel_get_crtc_for_plane(dev, 0);
@@ -1615,7 +1548,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	if (IS_I945G(dev) || IS_I945GM(dev))
 		I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN_MASK | 0);
 	else if (IS_I915GM(dev))
-		I915_WRITE(INSTPM, I915_READ(INSTPM) & ~INSTPM_SELF_EN);
+		I915_WRITE(INSTPM, _MASKED_BIT_DISABLE(INSTPM_SELF_EN));
 
 	/* Calc sr entries for one plane configs */
 	if (HAS_FW_BLC(dev) && enabled) {
@@ -1667,14 +1600,14 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 				I915_WRITE(FW_BLC_SELF,
 					   FW_BLC_SELF_EN_MASK | FW_BLC_SELF_EN);
 			else if (IS_I915GM(dev))
-				I915_WRITE(INSTPM, I915_READ(INSTPM) | INSTPM_SELF_EN);
+				I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_SELF_EN));
 			DRM_DEBUG_KMS("memory self refresh enabled\n");
 		} else
 			DRM_DEBUG_KMS("memory self refresh disabled\n");
 	}
 }
 
-static void i830_update_wm(struct drm_crtc *unused_crtc)
+static void i845_update_wm(struct drm_crtc *unused_crtc)
 {
 	struct drm_device *dev = unused_crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1689,7 +1622,7 @@ static void i830_update_wm(struct drm_crtc *unused_crtc)
 
 	adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
 	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
-				       &i830_wm_info,
+				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev, 0),
 				       4, latency_ns);
 	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
@@ -1700,423 +1633,6 @@ static void i830_update_wm(struct drm_crtc *unused_crtc)
 	I915_WRITE(FW_BLC, fwater_lo);
 }
 
-/*
- * Check the wm result.
- *
- * If any calculated watermark values is larger than the maximum value that
- * can be programmed into the associated watermark register, that watermark
- * must be disabled.
- */
-static bool ironlake_check_srwm(struct drm_device *dev, int level,
-				int fbc_wm, int display_wm, int cursor_wm,
-				const struct intel_watermark_params *display,
-				const struct intel_watermark_params *cursor)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	DRM_DEBUG_KMS("watermark %d: display plane %d, fbc lines %d,"
-		      " cursor %d\n", level, display_wm, fbc_wm, cursor_wm);
-
-	if (fbc_wm > SNB_FBC_MAX_SRWM) {
-		DRM_DEBUG_KMS("fbc watermark(%d) is too large(%d), disabling wm%d+\n",
-			      fbc_wm, SNB_FBC_MAX_SRWM, level);
-
-		/* fbc has it's own way to disable FBC WM */
-		I915_WRITE(DISP_ARB_CTL,
-			   I915_READ(DISP_ARB_CTL) | DISP_FBC_WM_DIS);
-		return false;
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		/* enable FBC WM (except on ILK, where it must remain off) */
-		I915_WRITE(DISP_ARB_CTL,
-			   I915_READ(DISP_ARB_CTL) & ~DISP_FBC_WM_DIS);
-	}
-
-	if (display_wm > display->max_wm) {
-		DRM_DEBUG_KMS("display watermark(%d) is too large(%d), disabling wm%d+\n",
-			      display_wm, SNB_DISPLAY_MAX_SRWM, level);
-		return false;
-	}
-
-	if (cursor_wm > cursor->max_wm) {
-		DRM_DEBUG_KMS("cursor watermark(%d) is too large(%d), disabling wm%d+\n",
-			      cursor_wm, SNB_CURSOR_MAX_SRWM, level);
-		return false;
-	}
-
-	if (!(fbc_wm || display_wm || cursor_wm)) {
-		DRM_DEBUG_KMS("latency %d is 0, disabling wm%d+\n", level, level);
-		return false;
-	}
-
-	return true;
-}
-
-/*
- * Compute watermark values of WM[1-3],
- */
-static bool ironlake_compute_srwm(struct drm_device *dev, int level, int plane,
-				  int latency_ns,
-				  const struct intel_watermark_params *display,
-				  const struct intel_watermark_params *cursor,
-				  int *fbc_wm, int *display_wm, int *cursor_wm)
-{
-	struct drm_crtc *crtc;
-	const struct drm_display_mode *adjusted_mode;
-	unsigned long line_time_us;
-	int hdisplay, htotal, pixel_size, clock;
-	int line_count, line_size;
-	int small, large;
-	int entries;
-
-	if (!latency_ns) {
-		*fbc_wm = *display_wm = *cursor_wm = 0;
-		return false;
-	}
-
-	crtc = intel_get_crtc_for_plane(dev, plane);
-	adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
-	clock = adjusted_mode->crtc_clock;
-	htotal = adjusted_mode->crtc_htotal;
-	hdisplay = to_intel_crtc(crtc)->config.pipe_src_w;
-	pixel_size = crtc->fb->bits_per_pixel / 8;
-
-	line_time_us = (htotal * 1000) / clock;
-	line_count = (latency_ns / line_time_us + 1000) / 1000;
-	line_size = hdisplay * pixel_size;
-
-	/* Use the minimum of the small and large buffer method for primary */
-	small = ((clock * pixel_size / 1000) * latency_ns) / 1000;
-	large = line_count * line_size;
-
-	entries = DIV_ROUND_UP(min(small, large), display->cacheline_size);
-	*display_wm = entries + display->guard_size;
-
-	/*
-	 * Spec says:
-	 * FBC WM = ((Final Primary WM * 64) / number of bytes per line) + 2
-	 */
-	*fbc_wm = DIV_ROUND_UP(*display_wm * 64, line_size) + 2;
-
-	/* calculate the self-refresh watermark for display cursor */
-	entries = line_count * pixel_size * 64;
-	entries = DIV_ROUND_UP(entries, cursor->cacheline_size);
-	*cursor_wm = entries + cursor->guard_size;
-
-	return ironlake_check_srwm(dev, level,
-				   *fbc_wm, *display_wm, *cursor_wm,
-				   display, cursor);
-}
-
-static void ironlake_update_wm(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int fbc_wm, plane_wm, cursor_wm;
-	unsigned int enabled;
-
-	enabled = 0;
-	if (g4x_compute_wm0(dev, PIPE_A,
-			    &ironlake_display_wm_info,
-			    dev_priv->wm.pri_latency[0] * 100,
-			    &ironlake_cursor_wm_info,
-			    dev_priv->wm.cur_latency[0] * 100,
-			    &plane_wm, &cursor_wm)) {
-		I915_WRITE(WM0_PIPEA_ILK,
-			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
-		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
-			      " plane %d, " "cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_A;
-	}
-
-	if (g4x_compute_wm0(dev, PIPE_B,
-			    &ironlake_display_wm_info,
-			    dev_priv->wm.pri_latency[0] * 100,
-			    &ironlake_cursor_wm_info,
-			    dev_priv->wm.cur_latency[0] * 100,
-			    &plane_wm, &cursor_wm)) {
-		I915_WRITE(WM0_PIPEB_ILK,
-			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
-		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
-			      " plane %d, cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_B;
-	}
-
-	/*
-	 * Calculate and update the self-refresh watermark only when one
-	 * display plane is used.
-	 */
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
-
-	if (!single_plane_enabled(enabled))
-		return;
-	enabled = ffs(enabled) - 1;
-
-	/* WM1 */
-	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   dev_priv->wm.pri_latency[1] * 500,
-				   &ironlake_display_srwm_info,
-				   &ironlake_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM1_LP_ILK,
-		   WM1_LP_SR_EN |
-		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/* WM2 */
-	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   dev_priv->wm.pri_latency[2] * 500,
-				   &ironlake_display_srwm_info,
-				   &ironlake_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM2_LP_ILK,
-		   WM2_LP_EN |
-		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/*
-	 * WM3 is unsupported on ILK, probably because we don't have latency
-	 * data for that power state
-	 */
-}
-
-static void sandybridge_update_wm(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
-	u32 val;
-	int fbc_wm, plane_wm, cursor_wm;
-	unsigned int enabled;
-
-	enabled = 0;
-	if (g4x_compute_wm0(dev, PIPE_A,
-			    &sandybridge_display_wm_info, latency,
-			    &sandybridge_cursor_wm_info, latency,
-			    &plane_wm, &cursor_wm)) {
-		val = I915_READ(WM0_PIPEA_ILK);
-		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
-		I915_WRITE(WM0_PIPEA_ILK, val |
-			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
-		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
-			      " plane %d, " "cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_A;
-	}
-
-	if (g4x_compute_wm0(dev, PIPE_B,
-			    &sandybridge_display_wm_info, latency,
-			    &sandybridge_cursor_wm_info, latency,
-			    &plane_wm, &cursor_wm)) {
-		val = I915_READ(WM0_PIPEB_ILK);
-		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
-		I915_WRITE(WM0_PIPEB_ILK, val |
-			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
-		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
-			      " plane %d, cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_B;
-	}
-
-	/*
-	 * Calculate and update the self-refresh watermark only when one
-	 * display plane is used.
-	 *
-	 * SNB support 3 levels of watermark.
-	 *
-	 * WM1/WM2/WM2 watermarks have to be enabled in the ascending order,
-	 * and disabled in the descending order
-	 *
-	 */
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
-
-	if (!single_plane_enabled(enabled) ||
-	    dev_priv->sprite_scaling_enabled)
-		return;
-	enabled = ffs(enabled) - 1;
-
-	/* WM1 */
-	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   dev_priv->wm.pri_latency[1] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM1_LP_ILK,
-		   WM1_LP_SR_EN |
-		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/* WM2 */
-	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   dev_priv->wm.pri_latency[2] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM2_LP_ILK,
-		   WM2_LP_EN |
-		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/* WM3 */
-	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   dev_priv->wm.pri_latency[3] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM3_LP_ILK,
-		   WM3_LP_EN |
-		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-}
-
-static void ivybridge_update_wm(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
-	u32 val;
-	int fbc_wm, plane_wm, cursor_wm;
-	int ignore_fbc_wm, ignore_plane_wm, ignore_cursor_wm;
-	unsigned int enabled;
-
-	enabled = 0;
-	if (g4x_compute_wm0(dev, PIPE_A,
-			    &sandybridge_display_wm_info, latency,
-			    &sandybridge_cursor_wm_info, latency,
-			    &plane_wm, &cursor_wm)) {
-		val = I915_READ(WM0_PIPEA_ILK);
-		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
-		I915_WRITE(WM0_PIPEA_ILK, val |
-			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
-		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
-			      " plane %d, " "cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_A;
-	}
-
-	if (g4x_compute_wm0(dev, PIPE_B,
-			    &sandybridge_display_wm_info, latency,
-			    &sandybridge_cursor_wm_info, latency,
-			    &plane_wm, &cursor_wm)) {
-		val = I915_READ(WM0_PIPEB_ILK);
-		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
-		I915_WRITE(WM0_PIPEB_ILK, val |
-			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
-		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
-			      " plane %d, cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_B;
-	}
-
-	if (g4x_compute_wm0(dev, PIPE_C,
-			    &sandybridge_display_wm_info, latency,
-			    &sandybridge_cursor_wm_info, latency,
-			    &plane_wm, &cursor_wm)) {
-		val = I915_READ(WM0_PIPEC_IVB);
-		val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK);
-		I915_WRITE(WM0_PIPEC_IVB, val |
-			   ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm));
-		DRM_DEBUG_KMS("FIFO watermarks For pipe C -"
-			      " plane %d, cursor: %d\n",
-			      plane_wm, cursor_wm);
-		enabled |= 1 << PIPE_C;
-	}
-
-	/*
-	 * Calculate and update the self-refresh watermark only when one
-	 * display plane is used.
-	 *
-	 * SNB support 3 levels of watermark.
-	 *
-	 * WM1/WM2/WM2 watermarks have to be enabled in the ascending order,
-	 * and disabled in the descending order
-	 *
-	 */
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
-
-	if (!single_plane_enabled(enabled) ||
-	    dev_priv->sprite_scaling_enabled)
-		return;
-	enabled = ffs(enabled) - 1;
-
-	/* WM1 */
-	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   dev_priv->wm.pri_latency[1] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM1_LP_ILK,
-		   WM1_LP_SR_EN |
-		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/* WM2 */
-	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   dev_priv->wm.pri_latency[2] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM2_LP_ILK,
-		   WM2_LP_EN |
-		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-
-	/* WM3, note we have to correct the cursor latency */
-	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   dev_priv->wm.pri_latency[3] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &fbc_wm, &plane_wm, &ignore_cursor_wm) ||
-	    !ironlake_compute_srwm(dev, 3, enabled,
-				   dev_priv->wm.cur_latency[3] * 500,
-				   &sandybridge_display_srwm_info,
-				   &sandybridge_cursor_srwm_info,
-				   &ignore_fbc_wm, &ignore_plane_wm, &cursor_wm))
-		return;
-
-	I915_WRITE(WM3_LP_ILK,
-		   WM3_LP_EN |
-		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
-		   (fbc_wm << WM1_LP_FBC_SHIFT) |
-		   (plane_wm << WM1_LP_SR_SHIFT) |
-		   cursor_wm);
-}
-
 static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev,
 				    struct drm_crtc *crtc)
 {
@@ -2185,7 +1701,7 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
 }
 
-struct hsw_pipe_wm_parameters {
+struct ilk_pipe_wm_parameters {
 	bool active;
 	uint32_t pipe_htotal;
 	uint32_t pixel_rate;
@@ -2194,7 +1710,7 @@ struct hsw_pipe_wm_parameters {
 	struct intel_plane_wm_parameters cur;
 };
 
-struct hsw_wm_maximums {
+struct ilk_wm_maximums {
 	uint16_t pri;
 	uint16_t spr;
 	uint16_t cur;
@@ -2212,7 +1728,7 @@ struct intel_wm_config {
  * For both WM_PIPE and WM_LP.
  * mem_value must be in 0.1us units.
  */
-static uint32_t ilk_compute_pri_wm(const struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_pri_wm(const struct ilk_pipe_wm_parameters *params,
 				   uint32_t mem_value,
 				   bool is_lp)
 {
@@ -2241,7 +1757,7 @@ static uint32_t ilk_compute_pri_wm(const struct hsw_pipe_wm_parameters *params,
  * For both WM_PIPE and WM_LP.
  * mem_value must be in 0.1us units.
  */
-static uint32_t ilk_compute_spr_wm(const struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_spr_wm(const struct ilk_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
 	uint32_t method1, method2;
@@ -2264,7 +1780,7 @@ static uint32_t ilk_compute_spr_wm(const struct hsw_pipe_wm_parameters *params,
  * For both WM_PIPE and WM_LP.
  * mem_value must be in 0.1us units.
  */
-static uint32_t ilk_compute_cur_wm(const struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_cur_wm(const struct ilk_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
 	if (!params->active || !params->cur.enabled)
@@ -2278,7 +1794,7 @@ static uint32_t ilk_compute_cur_wm(const struct hsw_pipe_wm_parameters *params,
 }
 
 /* Only for WM_LP. */
-static uint32_t ilk_compute_fbc_wm(const struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_fbc_wm(const struct ilk_pipe_wm_parameters *params,
 				   uint32_t pri_val)
 {
 	if (!params->active || !params->pri.enabled)
@@ -2383,7 +1899,7 @@ static void ilk_compute_wm_maximums(struct drm_device *dev,
 				    int level,
 				    const struct intel_wm_config *config,
 				    enum intel_ddb_partitioning ddb_partitioning,
-				    struct hsw_wm_maximums *max)
+				    struct ilk_wm_maximums *max)
 {
 	max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
 	max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
@@ -2392,7 +1908,7 @@ static void ilk_compute_wm_maximums(struct drm_device *dev,
 }
 
 static bool ilk_validate_wm_level(int level,
-				  const struct hsw_wm_maximums *max,
+				  const struct ilk_wm_maximums *max,
 				  struct intel_wm_level *result)
 {
 	bool ret;
@@ -2434,7 +1950,7 @@ static bool ilk_validate_wm_level(int level,
 
 static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
 				 int level,
-				 const struct hsw_pipe_wm_parameters *p,
+				 const struct ilk_pipe_wm_parameters *p,
 				 struct intel_wm_level *result)
 {
 	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
@@ -2482,7 +1998,7 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (IS_HASWELL(dev)) {
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		uint64_t sskpd = I915_READ64(MCH_SSKPD);
 
 		wm[0] = (sskpd >> 56) & 0xFF;
@@ -2530,7 +2046,7 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
 static int ilk_wm_max_level(const struct drm_device *dev)
 {
 	/* how many WM levels are we expecting */
-	if (IS_HASWELL(dev))
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		return 4;
 	else if (INTEL_INFO(dev)->gen >= 6)
 		return 3;
@@ -2582,8 +2098,8 @@ static void intel_setup_wm_latency(struct drm_device *dev)
 	intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency);
 }
 
-static void hsw_compute_wm_parameters(struct drm_crtc *crtc,
-				      struct hsw_pipe_wm_parameters *p,
+static void ilk_compute_wm_parameters(struct drm_crtc *crtc,
+				      struct ilk_pipe_wm_parameters *p,
 				      struct intel_wm_config *config)
 {
 	struct drm_device *dev = crtc->dev;
@@ -2593,7 +2109,7 @@ static void hsw_compute_wm_parameters(struct drm_crtc *crtc,
 
 	p->active = intel_crtc_active(crtc);
 	if (p->active) {
-		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
+		p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal;
 		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
 		p->pri.bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
 		p->cur.bytes_per_pixel = 4;
@@ -2620,7 +2136,7 @@ static void hsw_compute_wm_parameters(struct drm_crtc *crtc,
 
 /* Compute new watermarks for the pipe */
 static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
-				  const struct hsw_pipe_wm_parameters *params,
+				  const struct ilk_pipe_wm_parameters *params,
 				  struct intel_pipe_wm *pipe_wm)
 {
 	struct drm_device *dev = crtc->dev;
@@ -2632,16 +2148,25 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
 		.sprites_enabled = params->spr.enabled,
 		.sprites_scaled = params->spr.scaled,
 	};
-	struct hsw_wm_maximums max;
+	struct ilk_wm_maximums max;
 
 	/* LP0 watermarks always use 1/2 DDB partitioning */
 	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
 
+	/* ILK/SNB: LP2+ watermarks only w/o sprites */
+	if (INTEL_INFO(dev)->gen <= 6 && params->spr.enabled)
+		max_level = 1;
+
+	/* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */
+	if (params->spr.scaled)
+		max_level = 0;
+
 	for (level = 0; level <= max_level; level++)
 		ilk_compute_wm_level(dev_priv, level, params,
 				     &pipe_wm->wm[level]);
 
-	pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc);
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc);
 
 	/* At least LP0 must be valid */
 	return ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]);
@@ -2676,12 +2201,19 @@ static void ilk_merge_wm_level(struct drm_device *dev,
  * Merge all low power watermarks for all active pipes.
  */
 static void ilk_wm_merge(struct drm_device *dev,
-			 const struct hsw_wm_maximums *max,
+			 const struct intel_wm_config *config,
+			 const struct ilk_wm_maximums *max,
 			 struct intel_pipe_wm *merged)
 {
 	int level, max_level = ilk_wm_max_level(dev);
 
-	merged->fbc_wm_enabled = true;
+	/* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */
+	if ((INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev)) &&
+	    config->num_pipes_active > 1)
+		return;
+
+	/* ILK: FBC WM must be disabled always */
+	merged->fbc_wm_enabled = INTEL_INFO(dev)->gen >= 6;
 
 	/* merge each WM1+ level */
 	for (level = 1; level <= max_level; level++) {
@@ -2701,6 +2233,20 @@ static void ilk_wm_merge(struct drm_device *dev,
 			wm->fbc_val = 0;
 		}
 	}
+
+	/* ILK: LP2+ must be disabled when FBC WM is disabled but FBC enabled */
+	/*
+	 * FIXME this is racy. FBC might get enabled later.
+	 * What we should check here is whether FBC can be
+	 * enabled sometime later.
+	 */
+	if (IS_GEN5(dev) && !merged->fbc_wm_enabled && intel_fbc_enabled(dev)) {
+		for (level = 2; level <= max_level; level++) {
+			struct intel_wm_level *wm = &merged->wm[level];
+
+			wm->enable = false;
+		}
+	}
 }
 
 static int ilk_wm_lp_to_level(int wm_lp, const struct intel_pipe_wm *pipe_wm)
@@ -2709,10 +2255,21 @@ static int ilk_wm_lp_to_level(int wm_lp, const struct intel_pipe_wm *pipe_wm)
 	return wm_lp + (wm_lp >= 2 && pipe_wm->wm[4].enable);
 }
 
-static void hsw_compute_wm_results(struct drm_device *dev,
+/* The value we need to program into the WM_LPx latency field */
+static unsigned int ilk_wm_lp_latency(struct drm_device *dev, int level)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		return 2 * level;
+	else
+		return dev_priv->wm.pri_latency[level];
+}
+
+static void ilk_compute_wm_results(struct drm_device *dev,
 				   const struct intel_pipe_wm *merged,
 				   enum intel_ddb_partitioning partitioning,
-				   struct hsw_wm_values *results)
+				   struct ilk_wm_values *results)
 {
 	struct intel_crtc *intel_crtc;
 	int level, wm_lp;
@@ -2731,7 +2288,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 			break;
 
 		results->wm_lp[wm_lp - 1] = WM3_LP_EN |
-			((level * 2) << WM1_LP_LATENCY_SHIFT) |
+			(ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) |
 			(r->pri_val << WM1_LP_SR_SHIFT) |
 			r->cur_val;
 
@@ -2742,7 +2299,11 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 			results->wm_lp[wm_lp - 1] |=
 				r->fbc_val << WM1_LP_FBC_SHIFT;
 
-		results->wm_lp_spr[wm_lp - 1] = r->spr_val;
+		if (INTEL_INFO(dev)->gen <= 6 && r->spr_val) {
+			WARN_ON(wm_lp != 1);
+			results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val;
+		} else
+			results->wm_lp_spr[wm_lp - 1] = r->spr_val;
 	}
 
 	/* LP0 register values */
@@ -2765,7 +2326,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 
 /* Find the result with the highest level enabled. Check for enable_fbc_wm in
  * case both are at the same level. Prefer r1 in case they're the same. */
-static struct intel_pipe_wm *hsw_find_best_result(struct drm_device *dev,
+static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev,
 						  struct intel_pipe_wm *r1,
 						  struct intel_pipe_wm *r2)
 {
@@ -2800,8 +2361,8 @@ static struct intel_pipe_wm *hsw_find_best_result(struct drm_device *dev,
 #define WM_DIRTY_DDB (1 << 25)
 
 static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
-					 const struct hsw_wm_values *old,
-					 const struct hsw_wm_values *new)
+					 const struct ilk_wm_values *old,
+					 const struct ilk_wm_values *new)
 {
 	unsigned int dirty = 0;
 	enum pipe pipe;
@@ -2851,27 +2412,53 @@ static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
 	return dirty;
 }
 
+static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv,
+			       unsigned int dirty)
+{
+	struct ilk_wm_values *previous = &dev_priv->wm.hw;
+	bool changed = false;
+
+	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] & WM1_LP_SR_EN) {
+		previous->wm_lp[2] &= ~WM1_LP_SR_EN;
+		I915_WRITE(WM3_LP_ILK, previous->wm_lp[2]);
+		changed = true;
+	}
+	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] & WM1_LP_SR_EN) {
+		previous->wm_lp[1] &= ~WM1_LP_SR_EN;
+		I915_WRITE(WM2_LP_ILK, previous->wm_lp[1]);
+		changed = true;
+	}
+	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] & WM1_LP_SR_EN) {
+		previous->wm_lp[0] &= ~WM1_LP_SR_EN;
+		I915_WRITE(WM1_LP_ILK, previous->wm_lp[0]);
+		changed = true;
+	}
+
+	/*
+	 * Don't touch WM1S_LP_EN here.
+	 * Doing so could cause underruns.
+	 */
+
+	return changed;
+}
+
 /*
  * The spec says we shouldn't write when we don't need, because every write
  * causes WMs to be re-evaluated, expending some power.
  */
-static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
-				struct hsw_wm_values *results)
+static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
+				struct ilk_wm_values *results)
 {
-	struct hsw_wm_values *previous = &dev_priv->wm.hw;
+	struct drm_device *dev = dev_priv->dev;
+	struct ilk_wm_values *previous = &dev_priv->wm.hw;
 	unsigned int dirty;
 	uint32_t val;
 
-	dirty = ilk_compute_wm_dirty(dev_priv->dev, previous, results);
+	dirty = ilk_compute_wm_dirty(dev, previous, results);
 	if (!dirty)
 		return;
 
-	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] != 0)
-		I915_WRITE(WM3_LP_ILK, 0);
-	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] != 0)
-		I915_WRITE(WM2_LP_ILK, 0);
-	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] != 0)
-		I915_WRITE(WM1_LP_ILK, 0);
+	_ilk_disable_lp_wm(dev_priv, dirty);
 
 	if (dirty & WM_DIRTY_PIPE(PIPE_A))
 		I915_WRITE(WM0_PIPEA_ILK, results->wm_pipe[0]);
@@ -2888,12 +2475,21 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 		I915_WRITE(PIPE_WM_LINETIME(PIPE_C), results->wm_linetime[2]);
 
 	if (dirty & WM_DIRTY_DDB) {
-		val = I915_READ(WM_MISC);
-		if (results->partitioning == INTEL_DDB_PART_1_2)
-			val &= ~WM_MISC_DATA_PARTITION_5_6;
-		else
-			val |= WM_MISC_DATA_PARTITION_5_6;
-		I915_WRITE(WM_MISC, val);
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+			val = I915_READ(WM_MISC);
+			if (results->partitioning == INTEL_DDB_PART_1_2)
+				val &= ~WM_MISC_DATA_PARTITION_5_6;
+			else
+				val |= WM_MISC_DATA_PARTITION_5_6;
+			I915_WRITE(WM_MISC, val);
+		} else {
+			val = I915_READ(DISP_ARB_CTL2);
+			if (results->partitioning == INTEL_DDB_PART_1_2)
+				val &= ~DISP_DATA_PARTITION_5_6;
+			else
+				val |= DISP_DATA_PARTITION_5_6;
+			I915_WRITE(DISP_ARB_CTL2, val);
+		}
 	}
 
 	if (dirty & WM_DIRTY_FBC) {
@@ -2905,37 +2501,48 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 		I915_WRITE(DISP_ARB_CTL, val);
 	}
 
-	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp_spr[0] != results->wm_lp_spr[0])
+	if (dirty & WM_DIRTY_LP(1) &&
+	    previous->wm_lp_spr[0] != results->wm_lp_spr[0])
 		I915_WRITE(WM1S_LP_ILK, results->wm_lp_spr[0]);
-	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp_spr[1] != results->wm_lp_spr[1])
-		I915_WRITE(WM2S_LP_IVB, results->wm_lp_spr[1]);
-	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp_spr[2] != results->wm_lp_spr[2])
-		I915_WRITE(WM3S_LP_IVB, results->wm_lp_spr[2]);
 
-	if (dirty & WM_DIRTY_LP(1) && results->wm_lp[0] != 0)
+	if (INTEL_INFO(dev)->gen >= 7) {
+		if (dirty & WM_DIRTY_LP(2) && previous->wm_lp_spr[1] != results->wm_lp_spr[1])
+			I915_WRITE(WM2S_LP_IVB, results->wm_lp_spr[1]);
+		if (dirty & WM_DIRTY_LP(3) && previous->wm_lp_spr[2] != results->wm_lp_spr[2])
+			I915_WRITE(WM3S_LP_IVB, results->wm_lp_spr[2]);
+	}
+
+	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] != results->wm_lp[0])
 		I915_WRITE(WM1_LP_ILK, results->wm_lp[0]);
-	if (dirty & WM_DIRTY_LP(2) && results->wm_lp[1] != 0)
+	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] != results->wm_lp[1])
 		I915_WRITE(WM2_LP_ILK, results->wm_lp[1]);
-	if (dirty & WM_DIRTY_LP(3) && results->wm_lp[2] != 0)
+	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] != results->wm_lp[2])
 		I915_WRITE(WM3_LP_ILK, results->wm_lp[2]);
 
 	dev_priv->wm.hw = *results;
 }
 
-static void haswell_update_wm(struct drm_crtc *crtc)
+static bool ilk_disable_lp_wm(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
+}
+
+static void ilk_update_wm(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct hsw_wm_maximums max;
-	struct hsw_pipe_wm_parameters params = {};
-	struct hsw_wm_values results = {};
+	struct ilk_wm_maximums max;
+	struct ilk_pipe_wm_parameters params = {};
+	struct ilk_wm_values results = {};
 	enum intel_ddb_partitioning partitioning;
 	struct intel_pipe_wm pipe_wm = {};
 	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
 	struct intel_wm_config config = {};
 
-	hsw_compute_wm_parameters(crtc, &params, &config);
+	ilk_compute_wm_parameters(crtc, &params, &config);
 
 	intel_compute_pipe_wm(crtc, &params, &pipe_wm);
 
@@ -2945,15 +2552,15 @@ static void haswell_update_wm(struct drm_crtc *crtc)
 	intel_crtc->wm.active = pipe_wm;
 
 	ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max);
-	ilk_wm_merge(dev, &max, &lp_wm_1_2);
+	ilk_wm_merge(dev, &config, &max, &lp_wm_1_2);
 
 	/* 5/6 split only in single pipe config on IVB+ */
 	if (INTEL_INFO(dev)->gen >= 7 &&
 	    config.num_pipes_active == 1 && config.sprites_enabled) {
 		ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max);
-		ilk_wm_merge(dev, &max, &lp_wm_5_6);
+		ilk_wm_merge(dev, &config, &max, &lp_wm_5_6);
 
-		best_lp_wm = hsw_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6);
+		best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6);
 	} else {
 		best_lp_wm = &lp_wm_1_2;
 	}
@@ -2961,16 +2568,17 @@ static void haswell_update_wm(struct drm_crtc *crtc)
 	partitioning = (best_lp_wm == &lp_wm_1_2) ?
 		       INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6;
 
-	hsw_compute_wm_results(dev, best_lp_wm, partitioning, &results);
+	ilk_compute_wm_results(dev, best_lp_wm, partitioning, &results);
 
-	hsw_write_wm_values(dev_priv, &results);
+	ilk_write_wm_values(dev_priv, &results);
 }
 
-static void haswell_update_sprite_wm(struct drm_plane *plane,
+static void ilk_update_sprite_wm(struct drm_plane *plane,
 				     struct drm_crtc *crtc,
 				     uint32_t sprite_width, int pixel_size,
 				     bool enabled, bool scaled)
 {
+	struct drm_device *dev = plane->dev;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 
 	intel_plane->wm.enabled = enabled;
@@ -2978,176 +2586,24 @@ static void haswell_update_sprite_wm(struct drm_plane *plane,
 	intel_plane->wm.horiz_pixels = sprite_width;
 	intel_plane->wm.bytes_per_pixel = pixel_size;
 
-	haswell_update_wm(crtc);
-}
-
-static bool
-sandybridge_compute_sprite_wm(struct drm_device *dev, int plane,
-			      uint32_t sprite_width, int pixel_size,
-			      const struct intel_watermark_params *display,
-			      int display_latency_ns, int *sprite_wm)
-{
-	struct drm_crtc *crtc;
-	int clock;
-	int entries, tlb_miss;
-
-	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (!intel_crtc_active(crtc)) {
-		*sprite_wm = display->guard_size;
-		return false;
-	}
-
-	clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
-
-	/* Use the small buffer method to calculate the sprite watermark */
-	entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000;
-	tlb_miss = display->fifo_size*display->cacheline_size -
-		sprite_width * 8;
-	if (tlb_miss > 0)
-		entries += tlb_miss;
-	entries = DIV_ROUND_UP(entries, display->cacheline_size);
-	*sprite_wm = entries + display->guard_size;
-	if (*sprite_wm > (int)display->max_wm)
-		*sprite_wm = display->max_wm;
-
-	return true;
-}
-
-static bool
-sandybridge_compute_sprite_srwm(struct drm_device *dev, int plane,
-				uint32_t sprite_width, int pixel_size,
-				const struct intel_watermark_params *display,
-				int latency_ns, int *sprite_wm)
-{
-	struct drm_crtc *crtc;
-	unsigned long line_time_us;
-	int clock;
-	int line_count, line_size;
-	int small, large;
-	int entries;
-
-	if (!latency_ns) {
-		*sprite_wm = 0;
-		return false;
-	}
-
-	crtc = intel_get_crtc_for_plane(dev, plane);
-	clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
-	if (!clock) {
-		*sprite_wm = 0;
-		return false;
-	}
-
-	line_time_us = (sprite_width * 1000) / clock;
-	if (!line_time_us) {
-		*sprite_wm = 0;
-		return false;
-	}
-
-	line_count = (latency_ns / line_time_us + 1000) / 1000;
-	line_size = sprite_width * pixel_size;
-
-	/* Use the minimum of the small and large buffer method for primary */
-	small = ((clock * pixel_size / 1000) * latency_ns) / 1000;
-	large = line_count * line_size;
-
-	entries = DIV_ROUND_UP(min(small, large), display->cacheline_size);
-	*sprite_wm = entries + display->guard_size;
-
-	return *sprite_wm > 0x3ff ? false : true;
-}
-
-static void sandybridge_update_sprite_wm(struct drm_plane *plane,
-					 struct drm_crtc *crtc,
-					 uint32_t sprite_width, int pixel_size,
-					 bool enabled, bool scaled)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe = to_intel_plane(plane)->pipe;
-	int latency = dev_priv->wm.spr_latency[0] * 100;	/* In unit 0.1us */
-	u32 val;
-	int sprite_wm, reg;
-	int ret;
-
-	if (!enabled)
-		return;
-
-	switch (pipe) {
-	case 0:
-		reg = WM0_PIPEA_ILK;
-		break;
-	case 1:
-		reg = WM0_PIPEB_ILK;
-		break;
-	case 2:
-		reg = WM0_PIPEC_IVB;
-		break;
-	default:
-		return; /* bad pipe */
-	}
-
-	ret = sandybridge_compute_sprite_wm(dev, pipe, sprite_width, pixel_size,
-					    &sandybridge_display_wm_info,
-					    latency, &sprite_wm);
-	if (!ret) {
-		DRM_DEBUG_KMS("failed to compute sprite wm for pipe %c\n",
-			      pipe_name(pipe));
-		return;
-	}
-
-	val = I915_READ(reg);
-	val &= ~WM0_PIPE_SPRITE_MASK;
-	I915_WRITE(reg, val | (sprite_wm << WM0_PIPE_SPRITE_SHIFT));
-	DRM_DEBUG_KMS("sprite watermarks For pipe %c - %d\n", pipe_name(pipe), sprite_wm);
-
-
-	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
-					      pixel_size,
-					      &sandybridge_display_srwm_info,
-					      dev_priv->wm.spr_latency[1] * 500,
-					      &sprite_wm);
-	if (!ret) {
-		DRM_DEBUG_KMS("failed to compute sprite lp1 wm on pipe %c\n",
-			      pipe_name(pipe));
-		return;
-	}
-	I915_WRITE(WM1S_LP_ILK, sprite_wm);
-
-	/* Only IVB has two more LP watermarks for sprite */
-	if (!IS_IVYBRIDGE(dev))
-		return;
-
-	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
-					      pixel_size,
-					      &sandybridge_display_srwm_info,
-					      dev_priv->wm.spr_latency[2] * 500,
-					      &sprite_wm);
-	if (!ret) {
-		DRM_DEBUG_KMS("failed to compute sprite lp2 wm on pipe %c\n",
-			      pipe_name(pipe));
-		return;
-	}
-	I915_WRITE(WM2S_LP_IVB, sprite_wm);
+	/*
+	 * IVB workaround: must disable low power watermarks for at least
+	 * one frame before enabling scaling.  LP watermarks can be re-enabled
+	 * when scaling is disabled.
+	 *
+	 * WaCxSRDisabledForSpriteScaling:ivb
+	 */
+	if (IS_IVYBRIDGE(dev) && scaled && ilk_disable_lp_wm(dev))
+		intel_wait_for_vblank(dev, intel_plane->pipe);
 
-	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
-					      pixel_size,
-					      &sandybridge_display_srwm_info,
-					      dev_priv->wm.spr_latency[3] * 500,
-					      &sprite_wm);
-	if (!ret) {
-		DRM_DEBUG_KMS("failed to compute sprite lp3 wm on pipe %c\n",
-			      pipe_name(pipe));
-		return;
-	}
-	I915_WRITE(WM3S_LP_IVB, sprite_wm);
+	ilk_update_wm(crtc);
 }
 
 static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct hsw_wm_values *hw = &dev_priv->wm.hw;
+	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_pipe_wm *active = &intel_crtc->wm.active;
 	enum pipe pipe = intel_crtc->pipe;
@@ -3158,7 +2614,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 	};
 
 	hw->wm_pipe[pipe] = I915_READ(wm0_pipe_reg[pipe]);
-	hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
 
 	if (intel_crtc_active(crtc)) {
 		u32 tmp = hw->wm_pipe[pipe];
@@ -3190,7 +2647,7 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 void ilk_wm_get_hw_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct hsw_wm_values *hw = &dev_priv->wm.hw;
+	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct drm_crtc *crtc;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
@@ -3204,8 +2661,12 @@ void ilk_wm_get_hw_state(struct drm_device *dev)
 	hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB);
 	hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB);
 
-	hw->partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
-		INTEL_DDB_PART_5_6 : INTEL_DDB_PART_1_2;
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		hw->partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
+			INTEL_DDB_PART_5_6 : INTEL_DDB_PART_1_2;
+	else if (IS_IVYBRIDGE(dev))
+		hw->partitioning = (I915_READ(DISP_ARB_CTL2) & DISP_DATA_PARTITION_5_6) ?
+			INTEL_DDB_PART_5_6 : INTEL_DDB_PART_1_2;
 
 	hw->enable_fbc_wm =
 		!(I915_READ(DISP_ARB_CTL) & DISP_FBC_WM_DIS);
@@ -3430,26 +2891,19 @@ static void ironlake_disable_drps(struct drm_device *dev)
  * ourselves, instead of doing a rmw cycle (which might result in us clearing
  * all limits and the gpu stuck at whatever frequency it is at atm).
  */
-static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 *val)
+static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 {
 	u32 limits;
 
-	limits = 0;
-
-	if (*val >= dev_priv->rps.max_delay)
-		*val = dev_priv->rps.max_delay;
-	limits |= dev_priv->rps.max_delay << 24;
-
 	/* Only set the down limit when we've reached the lowest level to avoid
 	 * getting more interrupts, otherwise leave this clear. This prevents a
 	 * race in the hw when coming out of rc6: There's a tiny window where
 	 * the hw runs at the minimal clock before selecting the desired
 	 * frequency, if the down threshold expires in that window we will not
 	 * receive a down interrupt. */
-	if (*val <= dev_priv->rps.min_delay) {
-		*val = dev_priv->rps.min_delay;
+	limits = dev_priv->rps.max_delay << 24;
+	if (val <= dev_priv->rps.min_delay)
 		limits |= dev_priv->rps.min_delay << 16;
-	}
 
 	return limits;
 }
@@ -3549,7 +3003,6 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 void gen6_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 limits = gen6_rps_limits(dev_priv, &val);
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 	WARN_ON(val > dev_priv->rps.max_delay);
@@ -3572,7 +3025,8 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	/* Make sure we continue to get interrupts
 	 * until we hit the minimum or maximum frequencies.
 	 */
-	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
+	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+		   gen6_rps_limits(dev_priv, val));
 
 	POSTING_READ(GEN6_RPNSWREQ);
 
@@ -3583,9 +3037,11 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
+
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (dev_priv->info->is_valleyview)
+		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
 		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
@@ -3596,9 +3052,11 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 
 void gen6_rps_boost(struct drm_i915_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
+
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (dev_priv->info->is_valleyview)
+		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
 		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
@@ -3607,48 +3065,18 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-/*
- * Wait until the previous freq change has completed,
- * or the timeout elapsed, and then update our notion
- * of the current GPU frequency.
- */
-static void vlv_update_rps_cur_delay(struct drm_i915_private *dev_priv)
-{
-	u32 pval;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-
-	if (wait_for(((pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) & GENFREQSTATUS) == 0, 10))
-		DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
-
-	pval >>= 8;
-
-	if (pval != dev_priv->rps.cur_delay)
-		DRM_DEBUG_DRIVER("Punit overrode GPU freq: %d MHz (%u) requested, but got %d Mhz (%u)\n",
-				 vlv_gpu_freq(dev_priv->mem_freq, dev_priv->rps.cur_delay),
-				 dev_priv->rps.cur_delay,
-				 vlv_gpu_freq(dev_priv->mem_freq, pval), pval);
-
-	dev_priv->rps.cur_delay = pval;
-}
-
 void valleyview_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	gen6_rps_limits(dev_priv, &val);
-
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 	WARN_ON(val > dev_priv->rps.max_delay);
 	WARN_ON(val < dev_priv->rps.min_delay);
 
-	vlv_update_rps_cur_delay(dev_priv);
-
 	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.cur_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
 			 dev_priv->rps.cur_delay,
-			 vlv_gpu_freq(dev_priv->mem_freq, val), val);
+			 vlv_gpu_freq(dev_priv, val), val);
 
 	if (val == dev_priv->rps.cur_delay)
 		return;
@@ -3657,7 +3085,7 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 
 	dev_priv->rps.cur_delay = val;
 
-	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv->mem_freq, val));
+	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
 }
 
 static void gen6_disable_rps_interrupts(struct drm_device *dev)
@@ -3775,7 +3203,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 
 	/* 1c & 1d: Get forcewake during program sequence. Although the driver
 	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
-	gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	/* 2a: Disable RC states. */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -3832,7 +3260,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 
 	gen6_enable_rps_interrupts(dev);
 
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
 static void gen6_enable_rps(struct drm_device *dev)
@@ -3862,7 +3290,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 		I915_WRITE(GTFIFODBG, gtfifodbg);
 	}
 
-	gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
 	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
@@ -3954,7 +3382,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 			DRM_ERROR("Couldn't fix incorrect rc6 voltage\n");
 	}
 
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
 void gen6_update_ring_freq(struct drm_device *dev)
@@ -4116,7 +3544,8 @@ static void valleyview_enable_rps(struct drm_device *dev)
 
 	valleyview_setup_pctx(dev);
 
-	gen6_gt_force_wake_get(dev_priv);
+	/* If VLV, Forcewake all wells, else re-direct to regular path */
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
@@ -4140,7 +3569,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i)
 		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
 
-	I915_WRITE(GEN6_RC6_THRESHOLD, 0xc350);
+	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
 
 	/* allows RC6 residency counter to work */
 	I915_WRITE(VLV_COUNTER_CONTROL,
@@ -4148,65 +3577,47 @@ static void valleyview_enable_rps(struct drm_device *dev)
 				      VLV_MEDIA_RC6_COUNT_EN |
 				      VLV_RENDER_RC6_COUNT_EN));
 	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
-		rc6_mode = GEN7_RC_CTL_TO_MODE;
+		rc6_mode = GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
 
 	intel_print_rc6_info(dev, rc6_mode);
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
 	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-	switch ((val >> 6) & 3) {
-	case 0:
-	case 1:
-		dev_priv->mem_freq = 800;
-		break;
-	case 2:
-		dev_priv->mem_freq = 1066;
-		break;
-	case 3:
-		dev_priv->mem_freq = 1333;
-		break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
 	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
 
 	dev_priv->rps.cur_delay = (val >> 8) & 0xff;
 	DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.cur_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_delay),
 			 dev_priv->rps.cur_delay);
 
 	dev_priv->rps.max_delay = valleyview_rps_max_freq(dev_priv);
 	dev_priv->rps.hw_max = dev_priv->rps.max_delay;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.max_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_delay),
 			 dev_priv->rps.max_delay);
 
 	dev_priv->rps.rpe_delay = valleyview_rps_rpe_freq(dev_priv);
 	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.rpe_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
 	dev_priv->rps.min_delay = valleyview_rps_min_freq(dev_priv);
 	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.min_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_delay),
 			 dev_priv->rps.min_delay);
 
 	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv->mem_freq,
-				      dev_priv->rps.rpe_delay),
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
 
 	gen6_enable_rps_interrupts(dev);
 
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
 void ironlake_teardown_rc6(struct drm_device *dev)
@@ -5019,6 +4430,20 @@ static void g4x_disable_trickle_feed(struct drm_device *dev)
 	}
 }
 
+static void ilk_init_lp_watermarks(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(WM3_LP_ILK, I915_READ(WM3_LP_ILK) & ~WM1_LP_SR_EN);
+	I915_WRITE(WM2_LP_ILK, I915_READ(WM2_LP_ILK) & ~WM1_LP_SR_EN);
+	I915_WRITE(WM1_LP_ILK, I915_READ(WM1_LP_ILK) & ~WM1_LP_SR_EN);
+
+	/*
+	 * Don't touch WM1S_LP_EN here.
+	 * Doing so could cause underruns.
+	 */
+}
+
 static void ironlake_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -5052,9 +4477,8 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(DISP_ARB_CTL,
 		   (I915_READ(DISP_ARB_CTL) |
 		    DISP_FBC_WM_DIS));
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
+
+	ilk_init_lp_watermarks(dev);
 
 	/*
 	 * Based on the document from hardware guys the following bits
@@ -5161,9 +4585,7 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		I915_WRITE(GEN6_GT_MODE,
 			   _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE));
 
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
+	ilk_init_lp_watermarks(dev);
 
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
@@ -5304,28 +4726,40 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
 		   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
 
-	/* WaSwitchSolVfFArbitrationPriority */
+	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
-	/* WaPsrDPAMaskVBlankInSRD */
+	/* WaPsrDPAMaskVBlankInSRD:bdw */
 	I915_WRITE(CHICKEN_PAR1_1,
 		   I915_READ(CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
-	/* WaPsrDPRSUnmaskVBlankInSRD */
+	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 	for_each_pipe(i) {
 		I915_WRITE(CHICKEN_PIPESL_1(i),
 			   I915_READ(CHICKEN_PIPESL_1(i) |
 				     DPRS_MASK_VBLANK_SRD));
 	}
+
+	/* Use Force Non-Coherent whenever executing a 3D context. This is a
+	 * workaround for for a possible hang in the unlikely event a TLB
+	 * invalidation occurs during a PSD flush.
+	 */
+	I915_WRITE(HDC_CHICKEN0,
+		   I915_READ(HDC_CHICKEN0) |
+		   _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
+
+	/* WaVSRefCountFullforceMissDisable:bdw */
+	/* WaDSRefCountFullforceMissDisable:bdw */
+	I915_WRITE(GEN7_FF_THREAD_MODE,
+		   I915_READ(GEN7_FF_THREAD_MODE) &
+		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
 }
 
 static void haswell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
+	ilk_init_lp_watermarks(dev);
 
 	/* According to the spec, bit 13 (RCZUNIT) must be set on IVB.
 	 * This implements the WaDisableRCZUnitClockGating:hsw workaround.
@@ -5374,9 +4808,7 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t snpcr;
 
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
+	ilk_init_lp_watermarks(dev);
 
 	I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
@@ -5463,6 +4895,26 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 static void valleyview_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	switch ((val >> 6) & 3) {
+	case 0:
+		dev_priv->mem_freq = 800;
+		break;
+	case 1:
+		dev_priv->mem_freq = 1066;
+		break;
+	case 2:
+		dev_priv->mem_freq = 1333;
+		break;
+	case 3:
+		dev_priv->mem_freq = 1333;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
@@ -5642,50 +5094,133 @@ void intel_suspend_hw(struct drm_device *dev)
 		lpt_suspend_hw(dev);
 }
 
-static bool is_always_on_power_domain(struct drm_device *dev,
-				      enum intel_display_power_domain domain)
-{
-	unsigned long always_on_domains;
+#define for_each_power_well(i, power_well, domain_mask, power_domains)	\
+	for (i = 0;							\
+	     i < (power_domains)->power_well_count &&			\
+		 ((power_well) = &(power_domains)->power_wells[i]);	\
+	     i++)							\
+		if ((power_well)->domains & (domain_mask))
 
-	BUG_ON(BIT(domain) & ~POWER_DOMAIN_MASK);
-
-	if (IS_BROADWELL(dev)) {
-		always_on_domains = BDW_ALWAYS_ON_POWER_DOMAINS;
-	} else if (IS_HASWELL(dev)) {
-		always_on_domains = HSW_ALWAYS_ON_POWER_DOMAINS;
-	} else {
-		WARN_ON(1);
-		return true;
-	}
-
-	return BIT(domain) & always_on_domains;
-}
+#define for_each_power_well_rev(i, power_well, domain_mask, power_domains) \
+	for (i = (power_domains)->power_well_count - 1;			 \
+	     i >= 0 && ((power_well) = &(power_domains)->power_wells[i]);\
+	     i--)							 \
+		if ((power_well)->domains & (domain_mask))
 
 /**
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
  * be enabled.
  */
+static bool hsw_power_well_enabled(struct drm_device *dev,
+				   struct i915_power_well *power_well)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	return I915_READ(HSW_PWR_WELL_DRIVER) ==
+		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
+}
+
+bool intel_display_power_enabled_sw(struct drm_device *dev,
+				    enum intel_display_power_domain domain)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_power_domains *power_domains;
+
+	power_domains = &dev_priv->power_domains;
+
+	return power_domains->domain_use_count[domain];
+}
+
 bool intel_display_power_enabled(struct drm_device *dev,
 				 enum intel_display_power_domain domain)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_power_domains *power_domains;
+	struct i915_power_well *power_well;
+	bool is_enabled;
+	int i;
 
-	if (!HAS_POWER_WELL(dev))
-		return true;
+	power_domains = &dev_priv->power_domains;
 
-	if (is_always_on_power_domain(dev, domain))
-		return true;
+	is_enabled = true;
 
-	return I915_READ(HSW_PWR_WELL_DRIVER) ==
-		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
+	mutex_lock(&power_domains->lock);
+	for_each_power_well_rev(i, power_well, BIT(domain), power_domains) {
+		if (power_well->always_on)
+			continue;
+
+		if (!power_well->is_enabled(dev, power_well)) {
+			is_enabled = false;
+			break;
+		}
+	}
+	mutex_unlock(&power_domains->lock);
+
+	return is_enabled;
+}
+
+static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	unsigned long irqflags;
+
+	/*
+	 * After we re-enable the power well, if we touch VGA register 0x3d5
+	 * we'll get unclaimed register interrupts. This stops after we write
+	 * anything to the VGA MSR register. The vgacon module uses this
+	 * register all the time, so if we unbind our driver and, as a
+	 * consequence, bind vgacon, we'll get stuck in an infinite loop at
+	 * console_unlock(). So make here we touch the VGA MSR register, making
+	 * sure vgacon can keep working normally without triggering interrupts
+	 * and error messages.
+	 */
+	vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO);
+	outb(inb(VGA_MSR_READ), VGA_MSR_WRITE);
+	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
+
+	if (IS_BROADWELL(dev)) {
+		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+		I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_B),
+			   dev_priv->de_irq_mask[PIPE_B]);
+		I915_WRITE(GEN8_DE_PIPE_IER(PIPE_B),
+			   ~dev_priv->de_irq_mask[PIPE_B] |
+			   GEN8_PIPE_VBLANK);
+		I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_C),
+			   dev_priv->de_irq_mask[PIPE_C]);
+		I915_WRITE(GEN8_DE_PIPE_IER(PIPE_C),
+			   ~dev_priv->de_irq_mask[PIPE_C] |
+			   GEN8_PIPE_VBLANK);
+		POSTING_READ(GEN8_DE_PIPE_IER(PIPE_C));
+		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+	}
 }
 
-static void __intel_set_power_well(struct drm_device *dev, bool enable)
+static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	enum pipe p;
+	unsigned long irqflags;
+
+	/*
+	 * After this, the registers on the pipes that are part of the power
+	 * well will become zero, so we have to adjust our counters according to
+	 * that.
+	 *
+	 * FIXME: Should we do this in general in drm_vblank_post_modeset?
+	 */
+	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	for_each_pipe(p)
+		if (p != PIPE_A)
+			dev->vblank[p].last = 0;
+	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+}
+
+static void hsw_set_power_well(struct drm_device *dev,
+			       struct i915_power_well *power_well, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool is_enabled, enable_requested;
-	unsigned long irqflags;
 	uint32_t tmp;
 
 	WARN_ON(dev_priv->pc8.enabled);
@@ -5706,42 +5241,14 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 				DRM_ERROR("Timeout enabling power well\n");
 		}
 
-		if (IS_BROADWELL(dev)) {
-			spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-			I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_B),
-				   dev_priv->de_irq_mask[PIPE_B]);
-			I915_WRITE(GEN8_DE_PIPE_IER(PIPE_B),
-				   ~dev_priv->de_irq_mask[PIPE_B] |
-				   GEN8_PIPE_VBLANK);
-			I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_C),
-				   dev_priv->de_irq_mask[PIPE_C]);
-			I915_WRITE(GEN8_DE_PIPE_IER(PIPE_C),
-				   ~dev_priv->de_irq_mask[PIPE_C] |
-				   GEN8_PIPE_VBLANK);
-			POSTING_READ(GEN8_DE_PIPE_IER(PIPE_C));
-			spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-		}
+		hsw_power_well_post_enable(dev_priv);
 	} else {
 		if (enable_requested) {
-			enum pipe p;
-
 			I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
 			POSTING_READ(HSW_PWR_WELL_DRIVER);
 			DRM_DEBUG_KMS("Requesting to disable the power well\n");
 
-			/*
-			 * After this, the registers on the pipes that are part
-			 * of the power well will become zero, so we have to
-			 * adjust our counters according to that.
-			 *
-			 * FIXME: Should we do this in general in
-			 * drm_vblank_post_modeset?
-			 */
-			spin_lock_irqsave(&dev->vbl_lock, irqflags);
-			for_each_pipe(p)
-				if (p != PIPE_A)
-					dev->vblank[p].last = 0;
-			spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+			hsw_power_well_post_disable(dev_priv);
 		}
 	}
 }
@@ -5751,9 +5258,9 @@ static void __intel_power_well_get(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!power_well->count++) {
+	if (!power_well->count++ && power_well->set) {
 		hsw_disable_package_c8(dev_priv);
-		__intel_set_power_well(dev, true);
+		power_well->set(dev, power_well, true);
 	}
 }
 
@@ -5763,8 +5270,10 @@ static void __intel_power_well_put(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!power_well->count);
-	if (!--power_well->count && i915_disable_power_well) {
-		__intel_set_power_well(dev, false);
+
+	if (!--power_well->count && power_well->set &&
+	    i915_disable_power_well) {
+		power_well->set(dev, power_well, false);
 		hsw_enable_package_c8(dev_priv);
 	}
 }
@@ -5774,17 +5283,18 @@ void intel_display_power_get(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
-
-	if (!HAS_POWER_WELL(dev))
-		return;
-
-	if (is_always_on_power_domain(dev, domain))
-		return;
+	struct i915_power_well *power_well;
+	int i;
 
 	power_domains = &dev_priv->power_domains;
 
 	mutex_lock(&power_domains->lock);
-	__intel_power_well_get(dev, &power_domains->power_wells[0]);
+
+	for_each_power_well(i, power_well, BIT(domain), power_domains)
+		__intel_power_well_get(dev, power_well);
+
+	power_domains->domain_use_count[domain]++;
+
 	mutex_unlock(&power_domains->lock);
 }
 
@@ -5793,17 +5303,19 @@ void intel_display_power_put(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
-
-	if (!HAS_POWER_WELL(dev))
-		return;
-
-	if (is_always_on_power_domain(dev, domain))
-		return;
+	struct i915_power_well *power_well;
+	int i;
 
 	power_domains = &dev_priv->power_domains;
 
 	mutex_lock(&power_domains->lock);
-	__intel_power_well_put(dev, &power_domains->power_wells[0]);
+
+	WARN_ON(!power_domains->domain_use_count[domain]);
+	power_domains->domain_use_count[domain]--;
+
+	for_each_power_well_rev(i, power_well, BIT(domain), power_domains)
+		__intel_power_well_put(dev, power_well);
+
 	mutex_unlock(&power_domains->lock);
 }
 
@@ -5819,10 +5331,7 @@ void i915_request_power_well(void)
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
-
-	mutex_lock(&hsw_pwr->lock);
-	__intel_power_well_get(dev_priv->dev, &hsw_pwr->power_wells[0]);
-	mutex_unlock(&hsw_pwr->lock);
+	intel_display_power_get(dev_priv->dev, POWER_DOMAIN_AUDIO);
 }
 EXPORT_SYMBOL_GPL(i915_request_power_well);
 
@@ -5836,24 +5345,71 @@ void i915_release_power_well(void)
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
-
-	mutex_lock(&hsw_pwr->lock);
-	__intel_power_well_put(dev_priv->dev, &hsw_pwr->power_wells[0]);
-	mutex_unlock(&hsw_pwr->lock);
+	intel_display_power_put(dev_priv->dev, POWER_DOMAIN_AUDIO);
 }
 EXPORT_SYMBOL_GPL(i915_release_power_well);
 
+static struct i915_power_well i9xx_always_on_power_well[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = POWER_DOMAIN_MASK,
+	},
+};
+
+static struct i915_power_well hsw_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = HSW_ALWAYS_ON_POWER_DOMAINS,
+	},
+	{
+		.name = "display",
+		.domains = POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS,
+		.is_enabled = hsw_power_well_enabled,
+		.set = hsw_set_power_well,
+	},
+};
+
+static struct i915_power_well bdw_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = BDW_ALWAYS_ON_POWER_DOMAINS,
+	},
+	{
+		.name = "display",
+		.domains = POWER_DOMAIN_MASK & ~BDW_ALWAYS_ON_POWER_DOMAINS,
+		.is_enabled = hsw_power_well_enabled,
+		.set = hsw_set_power_well,
+	},
+};
+
+#define set_power_wells(power_domains, __power_wells) ({		\
+	(power_domains)->power_wells = (__power_wells);			\
+	(power_domains)->power_well_count = ARRAY_SIZE(__power_wells);	\
+})
+
 int intel_power_domains_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-	struct i915_power_well *power_well;
 
 	mutex_init(&power_domains->lock);
-	hsw_pwr = power_domains;
 
-	power_well = &power_domains->power_wells[0];
-	power_well->count = 0;
+	/*
+	 * The enabling order will be from lower to higher indexed wells,
+	 * the disabling order is reversed.
+	 */
+	if (IS_HASWELL(dev)) {
+		set_power_wells(power_domains, hsw_power_wells);
+		hsw_pwr = power_domains;
+	} else if (IS_BROADWELL(dev)) {
+		set_power_wells(power_domains, bdw_power_wells);
+		hsw_pwr = power_domains;
+	} else {
+		set_power_wells(power_domains, i9xx_always_on_power_well);
+	}
 
 	return 0;
 }
@@ -5868,15 +5424,13 @@ static void intel_power_domains_resume(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 	struct i915_power_well *power_well;
-
-	if (!HAS_POWER_WELL(dev))
-		return;
+	int i;
 
 	mutex_lock(&power_domains->lock);
-
-	power_well = &power_domains->power_wells[0];
-	__intel_set_power_well(dev, power_well->count > 0);
-
+	for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
+		if (power_well->set)
+			power_well->set(dev, power_well, power_well->count > 0);
+	}
 	mutex_unlock(&power_domains->lock);
 }
 
@@ -5890,13 +5444,13 @@ void intel_power_domains_init_hw(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!HAS_POWER_WELL(dev))
-		return;
-
 	/* For now, we need the power well to be always enabled. */
 	intel_display_set_init_power(dev, true);
 	intel_power_domains_resume(dev);
 
+	if (!(IS_HASWELL(dev) || IS_BROADWELL(dev)))
+		return;
+
 	/* 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_REQUEST)
@@ -5914,31 +5468,86 @@ void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
 	hsw_enable_package_c8(dev_priv);
 }
 
+void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	pm_runtime_get_sync(device);
+	WARN(dev_priv->pm.suspended, "Device still suspended.\n");
+}
+
+void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	pm_runtime_mark_last_busy(device);
+	pm_runtime_put_autosuspend(device);
+}
+
+void intel_init_runtime_pm(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	dev_priv->pm.suspended = false;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	pm_runtime_set_active(device);
+
+	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
+	pm_runtime_mark_last_busy(device);
+	pm_runtime_use_autosuspend(device);
+}
+
+void intel_fini_runtime_pm(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	/* Make sure we're not suspended first. */
+	pm_runtime_get_sync(device);
+	pm_runtime_disable(device);
+}
+
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (I915_HAS_FBC(dev)) {
-		if (HAS_PCH_SPLIT(dev)) {
+	if (HAS_FBC(dev)) {
+		if (INTEL_INFO(dev)->gen >= 7) {
 			dev_priv->display.fbc_enabled = ironlake_fbc_enabled;
-			if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-				dev_priv->display.enable_fbc =
-					gen7_enable_fbc;
-			else
-				dev_priv->display.enable_fbc =
-					ironlake_enable_fbc;
+			dev_priv->display.enable_fbc = gen7_enable_fbc;
+			dev_priv->display.disable_fbc = ironlake_disable_fbc;
+		} else if (INTEL_INFO(dev)->gen >= 5) {
+			dev_priv->display.fbc_enabled = ironlake_fbc_enabled;
+			dev_priv->display.enable_fbc = ironlake_enable_fbc;
 			dev_priv->display.disable_fbc = ironlake_disable_fbc;
 		} else if (IS_GM45(dev)) {
 			dev_priv->display.fbc_enabled = g4x_fbc_enabled;
 			dev_priv->display.enable_fbc = g4x_enable_fbc;
 			dev_priv->display.disable_fbc = g4x_disable_fbc;
-		} else if (IS_CRESTLINE(dev)) {
+		} else {
 			dev_priv->display.fbc_enabled = i8xx_fbc_enabled;
 			dev_priv->display.enable_fbc = i8xx_enable_fbc;
 			dev_priv->display.disable_fbc = i8xx_disable_fbc;
+
+			/* This value was pulled out of someone's hat */
+			I915_WRITE(FBC_CONTROL, 500 << FBC_CTL_INTERVAL_SHIFT);
 		}
-		/* 855GM needs testing */
 	}
 
 	/* For cxsr */
@@ -5951,58 +5560,27 @@ void intel_init_pm(struct drm_device *dev)
 	if (HAS_PCH_SPLIT(dev)) {
 		intel_setup_wm_latency(dev);
 
-		if (IS_GEN5(dev)) {
-			if (dev_priv->wm.pri_latency[1] &&
-			    dev_priv->wm.spr_latency[1] &&
-			    dev_priv->wm.cur_latency[1])
-				dev_priv->display.update_wm = ironlake_update_wm;
-			else {
-				DRM_DEBUG_KMS("Failed to get proper latency. "
-					      "Disable CxSR\n");
-				dev_priv->display.update_wm = NULL;
-			}
+		if ((IS_GEN5(dev) && dev_priv->wm.pri_latency[1] &&
+		     dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) ||
+		    (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] &&
+		     dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) {
+			dev_priv->display.update_wm = ilk_update_wm;
+			dev_priv->display.update_sprite_wm = ilk_update_sprite_wm;
+		} else {
+			DRM_DEBUG_KMS("Failed to read display plane latency. "
+				      "Disable CxSR\n");
+		}
+
+		if (IS_GEN5(dev))
 			dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
-		} else if (IS_GEN6(dev)) {
-			if (dev_priv->wm.pri_latency[0] &&
-			    dev_priv->wm.spr_latency[0] &&
-			    dev_priv->wm.cur_latency[0]) {
-				dev_priv->display.update_wm = sandybridge_update_wm;
-				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
-			} else {
-				DRM_DEBUG_KMS("Failed to read display plane latency. "
-					      "Disable CxSR\n");
-				dev_priv->display.update_wm = NULL;
-			}
+		else if (IS_GEN6(dev))
 			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
-		} else if (IS_IVYBRIDGE(dev)) {
-			if (dev_priv->wm.pri_latency[0] &&
-			    dev_priv->wm.spr_latency[0] &&
-			    dev_priv->wm.cur_latency[0]) {
-				dev_priv->display.update_wm = ivybridge_update_wm;
-				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
-			} else {
-				DRM_DEBUG_KMS("Failed to read display plane latency. "
-					      "Disable CxSR\n");
-				dev_priv->display.update_wm = NULL;
-			}
+		else if (IS_IVYBRIDGE(dev))
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
-		} else if (IS_HASWELL(dev)) {
-			if (dev_priv->wm.pri_latency[0] &&
-			    dev_priv->wm.spr_latency[0] &&
-			    dev_priv->wm.cur_latency[0]) {
-				dev_priv->display.update_wm = haswell_update_wm;
-				dev_priv->display.update_sprite_wm =
-					haswell_update_sprite_wm;
-			} else {
-				DRM_DEBUG_KMS("Failed to read display plane latency. "
-					      "Disable CxSR\n");
-				dev_priv->display.update_wm = NULL;
-			}
+		else if (IS_HASWELL(dev))
 			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
-		} else if (INTEL_INFO(dev)->gen == 8) {
+		else if (INTEL_INFO(dev)->gen == 8)
 			dev_priv->display.init_clock_gating = gen8_init_clock_gating;
-		} else
-			dev_priv->display.update_wm = NULL;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.update_wm = valleyview_update_wm;
 		dev_priv->display.init_clock_gating =
@@ -6036,21 +5614,21 @@ void intel_init_pm(struct drm_device *dev)
 		dev_priv->display.update_wm = i9xx_update_wm;
 		dev_priv->display.get_fifo_size = i9xx_get_fifo_size;
 		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
-	} else if (IS_I865G(dev)) {
-		dev_priv->display.update_wm = i830_update_wm;
-		dev_priv->display.init_clock_gating = i85x_init_clock_gating;
-		dev_priv->display.get_fifo_size = i830_get_fifo_size;
-	} else if (IS_I85X(dev)) {
-		dev_priv->display.update_wm = i9xx_update_wm;
-		dev_priv->display.get_fifo_size = i85x_get_fifo_size;
-		dev_priv->display.init_clock_gating = i85x_init_clock_gating;
-	} else {
-		dev_priv->display.update_wm = i830_update_wm;
-		dev_priv->display.init_clock_gating = i830_init_clock_gating;
-		if (IS_845G(dev))
+	} else if (IS_GEN2(dev)) {
+		if (INTEL_INFO(dev)->num_pipes == 1) {
+			dev_priv->display.update_wm = i845_update_wm;
 			dev_priv->display.get_fifo_size = i845_get_fifo_size;
-		else
+		} else {
+			dev_priv->display.update_wm = i9xx_update_wm;
 			dev_priv->display.get_fifo_size = i830_get_fifo_size;
+		}
+
+		if (IS_I85X(dev) || IS_I865G(dev))
+			dev_priv->display.init_clock_gating = i85x_init_clock_gating;
+		else
+			dev_priv->display.init_clock_gating = i830_init_clock_gating;
+	} else {
+		DRM_ERROR("unexpected fall-through in intel_init_pm\n");
 	}
 }
 
@@ -6101,59 +5679,48 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val)
 	return 0;
 }
 
-int vlv_gpu_freq(int ddr_freq, int val)
+int vlv_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
-	int mult, base;
+	int div;
 
-	switch (ddr_freq) {
+	/* 4 x czclk */
+	switch (dev_priv->mem_freq) {
 	case 800:
-		mult = 20;
-		base = 120;
+		div = 10;
 		break;
 	case 1066:
-		mult = 22;
-		base = 133;
+		div = 12;
 		break;
 	case 1333:
-		mult = 21;
-		base = 125;
+		div = 16;
 		break;
 	default:
 		return -1;
 	}
 
-	return ((val - 0xbd) * mult) + base;
+	return DIV_ROUND_CLOSEST(dev_priv->mem_freq * (val + 6 - 0xbd), 4 * div);
 }
 
-int vlv_freq_opcode(int ddr_freq, int val)
+int vlv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
-	int mult, base;
+	int mul;
 
-	switch (ddr_freq) {
+	/* 4 x czclk */
+	switch (dev_priv->mem_freq) {
 	case 800:
-		mult = 20;
-		base = 120;
+		mul = 10;
 		break;
 	case 1066:
-		mult = 22;
-		base = 133;
+		mul = 12;
 		break;
 	case 1333:
-		mult = 21;
-		base = 125;
+		mul = 16;
 		break;
 	default:
 		return -1;
 	}
 
-	val /= mult;
-	val -= base / mult;
-	val += 0xbd;
-
-	if (val > 0xea)
-		val = 0xea;
-
-	return val;
+	return DIV_ROUND_CLOSEST(4 * mul * val, dev_priv->mem_freq) + 0xbd - 6;
 }
 
 void intel_pm_setup(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c2f09d456300..b7f1742caf87 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -285,14 +285,16 @@ static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value)
 	if (!ring->fbc_dirty)
 		return 0;
 
-	ret = intel_ring_begin(ring, 4);
+	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
-	intel_ring_emit(ring, MI_NOOP);
 	/* WaFbcNukeOn3DBlt:ivb/hsw */
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
 	intel_ring_emit(ring, MSG_FBC_REND_STATE);
 	intel_ring_emit(ring, value);
+	intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | MI_SRM_LRM_GLOBAL_GTT);
+	intel_ring_emit(ring, MSG_FBC_REND_STATE);
+	intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
 	intel_ring_advance(ring);
 
 	ring->fbc_dirty = false;
@@ -354,7 +356,7 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
-	if (flush_domains)
+	if (!invalidate_domains && flush_domains)
 		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
 
 	return 0;
@@ -436,7 +438,7 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	int ret = 0;
 	u32 head;
 
-	gen6_gt_force_wake_get(dev_priv);
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	if (I915_NEED_GFX_HWS(dev))
 		intel_ring_setup_status_page(ring);
@@ -509,7 +511,7 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
 
 out:
-	gen6_gt_force_wake_put(dev_priv);
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 
 	return ret;
 }
@@ -661,19 +663,22 @@ gen6_add_request(struct intel_ring_buffer *ring)
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *useless;
-	int i, ret;
+	int i, ret, num_dwords = 4;
 
-	ret = intel_ring_begin(ring, ((I915_NUM_RINGS-1) *
-				      MBOX_UPDATE_DWORDS) +
-				      4);
+	if (i915_semaphore_is_enabled(dev))
+		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
+#undef MBOX_UPDATE_DWORDS
+
+	ret = intel_ring_begin(ring, num_dwords);
 	if (ret)
 		return ret;
-#undef MBOX_UPDATE_DWORDS
 
-	for_each_ring(useless, dev_priv, i) {
-		u32 mbox_reg = ring->signal_mbox[i];
-		if (mbox_reg != GEN6_NOSYNC)
-			update_mboxes(ring, mbox_reg);
+	if (i915_semaphore_is_enabled(dev)) {
+		for_each_ring(useless, dev_priv, i) {
+			u32 mbox_reg = ring->signal_mbox[i];
+			if (mbox_reg != GEN6_NOSYNC)
+				update_mboxes(ring, mbox_reg);
+		}
 	}
 
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
@@ -1030,11 +1035,6 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 	if (!dev->irq_enabled)
 	       return false;
 
-	/* It looks like we need to prevent the gt from suspending while waiting
-	 * for an notifiy irq, otherwise irqs seem to get lost on at least the
-	 * blt/bsd rings on ivb. */
-	gen6_gt_force_wake_get(dev_priv);
-
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
 		if (HAS_L3_DPF(dev) && ring->id == RCS)
@@ -1066,8 +1066,6 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-
-	gen6_gt_force_wake_put(dev_priv);
 }
 
 static bool
@@ -1611,8 +1609,8 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring)
 	return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
 }
 
-static int __intel_ring_begin(struct intel_ring_buffer *ring,
-			      int bytes)
+static int __intel_ring_prepare(struct intel_ring_buffer *ring,
+				int bytes)
 {
 	int ret;
 
@@ -1628,7 +1626,6 @@ static int __intel_ring_begin(struct intel_ring_buffer *ring,
 			return ret;
 	}
 
-	ring->space -= bytes;
 	return 0;
 }
 
@@ -1643,12 +1640,17 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
+	ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
+	if (ret)
+		return ret;
+
 	/* Preallocate the olr before touching the ring */
 	ret = intel_ring_alloc_seqno(ring);
 	if (ret)
 		return ret;
 
-	return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t));
+	ring->space -= num_dwords * sizeof(uint32_t);
+	return 0;
 }
 
 void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
@@ -1838,7 +1840,7 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 	}
 	intel_ring_advance(ring);
 
-	if (IS_GEN7(dev) && flush)
+	if (IS_GEN7(dev) && !invalidate && flush)
 		return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index a583e8f718a7..95bdfb3c431c 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -413,23 +413,34 @@ static const struct _sdvo_cmd_name {
 static void intel_sdvo_debug_write(struct intel_sdvo *intel_sdvo, u8 cmd,
 				   const void *args, int args_len)
 {
-	int i;
+	int i, pos = 0;
+#define BUF_LEN 256
+	char buffer[BUF_LEN];
+
+#define BUF_PRINT(args...) \
+	pos += snprintf(buffer + pos, max_t(int, BUF_LEN - pos, 0), args)
+
 
-	DRM_DEBUG_KMS("%s: W: %02X ",
-				SDVO_NAME(intel_sdvo), cmd);
-	for (i = 0; i < args_len; i++)
-		DRM_LOG_KMS("%02X ", ((u8 *)args)[i]);
-	for (; i < 8; i++)
-		DRM_LOG_KMS("   ");
+	for (i = 0; i < args_len; i++) {
+		BUF_PRINT("%02X ", ((u8 *)args)[i]);
+	}
+	for (; i < 8; i++) {
+		BUF_PRINT("   ");
+	}
 	for (i = 0; i < ARRAY_SIZE(sdvo_cmd_names); i++) {
 		if (cmd == sdvo_cmd_names[i].cmd) {
-			DRM_LOG_KMS("(%s)", sdvo_cmd_names[i].name);
+			BUF_PRINT("(%s)", sdvo_cmd_names[i].name);
 			break;
 		}
 	}
-	if (i == ARRAY_SIZE(sdvo_cmd_names))
-		DRM_LOG_KMS("(%02X)", cmd);
-	DRM_LOG_KMS("\n");
+	if (i == ARRAY_SIZE(sdvo_cmd_names)) {
+		BUF_PRINT("(%02X)", cmd);
+	}
+	BUG_ON(pos >= BUF_LEN - 1);
+#undef BUF_PRINT
+#undef BUF_LEN
+
+	DRM_DEBUG_KMS("%s: W: %02X %s\n", SDVO_NAME(intel_sdvo), cmd, buffer);
 }
 
 static const char *cmd_status_names[] = {
@@ -512,9 +523,10 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo,
 {
 	u8 retry = 15; /* 5 quick checks, followed by 10 long checks */
 	u8 status;
-	int i;
+	int i, pos = 0;
+#define BUF_LEN 256
+	char buffer[BUF_LEN];
 
-	DRM_DEBUG_KMS("%s: R: ", SDVO_NAME(intel_sdvo));
 
 	/*
 	 * The documentation states that all commands will be
@@ -551,10 +563,13 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo,
 			goto log_fail;
 	}
 
+#define BUF_PRINT(args...) \
+	pos += snprintf(buffer + pos, max_t(int, BUF_LEN - pos, 0), args)
+
 	if (status <= SDVO_CMD_STATUS_SCALING_NOT_SUPP)
-		DRM_LOG_KMS("(%s)", cmd_status_names[status]);
+		BUF_PRINT("(%s)", cmd_status_names[status]);
 	else
-		DRM_LOG_KMS("(??? %d)", status);
+		BUF_PRINT("(??? %d)", status);
 
 	if (status != SDVO_CMD_STATUS_SUCCESS)
 		goto log_fail;
@@ -565,13 +580,17 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo,
 					  SDVO_I2C_RETURN_0 + i,
 					  &((u8 *)response)[i]))
 			goto log_fail;
-		DRM_LOG_KMS(" %02X", ((u8 *)response)[i]);
+		BUF_PRINT(" %02X", ((u8 *)response)[i]);
 	}
-	DRM_LOG_KMS("\n");
+	BUG_ON(pos >= BUF_LEN - 1);
+#undef BUF_PRINT
+#undef BUF_LEN
+
+	DRM_DEBUG_KMS("%s: R: %s\n", SDVO_NAME(intel_sdvo), buffer);
 	return true;
 
 log_fail:
-	DRM_LOG_KMS("... failed\n");
+	DRM_DEBUG_KMS("%s: R: ... failed\n", SDVO_NAME(intel_sdvo));
 	return false;
 }
 
@@ -933,7 +952,7 @@ static void intel_sdvo_dump_hdmi_buf(struct intel_sdvo *intel_sdvo)
 
 static bool intel_sdvo_write_infoframe(struct intel_sdvo *intel_sdvo,
 				       unsigned if_index, uint8_t tx_rate,
-				       uint8_t *data, unsigned length)
+				       const uint8_t *data, unsigned length)
 {
 	uint8_t set_buf_index[2] = { if_index, 0 };
 	uint8_t hbuf_size, tmp[8];
@@ -1517,8 +1536,9 @@ static void intel_sdvo_dpms(struct drm_connector *connector, int mode)
 	intel_modeset_check_state(connector->dev);
 }
 
-static int intel_sdvo_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
+static enum drm_mode_status
+intel_sdvo_mode_valid(struct drm_connector *connector,
+		      struct drm_display_mode *mode)
 {
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h
index 770bdd6ecd9f..2e2d4eb4a00d 100644
--- a/drivers/gpu/drm/i915/intel_sdvo_regs.h
+++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h
@@ -59,7 +59,7 @@ struct intel_sdvo_caps {
 	unsigned int stall_support:1;
 	unsigned int pad:1;
 	u16 output_flags;
-} __attribute__((packed));
+} __packed;
 
 /* Note: SDVO detailed timing flags match EDID misc flags. */
 #define DTD_FLAG_HSYNC_POSITIVE (1 << 1)
@@ -94,12 +94,12 @@ struct intel_sdvo_dtd {
 		u8 v_sync_off_high;
 		u8 reserved;
 	} part2;
-} __attribute__((packed));
+} __packed;
 
 struct intel_sdvo_pixel_clock_range {
 	u16 min;	/**< pixel clock, in 10kHz units */
 	u16 max;	/**< pixel clock, in 10kHz units */
-} __attribute__((packed));
+} __packed;
 
 struct intel_sdvo_preferred_input_timing_args {
 	u16 clock;
@@ -108,7 +108,7 @@ struct intel_sdvo_preferred_input_timing_args {
 	u8	interlace:1;
 	u8	scaled:1;
 	u8	pad:6;
-} __attribute__((packed));
+} __packed;
 
 /* I2C registers for SDVO */
 #define SDVO_I2C_ARG_0				0x07
@@ -162,7 +162,7 @@ struct intel_sdvo_get_trained_inputs_response {
 	unsigned int input0_trained:1;
 	unsigned int input1_trained:1;
 	unsigned int pad:6;
-} __attribute__((packed));
+} __packed;
 
 /** Returns a struct intel_sdvo_output_flags of active outputs. */
 #define SDVO_CMD_GET_ACTIVE_OUTPUTS			0x04
@@ -219,7 +219,7 @@ struct intel_sdvo_get_interrupt_event_source_response {
 	unsigned int ambient_light_interrupt:1;
 	unsigned int hdmi_audio_encrypt_change:1;
 	unsigned int pad:6;
-} __attribute__((packed));
+} __packed;
 
 /**
  * Selects which input is affected by future input commands.
@@ -232,7 +232,7 @@ struct intel_sdvo_get_interrupt_event_source_response {
 struct intel_sdvo_set_target_input_args {
 	unsigned int target_1:1;
 	unsigned int pad:7;
-} __attribute__((packed));
+} __packed;
 
 /**
  * Takes a struct intel_sdvo_output_flags of which outputs are targeted by
@@ -370,7 +370,7 @@ struct intel_sdvo_tv_format {
 	unsigned int hdtv_std_eia_7702a_480i_60:1;
 	unsigned int hdtv_std_eia_7702a_480p_60:1;
 	unsigned int pad:3;
-} __attribute__((packed));
+} __packed;
 
 #define SDVO_CMD_GET_TV_FORMAT				0x28
 
@@ -401,7 +401,7 @@ struct intel_sdvo_sdtv_resolution_request {
 	unsigned int secam_l:1;
 	unsigned int secam_60:1;
 	unsigned int pad:5;
-} __attribute__((packed));
+} __packed;
 
 struct intel_sdvo_sdtv_resolution_reply {
 	unsigned int res_320x200:1;
@@ -426,7 +426,7 @@ struct intel_sdvo_sdtv_resolution_reply {
 	unsigned int res_1024x768:1;
 	unsigned int res_1280x1024:1;
 	unsigned int pad:5;
-} __attribute__((packed));
+} __packed;
 
 /* Get supported resolution with squire pixel aspect ratio that can be
    scaled for the requested HDTV format */
@@ -463,7 +463,7 @@ struct intel_sdvo_hdtv_resolution_request {
 	unsigned int hdtv_std_eia_7702a_480i_60:1;
 	unsigned int hdtv_std_eia_7702a_480p_60:1;
 	unsigned int pad:6;
-} __attribute__((packed));
+} __packed;
 
 struct intel_sdvo_hdtv_resolution_reply {
 	unsigned int res_640x480:1;
@@ -517,7 +517,7 @@ struct intel_sdvo_hdtv_resolution_reply {
 
 	unsigned int res_1280x768:1;
 	unsigned int pad5:7;
-} __attribute__((packed));
+} __packed;
 
 /* Get supported power state returns info for encoder and monitor, rely on
    last SetTargetInput and SetTargetOutput calls */
@@ -557,13 +557,13 @@ struct sdvo_panel_power_sequencing {
 
 	unsigned int t4_high:2;
 	unsigned int pad:6;
-} __attribute__((packed));
+} __packed;
 
 #define SDVO_CMD_GET_MAX_BACKLIGHT_LEVEL		0x30
 struct sdvo_max_backlight_reply {
 	u8 max_value;
 	u8 default_value;
-} __attribute__((packed));
+} __packed;
 
 #define SDVO_CMD_GET_BACKLIGHT_LEVEL			0x31
 #define SDVO_CMD_SET_BACKLIGHT_LEVEL			0x32
@@ -573,14 +573,14 @@ struct sdvo_get_ambient_light_reply {
 	u16 trip_low;
 	u16 trip_high;
 	u16 value;
-} __attribute__((packed));
+} __packed;
 #define SDVO_CMD_SET_AMBIENT_LIGHT			0x34
 struct sdvo_set_ambient_light_reply {
 	u16 trip_low;
 	u16 trip_high;
 	unsigned int enable:1;
 	unsigned int pad:7;
-} __attribute__((packed));
+} __packed;
 
 /* Set display power state */
 #define SDVO_CMD_SET_DISPLAY_POWER_STATE		0x7d
@@ -608,7 +608,7 @@ struct intel_sdvo_enhancements_reply {
 	unsigned int dither:1;
 	unsigned int tv_chroma_filter:1;
 	unsigned int tv_luma_filter:1;
-} __attribute__((packed));
+} __packed;
 
 /* Picture enhancement limits below are dependent on the current TV format,
  * and thus need to be queried and set after it.
@@ -630,7 +630,7 @@ struct intel_sdvo_enhancements_reply {
 struct intel_sdvo_enhancement_limits_reply {
 	u16 max_value;
 	u16 default_value;
-} __attribute__((packed));
+} __packed;
 
 #define SDVO_CMD_GET_LVDS_PANEL_INFORMATION		0x7f
 #define SDVO_CMD_SET_LVDS_PANEL_INFORMATION		0x80
@@ -671,7 +671,7 @@ struct intel_sdvo_enhancement_limits_reply {
 #define SDVO_CMD_SET_TV_LUMA_FILTER			0x79
 struct intel_sdvo_enhancements_arg {
 	u16 value;
-} __attribute__((packed));
+} __packed;
 
 #define SDVO_CMD_GET_DOT_CRAWL				0x70
 #define SDVO_CMD_SET_DOT_CRAWL				0x71
@@ -727,4 +727,4 @@ struct intel_sdvo_enhancements_arg {
 struct intel_sdvo_encode {
 	u8 dvi_rev;
 	u8 hdmi_rev;
-} __attribute__ ((packed));
+} __packed;
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 9944d8135e87..0954f132726e 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -90,6 +90,22 @@ void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg)
+{
+	u32 val = 0;
+
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+			PUNIT_OPCODE_REG_READ, reg, &val);
+
+	return val;
+}
+
+void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
+{
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+			PUNIT_OPCODE_REG_WRITE, reg, &val);
+}
+
 u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 {
 	u32 val = 0;
@@ -160,27 +176,18 @@ void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 			PUNIT_OPCODE_REG_WRITE, reg, &val);
 }
 
-static u32 vlv_get_phy_port(enum pipe pipe)
-{
-	u32 port = IOSF_PORT_DPIO;
-
-	WARN_ON ((pipe != PIPE_A) && (pipe != PIPE_B));
-
-	return port;
-}
-
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg)
 {
 	u32 val = 0;
 
-	vlv_sideband_rw(dev_priv, DPIO_DEVFN, vlv_get_phy_port(pipe),
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)),
 			DPIO_OPCODE_REG_READ, reg, &val);
 	return val;
 }
 
 void vlv_dpio_write(struct drm_i915_private *dev_priv, enum pipe pipe, int reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, DPIO_DEVFN, vlv_get_phy_port(pipe),
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)),
 			DPIO_OPCODE_REG_WRITE, reg, &val);
 }
 
@@ -242,3 +249,17 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 		return;
 	}
 }
+
+u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg)
+{
+	u32 val = 0;
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI,
+					DPIO_OPCODE_REG_READ, reg, &val);
+	return val;
+}
+
+void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
+{
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI,
+					DPIO_OPCODE_REG_WRITE, reg, &val);
+}
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index b9fabf826f7d..716a3c9c0751 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -104,6 +104,12 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 		break;
 	}
 
+	/*
+	 * Enable gamma to match primary/cursor plane behaviour.
+	 * FIXME should be user controllable via propertiesa.
+	 */
+	sprctl |= SP_GAMMA_ENABLE;
+
 	if (obj->tiling_mode != I915_TILING_NONE)
 		sprctl |= SP_TILED;
 
@@ -135,8 +141,8 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
-			     sprsurf_offset);
+	I915_WRITE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
+		   sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
 
@@ -152,7 +158,7 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 	I915_WRITE(SPCNTR(pipe, plane), I915_READ(SPCNTR(pipe, plane)) &
 		   ~SP_ENABLE);
 	/* Activate double buffered register update */
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), 0);
+	I915_WRITE(SPSURF(pipe, plane), 0);
 	POSTING_READ(SPSURF(pipe, plane));
 
 	intel_update_sprite_watermarks(dplane, crtc, 0, 0, false, false);
@@ -224,7 +230,6 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	u32 sprctl, sprscale = 0;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
-	bool scaling_was_enabled = dev_priv->sprite_scaling_enabled;
 
 	sprctl = I915_READ(SPRCTL(pipe));
 
@@ -257,6 +262,12 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		BUG();
 	}
 
+	/*
+	 * Enable gamma to match primary/cursor plane behaviour.
+	 * FIXME should be user controllable via propertiesa.
+	 */
+	sprctl |= SPRITE_GAMMA_ENABLE;
+
 	if (obj->tiling_mode != I915_TILING_NONE)
 		sprctl |= SPRITE_TILED;
 
@@ -279,21 +290,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	crtc_w--;
 	crtc_h--;
 
-	/*
-	 * IVB workaround: must disable low power watermarks for at least
-	 * one frame before enabling scaling.  LP watermarks can be re-enabled
-	 * when scaling is disabled.
-	 */
-	if (crtc_w != src_w || crtc_h != src_h) {
-		dev_priv->sprite_scaling_enabled |= 1 << pipe;
-
-		if (!scaling_was_enabled) {
-			intel_update_watermarks(crtc);
-			intel_wait_for_vblank(dev, pipe);
-		}
+	if (crtc_w != src_w || crtc_h != src_h)
 		sprscale = SPRITE_SCALE_ENABLE | (src_w << 16) | src_h;
-	} else
-		dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
 
 	I915_WRITE(SPRSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(SPRPOS(pipe), (crtc_y << 16) | crtc_x);
@@ -317,13 +315,9 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
-	I915_MODIFY_DISPBASE(SPRSURF(pipe),
-			     i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
+	I915_WRITE(SPRSURF(pipe),
+		   i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
-
-	/* potentially re-enable LP watermarks */
-	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
-		intel_update_watermarks(crtc);
 }
 
 static void
@@ -333,23 +327,22 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	int pipe = intel_plane->pipe;
-	bool scaling_was_enabled = dev_priv->sprite_scaling_enabled;
 
 	I915_WRITE(SPRCTL(pipe), I915_READ(SPRCTL(pipe)) & ~SPRITE_ENABLE);
 	/* Can't leave the scaler enabled... */
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), 0);
 	/* Activate double buffered register update */
-	I915_MODIFY_DISPBASE(SPRSURF(pipe), 0);
+	I915_WRITE(SPRSURF(pipe), 0);
 	POSTING_READ(SPRSURF(pipe));
 
-	dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
+	/*
+	 * Avoid underruns when disabling the sprite.
+	 * FIXME remove once watermark updates are done properly.
+	 */
+	intel_wait_for_vblank(dev, pipe);
 
 	intel_update_sprite_watermarks(plane, crtc, 0, 0, false, false);
-
-	/* potentially re-enable LP watermarks */
-	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
-		intel_update_watermarks(crtc);
 }
 
 static int
@@ -453,6 +446,12 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		BUG();
 	}
 
+	/*
+	 * Enable gamma to match primary/cursor plane behaviour.
+	 * FIXME should be user controllable via propertiesa.
+	 */
+	dvscntr |= DVS_GAMMA_ENABLE;
+
 	if (obj->tiling_mode != I915_TILING_NONE)
 		dvscntr |= DVS_TILED;
 
@@ -470,7 +469,7 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	crtc_h--;
 
 	dvsscale = 0;
-	if (IS_GEN5(dev) || crtc_w != src_w || crtc_h != src_h)
+	if (crtc_w != src_w || crtc_h != src_h)
 		dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h;
 
 	I915_WRITE(DVSSTRIDE(pipe), fb->pitches[0]);
@@ -490,8 +489,8 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w);
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
-	I915_MODIFY_DISPBASE(DVSSURF(pipe),
-			     i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
+	I915_WRITE(DVSSURF(pipe),
+		   i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
@@ -507,9 +506,15 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	/* Disable the scaler */
 	I915_WRITE(DVSSCALE(pipe), 0);
 	/* Flush double buffered register updates */
-	I915_MODIFY_DISPBASE(DVSSURF(pipe), 0);
+	I915_WRITE(DVSSURF(pipe), 0);
 	POSTING_READ(DVSSURF(pipe));
 
+	/*
+	 * Avoid underruns when disabling the sprite.
+	 * FIXME remove once watermark updates are done properly.
+	 */
+	intel_wait_for_vblank(dev, pipe);
+
 	intel_update_sprite_watermarks(plane, crtc, 0, 0, false, false);
 }
 
@@ -643,6 +648,15 @@ format_is_yuv(uint32_t format)
 	}
 }
 
+static bool colorkey_enabled(struct intel_plane *intel_plane)
+{
+	struct drm_intel_sprite_colorkey key;
+
+	intel_plane->get_colorkey(&intel_plane->base, &key);
+
+	return key.flags != I915_SET_COLORKEY_NONE;
+}
+
 static int
 intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		   struct drm_framebuffer *fb, int crtc_x, int crtc_y,
@@ -828,7 +842,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	 * If the sprite is completely covering the primary plane,
 	 * we can disable the primary and save power.
 	 */
-	disable_primary = drm_rect_equals(&dst, &clip);
+	disable_primary = drm_rect_equals(&dst, &clip) && !colorkey_enabled(intel_plane);
 	WARN_ON(disable_primary && !visible && intel_crtc->active);
 
 	mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 25cbe073c388..87df68f5f504 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -64,7 +64,8 @@ static void __gen6_gt_force_wake_reset(struct drm_i915_private *dev_priv)
 	__raw_posting_read(dev_priv, ECOBUS);
 }
 
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv,
+							int fw_engine)
 {
 	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK) & 1) == 0,
 			    FORCEWAKE_ACK_TIMEOUT_MS))
@@ -89,7 +90,8 @@ static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
 	__raw_posting_read(dev_priv, ECOBUS);
 }
 
-static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv,
+							int fw_engine)
 {
 	u32 forcewake_ack;
 
@@ -121,12 +123,12 @@ static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
 	u32 gtfifodbg;
 
 	gtfifodbg = __raw_i915_read32(dev_priv, GTFIFODBG);
-	if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK,
-	     "MMIO read or write has been dropped %x\n", gtfifodbg))
-		__raw_i915_write32(dev_priv, GTFIFODBG, GT_FIFO_CPU_ERROR_MASK);
+	if (WARN(gtfifodbg, "GT wake FIFO error 0x%x\n", gtfifodbg))
+		__raw_i915_write32(dev_priv, GTFIFODBG, gtfifodbg);
 }
 
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv,
+							int fw_engine)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE, 0);
 	/* something from same cacheline, but !FORCEWAKE */
@@ -134,7 +136,8 @@ static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
-static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv,
+							int fw_engine)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE_MT,
 			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
@@ -147,12 +150,19 @@ static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
 {
 	int ret = 0;
 
+	/* On VLV, FIFO will be shared by both SW and HW.
+	 * So, we need to read the FREE_ENTRIES everytime */
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		dev_priv->uncore.fifo_count =
+			__raw_i915_read32(dev_priv, GTFIFOCTL) &
+						GT_FIFO_FREE_ENTRIES_MASK;
+
 	if (dev_priv->uncore.fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
 		int loop = 500;
-		u32 fifo = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+		u32 fifo = __raw_i915_read32(dev_priv, GTFIFOCTL) & GT_FIFO_FREE_ENTRIES_MASK;
 		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
 			udelay(10);
-			fifo = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+			fifo = __raw_i915_read32(dev_priv, GTFIFOCTL) & GT_FIFO_FREE_ENTRIES_MASK;
 		}
 		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
 			++ret;
@@ -171,38 +181,112 @@ static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
 	__raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
 }
 
-static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
+static void __vlv_force_wake_get(struct drm_i915_private *dev_priv,
+						int fw_engine)
 {
-	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+	/* Check for Render Engine */
+	if (FORCEWAKE_RENDER & fw_engine) {
+		if (wait_for_atomic((__raw_i915_read32(dev_priv,
+						FORCEWAKE_ACK_VLV) &
+						FORCEWAKE_KERNEL) == 0,
+					FORCEWAKE_ACK_TIMEOUT_MS))
+			DRM_ERROR("Timed out: Render forcewake old ack to clear.\n");
 
-	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
-			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+		__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
+				   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
 
-	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for GT to ack forcewake request.\n");
+		if (wait_for_atomic((__raw_i915_read32(dev_priv,
+						FORCEWAKE_ACK_VLV) &
+						FORCEWAKE_KERNEL),
+					FORCEWAKE_ACK_TIMEOUT_MS))
+			DRM_ERROR("Timed out: waiting for Render to ack.\n");
+	}
 
-	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_MEDIA_VLV) &
-			     FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for media to ack forcewake request.\n");
+	/* Check for Media Engine */
+	if (FORCEWAKE_MEDIA & fw_engine) {
+		if (wait_for_atomic((__raw_i915_read32(dev_priv,
+						FORCEWAKE_ACK_MEDIA_VLV) &
+						FORCEWAKE_KERNEL) == 0,
+					FORCEWAKE_ACK_TIMEOUT_MS))
+			DRM_ERROR("Timed out: Media forcewake old ack to clear.\n");
+
+		__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+				   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+
+		if (wait_for_atomic((__raw_i915_read32(dev_priv,
+						FORCEWAKE_ACK_MEDIA_VLV) &
+						FORCEWAKE_KERNEL),
+					FORCEWAKE_ACK_TIMEOUT_MS))
+			DRM_ERROR("Timed out: waiting for media to ack.\n");
+	}
 
 	/* WaRsForcewakeWaitTC0:vlv */
 	__gen6_gt_wait_for_thread_c0(dev_priv);
+
 }
 
-static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
+static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
+					int fw_engine)
 {
-	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
-			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+
+	/* Check for Render Engine */
+	if (FORCEWAKE_RENDER & fw_engine)
+		__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
+					_MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+
+
+	/* Check for Media Engine */
+	if (FORCEWAKE_MEDIA & fw_engine)
+		__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+				_MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+
 	/* The below doubles as a POSTING_READ */
 	gen6_gt_check_fifodbg(dev_priv);
+
+}
+
+void vlv_force_wake_get(struct drm_i915_private *dev_priv,
+						int fw_engine)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (FORCEWAKE_RENDER & fw_engine) {
+		if (dev_priv->uncore.fw_rendercount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							FORCEWAKE_RENDER);
+	}
+	if (FORCEWAKE_MEDIA & fw_engine) {
+		if (dev_priv->uncore.fw_mediacount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							FORCEWAKE_MEDIA);
+	}
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+void vlv_force_wake_put(struct drm_i915_private *dev_priv,
+						int fw_engine)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+
+	if (FORCEWAKE_RENDER & fw_engine) {
+		WARN_ON(dev_priv->uncore.fw_rendercount == 0);
+		if (--dev_priv->uncore.fw_rendercount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							FORCEWAKE_RENDER);
+	}
+
+	if (FORCEWAKE_MEDIA & fw_engine) {
+		WARN_ON(dev_priv->uncore.fw_mediacount == 0);
+		if (--dev_priv->uncore.fw_mediacount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							FORCEWAKE_MEDIA);
+	}
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
 static void gen6_force_wake_work(struct work_struct *work)
@@ -213,7 +297,7 @@ static void gen6_force_wake_work(struct work_struct *work)
 
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 	if (--dev_priv->uncore.forcewake_count == 0)
-		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
@@ -248,6 +332,11 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 		DRM_INFO("Found %zuMB of eLLC\n", dev_priv->ellc_size);
 	}
 
+	/* clear out old GT FIFO errors */
+	if (IS_GEN6(dev) || IS_GEN7(dev))
+		__raw_i915_write32(dev_priv, GTFIFODBG,
+				   __raw_i915_read32(dev_priv, GTFIFODBG));
+
 	intel_uncore_forcewake_reset(dev);
 }
 
@@ -256,8 +345,6 @@ void intel_uncore_sanitize(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg_val;
 
-	intel_uncore_forcewake_reset(dev);
-
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
 	intel_disable_gt_powersave(dev);
 
@@ -281,29 +368,40 @@ void intel_uncore_sanitize(struct drm_device *dev)
  * be called at the beginning of the sequence followed by a call to
  * gen6_gt_force_wake_put() at the end of the sequence.
  */
-void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
 {
 	unsigned long irqflags;
 
 	if (!dev_priv->uncore.funcs.force_wake_get)
 		return;
 
+	intel_runtime_pm_get(dev_priv);
+
+	/* Redirect to VLV specific routine */
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		return vlv_force_wake_get(dev_priv, fw_engine);
+
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 	if (dev_priv->uncore.forcewake_count++ == 0)
-		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
 /*
  * see gen6_gt_force_wake_get()
  */
-void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
 {
 	unsigned long irqflags;
 
 	if (!dev_priv->uncore.funcs.force_wake_put)
 		return;
 
+	/* Redirect to VLV specific routine */
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		return vlv_force_wake_put(dev_priv, fw_engine);
+
+
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 	if (--dev_priv->uncore.forcewake_count == 0) {
 		dev_priv->uncore.forcewake_count++;
@@ -312,6 +410,8 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 				 1);
 	}
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 /* We give fast paths for the really cool registers */
@@ -346,6 +446,13 @@ hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
 	}
 }
 
+static void
+assert_device_not_suspended(struct drm_i915_private *dev_priv)
+{
+	WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
+	     "Device suspended\n");
+}
+
 #define REG_READ_HEADER(x) \
 	unsigned long irqflags; \
 	u##x val = 0; \
@@ -379,16 +486,51 @@ gen6_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	REG_READ_HEADER(x); \
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		if (dev_priv->uncore.forcewake_count == 0) \
-			dev_priv->uncore.funcs.force_wake_get(dev_priv); \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv, \
+							FORCEWAKE_ALL); \
 		val = __raw_i915_read##x(dev_priv, reg); \
 		if (dev_priv->uncore.forcewake_count == 0) \
-			dev_priv->uncore.funcs.force_wake_put(dev_priv); \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv, \
+							FORCEWAKE_ALL); \
 	} else { \
 		val = __raw_i915_read##x(dev_priv, reg); \
 	} \
 	REG_READ_FOOTER; \
 }
 
+#define __vlv_read(x) \
+static u##x \
+vlv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
+	unsigned fwengine = 0; \
+	unsigned *fwcount; \
+	REG_READ_HEADER(x); \
+	if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg)) {   \
+		fwengine = FORCEWAKE_RENDER;            \
+		fwcount = &dev_priv->uncore.fw_rendercount;    \
+	}                                               \
+	else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)) {       \
+		fwengine = FORCEWAKE_MEDIA;             \
+		fwcount = &dev_priv->uncore.fw_mediacount;     \
+	}  \
+	if (fwengine != 0) {		\
+		if ((*fwcount)++ == 0) \
+			(dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
+								fwengine); \
+		val = __raw_i915_read##x(dev_priv, reg); \
+		if (--(*fwcount) == 0) \
+			(dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
+							fwengine); \
+	} else { \
+		val = __raw_i915_read##x(dev_priv, reg); \
+	} \
+	REG_READ_FOOTER; \
+}
+
+
+__vlv_read(8)
+__vlv_read(16)
+__vlv_read(32)
+__vlv_read(64)
 __gen6_read(8)
 __gen6_read(16)
 __gen6_read(32)
@@ -402,6 +544,7 @@ __gen4_read(16)
 __gen4_read(32)
 __gen4_read(64)
 
+#undef __vlv_read
 #undef __gen6_read
 #undef __gen5_read
 #undef __gen4_read
@@ -413,12 +556,15 @@ __gen4_read(64)
 	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags)
 
+#define REG_WRITE_FOOTER \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags)
+
 #define __gen4_write(x) \
 static void \
 gen4_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
 	REG_WRITE_HEADER; \
 	__raw_i915_write##x(dev_priv, reg, val); \
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	REG_WRITE_FOOTER; \
 }
 
 #define __gen5_write(x) \
@@ -427,7 +573,7 @@ gen5_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
 	REG_WRITE_HEADER; \
 	ilk_dummy_write(dev_priv); \
 	__raw_i915_write##x(dev_priv, reg, val); \
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	REG_WRITE_FOOTER; \
 }
 
 #define __gen6_write(x) \
@@ -438,11 +584,12 @@ gen6_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
+	assert_device_not_suspended(dev_priv); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (unlikely(__fifo_ret)) { \
 		gen6_gt_check_fifodbg(dev_priv); \
 	} \
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	REG_WRITE_FOOTER; \
 }
 
 #define __hsw_write(x) \
@@ -453,13 +600,14 @@ hsw_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace)
 	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
 		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
 	} \
+	assert_device_not_suspended(dev_priv); \
 	hsw_unclaimed_reg_clear(dev_priv, reg); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (unlikely(__fifo_ret)) { \
 		gen6_gt_check_fifodbg(dev_priv); \
 	} \
 	hsw_unclaimed_reg_check(dev_priv, reg); \
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	REG_WRITE_FOOTER; \
 }
 
 static const u32 gen8_shadowed_regs[] = {
@@ -486,16 +634,18 @@ static bool is_gen8_shadowed(struct drm_i915_private *dev_priv, u32 reg)
 #define __gen8_write(x) \
 static void \
 gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
-	bool __needs_put = !is_gen8_shadowed(dev_priv, reg); \
+	bool __needs_put = reg < 0x40000 && !is_gen8_shadowed(dev_priv, reg); \
 	REG_WRITE_HEADER; \
 	if (__needs_put) { \
-		dev_priv->uncore.funcs.force_wake_get(dev_priv); \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, \
+							FORCEWAKE_ALL); \
 	} \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	if (__needs_put) { \
-		dev_priv->uncore.funcs.force_wake_put(dev_priv); \
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, \
+							FORCEWAKE_ALL); \
 	} \
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	REG_WRITE_FOOTER; \
 }
 
 __gen8_write(8)
@@ -524,6 +674,7 @@ __gen4_write(64)
 #undef __gen6_write
 #undef __gen5_write
 #undef __gen4_write
+#undef REG_WRITE_FOOTER
 #undef REG_WRITE_HEADER
 
 void intel_uncore_init(struct drm_device *dev)
@@ -534,8 +685,8 @@ void intel_uncore_init(struct drm_device *dev)
 			  gen6_force_wake_work);
 
 	if (IS_VALLEYVIEW(dev)) {
-		dev_priv->uncore.funcs.force_wake_get = vlv_force_wake_get;
-		dev_priv->uncore.funcs.force_wake_put = vlv_force_wake_put;
+		dev_priv->uncore.funcs.force_wake_get = __vlv_force_wake_get;
+		dev_priv->uncore.funcs.force_wake_put = __vlv_force_wake_put;
 	} else if (IS_HASWELL(dev) || IS_GEN8(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __gen6_gt_force_wake_mt_get;
 		dev_priv->uncore.funcs.force_wake_put = __gen6_gt_force_wake_mt_put;
@@ -552,9 +703,9 @@ void intel_uncore_init(struct drm_device *dev)
 		 * forcewake being disabled.
 		 */
 		mutex_lock(&dev->struct_mutex);
-		__gen6_gt_force_wake_mt_get(dev_priv);
+		__gen6_gt_force_wake_mt_get(dev_priv, FORCEWAKE_ALL);
 		ecobus = __raw_i915_read32(dev_priv, ECOBUS);
-		__gen6_gt_force_wake_mt_put(dev_priv);
+		__gen6_gt_force_wake_mt_put(dev_priv, FORCEWAKE_ALL);
 		mutex_unlock(&dev->struct_mutex);
 
 		if (ecobus & FORCEWAKE_MT_ENABLE) {
@@ -601,10 +752,18 @@ void intel_uncore_init(struct drm_device *dev)
 			dev_priv->uncore.funcs.mmio_writel  = gen6_write32;
 			dev_priv->uncore.funcs.mmio_writeq  = gen6_write64;
 		}
-		dev_priv->uncore.funcs.mmio_readb  = gen6_read8;
-		dev_priv->uncore.funcs.mmio_readw  = gen6_read16;
-		dev_priv->uncore.funcs.mmio_readl  = gen6_read32;
-		dev_priv->uncore.funcs.mmio_readq  = gen6_read64;
+
+		if (IS_VALLEYVIEW(dev)) {
+			dev_priv->uncore.funcs.mmio_readb  = vlv_read8;
+			dev_priv->uncore.funcs.mmio_readw  = vlv_read16;
+			dev_priv->uncore.funcs.mmio_readl  = vlv_read32;
+			dev_priv->uncore.funcs.mmio_readq  = vlv_read64;
+		} else {
+			dev_priv->uncore.funcs.mmio_readb  = gen6_read8;
+			dev_priv->uncore.funcs.mmio_readw  = gen6_read16;
+			dev_priv->uncore.funcs.mmio_readl  = gen6_read32;
+			dev_priv->uncore.funcs.mmio_readq  = gen6_read64;
+		}
 		break;
 	case 5:
 		dev_priv->uncore.funcs.mmio_writeb  = gen5_write8;
@@ -646,7 +805,7 @@ static const struct register_whitelist {
 	uint32_t size;
 	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
 } whitelist[] = {
-	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
+	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0x1F0 },
 };
 
 int i915_reg_read_ioctl(struct drm_device *dev,
@@ -687,6 +846,43 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	return 0;
 }
 
+int i915_get_reset_stats_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_reset_stats *args = data;
+	struct i915_ctx_hang_stats *hs;
+	int ret;
+
+	if (args->flags || args->pad)
+		return -EINVAL;
+
+	if (args->ctx_id == DEFAULT_CONTEXT_ID && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	hs = i915_gem_context_get_hang_stats(dev, file, args->ctx_id);
+	if (IS_ERR(hs)) {
+		mutex_unlock(&dev->struct_mutex);
+		return PTR_ERR(hs);
+	}
+
+	if (capable(CAP_SYS_ADMIN))
+		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
+	else
+		args->reset_count = 0;
+
+	args->batch_active = hs->batch_active;
+	args->batch_pending = hs->batch_pending;
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
 static int i965_reset_complete(struct drm_device *dev)
 {
 	u8 gdrst;
@@ -770,12 +966,12 @@ static int gen6_do_reset(struct drm_device *dev)
 
 	/* If reset with a user forcewake, try to restore, otherwise turn it off */
 	if (dev_priv->uncore.forcewake_count)
-		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
 	else
-		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
 
 	/* Restore fifo count */
-	dev_priv->uncore.fifo_count = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+	dev_priv->uncore.fifo_count = __raw_i915_read32(dev_priv, GTFIFOCTL) & GT_FIFO_FREE_ENTRIES_MASK;
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 	return ret;
@@ -793,15 +989,6 @@ int intel_gpu_reset(struct drm_device *dev)
 	}
 }
 
-void intel_uncore_clear_errors(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	/* XXX needs spinlock around caller's grouping */
-	if (HAS_FPGA_DBG_UNCLAIMED(dev))
-		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-}
-
 void intel_uncore_check_errors(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;