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

Pull drm merge (part 1) from Dave Airlie:
 "So first of all my tree and uapi stuff has a conflict mess, its my
  fault as the nouveau stuff didn't hit -next as were trying to rebase
  regressions out of it before we merged.

  Highlights:
   - SH mobile modesetting driver and associated helpers
   - some DRM core documentation
   - i915 modesetting rework, haswell hdmi, haswell and vlv fixes, write
     combined pte writing, ilk rc6 support,
   - nouveau: major driver rework into a hw core driver, makes features
     like SLI a lot saner to implement,
   - psb: add eDP/DP support for Cedarview
   - radeon: 2 layer page tables, async VM pte updates, better PLL
     selection for > 2 screens, better ACPI interactions

  The rest is general grab bag of fixes.

  So why part 1? well I have the exynos pull req which came in a bit
  late but was waiting for me to do something they shouldn't have and it
  looks fairly safe, and David Howells has some more header cleanups
  he'd like me to pull, that seem like a good idea, but I'd like to get
  this merge out of the way so -next dosen't get blocked."

Tons of conflicts mostly due to silly include line changes, but mostly
mindless.  A few other small semantic conflicts too, noted from Dave's
pre-merged branch.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (447 commits)
  drm/nv98/crypt: fix fuc build with latest envyas
  drm/nouveau/devinit: fixup various issues with subdev ctor/init ordering
  drm/nv41/vm: fix and enable use of "real" pciegart
  drm/nv44/vm: fix and enable use of "real" pciegart
  drm/nv04/dmaobj: fixup vm target handling in preparation for nv4x pcie
  drm/nouveau: store supported dma mask in vmmgr
  drm/nvc0/ibus: initial implementation of subdev
  drm/nouveau/therm: add support for fan-control modes
  drm/nouveau/hwmon: rename pwm0* to pmw1* to follow hwmon's rules
  drm/nouveau/therm: calculate the pwm divisor on nv50+
  drm/nouveau/fan: rewrite the fan tachometer driver to get more precision, faster
  drm/nouveau/therm: move thermal-related functions to the therm subdev
  drm/nouveau/bios: parse the pwm divisor from the perf table
  drm/nouveau/therm: use the EXTDEV table to detect i2c monitoring devices
  drm/nouveau/therm: rework thermal table parsing
  drm/nouveau/gpio: expose the PWM/TOGGLE parameter found in the gpio vbios table
  drm/nouveau: fix pm initialization order
  drm/nouveau/bios: check that fixed tvdac gpio data is valid before using it
  drm/nouveau: log channel debug/error messages from client object rather than drm client
  drm/nouveau: have drm debugging macros build on top of core macros
  ...

1 files changed, 236 insertions, 184 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ba8a27b1757a..d69f8f49beb5 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -31,6 +31,8 @@
 #include "../../../platform/x86/intel_ips.h"
 #include <linux/module.h>
 
+#define FORCEWAKE_ACK_TIMEOUT_MS 2
+
 /* FBC, or Frame Buffer Compression, is a technique employed to compress the
  * framebuffer contents in-memory, aiming at reducing the required bandwidth
  * during in-memory transfers and, therefore, reduce the power packet.
@@ -593,7 +595,7 @@ static void i915_ironlake_get_mem_freq(struct drm_device *dev)
 		break;
 	}
 
-	dev_priv->r_t = dev_priv->mem_freq;
+	dev_priv->ips.r_t = dev_priv->mem_freq;
 
 	switch (csipll & 0x3ff) {
 	case 0x00c:
@@ -625,11 +627,11 @@ static void i915_ironlake_get_mem_freq(struct drm_device *dev)
 	}
 
 	if (dev_priv->fsb_freq == 3200) {
-		dev_priv->c_m = 0;
+		dev_priv->ips.c_m = 0;
 	} else if (dev_priv->fsb_freq > 3200 && dev_priv->fsb_freq <= 4800) {
-		dev_priv->c_m = 1;
+		dev_priv->ips.c_m = 1;
 	} else {
-		dev_priv->c_m = 2;
+		dev_priv->ips.c_m = 2;
 	}
 }
 
@@ -2138,7 +2140,7 @@ intel_alloc_context_page(struct drm_device *dev)
 		return NULL;
 	}
 
-	ret = i915_gem_object_pin(ctx, 4096, true);
+	ret = i915_gem_object_pin(ctx, 4096, true, false);
 	if (ret) {
 		DRM_ERROR("failed to pin power context: %d\n", ret);
 		goto err_unref;
@@ -2160,11 +2162,22 @@ err_unref:
 	return NULL;
 }
 
+/**
+ * Lock protecting IPS related data structures
+ */
+DEFINE_SPINLOCK(mchdev_lock);
+
+/* Global for IPS driver to get at the current i915 device. Protected by
+ * mchdev_lock. */
+static struct drm_i915_private *i915_mch_dev;
+
 bool ironlake_set_drps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 rgvswctl;
 
+	assert_spin_locked(&mchdev_lock);
+
 	rgvswctl = I915_READ16(MEMSWCTL);
 	if (rgvswctl & MEMCTL_CMD_STS) {
 		DRM_DEBUG("gpu busy, RCS change rejected\n");
@@ -2188,6 +2201,8 @@ static void ironlake_enable_drps(struct drm_device *dev)
 	u32 rgvmodectl = I915_READ(MEMMODECTL);
 	u8 fmax, fmin, fstart, vstart;
 
+	spin_lock_irq(&mchdev_lock);
+
 	/* Enable temp reporting */
 	I915_WRITE16(PMMISC, I915_READ(PMMISC) | MCPPCE_EN);
 	I915_WRITE16(TSC1, I915_READ(TSC1) | TSE);
@@ -2211,12 +2226,12 @@ static void ironlake_enable_drps(struct drm_device *dev)
 	vstart = (I915_READ(PXVFREQ_BASE + (fstart * 4)) & PXVFREQ_PX_MASK) >>
 		PXVFREQ_PX_SHIFT;
 
-	dev_priv->fmax = fmax; /* IPS callback will increase this */
-	dev_priv->fstart = fstart;
+	dev_priv->ips.fmax = fmax; /* IPS callback will increase this */
+	dev_priv->ips.fstart = fstart;
 
-	dev_priv->max_delay = fstart;
-	dev_priv->min_delay = fmin;
-	dev_priv->cur_delay = fstart;
+	dev_priv->ips.max_delay = fstart;
+	dev_priv->ips.min_delay = fmin;
+	dev_priv->ips.cur_delay = fstart;
 
 	DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n",
 			 fmax, fmin, fstart);
@@ -2233,23 +2248,29 @@ static void ironlake_enable_drps(struct drm_device *dev)
 	rgvmodectl |= MEMMODE_SWMODE_EN;
 	I915_WRITE(MEMMODECTL, rgvmodectl);
 
-	if (wait_for((I915_READ(MEMSWCTL) & MEMCTL_CMD_STS) == 0, 10))
+	if (wait_for_atomic((I915_READ(MEMSWCTL) & MEMCTL_CMD_STS) == 0, 10))
 		DRM_ERROR("stuck trying to change perf mode\n");
-	msleep(1);
+	mdelay(1);
 
 	ironlake_set_drps(dev, fstart);
 
-	dev_priv->last_count1 = I915_READ(0x112e4) + I915_READ(0x112e8) +
+	dev_priv->ips.last_count1 = I915_READ(0x112e4) + I915_READ(0x112e8) +
 		I915_READ(0x112e0);
-	dev_priv->last_time1 = jiffies_to_msecs(jiffies);
-	dev_priv->last_count2 = I915_READ(0x112f4);
-	getrawmonotonic(&dev_priv->last_time2);
+	dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies);
+	dev_priv->ips.last_count2 = I915_READ(0x112f4);
+	getrawmonotonic(&dev_priv->ips.last_time2);
+
+	spin_unlock_irq(&mchdev_lock);
 }
 
 static void ironlake_disable_drps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u16 rgvswctl = I915_READ16(MEMSWCTL);
+	u16 rgvswctl;
+
+	spin_lock_irq(&mchdev_lock);
+
+	rgvswctl = I915_READ16(MEMSWCTL);
 
 	/* Ack interrupts, disable EFC interrupt */
 	I915_WRITE(MEMINTREN, I915_READ(MEMINTREN) & ~MEMINT_EVAL_CHG_EN);
@@ -2259,31 +2280,54 @@ static void ironlake_disable_drps(struct drm_device *dev)
 	I915_WRITE(DEIMR, I915_READ(DEIMR) | DE_PCU_EVENT);
 
 	/* Go back to the starting frequency */
-	ironlake_set_drps(dev, dev_priv->fstart);
-	msleep(1);
+	ironlake_set_drps(dev, dev_priv->ips.fstart);
+	mdelay(1);
 	rgvswctl |= MEMCTL_CMD_STS;
 	I915_WRITE(MEMSWCTL, rgvswctl);
-	msleep(1);
+	mdelay(1);
 
+	spin_unlock_irq(&mchdev_lock);
 }
 
-void gen6_set_rps(struct drm_device *dev, u8 val)
+/* There's a funny hw issue where the hw returns all 0 when reading from
+ * GEN6_RP_INTERRUPT_LIMITS. Hence we always need to compute the desired value
+ * 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)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 limits;
 
 	limits = 0;
-	if (val >= dev_priv->max_delay)
-		val = dev_priv->max_delay;
-	else
-		limits |= dev_priv->max_delay << 24;
 
-	if (val <= dev_priv->min_delay)
-		val = dev_priv->min_delay;
-	else
-		limits |= dev_priv->min_delay << 16;
+	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.min_delay << 16;
+	}
 
-	if (val == dev_priv->cur_delay)
+	return limits;
+}
+
+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->struct_mutex));
+	WARN_ON(val > dev_priv->rps.max_delay);
+	WARN_ON(val < dev_priv->rps.min_delay);
+
+	if (val == dev_priv->rps.cur_delay)
 		return;
 
 	I915_WRITE(GEN6_RPNSWREQ,
@@ -2296,7 +2340,11 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	 */
 	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
 
-	dev_priv->cur_delay = val;
+	POSTING_READ(GEN6_RPNSWREQ);
+
+	dev_priv->rps.cur_delay = val;
+
+	trace_intel_gpu_freq_change(val * 50);
 }
 
 static void gen6_disable_rps(struct drm_device *dev)
@@ -2312,40 +2360,40 @@ static void gen6_disable_rps(struct drm_device *dev)
 	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
 	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
 
-	spin_lock_irq(&dev_priv->rps_lock);
-	dev_priv->pm_iir = 0;
-	spin_unlock_irq(&dev_priv->rps_lock);
+	spin_lock_irq(&dev_priv->rps.lock);
+	dev_priv->rps.pm_iir = 0;
+	spin_unlock_irq(&dev_priv->rps.lock);
 
 	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
 }
 
 int intel_enable_rc6(const struct drm_device *dev)
 {
-	/*
-	 * Respect the kernel parameter if it is set
-	 */
+	/* Respect the kernel parameter if it is set */
 	if (i915_enable_rc6 >= 0)
 		return i915_enable_rc6;
 
-	/*
-	 * Disable RC6 on Ironlake
-	 */
-	if (INTEL_INFO(dev)->gen == 5)
-		return 0;
+	if (INTEL_INFO(dev)->gen == 5) {
+#ifdef CONFIG_INTEL_IOMMU
+		/* Disable rc6 on ilk if VT-d is on. */
+		if (intel_iommu_gfx_mapped)
+			return false;
+#endif
+		DRM_DEBUG_DRIVER("Ironlake: only RC6 available\n");
+		return INTEL_RC6_ENABLE;
+	}
 
-	/* On Haswell, only RC6 is available. So let's enable it by default to
-	 * provide better testing and coverage since the beginning.
-	 */
-	if (IS_HASWELL(dev))
+	if (IS_HASWELL(dev)) {
+		DRM_DEBUG_DRIVER("Haswell: only RC6 available\n");
 		return INTEL_RC6_ENABLE;
+	}
 
-	/*
-	 * Disable rc6 on Sandybridge
-	 */
+	/* snb/ivb have more than one rc6 state. */
 	if (INTEL_INFO(dev)->gen == 6) {
 		DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n");
 		return INTEL_RC6_ENABLE;
 	}
+
 	DRM_DEBUG_DRIVER("RC6 and deep RC6 enabled\n");
 	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 }
@@ -2383,9 +2431,9 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
 	/* In units of 100MHz */
-	dev_priv->max_delay = rp_state_cap & 0xff;
-	dev_priv->min_delay = (rp_state_cap & 0xff0000) >> 16;
-	dev_priv->cur_delay = 0;
+	dev_priv->rps.max_delay = rp_state_cap & 0xff;
+	dev_priv->rps.min_delay = (rp_state_cap & 0xff0000) >> 16;
+	dev_priv->rps.cur_delay = 0;
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -2438,8 +2486,8 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
 	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-		   dev_priv->max_delay << 24 |
-		   dev_priv->min_delay << 16);
+		   dev_priv->rps.max_delay << 24 |
+		   dev_priv->rps.min_delay << 16);
 
 	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
@@ -2477,7 +2525,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 		     500))
 		DRM_ERROR("timeout waiting for pcode mailbox to finish\n");
 	if (pcu_mbox & (1<<31)) { /* OC supported */
-		dev_priv->max_delay = pcu_mbox & 0xff;
+		dev_priv->rps.max_delay = pcu_mbox & 0xff;
 		DRM_DEBUG_DRIVER("overclocking supported, adjusting frequency max to %dMHz\n", pcu_mbox * 50);
 	}
 
@@ -2485,10 +2533,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	/* requires MSI enabled */
 	I915_WRITE(GEN6_PMIER, GEN6_PM_DEFERRED_EVENTS);
-	spin_lock_irq(&dev_priv->rps_lock);
-	WARN_ON(dev_priv->pm_iir != 0);
+	spin_lock_irq(&dev_priv->rps.lock);
+	WARN_ON(dev_priv->rps.pm_iir != 0);
 	I915_WRITE(GEN6_PMIMR, 0);
-	spin_unlock_irq(&dev_priv->rps_lock);
+	spin_unlock_irq(&dev_priv->rps.lock);
 	/* enable all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
@@ -2520,9 +2568,9 @@ static void gen6_update_ring_freq(struct drm_device *dev)
 	 * to use for memory access.  We do this by specifying the IA frequency
 	 * the PCU should use as a reference to determine the ring frequency.
 	 */
-	for (gpu_freq = dev_priv->max_delay; gpu_freq >= dev_priv->min_delay;
+	for (gpu_freq = dev_priv->rps.max_delay; gpu_freq >= dev_priv->rps.min_delay;
 	     gpu_freq--) {
-		int diff = dev_priv->max_delay - gpu_freq;
+		int diff = dev_priv->rps.max_delay - gpu_freq;
 
 		/*
 		 * For GPU frequencies less than 750MHz, just use the lowest
@@ -2686,14 +2734,16 @@ static const struct cparams {
 	{ 0, 800, 231, 23784 },
 };
 
-unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
+static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv)
 {
 	u64 total_count, diff, ret;
 	u32 count1, count2, count3, m = 0, c = 0;
 	unsigned long now = jiffies_to_msecs(jiffies), diff1;
 	int i;
 
-	diff1 = now - dev_priv->last_time1;
+	assert_spin_locked(&mchdev_lock);
+
+	diff1 = now - dev_priv->ips.last_time1;
 
 	/* Prevent division-by-zero if we are asking too fast.
 	 * Also, we don't get interesting results if we are polling
@@ -2701,7 +2751,7 @@ unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 	 * in such cases.
 	 */
 	if (diff1 <= 10)
-		return dev_priv->chipset_power;
+		return dev_priv->ips.chipset_power;
 
 	count1 = I915_READ(DMIEC);
 	count2 = I915_READ(DDREC);
@@ -2710,16 +2760,16 @@ unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 	total_count = count1 + count2 + count3;
 
 	/* FIXME: handle per-counter overflow */
-	if (total_count < dev_priv->last_count1) {
-		diff = ~0UL - dev_priv->last_count1;
+	if (total_count < dev_priv->ips.last_count1) {
+		diff = ~0UL - dev_priv->ips.last_count1;
 		diff += total_count;
 	} else {
-		diff = total_count - dev_priv->last_count1;
+		diff = total_count - dev_priv->ips.last_count1;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(cparams); i++) {
-		if (cparams[i].i == dev_priv->c_m &&
-		    cparams[i].t == dev_priv->r_t) {
+		if (cparams[i].i == dev_priv->ips.c_m &&
+		    cparams[i].t == dev_priv->ips.r_t) {
 			m = cparams[i].m;
 			c = cparams[i].c;
 			break;
@@ -2730,14 +2780,30 @@ unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 	ret = ((m * diff) + c);
 	ret = div_u64(ret, 10);
 
-	dev_priv->last_count1 = total_count;
-	dev_priv->last_time1 = now;
+	dev_priv->ips.last_count1 = total_count;
+	dev_priv->ips.last_time1 = now;
 
-	dev_priv->chipset_power = ret;
+	dev_priv->ips.chipset_power = ret;
 
 	return ret;
 }
 
+unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
+{
+	unsigned long val;
+
+	if (dev_priv->info->gen != 5)
+		return 0;
+
+	spin_lock_irq(&mchdev_lock);
+
+	val = __i915_chipset_val(dev_priv);
+
+	spin_unlock_irq(&mchdev_lock);
+
+	return val;
+}
+
 unsigned long i915_mch_val(struct drm_i915_private *dev_priv)
 {
 	unsigned long m, x, b;
@@ -2894,18 +2960,17 @@ static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
 		return v_table[pxvid].vd;
 }
 
-void i915_update_gfx_val(struct drm_i915_private *dev_priv)
+static void __i915_update_gfx_val(struct drm_i915_private *dev_priv)
 {
 	struct timespec now, diff1;
 	u64 diff;
 	unsigned long diffms;
 	u32 count;
 
-	if (dev_priv->info->gen != 5)
-		return;
+	assert_spin_locked(&mchdev_lock);
 
 	getrawmonotonic(&now);
-	diff1 = timespec_sub(now, dev_priv->last_time2);
+	diff1 = timespec_sub(now, dev_priv->ips.last_time2);
 
 	/* Don't divide by 0 */
 	diffms = diff1.tv_sec * 1000 + diff1.tv_nsec / 1000000;
@@ -2914,28 +2979,42 @@ void i915_update_gfx_val(struct drm_i915_private *dev_priv)
 
 	count = I915_READ(GFXEC);
 
-	if (count < dev_priv->last_count2) {
-		diff = ~0UL - dev_priv->last_count2;
+	if (count < dev_priv->ips.last_count2) {
+		diff = ~0UL - dev_priv->ips.last_count2;
 		diff += count;
 	} else {
-		diff = count - dev_priv->last_count2;
+		diff = count - dev_priv->ips.last_count2;
 	}
 
-	dev_priv->last_count2 = count;
-	dev_priv->last_time2 = now;
+	dev_priv->ips.last_count2 = count;
+	dev_priv->ips.last_time2 = now;
 
 	/* More magic constants... */
 	diff = diff * 1181;
 	diff = div_u64(diff, diffms * 10);
-	dev_priv->gfx_power = diff;
+	dev_priv->ips.gfx_power = diff;
 }
 
-unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
+void i915_update_gfx_val(struct drm_i915_private *dev_priv)
+{
+	if (dev_priv->info->gen != 5)
+		return;
+
+	spin_lock_irq(&mchdev_lock);
+
+	__i915_update_gfx_val(dev_priv);
+
+	spin_unlock_irq(&mchdev_lock);
+}
+
+static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
 {
 	unsigned long t, corr, state1, corr2, state2;
 	u32 pxvid, ext_v;
 
-	pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->cur_delay * 4));
+	assert_spin_locked(&mchdev_lock);
+
+	pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_delay * 4));
 	pxvid = (pxvid >> 24) & 0x7f;
 	ext_v = pvid_to_extvid(dev_priv, pxvid);
 
@@ -2955,27 +3034,31 @@ unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
 
 	corr = corr * ((150142 * state1) / 10000 - 78642);
 	corr /= 100000;
-	corr2 = (corr * dev_priv->corr);
+	corr2 = (corr * dev_priv->ips.corr);
 
 	state2 = (corr2 * state1) / 10000;
 	state2 /= 100; /* convert to mW */
 
-	i915_update_gfx_val(dev_priv);
+	__i915_update_gfx_val(dev_priv);
 
-	return dev_priv->gfx_power + state2;
+	return dev_priv->ips.gfx_power + state2;
 }
 
-/* Global for IPS driver to get at the current i915 device */
-static struct drm_i915_private *i915_mch_dev;
-/*
- * Lock protecting IPS related data structures
- *   - i915_mch_dev
- *   - dev_priv->max_delay
- *   - dev_priv->min_delay
- *   - dev_priv->fmax
- *   - dev_priv->gpu_busy
- */
-static DEFINE_SPINLOCK(mchdev_lock);
+unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
+{
+	unsigned long val;
+
+	if (dev_priv->info->gen != 5)
+		return 0;
+
+	spin_lock_irq(&mchdev_lock);
+
+	val = __i915_gfx_val(dev_priv);
+
+	spin_unlock_irq(&mchdev_lock);
+
+	return val;
+}
 
 /**
  * i915_read_mch_val - return value for IPS use
@@ -2988,18 +3071,18 @@ unsigned long i915_read_mch_val(void)
 	struct drm_i915_private *dev_priv;
 	unsigned long chipset_val, graphics_val, ret = 0;
 
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev)
 		goto out_unlock;
 	dev_priv = i915_mch_dev;
 
-	chipset_val = i915_chipset_val(dev_priv);
-	graphics_val = i915_gfx_val(dev_priv);
+	chipset_val = __i915_chipset_val(dev_priv);
+	graphics_val = __i915_gfx_val(dev_priv);
 
 	ret = chipset_val + graphics_val;
 
 out_unlock:
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	return ret;
 }
@@ -3015,18 +3098,18 @@ bool i915_gpu_raise(void)
 	struct drm_i915_private *dev_priv;
 	bool ret = true;
 
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev) {
 		ret = false;
 		goto out_unlock;
 	}
 	dev_priv = i915_mch_dev;
 
-	if (dev_priv->max_delay > dev_priv->fmax)
-		dev_priv->max_delay--;
+	if (dev_priv->ips.max_delay > dev_priv->ips.fmax)
+		dev_priv->ips.max_delay--;
 
 out_unlock:
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	return ret;
 }
@@ -3043,18 +3126,18 @@ bool i915_gpu_lower(void)
 	struct drm_i915_private *dev_priv;
 	bool ret = true;
 
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev) {
 		ret = false;
 		goto out_unlock;
 	}
 	dev_priv = i915_mch_dev;
 
-	if (dev_priv->max_delay < dev_priv->min_delay)
-		dev_priv->max_delay++;
+	if (dev_priv->ips.max_delay < dev_priv->ips.min_delay)
+		dev_priv->ips.max_delay++;
 
 out_unlock:
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	return ret;
 }
@@ -3068,17 +3151,20 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower);
 bool i915_gpu_busy(void)
 {
 	struct drm_i915_private *dev_priv;
+	struct intel_ring_buffer *ring;
 	bool ret = false;
+	int i;
 
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev)
 		goto out_unlock;
 	dev_priv = i915_mch_dev;
 
-	ret = dev_priv->busy;
+	for_each_ring(ring, dev_priv, i)
+		ret |= !list_empty(&ring->request_list);
 
 out_unlock:
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	return ret;
 }
@@ -3095,20 +3181,20 @@ bool i915_gpu_turbo_disable(void)
 	struct drm_i915_private *dev_priv;
 	bool ret = true;
 
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	if (!i915_mch_dev) {
 		ret = false;
 		goto out_unlock;
 	}
 	dev_priv = i915_mch_dev;
 
-	dev_priv->max_delay = dev_priv->fstart;
+	dev_priv->ips.max_delay = dev_priv->ips.fstart;
 
-	if (!ironlake_set_drps(dev_priv->dev, dev_priv->fstart))
+	if (!ironlake_set_drps(dev_priv->dev, dev_priv->ips.fstart))
 		ret = false;
 
 out_unlock:
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	return ret;
 }
@@ -3136,19 +3222,20 @@ ips_ping_for_i915_load(void)
 
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv)
 {
-	spin_lock(&mchdev_lock);
+	/* We only register the i915 ips part with intel-ips once everything is
+	 * set up, to avoid intel-ips sneaking in and reading bogus values. */
+	spin_lock_irq(&mchdev_lock);
 	i915_mch_dev = dev_priv;
-	dev_priv->mchdev_lock = &mchdev_lock;
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 
 	ips_ping_for_i915_load();
 }
 
 void intel_gpu_ips_teardown(void)
 {
-	spin_lock(&mchdev_lock);
+	spin_lock_irq(&mchdev_lock);
 	i915_mch_dev = NULL;
-	spin_unlock(&mchdev_lock);
+	spin_unlock_irq(&mchdev_lock);
 }
 static void intel_init_emon(struct drm_device *dev)
 {
@@ -3218,7 +3305,7 @@ static void intel_init_emon(struct drm_device *dev)
 
 	lcfuse = I915_READ(LCFUSE02);
 
-	dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
+	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
 void intel_disable_gt_powersave(struct drm_device *dev)
@@ -3731,42 +3818,6 @@ void intel_init_clock_gating(struct drm_device *dev)
 		dev_priv->display.init_pch_clock_gating(dev);
 }
 
-static void gen6_sanitize_pm(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 limits, delay, old;
-
-	gen6_gt_force_wake_get(dev_priv);
-
-	old = limits = I915_READ(GEN6_RP_INTERRUPT_LIMITS);
-	/* Make sure we continue to get interrupts
-	 * until we hit the minimum or maximum frequencies.
-	 */
-	limits &= ~(0x3f << 16 | 0x3f << 24);
-	delay = dev_priv->cur_delay;
-	if (delay < dev_priv->max_delay)
-		limits |= (dev_priv->max_delay & 0x3f) << 24;
-	if (delay > dev_priv->min_delay)
-		limits |= (dev_priv->min_delay & 0x3f) << 16;
-
-	if (old != limits) {
-		/* Note that the known failure case is to read back 0. */
-		DRM_DEBUG_DRIVER("Power management discrepancy: GEN6_RP_INTERRUPT_LIMITS "
-				 "expected %08x, was %08x\n", limits, old);
-		I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
-	}
-
-	gen6_gt_force_wake_put(dev_priv);
-}
-
-void intel_sanitize_pm(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (dev_priv->display.sanitize_pm)
-		dev_priv->display.sanitize_pm(dev);
-}
-
 /* Starting with Haswell, we have different power wells for
  * different parts of the GPU. This attempts to enable them all.
  */
@@ -3852,7 +3903,6 @@ void intel_init_pm(struct drm_device *dev)
 				dev_priv->display.update_wm = NULL;
 			}
 			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
-			dev_priv->display.sanitize_pm = gen6_sanitize_pm;
 		} else if (IS_IVYBRIDGE(dev)) {
 			/* FIXME: detect B0+ stepping and use auto training */
 			if (SNB_READ_WM0_LATENCY()) {
@@ -3864,7 +3914,6 @@ void intel_init_pm(struct drm_device *dev)
 				dev_priv->display.update_wm = NULL;
 			}
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
-			dev_priv->display.sanitize_pm = gen6_sanitize_pm;
 		} else if (IS_HASWELL(dev)) {
 			if (SNB_READ_WM0_LATENCY()) {
 				dev_priv->display.update_wm = sandybridge_update_wm;
@@ -3876,7 +3925,6 @@ void intel_init_pm(struct drm_device *dev)
 				dev_priv->display.update_wm = NULL;
 			}
 			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
-			dev_priv->display.sanitize_pm = gen6_sanitize_pm;
 		} else
 			dev_priv->display.update_wm = NULL;
 	} else if (IS_VALLEYVIEW(dev)) {
@@ -3955,14 +4003,16 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 	else
 		forcewake_ack = FORCEWAKE_ACK;
 
-	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1) == 0, 500))
-		DRM_ERROR("Force wake wait timed out\n");
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & 1) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE, 1);
-	POSTING_READ(FORCEWAKE);
+	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
 
-	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
-		DRM_ERROR("Force wake wait timed out\n");
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & 1),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
 
 	__gen6_gt_wait_for_thread_c0(dev_priv);
 }
@@ -3976,14 +4026,16 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 	else
 		forcewake_ack = FORCEWAKE_MT_ACK;
 
-	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1) == 0, 500))
-		DRM_ERROR("Force wake wait timed out\n");
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & 1) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(1));
-	POSTING_READ(FORCEWAKE_MT);
+	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
 
-	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
-		DRM_ERROR("Force wake wait timed out\n");
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & 1),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
 
 	__gen6_gt_wait_for_thread_c0(dev_priv);
 }
@@ -4016,14 +4068,14 @@ void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
 static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	POSTING_READ(FORCEWAKE);
+	/* gen6_gt_check_fifodbg doubles as the POSTING_READ */
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
 static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(1));
-	POSTING_READ(FORCEWAKE_MT);
+	/* gen6_gt_check_fifodbg doubles as the POSTING_READ */
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
@@ -4062,24 +4114,24 @@ int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
 
 static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
 {
-	/* Already awake? */
-	if ((I915_READ(0x130094) & 0xa1) == 0xa1)
-		return;
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & 1) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
 
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, 0xffffffff);
-	POSTING_READ(FORCEWAKE_VLV);
+	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_ENABLE(1));
 
-	if (wait_for_atomic_us((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & 1), 500))
-		DRM_ERROR("Force wake wait timed out\n");
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & 1),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
 
 	__gen6_gt_wait_for_thread_c0(dev_priv);
 }
 
 static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, 0xffff0000);
-	/* FIXME: confirm VLV behavior with Punit folks */
-	POSTING_READ(FORCEWAKE_VLV);
+	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(1));
+	/* The below doubles as a POSTING_READ */
+	gen6_gt_check_fifodbg(dev_priv);
 }
 
 void intel_gt_init(struct drm_device *dev)