Merge branch 'drm-intel-next-fixes' into drm-intel-next

So I've sent the first pull request to Dave and I expect his request
for a merge tree any second now ;-)

More seriously I have some pending patches for 3.19 that depend upon
both trees, hence backmerge. Conflicts are all trivial.

Conflicts:
	drivers/gpu/drm/i915/i915_irq.c
	drivers/gpu/drm/i915/intel_display.c

v2: Of course I've forgotten the fixup script for the silent conflict.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

9 files changed, 118 insertions, 300 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 821ba26438fb..9962da202456 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -968,23 +968,6 @@ struct intel_rps_ei {
 	u32 media_c0;
 };
 
-struct intel_rps_bdw_cal {
-	u32 it_threshold_pct; /* interrupt, in percentage */
-	u32 eval_interval; /* evaluation interval, in us */
-	u32 last_ts;
-	u32 last_c0;
-	bool is_up;
-};
-
-struct intel_rps_bdw_turbo {
-	struct intel_rps_bdw_cal up;
-	struct intel_rps_bdw_cal down;
-	struct timer_list flip_timer;
-	u32 timeout;
-	atomic_t flip_received;
-	struct work_struct work_max_freq;
-};
-
 struct intel_gen6_power_mgmt {
 	/* work and pm_iir are protected by dev_priv->irq_lock */
 	struct work_struct work;
@@ -1018,9 +1001,6 @@ struct intel_gen6_power_mgmt {
 	bool enabled;
 	struct delayed_work delayed_resume_work;
 
-	bool is_bdw_sw_turbo;	/* Switch of BDW software turbo */
-	struct intel_rps_bdw_turbo sw_turbo; /* Calculate RP interrupt timing */
-
 	/* manual wa residency calculations */
 	struct intel_rps_ei up_ei, down_ei;
 
@@ -2857,8 +2837,6 @@ extern void intel_disable_fbc(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);
 extern void gen6_set_rps(struct drm_device *dev, u8 val);
-extern void bdw_software_turbo(struct drm_device *dev);
-extern void gen8_flip_interrupt(struct drm_device *dev);
 extern void valleyview_set_rps(struct drm_device *dev, u8 val);
 extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d38413997379..d182058383a9 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -293,15 +293,23 @@ i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 static struct i915_mmu_notifier *
 i915_mmu_notifier_find(struct i915_mm_struct *mm)
 {
-	if (mm->mn == NULL) {
-		down_write(&mm->mm->mmap_sem);
-		mutex_lock(&to_i915(mm->dev)->mm_lock);
-		if (mm->mn == NULL)
-			mm->mn = i915_mmu_notifier_create(mm->mm);
-		mutex_unlock(&to_i915(mm->dev)->mm_lock);
-		up_write(&mm->mm->mmap_sem);
+	struct i915_mmu_notifier *mn = mm->mn;
+
+	mn = mm->mn;
+	if (mn)
+		return mn;
+
+	down_write(&mm->mm->mmap_sem);
+	mutex_lock(&to_i915(mm->dev)->mm_lock);
+	if ((mn = mm->mn) == NULL) {
+		mn = i915_mmu_notifier_create(mm->mm);
+		if (!IS_ERR(mn))
+			mm->mn = mn;
 	}
-	return mm->mn;
+	mutex_unlock(&to_i915(mm->dev)->mm_lock);
+	up_write(&mm->mm->mmap_sem);
+
+	return mn;
 }
 
 static int
@@ -681,16 +689,15 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 static void
 i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 {
-	struct scatterlist *sg;
-	int i;
+	struct sg_page_iter sg_iter;
 
 	BUG_ON(obj->userptr.work != NULL);
 
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;
 
-	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
-		struct page *page = sg_page(sg);
+	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
 
 		if (obj->dirty)
 			set_page_dirty(page);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 737b23982b95..f17bbf3ac136 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1716,7 +1716,7 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 #define HPD_STORM_DETECT_PERIOD 1000
 #define HPD_STORM_THRESHOLD 5
 
-static int ilk_port_to_hotplug_shift(enum port port)
+static int pch_port_to_hotplug_shift(enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -1732,7 +1732,7 @@ static int ilk_port_to_hotplug_shift(enum port port)
 	}
 }
 
-static int g4x_port_to_hotplug_shift(enum port port)
+static int i915_port_to_hotplug_shift(enum port port)
 {
 	switch (port) {
 	case PORT_A:
@@ -1790,12 +1790,12 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 		if (port && dev_priv->hpd_irq_port[port]) {
 			bool long_hpd;
 
-			if (IS_G4X(dev)) {
-				dig_shift = g4x_port_to_hotplug_shift(port);
-				long_hpd = (hotplug_trigger >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
-			} else {
-				dig_shift = ilk_port_to_hotplug_shift(port);
+			if (HAS_PCH_SPLIT(dev)) {
+				dig_shift = pch_port_to_hotplug_shift(port);
 				long_hpd = (dig_hotplug_reg >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
+			} else {
+				dig_shift = i915_port_to_hotplug_shift(port);
+				long_hpd = (hotplug_trigger >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
 			}
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n",
@@ -1984,27 +1984,6 @@ static void i9xx_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
 				     res1, res2);
 }
 
-void gen8_flip_interrupt(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		return;
-
-	if(atomic_read(&dev_priv->rps.sw_turbo.flip_received)) {
-		mod_timer(&dev_priv->rps.sw_turbo.flip_timer,
-				usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies);
-	}
-	else {
-		dev_priv->rps.sw_turbo.flip_timer.expires =
-				usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies;
-		add_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		atomic_set(&dev_priv->rps.sw_turbo.flip_received, true);
-	}
-
-	bdw_software_turbo(dev);
-}
-
 /* The RPS events need forcewake, so we add them to a work queue and mask their
  * IMR bits until the work is done. Other interrupts can be processed without
  * the work queue. */
@@ -3494,11 +3473,13 @@ static void gen8_irq_reset(struct drm_device *dev)
 
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv)
 {
+	uint32_t extra_ier = GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN;
+
 	spin_lock_irq(&dev_priv->irq_lock);
 	GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_B, dev_priv->de_irq_mask[PIPE_B],
-			  ~dev_priv->de_irq_mask[PIPE_B]);
+			  ~dev_priv->de_irq_mask[PIPE_B] | extra_ier);
 	GEN8_IRQ_INIT_NDX(DE_PIPE, PIPE_C, dev_priv->de_irq_mask[PIPE_C],
-			  ~dev_priv->de_irq_mask[PIPE_C]);
+			  ~dev_priv->de_irq_mask[PIPE_C] | extra_ier);
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2ed02c391f3b..a56d9a7e7e0e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2474,6 +2474,7 @@ enum punit_power_well {
 #define _PIPEASRC	0x6001c
 #define _BCLRPAT_A	0x60020
 #define _VSYNCSHIFT_A	0x60028
+#define _PIPE_MULT_A	0x6002c
 
 /* Pipe B timing regs */
 #define _HTOTAL_B	0x61000
@@ -2485,6 +2486,7 @@ enum punit_power_well {
 #define _PIPEBSRC	0x6101c
 #define _BCLRPAT_B	0x61020
 #define _VSYNCSHIFT_B	0x61028
+#define _PIPE_MULT_B	0x6102c
 
 #define TRANSCODER_A_OFFSET 0x60000
 #define TRANSCODER_B_OFFSET 0x61000
@@ -2505,6 +2507,7 @@ enum punit_power_well {
 #define BCLRPAT(trans) _TRANSCODER2(trans, _BCLRPAT_A)
 #define VSYNCSHIFT(trans) _TRANSCODER2(trans, _VSYNCSHIFT_A)
 #define PIPESRC(trans) _TRANSCODER2(trans, _PIPEASRC)
+#define PIPE_MULT(trans) _TRANSCODER2(trans, _PIPE_MULT_A)
 
 /* HSW+ eDP PSR registers */
 #define EDP_PSR_BASE(dev)                       (IS_HASWELL(dev) ? 0x64800 : 0x6f800)
@@ -5766,10 +5769,6 @@ enum punit_power_well {
 #define GEN8_UCGCTL6				0x9430
 #define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
-#define TIMESTAMP_CTR		0x44070
-#define FREQ_1_28_US(us)	(((us) * 100) >> 7)
-#define MCHBAR_PCU_C0		(MCHBAR_MIRROR_BASE_SNB + 0x5960)
-
 #define GEN6_GFXPAUSE				0xA000
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 6fc77a100cc6..1fc05ffc4695 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -73,9 +73,6 @@ static const uint32_t intel_cursor_formats[] = {
 	DRM_FORMAT_ARGB8888,
 };
 
-#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
-({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
-
 static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
 
 static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
@@ -4265,6 +4262,11 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 
 	intel_set_pipe_timings(intel_crtc);
 
+	if (intel_crtc->config.cpu_transcoder != TRANSCODER_EDP) {
+		I915_WRITE(PIPE_MULT(intel_crtc->config.cpu_transcoder),
+			   intel_crtc->config.pixel_multiplier - 1);
+	}
+
 	if (intel_crtc->config.has_pch_encoder) {
 		intel_cpu_transcoder_set_m_n(intel_crtc,
 				     &intel_crtc->config.fdi_m_n, NULL);
@@ -7937,7 +7939,12 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
 			(I915_READ(IPS_CTL) & IPS_ENABLE);
 
-	pipe_config->pixel_multiplier = 1;
+	if (pipe_config->cpu_transcoder != TRANSCODER_EDP) {
+		pipe_config->pixel_multiplier =
+			I915_READ(PIPE_MULT(pipe_config->cpu_transcoder)) + 1;
+	} else {
+		pipe_config->pixel_multiplier = 1;
+	}
 
 	return true;
 }
@@ -9773,9 +9780,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	struct intel_engine_cs *ring;
 	int ret;
 
-	//trigger software GT busyness calculation
-	gen8_flip_interrupt(dev);
-
 	/*
 	 * drm_mode_page_flip_ioctl() should already catch this, but double
 	 * check to be safe.  In the future we may enable pageflipping from
@@ -12223,27 +12227,36 @@ static void intel_setup_outputs(struct drm_device *dev)
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev)) {
-		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED) {
+		/*
+		 * The DP_DETECTED bit is the latched state of the DDC
+		 * SDA pin at boot. However since eDP doesn't require DDC
+		 * (no way to plug in a DP->HDMI dongle) the DDC pins for
+		 * eDP ports may have been muxed to an alternate function.
+		 * Thus we can't rely on the DP_DETECTED bit alone to detect
+		 * eDP ports. Consult the VBT as well as DP_DETECTED to
+		 * detect eDP ports.
+		 */
+		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED)
 			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIB,
 					PORT_B);
-			if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED)
-				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B);
-		}
+		if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED ||
+		    intel_dp_is_edp(dev, PORT_B))
+			intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B);
 
-		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED) {
+		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED)
 			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIC,
 					PORT_C);
-			if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED)
-				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
-		}
+		if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED ||
+		    intel_dp_is_edp(dev, PORT_C))
+			intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
 
 		if (IS_CHERRYVIEW(dev)) {
-			if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) {
+			if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED)
 				intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID,
 						PORT_D);
-				if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED)
-					intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D);
-			}
+			/* eDP not supported on port D, so don't check VBT */
+			if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED)
+				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D);
 		}
 
 		intel_dsi_init(dev);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ffbf38d9b536..94993d23e547 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -36,6 +36,9 @@
 #include <drm/drm_dp_mst_helper.h>
 #include <drm/drm_rect.h>
 
+#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
+({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
+
 /**
  * _wait_for - magic (register) wait macro
  *
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 543e0f17ee62..e3def5ad4a77 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -419,9 +419,8 @@ static uint32_t scale(uint32_t source_val,
 	source_val = clamp(source_val, source_min, source_max);
 
 	/* avoid overflows */
-	target_val = (uint64_t)(source_val - source_min) *
-		(target_max - target_min);
-	do_div(target_val, source_max - source_min);
+	target_val = DIV_ROUND_CLOSEST_ULL((uint64_t)(source_val - source_min) *
+			(target_max - target_min), source_max - source_min);
 	target_val += target_min;
 
 	return target_val;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 79108059b79b..a14be5d56c6b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2320,6 +2320,7 @@ int ilk_wm_max_level(const struct drm_device *dev)
 	else
 		return 2;
 }
+
 static void intel_print_wm_latency(struct drm_device *dev,
 				   const char *name,
 				   const uint16_t wm[5])
@@ -3288,9 +3289,6 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 {
 	int new_power;
 
-	if (dev_priv->rps.is_bdw_sw_turbo)
-		return;
-
 	new_power = dev_priv->rps.power;
 	switch (dev_priv->rps.power) {
 	case LOW_POWER:
@@ -3498,11 +3496,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
 		else if (IS_VALLEYVIEW(dev))
 			vlv_set_rps_idle(dev_priv);
-		else if (!dev_priv->rps.is_bdw_sw_turbo
-					|| atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
+		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
-		}
-
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3516,11 +3511,8 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 	if (dev_priv->rps.enabled) {
 		if (IS_VALLEYVIEW(dev))
 			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
-		else if (!dev_priv->rps.is_bdw_sw_turbo
-					|| atomic_read(&dev_priv->rps.sw_turbo.flip_received)){
+		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
-		}
-
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3534,17 +3526,18 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
 	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
-	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
-			 dev_priv->rps.cur_freq,
-			 vlv_gpu_freq(dev_priv, val), val);
-
 	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
 		      "Odd GPU freq value\n"))
 		val &= ~1;
 
-	if (val != dev_priv->rps.cur_freq)
+	if (val != dev_priv->rps.cur_freq) {
+		DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
+				 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+				 dev_priv->rps.cur_freq,
+				 vlv_gpu_freq(dev_priv, val), val);
+
 		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+	}
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
@@ -3555,26 +3548,21 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 static void gen8_disable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	if (IS_BROADWELL(dev) && dev_priv->rps.is_bdw_sw_turbo){
-		if (atomic_read(&dev_priv->rps.sw_turbo.flip_received))
-			del_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		dev_priv-> rps.is_bdw_sw_turbo = false;
-	} else {
-		I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
-		I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
-					   ~dev_priv->pm_rps_events);
-		/* Complete PM interrupt masking here doesn't race with the rps work
-		 * item again unmasking PM interrupts because that is using a different
-		 * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
-		 * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
-		 * gen8_enable_rps will clean up. */
 
-		spin_lock_irq(&dev_priv->irq_lock);
-		dev_priv->rps.pm_iir = 0;
-		spin_unlock_irq(&dev_priv->irq_lock);
+	I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
+	I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
+				   ~dev_priv->pm_rps_events);
+	/* Complete PM interrupt masking here doesn't race with the rps work
+	 * item again unmasking PM interrupts because that is using a different
+	 * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
+	 * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
+	 * gen8_enable_rps will clean up. */
 
-		I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
-	}
+	spin_lock_irq(&dev_priv->irq_lock);
+	dev_priv->rps.pm_iir = 0;
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
 }
 
 static void gen6_disable_rps_interrupts(struct drm_device *dev)
@@ -3732,111 +3720,13 @@ static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_c
 		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
 }
 
-static void bdw_sw_calculate_freq(struct drm_device *dev,
-		struct intel_rps_bdw_cal *c, u32 *cur_time, u32 *c0)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u64 busy = 0;
-	u32 busyness_pct = 0;
-	u32 elapsed_time = 0;
-	u16 new_freq = 0;
-
-	if (!c || !cur_time || !c0)
-		return;
-
-	if (0 == c->last_c0)
-		goto out;
-
-	/* Check Evaluation interval */
-	elapsed_time = *cur_time - c->last_ts;
-	if (elapsed_time < c->eval_interval)
-		return;
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-
-	/*
-	 * c0 unit in 32*1.28 usec, elapsed_time unit in 1 usec.
-	 * Whole busyness_pct calculation should be
-	 *     busy = ((u64)(*c0 - c->last_c0) << 5 << 7) / 100;
-	 *     busyness_pct = (u32)(busy * 100 / elapsed_time);
-	 * The final formula is to simplify CPU calculation
-	 */
-	busy = (u64)(*c0 - c->last_c0) << 12;
-	do_div(busy, elapsed_time);
-	busyness_pct = (u32)busy;
-
-	if (c->is_up && busyness_pct >= c->it_threshold_pct)
-		new_freq = (u16)dev_priv->rps.cur_freq + 3;
-	if (!c->is_up && busyness_pct <= c->it_threshold_pct)
-		new_freq = (u16)dev_priv->rps.cur_freq - 1;
-
-	/* Adjust to new frequency busyness and compare with threshold */
-	if (0 != new_freq) {
-		if (new_freq > dev_priv->rps.max_freq_softlimit)
-			new_freq = dev_priv->rps.max_freq_softlimit;
-		else if (new_freq < dev_priv->rps.min_freq_softlimit)
-			new_freq = dev_priv->rps.min_freq_softlimit;
-
-		gen6_set_rps(dev, new_freq);
-	}
-
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-out:
-	c->last_c0 = *c0;
-	c->last_ts = *cur_time;
-}
-
-static void gen8_set_frequency_RP0(struct work_struct *work)
-{
-	struct intel_rps_bdw_turbo *p_bdw_turbo =
-			container_of(work, struct intel_rps_bdw_turbo, work_max_freq);
-	struct intel_gen6_power_mgmt *p_power_mgmt =
-			container_of(p_bdw_turbo, struct intel_gen6_power_mgmt, sw_turbo);
-	struct drm_i915_private *dev_priv =
-			container_of(p_power_mgmt, struct drm_i915_private, rps);
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.rp0_freq);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-}
-
-static void flip_active_timeout_handler(unsigned long var)
-{
-	struct drm_i915_private *dev_priv = (struct drm_i915_private *) var;
-
-	del_timer(&dev_priv->rps.sw_turbo.flip_timer);
-	atomic_set(&dev_priv->rps.sw_turbo.flip_received, false);
-
-	queue_work(dev_priv->wq, &dev_priv->rps.sw_turbo.work_max_freq);
-}
-
-void bdw_software_turbo(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	u32 current_time = I915_READ(TIMESTAMP_CTR); /* unit in usec */
-	u32 current_c0 = I915_READ(MCHBAR_PCU_C0); /* unit in 32*1.28 usec */
-
-	bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.up,
-			&current_time, &current_c0);
-	bdw_sw_calculate_freq(dev, &dev_priv->rps.sw_turbo.down,
-			&current_time, &current_c0);
-}
-
 static void gen8_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
 	uint32_t rc6_mask = 0, rp_state_cap;
-	uint32_t threshold_up_pct, threshold_down_pct;
-	uint32_t ei_up, ei_down; /* up and down evaluation interval */
-	u32 rp_ctl_flag;
 	int unused;
 
-	/* Use software Turbo for BDW */
-	dev_priv->rps.is_bdw_sw_turbo = IS_BROADWELL(dev);
-
 	/* 1a: Software RC state - RC0 */
 	I915_WRITE(GEN6_RC_STATE, 0);
 
@@ -3880,74 +3770,35 @@ static void gen8_enable_rps(struct drm_device *dev)
 		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
 	I915_WRITE(GEN6_RC_VIDEO_FREQ,
 		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
-	ei_up = 84480; /* 84.48ms */
-	ei_down = 448000;
-	threshold_up_pct = 90; /* x percent busy */
-	threshold_down_pct = 70;
-
-	if (dev_priv->rps.is_bdw_sw_turbo) {
-		dev_priv->rps.sw_turbo.up.it_threshold_pct = threshold_up_pct;
-		dev_priv->rps.sw_turbo.up.eval_interval = ei_up;
-		dev_priv->rps.sw_turbo.up.is_up = true;
-		dev_priv->rps.sw_turbo.up.last_ts = 0;
-		dev_priv->rps.sw_turbo.up.last_c0 = 0;
-
-		dev_priv->rps.sw_turbo.down.it_threshold_pct = threshold_down_pct;
-		dev_priv->rps.sw_turbo.down.eval_interval = ei_down;
-		dev_priv->rps.sw_turbo.down.is_up = false;
-		dev_priv->rps.sw_turbo.down.last_ts = 0;
-		dev_priv->rps.sw_turbo.down.last_c0 = 0;
-
-		/* Start the timer to track if flip comes*/
-		dev_priv->rps.sw_turbo.timeout = 200*1000; /* in us */
-
-		init_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		dev_priv->rps.sw_turbo.flip_timer.function = flip_active_timeout_handler;
-		dev_priv->rps.sw_turbo.flip_timer.data  = (unsigned long) dev_priv;
-		dev_priv->rps.sw_turbo.flip_timer.expires =
-			usecs_to_jiffies(dev_priv->rps.sw_turbo.timeout) + jiffies;
-		add_timer(&dev_priv->rps.sw_turbo.flip_timer);
-		INIT_WORK(&dev_priv->rps.sw_turbo.work_max_freq, gen8_set_frequency_RP0);
-
-		atomic_set(&dev_priv->rps.sw_turbo.flip_received, true);
-	} else {
-		/* NB: Docs say 1s, and 1000000 - which aren't equivalent
-		 * 1 second timeout*/
-		I915_WRITE(GEN6_RP_DOWN_TIMEOUT, FREQ_1_28_US(1000000));
+	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
 
-		/* Docs recommend 900MHz, and 300 MHz respectively */
-		I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-			   dev_priv->rps.max_freq_softlimit << 24 |
-			   dev_priv->rps.min_freq_softlimit << 16);
+	/* Docs recommend 900MHz, and 300 MHz respectively */
+	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
+		   dev_priv->rps.max_freq_softlimit << 24 |
+		   dev_priv->rps.min_freq_softlimit << 16);
 
-		I915_WRITE(GEN6_RP_UP_THRESHOLD,
-			FREQ_1_28_US(ei_up * threshold_up_pct / 100));
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
-			FREQ_1_28_US(ei_down * threshold_down_pct / 100));
-		I915_WRITE(GEN6_RP_UP_EI,
-			FREQ_1_28_US(ei_up));
-		I915_WRITE(GEN6_RP_DOWN_EI,
-			FREQ_1_28_US(ei_down));
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
+	I915_WRITE(GEN6_RP_UP_EI, 66000); /* 84.48ms, XXX: random? */
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000); /* 448ms, XXX: random? */
 
-		I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-	}
+	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
 	/* 5: Enable RPS */
-	rp_ctl_flag = GEN6_RP_MEDIA_TURBO |
-					GEN6_RP_MEDIA_HW_NORMAL_MODE |
-					GEN6_RP_MEDIA_IS_GFX |
-					GEN6_RP_UP_BUSY_AVG |
-					GEN6_RP_DOWN_IDLE_AVG;
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		rp_ctl_flag |= GEN6_RP_ENABLE;
-
-	I915_WRITE(GEN6_RP_CONTROL, rp_ctl_flag);
-
-	/* 6: Ring frequency + overclocking
-	 * (our driver does this later */
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_TURBO |
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX |
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_AVG);
+
+	/* 6: Ring frequency + overclocking (our driver does this later */
+
 	gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
-	if (!dev_priv->rps.is_bdw_sw_turbo)
-		gen8_enable_rps_interrupts(dev);
+
+	gen8_enable_rps_interrupts(dev);
 
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
@@ -5421,8 +5272,6 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 			     rps.delayed_resume_work.work);
 	struct drm_device *dev = dev_priv->dev;
 
-	dev_priv->rps.is_bdw_sw_turbo = false;
-
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	if (IS_CHERRYVIEW(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index cc50bf65d35a..7c0c28c65cb4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -707,7 +707,7 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * update the number of dwords required based on the
 	 * actual number of workarounds applied
 	 */
-	ret = intel_ring_begin(ring, 24);
+	ret = intel_ring_begin(ring, 18);
 	if (ret)
 		return ret;
 
@@ -722,19 +722,8 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
 	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
-			   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS
-					      | GEN8_SAMPLER_POWER_BYPASS_DIS));
-
-	intel_ring_emit_wa(ring, GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	intel_ring_emit_wa(ring, COMMON_SLICE_CHICKEN2,
-			   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 
 	/* Use Force Non-Coherent whenever executing a 3D context. This is a
 	 * workaround for for a possible hang in the unlikely event a TLB