Merge branch 'topic/bxt-stage1' into drm-intel-next-queued

Separate topic branch for bxt didn't work out since we needed to
refactor the gmbus code a bit to make it look decent. So backmerge.

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

13 files changed, 391 insertions, 209 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5081e6f8a385..23949247cf10 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4541,12 +4541,116 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_cache_sharing_fops,
 			i915_cache_sharing_get, i915_cache_sharing_set,
 			"%llu\n");
 
+struct sseu_dev_status {
+	unsigned int slice_total;
+	unsigned int subslice_total;
+	unsigned int subslice_per_slice;
+	unsigned int eu_total;
+	unsigned int eu_per_subslice;
+};
+
+static void cherryview_sseu_device_status(struct drm_device *dev,
+					  struct sseu_dev_status *stat)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	const int ss_max = 2;
+	int ss;
+	u32 sig1[ss_max], sig2[ss_max];
+
+	sig1[0] = I915_READ(CHV_POWER_SS0_SIG1);
+	sig1[1] = I915_READ(CHV_POWER_SS1_SIG1);
+	sig2[0] = I915_READ(CHV_POWER_SS0_SIG2);
+	sig2[1] = I915_READ(CHV_POWER_SS1_SIG2);
+
+	for (ss = 0; ss < ss_max; ss++) {
+		unsigned int eu_cnt;
+
+		if (sig1[ss] & CHV_SS_PG_ENABLE)
+			/* skip disabled subslice */
+			continue;
+
+		stat->slice_total = 1;
+		stat->subslice_per_slice++;
+		eu_cnt = ((sig1[ss] & CHV_EU08_PG_ENABLE) ? 0 : 2) +
+			 ((sig1[ss] & CHV_EU19_PG_ENABLE) ? 0 : 2) +
+			 ((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) +
+			 ((sig2[ss] & CHV_EU311_PG_ENABLE) ? 0 : 2);
+		stat->eu_total += eu_cnt;
+		stat->eu_per_subslice = max(stat->eu_per_subslice, eu_cnt);
+	}
+	stat->subslice_total = stat->subslice_per_slice;
+}
+
+static void gen9_sseu_device_status(struct drm_device *dev,
+				    struct sseu_dev_status *stat)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int s_max = 3, ss_max = 4;
+	int s, ss;
+	u32 s_reg[s_max], eu_reg[2*s_max], eu_mask[2];
+
+	/* BXT has a single slice and at most 3 subslices. */
+	if (IS_BROXTON(dev)) {
+		s_max = 1;
+		ss_max = 3;
+	}
+
+	for (s = 0; s < s_max; s++) {
+		s_reg[s] = I915_READ(GEN9_SLICE_PGCTL_ACK(s));
+		eu_reg[2*s] = I915_READ(GEN9_SS01_EU_PGCTL_ACK(s));
+		eu_reg[2*s + 1] = I915_READ(GEN9_SS23_EU_PGCTL_ACK(s));
+	}
+
+	eu_mask[0] = GEN9_PGCTL_SSA_EU08_ACK |
+		     GEN9_PGCTL_SSA_EU19_ACK |
+		     GEN9_PGCTL_SSA_EU210_ACK |
+		     GEN9_PGCTL_SSA_EU311_ACK;
+	eu_mask[1] = GEN9_PGCTL_SSB_EU08_ACK |
+		     GEN9_PGCTL_SSB_EU19_ACK |
+		     GEN9_PGCTL_SSB_EU210_ACK |
+		     GEN9_PGCTL_SSB_EU311_ACK;
+
+	for (s = 0; s < s_max; s++) {
+		unsigned int ss_cnt = 0;
+
+		if ((s_reg[s] & GEN9_PGCTL_SLICE_ACK) == 0)
+			/* skip disabled slice */
+			continue;
+
+		stat->slice_total++;
+
+		if (IS_SKYLAKE(dev))
+			ss_cnt = INTEL_INFO(dev)->subslice_per_slice;
+
+		for (ss = 0; ss < ss_max; ss++) {
+			unsigned int eu_cnt;
+
+			if (IS_BROXTON(dev) &&
+			    !(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
+				/* skip disabled subslice */
+				continue;
+
+			if (IS_BROXTON(dev))
+				ss_cnt++;
+
+			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
+					       eu_mask[ss%2]);
+			stat->eu_total += eu_cnt;
+			stat->eu_per_subslice = max(stat->eu_per_subslice,
+						    eu_cnt);
+		}
+
+		stat->subslice_total += ss_cnt;
+		stat->subslice_per_slice = max(stat->subslice_per_slice,
+					       ss_cnt);
+	}
+}
+
 static int i915_sseu_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned int s_tot = 0, ss_tot = 0, ss_per = 0, eu_tot = 0, eu_per = 0;
+	struct sseu_dev_status stat;
 
 	if ((INTEL_INFO(dev)->gen < 8) || IS_BROADWELL(dev))
 		return -ENODEV;
@@ -4570,79 +4674,22 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		   yesno(INTEL_INFO(dev)->has_eu_pg));
 
 	seq_puts(m, "SSEU Device Status\n");
+	memset(&stat, 0, sizeof(stat));
 	if (IS_CHERRYVIEW(dev)) {
-		const int ss_max = 2;
-		int ss;
-		u32 sig1[ss_max], sig2[ss_max];
-
-		sig1[0] = I915_READ(CHV_POWER_SS0_SIG1);
-		sig1[1] = I915_READ(CHV_POWER_SS1_SIG1);
-		sig2[0] = I915_READ(CHV_POWER_SS0_SIG2);
-		sig2[1] = I915_READ(CHV_POWER_SS1_SIG2);
-
-		for (ss = 0; ss < ss_max; ss++) {
-			unsigned int eu_cnt;
-
-			if (sig1[ss] & CHV_SS_PG_ENABLE)
-				/* skip disabled subslice */
-				continue;
-
-			s_tot = 1;
-			ss_per++;
-			eu_cnt = ((sig1[ss] & CHV_EU08_PG_ENABLE) ? 0 : 2) +
-				 ((sig1[ss] & CHV_EU19_PG_ENABLE) ? 0 : 2) +
-				 ((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) +
-				 ((sig2[ss] & CHV_EU311_PG_ENABLE) ? 0 : 2);
-			eu_tot += eu_cnt;
-			eu_per = max(eu_per, eu_cnt);
-		}
-		ss_tot = ss_per;
-	} else if (IS_SKYLAKE(dev)) {
-		const int s_max = 3, ss_max = 4;
-		int s, ss;
-		u32 s_reg[s_max], eu_reg[2*s_max], eu_mask[2];
-
-		s_reg[0] = I915_READ(GEN9_SLICE0_PGCTL_ACK);
-		s_reg[1] = I915_READ(GEN9_SLICE1_PGCTL_ACK);
-		s_reg[2] = I915_READ(GEN9_SLICE2_PGCTL_ACK);
-		eu_reg[0] = I915_READ(GEN9_SLICE0_SS01_EU_PGCTL_ACK);
-		eu_reg[1] = I915_READ(GEN9_SLICE0_SS23_EU_PGCTL_ACK);
-		eu_reg[2] = I915_READ(GEN9_SLICE1_SS01_EU_PGCTL_ACK);
-		eu_reg[3] = I915_READ(GEN9_SLICE1_SS23_EU_PGCTL_ACK);
-		eu_reg[4] = I915_READ(GEN9_SLICE2_SS01_EU_PGCTL_ACK);
-		eu_reg[5] = I915_READ(GEN9_SLICE2_SS23_EU_PGCTL_ACK);
-		eu_mask[0] = GEN9_PGCTL_SSA_EU08_ACK |
-			     GEN9_PGCTL_SSA_EU19_ACK |
-			     GEN9_PGCTL_SSA_EU210_ACK |
-			     GEN9_PGCTL_SSA_EU311_ACK;
-		eu_mask[1] = GEN9_PGCTL_SSB_EU08_ACK |
-			     GEN9_PGCTL_SSB_EU19_ACK |
-			     GEN9_PGCTL_SSB_EU210_ACK |
-			     GEN9_PGCTL_SSB_EU311_ACK;
-
-		for (s = 0; s < s_max; s++) {
-			if ((s_reg[s] & GEN9_PGCTL_SLICE_ACK) == 0)
-				/* skip disabled slice */
-				continue;
-
-			s_tot++;
-			ss_per = INTEL_INFO(dev)->subslice_per_slice;
-			ss_tot += ss_per;
-			for (ss = 0; ss < ss_max; ss++) {
-				unsigned int eu_cnt;
-
-				eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
-						       eu_mask[ss%2]);
-				eu_tot += eu_cnt;
-				eu_per = max(eu_per, eu_cnt);
-			}
-		}
+		cherryview_sseu_device_status(dev, &stat);
+	} else if (INTEL_INFO(dev)->gen >= 9) {
+		gen9_sseu_device_status(dev, &stat);
 	}
-	seq_printf(m, "  Enabled Slice Total: %u\n", s_tot);
-	seq_printf(m, "  Enabled Subslice Total: %u\n", ss_tot);
-	seq_printf(m, "  Enabled Subslice Per Slice: %u\n", ss_per);
-	seq_printf(m, "  Enabled EU Total: %u\n", eu_tot);
-	seq_printf(m, "  Enabled EU Per Subslice: %u\n", eu_per);
+	seq_printf(m, "  Enabled Slice Total: %u\n",
+		   stat.slice_total);
+	seq_printf(m, "  Enabled Subslice Total: %u\n",
+		   stat.subslice_total);
+	seq_printf(m, "  Enabled Subslice Per Slice: %u\n",
+		   stat.subslice_per_slice);
+	seq_printf(m, "  Enabled EU Total: %u\n",
+		   stat.eu_total);
+	seq_printf(m, "  Enabled EU Per Subslice: %u\n",
+		   stat.eu_per_subslice);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index d67cd9e0ef14..e44116f0ad0a 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -564,6 +564,140 @@ static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 #undef SEP_COMMA
 }
 
+static void cherryview_sseu_info_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_device_info *info;
+	u32 fuse, eu_dis;
+
+	info = (struct intel_device_info *)&dev_priv->info;
+	fuse = I915_READ(CHV_FUSE_GT);
+
+	info->slice_total = 1;
+
+	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
+		info->subslice_per_slice++;
+		eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK |
+				 CHV_FGT_EU_DIS_SS0_R1_MASK);
+		info->eu_total += 8 - hweight32(eu_dis);
+	}
+
+	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
+		info->subslice_per_slice++;
+		eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK |
+				 CHV_FGT_EU_DIS_SS1_R1_MASK);
+		info->eu_total += 8 - hweight32(eu_dis);
+	}
+
+	info->subslice_total = info->subslice_per_slice;
+	/*
+	 * CHV expected to always have a uniform distribution of EU
+	 * across subslices.
+	*/
+	info->eu_per_subslice = info->subslice_total ?
+				info->eu_total / info->subslice_total :
+				0;
+	/*
+	 * CHV supports subslice power gating on devices with more than
+	 * one subslice, and supports EU power gating on devices with
+	 * more than one EU pair per subslice.
+	*/
+	info->has_slice_pg = 0;
+	info->has_subslice_pg = (info->subslice_total > 1);
+	info->has_eu_pg = (info->eu_per_subslice > 2);
+}
+
+static void gen9_sseu_info_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_device_info *info;
+	int s_max = 3, ss_max = 4, eu_max = 8;
+	int s, ss;
+	u32 fuse2, s_enable, ss_disable, eu_disable;
+	u8 eu_mask = 0xff;
+
+	/*
+	 * BXT has a single slice. BXT also has at most 6 EU per subslice,
+	 * and therefore only the lowest 6 bits of the 8-bit EU disable
+	 * fields are valid.
+	*/
+	if (IS_BROXTON(dev)) {
+		s_max = 1;
+		eu_max = 6;
+		eu_mask = 0x3f;
+	}
+
+	info = (struct intel_device_info *)&dev_priv->info;
+	fuse2 = I915_READ(GEN8_FUSE2);
+	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >>
+		   GEN8_F2_S_ENA_SHIFT;
+	ss_disable = (fuse2 & GEN9_F2_SS_DIS_MASK) >>
+		     GEN9_F2_SS_DIS_SHIFT;
+
+	info->slice_total = hweight32(s_enable);
+	/*
+	 * The subslice disable field is global, i.e. it applies
+	 * to each of the enabled slices.
+	*/
+	info->subslice_per_slice = ss_max - hweight32(ss_disable);
+	info->subslice_total = info->slice_total *
+			       info->subslice_per_slice;
+
+	/*
+	 * Iterate through enabled slices and subslices to
+	 * count the total enabled EU.
+	*/
+	for (s = 0; s < s_max; s++) {
+		if (!(s_enable & (0x1 << s)))
+			/* skip disabled slice */
+			continue;
+
+		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
+		for (ss = 0; ss < ss_max; ss++) {
+			int eu_per_ss;
+
+			if (ss_disable & (0x1 << ss))
+				/* skip disabled subslice */
+				continue;
+
+			eu_per_ss = eu_max - hweight8((eu_disable >> (ss*8)) &
+						      eu_mask);
+
+			/*
+			 * Record which subslice(s) has(have) 7 EUs. we
+			 * can tune the hash used to spread work among
+			 * subslices if they are unbalanced.
+			 */
+			if (eu_per_ss == 7)
+				info->subslice_7eu[s] |= 1 << ss;
+
+			info->eu_total += eu_per_ss;
+		}
+	}
+
+	/*
+	 * SKL is expected to always have a uniform distribution
+	 * of EU across subslices with the exception that any one
+	 * EU in any one subslice may be fused off for die
+	 * recovery. BXT is expected to be perfectly uniform in EU
+	 * distribution.
+	*/
+	info->eu_per_subslice = info->subslice_total ?
+				DIV_ROUND_UP(info->eu_total,
+					     info->subslice_total) : 0;
+	/*
+	 * SKL supports slice power gating on devices with more than
+	 * one slice, and supports EU power gating on devices with
+	 * more than one EU pair per subslice. BXT supports subslice
+	 * power gating on devices with more than one subslice, and
+	 * supports EU power gating on devices with more than one EU
+	 * pair per subslice.
+	*/
+	info->has_slice_pg = (IS_SKYLAKE(dev) && (info->slice_total > 1));
+	info->has_subslice_pg = (IS_BROXTON(dev) && (info->subslice_total > 1));
+	info->has_eu_pg = (info->eu_per_subslice > 2);
+}
+
 /*
  * Determine various intel_device_info fields at runtime.
  *
@@ -585,7 +719,11 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 
 	info = (struct intel_device_info *)&dev_priv->info;
 
-	if (IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen == 9)
+	if (IS_BROXTON(dev)) {
+		info->num_sprites[PIPE_A] = 3;
+		info->num_sprites[PIPE_B] = 3;
+		info->num_sprites[PIPE_C] = 2;
+	} else if (IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen == 9)
 		for_each_pipe(dev_priv, pipe)
 			info->num_sprites[pipe] = 2;
 	else
@@ -620,116 +758,11 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 	}
 
 	/* Initialize slice/subslice/EU info */
-	if (IS_CHERRYVIEW(dev)) {
-		u32 fuse, eu_dis;
-
-		fuse = I915_READ(CHV_FUSE_GT);
-
-		info->slice_total = 1;
-
-		if (!(fuse & CHV_FGT_DISABLE_SS0)) {
-			info->subslice_per_slice++;
-			eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK |
-					 CHV_FGT_EU_DIS_SS0_R1_MASK);
-			info->eu_total += 8 - hweight32(eu_dis);
-		}
-
-		if (!(fuse & CHV_FGT_DISABLE_SS1)) {
-			info->subslice_per_slice++;
-			eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK |
-					CHV_FGT_EU_DIS_SS1_R1_MASK);
-			info->eu_total += 8 - hweight32(eu_dis);
-		}
-
-		info->subslice_total = info->subslice_per_slice;
-		/*
-		 * CHV expected to always have a uniform distribution of EU
-		 * across subslices.
-		*/
-		info->eu_per_subslice = info->subslice_total ?
-					info->eu_total / info->subslice_total :
-					0;
-		/*
-		 * CHV supports subslice power gating on devices with more than
-		 * one subslice, and supports EU power gating on devices with
-		 * more than one EU pair per subslice.
-		*/
-		info->has_slice_pg = 0;
-		info->has_subslice_pg = (info->subslice_total > 1);
-		info->has_eu_pg = (info->eu_per_subslice > 2);
-	} else if (IS_SKYLAKE(dev)) {
-		const int s_max = 3, ss_max = 4, eu_max = 8;
-		int s, ss;
-		u32 fuse2, eu_disable[s_max], s_enable, ss_disable;
-
-		fuse2 = I915_READ(GEN8_FUSE2);
-		s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >>
-			   GEN8_F2_S_ENA_SHIFT;
-		ss_disable = (fuse2 & GEN9_F2_SS_DIS_MASK) >>
-			     GEN9_F2_SS_DIS_SHIFT;
-
-		eu_disable[0] = I915_READ(GEN8_EU_DISABLE0);
-		eu_disable[1] = I915_READ(GEN8_EU_DISABLE1);
-		eu_disable[2] = I915_READ(GEN8_EU_DISABLE2);
-
-		info->slice_total = hweight32(s_enable);
-		/*
-		 * The subslice disable field is global, i.e. it applies
-		 * to each of the enabled slices.
-		*/
-		info->subslice_per_slice = ss_max - hweight32(ss_disable);
-		info->subslice_total = info->slice_total *
-				       info->subslice_per_slice;
-
-		/*
-		 * Iterate through enabled slices and subslices to
-		 * count the total enabled EU.
-		*/
-		for (s = 0; s < s_max; s++) {
-			if (!(s_enable & (0x1 << s)))
-				/* skip disabled slice */
-				continue;
-
-			for (ss = 0; ss < ss_max; ss++) {
-				u32 n_disabled;
-
-				if (ss_disable & (0x1 << ss))
-					/* skip disabled subslice */
-					continue;
+	if (IS_CHERRYVIEW(dev))
+		cherryview_sseu_info_init(dev);
+	else if (INTEL_INFO(dev)->gen >= 9)
+		gen9_sseu_info_init(dev);
 
-				n_disabled = hweight8(eu_disable[s] >>
-						      (ss * eu_max));
-
-				/*
-				 * Record which subslice(s) has(have) 7 EUs. we
-				 * can tune the hash used to spread work among
-				 * subslices if they are unbalanced.
-				 */
-				if (eu_max - n_disabled == 7)
-					info->subslice_7eu[s] |= 1 << ss;
-
-				info->eu_total += eu_max - n_disabled;
-			}
-		}
-
-		/*
-		 * SKL is expected to always have a uniform distribution
-		 * of EU across subslices with the exception that any one
-		 * EU in any one subslice may be fused off for die
-		 * recovery.
-		*/
-		info->eu_per_subslice = info->subslice_total ?
-					DIV_ROUND_UP(info->eu_total,
-						     info->subslice_total) : 0;
-		/*
-		 * SKL supports slice power gating on devices with more than
-		 * one slice, and supports EU power gating on devices with
-		 * more than one EU pair per subslice.
-		*/
-		info->has_slice_pg = (info->slice_total > 1) ? 1 : 0;
-		info->has_subslice_pg = 0;
-		info->has_eu_pg = (info->eu_per_subslice > 2) ? 1 : 0;
-	}
 	DRM_DEBUG_DRIVER("slice total: %u\n", info->slice_total);
 	DRM_DEBUG_DRIVER("subslice total: %u\n", info->subslice_total);
 	DRM_DEBUG_DRIVER("subslice per slice: %u\n", info->subslice_per_slice);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 182d6a742778..c1a3cdb5189b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -381,6 +381,18 @@ static const struct intel_device_info intel_skylake_gt3_info = {
 	IVB_CURSOR_OFFSETS,
 };
 
+static const struct intel_device_info intel_broxton_info = {
+	.is_preliminary = 1,
+	.gen = 9,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.num_pipes = 3,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
@@ -420,7 +432,8 @@ static const struct intel_device_info intel_skylake_gt3_info = {
 	INTEL_CHV_IDS(&intel_cherryview_info),	\
 	INTEL_SKL_GT1_IDS(&intel_skylake_info),	\
 	INTEL_SKL_GT2_IDS(&intel_skylake_info),	\
-	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info)	\
+	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),	\
+	INTEL_BXT_IDS(&intel_broxton_info)
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_PCI_IDS,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 745dcd84849d..3b2124930058 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -130,7 +130,7 @@ enum transcoder {
  *
  * This value doesn't count the cursor plane.
  */
-#define I915_MAX_PLANES	3
+#define I915_MAX_PLANES	4
 
 enum plane {
 	PLANE_A = 0,
@@ -2319,6 +2319,7 @@ struct drm_i915_cmd_table {
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_BROADWELL(dev)	(!INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_SKYLAKE(dev)	(INTEL_INFO(dev)->is_skylake)
+#define IS_BROXTON(dev)	(!INTEL_INFO(dev)->is_skylake && IS_GEN9(dev))
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
@@ -2343,6 +2344,10 @@ struct drm_i915_cmd_table {
 #define SKL_REVID_D0		(0x3)
 #define SKL_REVID_E0		(0x4)
 
+#define BXT_REVID_A0		(0x0)
+#define BXT_REVID_B0		(0x3)
+#define BXT_REVID_C0		(0x6)
+
 /*
  * The genX designation typically refers to the render engine, so render
  * capability related checks should use IS_GEN, while display and other checks
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0b679143772a..9041f3dfdfb4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1867,7 +1867,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 
 
 	if (INTEL_INFO(dev)->gen >= 8) {
-		if (IS_CHERRYVIEW(dev))
+		if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
 			chv_setup_private_ppat(dev_priv);
 		else
 			bdw_setup_private_ppat(dev_priv);
@@ -2433,7 +2433,17 @@ static int ggtt_probe_common(struct drm_device *dev,
 	gtt_phys_addr = pci_resource_start(dev->pdev, 0) +
 		(pci_resource_len(dev->pdev, 0) / 2);
 
-	dev_priv->gtt.gsm = ioremap_wc(gtt_phys_addr, gtt_size);
+	/*
+	 * On BXT writes larger than 64 bit to the GTT pagetable range will be
+	 * dropped. For WC mappings in general we have 64 byte burst writes
+	 * when the WC buffer is flushed, so we can't use it, but have to
+	 * resort to an uncached mapping. The WC issue is easily caught by the
+	 * readback check when writing GTT PTE entries.
+	 */
+	if (IS_BROXTON(dev))
+		dev_priv->gtt.gsm = ioremap_nocache(gtt_phys_addr, gtt_size);
+	else
+		dev_priv->gtt.gsm = ioremap_wc(gtt_phys_addr, gtt_size);
 	if (!dev_priv->gtt.gsm) {
 		DRM_ERROR("Failed to map the gtt page table\n");
 		return -ENOMEM;
@@ -2555,7 +2565,7 @@ static int gen8_gmch_probe(struct drm_device *dev,
 
 	*gtt_total = (gtt_size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
 
-	if (IS_CHERRYVIEW(dev))
+	if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
 		chv_setup_private_ppat(dev_priv);
 	else
 		bdw_setup_private_ppat(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index f8da71682c96..348ed5abcdbf 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -209,7 +209,7 @@ static int i915_setup_compression(struct drm_device *dev, int size, int fb_cpp)
 
 	dev_priv->fbc.threshold = ret;
 
-	if (HAS_PCH_SPLIT(dev))
+	if (INTEL_INFO(dev_priv)->gen >= 5)
 		I915_WRITE(ILK_DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
 	else if (IS_GM45(dev)) {
 		I915_WRITE(DPFC_CB_BASE, dev_priv->fbc.compressed_fb.start);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index da5c86acace5..87d9c0fbc7d9 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1148,6 +1148,7 @@ enum skl_disp_power_wells {
 /* control register for cpu gtt access */
 #define TILECTL				0x101000
 #define   TILECTL_SWZCTL			(1 << 0)
+#define   TILECTL_TLBPF			(1 << 1)
 #define   TILECTL_TLB_PREFETCH_DIS	(1 << 2)
 #define   TILECTL_BACKSNOOP_DIS		(1 << 3)
 
@@ -1552,9 +1553,7 @@ enum skl_disp_power_wells {
 #define   GEN9_F2_SS_DIS_SHIFT		20
 #define   GEN9_F2_SS_DIS_MASK		(0xf << GEN9_F2_SS_DIS_SHIFT)
 
-#define GEN8_EU_DISABLE0		0x9134
-#define GEN8_EU_DISABLE1		0x9138
-#define GEN8_EU_DISABLE2		0x913c
+#define GEN9_EU_DISABLE(slice)		(0x9134 + (slice)*0x4)
 
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	0x12050
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
@@ -5347,9 +5346,11 @@ enum skl_disp_power_wells {
 #define  GEN8_PIPE_VSYNC		(1 << 1)
 #define  GEN8_PIPE_VBLANK		(1 << 0)
 #define  GEN9_PIPE_CURSOR_FAULT		(1 << 11)
+#define  GEN9_PIPE_PLANE4_FAULT		(1 << 10)
 #define  GEN9_PIPE_PLANE3_FAULT		(1 << 9)
 #define  GEN9_PIPE_PLANE2_FAULT		(1 << 8)
 #define  GEN9_PIPE_PLANE1_FAULT		(1 << 7)
+#define  GEN9_PIPE_PLANE4_FLIP_DONE	(1 << 6)
 #define  GEN9_PIPE_PLANE3_FLIP_DONE	(1 << 5)
 #define  GEN9_PIPE_PLANE2_FLIP_DONE	(1 << 4)
 #define  GEN9_PIPE_PLANE1_FLIP_DONE	(1 << 3)
@@ -5360,6 +5361,7 @@ enum skl_disp_power_wells {
 	 GEN8_PIPE_PRIMARY_FAULT)
 #define GEN9_DE_PIPE_IRQ_FAULT_ERRORS \
 	(GEN9_PIPE_CURSOR_FAULT | \
+	 GEN9_PIPE_PLANE4_FAULT | \
 	 GEN9_PIPE_PLANE3_FAULT | \
 	 GEN9_PIPE_PLANE2_FAULT | \
 	 GEN9_PIPE_PLANE1_FAULT)
@@ -5477,6 +5479,10 @@ enum skl_disp_power_wells {
 #define  HDC_FORCE_NON_COHERENT			(1<<4)
 #define  HDC_BARRIER_PERFORMANCE_DISABLE	(1<<10)
 
+/* GEN9 chicken */
+#define SLICE_ECO_CHICKEN0			0x7308
+#define   PIXEL_MASK_CAMMING_DISABLE		(1 << 14)
+
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
@@ -6236,6 +6242,7 @@ enum skl_disp_power_wells {
 #define GEN8_UCGCTL6				0x9430
 #define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1<<24)
 #define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
+#define   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1<<28)
 
 #define GEN6_GFXPAUSE				0xA000
 #define GEN6_RPNSWREQ				0xA008
@@ -6403,17 +6410,12 @@ enum skl_disp_power_wells {
 #define CHV_POWER_SS1_SIG2		0xa72c
 #define   CHV_EU311_PG_ENABLE		(1<<1)
 
-#define GEN9_SLICE0_PGCTL_ACK		0x804c
-#define GEN9_SLICE1_PGCTL_ACK		0x8050
-#define GEN9_SLICE2_PGCTL_ACK		0x8054
+#define GEN9_SLICE_PGCTL_ACK(slice)	(0x804c + (slice)*0x4)
 #define   GEN9_PGCTL_SLICE_ACK		(1 << 0)
+#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice)*2))
 
-#define GEN9_SLICE0_SS01_EU_PGCTL_ACK	0x805c
-#define GEN9_SLICE0_SS23_EU_PGCTL_ACK	0x8060
-#define GEN9_SLICE1_SS01_EU_PGCTL_ACK	0x8064
-#define GEN9_SLICE1_SS23_EU_PGCTL_ACK	0x8068
-#define GEN9_SLICE2_SS01_EU_PGCTL_ACK	0x806c
-#define GEN9_SLICE2_SS23_EU_PGCTL_ACK	0x8070
+#define GEN9_SS01_EU_PGCTL_ACK(slice)	(0x805c + (slice)*0x8)
+#define GEN9_SS23_EU_PGCTL_ACK(slice)	(0x8060 + (slice)*0x8)
 #define   GEN9_PGCTL_SSA_EU08_ACK	(1 << 0)
 #define   GEN9_PGCTL_SSA_EU19_ACK	(1 << 2)
 #define   GEN9_PGCTL_SSA_EU210_ACK	(1 << 4)
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 486f6fa68db1..5b5048437115 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -322,7 +322,7 @@ static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 	uint32_t reg = DDI_BUF_CTL(port);
 	int i;
 
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < 16; i++) {
 		udelay(1);
 		if (I915_READ(reg) & DDI_BUF_IS_IDLE)
 			return;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 97922fb90824..9f72d9a76a38 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13505,7 +13505,16 @@ static void intel_setup_outputs(struct drm_device *dev)
 	if (intel_crt_present(dev))
 		intel_crt_init(dev);
 
-	if (HAS_DDI(dev)) {
+	if (IS_BROXTON(dev)) {
+		/*
+		 * FIXME: Broxton doesn't support port detection via the
+		 * DDI_BUF_CTL_A or SFUSE_STRAP registers, find another way to
+		 * detect the ports.
+		 */
+		intel_ddi_init(dev, PORT_A);
+		intel_ddi_init(dev, PORT_B);
+		intel_ddi_init(dev, PORT_C);
+	} else if (HAS_DDI(dev)) {
 		int found;
 
 		/*
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0fc35dd8a15c..a798d75f2a27 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1207,6 +1207,7 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	bool vf_flush_wa;
 	u32 flags = 0;
 	int ret;
 
@@ -1228,10 +1229,26 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
 	}
 
-	ret = intel_logical_ring_begin(ringbuf, ctx, 6);
+	/*
+	 * On GEN9+ Before VF_CACHE_INVALIDATE we need to emit a NULL pipe
+	 * control.
+	 */
+	vf_flush_wa = INTEL_INFO(ring->dev)->gen >= 9 &&
+		      flags & PIPE_CONTROL_VF_CACHE_INVALIDATE;
+
+	ret = intel_logical_ring_begin(ringbuf, ctx, vf_flush_wa ? 12 : 6);
 	if (ret)
 		return ret;
 
+	if (vf_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf, flags);
 	intel_logical_ring_emit(ringbuf, scratch_addr);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index fc7e0c7545fd..a80bfd565ce4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -98,6 +98,26 @@ static void skl_init_clock_gating(struct drm_device *dev)
 			   GEN8_LQSC_RO_PERF_DIS);
 }
 
+static void bxt_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gen9_init_clock_gating(dev);
+
+	/*
+	 * FIXME:
+	 * GEN8_SDEUNIT_CLOCK_GATE_DISABLE applies on A0 only.
+	 * GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only.
+	 */
+	 /* WaDisableSDEUnitClockGating:bxt */
+	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE |
+		   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);
+
+	/* FIXME: apply on A0 only */
+	I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
+}
+
 static void i915_pineview_get_mem_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2542,6 +2562,7 @@ static bool ilk_disable_lp_wm(struct drm_device *dev)
  */
 
 #define SKL_DDB_SIZE		896	/* in blocks */
+#define BXT_DDB_SIZE		512
 
 static void
 skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
@@ -2560,7 +2581,10 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 		return;
 	}
 
-	ddb_size = SKL_DDB_SIZE;
+	if (IS_BROXTON(dev))
+		ddb_size = BXT_DDB_SIZE;
+	else
+		ddb_size = SKL_DDB_SIZE;
 
 	ddb_size -= 4; /* 4 blocks for bypass path allocation */
 
@@ -6570,7 +6594,12 @@ void intel_init_pm(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen >= 9) {
 		skl_setup_wm_latency(dev);
 
-		dev_priv->display.init_clock_gating = skl_init_clock_gating;
+		if (IS_BROXTON(dev))
+			dev_priv->display.init_clock_gating =
+				bxt_init_clock_gating;
+		else if (IS_SKYLAKE(dev))
+			dev_priv->display.init_clock_gating =
+				skl_init_clock_gating;
 		dev_priv->display.update_wm = skl_update_wm;
 		dev_priv->display.update_sprite_wm = skl_update_sprite_wm;
 	} else if (HAS_PCH_SPLIT(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 9f3fc81149a4..de8c0747aaef 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -969,6 +969,15 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
 			  GEN9_CCS_TLB_PREFETCH_ENABLE);
 
+	/*
+	 * FIXME: don't apply the following on BXT for stepping C. On BXT A0
+	 * the flag reads back as 0.
+	 */
+	/* WaDisableMaskBasedCammingInRCC:sklC,bxtA */
+	if (INTEL_REVID(dev) == SKL_REVID_C0 || IS_BROXTON(dev))
+		WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0,
+				  PIXEL_MASK_CAMMING_DISABLE);
+
 	return 0;
 }
 
@@ -1030,6 +1039,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 	return skl_tune_iz_hashing(ring);
 }
 
+static int bxt_init_workarounds(struct intel_engine_cs *ring)
+{
+	gen9_init_workarounds(ring);
+
+	return 0;
+}
+
 int init_workarounds_ring(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -1047,8 +1063,9 @@ int init_workarounds_ring(struct intel_engine_cs *ring)
 
 	if (IS_SKYLAKE(dev))
 		return skl_init_workarounds(ring);
-	else if (IS_GEN9(dev))
-		return gen9_init_workarounds(ring);
+
+	if (IS_BROXTON(dev))
+		return bxt_init_workarounds(ring);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 0cb37674b43a..e3d41c096dc6 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -1144,7 +1144,7 @@ int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, set->plane_id);
-	if (!plane) {
+	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY) {
 		ret = -ENOENT;
 		goto out_unlock;
 	}