Merge remote-tracking branch 'drm_intel_push/drm-intel-next' into drm-tip

# Conflicts:
#	drivers/gpu/drm/i915/i915_module.c

136 files changed, 3981 insertions, 3054 deletions

diff --git a/drivers/gpu/drm/dp/drm_dp.c b/drivers/gpu/drm/dp/drm_dp.c
index c43577c8ac4d..e159b81800d4 100644
--- a/drivers/gpu/drm/dp/drm_dp.c
+++ b/drivers/gpu/drm/dp/drm_dp.c
@@ -145,6 +145,69 @@ u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_get_adjust_tx_ffe_preset);
 
+/* DP 2.0 errata for 128b/132b */
+bool drm_dp_128b132b_lane_channel_eq_done(const u8 link_status[DP_LINK_STATUS_SIZE],
+					  int lane_count)
+{
+	u8 lane_align, lane_status;
+	int lane;
+
+	lane_align = dp_link_status(link_status, DP_LANE_ALIGN_STATUS_UPDATED);
+	if (!(lane_align & DP_INTERLANE_ALIGN_DONE))
+		return false;
+
+	for (lane = 0; lane < lane_count; lane++) {
+		lane_status = dp_get_lane_status(link_status, lane);
+		if (!(lane_status & DP_LANE_CHANNEL_EQ_DONE))
+			return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_lane_channel_eq_done);
+
+/* DP 2.0 errata for 128b/132b */
+bool drm_dp_128b132b_lane_symbol_locked(const u8 link_status[DP_LINK_STATUS_SIZE],
+					int lane_count)
+{
+	u8 lane_status;
+	int lane;
+
+	for (lane = 0; lane < lane_count; lane++) {
+		lane_status = dp_get_lane_status(link_status, lane);
+		if (!(lane_status & DP_LANE_SYMBOL_LOCKED))
+			return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_lane_symbol_locked);
+
+/* DP 2.0 errata for 128b/132b */
+bool drm_dp_128b132b_eq_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE])
+{
+	u8 status = dp_link_status(link_status, DP_LANE_ALIGN_STATUS_UPDATED);
+
+	return status & DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_eq_interlane_align_done);
+
+/* DP 2.0 errata for 128b/132b */
+bool drm_dp_128b132b_cds_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE])
+{
+	u8 status = dp_link_status(link_status, DP_LANE_ALIGN_STATUS_UPDATED);
+
+	return status & DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_cds_interlane_align_done);
+
+/* DP 2.0 errata for 128b/132b */
+bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SIZE])
+{
+	u8 status = dp_link_status(link_status, DP_LANE_ALIGN_STATUS_UPDATED);
+
+	return status & DP_128B132B_LT_FAILED;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_link_training_failed);
+
 u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE],
 					 unsigned int lane)
 {
@@ -282,6 +345,26 @@ int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIV
 }
 EXPORT_SYMBOL(drm_dp_read_channel_eq_delay);
 
+/* Per DP 2.0 Errata */
+int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux)
+{
+	int unit;
+	u8 val;
+
+	if (drm_dp_dpcd_readb(aux, DP_128B132B_TRAINING_AUX_RD_INTERVAL, &val) != 1) {
+		drm_err(aux->drm_dev, "%s: failed rd interval read\n",
+			aux->name);
+		/* default to max */
+		val = DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK;
+	}
+
+	unit = (val & DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT) ? 1 : 2;
+	val &= DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK;
+
+	return (val + 1) * unit * 1000;
+}
+EXPORT_SYMBOL(drm_dp_128b132b_read_aux_rd_interval);
+
 void drm_dp_link_train_clock_recovery_delay(const struct drm_dp_aux *aux,
 					    const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 139e0e7eba94..7686f46e42a4 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -13,6 +13,7 @@
 # will most likely get a sudden build breakage... Hopefully we will fix
 # new warnings before CI updates!
 subdir-ccflags-y := -Wall -Wextra
+subdir-ccflags-y += -Wno-format-security
 subdir-ccflags-y += -Wno-unused-parameter
 subdir-ccflags-y += -Wno-type-limits
 subdir-ccflags-y += -Wno-missing-field-initializers
@@ -197,6 +198,7 @@ i915-y += gt/uc/intel_uc.o \
 
 # modesetting core code
 i915-y += \
+	display/hsw_ips.o \
 	display/intel_atomic.o \
 	display/intel_atomic_plane.o \
 	display/intel_audio.o \
diff --git a/drivers/gpu/drm/i915/display/hsw_ips.c b/drivers/gpu/drm/i915/display/hsw_ips.c
new file mode 100644
index 000000000000..38014e0cc9ad
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/hsw_ips.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "hsw_ips.h"
+#include "i915_drv.h"
+#include "i915_reg.h"
+#include "intel_de.h"
+#include "intel_display_types.h"
+#include "intel_pcode.h"
+
+static void hsw_ips_enable(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	if (!crtc_state->ips_enabled)
+		return;
+
+	/*
+	 * We can only enable IPS after we enable a plane and wait for a vblank
+	 * This function is called from post_plane_update, which is run after
+	 * a vblank wait.
+	 */
+	drm_WARN_ON(&i915->drm,
+		    !(crtc_state->active_planes & ~BIT(PLANE_CURSOR)));
+
+	if (IS_BROADWELL(i915)) {
+		drm_WARN_ON(&i915->drm,
+			    snb_pcode_write(i915, DISPLAY_IPS_CONTROL,
+					    IPS_ENABLE | IPS_PCODE_CONTROL));
+		/*
+		 * Quoting Art Runyan: "its not safe to expect any particular
+		 * value in IPS_CTL bit 31 after enabling IPS through the
+		 * mailbox." Moreover, the mailbox may return a bogus state,
+		 * so we need to just enable it and continue on.
+		 */
+	} else {
+		intel_de_write(i915, IPS_CTL, IPS_ENABLE);
+		/*
+		 * The bit only becomes 1 in the next vblank, so this wait here
+		 * is essentially intel_wait_for_vblank. If we don't have this
+		 * and don't wait for vblanks until the end of crtc_enable, then
+		 * the HW state readout code will complain that the expected
+		 * IPS_CTL value is not the one we read.
+		 */
+		if (intel_de_wait_for_set(i915, IPS_CTL, IPS_ENABLE, 50))
+			drm_err(&i915->drm,
+				"Timed out waiting for IPS enable\n");
+	}
+}
+
+bool hsw_ips_disable(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	bool need_vblank_wait = false;
+
+	if (!crtc_state->ips_enabled)
+		return need_vblank_wait;
+
+	if (IS_BROADWELL(i915)) {
+		drm_WARN_ON(&i915->drm,
+			    snb_pcode_write(i915, DISPLAY_IPS_CONTROL, 0));
+		/*
+		 * Wait for PCODE to finish disabling IPS. The BSpec specified
+		 * 42ms timeout value leads to occasional timeouts so use 100ms
+		 * instead.
+		 */
+		if (intel_de_wait_for_clear(i915, IPS_CTL, IPS_ENABLE, 100))
+			drm_err(&i915->drm,
+				"Timed out waiting for IPS disable\n");
+	} else {
+		intel_de_write(i915, IPS_CTL, 0);
+		intel_de_posting_read(i915, IPS_CTL);
+	}
+
+	/* We need to wait for a vblank before we can disable the plane. */
+	need_vblank_wait = true;
+
+	return need_vblank_wait;
+}
+
+static bool hsw_ips_need_disable(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+
+	if (!old_crtc_state->ips_enabled)
+		return false;
+
+	if (intel_crtc_needs_modeset(new_crtc_state))
+		return true;
+
+	/*
+	 * 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.
+	 *
+	 * Disable IPS before we program the LUT.
+	 */
+	if (IS_HASWELL(i915) &&
+	    (new_crtc_state->uapi.color_mgmt_changed ||
+	     new_crtc_state->update_pipe) &&
+	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
+		return true;
+
+	return !new_crtc_state->ips_enabled;
+}
+
+bool hsw_ips_pre_update(struct intel_atomic_state *state,
+			struct intel_crtc *crtc)
+{
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	if (!hsw_ips_need_disable(state, crtc))
+		return false;
+
+	return hsw_ips_disable(old_crtc_state);
+}
+
+static bool hsw_ips_need_enable(struct intel_atomic_state *state,
+				struct intel_crtc *crtc)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+
+	if (!new_crtc_state->ips_enabled)
+		return false;
+
+	if (intel_crtc_needs_modeset(new_crtc_state))
+		return true;
+
+	/*
+	 * 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.
+	 *
+	 * Re-enable IPS after the LUT has been programmed.
+	 */
+	if (IS_HASWELL(i915) &&
+	    (new_crtc_state->uapi.color_mgmt_changed ||
+	     new_crtc_state->update_pipe) &&
+	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
+		return true;
+
+	/*
+	 * We can't read out IPS on broadwell, assume the worst and
+	 * forcibly enable IPS on the first fastset.
+	 */
+	if (new_crtc_state->update_pipe && old_crtc_state->inherited)
+		return true;
+
+	return !old_crtc_state->ips_enabled;
+}
+
+void hsw_ips_post_update(struct intel_atomic_state *state,
+			 struct intel_crtc *crtc)
+{
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+
+	if (!hsw_ips_need_enable(state, crtc))
+		return;
+
+	hsw_ips_enable(new_crtc_state);
+}
+
+/* IPS only exists on ULT machines and is tied to pipe A. */
+bool hsw_crtc_supports_ips(struct intel_crtc *crtc)
+{
+	return HAS_IPS(to_i915(crtc->base.dev)) && crtc->pipe == PIPE_A;
+}
+
+bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	/* IPS only exists on ULT machines and is tied to pipe A. */
+	if (!hsw_crtc_supports_ips(crtc))
+		return false;
+
+	if (!i915->params.enable_ips)
+		return false;
+
+	if (crtc_state->pipe_bpp > 24)
+		return false;
+
+	/*
+	 * We compare against max which means we must take
+	 * the increased cdclk requirement into account when
+	 * calculating the new cdclk.
+	 *
+	 * Should measure whether using a lower cdclk w/o IPS
+	 */
+	if (IS_BROADWELL(i915) &&
+	    crtc_state->pixel_rate > i915->max_cdclk_freq * 95 / 100)
+		return false;
+
+	return true;
+}
+
+int hsw_ips_compute_config(struct intel_atomic_state *state,
+			   struct intel_crtc *crtc)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+
+	crtc_state->ips_enabled = false;
+
+	if (!hsw_crtc_state_ips_capable(crtc_state))
+		return 0;
+
+	/*
+	 * When IPS gets enabled, the pipe CRC changes. Since IPS gets
+	 * enabled and disabled dynamically based on package C states,
+	 * user space can't make reliable use of the CRCs, so let's just
+	 * completely disable it.
+	 */
+	if (crtc_state->crc_enabled)
+		return 0;
+
+	/* IPS should be fine as long as at least one plane is enabled. */
+	if (!(crtc_state->active_planes & ~BIT(PLANE_CURSOR)))
+		return 0;
+
+	if (IS_BROADWELL(i915)) {
+		const struct intel_cdclk_state *cdclk_state;
+
+		cdclk_state = intel_atomic_get_cdclk_state(state);
+		if (IS_ERR(cdclk_state))
+			return PTR_ERR(cdclk_state);
+
+		/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+		if (crtc_state->pixel_rate > cdclk_state->logical.cdclk * 95 / 100)
+			return 0;
+	}
+
+	crtc_state->ips_enabled = true;
+
+	return 0;
+}
+
+void hsw_ips_get_config(struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	if (!hsw_crtc_supports_ips(crtc))
+		return;
+
+	if (IS_HASWELL(i915)) {
+		crtc_state->ips_enabled = intel_de_read(i915, IPS_CTL) & IPS_ENABLE;
+	} else {
+		/*
+		 * We cannot readout IPS state on broadwell, set to
+		 * true so we can set it to a defined state on first
+		 * commit.
+		 */
+		crtc_state->ips_enabled = true;
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/hsw_ips.h b/drivers/gpu/drm/i915/display/hsw_ips.h
new file mode 100644
index 000000000000..4564dee497d7
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/hsw_ips.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __HSW_IPS_H__
+#define __HSW_IPS_H__
+
+#include <linux/types.h>
+
+struct intel_atomic_state;
+struct intel_crtc;
+struct intel_crtc_state;
+
+bool hsw_ips_disable(const struct intel_crtc_state *crtc_state);
+bool hsw_ips_pre_update(struct intel_atomic_state *state,
+			struct intel_crtc *crtc);
+void hsw_ips_post_update(struct intel_atomic_state *state,
+			 struct intel_crtc *crtc);
+bool hsw_crtc_supports_ips(struct intel_crtc *crtc);
+bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state);
+int hsw_ips_compute_config(struct intel_atomic_state *state,
+			   struct intel_crtc *crtc);
+void hsw_ips_get_config(struct intel_crtc_state *crtc_state);
+
+#endif /* __HSW_IPS_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index 093904065112..e0667d163266 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -281,17 +281,6 @@ void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state)
 	intel_crtc_put_color_blobs(crtc_state);
 }
 
-void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state,
-				 const struct intel_crtc_state *from_crtc_state)
-{
-	drm_property_replace_blob(&crtc_state->hw.degamma_lut,
-				  from_crtc_state->uapi.degamma_lut);
-	drm_property_replace_blob(&crtc_state->hw.gamma_lut,
-				  from_crtc_state->uapi.gamma_lut);
-	drm_property_replace_blob(&crtc_state->hw.ctm,
-				  from_crtc_state->uapi.ctm);
-}
-
 /**
  * intel_crtc_destroy_state - destroy crtc state
  * @crtc: drm crtc
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h
index d2700c74c9da..1dc439983dd9 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic.h
@@ -44,8 +44,6 @@ struct drm_crtc_state *intel_crtc_duplicate_state(struct drm_crtc *crtc);
 void intel_crtc_destroy_state(struct drm_crtc *crtc,
 			       struct drm_crtc_state *state);
 void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state);
-void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state,
-				 const struct intel_crtc_state *from_crtc_state);
 struct drm_atomic_state *intel_atomic_state_alloc(struct drm_device *dev);
 void intel_atomic_state_free(struct drm_atomic_state *state);
 void intel_atomic_state_clear(struct drm_atomic_state *state);
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index bec02333bdeb..c53aa6a4c7a0 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -45,6 +45,7 @@
 #include "intel_fb_pin.h"
 #include "intel_pm.h"
 #include "intel_sprite.h"
+#include "skl_scaler.h"
 
 static void intel_plane_state_reset(struct intel_plane_state *plane_state,
 				    struct intel_plane *plane)
@@ -322,6 +323,7 @@ void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
 	crtc_state->active_planes &= ~BIT(plane->id);
+	crtc_state->scaled_planes &= ~BIT(plane->id);
 	crtc_state->nv12_planes &= ~BIT(plane->id);
 	crtc_state->c8_planes &= ~BIT(plane->id);
 	crtc_state->data_rate[plane->id] = 0;
@@ -330,6 +332,185 @@ void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
 	plane_state->uapi.visible = false;
 }
 
+/* FIXME nuke when all wm code is atomic */
+static bool intel_wm_need_update(const struct intel_plane_state *cur,
+				 struct intel_plane_state *new)
+{
+	/* Update watermarks on tiling or size changes. */
+	if (new->uapi.visible != cur->uapi.visible)
+		return true;
+
+	if (!cur->hw.fb || !new->hw.fb)
+		return false;
+
+	if (cur->hw.fb->modifier != new->hw.fb->modifier ||
+	    cur->hw.rotation != new->hw.rotation ||
+	    drm_rect_width(&new->uapi.src) != drm_rect_width(&cur->uapi.src) ||
+	    drm_rect_height(&new->uapi.src) != drm_rect_height(&cur->uapi.src) ||
+	    drm_rect_width(&new->uapi.dst) != drm_rect_width(&cur->uapi.dst) ||
+	    drm_rect_height(&new->uapi.dst) != drm_rect_height(&cur->uapi.dst))
+		return true;
+
+	return false;
+}
+
+static bool intel_plane_is_scaled(const struct intel_plane_state *plane_state)
+{
+	int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	int src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	int dst_w = drm_rect_width(&plane_state->uapi.dst);
+	int dst_h = drm_rect_height(&plane_state->uapi.dst);
+
+	return src_w != dst_w || src_h != dst_h;
+}
+
+static bool intel_plane_do_async_flip(struct intel_plane *plane,
+				      const struct intel_crtc_state *old_crtc_state,
+				      const struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+
+	if (!plane->async_flip)
+		return false;
+
+	if (!new_crtc_state->uapi.async_flip)
+		return false;
+
+	/*
+	 * In platforms after DISPLAY13, we might need to override
+	 * first async flip in order to change watermark levels
+	 * as part of optimization.
+	 * So for those, we are checking if this is a first async flip.
+	 * For platforms earlier than DISPLAY13 we always do async flip.
+	 */
+	return DISPLAY_VER(i915) < 13 || old_crtc_state->uapi.async_flip;
+}
+
+static int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state,
+					   struct intel_crtc_state *new_crtc_state,
+					   const struct intel_plane_state *old_plane_state,
+					   struct intel_plane_state *new_plane_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
+	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	bool mode_changed = intel_crtc_needs_modeset(new_crtc_state);
+	bool was_crtc_enabled = old_crtc_state->hw.active;
+	bool is_crtc_enabled = new_crtc_state->hw.active;
+	bool turn_off, turn_on, visible, was_visible;
+	int ret;
+
+	if (DISPLAY_VER(dev_priv) >= 9 && plane->id != PLANE_CURSOR) {
+		ret = skl_update_scaler_plane(new_crtc_state, new_plane_state);
+		if (ret)
+			return ret;
+	}
+
+	was_visible = old_plane_state->uapi.visible;
+	visible = new_plane_state->uapi.visible;
+
+	if (!was_crtc_enabled && drm_WARN_ON(&dev_priv->drm, was_visible))
+		was_visible = false;
+
+	/*
+	 * Visibility is calculated as if the crtc was on, but
+	 * after scaler setup everything depends on it being off
+	 * when the crtc isn't active.
+	 *
+	 * FIXME this is wrong for watermarks. Watermarks should also
+	 * be computed as if the pipe would be active. Perhaps move
+	 * per-plane wm computation to the .check_plane() hook, and
+	 * only combine the results from all planes in the current place?
+	 */
+	if (!is_crtc_enabled) {
+		intel_plane_set_invisible(new_crtc_state, new_plane_state);
+		visible = false;
+	}
+
+	if (!was_visible && !visible)
+		return 0;
+
+	turn_off = was_visible && (!visible || mode_changed);
+	turn_on = visible && (!was_visible || mode_changed);
+
+	drm_dbg_atomic(&dev_priv->drm,
+		       "[CRTC:%d:%s] with [PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n",
+		       crtc->base.base.id, crtc->base.name,
+		       plane->base.base.id, plane->base.name,
+		       was_visible, visible,
+		       turn_off, turn_on, mode_changed);
+
+	if (turn_on) {
+		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
+			new_crtc_state->update_wm_pre = true;
+
+		/* must disable cxsr around plane enable/disable */
+		if (plane->id != PLANE_CURSOR)
+			new_crtc_state->disable_cxsr = true;
+	} else if (turn_off) {
+		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
+			new_crtc_state->update_wm_post = true;
+
+		/* must disable cxsr around plane enable/disable */
+		if (plane->id != PLANE_CURSOR)
+			new_crtc_state->disable_cxsr = true;
+	} else if (intel_wm_need_update(old_plane_state, new_plane_state)) {
+		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) {
+			/* FIXME bollocks */
+			new_crtc_state->update_wm_pre = true;
+			new_crtc_state->update_wm_post = true;
+		}
+	}
+
+	if (visible || was_visible)
+		new_crtc_state->fb_bits |= plane->frontbuffer_bit;
+
+	/*
+	 * ILK/SNB DVSACNTR/Sprite Enable
+	 * IVB SPR_CTL/Sprite Enable
+	 * "When in Self Refresh Big FIFO mode, a write to enable the
+	 *  plane will be internally buffered and delayed while Big FIFO
+	 *  mode is exiting."
+	 *
+	 * Which means that enabling the sprite can take an extra frame
+	 * when we start in big FIFO mode (LP1+). Thus we need to drop
+	 * down to LP0 and wait for vblank in order to make sure the
+	 * sprite gets enabled on the next vblank after the register write.
+	 * Doing otherwise would risk enabling the sprite one frame after
+	 * we've already signalled flip completion. We can resume LP1+
+	 * once the sprite has been enabled.
+	 *
+	 *
+	 * WaCxSRDisabledForSpriteScaling:ivb
+	 * IVB SPR_SCALE/Scaling Enable
+	 * "Low Power watermarks must be disabled for at least one
+	 *  frame before enabling sprite scaling, and kept disabled
+	 *  until sprite scaling is disabled."
+	 *
+	 * ILK/SNB DVSASCALE/Scaling Enable
+	 * "When in Self Refresh Big FIFO mode, scaling enable will be
+	 *  masked off while Big FIFO mode is exiting."
+	 *
+	 * Despite the w/a only being listed for IVB we assume that
+	 * the ILK/SNB note has similar ramifications, hence we apply
+	 * the w/a on all three platforms.
+	 *
+	 * With experimental results seems this is needed also for primary
+	 * plane, not only sprite plane.
+	 */
+	if (plane->id != PLANE_CURSOR &&
+	    (IS_IRONLAKE(dev_priv) || IS_SANDYBRIDGE(dev_priv) ||
+	     IS_IVYBRIDGE(dev_priv)) &&
+	    (turn_on || (!intel_plane_is_scaled(old_plane_state) &&
+			 intel_plane_is_scaled(new_plane_state))))
+		new_crtc_state->disable_lp_wm = true;
+
+	if (intel_plane_do_async_flip(plane, old_crtc_state, new_crtc_state))
+		new_plane_state->do_async_flip = true;
+
+	return 0;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
@@ -357,6 +538,10 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		new_crtc_state->active_planes |= BIT(plane->id);
 
 	if (new_plane_state->uapi.visible &&
+	    intel_plane_is_scaled(new_plane_state))
+		new_crtc_state->scaled_planes |= BIT(plane->id);
+
+	if (new_plane_state->uapi.visible &&
 	    intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		new_crtc_state->nv12_planes |= BIT(plane->id);
 
@@ -403,10 +588,11 @@ int intel_plane_atomic_check(struct intel_atomic_state *state,
 	struct intel_crtc_state *new_crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
 
-	if (new_crtc_state && new_crtc_state->bigjoiner_slave) {
+	if (new_crtc_state && intel_crtc_is_bigjoiner_slave(new_crtc_state)) {
+		struct intel_crtc *master_crtc =
+			intel_master_crtc(new_crtc_state);
 		struct intel_plane *master_plane =
-			intel_crtc_get_plane(new_crtc_state->bigjoiner_linked_crtc,
-					     plane->id);
+			intel_crtc_get_plane(master_crtc, plane->id);
 
 		new_master_plane_state =
 			intel_atomic_get_new_plane_state(state, master_plane);
@@ -507,8 +693,8 @@ void intel_plane_disable_arm(struct intel_plane *plane,
 	plane->disable_arm(plane, crtc_state);
 }
 
-void intel_update_planes_on_crtc(struct intel_atomic_state *state,
-				 struct intel_crtc *crtc)
+void intel_crtc_planes_update_noarm(struct intel_atomic_state *state,
+				    struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *new_crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
@@ -536,8 +722,8 @@ void intel_update_planes_on_crtc(struct intel_atomic_state *state,
 	}
 }
 
-void skl_arm_planes_on_crtc(struct intel_atomic_state *state,
-			    struct intel_crtc *crtc)
+static void skl_crtc_planes_update_arm(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
@@ -571,8 +757,8 @@ void skl_arm_planes_on_crtc(struct intel_atomic_state *state,
 	}
 }
 
-void i9xx_arm_planes_on_crtc(struct intel_atomic_state *state,
-			     struct intel_crtc *crtc)
+static void i9xx_crtc_planes_update_arm(struct intel_atomic_state *state,
+					struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *new_crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
@@ -597,6 +783,17 @@ void i9xx_arm_planes_on_crtc(struct intel_atomic_state *state,
 	}
 }
 
+void intel_crtc_planes_update_arm(struct intel_atomic_state *state,
+				  struct intel_crtc *crtc)
+{
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+
+	if (DISPLAY_VER(i915) >= 9)
+		skl_crtc_planes_update_arm(state, crtc);
+	else
+		i9xx_crtc_planes_update_arm(state, crtc);
+}
+
 int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state,
 				      struct intel_crtc_state *crtc_state,
 				      int min_scale, int max_scale,
@@ -633,7 +830,7 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state,
 	}
 
 	/* right side of the image is on the slave crtc, adjust dst to match */
-	if (crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(crtc_state))
 		drm_rect_translate(dst, -crtc_state->pipe_src_w, 0);
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index ead789709477..f4763a53541e 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -44,22 +44,16 @@ void intel_plane_free(struct intel_plane *plane);
 struct drm_plane_state *intel_plane_duplicate_state(struct drm_plane *plane);
 void intel_plane_destroy_state(struct drm_plane *plane,
 			       struct drm_plane_state *state);
-void intel_update_planes_on_crtc(struct intel_atomic_state *state,
-				 struct intel_crtc *crtc);
-void skl_arm_planes_on_crtc(struct intel_atomic_state *state,
-			    struct intel_crtc *crtc);
-void i9xx_arm_planes_on_crtc(struct intel_atomic_state *state,
-			     struct intel_crtc *crtc);
+void intel_crtc_planes_update_noarm(struct intel_atomic_state *state,
+				    struct intel_crtc *crtc);
+void intel_crtc_planes_update_arm(struct intel_atomic_state *state,
+				  struct intel_crtc *crtc);
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *crtc_state,
 					const struct intel_plane_state *old_plane_state,
 					struct intel_plane_state *intel_state);
 int intel_plane_atomic_check(struct intel_atomic_state *state,
 			     struct intel_plane *plane);
-int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state,
-				    struct intel_crtc_state *crtc_state,
-				    const struct intel_plane_state *old_plane_state,
-				    struct intel_plane_state *plane_state);
 int intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 			       struct intel_plane *plane,
 			       bool *need_cdclk_calc);
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index aec0efd5350e..40b5e7ed12c2 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -596,6 +596,12 @@ parse_general_features(struct drm_i915_private *i915,
 	} else {
 		i915->vbt.orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
 	}
+
+	if (bdb->version >= 249 && general->afc_startup_config) {
+		i915->vbt.override_afc_startup = true;
+		i915->vbt.override_afc_startup_val = general->afc_startup_config == 0x1 ? 0x0 : 0x7;
+	}
+
 	drm_dbg_kms(&i915->drm,
 		    "BDB_GENERAL_FEATURES int_tv_support %d int_crt_support %d lvds_use_ssc %d lvds_ssc_freq %d display_clock_mode %d fdi_rx_polarity_inverted %d\n",
 		    i915->vbt.int_tv_support,
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 5dce3cf0ed12..7bbe0dc5926b 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -10,6 +10,7 @@
 #include "intel_bw.h"
 #include "intel_cdclk.h"
 #include "intel_display_types.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 #include "intel_pm.h"
 
@@ -673,6 +674,49 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state)
 	return to_intel_bw_state(bw_state);
 }
 
+static void skl_crtc_calc_dbuf_bw(struct intel_bw_state *bw_state,
+				  const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	struct intel_dbuf_bw *crtc_bw = &bw_state->dbuf_bw[crtc->pipe];
+	enum plane_id plane_id;
+
+	memset(&crtc_bw->used_bw, 0, sizeof(crtc_bw->used_bw));
+
+	if (!crtc_state->hw.active)
+		return;
+
+	for_each_plane_id_on_crtc(crtc, plane_id) {
+		const struct skl_ddb_entry *ddb_y =
+			&crtc_state->wm.skl.plane_ddb_y[plane_id];
+		const struct skl_ddb_entry *ddb_uv =
+			&crtc_state->wm.skl.plane_ddb_uv[plane_id];
+		unsigned int data_rate = crtc_state->data_rate[plane_id];
+		unsigned int dbuf_mask = 0;
+		enum dbuf_slice slice;
+
+		dbuf_mask |= skl_ddb_dbuf_slice_mask(i915, ddb_y);
+		dbuf_mask |= skl_ddb_dbuf_slice_mask(i915, ddb_uv);
+
+		/*
+		 * FIXME: To calculate that more properly we probably
+		 * need to split per plane data_rate into data_rate_y
+		 * and data_rate_uv for multiplanar formats in order not
+		 * to get accounted those twice if they happen to reside
+		 * on different slices.
+		 * However for pre-icl this would work anyway because
+		 * we have only single slice and for icl+ uv plane has
+		 * non-zero data rate.
+		 * So in worst case those calculation are a bit
+		 * pessimistic, which shouldn't pose any significant
+		 * problem anyway.
+		 */
+		for_each_dbuf_slice_in_mask(i915, slice, dbuf_mask)
+			crtc_bw->used_bw[slice] += data_rate;
+	}
+}
+
 int skl_bw_calc_min_cdclk(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
@@ -685,50 +729,13 @@ int skl_bw_calc_min_cdclk(struct intel_atomic_state *state)
 	int i;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		enum plane_id plane_id;
-		struct intel_dbuf_bw *crtc_bw;
-
 		new_bw_state = intel_atomic_get_bw_state(state);
 		if (IS_ERR(new_bw_state))
 			return PTR_ERR(new_bw_state);
 
 		old_bw_state = intel_atomic_get_old_bw_state(state);
 
-		crtc_bw = &new_bw_state->dbuf_bw[crtc->pipe];
-
-		memset(&crtc_bw->used_bw, 0, sizeof(crtc_bw->used_bw));
-
-		if (!crtc_state->hw.active)
-			continue;
-
-		for_each_plane_id_on_crtc(crtc, plane_id) {
-			const struct skl_ddb_entry *plane_alloc =
-				&crtc_state->wm.skl.plane_ddb_y[plane_id];
-			const struct skl_ddb_entry *uv_plane_alloc =
-				&crtc_state->wm.skl.plane_ddb_uv[plane_id];
-			unsigned int data_rate = crtc_state->data_rate[plane_id];
-			unsigned int dbuf_mask = 0;
-			enum dbuf_slice slice;
-
-			dbuf_mask |= skl_ddb_dbuf_slice_mask(dev_priv, plane_alloc);
-			dbuf_mask |= skl_ddb_dbuf_slice_mask(dev_priv, uv_plane_alloc);
-
-			/*
-			 * FIXME: To calculate that more properly we probably
-			 * need to to split per plane data_rate into data_rate_y
-			 * and data_rate_uv for multiplanar formats in order not
-			 * to get accounted those twice if they happen to reside
-			 * on different slices.
-			 * However for pre-icl this would work anyway because
-			 * we have only single slice and for icl+ uv plane has
-			 * non-zero data rate.
-			 * So in worst case those calculation are a bit
-			 * pessimistic, which shouldn't pose any significant
-			 * problem anyway.
-			 */
-			for_each_dbuf_slice_in_mask(dev_priv, slice, dbuf_mask)
-				crtc_bw->used_bw[slice] += data_rate;
-		}
+		skl_crtc_calc_dbuf_bw(new_bw_state, crtc_state);
 	}
 
 	if (!old_bw_state)
diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h
index 46c6eecbd917..0ceaed1c9656 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_bw.h
@@ -30,19 +30,19 @@ struct intel_bw_state {
 	 */
 	u8 pipe_sagv_reject;
 
+	/* bitmask of active pipes */
+	u8 active_pipes;
+
 	/*
 	 * Current QGV points mask, which restricts
 	 * some particular SAGV states, not to confuse
 	 * with pipe_sagv_mask.
 	 */
-	u8 qgv_points_mask;
+	u16 qgv_points_mask;
 
 	unsigned int data_rate[I915_MAX_PIPES];
 	u8 num_active_planes[I915_MAX_PIPES];
 
-	/* bitmask of active pipes */
-	u8 active_pipes;
-
 	int min_cdclk;
 };
 
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 4b140a014ca8..8888fda8b701 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -23,6 +23,7 @@
 
 #include <linux/time.h>
 
+#include "hsw_ips.h"
 #include "intel_atomic.h"
 #include "intel_atomic_plane.h"
 #include "intel_audio.h"
@@ -31,6 +32,7 @@
 #include "intel_crtc.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pci_config.h"
 #include "intel_pcode.h"
 #include "intel_psr.h"
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index de3ded1e327a..e94ec57260f1 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -28,6 +28,25 @@
 #include "intel_dpll.h"
 #include "vlv_dsi_pll.h"
 
+struct intel_color_funcs {
+	int (*color_check)(struct intel_crtc_state *crtc_state);
+	/*
+	 * Program double buffered color management registers during
+	 * vblank evasion. The registers should then latch during the
+	 * next vblank start, alongside any other double buffered registers
+	 * involved with the same commit.
+	 */
+	void (*color_commit)(const struct intel_crtc_state *crtc_state);
+	/*
+	 * Load LUTs (and other single buffered color management
+	 * registers). Will (hopefully) be called during the vblank
+	 * following the latching of any double buffered registers
+	 * involved with the same commit.
+	 */
+	void (*load_luts)(const struct intel_crtc_state *crtc_state);
+	void (*read_luts)(struct intel_crtc_state *crtc_state);
+};
+
 #define CTM_COEFF_SIGN	(1ULL << 63)
 
 #define CTM_COEFF_1_0	(1ULL << 32)
@@ -160,29 +179,29 @@ static void ilk_update_pipe_csc(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	intel_de_write(dev_priv, PIPE_CSC_PREOFF_HI(pipe), preoff[0]);
-	intel_de_write(dev_priv, PIPE_CSC_PREOFF_ME(pipe), preoff[1]);
-	intel_de_write(dev_priv, PIPE_CSC_PREOFF_LO(pipe), preoff[2]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_HI(pipe), preoff[0]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_ME(pipe), preoff[1]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_PREOFF_LO(pipe), preoff[2]);
 
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_RY_GY(pipe),
-		       coeff[0] << 16 | coeff[1]);
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_BY(pipe), coeff[2] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RY_GY(pipe),
+			  coeff[0] << 16 | coeff[1]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BY(pipe), coeff[2] << 16);
 
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_RU_GU(pipe),
-		       coeff[3] << 16 | coeff[4]);
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_BU(pipe), coeff[5] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RU_GU(pipe),
+			  coeff[3] << 16 | coeff[4]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BU(pipe), coeff[5] << 16);
 
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_RV_GV(pipe),
-		       coeff[6] << 16 | coeff[7]);
-	intel_de_write(dev_priv, PIPE_CSC_COEFF_BV(pipe), coeff[8] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_RV_GV(pipe),
+			  coeff[6] << 16 | coeff[7]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_COEFF_BV(pipe), coeff[8] << 16);
 
 	if (DISPLAY_VER(dev_priv) >= 7) {
-		intel_de_write(dev_priv, PIPE_CSC_POSTOFF_HI(pipe),
-			       postoff[0]);
-		intel_de_write(dev_priv, PIPE_CSC_POSTOFF_ME(pipe),
-			       postoff[1]);
-		intel_de_write(dev_priv, PIPE_CSC_POSTOFF_LO(pipe),
-			       postoff[2]);
+		intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_HI(pipe),
+				  postoff[0]);
+		intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_ME(pipe),
+				  postoff[1]);
+		intel_de_write_fw(dev_priv, PIPE_CSC_POSTOFF_LO(pipe),
+				  postoff[2]);
 	}
 }
 
@@ -194,28 +213,28 @@ static void icl_update_output_csc(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_PREOFF_HI(pipe), preoff[0]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_PREOFF_ME(pipe), preoff[1]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_PREOFF_LO(pipe), preoff[2]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_HI(pipe), preoff[0]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_ME(pipe), preoff[1]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_PREOFF_LO(pipe), preoff[2]);
 
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_RY_GY(pipe),
-		       coeff[0] << 16 | coeff[1]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_BY(pipe),
-		       coeff[2] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RY_GY(pipe),
+			  coeff[0] << 16 | coeff[1]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BY(pipe),
+			  coeff[2] << 16);
 
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_RU_GU(pipe),
-		       coeff[3] << 16 | coeff[4]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_BU(pipe),
-		       coeff[5] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RU_GU(pipe),
+			  coeff[3] << 16 | coeff[4]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BU(pipe),
+			  coeff[5] << 16);
 
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_RV_GV(pipe),
-		       coeff[6] << 16 | coeff[7]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_COEFF_BV(pipe),
-		       coeff[8] << 16);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_RV_GV(pipe),
+			  coeff[6] << 16 | coeff[7]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_COEFF_BV(pipe),
+			  coeff[8] << 16);
 
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_HI(pipe), postoff[0]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_ME(pipe), postoff[1]);
-	intel_de_write(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_LO(pipe), postoff[2]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_HI(pipe), postoff[0]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_ME(pipe), postoff[1]);
+	intel_de_write_fw(dev_priv, PIPE_CSC_OUTPUT_POSTOFF_LO(pipe), postoff[2]);
 }
 
 static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state)
@@ -319,8 +338,8 @@ static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 				    ilk_csc_off_zero);
 	}
 
-	intel_de_write(dev_priv, PIPE_CSC_MODE(crtc->pipe),
-		       crtc_state->csc_mode);
+	intel_de_write_fw(dev_priv, PIPE_CSC_MODE(crtc->pipe),
+			  crtc_state->csc_mode);
 }
 
 static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
@@ -346,8 +365,8 @@ static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 				      ilk_csc_postoff_limited_range);
 	}
 
-	intel_de_write(dev_priv, PIPE_CSC_MODE(crtc->pipe),
-		       crtc_state->csc_mode);
+	intel_de_write_fw(dev_priv, PIPE_CSC_MODE(crtc->pipe),
+			  crtc_state->csc_mode);
 }
 
 static void chv_load_cgm_csc(struct intel_crtc *crtc,
@@ -377,16 +396,16 @@ static void chv_load_cgm_csc(struct intel_crtc *crtc,
 		coeffs[i] |= (abs_coeff >> 20) & 0xfff;
 	}
 
-	intel_de_write(dev_priv, CGM_PIPE_CSC_COEFF01(pipe),
-		       coeffs[1] << 16 | coeffs[0]);
-	intel_de_write(dev_priv, CGM_PIPE_CSC_COEFF23(pipe),
-		       coeffs[3] << 16 | coeffs[2]);
-	intel_de_write(dev_priv, CGM_PIPE_CSC_COEFF45(pipe),
-		       coeffs[5] << 16 | coeffs[4]);
-	intel_de_write(dev_priv, CGM_PIPE_CSC_COEFF67(pipe),
-		       coeffs[7] << 16 | coeffs[6]);
-	intel_de_write(dev_priv, CGM_PIPE_CSC_COEFF8(pipe),
-		       coeffs[8]);
+	intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF01(pipe),
+			  coeffs[1] << 16 | coeffs[0]);
+	intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF23(pipe),
+			  coeffs[3] << 16 | coeffs[2]);
+	intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF45(pipe),
+			  coeffs[5] << 16 | coeffs[4]);
+	intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF67(pipe),
+			  coeffs[7] << 16 | coeffs[6]);
+	intel_de_write_fw(dev_priv, CGM_PIPE_CSC_COEFF8(pipe),
+			  coeffs[8]);
 }
 
 /* convert hw value with given bit_precision to lut property val */
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 354b08d6f81d..9dee12986991 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2703,6 +2703,7 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state,
 	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
+	struct intel_crtc *slave_crtc;
 
 	if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) {
 		intel_crtc_vblank_off(old_crtc_state);
@@ -2721,9 +2722,8 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state,
 			ilk_pfit_disable(old_crtc_state);
 	}
 
-	if (old_crtc_state->bigjoiner_linked_crtc) {
-		struct intel_crtc *slave_crtc =
-			old_crtc_state->bigjoiner_linked_crtc;
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, slave_crtc,
+					 intel_crtc_bigjoiner_slave_pipes(old_crtc_state)) {
 		const struct intel_crtc_state *old_slave_crtc_state =
 			intel_atomic_get_old_crtc_state(state, slave_crtc);
 
@@ -2926,7 +2926,7 @@ static void intel_enable_ddi(struct intel_atomic_state *state,
 {
 	drm_WARN_ON(state->base.dev, crtc_state->has_pch_encoder);
 
-	if (!crtc_state->bigjoiner_slave)
+	if (!intel_crtc_is_bigjoiner_slave(crtc_state))
 		intel_ddi_enable_transcoder_func(encoder, crtc_state);
 
 	intel_vrr_enable(encoder, crtc_state);
@@ -3041,6 +3041,7 @@ intel_ddi_update_prepare(struct intel_atomic_state *state,
 			 struct intel_encoder *encoder,
 			 struct intel_crtc *crtc)
 {
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	struct intel_crtc_state *crtc_state =
 		crtc ? intel_atomic_get_new_crtc_state(state, crtc) : NULL;
 	int required_lanes = crtc_state ? crtc_state->lane_count : 1;
@@ -3050,11 +3051,12 @@ intel_ddi_update_prepare(struct intel_atomic_state *state,
 	intel_tc_port_get_link(enc_to_dig_port(encoder),
 		               required_lanes);
 	if (crtc_state && crtc_state->hw.active) {
-		struct intel_crtc *slave_crtc = crtc_state->bigjoiner_linked_crtc;
+		struct intel_crtc *slave_crtc;
 
 		intel_update_active_dpll(state, crtc, encoder);
 
-		if (slave_crtc)
+		for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc,
+						 intel_crtc_bigjoiner_slave_pipes(crtc_state))
 			intel_update_active_dpll(state, slave_crtc, encoder);
 	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7f512f9e9e5c..aaf2aee4da35 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -74,6 +74,7 @@
 
 #include "g4x_dp.h"
 #include "g4x_hdmi.h"
+#include "hsw_ips.h"
 #include "i915_drv.h"
 #include "icl_dsi.h"
 #include "intel_acpi.h"
@@ -337,10 +338,38 @@ is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
 		is_trans_port_sync_slave(crtc_state);
 }
 
-static struct intel_crtc *intel_master_crtc(const struct intel_crtc_state *crtc_state)
+static enum pipe bigjoiner_master_pipe(const struct intel_crtc_state *crtc_state)
 {
-	if (crtc_state->bigjoiner_slave)
-		return crtc_state->bigjoiner_linked_crtc;
+	return ffs(crtc_state->bigjoiner_pipes) - 1;
+}
+
+u8 intel_crtc_bigjoiner_slave_pipes(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->bigjoiner_pipes & ~BIT(bigjoiner_master_pipe(crtc_state));
+}
+
+bool intel_crtc_is_bigjoiner_slave(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+
+	return crtc_state->bigjoiner_pipes &&
+		crtc->pipe != bigjoiner_master_pipe(crtc_state);
+}
+
+bool intel_crtc_is_bigjoiner_master(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+
+	return crtc_state->bigjoiner_pipes &&
+		crtc->pipe == bigjoiner_master_pipe(crtc_state);
+}
+
+struct intel_crtc *intel_master_crtc(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev);
+
+	if (intel_crtc_is_bigjoiner_slave(crtc_state))
+		return intel_crtc_for_pipe(i915, bigjoiner_master_pipe(crtc_state));
 	else
 		return to_intel_crtc(crtc_state->uapi.crtc);
 }
@@ -752,8 +781,11 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	crtc_state->data_rate[plane->id] = 0;
 	crtc_state->min_cdclk[plane->id] = 0;
 
-	if (plane->id == PLANE_PRIMARY)
-		hsw_disable_ips(crtc_state);
+	if ((crtc_state->active_planes & ~BIT(PLANE_CURSOR)) == 0 &&
+	    hsw_ips_disable(crtc_state)) {
+		crtc_state->ips_enabled = false;
+		intel_crtc_wait_for_next_vblank(crtc);
+	}
 
 	/*
 	 * Vblank time updates from the shadow to live plane control register
@@ -1090,72 +1122,6 @@ static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state)
 	intel_de_write(dev_priv, PF_WIN_SZ(pipe), width << 16 | height);
 }
 
-void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (!crtc_state->ips_enabled)
-		return;
-
-	/*
-	 * We can only enable IPS after we enable a plane and wait for a vblank
-	 * This function is called from post_plane_update, which is run after
-	 * a vblank wait.
-	 */
-	drm_WARN_ON(dev, !(crtc_state->active_planes & ~BIT(PLANE_CURSOR)));
-
-	if (IS_BROADWELL(dev_priv)) {
-		drm_WARN_ON(dev, snb_pcode_write(dev_priv, DISPLAY_IPS_CONTROL,
-						 IPS_ENABLE | IPS_PCODE_CONTROL));
-		/* Quoting Art Runyan: "its not safe to expect any particular
-		 * value in IPS_CTL bit 31 after enabling IPS through the
-		 * mailbox." Moreover, the mailbox may return a bogus state,
-		 * so we need to just enable it and continue on.
-		 */
-	} else {
-		intel_de_write(dev_priv, IPS_CTL, IPS_ENABLE);
-		/* The bit only becomes 1 in the next vblank, so this wait here
-		 * is essentially intel_wait_for_vblank. If we don't have this
-		 * and don't wait for vblanks until the end of crtc_enable, then
-		 * the HW state readout code will complain that the expected
-		 * IPS_CTL value is not the one we read. */
-		if (intel_de_wait_for_set(dev_priv, IPS_CTL, IPS_ENABLE, 50))
-			drm_err(&dev_priv->drm,
-				"Timed out waiting for IPS enable\n");
-	}
-}
-
-void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (!crtc_state->ips_enabled)
-		return;
-
-	if (IS_BROADWELL(dev_priv)) {
-		drm_WARN_ON(dev,
-			    snb_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0));
-		/*
-		 * Wait for PCODE to finish disabling IPS. The BSpec specified
-		 * 42ms timeout value leads to occasional timeouts so use 100ms
-		 * instead.
-		 */
-		if (intel_de_wait_for_clear(dev_priv, IPS_CTL, IPS_ENABLE, 100))
-			drm_err(&dev_priv->drm,
-				"Timed out waiting for IPS disable\n");
-	} else {
-		intel_de_write(dev_priv, IPS_CTL, 0);
-		intel_de_posting_read(dev_priv, IPS_CTL);
-	}
-
-	/* We need to wait for a vblank before we can disable the plane. */
-	intel_crtc_wait_for_next_vblank(crtc);
-}
-
 static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc)
 {
 	if (crtc->overlay)
@@ -1166,67 +1132,6 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *crtc)
 	 */
 }
 
-static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_state,
-				       const struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	if (!old_crtc_state->ips_enabled)
-		return false;
-
-	if (intel_crtc_needs_modeset(new_crtc_state))
-		return true;
-
-	/*
-	 * 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.
-	 *
-	 * Disable IPS before we program the LUT.
-	 */
-	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->uapi.color_mgmt_changed ||
-	     new_crtc_state->update_pipe) &&
-	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
-		return true;
-
-	return !new_crtc_state->ips_enabled;
-}
-
-static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_state,
-				       const struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	if (!new_crtc_state->ips_enabled)
-		return false;
-
-	if (intel_crtc_needs_modeset(new_crtc_state))
-		return true;
-
-	/*
-	 * 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.
-	 *
-	 * Re-enable IPS after the LUT has been programmed.
-	 */
-	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->uapi.color_mgmt_changed ||
-	     new_crtc_state->update_pipe) &&
-	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
-		return true;
-
-	/*
-	 * We can't read out IPS on broadwell, assume the worst and
-	 * forcibly enable IPS on the first fastset.
-	 */
-	if (new_crtc_state->update_pipe && old_crtc_state->inherited)
-		return true;
-
-	return !old_crtc_state->ips_enabled;
-}
-
 static bool needs_nv12_wa(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
@@ -1321,9 +1226,7 @@ static void intel_post_plane_update(struct intel_atomic_state *state,
 	if (new_crtc_state->update_wm_post && new_crtc_state->hw.active)
 		intel_update_watermarks(dev_priv);
 
-	if (hsw_post_update_enable_ips(old_crtc_state, new_crtc_state))
-		hsw_enable_ips(new_crtc_state);
-
+	hsw_ips_post_update(state, crtc);
 	intel_fbc_post_update(state, crtc);
 	intel_drrs_page_flip(state, crtc);
 
@@ -1426,8 +1329,8 @@ static void intel_pre_plane_update(struct intel_atomic_state *state,
 
 	intel_psr_pre_plane_update(state, crtc);
 
-	if (hsw_pre_update_disable_ips(old_crtc_state, new_crtc_state))
-		hsw_disable_ips(old_crtc_state);
+	if (hsw_ips_pre_update(state, crtc))
+		intel_crtc_wait_for_next_vblank(crtc);
 
 	if (intel_fbc_pre_update(state, crtc))
 		intel_crtc_wait_for_next_vblank(crtc);
@@ -1905,12 +1808,6 @@ static void ilk_crtc_enable(struct intel_atomic_state *state,
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
 }
 
-/* IPS only exists on ULT machines and is tied to pipe A. */
-static bool hsw_crtc_supports_ips(struct intel_crtc *crtc)
-{
-	return HAS_IPS(to_i915(crtc->base.dev)) && crtc->pipe == PIPE_A;
-}
-
 static void glk_pipe_scaler_clock_gating_wa(struct drm_i915_private *dev_priv,
 					    enum pipe pipe, bool apply)
 {
@@ -1974,34 +1871,18 @@ static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state)
 static void icl_ddi_bigjoiner_pre_enable(struct intel_atomic_state *state,
 					 const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc_state *master_crtc_state;
-	struct intel_crtc *master_crtc;
-	struct drm_connector_state *conn_state;
-	struct drm_connector *conn;
-	struct intel_encoder *encoder = NULL;
-	int i;
-
-	master_crtc = intel_master_crtc(crtc_state);
-	master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc);
-
-	for_each_new_connector_in_state(&state->base, conn, conn_state, i) {
-		if (conn_state->crtc != &master_crtc->base)
-			continue;
-
-		encoder = to_intel_encoder(conn_state->best_encoder);
-		break;
-	}
+	struct intel_crtc *master_crtc = intel_master_crtc(crtc_state);
 
 	/*
 	 * Enable sequence steps 1-7 on bigjoiner master
 	 */
-	if (crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(crtc_state))
 		intel_encoders_pre_pll_enable(state, master_crtc);
 
 	if (crtc_state->shared_dpll)
 		intel_enable_shared_dpll(crtc_state);
 
-	if (crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(crtc_state))
 		intel_encoders_pre_enable(state, master_crtc);
 }
 
@@ -2065,7 +1946,8 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 	if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
 		bdw_set_pipemisc(new_crtc_state);
 
-	if (!new_crtc_state->bigjoiner_slave && !transcoder_is_dsi(cpu_transcoder))
+	if (!intel_crtc_is_bigjoiner_slave(new_crtc_state) &&
+	    !transcoder_is_dsi(cpu_transcoder))
 		hsw_configure_cpu_transcoder(new_crtc_state);
 
 	crtc->active = true;
@@ -2105,7 +1987,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 		icl_pipe_mbus_enable(crtc, dbuf_state->joined_mbus);
 	}
 
-	if (new_crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(new_crtc_state))
 		intel_crtc_vblank_on(new_crtc_state);
 
 	intel_encoders_enable(state, crtc);
@@ -2190,7 +2072,7 @@ static void hsw_crtc_disable(struct intel_atomic_state *state,
 	 * FIXME collapse everything to one hook.
 	 * Need care with mst->ddi interactions.
 	 */
-	if (!old_crtc_state->bigjoiner_slave) {
+	if (!intel_crtc_is_bigjoiner_slave(old_crtc_state)) {
 		intel_encoders_disable(state, crtc);
 		intel_encoders_post_disable(state, crtc);
 	}
@@ -2778,77 +2660,6 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 	}
 }
 
-bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	/* IPS only exists on ULT machines and is tied to pipe A. */
-	if (!hsw_crtc_supports_ips(crtc))
-		return false;
-
-	if (!dev_priv->params.enable_ips)
-		return false;
-
-	if (crtc_state->pipe_bpp > 24)
-		return false;
-
-	/*
-	 * We compare against max which means we must take
-	 * the increased cdclk requirement into account when
-	 * calculating the new cdclk.
-	 *
-	 * Should measure whether using a lower cdclk w/o IPS
-	 */
-	if (IS_BROADWELL(dev_priv) &&
-	    crtc_state->pixel_rate > dev_priv->max_cdclk_freq * 95 / 100)
-		return false;
-
-	return true;
-}
-
-static int hsw_compute_ips_config(struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->uapi.crtc->dev);
-	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->uapi.state);
-
-	crtc_state->ips_enabled = false;
-
-	if (!hsw_crtc_state_ips_capable(crtc_state))
-		return 0;
-
-	/*
-	 * When IPS gets enabled, the pipe CRC changes. Since IPS gets
-	 * enabled and disabled dynamically based on package C states,
-	 * user space can't make reliable use of the CRCs, so let's just
-	 * completely disable it.
-	 */
-	if (crtc_state->crc_enabled)
-		return 0;
-
-	/* IPS should be fine as long as at least one plane is enabled. */
-	if (!(crtc_state->active_planes & ~BIT(PLANE_CURSOR)))
-		return 0;
-
-	if (IS_BROADWELL(dev_priv)) {
-		const struct intel_cdclk_state *cdclk_state;
-
-		cdclk_state = intel_atomic_get_cdclk_state(state);
-		if (IS_ERR(cdclk_state))
-			return PTR_ERR(cdclk_state);
-
-		/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
-		if (crtc_state->pixel_rate > cdclk_state->logical.cdclk * 95 / 100)
-			return 0;
-	}
-
-	crtc_state->ips_enabled = true;
-
-	return 0;
-}
-
 static bool intel_crtc_supports_double_wide(const struct intel_crtc *crtc)
 {
 	const struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -3347,13 +3158,11 @@ static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	u32 pipeconf;
-
-	pipeconf = 0;
+	u32 pipeconf = 0;
 
 	/* we keep both pipes enabled on 830 */
 	if (IS_I830(dev_priv))
-		pipeconf |= intel_de_read(dev_priv, PIPECONF(crtc->pipe)) & PIPECONF_ENABLE;
+		pipeconf |= PIPECONF_ENABLE;
 
 	if (crtc_state->double_wide)
 		pipeconf |= PIPECONF_DOUBLE_WIDE;
@@ -4069,19 +3878,20 @@ static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv,
 	return tmp & TRANS_DDI_FUNC_ENABLE;
 }
 
-static u8 enabled_bigjoiner_pipes(struct drm_i915_private *dev_priv)
+static void enabled_bigjoiner_pipes(struct drm_i915_private *dev_priv,
+				    u8 *master_pipes, u8 *slave_pipes)
 {
-	u8 master_pipes = 0, slave_pipes = 0;
 	struct intel_crtc *crtc;
 
-	for_each_intel_crtc(&dev_priv->drm, crtc) {
+	*master_pipes = 0;
+	*slave_pipes = 0;
+
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, crtc,
+					 bigjoiner_pipes(dev_priv)) {
 		enum intel_display_power_domain power_domain;
 		enum pipe pipe = crtc->pipe;
 		intel_wakeref_t wakeref;
 
-		if ((bigjoiner_pipes(dev_priv) & BIT(pipe)) == 0)
-			continue;
-
 		power_domain = intel_dsc_power_domain(crtc, (enum transcoder) pipe);
 		with_intel_display_power_if_enabled(dev_priv, power_domain, wakeref) {
 			u32 tmp = intel_de_read(dev_priv, ICL_PIPE_DSS_CTL1(pipe));
@@ -4090,9 +3900,9 @@ static u8 enabled_bigjoiner_pipes(struct drm_i915_private *dev_priv)
 				continue;
 
 			if (tmp & MASTER_BIG_JOINER_ENABLE)
-				master_pipes |= BIT(pipe);
+				*master_pipes |= BIT(pipe);
 			else
-				slave_pipes |= BIT(pipe);
+				*slave_pipes |= BIT(pipe);
 		}
 
 		if (DISPLAY_VER(dev_priv) < 13)
@@ -4103,18 +3913,47 @@ static u8 enabled_bigjoiner_pipes(struct drm_i915_private *dev_priv)
 			u32 tmp = intel_de_read(dev_priv, ICL_PIPE_DSS_CTL1(pipe));
 
 			if (tmp & UNCOMPRESSED_JOINER_MASTER)
-				master_pipes |= BIT(pipe);
+				*master_pipes |= BIT(pipe);
 			if (tmp & UNCOMPRESSED_JOINER_SLAVE)
-				slave_pipes |= BIT(pipe);
+				*slave_pipes |= BIT(pipe);
 		}
 	}
 
 	/* Bigjoiner pipes should always be consecutive master and slave */
-	drm_WARN(&dev_priv->drm, slave_pipes != master_pipes << 1,
+	drm_WARN(&dev_priv->drm, *slave_pipes != *master_pipes << 1,
 		 "Bigjoiner misconfigured (master pipes 0x%x, slave pipes 0x%x)\n",
-		 master_pipes, slave_pipes);
+		 *master_pipes, *slave_pipes);
+}
+
+static enum pipe get_bigjoiner_master_pipe(enum pipe pipe, u8 master_pipes, u8 slave_pipes)
+{
+	if ((slave_pipes & BIT(pipe)) == 0)
+		return pipe;
+
+	/* ignore everything above our pipe */
+	master_pipes &= ~GENMASK(7, pipe);
+
+	/* highest remaining bit should be our master pipe */
+	return fls(master_pipes) - 1;
+}
+
+static u8 get_bigjoiner_slave_pipes(enum pipe pipe, u8 master_pipes, u8 slave_pipes)
+{
+	enum pipe master_pipe, next_master_pipe;
+
+	master_pipe = get_bigjoiner_master_pipe(pipe, master_pipes, slave_pipes);
+
+	if ((master_pipes & BIT(master_pipe)) == 0)
+		return 0;
 
-	return slave_pipes;
+	/* ignore our master pipe and everything below it */
+	master_pipes &= ~GENMASK(master_pipe, 0);
+	/* make sure a high bit is set for the ffs() */
+	master_pipes |= BIT(7);
+	/* lowest remaining bit should be the next master pipe */
+	next_master_pipe = ffs(master_pipes) - 1;
+
+	return slave_pipes & GENMASK(next_master_pipe - 1, master_pipe);
 }
 
 static u8 hsw_panel_transcoders(struct drm_i915_private *i915)
@@ -4133,6 +3972,7 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u8 panel_transcoder_mask = hsw_panel_transcoders(dev_priv);
 	enum transcoder cpu_transcoder;
+	u8 master_pipes, slave_pipes;
 	u8 enabled_transcoders = 0;
 
 	/*
@@ -4184,8 +4024,10 @@ static u8 hsw_enabled_transcoders(struct intel_crtc *crtc)
 		enabled_transcoders |= BIT(cpu_transcoder);
 
 	/* bigjoiner slave -> consider the master pipe's transcoder as well */
-	if (enabled_bigjoiner_pipes(dev_priv) & BIT(crtc->pipe)) {
-		cpu_transcoder = (enum transcoder) crtc->pipe - 1;
+	enabled_bigjoiner_pipes(dev_priv, &master_pipes, &slave_pipes);
+	if (slave_pipes & BIT(crtc->pipe)) {
+		cpu_transcoder = (enum transcoder)
+			get_bigjoiner_master_pipe(crtc->pipe, master_pipes, slave_pipes);
 		if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder))
 			enabled_transcoders |= BIT(cpu_transcoder);
 	}
@@ -4310,6 +4152,24 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 	return transcoder_is_dsi(pipe_config->cpu_transcoder);
 }
 
+static void intel_bigjoiner_get_config(struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	u8 master_pipes, slave_pipes;
+	enum pipe pipe = crtc->pipe;
+
+	enabled_bigjoiner_pipes(i915, &master_pipes, &slave_pipes);
+
+	if (((master_pipes | slave_pipes) & BIT(pipe)) == 0)
+		return;
+
+	crtc_state->bigjoiner = true;
+	crtc_state->bigjoiner_pipes =
+		BIT(get_bigjoiner_master_pipe(pipe, master_pipes, slave_pipes)) |
+		get_bigjoiner_slave_pipes(pipe, master_pipes, slave_pipes);
+}
+
 static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config)
 {
@@ -4336,8 +4196,7 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 		goto out;
 
 	intel_dsc_get_config(pipe_config);
-	if (DISPLAY_VER(dev_priv) >= 13 && !pipe_config->dsc.compression_enable)
-		intel_uncompressed_joiner_get_config(pipe_config);
+	intel_bigjoiner_get_config(pipe_config);
 
 	if (!transcoder_is_dsi(pipe_config->cpu_transcoder) ||
 	    DISPLAY_VER(dev_priv) >= 11)
@@ -4395,19 +4254,7 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 			ilk_get_pfit_config(pipe_config);
 	}
 
-	if (hsw_crtc_supports_ips(crtc)) {
-		if (IS_HASWELL(dev_priv))
-			pipe_config->ips_enabled = intel_de_read(dev_priv,
-								 IPS_CTL) & IPS_ENABLE;
-		else {
-			/*
-			 * We cannot readout IPS state on broadwell, set to
-			 * true so we can set it to a defined state on first
-			 * commit.
-			 */
-			pipe_config->ips_enabled = true;
-		}
-	}
+	hsw_ips_get_config(pipe_config);
 
 	if (pipe_config->cpu_transcoder != TRANSCODER_EDP &&
 	    !transcoder_is_dsi(pipe_config->cpu_transcoder)) {
@@ -4819,194 +4666,6 @@ intel_encoder_current_mode(struct intel_encoder *encoder)
 	return mode;
 }
 
-/**
- * intel_wm_need_update - Check whether watermarks need updating
- * @cur: current plane state
- * @new: new plane state
- *
- * Check current plane state versus the new one to determine whether
- * watermarks need to be recalculated.
- *
- * Returns true or false.
- */
-static bool intel_wm_need_update(const struct intel_plane_state *cur,
-				 struct intel_plane_state *new)
-{
-	/* Update watermarks on tiling or size changes. */
-	if (new->uapi.visible != cur->uapi.visible)
-		return true;
-
-	if (!cur->hw.fb || !new->hw.fb)
-		return false;
-
-	if (cur->hw.fb->modifier != new->hw.fb->modifier ||
-	    cur->hw.rotation != new->hw.rotation ||
-	    drm_rect_width(&new->uapi.src) != drm_rect_width(&cur->uapi.src) ||
-	    drm_rect_height(&new->uapi.src) != drm_rect_height(&cur->uapi.src) ||
-	    drm_rect_width(&new->uapi.dst) != drm_rect_width(&cur->uapi.dst) ||
-	    drm_rect_height(&new->uapi.dst) != drm_rect_height(&cur->uapi.dst))
-		return true;
-
-	return false;
-}
-
-static bool needs_scaling(const struct intel_plane_state *state)
-{
-	int src_w = drm_rect_width(&state->uapi.src) >> 16;
-	int src_h = drm_rect_height(&state->uapi.src) >> 16;
-	int dst_w = drm_rect_width(&state->uapi.dst);
-	int dst_h = drm_rect_height(&state->uapi.dst);
-
-	return (src_w != dst_w || src_h != dst_h);
-}
-
-static bool intel_plane_do_async_flip(struct intel_plane *plane,
-				      const struct intel_crtc_state *old_crtc_state,
-				      const struct intel_crtc_state *new_crtc_state)
-{
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
-
-	if (!plane->async_flip)
-		return false;
-
-	if (!new_crtc_state->uapi.async_flip)
-		return false;
-
-	/*
-	 * In platforms after DISPLAY13, we might need to override
-	 * first async flip in order to change watermark levels
-	 * as part of optimization.
-	 * So for those, we are checking if this is a first async flip.
-	 * For platforms earlier than DISPLAY13 we always do async flip.
-	 */
-	return DISPLAY_VER(i915) < 13 || old_crtc_state->uapi.async_flip;
-}
-
-int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state,
-				    struct intel_crtc_state *new_crtc_state,
-				    const struct intel_plane_state *old_plane_state,
-				    struct intel_plane_state *new_plane_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
-	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	bool mode_changed = intel_crtc_needs_modeset(new_crtc_state);
-	bool was_crtc_enabled = old_crtc_state->hw.active;
-	bool is_crtc_enabled = new_crtc_state->hw.active;
-	bool turn_off, turn_on, visible, was_visible;
-	int ret;
-
-	if (DISPLAY_VER(dev_priv) >= 9 && plane->id != PLANE_CURSOR) {
-		ret = skl_update_scaler_plane(new_crtc_state, new_plane_state);
-		if (ret)
-			return ret;
-	}
-
-	was_visible = old_plane_state->uapi.visible;
-	visible = new_plane_state->uapi.visible;
-
-	if (!was_crtc_enabled && drm_WARN_ON(&dev_priv->drm, was_visible))
-		was_visible = false;
-
-	/*
-	 * Visibility is calculated as if the crtc was on, but
-	 * after scaler setup everything depends on it being off
-	 * when the crtc isn't active.
-	 *
-	 * FIXME this is wrong for watermarks. Watermarks should also
-	 * be computed as if the pipe would be active. Perhaps move
-	 * per-plane wm computation to the .check_plane() hook, and
-	 * only combine the results from all planes in the current place?
-	 */
-	if (!is_crtc_enabled) {
-		intel_plane_set_invisible(new_crtc_state, new_plane_state);
-		visible = false;
-	}
-
-	if (!was_visible && !visible)
-		return 0;
-
-	turn_off = was_visible && (!visible || mode_changed);
-	turn_on = visible && (!was_visible || mode_changed);
-
-	drm_dbg_atomic(&dev_priv->drm,
-		       "[CRTC:%d:%s] with [PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n",
-		       crtc->base.base.id, crtc->base.name,
-		       plane->base.base.id, plane->base.name,
-		       was_visible, visible,
-		       turn_off, turn_on, mode_changed);
-
-	if (turn_on) {
-		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
-			new_crtc_state->update_wm_pre = true;
-
-		/* must disable cxsr around plane enable/disable */
-		if (plane->id != PLANE_CURSOR)
-			new_crtc_state->disable_cxsr = true;
-	} else if (turn_off) {
-		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv))
-			new_crtc_state->update_wm_post = true;
-
-		/* must disable cxsr around plane enable/disable */
-		if (plane->id != PLANE_CURSOR)
-			new_crtc_state->disable_cxsr = true;
-	} else if (intel_wm_need_update(old_plane_state, new_plane_state)) {
-		if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) {
-			/* FIXME bollocks */
-			new_crtc_state->update_wm_pre = true;
-			new_crtc_state->update_wm_post = true;
-		}
-	}
-
-	if (visible || was_visible)
-		new_crtc_state->fb_bits |= plane->frontbuffer_bit;
-
-	/*
-	 * ILK/SNB DVSACNTR/Sprite Enable
-	 * IVB SPR_CTL/Sprite Enable
-	 * "When in Self Refresh Big FIFO mode, a write to enable the
-	 *  plane will be internally buffered and delayed while Big FIFO
-	 *  mode is exiting."
-	 *
-	 * Which means that enabling the sprite can take an extra frame
-	 * when we start in big FIFO mode (LP1+). Thus we need to drop
-	 * down to LP0 and wait for vblank in order to make sure the
-	 * sprite gets enabled on the next vblank after the register write.
-	 * Doing otherwise would risk enabling the sprite one frame after
-	 * we've already signalled flip completion. We can resume LP1+
-	 * once the sprite has been enabled.
-	 *
-	 *
-	 * WaCxSRDisabledForSpriteScaling:ivb
-	 * IVB SPR_SCALE/Scaling Enable
-	 * "Low Power watermarks must be disabled for at least one
-	 *  frame before enabling sprite scaling, and kept disabled
-	 *  until sprite scaling is disabled."
-	 *
-	 * ILK/SNB DVSASCALE/Scaling Enable
-	 * "When in Self Refresh Big FIFO mode, scaling enable will be
-	 *  masked off while Big FIFO mode is exiting."
-	 *
-	 * Despite the w/a only being listed for IVB we assume that
-	 * the ILK/SNB note has similar ramifications, hence we apply
-	 * the w/a on all three platforms.
-	 *
-	 * With experimental results seems this is needed also for primary
-	 * plane, not only sprite plane.
-	 */
-	if (plane->id != PLANE_CURSOR &&
-	    (IS_IRONLAKE(dev_priv) || IS_SANDYBRIDGE(dev_priv) ||
-	     IS_IVYBRIDGE(dev_priv)) &&
-	    (turn_on || (!needs_scaling(old_plane_state) &&
-			 needs_scaling(new_plane_state))))
-		new_crtc_state->disable_lp_wm = true;
-
-	if (intel_plane_do_async_flip(plane, old_crtc_state, new_crtc_state))
-		new_plane_state->do_async_flip = true;
-
-	return 0;
-}
-
 static bool encoders_cloneable(const struct intel_encoder *a,
 			       const struct intel_encoder *b)
 {
@@ -5266,7 +4925,7 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 
 	if (mode_changed && crtc_state->hw.enable &&
 	    !drm_WARN_ON(&dev_priv->drm, crtc_state->shared_dpll)) {
-		ret = dev_priv->dpll_funcs->crtc_compute_clock(crtc_state);
+		ret = intel_dpll_crtc_compute_clock(crtc_state);
 		if (ret)
 			return ret;
 	}
@@ -5317,7 +4976,7 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	}
 
 	if (HAS_IPS(dev_priv)) {
-		ret = hsw_compute_ips_config(crtc_state);
+		ret = hsw_ips_compute_config(state, crtc);
 		if (ret)
 			return ret;
 	}
@@ -5619,9 +5278,10 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 		    transcoder_name(pipe_config->master_transcoder),
 		    pipe_config->sync_mode_slaves_mask);
 
-	drm_dbg_kms(&dev_priv->drm, "bigjoiner: %s\n",
-		    pipe_config->bigjoiner_slave ? "slave" :
-		    pipe_config->bigjoiner ? "master" : "no");
+	drm_dbg_kms(&dev_priv->drm, "bigjoiner: %s, pipes: 0x%x\n",
+		    intel_crtc_is_bigjoiner_slave(pipe_config) ? "slave" :
+		    intel_crtc_is_bigjoiner_master(pipe_config) ? "master" : "no",
+		    pipe_config->bigjoiner_pipes);
 
 	drm_dbg_kms(&dev_priv->drm, "splitter: %s, link count %d, overlap %d\n",
 		    enableddisabled(pipe_config->splitter.enable),
@@ -5818,35 +5478,42 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state)
 
 static void
 intel_crtc_copy_uapi_to_hw_state_nomodeset(struct intel_atomic_state *state,
-					   struct intel_crtc_state *crtc_state)
+					   struct intel_crtc *crtc)
 {
-	const struct intel_crtc_state *master_crtc_state;
-	struct intel_crtc *master_crtc;
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
-	master_crtc = intel_master_crtc(crtc_state);
-	master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc);
+	WARN_ON(intel_crtc_is_bigjoiner_slave(crtc_state));
 
-	/* No need to copy state if the master state is unchanged */
-	if (master_crtc_state)
-		intel_crtc_copy_color_blobs(crtc_state, master_crtc_state);
+	drm_property_replace_blob(&crtc_state->hw.degamma_lut,
+				  crtc_state->uapi.degamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.gamma_lut,
+				  crtc_state->uapi.gamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.ctm,
+				  crtc_state->uapi.ctm);
 }
 
 static void
-intel_crtc_copy_uapi_to_hw_state(struct intel_atomic_state *state,
-				 struct intel_crtc_state *crtc_state)
+intel_crtc_copy_uapi_to_hw_state_modeset(struct intel_atomic_state *state,
+					 struct intel_crtc *crtc)
 {
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+
+	WARN_ON(intel_crtc_is_bigjoiner_slave(crtc_state));
+
 	crtc_state->hw.enable = crtc_state->uapi.enable;
 	crtc_state->hw.active = crtc_state->uapi.active;
 	crtc_state->hw.mode = crtc_state->uapi.mode;
 	crtc_state->hw.adjusted_mode = crtc_state->uapi.adjusted_mode;
 	crtc_state->hw.scaling_filter = crtc_state->uapi.scaling_filter;
 
-	intel_crtc_copy_uapi_to_hw_state_nomodeset(state, crtc_state);
+	intel_crtc_copy_uapi_to_hw_state_nomodeset(state, crtc);
 }
 
 static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state)
 {
-	if (crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(crtc_state))
 		return;
 
 	crtc_state->uapi.enable = crtc_state->hw.enable;
@@ -5857,7 +5524,6 @@ static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state
 	crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode;
 	crtc_state->uapi.scaling_filter = crtc_state->hw.scaling_filter;
 
-	/* copy color blobs to uapi */
 	drm_property_replace_blob(&crtc_state->uapi.degamma_lut,
 				  crtc_state->hw.degamma_lut);
 	drm_property_replace_blob(&crtc_state->uapi.gamma_lut,
@@ -5866,51 +5532,79 @@ static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state
 				  crtc_state->hw.ctm);
 }
 
+static void
+copy_bigjoiner_crtc_state_nomodeset(struct intel_atomic_state *state,
+				    struct intel_crtc *slave_crtc)
+{
+	struct intel_crtc_state *slave_crtc_state =
+		intel_atomic_get_new_crtc_state(state, slave_crtc);
+	struct intel_crtc *master_crtc = intel_master_crtc(slave_crtc_state);
+	const struct intel_crtc_state *master_crtc_state =
+		intel_atomic_get_new_crtc_state(state, master_crtc);
+
+	drm_property_replace_blob(&slave_crtc_state->hw.degamma_lut,
+				  master_crtc_state->hw.degamma_lut);
+	drm_property_replace_blob(&slave_crtc_state->hw.gamma_lut,
+				  master_crtc_state->hw.gamma_lut);
+	drm_property_replace_blob(&slave_crtc_state->hw.ctm,
+				  master_crtc_state->hw.ctm);
+
+	slave_crtc_state->uapi.color_mgmt_changed = master_crtc_state->uapi.color_mgmt_changed;
+}
+
 static int
-copy_bigjoiner_crtc_state(struct intel_crtc_state *crtc_state,
-			  const struct intel_crtc_state *from_crtc_state)
+copy_bigjoiner_crtc_state_modeset(struct intel_atomic_state *state,
+				  struct intel_crtc *slave_crtc)
 {
+	struct intel_crtc_state *slave_crtc_state =
+		intel_atomic_get_new_crtc_state(state, slave_crtc);
+	struct intel_crtc *master_crtc = intel_master_crtc(slave_crtc_state);
+	const struct intel_crtc_state *master_crtc_state =
+		intel_atomic_get_new_crtc_state(state, master_crtc);
 	struct intel_crtc_state *saved_state;
 
-	saved_state = kmemdup(from_crtc_state, sizeof(*saved_state), GFP_KERNEL);
+	saved_state = kmemdup(master_crtc_state, sizeof(*saved_state), GFP_KERNEL);
 	if (!saved_state)
 		return -ENOMEM;
 
-	saved_state->uapi = crtc_state->uapi;
-	saved_state->scaler_state = crtc_state->scaler_state;
-	saved_state->shared_dpll = crtc_state->shared_dpll;
-	saved_state->dpll_hw_state = crtc_state->dpll_hw_state;
-	saved_state->crc_enabled = crtc_state->crc_enabled;
+	/* preserve some things from the slave's original crtc state */
+	saved_state->uapi = slave_crtc_state->uapi;
+	saved_state->scaler_state = slave_crtc_state->scaler_state;
+	saved_state->shared_dpll = slave_crtc_state->shared_dpll;
+	saved_state->dpll_hw_state = slave_crtc_state->dpll_hw_state;
+	saved_state->crc_enabled = slave_crtc_state->crc_enabled;
 
-	intel_crtc_free_hw_state(crtc_state);
-	memcpy(crtc_state, saved_state, sizeof(*crtc_state));
+	intel_crtc_free_hw_state(slave_crtc_state);
+	memcpy(slave_crtc_state, saved_state, sizeof(*slave_crtc_state));
 	kfree(saved_state);
 
 	/* Re-init hw state */
-	memset(&crtc_state->hw, 0, sizeof(saved_state->hw));
-	crtc_state->hw.enable = from_crtc_state->hw.enable;
-	crtc_state->hw.active = from_crtc_state->hw.active;
-	crtc_state->hw.pipe_mode = from_crtc_state->hw.pipe_mode;
-	crtc_state->hw.adjusted_mode = from_crtc_state->hw.adjusted_mode;
+	memset(&slave_crtc_state->hw, 0, sizeof(slave_crtc_state->hw));
+	slave_crtc_state->hw.enable = master_crtc_state->hw.enable;
+	slave_crtc_state->hw.active = master_crtc_state->hw.active;
+	slave_crtc_state->hw.mode = master_crtc_state->hw.mode;
+	slave_crtc_state->hw.pipe_mode = master_crtc_state->hw.pipe_mode;
+	slave_crtc_state->hw.adjusted_mode = master_crtc_state->hw.adjusted_mode;
+	slave_crtc_state->hw.scaling_filter = master_crtc_state->hw.scaling_filter;
+
+	copy_bigjoiner_crtc_state_nomodeset(state, slave_crtc);
 
 	/* Some fixups */
-	crtc_state->uapi.mode_changed = from_crtc_state->uapi.mode_changed;
-	crtc_state->uapi.connectors_changed = from_crtc_state->uapi.connectors_changed;
-	crtc_state->uapi.active_changed = from_crtc_state->uapi.active_changed;
-	crtc_state->nv12_planes = crtc_state->c8_planes = crtc_state->update_planes = 0;
-	crtc_state->bigjoiner_linked_crtc = to_intel_crtc(from_crtc_state->uapi.crtc);
-	crtc_state->bigjoiner_slave = true;
-	crtc_state->cpu_transcoder = from_crtc_state->cpu_transcoder;
-	crtc_state->has_audio = from_crtc_state->has_audio;
+	slave_crtc_state->uapi.mode_changed = master_crtc_state->uapi.mode_changed;
+	slave_crtc_state->uapi.connectors_changed = master_crtc_state->uapi.connectors_changed;
+	slave_crtc_state->uapi.active_changed = master_crtc_state->uapi.active_changed;
+	slave_crtc_state->cpu_transcoder = master_crtc_state->cpu_transcoder;
+	slave_crtc_state->has_audio = master_crtc_state->has_audio;
 
 	return 0;
 }
 
 static int
 intel_crtc_prepare_cleared_state(struct intel_atomic_state *state,
-				 struct intel_crtc_state *crtc_state)
+				 struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *saved_state;
 
@@ -5940,7 +5634,7 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state,
 	memcpy(crtc_state, saved_state, sizeof(*crtc_state));
 	kfree(saved_state);
 
-	intel_crtc_copy_uapi_to_hw_state(state, crtc_state);
+	intel_crtc_copy_uapi_to_hw_state_modeset(state, crtc);
 
 	return 0;
 }
@@ -6618,6 +6312,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 		PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr1);
 		PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr2);
 		PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr0);
+		PIPE_CONF_CHECK_X(dpll_hw_state.div0);
 		PIPE_CONF_CHECK_X(dpll_hw_state.ebb0);
 		PIPE_CONF_CHECK_X(dpll_hw_state.ebb4);
 		PIPE_CONF_CHECK_X(dpll_hw_state.pll0);
@@ -6669,8 +6364,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_X(sync_mode_slaves_mask);
 	PIPE_CONF_CHECK_I(master_transcoder);
 	PIPE_CONF_CHECK_BOOL(bigjoiner);
-	PIPE_CONF_CHECK_BOOL(bigjoiner_slave);
-	PIPE_CONF_CHECK_P(bigjoiner_linked_crtc);
+	PIPE_CONF_CHECK_X(bigjoiner_pipes);
 
 	PIPE_CONF_CHECK_I(dsc.compression_enable);
 	PIPE_CONF_CHECK_I(dsc.dsc_split);
@@ -7456,20 +7150,25 @@ static int intel_crtc_add_bigjoiner_planes(struct intel_atomic_state *state,
 
 static int intel_bigjoiner_add_affected_planes(struct intel_atomic_state *state)
 {
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	const struct intel_crtc_state *crtc_state;
 	struct intel_crtc *crtc;
 	int i;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		int ret;
+		struct intel_crtc *other;
 
-		if (!crtc_state->bigjoiner)
-			continue;
+		for_each_intel_crtc_in_pipe_mask(&i915->drm, other,
+						 crtc_state->bigjoiner_pipes) {
+			int ret;
 
-		ret = intel_crtc_add_bigjoiner_planes(state, crtc,
-						      crtc_state->bigjoiner_linked_crtc);
-		if (ret)
-			return ret;
+			if (crtc == other)
+				continue;
+
+			ret = intel_crtc_add_bigjoiner_planes(state, crtc, other);
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
@@ -7571,71 +7270,123 @@ static bool intel_cpu_transcoders_need_modeset(struct intel_atomic_state *state,
 	return false;
 }
 
+static bool intel_pipes_need_modeset(struct intel_atomic_state *state,
+				     u8 pipes)
+{
+	const struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->hw.enable &&
+		    pipes & BIT(crtc->pipe) &&
+		    intel_crtc_needs_modeset(new_crtc_state))
+			return true;
+	}
+
+	return false;
+}
+
 static int intel_atomic_check_bigjoiner(struct intel_atomic_state *state,
-					struct intel_crtc *crtc,
-					struct intel_crtc_state *old_crtc_state,
-					struct intel_crtc_state *new_crtc_state)
+					struct intel_crtc *master_crtc)
 {
 	struct drm_i915_private *i915 = to_i915(state->base.dev);
-	struct intel_crtc_state *slave_crtc_state, *master_crtc_state;
-	struct intel_crtc *slave_crtc, *master_crtc;
+	struct intel_crtc_state *master_crtc_state =
+		intel_atomic_get_new_crtc_state(state, master_crtc);
+	struct intel_crtc *slave_crtc;
+	u8 slave_pipes;
 
-	/* slave being enabled, is master is still claiming this crtc? */
-	if (old_crtc_state->bigjoiner_slave) {
-		slave_crtc = crtc;
-		master_crtc = old_crtc_state->bigjoiner_linked_crtc;
-		master_crtc_state = intel_atomic_get_new_crtc_state(state, master_crtc);
-		if (!master_crtc_state || !intel_crtc_needs_modeset(master_crtc_state))
-			goto claimed;
-	}
+	/*
+	 * TODO: encoder.compute_config() may be the best
+	 * place to populate the bitmask for the master crtc.
+	 * For now encoder.compute_config() just flags things
+	 * as needing bigjoiner and we populate the bitmask
+	 * here.
+	 */
+	WARN_ON(master_crtc_state->bigjoiner_pipes);
 
-	if (!new_crtc_state->bigjoiner)
+	if (!master_crtc_state->bigjoiner)
 		return 0;
 
-	slave_crtc = intel_dsc_get_bigjoiner_secondary(crtc);
-	if (!slave_crtc) {
+	slave_pipes = BIT(master_crtc->pipe + 1);
+
+	if (slave_pipes & ~bigjoiner_pipes(i915)) {
 		drm_dbg_kms(&i915->drm,
-			    "[CRTC:%d:%s] Big joiner configuration requires "
-			    "CRTC + 1 to be used, doesn't exist\n",
-			    crtc->base.base.id, crtc->base.name);
+			    "[CRTC:%d:%s] Cannot act as big joiner master "
+			    "(need 0x%x as slave pipes, only 0x%x possible)\n",
+			    master_crtc->base.base.id, master_crtc->base.name,
+			    slave_pipes, bigjoiner_pipes(i915));
 		return -EINVAL;
 	}
 
-	new_crtc_state->bigjoiner_linked_crtc = slave_crtc;
-	slave_crtc_state = intel_atomic_get_crtc_state(&state->base, slave_crtc);
-	master_crtc = crtc;
-	if (IS_ERR(slave_crtc_state))
-		return PTR_ERR(slave_crtc_state);
+	for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc, slave_pipes) {
+		struct intel_crtc_state *slave_crtc_state;
+		int ret;
 
-	/* master being enabled, slave was already configured? */
-	if (slave_crtc_state->uapi.enable)
-		goto claimed;
+		slave_crtc_state = intel_atomic_get_crtc_state(&state->base, slave_crtc);
+		if (IS_ERR(slave_crtc_state))
+			return PTR_ERR(slave_crtc_state);
 
-	drm_dbg_kms(&i915->drm,
-		    "[CRTC:%d:%s] Used as slave for big joiner\n",
-		    slave_crtc->base.base.id, slave_crtc->base.name);
+		/* master being enabled, slave was already configured? */
+		if (slave_crtc_state->uapi.enable) {
+			drm_dbg_kms(&i915->drm,
+				    "[CRTC:%d:%s] Slave is enabled as normal CRTC, but "
+				    "[CRTC:%d:%s] claiming this CRTC for bigjoiner.\n",
+				    slave_crtc->base.base.id, slave_crtc->base.name,
+				    master_crtc->base.base.id, master_crtc->base.name);
+			return -EINVAL;
+		}
 
-	return copy_bigjoiner_crtc_state(slave_crtc_state, new_crtc_state);
+		/*
+		 * The state copy logic assumes the master crtc gets processed
+		 * before the slave crtc during the main compute_config loop.
+		 * This works because the crtcs are created in pipe order,
+		 * and the hardware requires master pipe < slave pipe as well.
+		 * Should that change we need to rethink the logic.
+		 */
+		if (WARN_ON(drm_crtc_index(&master_crtc->base) >
+			    drm_crtc_index(&slave_crtc->base)))
+			return -EINVAL;
 
-claimed:
-	drm_dbg_kms(&i915->drm,
-		    "[CRTC:%d:%s] Slave is enabled as normal CRTC, but "
-		    "[CRTC:%d:%s] claiming this CRTC for bigjoiner.\n",
-		    slave_crtc->base.base.id, slave_crtc->base.name,
-		    master_crtc->base.base.id, master_crtc->base.name);
-	return -EINVAL;
+		drm_dbg_kms(&i915->drm,
+			    "[CRTC:%d:%s] Used as slave for big joiner master [CRTC:%d:%s]\n",
+			    slave_crtc->base.base.id, slave_crtc->base.name,
+			    master_crtc->base.base.id, master_crtc->base.name);
+
+		master_crtc_state->bigjoiner_pipes =
+			BIT(master_crtc->pipe) | BIT(slave_crtc->pipe);
+		slave_crtc_state->bigjoiner_pipes =
+			BIT(master_crtc->pipe) | BIT(slave_crtc->pipe);
+
+		ret = copy_bigjoiner_crtc_state_modeset(state, slave_crtc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static void kill_bigjoiner_slave(struct intel_atomic_state *state,
-				 struct intel_crtc_state *master_crtc_state)
+				 struct intel_crtc *master_crtc)
 {
-	struct intel_crtc_state *slave_crtc_state =
-		intel_atomic_get_new_crtc_state(state, master_crtc_state->bigjoiner_linked_crtc);
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	struct intel_crtc_state *master_crtc_state =
+		intel_atomic_get_new_crtc_state(state, master_crtc);
+	struct intel_crtc *slave_crtc;
+
+	for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc,
+					 intel_crtc_bigjoiner_slave_pipes(master_crtc_state)) {
+		struct intel_crtc_state *slave_crtc_state =
+			intel_atomic_get_new_crtc_state(state, slave_crtc);
+
+		slave_crtc_state->bigjoiner = false;
+		slave_crtc_state->bigjoiner_pipes = 0;
+
+		intel_crtc_copy_uapi_to_hw_state_modeset(state, slave_crtc);
+	}
 
-	slave_crtc_state->bigjoiner = master_crtc_state->bigjoiner = false;
-	slave_crtc_state->bigjoiner_slave = master_crtc_state->bigjoiner_slave = false;
-	slave_crtc_state->bigjoiner_linked_crtc = master_crtc_state->bigjoiner_linked_crtc = NULL;
-	intel_crtc_copy_uapi_to_hw_state(state, slave_crtc_state);
+	master_crtc_state->bigjoiner = false;
+	master_crtc_state->bigjoiner_pipes = 0;
 }
 
 /**
@@ -7785,34 +7536,37 @@ static int intel_atomic_check_async(struct intel_atomic_state *state, struct int
 
 static int intel_bigjoiner_add_affected_crtcs(struct intel_atomic_state *state)
 {
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	struct intel_crtc_state *crtc_state;
 	struct intel_crtc *crtc;
+	u8 affected_pipes = 0;
+	u8 modeset_pipes = 0;
 	int i;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		struct intel_crtc_state *linked_crtc_state;
-		struct intel_crtc *linked_crtc;
-		int ret;
+		affected_pipes |= crtc_state->bigjoiner_pipes;
+		if (intel_crtc_needs_modeset(crtc_state))
+			modeset_pipes |= crtc_state->bigjoiner_pipes;
+	}
 
-		if (!crtc_state->bigjoiner)
-			continue;
+	for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, affected_pipes) {
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
 
-		linked_crtc = crtc_state->bigjoiner_linked_crtc;
-		linked_crtc_state = intel_atomic_get_crtc_state(&state->base, linked_crtc);
-		if (IS_ERR(linked_crtc_state))
-			return PTR_ERR(linked_crtc_state);
+	for_each_intel_crtc_in_pipe_mask(&i915->drm, crtc, modeset_pipes) {
+		int ret;
 
-		if (!intel_crtc_needs_modeset(crtc_state))
-			continue;
+		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
 
-		linked_crtc_state->uapi.mode_changed = true;
+		crtc_state->uapi.mode_changed = true;
 
-		ret = drm_atomic_add_affected_connectors(&state->base,
-							 &linked_crtc->base);
+		ret = drm_atomic_add_affected_connectors(&state->base, &crtc->base);
 		if (ret)
 			return ret;
 
-		ret = intel_atomic_add_affected_planes(state, linked_crtc);
+		ret = intel_atomic_add_affected_planes(state, crtc);
 		if (ret)
 			return ret;
 	}
@@ -7820,8 +7574,8 @@ static int intel_bigjoiner_add_affected_crtcs(struct intel_atomic_state *state)
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		/* Kill old bigjoiner link, we may re-establish afterwards */
 		if (intel_crtc_needs_modeset(crtc_state) &&
-		    crtc_state->bigjoiner && !crtc_state->bigjoiner_slave)
-			kill_bigjoiner_slave(state, crtc_state);
+		    intel_crtc_is_bigjoiner_master(crtc_state))
+			kill_bigjoiner_slave(state, crtc);
 	}
 
 	return 0;
@@ -7846,6 +7600,10 @@ static int intel_atomic_check(struct drm_device *dev,
 					    new_crtc_state, i) {
 		if (new_crtc_state->inherited != old_crtc_state->inherited)
 			new_crtc_state->uapi.mode_changed = true;
+
+		if (new_crtc_state->uapi.scaling_filter !=
+		    old_crtc_state->uapi.scaling_filter)
+			new_crtc_state->uapi.mode_changed = true;
 	}
 
 	intel_vrr_check_modeset(state);
@@ -7861,21 +7619,22 @@ static int intel_atomic_check(struct drm_device *dev,
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
 		if (!intel_crtc_needs_modeset(new_crtc_state)) {
-			/* Light copy */
-			intel_crtc_copy_uapi_to_hw_state_nomodeset(state, new_crtc_state);
-
+			if (intel_crtc_is_bigjoiner_slave(new_crtc_state))
+				copy_bigjoiner_crtc_state_nomodeset(state, crtc);
+			else
+				intel_crtc_copy_uapi_to_hw_state_nomodeset(state, crtc);
 			continue;
 		}
 
 		if (!new_crtc_state->uapi.enable) {
-			if (!new_crtc_state->bigjoiner_slave) {
-				intel_crtc_copy_uapi_to_hw_state(state, new_crtc_state);
+			if (!intel_crtc_is_bigjoiner_slave(new_crtc_state)) {
+				intel_crtc_copy_uapi_to_hw_state_modeset(state, crtc);
 				any_ms = true;
 			}
 			continue;
 		}
 
-		ret = intel_crtc_prepare_cleared_state(state, new_crtc_state);
+		ret = intel_crtc_prepare_cleared_state(state, crtc);
 		if (ret)
 			goto fail;
 
@@ -7883,8 +7642,7 @@ static int intel_atomic_check(struct drm_device *dev,
 		if (ret)
 			goto fail;
 
-		ret = intel_atomic_check_bigjoiner(state, crtc, old_crtc_state,
-						   new_crtc_state);
+		ret = intel_atomic_check_bigjoiner(state, crtc);
 		if (ret)
 			goto fail;
 	}
@@ -7938,10 +7696,7 @@ static int intel_atomic_check(struct drm_device *dev,
 		}
 
 		if (new_crtc_state->bigjoiner) {
-			struct intel_crtc_state *linked_crtc_state =
-				intel_atomic_get_new_crtc_state(state, new_crtc_state->bigjoiner_linked_crtc);
-
-			if (intel_crtc_needs_modeset(linked_crtc_state)) {
+			if (intel_pipes_need_modeset(state, new_crtc_state->bigjoiner_pipes)) {
 				new_crtc_state->uapi.mode_changed = true;
 				new_crtc_state->update_pipe = false;
 			}
@@ -8121,9 +7876,6 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 	if (DISPLAY_VER(dev_priv) >= 9 ||
 	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
 		hsw_set_linetime_wm(new_crtc_state);
-
-	if (DISPLAY_VER(dev_priv) >= 11)
-		icl_set_pipe_chicken(new_crtc_state);
 }
 
 static void commit_pipe_pre_planes(struct intel_atomic_state *state,
@@ -8188,7 +7940,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state,
 
 	dev_priv->display->crtc_enable(state, crtc);
 
-	if (new_crtc_state->bigjoiner_slave)
+	if (intel_crtc_is_bigjoiner_slave(new_crtc_state))
 		return;
 
 	/* vblanks work again, re-enable pipe CRC. */
@@ -8198,7 +7950,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state,
 static void intel_update_crtc(struct intel_atomic_state *state,
 			      struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_i915_private *i915 = to_i915(state->base.dev);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 	struct intel_crtc_state *new_crtc_state =
@@ -8215,21 +7967,22 @@ static void intel_update_crtc(struct intel_atomic_state *state,
 
 		if (new_crtc_state->update_pipe)
 			intel_encoders_update_pipe(state, crtc);
+
+		if (DISPLAY_VER(i915) >= 11 &&
+		    new_crtc_state->update_pipe)
+			icl_set_pipe_chicken(new_crtc_state);
 	}
 
 	intel_fbc_update(state, crtc);
 
-	intel_update_planes_on_crtc(state, crtc);
+	intel_crtc_planes_update_noarm(state, crtc);
 
 	/* Perform vblank evasion around commit operation */
 	intel_pipe_update_start(new_crtc_state);
 
 	commit_pipe_pre_planes(state, crtc);
 
-	if (DISPLAY_VER(dev_priv) >= 9)
-		skl_arm_planes_on_crtc(state, crtc);
-	else
-		i9xx_arm_planes_on_crtc(state, crtc);
+	intel_crtc_planes_update_arm(state, crtc);
 
 	commit_pipe_post_planes(state, crtc);
 
@@ -8305,7 +8058,7 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 		 */
 		if (!is_trans_port_sync_slave(old_crtc_state) &&
 		    !intel_dp_mst_is_slave_trans(old_crtc_state) &&
-		    !old_crtc_state->bigjoiner_slave)
+		    !intel_crtc_is_bigjoiner_slave(old_crtc_state))
 			continue;
 
 		intel_old_crtc_state_disables(state, old_crtc_state,
@@ -8420,7 +8173,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 
 		if (intel_dp_mst_is_slave_trans(new_crtc_state) ||
 		    is_trans_port_sync_master(new_crtc_state) ||
-		    (new_crtc_state->bigjoiner && !new_crtc_state->bigjoiner_slave))
+		    intel_crtc_is_bigjoiner_master(new_crtc_state))
 			continue;
 
 		modeset_pipes &= ~BIT(pipe);
@@ -8947,10 +8700,8 @@ static u32 intel_encoder_possible_crtcs(struct intel_encoder *encoder)
 	struct intel_crtc *crtc;
 	u32 possible_crtcs = 0;
 
-	for_each_intel_crtc(dev, crtc) {
-		if (encoder->pipe_mask & BIT(crtc->pipe))
-			possible_crtcs |= drm_crtc_mask(&crtc->base);
-	}
+	for_each_intel_crtc_in_pipe_mask(dev, crtc, encoder->pipe_mask)
+		possible_crtcs |= drm_crtc_mask(&crtc->base);
 
 	return possible_crtcs;
 }
@@ -10132,7 +9883,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 	/* Adjust the state of the output pipe according to whether we
 	 * have active connectors/encoders. */
 	if (crtc_state->hw.active && !intel_crtc_has_encoders(crtc) &&
-	    !crtc_state->bigjoiner_slave)
+	    !intel_crtc_is_bigjoiner_slave(crtc_state))
 		intel_crtc_disable_noatomic(crtc, ctx);
 
 	if (crtc_state->hw.active || HAS_GMCH(dev_priv)) {
@@ -10345,12 +10096,18 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 
 			/* read out to slave crtc as well for bigjoiner */
 			if (crtc_state->bigjoiner) {
+				struct intel_crtc *slave_crtc;
+
 				/* encoder should read be linked to bigjoiner master */
-				WARN_ON(crtc_state->bigjoiner_slave);
+				WARN_ON(intel_crtc_is_bigjoiner_slave(crtc_state));
 
-				crtc = crtc_state->bigjoiner_linked_crtc;
-				crtc_state = to_intel_crtc_state(crtc->base.state);
-				intel_encoder_get_config(encoder, crtc_state);
+				for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, slave_crtc,
+								 intel_crtc_bigjoiner_slave_pipes(crtc_state)) {
+					struct intel_crtc_state *slave_crtc_state;
+
+					slave_crtc_state = to_intel_crtc_state(slave_crtc->base.state);
+					intel_encoder_get_config(encoder, slave_crtc_state);
+				}
 			}
 		} else {
 			encoder->base.crtc = NULL;
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 457738aeee3e..11d6134c53c8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -430,11 +430,11 @@ enum hpd_pin {
 			    &(dev)->mode_config.crtc_list,		\
 			    base.head)
 
-#define for_each_intel_crtc_mask(dev, intel_crtc, crtc_mask)		\
+#define for_each_intel_crtc_in_pipe_mask(dev, intel_crtc, pipe_mask)	\
 	list_for_each_entry(intel_crtc,					\
 			    &(dev)->mode_config.crtc_list,		\
 			    base.head)					\
-		for_each_if((crtc_mask) & drm_crtc_mask(&intel_crtc->base))
+		for_each_if((pipe_mask) & BIT(intel_crtc->pipe))
 
 #define for_each_intel_encoder(dev, intel_encoder)		\
 	list_for_each_entry(intel_encoder,			\
@@ -555,6 +555,10 @@ intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
 				bool bigjoiner);
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
+bool intel_crtc_is_bigjoiner_slave(const struct intel_crtc_state *crtc_state);
+bool intel_crtc_is_bigjoiner_master(const struct intel_crtc_state *crtc_state);
+u8 intel_crtc_bigjoiner_slave_pipes(const struct intel_crtc_state *crtc_state);
+struct intel_crtc *intel_master_crtc(const struct intel_crtc_state *crtc_state);
 
 void intel_plane_destroy(struct drm_plane *plane);
 void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state);
@@ -632,9 +636,6 @@ void intel_cpu_transcoder_get_m2_n2(struct intel_crtc *crtc,
 void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 			 struct intel_crtc_state *pipe_config);
 int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n);
-bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state);
-void hsw_enable_ips(const struct intel_crtc_state *crtc_state);
-void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain intel_port_to_power_domain(enum port port);
 enum intel_display_power_domain
 intel_aux_power_domain(struct intel_digital_port *dig_port);
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index f4de004d470f..695aa6efe8c1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -16,6 +16,7 @@
 #include "intel_dp_mst.h"
 #include "intel_drrs.h"
 #include "intel_fbc.h"
+#include "intel_fbdev.h"
 #include "intel_hdcp.h"
 #include "intel_hdmi.h"
 #include "intel_pm.h"
@@ -78,7 +79,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 	if (DISPLAY_VER(dev_priv) >= 9)
 		/* no global SR status; inspect per-plane WM */;
 	else if (HAS_PCH_SPLIT(dev_priv))
-		sr_enabled = intel_de_read(dev_priv, WM1_LP_ILK) & WM1_LP_SR_EN;
+		sr_enabled = intel_de_read(dev_priv, WM1_LP_ILK) & WM_LP_ENABLE;
 	else if (IS_I965GM(dev_priv) || IS_G4X(dev_priv) ||
 		 IS_I945G(dev_priv) || IS_I945GM(dev_priv))
 		sr_enabled = intel_de_read(dev_priv, FW_BLC_SELF) & FW_BLC_SELF_EN;
@@ -124,9 +125,8 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 	struct drm_framebuffer *drm_fb;
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-	if (dev_priv->fbdev && dev_priv->fbdev->helper.fb) {
-		fbdev_fb = to_intel_framebuffer(dev_priv->fbdev->helper.fb);
-
+	fbdev_fb = intel_fbdev_framebuffer(dev_priv->fbdev);
+	if (fbdev_fb) {
 		seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ",
 			   fbdev_fb->base.width,
 			   fbdev_fb->base.height,
@@ -474,8 +474,8 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 		 * reg for DC3CO debugging and validation,
 		 * but TGL DMC f/w is using DMC_DEBUG3 reg for DC3CO counter.
 		 */
-		seq_printf(m, "DC3CO count: %d\n",
-			   intel_de_read(dev_priv, DMC_DEBUG3));
+		seq_printf(m, "DC3CO count: %d\n", intel_de_read(dev_priv, IS_DGFX(dev_priv) ?
+					DG1_DMC_DEBUG3 : TGL_DMC_DEBUG3));
 	} else {
 		dc5_reg = IS_BROXTON(dev_priv) ? BXT_DMC_DC3_DC5_COUNT :
 						 SKL_DMC_DC3_DC5_COUNT;
@@ -936,10 +936,9 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc)
 	}
 
 	if (crtc_state->bigjoiner)
-		seq_printf(m, "\tLinked to [CRTC:%d:%s] as a %s\n",
-			   crtc_state->bigjoiner_linked_crtc->base.base.id,
-			   crtc_state->bigjoiner_linked_crtc->base.name,
-			   crtc_state->bigjoiner_slave ? "slave" : "master");
+		seq_printf(m, "\tLinked to 0x%x pipes as a %s\n",
+			   crtc_state->bigjoiner_pipes,
+			   intel_crtc_is_bigjoiner_slave(crtc_state) ? "slave" : "master");
 
 	for_each_intel_encoder_mask(&dev_priv->drm, encoder,
 				    crtc_state->uapi.encoder_mask)
@@ -1015,6 +1014,7 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 		seq_printf(m, " wrpll:   0x%08x\n", pll->state.hw_state.wrpll);
 		seq_printf(m, " cfgcr0:  0x%08x\n", pll->state.hw_state.cfgcr0);
 		seq_printf(m, " cfgcr1:  0x%08x\n", pll->state.hw_state.cfgcr1);
+		seq_printf(m, " div0:    0x%08x\n", pll->state.hw_state.div0);
 		seq_printf(m, " mg_refclkin_ctl:        0x%08x\n",
 			   pll->state.hw_state.mg_refclkin_ctl);
 		seq_printf(m, " mg_clktop2_coreclkctl1: 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index d2102cc17bb4..9ebae7ac3235 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -16,6 +16,7 @@
 #include "intel_dpio_phy.h"
 #include "intel_dpll.h"
 #include "intel_hotplug.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pch_refclk.h"
 #include "intel_pcode.h"
 #include "intel_pm.h"
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 60e15226a8cb..b50d0e6efe21 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -26,7 +26,6 @@
 #ifndef __INTEL_DISPLAY_TYPES_H__
 #define __INTEL_DISPLAY_TYPES_H__
 
-#include <linux/async.h>
 #include <linux/i2c.h>
 #include <linux/pm_qos.h>
 #include <linux/pwm.h>
@@ -38,7 +37,6 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_dsc.h>
 #include <drm/drm_encoder.h>
-#include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_rect.h>
@@ -145,25 +143,6 @@ struct intel_framebuffer {
 	struct i915_address_space *dpt_vm;
 };
 
-struct intel_fbdev {
-	struct drm_fb_helper helper;
-	struct intel_framebuffer *fb;
-	struct i915_vma *vma;
-	unsigned long vma_flags;
-	async_cookie_t cookie;
-	int preferred_bpp;
-
-	/* Whether or not fbdev hpd processing is temporarily suspended */
-	bool hpd_suspended : 1;
-	/* Set when a hotplug was received while HPD processing was
-	 * suspended
-	 */
-	bool hpd_waiting : 1;
-
-	/* Protects hpd_suspended */
-	struct mutex hpd_lock;
-};
-
 enum intel_hotplug_state {
 	INTEL_HOTPLUG_UNCHANGED,
 	INTEL_HOTPLUG_CHANGED,
@@ -1168,6 +1147,7 @@ struct intel_crtc_state {
 
 	/* bitmask of actually visible planes (enum plane_id) */
 	u8 active_planes;
+	u8 scaled_planes;
 	u8 nv12_planes;
 	u8 c8_planes;
 
@@ -1202,11 +1182,8 @@ struct intel_crtc_state {
 	/* enable pipe big joiner? */
 	bool bigjoiner;
 
-	/* big joiner slave crtc? */
-	bool bigjoiner_slave;
-
-	/* linked crtc for bigjoiner, either slave or master */
-	struct intel_crtc *bigjoiner_linked_crtc;
+	/* big joiner pipe bitmask */
+	u8 bigjoiner_pipes;
 
 	/* Display Stream compression state */
 	struct {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 146b83916005..1046e7fe310a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -886,9 +886,8 @@ intel_dp_mode_valid_downstream(struct intel_connector *connector,
 		return MODE_CLOCK_HIGH;
 
 	/* Assume 8bpc for the DP++/HDMI/DVI TMDS clock check */
-	tmds_clock = target_clock;
-	if (drm_mode_is_420_only(info, mode))
-		tmds_clock /= 2;
+	tmds_clock = intel_hdmi_tmds_clock(target_clock, 8,
+					   drm_mode_is_420_only(info, mode));
 
 	if (intel_dp->dfp.min_tmds_clock &&
 	    tmds_clock < intel_dp->dfp.min_tmds_clock)
@@ -1139,21 +1138,12 @@ static bool intel_dp_hdmi_ycbcr420(struct intel_dp *intel_dp,
 		 intel_dp->dfp.ycbcr_444_to_420);
 }
 
-static int intel_dp_hdmi_tmds_clock(struct intel_dp *intel_dp,
-				    const struct intel_crtc_state *crtc_state, int bpc)
-{
-	int clock = crtc_state->hw.adjusted_mode.crtc_clock * bpc / 8;
-
-	if (intel_dp_hdmi_ycbcr420(intel_dp, crtc_state))
-		clock /= 2;
-
-	return clock;
-}
-
 static bool intel_dp_hdmi_tmds_clock_valid(struct intel_dp *intel_dp,
 					   const struct intel_crtc_state *crtc_state, int bpc)
 {
-	int tmds_clock = intel_dp_hdmi_tmds_clock(intel_dp, crtc_state, bpc);
+	int clock = crtc_state->hw.adjusted_mode.crtc_clock;
+	int tmds_clock = intel_hdmi_tmds_clock(clock, bpc,
+					       intel_dp_hdmi_ycbcr420(intel_dp, crtc_state));
 
 	if (intel_dp->dfp.min_tmds_clock &&
 	    tmds_clock < intel_dp->dfp.min_tmds_clock)
@@ -3628,6 +3618,32 @@ update_status:
 			    "Could not write test response to sink\n");
 }
 
+static bool intel_dp_link_ok(struct intel_dp *intel_dp,
+			     u8 link_status[DP_LINK_STATUS_SIZE])
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	bool uhbr = intel_dp->link_rate >= 1000000;
+	bool ok;
+
+	if (uhbr)
+		ok = drm_dp_128b132b_lane_channel_eq_done(link_status,
+							  intel_dp->lane_count);
+	else
+		ok = drm_dp_channel_eq_ok(link_status, intel_dp->lane_count);
+
+	if (ok)
+		return true;
+
+	intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+	drm_dbg_kms(&i915->drm,
+		    "[ENCODER:%d:%s] %s link not ok, retraining\n",
+		    encoder->base.base.id, encoder->base.name,
+		    uhbr ? "128b/132b" : "8b/10b");
+
+	return false;
+}
+
 static void
 intel_dp_mst_hpd_irq(struct intel_dp *intel_dp, u8 *esi, u8 *ack)
 {
@@ -3658,14 +3674,7 @@ static bool intel_dp_mst_link_status(struct intel_dp *intel_dp)
 		return false;
 	}
 
-	if (!drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) {
-		drm_dbg_kms(&i915->drm,
-			    "[ENCODER:%d:%s] channel EQ not ok, retraining\n",
-			    encoder->base.base.id, encoder->base.name);
-		return false;
-	}
-
-	return true;
+	return intel_dp_link_ok(intel_dp, link_status);
 }
 
 /**
@@ -3779,8 +3788,8 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp)
 					intel_dp->lane_count))
 		return false;
 
-	/* Retrain if Channel EQ or CR not ok */
-	return !drm_dp_channel_eq_ok(link_status, intel_dp->lane_count);
+	/* Retrain if link not ok */
+	return !intel_dp_link_ok(intel_dp, link_status);
 }
 
 static bool intel_dp_has_connector(struct intel_dp *intel_dp,
@@ -3810,14 +3819,14 @@ static bool intel_dp_has_connector(struct intel_dp *intel_dp,
 
 static int intel_dp_prep_link_retrain(struct intel_dp *intel_dp,
 				      struct drm_modeset_acquire_ctx *ctx,
-				      u32 *crtc_mask)
+				      u8 *pipe_mask)
 {
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	int ret = 0;
 
-	*crtc_mask = 0;
+	*pipe_mask = 0;
 
 	if (!intel_dp_needs_link_retrain(intel_dp))
 		return 0;
@@ -3851,12 +3860,12 @@ static int intel_dp_prep_link_retrain(struct intel_dp *intel_dp,
 		    !try_wait_for_completion(&conn_state->commit->hw_done))
 			continue;
 
-		*crtc_mask |= drm_crtc_mask(&crtc->base);
+		*pipe_mask |= BIT(crtc->pipe);
 	}
 	drm_connector_list_iter_end(&conn_iter);
 
 	if (!intel_dp_needs_link_retrain(intel_dp))
-		*crtc_mask = 0;
+		*pipe_mask = 0;
 
 	return ret;
 }
@@ -3875,7 +3884,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_crtc *crtc;
-	u32 crtc_mask;
+	u8 pipe_mask;
 	int ret;
 
 	if (!intel_dp_is_connected(intel_dp))
@@ -3886,17 +3895,17 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
-	ret = intel_dp_prep_link_retrain(intel_dp, ctx, &crtc_mask);
+	ret = intel_dp_prep_link_retrain(intel_dp, ctx, &pipe_mask);
 	if (ret)
 		return ret;
 
-	if (crtc_mask == 0)
+	if (pipe_mask == 0)
 		return 0;
 
 	drm_dbg_kms(&dev_priv->drm, "[ENCODER:%d:%s] retraining link\n",
 		    encoder->base.base.id, encoder->base.name);
 
-	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, crtc, pipe_mask) {
 		const struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
@@ -3907,7 +3916,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 							      intel_crtc_pch_transcoder(crtc), false);
 	}
 
-	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, crtc, pipe_mask) {
 		const struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
@@ -3924,7 +3933,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 		break;
 	}
 
-	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, crtc, pipe_mask) {
 		const struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
@@ -3942,14 +3951,14 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 
 static int intel_dp_prep_phy_test(struct intel_dp *intel_dp,
 				  struct drm_modeset_acquire_ctx *ctx,
-				  u32 *crtc_mask)
+				  u8 *pipe_mask)
 {
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct drm_connector_list_iter conn_iter;
 	struct intel_connector *connector;
 	int ret = 0;
 
-	*crtc_mask = 0;
+	*pipe_mask = 0;
 
 	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
@@ -3980,7 +3989,7 @@ static int intel_dp_prep_phy_test(struct intel_dp *intel_dp,
 		    !try_wait_for_completion(&conn_state->commit->hw_done))
 			continue;
 
-		*crtc_mask |= drm_crtc_mask(&crtc->base);
+		*pipe_mask |= BIT(crtc->pipe);
 	}
 	drm_connector_list_iter_end(&conn_iter);
 
@@ -3993,7 +4002,7 @@ static int intel_dp_do_phy_test(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_crtc *crtc;
-	u32 crtc_mask;
+	u8 pipe_mask;
 	int ret;
 
 	ret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex,
@@ -4001,17 +4010,17 @@ static int intel_dp_do_phy_test(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
-	ret = intel_dp_prep_phy_test(intel_dp, ctx, &crtc_mask);
+	ret = intel_dp_prep_phy_test(intel_dp, ctx, &pipe_mask);
 	if (ret)
 		return ret;
 
-	if (crtc_mask == 0)
+	if (pipe_mask == 0)
 		return 0;
 
 	drm_dbg_kms(&dev_priv->drm, "[ENCODER:%d:%s] PHY test\n",
 		    encoder->base.base.id, encoder->base.name);
 
-	for_each_intel_crtc_mask(&dev_priv->drm, crtc, crtc_mask) {
+	for_each_intel_crtc_in_pipe_mask(&dev_priv->drm, crtc, pipe_mask) {
 		const struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 9451f336f28f..5d98773efd1b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -712,7 +712,7 @@ static bool intel_dp_adjust_request_changed(const struct intel_crtc_state *crtc_
 	return false;
 }
 
-static void
+void
 intel_dp_dump_link_status(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy,
 			  const u8 link_status[DP_LINK_STATUS_SIZE])
 {
@@ -996,6 +996,23 @@ static bool intel_dp_disable_dpcd_training_pattern(struct intel_dp *intel_dp,
 	return drm_dp_dpcd_write(&intel_dp->aux, reg, &val, 1) == 1;
 }
 
+static int
+intel_dp_128b132b_intra_hop(struct intel_dp *intel_dp,
+			    const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	u8 sink_status;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_STATUS, &sink_status);
+	if (ret != 1) {
+		drm_dbg_kms(&i915->drm, "Failed to read sink status\n");
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return sink_status & DP_INTRA_HOP_AUX_REPLY_INDICATION ? 1 : 0;
+}
+
 /**
  * intel_dp_stop_link_train - stop link training
  * @intel_dp: DP struct
@@ -1015,11 +1032,21 @@ static bool intel_dp_disable_dpcd_training_pattern(struct intel_dp *intel_dp,
 void intel_dp_stop_link_train(struct intel_dp *intel_dp,
 			      const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+
 	intel_dp->link_trained = true;
 
 	intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
 	intel_dp_program_link_training_pattern(intel_dp, crtc_state, DP_PHY_DPRX,
 					       DP_TRAINING_PATTERN_DISABLE);
+
+	if (intel_dp_is_uhbr(crtc_state) &&
+	    wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
+		drm_dbg_kms(&i915->drm,
+			    "[ENCODER:%d:%s] 128b/132b intra-hop not clearing\n",
+			    encoder->base.base.id, encoder->base.name);
+	}
 }
 
 static bool
@@ -1083,8 +1110,6 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	bool ret = true;
 	int i;
 
-	intel_dp_prepare_link_train(intel_dp, crtc_state);
-
 	for (i = lttpr_count - 1; i >= 0; i--) {
 		enum drm_dp_phy dp_phy = DP_PHY_LTTPR(i);
 
@@ -1104,6 +1129,272 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	return ret;
 }
 
+/*
+ * 128b/132b DP LANEx_EQ_DONE Sequence (DP 2.0 E11 3.5.2.16.1)
+ */
+static bool
+intel_dp_128b132b_lane_eq(struct intel_dp *intel_dp,
+			  const struct intel_crtc_state *crtc_state)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	u8 link_status[DP_LINK_STATUS_SIZE];
+	int delay_us;
+	int try, max_tries = 20;
+	unsigned long deadline;
+	bool timeout = false;
+
+	/*
+	 * Reset signal levels. Start transmitting 128b/132b TPS1.
+	 *
+	 * Put DPRX and LTTPRs (if any) into intra-hop AUX mode by writing TPS1
+	 * in DP_TRAINING_PATTERN_SET.
+	 */
+	if (!intel_dp_reset_link_train(intel_dp, crtc_state, DP_PHY_DPRX,
+				       DP_TRAINING_PATTERN_1)) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Failed to start 128b/132b TPS1\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	delay_us = drm_dp_128b132b_read_aux_rd_interval(&intel_dp->aux);
+
+	/* Read the initial TX FFE settings. */
+	if (drm_dp_dpcd_read_link_status(&intel_dp->aux, link_status) < 0) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Failed to read TX FFE presets\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	/* Update signal levels and training set as requested. */
+	intel_dp_get_adjust_train(intel_dp, crtc_state, DP_PHY_DPRX, link_status);
+	if (!intel_dp_update_link_train(intel_dp, crtc_state, DP_PHY_DPRX)) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Failed to set initial TX FFE settings\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	/* Start transmitting 128b/132b TPS2. */
+	if (!intel_dp_set_link_train(intel_dp, crtc_state, DP_PHY_DPRX,
+				     DP_TRAINING_PATTERN_2)) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Failed to start 128b/132b TPS2\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	/* Time budget for the LANEx_EQ_DONE Sequence */
+	deadline = jiffies + msecs_to_jiffies_timeout(400);
+
+	for (try = 0; try < max_tries; try++) {
+		usleep_range(delay_us, 2 * delay_us);
+
+		/*
+		 * The delay may get updated. The transmitter shall read the
+		 * delay before link status during link training.
+		 */
+		delay_us = drm_dp_128b132b_read_aux_rd_interval(&intel_dp->aux);
+
+		if (drm_dp_dpcd_read_link_status(&intel_dp->aux, link_status) < 0) {
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Failed to read link status\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (drm_dp_128b132b_link_training_failed(link_status)) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Downstream link training failure\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (drm_dp_128b132b_lane_channel_eq_done(link_status, crtc_state->lane_count)) {
+			drm_dbg_kms(&i915->drm,
+				    "[ENCODER:%d:%s] Lane channel eq done\n",
+				    encoder->base.base.id, encoder->base.name);
+			break;
+		}
+
+		if (timeout) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Lane channel eq timeout\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (time_after(jiffies, deadline))
+			timeout = true; /* try one last time after deadline */
+
+		/* Update signal levels and training set as requested. */
+		intel_dp_get_adjust_train(intel_dp, crtc_state, DP_PHY_DPRX, link_status);
+		if (!intel_dp_update_link_train(intel_dp, crtc_state, DP_PHY_DPRX)) {
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Failed to update TX FFE settings\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+	}
+
+	if (try == max_tries) {
+		intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Max loop count reached\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	for (;;) {
+		if (time_after(jiffies, deadline))
+			timeout = true; /* try one last time after deadline */
+
+		if (drm_dp_dpcd_read_link_status(&intel_dp->aux, link_status) < 0) {
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Failed to read link status\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (drm_dp_128b132b_link_training_failed(link_status)) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Downstream link training failure\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (drm_dp_128b132b_eq_interlane_align_done(link_status)) {
+			drm_dbg_kms(&i915->drm,
+				    "[ENCODER:%d:%s] Interlane align done\n",
+				    encoder->base.base.id, encoder->base.name);
+			break;
+		}
+
+		if (timeout) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Interlane align timeout\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		usleep_range(2000, 3000);
+	}
+
+	return true;
+}
+
+/*
+ * 128b/132b DP LANEx_CDS_DONE Sequence (DP 2.0 E11 3.5.2.16.2)
+ */
+static bool
+intel_dp_128b132b_lane_cds(struct intel_dp *intel_dp,
+			   const struct intel_crtc_state *crtc_state,
+			   int lttpr_count)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	u8 link_status[DP_LINK_STATUS_SIZE];
+	unsigned long deadline;
+
+	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TRAINING_PATTERN_SET,
+			       DP_TRAINING_PATTERN_2_CDS) != 1) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] Failed to start 128b/132b TPS2 CDS\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	/* Time budget for the LANEx_CDS_DONE Sequence */
+	deadline = jiffies + msecs_to_jiffies_timeout((lttpr_count + 1) * 20);
+
+	for (;;) {
+		bool timeout = false;
+
+		if (time_after(jiffies, deadline))
+			timeout = true; /* try one last time after deadline */
+
+		usleep_range(2000, 3000);
+
+		if (drm_dp_dpcd_read_link_status(&intel_dp->aux, link_status) < 0) {
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Failed to read link status\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (drm_dp_128b132b_eq_interlane_align_done(link_status) &&
+		    drm_dp_128b132b_cds_interlane_align_done(link_status) &&
+		    drm_dp_128b132b_lane_symbol_locked(link_status, crtc_state->lane_count)) {
+			drm_dbg_kms(&i915->drm,
+				    "[ENCODER:%d:%s] CDS interlane align done\n",
+				    encoder->base.base.id, encoder->base.name);
+			break;
+		}
+
+		if (drm_dp_128b132b_link_training_failed(link_status)) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] Downstream link training failure\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+
+		if (timeout) {
+			intel_dp_dump_link_status(intel_dp, DP_PHY_DPRX, link_status);
+			drm_err(&i915->drm,
+				"[ENCODER:%d:%s] CDS timeout\n",
+				encoder->base.base.id, encoder->base.name);
+			return false;
+		}
+	}
+
+	/* FIXME: Should DP_TRAINING_PATTERN_DISABLE be written first? */
+	if (intel_dp->set_idle_link_train)
+		intel_dp->set_idle_link_train(intel_dp, crtc_state);
+
+	return true;
+}
+
+/*
+ * 128b/132b link training sequence. (DP 2.0 E11 SCR on link training.)
+ */
+static bool
+intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
+			     const struct intel_crtc_state *crtc_state,
+			     int lttpr_count)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	struct intel_connector *connector = intel_dp->attached_connector;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	bool passed = false;
+
+	if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
+		drm_err(&i915->drm,
+			"[ENCODER:%d:%s] 128b/132b intra-hop not clear\n",
+			encoder->base.base.id, encoder->base.name);
+		return false;
+	}
+
+	if (intel_dp_128b132b_lane_eq(intel_dp, crtc_state) &&
+	    intel_dp_128b132b_lane_cds(intel_dp, crtc_state, lttpr_count))
+		passed = true;
+
+	drm_dbg_kms(&i915->drm,
+		    "[CONNECTOR:%d:%s][ENCODER:%d:%s] 128b/132b Link Training %s at link rate = %d, lane count = %d\n",
+		    connector->base.base.id, connector->base.name,
+		    encoder->base.base.id, encoder->base.name,
+		    passed ? "passed" : "failed",
+		    crtc_state->port_clock, crtc_state->lane_count);
+
+	return passed;
+}
+
 /**
  * intel_dp_start_link_train - start link training
  * @intel_dp: DP struct
@@ -1117,6 +1408,7 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 void intel_dp_start_link_train(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state)
 {
+	bool passed;
 	/*
 	 * TODO: Reiniting LTTPRs here won't be needed once proper connector
 	 * HW state readout is added.
@@ -1127,6 +1419,13 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp,
 		/* Still continue with enabling the port and link training. */
 		lttpr_count = 0;
 
-	if (!intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count))
+	intel_dp_prepare_link_train(intel_dp, crtc_state);
+
+	if (intel_dp_is_uhbr(crtc_state))
+		passed = intel_dp_128b132b_link_train(intel_dp, crtc_state, lttpr_count);
+	else
+		passed = intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count);
+
+	if (!passed)
 		intel_dp_schedule_fallback_link_training(intel_dp, crtc_state);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
index dbfb15705aaa..dc1556b46b85 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
@@ -29,6 +29,10 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp,
 void intel_dp_stop_link_train(struct intel_dp *intel_dp,
 			      const struct intel_crtc_state *crtc_state);
 
+void
+intel_dp_dump_link_status(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy,
+			  const u8 link_status[DP_LINK_STATUS_SIZE]);
+
 /* Get the TPSx symbol type of the value programmed to DP_TRAINING_PATTERN_SET */
 static inline u8 intel_dp_training_pattern_symbol(u8 pattern)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6b6eab507d30..e30e698aa684 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -99,6 +99,29 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	return 0;
 }
 
+static int intel_dp_mst_update_slots(struct intel_encoder *encoder,
+				     struct intel_crtc_state *crtc_state,
+				     struct drm_connector_state *conn_state)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
+	struct intel_dp *intel_dp = &intel_mst->primary->dp;
+	struct drm_dp_mst_topology_mgr *mgr = &intel_dp->mst_mgr;
+	struct drm_dp_mst_topology_state *topology_state;
+	u8 link_coding_cap = intel_dp_is_uhbr(crtc_state) ?
+		DP_CAP_ANSI_128B132B : DP_CAP_ANSI_8B10B;
+
+	topology_state = drm_atomic_get_mst_topology_state(conn_state->state, mgr);
+	if (IS_ERR(topology_state)) {
+		drm_dbg_kms(&i915->drm, "slot update failed\n");
+		return PTR_ERR(topology_state);
+	}
+
+	drm_dp_mst_update_slots(topology_state, link_coding_cap);
+
+	return 0;
+}
+
 static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state)
@@ -155,6 +178,10 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
+	ret = intel_dp_mst_update_slots(encoder, pipe_config, conn_state);
+	if (ret)
+		return ret;
+
 	pipe_config->limited_color_range =
 		intel_dp_limited_color_range(pipe_config, conn_state);
 
@@ -357,6 +384,7 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state,
 	struct intel_connector *connector =
 		to_intel_connector(old_conn_state->connector);
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+	int start_slot = intel_dp_is_uhbr(old_crtc_state) ? 0 : 1;
 	int ret;
 
 	drm_dbg_kms(&i915->drm, "active links %d\n",
@@ -366,7 +394,7 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state,
 
 	drm_dp_mst_reset_vcpi_slots(&intel_dp->mst_mgr, connector->port);
 
-	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, 1);
+	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, start_slot);
 	if (ret) {
 		drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret);
 	}
@@ -475,6 +503,7 @@ static void intel_mst_pre_enable_dp(struct intel_atomic_state *state,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
+	int start_slot = intel_dp_is_uhbr(pipe_config) ? 0 : 1;
 	int ret;
 	bool first_mst_stream;
 
@@ -509,7 +538,7 @@ static void intel_mst_pre_enable_dp(struct intel_atomic_state *state,
 
 	intel_dp->active_mst_links++;
 
-	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, 1);
+	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, start_slot);
 
 	/*
 	 * Before Gen 12 this is not done as part of
diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c
index 1ce0c171f4fb..14f5ffe27d05 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll.c
@@ -16,6 +16,10 @@
 #include "intel_snps_phy.h"
 #include "vlv_sideband.h"
 
+struct intel_dpll_funcs {
+	int (*crtc_compute_clock)(struct intel_crtc_state *crtc_state);
+};
+
 struct intel_limit {
 	struct {
 		int min, max;
@@ -1400,6 +1404,14 @@ static const struct intel_dpll_funcs i8xx_dpll_funcs = {
 	.crtc_compute_clock = i8xx_crtc_compute_clock,
 };
 
+int intel_dpll_crtc_compute_clock(struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	return i915->dpll_funcs->crtc_compute_clock(crtc_state);
+}
+
 void
 intel_dpll_init_clock_hook(struct drm_i915_private *dev_priv)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_dpll.h b/drivers/gpu/drm/i915/display/intel_dpll.h
index 1af0ac43cca4..69b06a9e473e 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll.h
@@ -15,6 +15,7 @@ struct intel_crtc_state;
 enum pipe;
 
 void intel_dpll_init_clock_hook(struct drm_i915_private *dev_priv);
+int intel_dpll_crtc_compute_clock(struct intel_crtc_state *crtc_state);
 int vlv_calc_dpll_params(int refclk, struct dpll *clock);
 int pnv_calc_dpll_params(int refclk, struct dpll *clock);
 int i9xx_calc_dpll_params(int refclk, struct dpll *clock);
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 6723c3de5a80..569903d47aea 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2748,6 +2748,9 @@ static void icl_calc_dpll_state(struct drm_i915_private *i915,
 		pll_state->cfgcr1 |= TGL_DPLL_CFGCR1_CFSELOVRD_NORMAL_XTAL;
 	else
 		pll_state->cfgcr1 |= DPLL_CFGCR1_CENTRAL_FREQ_8400;
+
+	if (i915->vbt.override_afc_startup)
+		pll_state->div0 = TGL_DPLL0_DIV0_AFC_STARTUP(i915->vbt.override_afc_startup_val);
 }
 
 static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
@@ -2949,6 +2952,11 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 					 DKL_PLL_DIV0_PROP_COEFF(prop_coeff) |
 					 DKL_PLL_DIV0_FBPREDIV(m1div) |
 					 DKL_PLL_DIV0_FBDIV_INT(m2div_int);
+		if (dev_priv->vbt.override_afc_startup) {
+			u8 val = dev_priv->vbt.override_afc_startup_val;
+
+			pll_state->mg_pll_div0 |= DKL_PLL_DIV0_AFC_STARTUP(val);
+		}
 
 		pll_state->mg_pll_div1 = DKL_PLL_DIV1_IREF_TRIM(iref_trim) |
 					 DKL_PLL_DIV1_TDC_TARGET_CNT(tdc_targetcnt);
@@ -3448,10 +3456,10 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 		MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
 
 	hw_state->mg_pll_div0 = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port));
-	hw_state->mg_pll_div0 &= (DKL_PLL_DIV0_INTEG_COEFF_MASK |
-				  DKL_PLL_DIV0_PROP_COEFF_MASK |
-				  DKL_PLL_DIV0_FBPREDIV_MASK |
-				  DKL_PLL_DIV0_FBDIV_INT_MASK);
+	val = DKL_PLL_DIV0_MASK;
+	if (dev_priv->vbt.override_afc_startup)
+		val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
+	hw_state->mg_pll_div0 &= val;
 
 	hw_state->mg_pll_div1 = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
 	hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK |
@@ -3513,6 +3521,10 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 						 TGL_DPLL_CFGCR0(id));
 		hw_state->cfgcr1 = intel_de_read(dev_priv,
 						 TGL_DPLL_CFGCR1(id));
+		if (dev_priv->vbt.override_afc_startup) {
+			hw_state->div0 = intel_de_read(dev_priv, TGL_DPLL0_DIV0(id));
+			hw_state->div0 &= TGL_DPLL0_DIV0_AFC_STARTUP_MASK;
+		}
 	} else {
 		if (IS_JSL_EHL(dev_priv) && id == DPLL_ID_EHL_DPLL4) {
 			hw_state->cfgcr0 = intel_de_read(dev_priv,
@@ -3554,7 +3566,7 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv,
 {
 	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
 	const enum intel_dpll_id id = pll->info->id;
-	i915_reg_t cfgcr0_reg, cfgcr1_reg;
+	i915_reg_t cfgcr0_reg, cfgcr1_reg, div0_reg = INVALID_MMIO_REG;
 
 	if (IS_ALDERLAKE_S(dev_priv)) {
 		cfgcr0_reg = ADLS_DPLL_CFGCR0(id);
@@ -3568,6 +3580,7 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv,
 	} else if (DISPLAY_VER(dev_priv) >= 12) {
 		cfgcr0_reg = TGL_DPLL_CFGCR0(id);
 		cfgcr1_reg = TGL_DPLL_CFGCR1(id);
+		div0_reg = TGL_DPLL0_DIV0(id);
 	} else {
 		if (IS_JSL_EHL(dev_priv) && id == DPLL_ID_EHL_DPLL4) {
 			cfgcr0_reg = ICL_DPLL_CFGCR0(4);
@@ -3580,6 +3593,12 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv,
 
 	intel_de_write(dev_priv, cfgcr0_reg, hw_state->cfgcr0);
 	intel_de_write(dev_priv, cfgcr1_reg, hw_state->cfgcr1);
+	drm_WARN_ON_ONCE(&dev_priv->drm, dev_priv->vbt.override_afc_startup &&
+			 !i915_mmio_reg_valid(div0_reg));
+	if (dev_priv->vbt.override_afc_startup &&
+	    i915_mmio_reg_valid(div0_reg))
+		intel_de_rmw(dev_priv, div0_reg, TGL_DPLL0_DIV0_AFC_STARTUP_MASK,
+			     hw_state->div0);
 	intel_de_posting_read(dev_priv, cfgcr1_reg);
 }
 
@@ -3667,13 +3686,11 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv,
 	val |= hw_state->mg_clktop2_hsclkctl;
 	intel_de_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val);
 
-	val = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port));
-	val &= ~(DKL_PLL_DIV0_INTEG_COEFF_MASK |
-		 DKL_PLL_DIV0_PROP_COEFF_MASK |
-		 DKL_PLL_DIV0_FBPREDIV_MASK |
-		 DKL_PLL_DIV0_FBDIV_INT_MASK);
-	val |= hw_state->mg_pll_div0;
-	intel_de_write(dev_priv, DKL_PLL_DIV0(tc_port), val);
+	val = DKL_PLL_DIV0_MASK;
+	if (dev_priv->vbt.override_afc_startup)
+		val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
+	intel_de_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val,
+		     hw_state->mg_pll_div0);
 
 	val = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
 	val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK |
@@ -3912,13 +3929,14 @@ static void icl_dump_hw_state(struct drm_i915_private *dev_priv,
 			      const struct intel_dpll_hw_state *hw_state)
 {
 	drm_dbg_kms(&dev_priv->drm,
-		    "dpll_hw_state: cfgcr0: 0x%x, cfgcr1: 0x%x, "
+		    "dpll_hw_state: cfgcr0: 0x%x, cfgcr1: 0x%x, div0: 0x%x, "
 		    "mg_refclkin_ctl: 0x%x, hg_clktop2_coreclkctl1: 0x%x, "
 		    "mg_clktop2_hsclkctl: 0x%x, mg_pll_div0: 0x%x, "
 		    "mg_pll_div2: 0x%x, mg_pll_lf: 0x%x, "
 		    "mg_pll_frac_lock: 0x%x, mg_pll_ssc: 0x%x, "
 		    "mg_pll_bias: 0x%x, mg_pll_tdc_coldst_bias: 0x%x\n",
 		    hw_state->cfgcr0, hw_state->cfgcr1,
+		    hw_state->div0,
 		    hw_state->mg_refclkin_ctl,
 		    hw_state->mg_clktop2_coreclkctl1,
 		    hw_state->mg_clktop2_hsclkctl,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index 91fe181462b2..ba2fdfce1579 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -208,6 +208,9 @@ struct intel_dpll_hw_state {
 	/* icl */
 	u32 cfgcr0;
 
+	/* tgl */
+	u32 div0;
+
 	/* bxt */
 	u32 ebb0, ebb4, pll0, pll1, pll2, pll3, pll6, pll8, pll9, pll10, pcsdw12;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index 8f674745e7e0..2b8e89477f48 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -3,11 +3,13 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include "gem/i915_gem_domain.h"
+#include "gt/gen8_ppgtt.h"
+
 #include "i915_drv.h"
 #include "intel_display_types.h"
 #include "intel_dpt.h"
 #include "intel_fb.h"
-#include "gt/gen8_ppgtt.h"
 
 struct i915_dpt {
 	struct i915_address_space vm;
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 83a69a4a4fea..b34a67309976 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -4,6 +4,8 @@
  *
  */
 
+#include "gem/i915_gem_internal.h"
+
 #include "i915_drv.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 31c15e5fca95..e60046d90124 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -7,6 +7,7 @@
  * DOC: display pinning helpers
  */
 
+#include "gem/i915_gem_domain.h"
 #include "gem/i915_gem_object.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index adc3a81be9f7..837484cbcd33 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -50,6 +50,23 @@
 #include "intel_fbdev.h"
 #include "intel_frontbuffer.h"
 
+struct intel_fbdev {
+	struct drm_fb_helper helper;
+	struct intel_framebuffer *fb;
+	struct i915_vma *vma;
+	unsigned long vma_flags;
+	async_cookie_t cookie;
+	int preferred_bpp;
+
+	/* Whether or not fbdev hpd processing is temporarily suspended */
+	bool hpd_suspended: 1;
+	/* Set when a hotplug was received while HPD processing was suspended */
+	bool hpd_waiting: 1;
+
+	/* Protects hpd_suspended */
+	struct mutex hpd_lock;
+};
+
 static struct intel_frontbuffer *to_frontbuffer(struct intel_fbdev *ifbdev)
 {
 	return ifbdev->fb->frontbuffer;
@@ -680,3 +697,11 @@ void intel_fbdev_restore_mode(struct drm_device *dev)
 	if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper) == 0)
 		intel_fbdev_invalidate(ifbdev);
 }
+
+struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev)
+{
+	if (!fbdev || !fbdev->helper.fb)
+		return NULL;
+
+	return to_intel_framebuffer(fbdev->helper.fb);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.h b/drivers/gpu/drm/i915/display/intel_fbdev.h
index de7c84250eb5..0e95e9472fa3 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.h
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.h
@@ -10,6 +10,8 @@
 
 struct drm_device;
 struct drm_i915_private;
+struct intel_fbdev;
+struct intel_framebuffer;
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 int intel_fbdev_init(struct drm_device *dev);
@@ -19,6 +21,7 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv);
 void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous);
 void intel_fbdev_output_poll_changed(struct drm_device *dev);
 void intel_fbdev_restore_mode(struct drm_device *dev);
+struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev);
 #else
 static inline int intel_fbdev_init(struct drm_device *dev)
 {
@@ -48,6 +51,10 @@ static inline void intel_fbdev_output_poll_changed(struct drm_device *dev)
 static inline void intel_fbdev_restore_mode(struct drm_device *dev)
 {
 }
+static inline struct intel_framebuffer *intel_fbdev_framebuffer(struct intel_fbdev *fbdev)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __INTEL_FBDEV_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c
index 3d6e22923601..4e4b43669b14 100644
--- a/drivers/gpu/drm/i915/display/intel_fdi.c
+++ b/drivers/gpu/drm/i915/display/intel_fdi.c
@@ -10,6 +10,11 @@
 #include "intel_display_types.h"
 #include "intel_fdi.h"
 
+struct intel_fdi_funcs {
+	void (*fdi_link_train)(struct intel_crtc *crtc,
+			       const struct intel_crtc_state *crtc_state);
+};
+
 static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 6c72f8587240..1aa5bdc7b0dc 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1869,7 +1869,7 @@ hdmi_port_clock_valid(struct intel_hdmi *hdmi,
 	return MODE_OK;
 }
 
-static int intel_hdmi_tmds_clock(int clock, int bpc, bool ycbcr420_output)
+int intel_hdmi_tmds_clock(int clock, int bpc, bool ycbcr420_output)
 {
 	/* YCBCR420 TMDS rate requirement is half the pixel clock */
 	if (ycbcr420_output)
@@ -1935,25 +1935,30 @@ intel_hdmi_mode_clock_valid(struct drm_connector *connector, int clock,
 {
 	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector));
-	enum drm_mode_status status;
+	enum drm_mode_status status = MODE_OK;
+	int bpc;
+
+	/*
+	 * Try all color depths since valid port clock range
+	 * can have holes. Any mode that can be used with at
+	 * least one color depth is accepted.
+	 */
+	for (bpc = 12; bpc >= 8; bpc -= 2) {
+		int tmds_clock = intel_hdmi_tmds_clock(clock, bpc, ycbcr420_output);
+
+		if (!intel_hdmi_source_bpc_possible(i915, bpc))
+			continue;
+
+		if (!intel_hdmi_sink_bpc_possible(connector, bpc, has_hdmi_sink, ycbcr420_output))
+			continue;
+
+		status = hdmi_port_clock_valid(hdmi, tmds_clock, true, has_hdmi_sink);
+		if (status == MODE_OK)
+			return MODE_OK;
+	}
 
-	/* check if we can do 8bpc */
-	status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 8, ycbcr420_output),
-				       true, has_hdmi_sink);
-
-	/* if we can't do 8bpc we may still be able to do 12bpc */
-	if (status != MODE_OK &&
-	    intel_hdmi_source_bpc_possible(i915, 12) &&
-	    intel_hdmi_sink_bpc_possible(connector, 12, has_hdmi_sink, ycbcr420_output))
-		status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 12, ycbcr420_output),
-					       true, has_hdmi_sink);
-
-	/* if we can't do 8,12bpc we may still be able to do 10bpc */
-	if (status != MODE_OK &&
-	    intel_hdmi_source_bpc_possible(i915, 10) &&
-	    intel_hdmi_sink_bpc_possible(connector, 10, has_hdmi_sink, ycbcr420_output))
-		status = hdmi_port_clock_valid(hdmi, intel_hdmi_tmds_clock(clock, 10, ycbcr420_output),
-					       true, has_hdmi_sink);
+	/* can never happen */
+	drm_WARN_ON(&i915->drm, status == MODE_OK);
 
 	return status;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h
index b0804b862a89..93f65a917c36 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@@ -46,6 +46,7 @@ bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_state,
 				    const struct drm_connector_state *conn_state);
 bool intel_hdmi_bpc_possible(const struct intel_crtc_state *crtc_state,
 			     int bpc, bool has_hdmi_sink, bool ycbcr420_output);
+int intel_hdmi_tmds_clock(int clock, int bpc, bool ycbcr420_output);
 int intel_hdmi_dsc_get_bpp(int src_fractional_bpp, int slice_width,
 			   int num_slices, int output_format, bool hdmi_all_bpp,
 			   int hdmi_max_chunk_bytes);
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index 912b7003dcfa..8204126d17f9 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 
 #include "i915_drv.h"
+#include "i915_irq.h"
 #include "intel_display_types.h"
 #include "intel_hotplug.h"
 
@@ -213,12 +214,6 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void intel_hpd_irq_setup(struct drm_i915_private *i915)
-{
-	if (i915->display_irqs_enabled && i915->hotplug_funcs)
-		i915->hotplug_funcs->hpd_irq_setup(i915);
-}
-
 static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index ad1afe9df6c3..f31e8c3f8ce0 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -47,10 +47,11 @@
 #define OPREGION_ASLE_EXT_OFFSET	0x1C00
 
 #define OPREGION_SIGNATURE "IntelGraphicsMem"
-#define MBOX_ACPI      (1<<0)
-#define MBOX_SWSCI     (1<<1)
-#define MBOX_ASLE      (1<<2)
-#define MBOX_ASLE_EXT  (1<<4)
+#define MBOX_ACPI		BIT(0)	/* Mailbox #1 */
+#define MBOX_SWSCI		BIT(1)	/* Mailbox #2 (obsolete from v2.x) */
+#define MBOX_ASLE		BIT(2)	/* Mailbox #3 */
+#define MBOX_ASLE_EXT		BIT(4)	/* Mailbox #5 */
+#define MBOX_BACKLIGHT		BIT(5)	/* Mailbox #2 (valid from v3.x) */
 
 struct opregion_header {
 	u8 signature[16];
@@ -245,14 +246,10 @@ struct opregion_asle_ext {
 
 #define MAX_DSLP	1500
 
-static int swsci(struct drm_i915_private *dev_priv,
-		 u32 function, u32 parm, u32 *parm_out)
+static int check_swsci_function(struct drm_i915_private *i915, u32 function)
 {
-	struct opregion_swsci *swsci = dev_priv->opregion.swsci;
-	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
-	u32 main_function, sub_function, scic;
-	u16 swsci_val;
-	u32 dslp;
+	struct opregion_swsci *swsci = i915->opregion.swsci;
+	u32 main_function, sub_function;
 
 	if (!swsci)
 		return -ENODEV;
@@ -264,15 +261,31 @@ static int swsci(struct drm_i915_private *dev_priv,
 
 	/* Check if we can call the function. See swsci_setup for details. */
 	if (main_function == SWSCI_SBCB) {
-		if ((dev_priv->opregion.swsci_sbcb_sub_functions &
+		if ((i915->opregion.swsci_sbcb_sub_functions &
 		     (1 << sub_function)) == 0)
 			return -EINVAL;
 	} else if (main_function == SWSCI_GBDA) {
-		if ((dev_priv->opregion.swsci_gbda_sub_functions &
+		if ((i915->opregion.swsci_gbda_sub_functions &
 		     (1 << sub_function)) == 0)
 			return -EINVAL;
 	}
 
+	return 0;
+}
+
+static int swsci(struct drm_i915_private *dev_priv,
+		 u32 function, u32 parm, u32 *parm_out)
+{
+	struct opregion_swsci *swsci = dev_priv->opregion.swsci;
+	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
+	u32 scic, dslp;
+	u16 swsci_val;
+	int ret;
+
+	ret = check_swsci_function(dev_priv, function);
+	if (ret)
+		return ret;
+
 	/* Driver sleep timeout in ms. */
 	dslp = swsci->dslp;
 	if (!dslp) {
@@ -346,11 +359,17 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 	u32 parm = 0;
 	u32 type = 0;
 	u32 port;
+	int ret;
 
 	/* don't care about old stuff for now */
 	if (!HAS_DDI(dev_priv))
 		return 0;
 
+	/* Avoid port out of bounds checks if SWSCI isn't there. */
+	ret = check_swsci_function(dev_priv, SWSCI_SBCB_DISPLAY_POWER_STATE);
+	if (ret)
+		return ret;
+
 	if (intel_encoder->type == INTEL_OUTPUT_DSI)
 		port = 0;
 	else
@@ -914,9 +933,17 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv)
 	}
 
 	if (mboxes & MBOX_SWSCI) {
-		drm_dbg(&dev_priv->drm, "SWSCI supported\n");
-		opregion->swsci = base + OPREGION_SWSCI_OFFSET;
-		swsci_setup(dev_priv);
+		u8 major = opregion->header->over.major;
+
+		if (major >= 3) {
+			drm_err(&dev_priv->drm, "SWSCI Mailbox #2 present for opregion v3.x, ignoring\n");
+		} else {
+			if (major >= 2)
+				drm_dbg(&dev_priv->drm, "SWSCI Mailbox #2 present for opregion v2.x\n");
+			drm_dbg(&dev_priv->drm, "SWSCI supported\n");
+			opregion->swsci = base + OPREGION_SWSCI_OFFSET;
+			swsci_setup(dev_priv);
+		}
 	}
 
 	if (mboxes & MBOX_ASLE) {
@@ -931,6 +958,10 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv)
 		opregion->asle_ext = base + OPREGION_ASLE_EXT_OFFSET;
 	}
 
+	if (mboxes & MBOX_BACKLIGHT) {
+		drm_dbg(&dev_priv->drm, "Mailbox #2 for backlight present\n");
+	}
+
 	if (intel_load_vbt_firmware(dev_priv) == 0)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 5358f03b52db..76845d34ad0c 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -28,6 +28,7 @@
 
 #include <drm/drm_fourcc.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c
index 01ce1d72297f..f2fbb196d62a 100644
--- a/drivers/gpu/drm/i915/display/intel_plane_initial.c
+++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c
@@ -165,8 +165,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->base.state);
 	struct intel_plane *plane =
 		to_intel_plane(crtc->base.primary);
 	struct intel_plane_state *plane_state =
@@ -203,11 +201,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 	 * pretend the BIOS never had it enabled.
 	 */
 	intel_plane_disable_noatomic(crtc, plane);
-	if (crtc_state->bigjoiner) {
-		struct intel_crtc *slave =
-			crtc_state->bigjoiner_linked_crtc;
-		intel_plane_disable_noatomic(slave, to_intel_plane(slave->base.primary));
-	}
 
 	return;
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index a1a663f362e7..2e0b092f4b6b 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1063,31 +1063,28 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	intel_dp->psr.active = true;
 }
 
-static void intel_psr_enable_source(struct intel_dp *intel_dp)
+static u32 wa_16013835468_bit_get(struct intel_dp *intel_dp)
+{
+	switch (intel_dp->psr.pipe) {
+	case PIPE_A:
+		return LATENCY_REPORTING_REMOVED_PIPE_A;
+	case PIPE_B:
+		return LATENCY_REPORTING_REMOVED_PIPE_B;
+	case PIPE_C:
+		return LATENCY_REPORTING_REMOVED_PIPE_C;
+	default:
+		MISSING_CASE(intel_dp->psr.pipe);
+		return 0;
+	}
+}
+
+static void intel_psr_enable_source(struct intel_dp *intel_dp,
+				    const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	enum transcoder cpu_transcoder = intel_dp->psr.transcoder;
 	u32 mask;
 
-	if (intel_dp->psr.psr2_enabled && DISPLAY_VER(dev_priv) == 9) {
-		i915_reg_t reg = CHICKEN_TRANS(cpu_transcoder);
-		u32 chicken = intel_de_read(dev_priv, reg);
-
-		chicken |= PSR2_VSC_ENABLE_PROG_HEADER |
-			   PSR2_ADD_VERTICAL_LINE_COUNT;
-		intel_de_write(dev_priv, reg, chicken);
-	}
-
-	/*
-	 * Wa_16014451276:adlp
-	 * All supported adlp panels have 1-based X granularity, this may
-	 * cause issues if non-supported panels are used.
-	 */
-	if (IS_ALDERLAKE_P(dev_priv) &&
-	    intel_dp->psr.psr2_enabled)
-		intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), 0,
-			     ADLP_1_BASED_X_GRANULARITY);
-
 	/*
 	 * Per Spec: Avoid continuous PSR exit by masking MEMUP and HPD also
 	 * mask LPSP to avoid dependency on other drivers that might block
@@ -1126,18 +1123,47 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp)
 			     intel_dp->psr.psr2_sel_fetch_enabled ?
 			     IGNORE_PSR2_HW_TRACKING : 0);
 
-	/* Wa_16011168373:adl-p */
-	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) &&
-	    intel_dp->psr.psr2_enabled)
-		intel_de_rmw(dev_priv,
-			     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
-			     TRANS_SET_CONTEXT_LATENCY_MASK,
-			     TRANS_SET_CONTEXT_LATENCY_VALUE(1));
+	if (intel_dp->psr.psr2_enabled) {
+		if (DISPLAY_VER(dev_priv) == 9)
+			intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), 0,
+				     PSR2_VSC_ENABLE_PROG_HEADER |
+				     PSR2_ADD_VERTICAL_LINE_COUNT);
 
-	/* Wa_16012604467:adlp */
-	if (IS_ALDERLAKE_P(dev_priv) && intel_dp->psr.psr2_enabled)
-		intel_de_rmw(dev_priv, CLKGATE_DIS_MISC, 0,
-			     CLKGATE_DIS_MISC_DMASC_GATING_DIS);
+		/*
+		 * Wa_16014451276:adlp
+		 * All supported adlp panels have 1-based X granularity, this may
+		 * cause issues if non-supported panels are used.
+		 */
+		if (IS_ALDERLAKE_P(dev_priv))
+			intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), 0,
+				     ADLP_1_BASED_X_GRANULARITY);
+
+		/* Wa_16011168373:adl-p */
+		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
+			intel_de_rmw(dev_priv,
+				     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
+				     TRANS_SET_CONTEXT_LATENCY_MASK,
+				     TRANS_SET_CONTEXT_LATENCY_VALUE(1));
+
+		/* Wa_16012604467:adlp */
+		if (IS_ALDERLAKE_P(dev_priv))
+			intel_de_rmw(dev_priv, CLKGATE_DIS_MISC, 0,
+				     CLKGATE_DIS_MISC_DMASC_GATING_DIS);
+
+		/* Wa_16013835468:tgl[b0+], dg1 */
+		if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_B0, STEP_FOREVER) ||
+		    IS_DG1(dev_priv)) {
+			u16 vtotal, vblank;
+
+			vtotal = crtc_state->uapi.adjusted_mode.crtc_vtotal -
+				 crtc_state->uapi.adjusted_mode.crtc_vdisplay;
+			vblank = crtc_state->uapi.adjusted_mode.crtc_vblank_end -
+				 crtc_state->uapi.adjusted_mode.crtc_vblank_start;
+			if (vblank > vtotal)
+				intel_de_rmw(dev_priv, GEN8_CHICKEN_DCPR_1, 0,
+					     wa_16013835468_bit_get(intel_dp));
+		}
+	}
 }
 
 static bool psr_interrupt_error_check(struct intel_dp *intel_dp)
@@ -1202,7 +1228,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 	intel_write_dp_vsc_sdp(encoder, crtc_state, &crtc_state->psr_vsc);
 	intel_snps_phy_update_psr_power_state(dev_priv, phy, true);
 	intel_psr_enable_sink(intel_dp);
-	intel_psr_enable_source(intel_dp);
+	intel_psr_enable_source(intel_dp, crtc_state);
 	intel_dp->psr.enabled = true;
 	intel_dp->psr.paused = false;
 
@@ -1290,17 +1316,24 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
 			     DIS_RAM_BYPASS_PSR2_MAN_TRACK, 0);
 
-	/* Wa_16011168373:adl-p */
-	if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0) &&
-	    intel_dp->psr.psr2_enabled)
-		intel_de_rmw(dev_priv,
-			     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
-			     TRANS_SET_CONTEXT_LATENCY_MASK, 0);
-
-	/* Wa_16012604467:adlp */
-	if (IS_ALDERLAKE_P(dev_priv) && intel_dp->psr.psr2_enabled)
-		intel_de_rmw(dev_priv, CLKGATE_DIS_MISC,
-			     CLKGATE_DIS_MISC_DMASC_GATING_DIS, 0);
+	if (intel_dp->psr.psr2_enabled) {
+		/* Wa_16011168373:adl-p */
+		if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0))
+			intel_de_rmw(dev_priv,
+				     TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder),
+				     TRANS_SET_CONTEXT_LATENCY_MASK, 0);
+
+		/* Wa_16012604467:adlp */
+		if (IS_ALDERLAKE_P(dev_priv))
+			intel_de_rmw(dev_priv, CLKGATE_DIS_MISC,
+				     CLKGATE_DIS_MISC_DMASC_GATING_DIS, 0);
+
+		/* Wa_16013835468:tgl[b0+], dg1 */
+		if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_B0, STEP_FOREVER) ||
+		    IS_DG1(dev_priv))
+			intel_de_rmw(dev_priv, GEN8_CHICKEN_DCPR_1,
+				     wa_16013835468_bit_get(intel_dp), 0);
+	}
 
 	intel_snps_phy_update_psr_power_state(dev_priv, phy, false);
 
diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c
index 8573a458811a..8fd00de981fc 100644
--- a/drivers/gpu/drm/i915/display/intel_snps_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c
@@ -35,7 +35,7 @@ void intel_snps_phy_wait_for_calibration(struct drm_i915_private *i915)
 		if (intel_de_wait_for_clear(i915, ICL_PHY_MISC(phy),
 					    DG2_PHY_DP_TX_ACK_MASK, 25))
 			drm_err(&i915->drm, "SNPS PHY %c failed to calibrate after 25ms.\n",
-				phy);
+				phy_name(phy));
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index feead08ddf8f..fc037c027ea5 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -693,6 +693,8 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	struct intel_encoder *encoder = &dig_port->base;
+	intel_wakeref_t tc_cold_wref;
+	enum intel_display_power_domain domain;
 	int active_links = 0;
 
 	mutex_lock(&dig_port->tc_lock);
@@ -704,12 +706,11 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 
 	drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED);
 	drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref);
-	if (active_links) {
-		enum intel_display_power_domain domain;
-		intel_wakeref_t tc_cold_wref = tc_cold_block(dig_port, &domain);
 
-		dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port);
+	tc_cold_wref = tc_cold_block(dig_port, &domain);
 
+	dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port);
+	if (active_links) {
 		if (!icl_tc_phy_is_connected(dig_port))
 			drm_dbg_kms(&i915->drm,
 				    "Port %s: PHY disconnected with %d active link(s)\n",
@@ -718,10 +719,23 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port)
 
 		dig_port->tc_lock_wakeref = tc_cold_block(dig_port,
 							  &dig_port->tc_lock_power_domain);
-
-		tc_cold_unblock(dig_port, domain, tc_cold_wref);
+	} else {
+		/*
+		 * TBT-alt is the default mode in any case the PHY ownership is not
+		 * held (regardless of the sink's connected live state), so
+		 * we'll just switch to disconnected mode from it here without
+		 * a note.
+		 */
+		if (dig_port->tc_mode != TC_PORT_TBT_ALT)
+			drm_dbg_kms(&i915->drm,
+				    "Port %s: PHY left in %s mode on disabled port, disconnecting it\n",
+				    dig_port->tc_port_name,
+				    tc_port_mode_name(dig_port->tc_mode));
+		icl_tc_phy_disconnect(dig_port);
 	}
 
+	tc_cold_unblock(dig_port, domain, tc_cold_wref);
+
 	drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n",
 		    dig_port->tc_port_name,
 		    tc_port_mode_name(dig_port->tc_mode));
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index a39d6cfea87a..b9397d9363c5 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -162,6 +162,14 @@ struct bdb_general_features {
 	u8 dp_ssc_freq:1;	/* SSC freq for PCH attached eDP */
 	u8 dp_ssc_dongle_supported:1;
 	u8 rsvd11:2; /* finish byte */
+
+	/* bits 6 */
+	u8 tc_hpd_retry_timeout:7; /* 242 */
+	u8 rsvd12:1;
+
+	/* bits 7 */
+	u8 afc_startup_config:2;/* 249 */
+	u8 rsvd13:6;
 } __packed;
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 3faea903b9ae..545eff5bf158 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -1107,18 +1107,6 @@ static i915_reg_t dss_ctl2_reg(struct intel_crtc *crtc, enum transcoder cpu_tran
 		ICL_PIPE_DSS_CTL2(crtc->pipe) : DSS_CTL2;
 }
 
-struct intel_crtc *
-intel_dsc_get_bigjoiner_secondary(const struct intel_crtc *primary_crtc)
-{
-	return intel_crtc_for_pipe(to_i915(primary_crtc->base.dev), primary_crtc->pipe + 1);
-}
-
-static struct intel_crtc *
-intel_dsc_get_bigjoiner_primary(const struct intel_crtc *secondary_crtc)
-{
-	return intel_crtc_for_pipe(to_i915(secondary_crtc->base.dev), secondary_crtc->pipe - 1);
-}
-
 void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
@@ -1126,7 +1114,7 @@ void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state)
 	u32 dss_ctl1_val = 0;
 
 	if (crtc_state->bigjoiner && !crtc_state->dsc.compression_enable) {
-		if (crtc_state->bigjoiner_slave)
+		if (intel_crtc_is_bigjoiner_slave(crtc_state))
 			dss_ctl1_val |= UNCOMPRESSED_JOINER_SLAVE;
 		else
 			dss_ctl1_val |= UNCOMPRESSED_JOINER_MASTER;
@@ -1154,7 +1142,7 @@ void intel_dsc_enable(const struct intel_crtc_state *crtc_state)
 	}
 	if (crtc_state->bigjoiner) {
 		dss_ctl1_val |= BIG_JOINER_ENABLE;
-		if (!crtc_state->bigjoiner_slave)
+		if (!intel_crtc_is_bigjoiner_slave(crtc_state))
 			dss_ctl1_val |= MASTER_BIG_JOINER_ENABLE;
 	}
 	intel_de_write(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val);
@@ -1174,25 +1162,6 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 	}
 }
 
-void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	u32 dss_ctl1;
-
-	dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder));
-	if (dss_ctl1 & UNCOMPRESSED_JOINER_MASTER) {
-		crtc_state->bigjoiner = true;
-		crtc_state->bigjoiner_linked_crtc = intel_dsc_get_bigjoiner_secondary(crtc);
-		drm_WARN_ON(&dev_priv->drm, !crtc_state->bigjoiner_linked_crtc);
-	} else if (dss_ctl1 & UNCOMPRESSED_JOINER_SLAVE) {
-		crtc_state->bigjoiner = true;
-		crtc_state->bigjoiner_slave = true;
-		crtc_state->bigjoiner_linked_crtc = intel_dsc_get_bigjoiner_primary(crtc);
-		drm_WARN_ON(&dev_priv->drm, !crtc_state->bigjoiner_linked_crtc);
-	}
-}
-
 void intel_dsc_get_config(struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
@@ -1223,18 +1192,6 @@ void intel_dsc_get_config(struct intel_crtc_state *crtc_state)
 	crtc_state->dsc.dsc_split = (dss_ctl2 & RIGHT_BRANCH_VDSC_ENABLE) &&
 		(dss_ctl1 & JOINER_ENABLE);
 
-	if (dss_ctl1 & BIG_JOINER_ENABLE) {
-		crtc_state->bigjoiner = true;
-
-		if (!(dss_ctl1 & MASTER_BIG_JOINER_ENABLE)) {
-			crtc_state->bigjoiner_slave = true;
-			crtc_state->bigjoiner_linked_crtc = intel_dsc_get_bigjoiner_primary(crtc);
-		} else {
-			crtc_state->bigjoiner_linked_crtc = intel_dsc_get_bigjoiner_secondary(crtc);
-		}
-		drm_WARN_ON(&dev_priv->drm, !crtc_state->bigjoiner_linked_crtc);
-	}
-
 	/* FIXME: add more state readout as needed */
 
 	/* PPS1 */
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h
index 4ec75f715986..8763f00fa7e2 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.h
@@ -18,7 +18,6 @@ void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state)
 void intel_dsc_enable(const struct intel_crtc_state *crtc_state);
 void intel_dsc_disable(const struct intel_crtc_state *crtc_state);
 int intel_dsc_compute_params(struct intel_crtc_state *pipe_config);
-void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state);
 void intel_dsc_get_config(struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain
 intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 8a248003dfae..ce91b23385cf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -4,6 +4,8 @@
  * Copyright © 2016 Intel Corporation
  */
 
+#include <drm/drm_cache.h>
+
 #include "display/intel_frontbuffer.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 00327b750fbb..2958e2be4292 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -67,6 +67,7 @@
 #include <linux/log2.h>
 #include <linux/nospec.h>
 
+#include <drm/drm_cache.h>
 #include <drm/drm_syncobj.h>
 
 #include "gt/gen6_ppgtt.h"
@@ -79,6 +80,7 @@
 
 #include "pxp/intel_pxp.h"
 
+#include "i915_file_private.h"
 #include "i915_gem_context.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
@@ -343,6 +345,20 @@ static int proto_context_register(struct drm_i915_file_private *fpriv,
 	return ret;
 }
 
+static struct i915_address_space *
+i915_gem_vm_lookup(struct drm_i915_file_private *file_priv, u32 id)
+{
+	struct i915_address_space *vm;
+
+	xa_lock(&file_priv->vm_xa);
+	vm = xa_load(&file_priv->vm_xa, id);
+	if (vm)
+		kref_get(&vm->ref);
+	xa_unlock(&file_priv->vm_xa);
+
+	return vm;
+}
+
 static int set_proto_ctx_vm(struct drm_i915_file_private *fpriv,
 			    struct i915_gem_proto_context *pc,
 			    const struct drm_i915_gem_context_param *args)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index 9402d4bf4ffc..c6eb023d3d86 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -3,12 +3,15 @@
  * Copyright © 2020 Intel Corporation
  */
 
+#include <drm/drm_fourcc.h>
+
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
 #include "pxp/intel_pxp.h"
 
 #include "i915_drv.h"
+#include "i915_gem_create.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.h b/drivers/gpu/drm/i915/gem/i915_gem_create.h
new file mode 100644
index 000000000000..9536aa906001
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_GEM_CREATE_H__
+#define __I915_GEM_CREATE_H__
+
+struct drm_file;
+struct drm_device;
+struct drm_mode_create_dumb;
+
+int i915_gem_dumb_create(struct drm_file *file_priv,
+			 struct drm_device *dev,
+			 struct drm_mode_create_dumb *args);
+
+#endif /* __I915_GEM_CREATE_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 14fdb0796c52..13917231ae81 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -11,6 +11,7 @@
 
 #include <asm/smp.h>
 
+#include "gem/i915_gem_dmabuf.h"
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.h b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.h
new file mode 100644
index 000000000000..6e0405d47ce1
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __I915_GEM_DMABUF_H__
+#define __I915_GEM_DMABUF_H__
+
+struct drm_gem_object;
+struct drm_device;
+struct dma_buf;
+
+struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
+					     struct dma_buf *dma_buf);
+
+struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags);
+
+#endif /* __I915_GEM_DMABUF_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 26532c07d467..3e5d6057b3ef 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -9,12 +9,13 @@
 
 #include "i915_drv.h"
 #include "i915_gem_clflush.h"
+#include "i915_gem_domain.h"
 #include "i915_gem_gtt.h"
 #include "i915_gem_ioctls.h"
-#include "i915_gem_object.h"
-#include "i915_vma.h"
 #include "i915_gem_lmem.h"
 #include "i915_gem_mman.h"
+#include "i915_gem_object.h"
+#include "i915_vma.h"
 
 static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.h b/drivers/gpu/drm/i915/gem/i915_gem_domain.h
new file mode 100644
index 000000000000..9622df962bfc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __I915_GEM_DOMAIN_H__
+#define __I915_GEM_DOMAIN_H__
+
+struct drm_i915_gem_object;
+enum i915_cache_level;
+
+int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
+				    enum i915_cache_level cache_level);
+
+#endif /* __I915_GEM_DOMAIN_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 54cae821513b..0a4ecf71ee08 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,6 +25,7 @@
 
 #include "i915_cmd_parser.h"
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_evict.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index c5150a1ee3d2..c698f95af15f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -10,6 +10,7 @@
 
 #include "i915_drv.h"
 #include "i915_gem.h"
+#include "i915_gem_internal.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_utils.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.h b/drivers/gpu/drm/i915/gem/i915_gem_internal.h
new file mode 100644
index 000000000000..6664e06112fc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __I915_GEM_INTERNAL_H__
+#define __I915_GEM_INTERNAL_H__
+
+#include <linux/types.h>
+
+struct drm_i915_gem_object;
+struct drm_i915_gem_object_ops;
+struct drm_i915_private;
+
+struct drm_i915_gem_object *
+i915_gem_object_create_internal(struct drm_i915_private *i915,
+				phys_addr_t size);
+struct drm_i915_gem_object *
+__i915_gem_object_create_internal(struct drm_i915_private *i915,
+				  const struct drm_i915_gem_object_ops *ops,
+				  phys_addr_t size);
+
+#endif /* __I915_GEM_INTERNAL_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 1478c02a82cb..a3b60e1ede90 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -9,6 +9,8 @@
 #include <linux/pfn_t.h>
 #include <linux/sizes.h>
 
+#include <drm/drm_cache.h>
+
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index d87b508b59b1..9a478c19c477 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -24,11 +24,16 @@
 
 #include <linux/sched/mm.h>
 
+#include <drm/drm_cache.h>
+
 #include "display/intel_frontbuffer.h"
 #include "pxp/intel_pxp.h"
+
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
+#include "i915_gem_dmabuf.h"
 #include "i915_gem_mman.h"
 #include "i915_gem_object.h"
 #include "i915_gem_ttm.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index a50f884973bc..022582a1ca17 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -4,6 +4,8 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <drm/drm_cache.h>
+
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index ac56124760e1..e81e5ac8d376 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -10,6 +10,7 @@
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_gt_requests.h"
 
+#include "i915_driver.h"
 #include "i915_drv.h"
 
 #if defined(CONFIG_X86)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index cc9fe258fba7..60f962f0c041 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -5,8 +5,11 @@
  */
 
 #include <linux/pagevec.h>
+#include <linux/shmem_fs.h>
 #include <linux/swap.h>
 
+#include <drm/drm_cache.h>
+
 #include "gem/i915_gem_region.h"
 #include "i915_drv.h"
 #include "i915_gemfs.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 4dfed34191c6..0272b24c5c57 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -16,6 +16,7 @@
 #include "i915_gem_stolen.h"
 #include "i915_reg.h"
 #include "i915_vgpu.h"
+#include "intel_mchbar_regs.h"
 
 /*
  * The BIOS typically reserves some of the system's memory for the exclusive
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
index 75501db71041..af85d0c28168 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
@@ -9,6 +9,7 @@
 #include <drm/drm_file.h>
 
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 1f880c8c66e7..68f758ebbd4b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -3,6 +3,8 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include <linux/shmem_fs.h>
+
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 11f0aa65f8a3..6af237aa1854 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -8,9 +8,10 @@
 
 #include "i915_selftest.h"
 
-#include "gem/i915_gem_region.h"
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_pm.h"
+#include "gem/i915_gem_region.h"
 
 #include "gt/intel_gt.h"
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 7d327ffd0464..85bf9ba727d7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -6,6 +6,7 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_regs.h"
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index c6291429b00c..65e37d3cbb97 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -6,11 +6,13 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_region.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
-#include "gem/i915_gem_region.h"
+
 #include "huge_gem_object.h"
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
index b35c1219c852..3c55e77b0f1b 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
@@ -7,6 +7,7 @@
 #include "igt_gem_utils.h"
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_context.h"
 #include "gt/intel_gpu_commands.h"
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index c0a8ef368044..6d6082b5f31f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -4,6 +4,7 @@
  * Copyright © 2016 Intel Corporation
  */
 
+#include "i915_file_private.h"
 #include "mock_context.h"
 #include "selftests/mock_drm.h"
 #include "selftests/mock_gtt.h"
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index 8471758b3ef4..0bd0d611e0c8 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -5,6 +5,8 @@
 
 #include <linux/log2.h>
 
+#include "gem/i915_gem_internal.h"
+
 #include "gen6_ppgtt.h"
 #include "i915_scatterlist.h"
 #include "i915_trace.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_context_sseu.c b/drivers/gpu/drm/i915/gt/intel_context_sseu.c
index e86d8255feec..ece16c2b5b8e 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_context_sseu.c
@@ -9,6 +9,7 @@
 #include "intel_engine_pm.h"
 #include "intel_gpu_commands.h"
 #include "intel_lrc.h"
+#include "intel_lrc_reg.h"
 #include "intel_ring.h"
 #include "intel_sseu.h"
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 0e353d8c2bc8..be4b1e65442f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -182,6 +182,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_HWS_CSB_BUF0_INDEX		0x10
 #define I915_HWS_CSB_WRITE_INDEX	0x1f
 #define ICL_HWS_CSB_WRITE_INDEX		0x2f
+#define INTEL_HWS_CSB_WRITE_INDEX(__i915) \
+	(GRAPHICS_VER(__i915) >= 11 ? ICL_HWS_CSB_WRITE_INDEX : I915_HWS_CSB_WRITE_INDEX)
 
 void intel_engine_stop(struct intel_engine_cs *engine);
 void intel_engine_cleanup(struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 84ad09fb9b8b..959e9300ac9e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -6,6 +6,7 @@
 #include <drm/drm_print.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 #include "gt/intel_gt_regs.h"
 
 #include "i915_cmd_parser.h"
@@ -1229,17 +1230,6 @@ void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
 	ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
 }
 
-const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
-{
-	switch (type) {
-	case I915_CACHE_NONE: return " uncached";
-	case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
-	case I915_CACHE_L3_LLC: return " L3+LLC";
-	case I915_CACHE_WT: return " WT";
-	default: return "";
-	}
-}
-
 static u32
 read_subslice_reg(const struct intel_engine_cs *engine,
 		  int slice, int subslice, i915_reg_t reg)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index e9fec6214073..0bf8b45c9319 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -70,6 +70,12 @@
 #define RING_NOPID(base)			_MMIO((base) + 0x94)
 #define RING_HWSTAM(base)			_MMIO((base) + 0x98)
 #define RING_MI_MODE(base)			_MMIO((base) + 0x9c)
+#define   ASYNC_FLIP_PERF_DISABLE		REG_BIT(14)
+#define   MI_FLUSH_ENABLE			REG_BIT(12)
+#define   TGL_NESTED_BB_EN			REG_BIT(12)
+#define   MODE_IDLE				REG_BIT(9)
+#define   STOP_RING				REG_BIT(8)
+#define   VS_TIMER_DISPATCH			REG_BIT(6)
 #define RING_IMR(base)				_MMIO((base) + 0xa8)
 #define RING_EIR(base)				_MMIO((base) + 0xb0)
 #define RING_EMR(base)				_MMIO((base) + 0xb4)
@@ -211,8 +217,25 @@
 #define GEN8_RING_CS_GPR(base, n)		_MMIO((base) + 0x600 + (n) * 8)
 #define GEN8_RING_CS_GPR_UDW(base, n)		_MMIO((base) + 0x600 + (n) * 8 + 4)
 
+#define GEN11_VCS_SFC_FORCED_LOCK(base)		_MMIO((base) + 0x88c)
+#define   GEN11_VCS_SFC_FORCED_LOCK_BIT		(1 << 0)
+#define GEN11_VCS_SFC_LOCK_STATUS(base)		_MMIO((base) + 0x890)
+#define   GEN11_VCS_SFC_USAGE_BIT		(1 << 0)
+#define   GEN11_VCS_SFC_LOCK_ACK_BIT		(1 << 1)
+
+#define GEN11_VECS_SFC_FORCED_LOCK(base)	_MMIO((base) + 0x201c)
+#define   GEN11_VECS_SFC_FORCED_LOCK_BIT	(1 << 0)
+#define GEN11_VECS_SFC_LOCK_ACK(base)		_MMIO((base) + 0x2018)
+#define   GEN11_VECS_SFC_LOCK_ACK_BIT		(1 << 0)
+#define GEN11_VECS_SFC_USAGE(base)		_MMIO((base) + 0x2014)
+#define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
+
 #define RING_HWS_PGA_GEN6(base)	_MMIO((base) + 0x2080)
 
+#define GEN12_HCP_SFC_LOCK_STATUS(base)		_MMIO((base) + 0x2914)
+#define   GEN12_HCP_SFC_LOCK_ACK_BIT		REG_BIT(1)
+#define   GEN12_HCP_SFC_USAGE_BIT		REG_BIT(0)
+
 #define VDBOX_CGCTL3F10(base)			_MMIO((base) + 0x3f10)
 #define   IECPUNIT_CLKGATE_DIS			REG_BIT(22)
 
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 49e26d23ce1f..4a9ef688fac2 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3465,7 +3465,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 		(u64 *)&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
 
 	execlists->csb_write =
-		&engine->status_page.addr[intel_hws_csb_write_index(i915)];
+		&engine->status_page.addr[INTEL_HWS_CSB_WRITE_INDEX(i915)];
 
 	if (GRAPHICS_VER(i915) < 11)
 		execlists->csb_size = GEN8_CSB_ENTRIES;
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index 95c9145232f5..f294753bc947 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -9,6 +9,7 @@
 #include "i915_pvinfo.h"
 #include "i915_vgpu.h"
 #include "intel_gt_regs.h"
+#include "intel_mchbar_regs.h"
 
 /**
  * DOC: fence register handling
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 57763aede976..545a2b1f1834 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -5,15 +5,17 @@
 
 #include <drm/intel-gtt.h>
 
-#include "intel_gt_debugfs.h"
-
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_lmem.h"
+#include "pxp/intel_pxp.h"
+
 #include "i915_drv.h"
 #include "intel_context.h"
 #include "intel_engine_regs.h"
 #include "intel_gt.h"
 #include "intel_gt_buffer_pool.h"
 #include "intel_gt_clock_utils.h"
+#include "intel_gt_debugfs.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_regs.h"
 #include "intel_gt_requests.h"
@@ -25,7 +27,6 @@
 #include "intel_rps.h"
 #include "intel_uncore.h"
 #include "shmem_utils.h"
-#include "pxp/intel_pxp.h"
 
 void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
index 9db3dcbd917f..cadfd85785b1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c
@@ -3,6 +3,7 @@
  * Copyright © 2014-2018 Intel Corporation
  */
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_object.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
index 4e448c13a64c..37765919fe32 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
@@ -15,6 +15,7 @@
 #include "intel_gt_pm_debugfs.h"
 #include "intel_gt_regs.h"
 #include "intel_llc.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 #include "intel_rc6.h"
 #include "intel_rps.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 16d98ebee687..e8143fa4b5a8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -8,779 +8,166 @@
 
 #include "i915_reg_defs.h"
 
-#define ILK_GDSR _MMIO(MCHBAR_MIRROR_BASE + 0x2ca4)
-#define  ILK_GRDOM_FULL		(0 << 1)
-#define  ILK_GRDOM_RENDER	(1 << 1)
-#define  ILK_GRDOM_MEDIA	(3 << 1)
-#define  ILK_GRDOM_MASK		(3 << 1)
-#define  ILK_GRDOM_RESET_ENABLE (1 << 0)
-
-#define GEN6_MBCUNIT_SNPCR	_MMIO(0x900c) /* for LLC config */
-#define   GEN6_MBC_SNPCR_SHIFT	21
-#define   GEN6_MBC_SNPCR_MASK	(3 << 21)
-#define   GEN6_MBC_SNPCR_MAX	(0 << 21)
-#define   GEN6_MBC_SNPCR_MED	(1 << 21)
-#define   GEN6_MBC_SNPCR_LOW	(2 << 21)
-#define   GEN6_MBC_SNPCR_MIN	(3 << 21) /* only 1/16th of the cache is shared */
-
-#define VLV_G3DCTL		_MMIO(0x9024)
-#define VLV_GSCKGCTL		_MMIO(0x9028)
-
-#define FBC_LLC_READ_CTRL	_MMIO(0x9044)
-#define   FBC_LLC_FULLY_OPEN	REG_BIT(30)
-
-#define GEN6_MBCTL		_MMIO(0x0907c)
-#define   GEN6_MBCTL_ENABLE_BOOT_FETCH	(1 << 4)
-#define   GEN6_MBCTL_CTX_FETCH_NEEDED	(1 << 3)
-#define   GEN6_MBCTL_BME_UPDATE_ENABLE	(1 << 2)
-#define   GEN6_MBCTL_MAE_UPDATE_ENABLE	(1 << 1)
-#define   GEN6_MBCTL_BOOT_FETCH_MECH	(1 << 0)
-
-#define GEN6_GDRST	_MMIO(0x941c)
-#define  GEN6_GRDOM_FULL		(1 << 0)
-#define  GEN6_GRDOM_RENDER		(1 << 1)
-#define  GEN6_GRDOM_MEDIA		(1 << 2)
-#define  GEN6_GRDOM_BLT			(1 << 3)
-#define  GEN6_GRDOM_VECS		(1 << 4)
-#define  GEN9_GRDOM_GUC			(1 << 5)
-#define  GEN8_GRDOM_MEDIA2		(1 << 7)
-/* GEN11 changed all bit defs except for FULL & RENDER */
-#define  GEN11_GRDOM_FULL		GEN6_GRDOM_FULL
-#define  GEN11_GRDOM_RENDER		GEN6_GRDOM_RENDER
-#define  GEN11_GRDOM_BLT		(1 << 2)
-#define  GEN11_GRDOM_GUC		(1 << 3)
-#define  GEN11_GRDOM_MEDIA		(1 << 5)
-#define  GEN11_GRDOM_MEDIA2		(1 << 6)
-#define  GEN11_GRDOM_MEDIA3		(1 << 7)
-#define  GEN11_GRDOM_MEDIA4		(1 << 8)
-#define  GEN11_GRDOM_MEDIA5		(1 << 9)
-#define  GEN11_GRDOM_MEDIA6		(1 << 10)
-#define  GEN11_GRDOM_MEDIA7		(1 << 11)
-#define  GEN11_GRDOM_MEDIA8		(1 << 12)
-#define  GEN11_GRDOM_VECS		(1 << 13)
-#define  GEN11_GRDOM_VECS2		(1 << 14)
-#define  GEN11_GRDOM_VECS3		(1 << 15)
-#define  GEN11_GRDOM_VECS4		(1 << 16)
-#define  GEN11_GRDOM_SFC0		(1 << 17)
-#define  GEN11_GRDOM_SFC1		(1 << 18)
-#define  GEN11_GRDOM_SFC2		(1 << 19)
-#define  GEN11_GRDOM_SFC3		(1 << 20)
-#define  GEN11_VCS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << ((instance) >> 1))
-#define  GEN11_VECS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << (instance))
-
-#define GEN11_VCS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x88C)
-#define   GEN11_VCS_SFC_FORCED_LOCK_BIT		(1 << 0)
-#define GEN11_VCS_SFC_LOCK_STATUS(engine)	_MMIO((engine)->mmio_base + 0x890)
-#define   GEN11_VCS_SFC_USAGE_BIT		(1 << 0)
-#define   GEN11_VCS_SFC_LOCK_ACK_BIT		(1 << 1)
-
-#define GEN11_VECS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x201C)
-#define   GEN11_VECS_SFC_FORCED_LOCK_BIT	(1 << 0)
-#define GEN11_VECS_SFC_LOCK_ACK(engine)		_MMIO((engine)->mmio_base + 0x2018)
-#define   GEN11_VECS_SFC_LOCK_ACK_BIT		(1 << 0)
-#define GEN11_VECS_SFC_USAGE(engine)		_MMIO((engine)->mmio_base + 0x2014)
-#define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
-
-#define GEN12_HCP_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x2910)
-#define   GEN12_HCP_SFC_FORCED_LOCK_BIT		REG_BIT(0)
-#define GEN12_HCP_SFC_LOCK_STATUS(engine)	_MMIO((engine)->mmio_base + 0x2914)
-#define   GEN12_HCP_SFC_LOCK_ACK_BIT		REG_BIT(1)
-#define   GEN12_HCP_SFC_USAGE_BIT			REG_BIT(0)
-
-#define GEN12_SFC_DONE(n)		_MMIO(0x1cc000 + (n) * 0x1000)
-
-#define WAIT_FOR_RC6_EXIT		_MMIO(0x20CC)
-/* HSW only */
-#define   HSW_SELECTIVE_READ_ADDRESSING_SHIFT		2
-#define   HSW_SELECTIVE_READ_ADDRESSING_MASK		(0x3 << HSW_SLECTIVE_READ_ADDRESSING_SHIFT)
-#define   HSW_SELECTIVE_WRITE_ADDRESS_SHIFT		4
-#define   HSW_SELECTIVE_WRITE_ADDRESS_MASK		(0x7 << HSW_SELECTIVE_WRITE_ADDRESS_SHIFT)
-/* HSW+ */
-#define   HSW_WAIT_FOR_RC6_EXIT_ENABLE			(1 << 0)
-#define   HSW_RCS_CONTEXT_ENABLE			(1 << 7)
-#define   HSW_RCS_INHIBIT				(1 << 8)
-/* Gen8 */
-#define   GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT		4
-#define   GEN8_SELECTIVE_WRITE_ADDRESS_MASK		(0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT)
-#define   GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT		4
-#define   GEN8_SELECTIVE_WRITE_ADDRESS_MASK		(0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT)
-#define   GEN8_SELECTIVE_WRITE_ADDRESSING_ENABLE	(1 << 6)
-#define   GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT	9
-#define   GEN8_SELECTIVE_READ_SUBSLICE_SELECT_MASK	(0x3 << GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT)
-#define   GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT	11
-#define   GEN8_SELECTIVE_READ_SLICE_SELECT_MASK		(0x3 << GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT)
-#define   GEN8_SELECTIVE_READ_ADDRESSING_ENABLE         (1 << 13)
-
-#define GAM_ECOCHK			_MMIO(0x4090)
-#define   BDW_DISABLE_HDC_INVALIDATION	(1 << 25)
-#define   ECOCHK_SNB_BIT		(1 << 10)
-#define   ECOCHK_DIS_TLB		(1 << 8)
-#define   HSW_ECOCHK_ARB_PRIO_SOL	(1 << 6)
-#define   ECOCHK_PPGTT_CACHE64B		(0x3 << 3)
-#define   ECOCHK_PPGTT_CACHE4B		(0x0 << 3)
-#define   ECOCHK_PPGTT_GFDT_IVB		(0x1 << 4)
-#define   ECOCHK_PPGTT_LLC_IVB		(0x1 << 3)
-#define   ECOCHK_PPGTT_UC_HSW		(0x1 << 3)
-#define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
-#define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
-
-#define GEN8_RC6_CTX_INFO		_MMIO(0x8504)
-
-#define GAC_ECO_BITS			_MMIO(0x14090)
-#define   ECOBITS_SNB_BIT		(1 << 13)
-#define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
-#define   ECOBITS_PPGTT_CACHE4B		(0 << 8)
-
-#define GEN12_GAMCNTRL_CTRL			_MMIO(0xcf54)
-#define   INVALIDATION_BROADCAST_MODE_DIS	REG_BIT(12)
-#define   GLOBAL_INVALIDATION_MODE		REG_BIT(2)
-
-#define GEN12_GAMSTLB_CTRL		_MMIO(0xcf4c)
-#define   CONTROL_BLOCK_CLKGATE_DIS	REG_BIT(12)
-#define   EGRESS_BLOCK_CLKGATE_DIS	REG_BIT(11)
-#define   TAG_BLOCK_CLKGATE_DIS		REG_BIT(7)
-
-#define GEN12_MERT_MOD_CTRL		_MMIO(0xcf28)
-#define RENDER_MOD_CTRL			_MMIO(0xcf2c)
-#define COMP_MOD_CTRL			_MMIO(0xcf30)
-#define VDBX_MOD_CTRL			_MMIO(0xcf34)
-#define VEBX_MOD_CTRL			_MMIO(0xcf38)
-#define   FORCE_MISS_FTLB		REG_BIT(3)
-
-#define GAB_CTL				_MMIO(0x24000)
-#define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1 << 8)
-
-#define HSW_MI_PREDICATE_RESULT_2	_MMIO(0x2214)
-
-/*
- * Registers used only by the command parser
- */
-#define BCS_SWCTRL _MMIO(0x22200)
-#define   BCS_SRC_Y REG_BIT(0)
-#define   BCS_DST_Y REG_BIT(1)
-
-#define GPGPU_THREADS_DISPATCHED        _MMIO(0x2290)
-#define GPGPU_THREADS_DISPATCHED_UDW	_MMIO(0x2290 + 4)
-#define HS_INVOCATION_COUNT             _MMIO(0x2300)
-#define HS_INVOCATION_COUNT_UDW		_MMIO(0x2300 + 4)
-#define DS_INVOCATION_COUNT             _MMIO(0x2308)
-#define DS_INVOCATION_COUNT_UDW		_MMIO(0x2308 + 4)
-#define IA_VERTICES_COUNT               _MMIO(0x2310)
-#define IA_VERTICES_COUNT_UDW		_MMIO(0x2310 + 4)
-#define IA_PRIMITIVES_COUNT             _MMIO(0x2318)
-#define IA_PRIMITIVES_COUNT_UDW		_MMIO(0x2318 + 4)
-#define VS_INVOCATION_COUNT             _MMIO(0x2320)
-#define VS_INVOCATION_COUNT_UDW		_MMIO(0x2320 + 4)
-#define GS_INVOCATION_COUNT             _MMIO(0x2328)
-#define GS_INVOCATION_COUNT_UDW		_MMIO(0x2328 + 4)
-#define GS_PRIMITIVES_COUNT             _MMIO(0x2330)
-#define GS_PRIMITIVES_COUNT_UDW		_MMIO(0x2330 + 4)
-#define CL_INVOCATION_COUNT             _MMIO(0x2338)
-#define CL_INVOCATION_COUNT_UDW		_MMIO(0x2338 + 4)
-#define CL_PRIMITIVES_COUNT             _MMIO(0x2340)
-#define CL_PRIMITIVES_COUNT_UDW		_MMIO(0x2340 + 4)
-#define PS_INVOCATION_COUNT             _MMIO(0x2348)
-#define PS_INVOCATION_COUNT_UDW		_MMIO(0x2348 + 4)
-#define PS_DEPTH_COUNT                  _MMIO(0x2350)
-#define PS_DEPTH_COUNT_UDW		_MMIO(0x2350 + 4)
-
-/* There are the 4 64-bit counter registers, one for each stream output */
-#define GEN7_SO_NUM_PRIMS_WRITTEN(n)		_MMIO(0x5200 + (n) * 8)
-#define GEN7_SO_NUM_PRIMS_WRITTEN_UDW(n)	_MMIO(0x5200 + (n) * 8 + 4)
-
-#define GEN7_SO_PRIM_STORAGE_NEEDED(n)		_MMIO(0x5240 + (n) * 8)
-#define GEN7_SO_PRIM_STORAGE_NEEDED_UDW(n)	_MMIO(0x5240 + (n) * 8 + 4)
-
-#define GEN7_3DPRIM_END_OFFSET          _MMIO(0x2420)
-#define GEN7_3DPRIM_START_VERTEX        _MMIO(0x2430)
-#define GEN7_3DPRIM_VERTEX_COUNT        _MMIO(0x2434)
-#define GEN7_3DPRIM_INSTANCE_COUNT      _MMIO(0x2438)
-#define GEN7_3DPRIM_START_INSTANCE      _MMIO(0x243C)
-#define GEN7_3DPRIM_BASE_VERTEX         _MMIO(0x2440)
-
-#define GEN7_GPGPU_DISPATCHDIMX         _MMIO(0x2500)
-#define GEN7_GPGPU_DISPATCHDIMY         _MMIO(0x2504)
-#define GEN7_GPGPU_DISPATCHDIMZ         _MMIO(0x2508)
-
-#define GEN12_SQCM		_MMIO(0x8724)
-#define   EN_32B_ACCESS		REG_BIT(30)
-
-/*
- * Flexible, Aggregate EU Counter Registers.
- * Note: these aren't contiguous
- */
-#define EU_PERF_CNTL0	    _MMIO(0xe458)
-#define EU_PERF_CNTL1	    _MMIO(0xe558)
-#define EU_PERF_CNTL2	    _MMIO(0xe658)
-#define EU_PERF_CNTL3	    _MMIO(0xe758)
-#define EU_PERF_CNTL4	    _MMIO(0xe45c)
-#define EU_PERF_CNTL5	    _MMIO(0xe55c)
-#define EU_PERF_CNTL6	    _MMIO(0xe65c)
-
-#define RT_CTRL			_MMIO(0xe530)
-#define  DIS_NULL_QUERY		REG_BIT(10)
-
 /* RPM unit config (Gen8+) */
-#define RPM_CONFIG0	    _MMIO(0x0D00)
-#define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
-#define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(1 << GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
-#define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	0
-#define  GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	1
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(0x7 << GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	0
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	1
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ	2
-#define  GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ	3
-#define  GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT	1
-#define  GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK	(0x3 << GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT)
-
-#define RPM_CONFIG1	    _MMIO(0x0D04)
-#define  GEN10_GT_NOA_ENABLE  (1 << 9)
-
-/* GPM unit config (Gen9+) */
-#define CTC_MODE			_MMIO(0xA26C)
-#define  CTC_SOURCE_PARAMETER_MASK 1
-#define  CTC_SOURCE_CRYSTAL_CLOCK	0
-#define  CTC_SOURCE_DIVIDE_LOGIC	1
-#define  CTC_SHIFT_PARAMETER_SHIFT	1
-#define  CTC_SHIFT_PARAMETER_MASK	(0x3 << CTC_SHIFT_PARAMETER_SHIFT)
+#define RPM_CONFIG0				_MMIO(0xd00)
+#define   GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
+#define   GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(1 << GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
+#define   GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	0
+#define   GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	1
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT	3
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK	(0x7 << GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT)
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ	0
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ	1
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ	2
+#define   GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ	3
+#define   GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT	1
+#define   GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK	(0x3 << GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT)
+
+#define RPM_CONFIG1				_MMIO(0xd04)
+#define   GEN10_GT_NOA_ENABLE			(1 << 9)
 
 /* RCP unit config (Gen8+) */
-#define RCP_CONFIG	    _MMIO(0x0D08)
-
-#define MICRO_BP0_0	    _MMIO(0x9800)
-#define MICRO_BP0_2	    _MMIO(0x9804)
-#define MICRO_BP0_1	    _MMIO(0x9808)
-
-#define MICRO_BP1_0	    _MMIO(0x980C)
-#define MICRO_BP1_2	    _MMIO(0x9810)
-#define MICRO_BP1_1	    _MMIO(0x9814)
-
-#define MICRO_BP2_0	    _MMIO(0x9818)
-#define MICRO_BP2_2	    _MMIO(0x981C)
-#define MICRO_BP2_1	    _MMIO(0x9820)
-
-#define MICRO_BP3_0	    _MMIO(0x9824)
-#define MICRO_BP3_2	    _MMIO(0x9828)
-#define MICRO_BP3_1	    _MMIO(0x982C)
-
-#define MICRO_BP_TRIGGER		_MMIO(0x9830)
-#define MICRO_BP3_COUNT_STATUS01	_MMIO(0x9834)
-#define MICRO_BP3_COUNT_STATUS23	_MMIO(0x9838)
-#define MICRO_BP_FIRED_ARMED		_MMIO(0x983C)
-
-#define GAMTARBMODE		_MMIO(0x04a08)
-#define   ARB_MODE_BWGTLB_DISABLE (1 << 9)
-#define   ARB_MODE_SWIZZLE_BDW	(1 << 1)
-#define RENDER_HWS_PGA_GEN7	_MMIO(0x04080)
-
-#define _RING_FAULT_REG_RCS        0x4094
-#define _RING_FAULT_REG_VCS        0x4194
-#define _RING_FAULT_REG_BCS        0x4294
-#define _RING_FAULT_REG_VECS       0x4394
-#define RING_FAULT_REG(engine)     _MMIO(_PICK((engine)->class, \
-					       _RING_FAULT_REG_RCS, \
-					       _RING_FAULT_REG_VCS, \
-					       _RING_FAULT_REG_VECS, \
-					       _RING_FAULT_REG_BCS))
-#define GEN8_RING_FAULT_REG	_MMIO(0x4094)
-#define GEN12_RING_FAULT_REG	_MMIO(0xcec4)
-#define   GEN8_RING_FAULT_ENGINE_ID(x)	(((x) >> 12) & 0x7)
-#define   RING_FAULT_GTTSEL_MASK (1 << 11)
-#define   RING_FAULT_SRCID(x)	(((x) >> 3) & 0xff)
-#define   RING_FAULT_FAULT_TYPE(x) (((x) >> 1) & 0x3)
-#define   RING_FAULT_VALID	(1 << 0)
-#define DONE_REG		_MMIO(0x40b0)
-#define GEN12_GAM_DONE		_MMIO(0xcf68)
-#define GEN8_PRIVATE_PAT_LO	_MMIO(0x40e0)
-#define GEN8_PRIVATE_PAT_HI	_MMIO(0x40e0 + 4)
-#define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
-#define GEN12_PAT_INDEX(index)	_MMIO(0x4800 + (index) * 4)
-#define BSD_HWS_PGA_GEN7	_MMIO(0x04180)
-#define GEN12_GFX_CCS_AUX_NV	_MMIO(0x4208)
-#define GEN12_VD0_AUX_NV	_MMIO(0x4218)
-#define GEN12_VD1_AUX_NV	_MMIO(0x4228)
-#define GEN12_VD2_AUX_NV	_MMIO(0x4298)
-#define GEN12_VD3_AUX_NV	_MMIO(0x42A8)
-#define GEN12_VE0_AUX_NV	_MMIO(0x4238)
-#define GEN12_VE1_AUX_NV	_MMIO(0x42B8)
-#define   AUX_INV		REG_BIT(0)
-#define BLT_HWS_PGA_GEN7	_MMIO(0x04280)
-#define VEBOX_HWS_PGA_GEN7	_MMIO(0x04380)
-
-#define MISC_STATUS0		_MMIO(0xA500)
-#define MISC_STATUS1		_MMIO(0xA504)
-
-#define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
-
-#define GEN9_GAMT_ECO_REG_RW_IA _MMIO(0x4ab0)
-#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1 << 18)
-
-#define GEN8_GAMW_ECO_DEV_RW_IA _MMIO(0x4080)
-#define   GAMW_ECO_ENABLE_64K_IPS_FIELD 0xF
-#define   GAMW_ECO_DEV_CTX_RELOAD_DISABLE	(1 << 7)
-
-#define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
-#define   GAMT_CHKN_DISABLE_L3_COH_PIPE			(1 << 31)
-#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1 << 28)
-#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1 << 24)
+#define RCP_CONFIG				_MMIO(0xd08)
+
+#define RC6_LOCATION				_MMIO(0xd40)
+#define   RC6_CTX_IN_DRAM			(1 << 0)
+#define RC6_CTX_BASE				_MMIO(0xd48)
+#define   RC6_CTX_BASE_MASK			0xFFFFFFF0
+
+#define FORCEWAKE_ACK_MEDIA_VDBOX_GEN11(n)	_MMIO(0xd50 + (n) * 4)
+#define FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(n)	_MMIO(0xd70 + (n) * 4)
+#define FORCEWAKE_ACK_RENDER_GEN9		_MMIO(0xd84)
+#define FORCEWAKE_ACK_MEDIA_GEN9		_MMIO(0xd88)
+
+#define MCFG_MCR_SELECTOR			_MMIO(0xfd0)
+#define SF_MCR_SELECTOR				_MMIO(0xfd8)
+#define GEN8_MCR_SELECTOR			_MMIO(0xfdc)
+#define   GEN8_MCR_SLICE(slice)			(((slice) & 3) << 26)
+#define   GEN8_MCR_SLICE_MASK			GEN8_MCR_SLICE(3)
+#define   GEN8_MCR_SUBSLICE(subslice)		(((subslice) & 3) << 24)
+#define   GEN8_MCR_SUBSLICE_MASK		GEN8_MCR_SUBSLICE(3)
+#define   GEN11_MCR_SLICE(slice)		(((slice) & 0xf) << 27)
+#define   GEN11_MCR_SLICE_MASK			GEN11_MCR_SLICE(0xf)
+#define   GEN11_MCR_SUBSLICE(subslice)		(((subslice) & 0x7) << 24)
+#define   GEN11_MCR_SUBSLICE_MASK		GEN11_MCR_SUBSLICE(0x7)
+
+#define IPEIR_I965				_MMIO(0x2064)
+#define IPEHR_I965				_MMIO(0x2068)
 
-#define GEN8_RTCR	_MMIO(0x4260)
-#define GEN8_M1TCR	_MMIO(0x4264)
-#define GEN8_M2TCR	_MMIO(0x4268)
-#define GEN8_BTCR	_MMIO(0x426c)
-#define GEN8_VTCR	_MMIO(0x4270)
-
-#define IPEIR_I965	_MMIO(0x2064)
-#define IPEHR_I965	_MMIO(0x2068)
-#define GEN7_SC_INSTDONE	_MMIO(0x7100)
-#define GEN12_SC_INSTDONE_EXTRA		_MMIO(0x7104)
-#define GEN12_SC_INSTDONE_EXTRA2	_MMIO(0x7108)
-#define GEN7_SAMPLER_INSTDONE	_MMIO(0xe160)
-#define GEN7_ROW_INSTDONE	_MMIO(0xe164)
-#define XEHPG_INSTDONE_GEOM_SVG		_MMIO(0x666c)
-#define MCFG_MCR_SELECTOR		_MMIO(0xfd0)
-#define SF_MCR_SELECTOR			_MMIO(0xfd8)
-#define GEN8_MCR_SELECTOR		_MMIO(0xfdc)
-#define   GEN8_MCR_SLICE(slice)		(((slice) & 3) << 26)
-#define   GEN8_MCR_SLICE_MASK		GEN8_MCR_SLICE(3)
-#define   GEN8_MCR_SUBSLICE(subslice)	(((subslice) & 3) << 24)
-#define   GEN8_MCR_SUBSLICE_MASK	GEN8_MCR_SUBSLICE(3)
-#define   GEN11_MCR_SLICE(slice)	(((slice) & 0xf) << 27)
-#define   GEN11_MCR_SLICE_MASK		GEN11_MCR_SLICE(0xf)
-#define   GEN11_MCR_SUBSLICE(subslice)	(((subslice) & 0x7) << 24)
-#define   GEN11_MCR_SUBSLICE_MASK	GEN11_MCR_SUBSLICE(0x7)
 /*
  * On GEN4, only the render ring INSTDONE exists and has a different
  * layout than the GEN7+ version.
  * The GEN2 counterpart of this register is GEN2_INSTDONE.
  */
-#define INSTPS		_MMIO(0x2070) /* 965+ only */
-#define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
-#define ACTHD_I965	_MMIO(0x2074)
-#define HWS_PGA		_MMIO(0x2080)
-#define HWS_ADDRESS_MASK	0xfffff000
-#define HWS_START_ADDRESS_SHIFT	4
-#define PWRCTXA		_MMIO(0x2088) /* 965GM+ only */
-#define   PWRCTX_EN	(1 << 0)
-#define GEN2_INSTDONE	_MMIO(0x2090)
-#define NOPID		_MMIO(0x2094)
-#define HWSTAM		_MMIO(0x2098)
-
-#define VDBOX_CGCTL3F18(base)		_MMIO((base) + 0x3f18)
-#define   ALNUNIT_CLKGATE_DIS		REG_BIT(13)
-
-#define ERROR_GEN6	_MMIO(0x40a0)
-
-#define GEN8_FAULT_TLB_DATA0		_MMIO(0x4b10)
-#define GEN8_FAULT_TLB_DATA1		_MMIO(0x4b14)
-#define GEN12_FAULT_TLB_DATA0		_MMIO(0xceb8)
-#define GEN12_FAULT_TLB_DATA1		_MMIO(0xcebc)
-#define   FAULT_VA_HIGH_BITS		(0xf << 0)
-#define   FAULT_GTT_SEL			(1 << 4)
-
-#define GEN12_GFX_TLB_INV_CR	_MMIO(0xced8)
-#define GEN12_VD_TLB_INV_CR	_MMIO(0xcedc)
-#define GEN12_VE_TLB_INV_CR	_MMIO(0xcee0)
-#define GEN12_BLT_TLB_INV_CR	_MMIO(0xcee4)
-
-#define GEN12_AUX_ERR_DBG		_MMIO(0x43f4)
+#define INSTPS					_MMIO(0x2070) /* 965+ only */
+#define GEN4_INSTDONE1				_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
+#define ACTHD_I965				_MMIO(0x2074)
+#define HWS_PGA					_MMIO(0x2080)
+#define   HWS_ADDRESS_MASK			0xfffff000
+#define   HWS_START_ADDRESS_SHIFT		4
+
+#define _3D_CHICKEN				_MMIO(0x2084)
+#define   _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB	(1 << 10)
+
+#define PWRCTXA					_MMIO(0x2088) /* 965GM+ only */
+#define   PWRCTX_EN				(1 << 0)
+
+#define FF_SLICE_CHICKEN			_MMIO(0x2088)
+#define   FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX	(1 << 1)
 
 /* GM45+ chicken bits -- debug workaround bits that may be required
  * for various sorts of correct behavior.  The top 16 bits of each are
  * the enables for writing to the corresponding low bit.
  */
-#define _3D_CHICKEN	_MMIO(0x2084)
-#define  _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB	(1 << 10)
-#define _3D_CHICKEN2	_MMIO(0x208c)
-
-#define FF_SLICE_CHICKEN	_MMIO(0x2088)
-#define  FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX	(1 << 1)
-
+#define _3D_CHICKEN2				_MMIO(0x208c)
 /* Disables pipelining of read flushes past the SF-WIZ interface.
  * Required on all Ironlake steppings according to the B-Spec, but the
  * particular danger of not doing so is not specified.
  */
-# define _3D_CHICKEN2_WM_READ_PIPELINED			(1 << 14)
-#define _3D_CHICKEN3	_MMIO(0x2090)
-#define  _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX		(1 << 12)
-#define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
-#define  _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
-#define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
-#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x) << 1) /* gen8+ */
-#define  _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH	(1 << 1) /* gen6 */
-
-#define MI_MODE		_MMIO(0x209c)
-# define VS_TIMER_DISPATCH				(1 << 6)
-# define MI_FLUSH_ENABLE				(1 << 12)
-# define TGL_NESTED_BB_EN				(1 << 12)
-# define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
-# define MODE_IDLE					(1 << 9)
-# define STOP_RING					(1 << 8)
-
-#define GEN6_GT_MODE	_MMIO(0x20d0)
-#define GEN7_GT_MODE	_MMIO(0x7008)
-#define   GEN6_WIZ_HASHING(hi, lo)			(((hi) << 9) | ((lo) << 7))
-#define   GEN6_WIZ_HASHING_8x8				GEN6_WIZ_HASHING(0, 0)
-#define   GEN6_WIZ_HASHING_8x4				GEN6_WIZ_HASHING(0, 1)
-#define   GEN6_WIZ_HASHING_16x4				GEN6_WIZ_HASHING(1, 0)
-#define   GEN6_WIZ_HASHING_MASK				GEN6_WIZ_HASHING(1, 1)
-#define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE		(1 << 5)
-#define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << ((slice) * 2))
-#define   GEN9_IZ_HASHING(slice, val)			((val) << ((slice) * 2))
+#define   _3D_CHICKEN2_WM_READ_PIPELINED	(1 << 14)
+
+#define _3D_CHICKEN3				_MMIO(0x2090)
+#define   _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX	(1 << 12)
+#define   _3D_CHICKEN_SF_DISABLE_OBJEND_CULL	(1 << 10)
+#define   _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
+#define   _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL	(1 << 5)
+#define   _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x) << 1) /* gen8+ */
+#define   _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH	(1 << 1) /* gen6 */
+
+#define GEN2_INSTDONE				_MMIO(0x2090)
+#define NOPID					_MMIO(0x2094)
+#define HWSTAM					_MMIO(0x2098)
+
+#define WAIT_FOR_RC6_EXIT			_MMIO(0x20cc)
+/* HSW only */
+#define   HSW_SELECTIVE_READ_ADDRESSING_SHIFT	2
+#define   HSW_SELECTIVE_READ_ADDRESSING_MASK	(0x3 << HSW_SLECTIVE_READ_ADDRESSING_SHIFT)
+#define   HSW_SELECTIVE_WRITE_ADDRESS_SHIFT	4
+#define   HSW_SELECTIVE_WRITE_ADDRESS_MASK	(0x7 << HSW_SELECTIVE_WRITE_ADDRESS_SHIFT)
+/* HSW+ */
+#define   HSW_WAIT_FOR_RC6_EXIT_ENABLE		(1 << 0)
+#define   HSW_RCS_CONTEXT_ENABLE		(1 << 7)
+#define   HSW_RCS_INHIBIT			(1 << 8)
+/* Gen8 */
+#define   GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT	4
+#define   GEN8_SELECTIVE_WRITE_ADDRESS_MASK	(0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT)
+#define   GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT	4
+#define   GEN8_SELECTIVE_WRITE_ADDRESS_MASK	(0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT)
+#define   GEN8_SELECTIVE_WRITE_ADDRESSING_ENABLE	(1 << 6)
+#define   GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT	9
+#define   GEN8_SELECTIVE_READ_SUBSLICE_SELECT_MASK	(0x3 << GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT)
+#define   GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT	11
+#define   GEN8_SELECTIVE_READ_SLICE_SELECT_MASK	(0x3 << GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT)
+#define   GEN8_SELECTIVE_READ_ADDRESSING_ENABLE	(1 << 13)
+
+#define GEN6_GT_MODE				_MMIO(0x20d0)
+#define   GEN6_WIZ_HASHING(hi, lo)		(((hi) << 9) | ((lo) << 7))
+#define   GEN6_WIZ_HASHING_8x8			GEN6_WIZ_HASHING(0, 0)
+#define   GEN6_WIZ_HASHING_8x4			GEN6_WIZ_HASHING(0, 1)
+#define   GEN6_WIZ_HASHING_16x4			GEN6_WIZ_HASHING(1, 0)
+#define   GEN6_WIZ_HASHING_MASK			GEN6_WIZ_HASHING(1, 1)
+#define   GEN6_TD_FOUR_ROW_DISPATCH_DISABLE	(1 << 5)
 
 /* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */
-#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4)
-#define   GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2)
-#define   GEN11_ENABLE_32_PLANE_MODE (1 << 7)
+#define GEN9_CSFE_CHICKEN1_RCS			_MMIO(0x20d4)
+#define   GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE	(1 << 2)
+#define   GEN11_ENABLE_32_PLANE_MODE		(1 << 7)
 
-#define SCCGCTL94DC		_MMIO(0x94dc)
-#define   CG3DDISURB		REG_BIT(14)
+#define GEN7_FF_SLICE_CS_CHICKEN1		_MMIO(0x20e0)
+#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL		(1 << 14)
 
-#define MLTICTXCTL		_MMIO(0xb170)
-#define   TDONRENDER		REG_BIT(2)
+#define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
+#define   GEN9_TSG_BARRIER_ACK_DISABLE		(1 << 8)
+#define   GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE	(1 << 10)
 
-#define L3SQCREG1_CCS0		_MMIO(0xb200)
-#define   FLUSHALLNONCOH	REG_BIT(5)
+#define GEN9_CS_DEBUG_MODE1			_MMIO(0x20ec)
+#define   FF_DOP_CLOCK_GATE_DISABLE		REG_BIT(1)
+#define GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON	_MMIO(0x20ec)
+#define   GEN12_REPLAY_MODE_GRANULARITY		REG_BIT(0)
 
 /* WaClearTdlStateAckDirtyBits */
-#define GEN8_STATE_ACK		_MMIO(0x20F0)
-#define GEN9_STATE_ACK_SLICE1	_MMIO(0x20F8)
-#define GEN9_STATE_ACK_SLICE2	_MMIO(0x2100)
-#define   GEN9_STATE_ACK_TDL0 (1 << 12)
-#define   GEN9_STATE_ACK_TDL1 (1 << 13)
-#define   GEN9_STATE_ACK_TDL2 (1 << 14)
-#define   GEN9_STATE_ACK_TDL3 (1 << 15)
-#define   GEN9_SUBSLICE_TDL_ACK_BITS \
+#define GEN8_STATE_ACK				_MMIO(0x20f0)
+#define GEN9_STATE_ACK_SLICE1			_MMIO(0x20f8)
+#define GEN9_STATE_ACK_SLICE2			_MMIO(0x2100)
+#define   GEN9_STATE_ACK_TDL0			(1 << 12)
+#define   GEN9_STATE_ACK_TDL1			(1 << 13)
+#define   GEN9_STATE_ACK_TDL2			(1 << 14)
+#define   GEN9_STATE_ACK_TDL3			(1 << 15)
+#define   GEN9_SUBSLICE_TDL_ACK_BITS	\
 	(GEN9_STATE_ACK_TDL3 | GEN9_STATE_ACK_TDL2 | \
 	 GEN9_STATE_ACK_TDL1 | GEN9_STATE_ACK_TDL0)
 
-#define GFX_MODE	_MMIO(0x2520)
-
-#define CACHE_MODE_0	_MMIO(0x2120) /* 915+ only */
-#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1 << 8)
-#define   CM0_IZ_OPT_DISABLE      (1 << 6)
-#define   CM0_ZR_OPT_DISABLE      (1 << 5)
-#define	  CM0_STC_EVICT_DISABLE_LRA_SNB	(1 << 5)
-#define   CM0_DEPTH_EVICT_DISABLE (1 << 4)
-#define   CM0_COLOR_EVICT_DISABLE (1 << 3)
-#define   CM0_DEPTH_WRITE_DISABLE (1 << 1)
-#define   CM0_RC_OP_FLUSH_DISABLE (1 << 0)
-#define GFX_FLSH_CNTL	_MMIO(0x2170) /* 915+ only */
-#define GFX_FLSH_CNTL_GEN6	_MMIO(0x101008)
-#define   GFX_FLSH_CNTL_EN	(1 << 0)
-
-#define CACHE_MODE_0_GEN7	_MMIO(0x7000) /* IVB+ */
-#define RC_OP_FLUSH_ENABLE (1 << 0)
-#define   HIZ_RAW_STALL_OPT_DISABLE (1 << 2)
-#define CACHE_MODE_1		_MMIO(0x7004) /* IVB+ */
-#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1 << 6)
-#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
-#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
+#define CACHE_MODE_0				_MMIO(0x2120) /* 915+ only */
+#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE	(1 << 8)
+#define   CM0_IZ_OPT_DISABLE			(1 << 6)
+#define   CM0_ZR_OPT_DISABLE			(1 << 5)
+#define	  CM0_STC_EVICT_DISABLE_LRA_SNB		(1 << 5)
+#define   CM0_DEPTH_EVICT_DISABLE		(1 << 4)
+#define   CM0_COLOR_EVICT_DISABLE		(1 << 3)
+#define   CM0_DEPTH_WRITE_DISABLE		(1 << 1)
+#define   CM0_RC_OP_FLUSH_DISABLE		(1 << 0)
 
-#define GEN6_RCS_PWR_FSM _MMIO(0x22ac)
-#define GEN9_RCS_FE_FSM2 _MMIO(0x22a4)
-
-#define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
-#define   ENABLE_PREFETCH_INTO_IC		REG_BIT(3)
-#define   FLOAT_BLEND_OPTIMIZATION_ENABLE	REG_BIT(4)
-
-/* Fuse readout registers for GT */
-#define HSW_PAVP_FUSE1			_MMIO(0x911C)
-#define   XEHP_SFC_ENABLE_MASK		REG_GENMASK(27, 24)
-#define   HSW_F1_EU_DIS_MASK		REG_GENMASK(17, 16)
-#define   HSW_F1_EU_DIS_10EUS		0
-#define   HSW_F1_EU_DIS_8EUS		1
-#define   HSW_F1_EU_DIS_6EUS		2
-
-#define CHV_FUSE_GT			_MMIO(VLV_DISPLAY_BASE + 0x2168)
-#define   CHV_FGT_DISABLE_SS0		(1 << 10)
-#define   CHV_FGT_DISABLE_SS1		(1 << 11)
-#define   CHV_FGT_EU_DIS_SS0_R0_SHIFT	16
-#define   CHV_FGT_EU_DIS_SS0_R0_MASK	(0xf << CHV_FGT_EU_DIS_SS0_R0_SHIFT)
-#define   CHV_FGT_EU_DIS_SS0_R1_SHIFT	20
-#define   CHV_FGT_EU_DIS_SS0_R1_MASK	(0xf << CHV_FGT_EU_DIS_SS0_R1_SHIFT)
-#define   CHV_FGT_EU_DIS_SS1_R0_SHIFT	24
-#define   CHV_FGT_EU_DIS_SS1_R0_MASK	(0xf << CHV_FGT_EU_DIS_SS1_R0_SHIFT)
-#define   CHV_FGT_EU_DIS_SS1_R1_SHIFT	28
-#define   CHV_FGT_EU_DIS_SS1_R1_MASK	(0xf << CHV_FGT_EU_DIS_SS1_R1_SHIFT)
-
-#define GEN8_FUSE2			_MMIO(0x9120)
-#define   GEN8_F2_SS_DIS_SHIFT		21
-#define   GEN8_F2_SS_DIS_MASK		(0x7 << GEN8_F2_SS_DIS_SHIFT)
-#define   GEN8_F2_S_ENA_SHIFT		25
-#define   GEN8_F2_S_ENA_MASK		(0x7 << GEN8_F2_S_ENA_SHIFT)
-
-#define   GEN9_F2_SS_DIS_SHIFT		20
-#define   GEN9_F2_SS_DIS_MASK		(0xf << GEN9_F2_SS_DIS_SHIFT)
-
-#define   GEN10_F2_S_ENA_SHIFT		22
-#define   GEN10_F2_S_ENA_MASK		(0x3f << GEN10_F2_S_ENA_SHIFT)
-#define   GEN10_F2_SS_DIS_SHIFT		18
-#define   GEN10_F2_SS_DIS_MASK		(0xf << GEN10_F2_SS_DIS_SHIFT)
-
-#define	GEN10_MIRROR_FUSE3		_MMIO(0x9118)
-#define GEN10_L3BANK_PAIR_COUNT     4
-#define GEN10_L3BANK_MASK   0x0F
-/* on Xe_HP the same fuses indicates mslices instead of L3 banks */
-#define GEN12_MAX_MSLICES 4
-#define GEN12_MEML3_EN_MASK 0x0F
-
-#define GEN8_EU_DISABLE0		_MMIO(0x9134)
-#define   GEN8_EU_DIS0_S0_MASK		0xffffff
-#define   GEN8_EU_DIS0_S1_SHIFT		24
-#define   GEN8_EU_DIS0_S1_MASK		(0xff << GEN8_EU_DIS0_S1_SHIFT)
-
-#define GEN8_EU_DISABLE1		_MMIO(0x9138)
-#define   GEN8_EU_DIS1_S1_MASK		0xffff
-#define   GEN8_EU_DIS1_S2_SHIFT		16
-#define   GEN8_EU_DIS1_S2_MASK		(0xffff << GEN8_EU_DIS1_S2_SHIFT)
-
-#define GEN8_EU_DISABLE2		_MMIO(0x913c)
-#define   GEN8_EU_DIS2_S2_MASK		0xff
-
-#define GEN9_EU_DISABLE(slice)		_MMIO(0x9134 + (slice) * 0x4)
-
-#define GEN10_EU_DISABLE3		_MMIO(0x9140)
-#define   GEN10_EU_DIS_SS_MASK		0xff
-
-#define GEN11_GT_VEBOX_VDBOX_DISABLE	_MMIO(0x9140)
-#define   GEN11_GT_VDBOX_DISABLE_MASK	0xff
-#define   GEN11_GT_VEBOX_DISABLE_SHIFT	16
-#define   GEN11_GT_VEBOX_DISABLE_MASK	(0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT)
-
-#define GEN11_EU_DISABLE _MMIO(0x9134)
-#define GEN11_EU_DIS_MASK 0xFF
-
-#define GEN11_GT_SLICE_ENABLE _MMIO(0x9138)
-#define GEN11_GT_S_ENA_MASK 0xFF
-
-#define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
-
-#define GEN12_GT_GEOMETRY_DSS_ENABLE _MMIO(0x913C)
-#define GEN12_GT_COMPUTE_DSS_ENABLE _MMIO(0x9144)
-
-#define XEHP_EU_ENABLE			_MMIO(0x9134)
-#define XEHP_EU_ENA_MASK		0xFF
-
-#define CRSTANDVID		_MMIO(0x11100)
-#define PXVFREQ(fstart)		_MMIO(0x11110 + (fstart) * 4)  /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */
-#define   PXVFREQ_PX_MASK	0x7f000000
-#define   PXVFREQ_PX_SHIFT	24
-#define VIDFREQ_BASE		_MMIO(0x11110)
-#define VIDFREQ1		_MMIO(0x11110) /* VIDFREQ1-4 (0x1111c) (Cantiga) */
-#define VIDFREQ2		_MMIO(0x11114)
-#define VIDFREQ3		_MMIO(0x11118)
-#define VIDFREQ4		_MMIO(0x1111c)
-#define   VIDFREQ_P0_MASK	0x1f000000
-#define   VIDFREQ_P0_SHIFT	24
-#define   VIDFREQ_P0_CSCLK_MASK	0x00f00000
-#define   VIDFREQ_P0_CSCLK_SHIFT 20
-#define   VIDFREQ_P0_CRCLK_MASK	0x000f0000
-#define   VIDFREQ_P0_CRCLK_SHIFT 16
-#define   VIDFREQ_P1_MASK	0x00001f00
-#define   VIDFREQ_P1_SHIFT	8
-#define   VIDFREQ_P1_CSCLK_MASK	0x000000f0
-#define   VIDFREQ_P1_CSCLK_SHIFT 4
-#define   VIDFREQ_P1_CRCLK_MASK	0x0000000f
-#define INTTOEXT_BASE_ILK	_MMIO(0x11300)
-#define INTTOEXT_BASE		_MMIO(0x11120) /* INTTOEXT1-8 (0x1113c) */
-#define   INTTOEXT_MAP3_SHIFT	24
-#define   INTTOEXT_MAP3_MASK	(0x1f << INTTOEXT_MAP3_SHIFT)
-#define   INTTOEXT_MAP2_SHIFT	16
-#define   INTTOEXT_MAP2_MASK	(0x1f << INTTOEXT_MAP2_SHIFT)
-#define   INTTOEXT_MAP1_SHIFT	8
-#define   INTTOEXT_MAP1_MASK	(0x1f << INTTOEXT_MAP1_SHIFT)
-#define   INTTOEXT_MAP0_SHIFT	0
-#define   INTTOEXT_MAP0_MASK	(0x1f << INTTOEXT_MAP0_SHIFT)
-#define MEMSWCTL		_MMIO(0x11170) /* Ironlake only */
-#define   MEMCTL_CMD_MASK	0xe000
-#define   MEMCTL_CMD_SHIFT	13
-#define   MEMCTL_CMD_RCLK_OFF	0
-#define   MEMCTL_CMD_RCLK_ON	1
-#define   MEMCTL_CMD_CHFREQ	2
-#define   MEMCTL_CMD_CHVID	3
-#define   MEMCTL_CMD_VMMOFF	4
-#define   MEMCTL_CMD_VMMON	5
-#define   MEMCTL_CMD_STS	(1 << 12) /* write 1 triggers command, clears
-					     when command complete */
-#define   MEMCTL_FREQ_MASK	0x0f00 /* jitter, from 0-15 */
-#define   MEMCTL_FREQ_SHIFT	8
-#define   MEMCTL_SFCAVM		(1 << 7)
-#define   MEMCTL_TGT_VID_MASK	0x007f
-#define MEMIHYST		_MMIO(0x1117c)
-#define MEMINTREN		_MMIO(0x11180) /* 16 bits */
-#define   MEMINT_RSEXIT_EN	(1 << 8)
-#define   MEMINT_CX_SUPR_EN	(1 << 7)
-#define   MEMINT_CONT_BUSY_EN	(1 << 6)
-#define   MEMINT_AVG_BUSY_EN	(1 << 5)
-#define   MEMINT_EVAL_CHG_EN	(1 << 4)
-#define   MEMINT_MON_IDLE_EN	(1 << 3)
-#define   MEMINT_UP_EVAL_EN	(1 << 2)
-#define   MEMINT_DOWN_EVAL_EN	(1 << 1)
-#define   MEMINT_SW_CMD_EN	(1 << 0)
-#define MEMINTRSTR		_MMIO(0x11182) /* 16 bits */
-#define   MEM_RSEXIT_MASK	0xc000
-#define   MEM_RSEXIT_SHIFT	14
-#define   MEM_CONT_BUSY_MASK	0x3000
-#define   MEM_CONT_BUSY_SHIFT	12
-#define   MEM_AVG_BUSY_MASK	0x0c00
-#define   MEM_AVG_BUSY_SHIFT	10
-#define   MEM_EVAL_CHG_MASK	0x0300
-#define   MEM_EVAL_BUSY_SHIFT	8
-#define   MEM_MON_IDLE_MASK	0x00c0
-#define   MEM_MON_IDLE_SHIFT	6
-#define   MEM_UP_EVAL_MASK	0x0030
-#define   MEM_UP_EVAL_SHIFT	4
-#define   MEM_DOWN_EVAL_MASK	0x000c
-#define   MEM_DOWN_EVAL_SHIFT	2
-#define   MEM_SW_CMD_MASK	0x0003
-#define   MEM_INT_STEER_GFX	0
-#define   MEM_INT_STEER_CMR	1
-#define   MEM_INT_STEER_SMI	2
-#define   MEM_INT_STEER_SCI	3
-#define MEMINTRSTS		_MMIO(0x11184)
-#define   MEMINT_RSEXIT		(1 << 7)
-#define   MEMINT_CONT_BUSY	(1 << 6)
-#define   MEMINT_AVG_BUSY	(1 << 5)
-#define   MEMINT_EVAL_CHG	(1 << 4)
-#define   MEMINT_MON_IDLE	(1 << 3)
-#define   MEMINT_UP_EVAL	(1 << 2)
-#define   MEMINT_DOWN_EVAL	(1 << 1)
-#define   MEMINT_SW_CMD		(1 << 0)
-#define MEMMODECTL		_MMIO(0x11190)
-#define   MEMMODE_BOOST_EN	(1 << 31)
-#define   MEMMODE_BOOST_FREQ_MASK 0x0f000000 /* jitter for boost, 0-15 */
-#define   MEMMODE_BOOST_FREQ_SHIFT 24
-#define   MEMMODE_IDLE_MODE_MASK 0x00030000
-#define   MEMMODE_IDLE_MODE_SHIFT 16
-#define   MEMMODE_IDLE_MODE_EVAL 0
-#define   MEMMODE_IDLE_MODE_CONT 1
-#define   MEMMODE_HWIDLE_EN	(1 << 15)
-#define   MEMMODE_SWMODE_EN	(1 << 14)
-#define   MEMMODE_RCLK_GATE	(1 << 13)
-#define   MEMMODE_HW_UPDATE	(1 << 12)
-#define   MEMMODE_FSTART_MASK	0x00000f00 /* starting jitter, 0-15 */
-#define   MEMMODE_FSTART_SHIFT	8
-#define   MEMMODE_FMAX_MASK	0x000000f0 /* max jitter, 0-15 */
-#define   MEMMODE_FMAX_SHIFT	4
-#define   MEMMODE_FMIN_MASK	0x0000000f /* min jitter, 0-15 */
-#define RCBMAXAVG		_MMIO(0x1119c)
-#define MEMSWCTL2		_MMIO(0x1119e) /* Cantiga only */
-#define   SWMEMCMD_RENDER_OFF	(0 << 13)
-#define   SWMEMCMD_RENDER_ON	(1 << 13)
-#define   SWMEMCMD_SWFREQ	(2 << 13)
-#define   SWMEMCMD_TARVID	(3 << 13)
-#define   SWMEMCMD_VRM_OFF	(4 << 13)
-#define   SWMEMCMD_VRM_ON	(5 << 13)
-#define   CMDSTS		(1 << 12)
-#define   SFCAVM		(1 << 11)
-#define   SWFREQ_MASK		0x0380 /* P0-7 */
-#define   SWFREQ_SHIFT		7
-#define   TARVID_MASK		0x001f
-#define MEMSTAT_CTG		_MMIO(0x111a0)
-#define RCBMINAVG		_MMIO(0x111a0)
-#define RCUPEI			_MMIO(0x111b0)
-#define RCDNEI			_MMIO(0x111b4)
-#define RSTDBYCTL		_MMIO(0x111b8)
-#define   RS1EN			(1 << 31)
-#define   RS2EN			(1 << 30)
-#define   RS3EN			(1 << 29)
-#define   D3RS3EN		(1 << 28) /* Display D3 imlies RS3 */
-#define   SWPROMORSX		(1 << 27) /* RSx promotion timers ignored */
-#define   RCWAKERW		(1 << 26) /* Resetwarn from PCH causes wakeup */
-#define   DPRSLPVREN		(1 << 25) /* Fast voltage ramp enable */
-#define   GFXTGHYST		(1 << 24) /* Hysteresis to allow trunk gating */
-#define   RCX_SW_EXIT		(1 << 23) /* Leave RSx and prevent re-entry */
-#define   RSX_STATUS_MASK	(7 << 20)
-#define   RSX_STATUS_ON		(0 << 20)
-#define   RSX_STATUS_RC1	(1 << 20)
-#define   RSX_STATUS_RC1E	(2 << 20)
-#define   RSX_STATUS_RS1	(3 << 20)
-#define   RSX_STATUS_RS2	(4 << 20) /* aka rc6 */
-#define   RSX_STATUS_RSVD	(5 << 20) /* deep rc6 unsupported on ilk */
-#define   RSX_STATUS_RS3	(6 << 20) /* rs3 unsupported on ilk */
-#define   RSX_STATUS_RSVD2	(7 << 20)
-#define   UWRCRSXE		(1 << 19) /* wake counter limit prevents rsx */
-#define   RSCRP			(1 << 18) /* rs requests control on rs1/2 reqs */
-#define   JRSC			(1 << 17) /* rsx coupled to cpu c-state */
-#define   RS2INC0		(1 << 16) /* allow rs2 in cpu c0 */
-#define   RS1CONTSAV_MASK	(3 << 14)
-#define   RS1CONTSAV_NO_RS1	(0 << 14) /* rs1 doesn't save/restore context */
-#define   RS1CONTSAV_RSVD	(1 << 14)
-#define   RS1CONTSAV_SAVE_RS1	(2 << 14) /* rs1 saves context */
-#define   RS1CONTSAV_FULL_RS1	(3 << 14) /* rs1 saves and restores context */
-#define   NORMSLEXLAT_MASK	(3 << 12)
-#define   SLOW_RS123		(0 << 12)
-#define   SLOW_RS23		(1 << 12)
-#define   SLOW_RS3		(2 << 12)
-#define   NORMAL_RS123		(3 << 12)
-#define   RCMODE_TIMEOUT	(1 << 11) /* 0 is eval interval method */
-#define   IMPROMOEN		(1 << 10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
-#define   RCENTSYNC		(1 << 9) /* rs coupled to cpu c-state (3/6/7) */
-#define   STATELOCK		(1 << 7) /* locked to rs_cstate if 0 */
-#define   RS_CSTATE_MASK	(3 << 4)
-#define   RS_CSTATE_C367_RS1	(0 << 4)
-#define   RS_CSTATE_C36_RS1_C7_RS2 (1 << 4)
-#define   RS_CSTATE_RSVD	(2 << 4)
-#define   RS_CSTATE_C367_RS2	(3 << 4)
-#define   REDSAVES		(1 << 3) /* no context save if was idle during rs0 */
-#define   REDRESTORES		(1 << 2) /* no restore if was idle during rs0 */
-#define VIDCTL			_MMIO(0x111c0)
-#define VIDSTS			_MMIO(0x111c8)
-#define VIDSTART		_MMIO(0x111cc) /* 8 bits */
-#define MEMSTAT_ILK		_MMIO(0x111f8)
-#define   MEMSTAT_VID_MASK	0x7f00
-#define   MEMSTAT_VID_SHIFT	8
-#define   MEMSTAT_PSTATE_MASK	0x00f8
-#define   MEMSTAT_PSTATE_SHIFT  3
-#define   MEMSTAT_MON_ACTV	(1 << 2)
-#define   MEMSTAT_SRC_CTL_MASK	0x0003
-#define   MEMSTAT_SRC_CTL_CORE	0
-#define   MEMSTAT_SRC_CTL_TRB	1
-#define   MEMSTAT_SRC_CTL_THM	2
-#define   MEMSTAT_SRC_CTL_STDBY 3
-#define RCPREVBSYTUPAVG		_MMIO(0x113b8)
-#define RCPREVBSYTDNAVG		_MMIO(0x113bc)
-#define PMMISC			_MMIO(0x11214)
-#define   MCPPCE_EN		(1 << 0) /* enable PM_MSG from PCH->MPC */
-#define SDEW			_MMIO(0x1124c)
-#define CSIEW0			_MMIO(0x11250)
-#define CSIEW1			_MMIO(0x11254)
-#define CSIEW2			_MMIO(0x11258)
-#define PEW(i)			_MMIO(0x1125c + (i) * 4) /* 5 registers */
-#define DEW(i)			_MMIO(0x11270 + (i) * 4) /* 3 registers */
-#define MCHAFE			_MMIO(0x112c0)
-#define CSIEC			_MMIO(0x112e0)
-#define DMIEC			_MMIO(0x112e4)
-#define DDREC			_MMIO(0x112e8)
-#define PEG0EC			_MMIO(0x112ec)
-#define PEG1EC			_MMIO(0x112f0)
-#define GFXEC			_MMIO(0x112f4)
-#define RPPREVBSYTUPAVG		_MMIO(0x113b8)
-#define RPPREVBSYTDNAVG		_MMIO(0x113bc)
-#define ECR			_MMIO(0x11600)
-#define   ECR_GPFE		(1 << 31)
-#define   ECR_IMONE		(1 << 30)
-#define   ECR_CAP_MASK		0x0000001f /* Event range, 0-31 */
-#define OGW0			_MMIO(0x11608)
-#define OGW1			_MMIO(0x1160c)
-#define EG0			_MMIO(0x11610)
-#define EG1			_MMIO(0x11614)
-#define EG2			_MMIO(0x11618)
-#define EG3			_MMIO(0x1161c)
-#define EG4			_MMIO(0x11620)
-#define EG5			_MMIO(0x11624)
-#define EG6			_MMIO(0x11628)
-#define EG7			_MMIO(0x1162c)
-#define PXW(i)			_MMIO(0x11664 + (i) * 4) /* 4 registers */
-#define PXWL(i)			_MMIO(0x11680 + (i) * 8) /* 8 registers */
-#define LCFUSE02		_MMIO(0x116c0)
-#define   LCFUSE_HIV_MASK	0x000000ff
-
-#define GEN6_GT_THREAD_STATUS_REG _MMIO(0x13805c)
-#define GEN6_GT_THREAD_STATUS_CORE_MASK 0x7
+#define GFX_FLSH_CNTL				_MMIO(0x2170) /* 915+ only */
 
 /*
  * Logical Context regs
@@ -798,427 +185,538 @@
  * - GT1 size just indicates how much of render context
  *   doesn't need saving on GT1
  */
-#define CXT_SIZE		_MMIO(0x21a0)
-#define GEN6_CXT_POWER_SIZE(cxt_reg)	(((cxt_reg) >> 24) & 0x3f)
-#define GEN6_CXT_RING_SIZE(cxt_reg)	(((cxt_reg) >> 18) & 0x3f)
-#define GEN6_CXT_RENDER_SIZE(cxt_reg)	(((cxt_reg) >> 12) & 0x3f)
-#define GEN6_CXT_EXTENDED_SIZE(cxt_reg)	(((cxt_reg) >> 6) & 0x3f)
-#define GEN6_CXT_PIPELINE_SIZE(cxt_reg)	(((cxt_reg) >> 0) & 0x3f)
-#define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_RING_SIZE(cxt_reg) + \
-					GEN6_CXT_EXTENDED_SIZE(cxt_reg) + \
-					GEN6_CXT_PIPELINE_SIZE(cxt_reg))
-#define GEN7_CXT_SIZE		_MMIO(0x21a8)
-#define GEN7_CXT_POWER_SIZE(ctx_reg)	(((ctx_reg) >> 25) & 0x7f)
-#define GEN7_CXT_RING_SIZE(ctx_reg)	(((ctx_reg) >> 22) & 0x7)
-#define GEN7_CXT_RENDER_SIZE(ctx_reg)	(((ctx_reg) >> 16) & 0x3f)
-#define GEN7_CXT_EXTENDED_SIZE(ctx_reg)	(((ctx_reg) >> 9) & 0x7f)
-#define GEN7_CXT_GT1_SIZE(ctx_reg)	(((ctx_reg) >> 6) & 0x7)
-#define GEN7_CXT_VFSTATE_SIZE(ctx_reg)	(((ctx_reg) >> 0) & 0x3f)
-#define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
-					 GEN7_CXT_VFSTATE_SIZE(ctx_reg))
-
-enum {
-	INTEL_ADVANCED_CONTEXT = 0,
-	INTEL_LEGACY_32B_CONTEXT,
-	INTEL_ADVANCED_AD_CONTEXT,
-	INTEL_LEGACY_64B_CONTEXT
-};
-
-enum {
-	FAULT_AND_HANG = 0,
-	FAULT_AND_HALT, /* Debug only */
-	FAULT_AND_STREAM,
-	FAULT_AND_CONTINUE /* Unsupported */
-};
-
-#define CTX_GTT_ADDRESS_MASK GENMASK(31, 12)
-#define GEN8_CTX_VALID (1 << 0)
-#define GEN8_CTX_FORCE_PD_RESTORE (1 << 1)
-#define GEN8_CTX_FORCE_RESTORE (1 << 2)
-#define GEN8_CTX_L3LLC_COHERENT (1 << 5)
-#define GEN8_CTX_PRIVILEGE (1 << 8)
-#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
-
-#define GEN8_CTX_ID_SHIFT 32
-#define GEN8_CTX_ID_WIDTH 21
-#define GEN11_SW_CTX_ID_SHIFT 37
-#define GEN11_SW_CTX_ID_WIDTH 11
-#define GEN11_ENGINE_CLASS_SHIFT 61
-#define GEN11_ENGINE_CLASS_WIDTH 3
-#define GEN11_ENGINE_INSTANCE_SHIFT 48
-#define GEN11_ENGINE_INSTANCE_WIDTH 6
-
-#define XEHP_SW_CTX_ID_SHIFT 39
-#define XEHP_SW_CTX_ID_WIDTH 16
-#define XEHP_SW_COUNTER_SHIFT 58
-#define XEHP_SW_COUNTER_WIDTH 6
-
-#define UNSLCGCTL9440			_MMIO(0x9440)
-#define   GAMTLBOACS_CLKGATE_DIS	REG_BIT(28)
-#define   GAMTLBVDBOX5_CLKGATE_DIS	REG_BIT(27)
-#define   GAMTLBVDBOX6_CLKGATE_DIS	REG_BIT(26)
-#define   GAMTLBVDBOX3_CLKGATE_DIS	REG_BIT(24)
-#define   GAMTLBVDBOX4_CLKGATE_DIS	REG_BIT(23)
-#define   GAMTLBVDBOX7_CLKGATE_DIS	REG_BIT(22)
-#define   GAMTLBVDBOX2_CLKGATE_DIS	REG_BIT(21)
-#define   GAMTLBVDBOX0_CLKGATE_DIS	REG_BIT(17)
-#define   GAMTLBKCR_CLKGATE_DIS		REG_BIT(16)
-#define   GAMTLBGUC_CLKGATE_DIS		REG_BIT(15)
-#define   GAMTLBBLT_CLKGATE_DIS		REG_BIT(14)
-#define   GAMTLBVDBOX1_CLKGATE_DIS	REG_BIT(6)
-
-#define UNSLCGCTL9444			_MMIO(0x9444)
-#define   GAMTLBGFXA0_CLKGATE_DIS	REG_BIT(30)
-#define   GAMTLBGFXA1_CLKGATE_DIS	REG_BIT(29)
-#define   GAMTLBCOMPA0_CLKGATE_DIS	REG_BIT(28)
-#define   GAMTLBCOMPA1_CLKGATE_DIS	REG_BIT(27)
-#define   GAMTLBCOMPB0_CLKGATE_DIS	REG_BIT(26)
-#define   GAMTLBCOMPB1_CLKGATE_DIS	REG_BIT(25)
-#define   GAMTLBCOMPC0_CLKGATE_DIS	REG_BIT(24)
-#define   GAMTLBCOMPC1_CLKGATE_DIS	REG_BIT(23)
-#define   GAMTLBCOMPD0_CLKGATE_DIS	REG_BIT(22)
-#define   GAMTLBCOMPD1_CLKGATE_DIS	REG_BIT(21)
-#define   GAMTLBMERT_CLKGATE_DIS	REG_BIT(20)
-#define   GAMTLBVEBOX3_CLKGATE_DIS	REG_BIT(19)
-#define   GAMTLBVEBOX2_CLKGATE_DIS	REG_BIT(18)
-#define   GAMTLBVEBOX1_CLKGATE_DIS	REG_BIT(17)
-#define   GAMTLBVEBOX0_CLKGATE_DIS	REG_BIT(16)
-#define   LTCDD_CLKGATE_DIS		REG_BIT(10)
-
-#define SLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x94d4)
-#define  SARBUNIT_CLKGATE_DIS		(1 << 5)
-#define  RCCUNIT_CLKGATE_DIS		(1 << 7)
-#define  MSCUNIT_CLKGATE_DIS		(1 << 10)
-#define  NODEDSS_CLKGATE_DIS		REG_BIT(12)
-#define  L3_CLKGATE_DIS			REG_BIT(16)
-#define  L3_CR2X_CLKGATE_DIS		REG_BIT(17)
-
-#define SUBSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9524)
-#define   DSS_ROUTER_CLKGATE_DIS	REG_BIT(28)
-#define   GWUNIT_CLKGATE_DIS		REG_BIT(16)
-
-#define SUBSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x9528)
-#define  CPSSUNIT_CLKGATE_DIS		REG_BIT(9)
-
-#define SSMCGCTL9530			_MMIO(0x9530)
-#define   RTFUNIT_CLKGATE_DIS		REG_BIT(18)
-
-#define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
-#define   VFUNIT_CLKGATE_DIS		REG_BIT(20)
-#define   TSGUNIT_CLKGATE_DIS		REG_BIT(17) /* XEHPSDV */
-#define   CG3DDISCFEG_CLKGATE_DIS	REG_BIT(17) /* DG2 */
-#define   GAMEDIA_CLKGATE_DIS		REG_BIT(11)
-#define   HSUNIT_CLKGATE_DIS		REG_BIT(8)
-#define   VSUNIT_CLKGATE_DIS		REG_BIT(3)
-
-#define UNSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x94e4)
-#define   VSUNIT_CLKGATE_DIS_TGL	REG_BIT(19)
-#define   PSDUNIT_CLKGATE_DIS		REG_BIT(5)
-
-#define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
-#define   CGPSF_CLKGATE_DIS		(1 << 3)
-
-#define GEN11_GT_INTR_DW0		_MMIO(0x190018)
-#define  GEN11_CSME			(31)
-#define  GEN11_GUNIT			(28)
-#define  GEN11_GUC			(25)
-#define  GEN11_WDPERF			(20)
-#define  GEN11_KCR			(19)
-#define  GEN11_GTPM			(16)
-#define  GEN11_BCS			(15)
-#define  GEN11_RCS0			(0)
-
-#define GEN11_GT_INTR_DW1		_MMIO(0x19001c)
-#define  GEN11_VECS(x)			(31 - (x))
-#define  GEN11_VCS(x)			(x)
-
-#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + ((x) * 4))
-
-#define GEN11_INTR_IDENTITY_REG0	_MMIO(0x190060)
-#define GEN11_INTR_IDENTITY_REG1	_MMIO(0x190064)
-#define  GEN11_INTR_DATA_VALID		(1 << 31)
-#define  GEN11_INTR_ENGINE_CLASS(x)	(((x) & GENMASK(18, 16)) >> 16)
-#define  GEN11_INTR_ENGINE_INSTANCE(x)	(((x) & GENMASK(25, 20)) >> 20)
-#define  GEN11_INTR_ENGINE_INTR(x)	((x) & 0xffff)
-/* irq instances for OTHER_CLASS */
-#define OTHER_GUC_INSTANCE	0
-#define OTHER_GTPM_INSTANCE	1
-#define OTHER_KCR_INSTANCE	4
-
-#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + ((x) * 4))
-
-#define GEN11_IIR_REG0_SELECTOR		_MMIO(0x190070)
-#define GEN11_IIR_REG1_SELECTOR		_MMIO(0x190074)
-
-#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + ((x) * 4))
-
-#define GEN11_RENDER_COPY_INTR_ENABLE	_MMIO(0x190030)
-#define GEN11_VCS_VECS_INTR_ENABLE	_MMIO(0x190034)
-#define GEN11_GUC_SG_INTR_ENABLE	_MMIO(0x190038)
-#define GEN11_GPM_WGBOXPERF_INTR_ENABLE	_MMIO(0x19003c)
-#define GEN11_CRYPTO_RSVD_INTR_ENABLE	_MMIO(0x190040)
-#define GEN11_GUNIT_CSME_INTR_ENABLE	_MMIO(0x190044)
-
-#define GEN11_RCS0_RSVD_INTR_MASK	_MMIO(0x190090)
-#define GEN11_BCS_RSVD_INTR_MASK	_MMIO(0x1900a0)
-#define GEN11_VCS0_VCS1_INTR_MASK	_MMIO(0x1900a8)
-#define GEN11_VCS2_VCS3_INTR_MASK	_MMIO(0x1900ac)
-#define GEN12_VCS4_VCS5_INTR_MASK	_MMIO(0x1900b0)
-#define GEN12_VCS6_VCS7_INTR_MASK	_MMIO(0x1900b4)
-#define GEN11_VECS0_VECS1_INTR_MASK	_MMIO(0x1900d0)
-#define GEN12_VECS2_VECS3_INTR_MASK	_MMIO(0x1900d4)
-#define GEN11_GUC_SG_INTR_MASK		_MMIO(0x1900e8)
-#define GEN11_GPM_WGBOXPERF_INTR_MASK	_MMIO(0x1900ec)
-#define GEN11_CRYPTO_RSVD_INTR_MASK	_MMIO(0x1900f0)
-#define GEN11_GUNIT_CSME_INTR_MASK	_MMIO(0x1900f4)
-
-#define   ENGINE1_MASK			REG_GENMASK(31, 16)
-#define   ENGINE0_MASK			REG_GENMASK(15, 0)
-
-#define GEN7_FF_SLICE_CS_CHICKEN1	_MMIO(0x20e0)
-#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1 << 14)
-
-#define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
-#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1 << 8)
-#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1 << 10)
+#define CXT_SIZE				_MMIO(0x21a0)
+#define   GEN6_CXT_POWER_SIZE(cxt_reg)		(((cxt_reg) >> 24) & 0x3f)
+#define   GEN6_CXT_RING_SIZE(cxt_reg)		(((cxt_reg) >> 18) & 0x3f)
+#define   GEN6_CXT_RENDER_SIZE(cxt_reg)		(((cxt_reg) >> 12) & 0x3f)
+#define   GEN6_CXT_EXTENDED_SIZE(cxt_reg)	(((cxt_reg) >> 6) & 0x3f)
+#define   GEN6_CXT_PIPELINE_SIZE(cxt_reg)	(((cxt_reg) >> 0) & 0x3f)
+#define   GEN6_CXT_TOTAL_SIZE(cxt_reg)		(GEN6_CXT_RING_SIZE(cxt_reg) + \
+						GEN6_CXT_EXTENDED_SIZE(cxt_reg) + \
+						GEN6_CXT_PIPELINE_SIZE(cxt_reg))
+#define GEN7_CXT_SIZE				_MMIO(0x21a8)
+#define   GEN7_CXT_POWER_SIZE(ctx_reg)		(((ctx_reg) >> 25) & 0x7f)
+#define   GEN7_CXT_RING_SIZE(ctx_reg)		(((ctx_reg) >> 22) & 0x7)
+#define   GEN7_CXT_RENDER_SIZE(ctx_reg)		(((ctx_reg) >> 16) & 0x3f)
+#define   GEN7_CXT_EXTENDED_SIZE(ctx_reg)	(((ctx_reg) >> 9) & 0x7f)
+#define   GEN7_CXT_GT1_SIZE(ctx_reg)		(((ctx_reg) >> 6) & 0x7)
+#define   GEN7_CXT_VFSTATE_SIZE(ctx_reg)	(((ctx_reg) >> 0) & 0x3f)
+#define   GEN7_CXT_TOTAL_SIZE(ctx_reg)		(GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
+						 GEN7_CXT_VFSTATE_SIZE(ctx_reg))
+
+#define HSW_MI_PREDICATE_RESULT_2		_MMIO(0x2214)
+
+#define GEN9_CTX_PREEMPT_REG			_MMIO(0x2248)
+#define   GEN12_DISABLE_POSH_BUSY_FF_DOP_CG	REG_BIT(11)
+
+#define GPGPU_THREADS_DISPATCHED		_MMIO(0x2290)
+#define GPGPU_THREADS_DISPATCHED_UDW		_MMIO(0x2290 + 4)
+
+#define GEN9_RCS_FE_FSM2			_MMIO(0x22a4)
+#define GEN6_RCS_PWR_FSM			_MMIO(0x22ac)
+
+#define HS_INVOCATION_COUNT			_MMIO(0x2300)
+#define HS_INVOCATION_COUNT_UDW			_MMIO(0x2300 + 4)
+#define DS_INVOCATION_COUNT			_MMIO(0x2308)
+#define DS_INVOCATION_COUNT_UDW			_MMIO(0x2308 + 4)
+#define IA_VERTICES_COUNT			_MMIO(0x2310)
+#define IA_VERTICES_COUNT_UDW			_MMIO(0x2310 + 4)
+#define IA_PRIMITIVES_COUNT			_MMIO(0x2318)
+#define IA_PRIMITIVES_COUNT_UDW			_MMIO(0x2318 + 4)
+#define VS_INVOCATION_COUNT			_MMIO(0x2320)
+#define VS_INVOCATION_COUNT_UDW			_MMIO(0x2320 + 4)
+#define GS_INVOCATION_COUNT			_MMIO(0x2328)
+#define GS_INVOCATION_COUNT_UDW			_MMIO(0x2328 + 4)
+#define GS_PRIMITIVES_COUNT			_MMIO(0x2330)
+#define GS_PRIMITIVES_COUNT_UDW			_MMIO(0x2330 + 4)
+#define CL_INVOCATION_COUNT			_MMIO(0x2338)
+#define CL_INVOCATION_COUNT_UDW			_MMIO(0x2338 + 4)
+#define CL_PRIMITIVES_COUNT			_MMIO(0x2340)
+#define CL_PRIMITIVES_COUNT_UDW			_MMIO(0x2340 + 4)
+#define PS_INVOCATION_COUNT			_MMIO(0x2348)
+#define PS_INVOCATION_COUNT_UDW			_MMIO(0x2348 + 4)
+#define PS_DEPTH_COUNT				_MMIO(0x2350)
+#define PS_DEPTH_COUNT_UDW			_MMIO(0x2350 + 4)
+#define GEN7_3DPRIM_END_OFFSET			_MMIO(0x2420)
+#define GEN7_3DPRIM_START_VERTEX		_MMIO(0x2430)
+#define GEN7_3DPRIM_VERTEX_COUNT		_MMIO(0x2434)
+#define GEN7_3DPRIM_INSTANCE_COUNT		_MMIO(0x2438)
+#define GEN7_3DPRIM_START_INSTANCE		_MMIO(0x243c)
+#define GEN7_3DPRIM_BASE_VERTEX			_MMIO(0x2440)
+#define GEN7_GPGPU_DISPATCHDIMX			_MMIO(0x2500)
+#define GEN7_GPGPU_DISPATCHDIMY			_MMIO(0x2504)
+#define GEN7_GPGPU_DISPATCHDIMZ			_MMIO(0x2508)
+
+#define GFX_MODE				_MMIO(0x2520)
+
+#define GEN8_CS_CHICKEN1			_MMIO(0x2580)
+#define   GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
+#define   GEN9_PREEMPT_GPGPU_LEVEL(hi, lo)	(((hi) << 2) | ((lo) << 1))
+#define   GEN9_PREEMPT_GPGPU_MID_THREAD_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 0)
+#define   GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 1)
+#define   GEN9_PREEMPT_GPGPU_COMMAND_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(1, 0)
+#define   GEN9_PREEMPT_GPGPU_LEVEL_MASK		GEN9_PREEMPT_GPGPU_LEVEL(1, 1)
+
+#define GEN12_GLOBAL_MOCS(i)			_MMIO(0x4000 + (i) * 4) /* Global MOCS regs */
+
+#define RENDER_HWS_PGA_GEN7			_MMIO(0x4080)
+
+#define GEN8_GAMW_ECO_DEV_RW_IA			_MMIO(0x4080)
+#define   GAMW_ECO_ENABLE_64K_IPS_FIELD		0xF
+#define   GAMW_ECO_DEV_CTX_RELOAD_DISABLE	(1 << 7)
 
-#define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
-#define   FF_DOP_CLOCK_GATE_DISABLE	REG_BIT(1)
-#define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
-#define   GEN12_DISABLE_POSH_BUSY_FF_DOP_CG REG_BIT(11)
+#define GAM_ECOCHK				_MMIO(0x4090)
+#define   BDW_DISABLE_HDC_INVALIDATION		(1 << 25)
+#define   ECOCHK_SNB_BIT			(1 << 10)
+#define   ECOCHK_DIS_TLB			(1 << 8)
+#define   HSW_ECOCHK_ARB_PRIO_SOL		(1 << 6)
+#define   ECOCHK_PPGTT_CACHE64B			(0x3 << 3)
+#define   ECOCHK_PPGTT_CACHE4B			(0x0 << 3)
+#define   ECOCHK_PPGTT_GFDT_IVB			(0x1 << 4)
+#define   ECOCHK_PPGTT_LLC_IVB			(0x1 << 3)
+#define   ECOCHK_PPGTT_UC_HSW			(0x1 << 3)
+#define   ECOCHK_PPGTT_WT_HSW			(0x2 << 3)
+#define   ECOCHK_PPGTT_WB_HSW			(0x3 << 3)
+
+#define GEN8_RING_FAULT_REG			_MMIO(0x4094)
+#define _RING_FAULT_REG_RCS			0x4094
+#define _RING_FAULT_REG_VCS			0x4194
+#define _RING_FAULT_REG_BCS			0x4294
+#define _RING_FAULT_REG_VECS			0x4394
+#define RING_FAULT_REG(engine)			_MMIO(_PICK((engine)->class, \
+							    _RING_FAULT_REG_RCS, \
+							    _RING_FAULT_REG_VCS, \
+							    _RING_FAULT_REG_VECS, \
+							    _RING_FAULT_REG_BCS))
+
+#define ERROR_GEN6				_MMIO(0x40a0)
+
+#define DONE_REG				_MMIO(0x40b0)
+#define GEN8_PRIVATE_PAT_LO			_MMIO(0x40e0)
+#define GEN8_PRIVATE_PAT_HI			_MMIO(0x40e0 + 4)
+#define GEN10_PAT_INDEX(index)			_MMIO(0x40e0 + (index) * 4)
+#define BSD_HWS_PGA_GEN7			_MMIO(0x4180)
+#define GEN12_GFX_CCS_AUX_NV			_MMIO(0x4208)
+#define GEN12_VD0_AUX_NV			_MMIO(0x4218)
+#define GEN12_VD1_AUX_NV			_MMIO(0x4228)
+
+#define GEN8_RTCR				_MMIO(0x4260)
+#define GEN8_M1TCR				_MMIO(0x4264)
+#define GEN8_M2TCR				_MMIO(0x4268)
+#define GEN8_BTCR				_MMIO(0x426c)
+#define GEN8_VTCR				_MMIO(0x4270)
+
+#define GEN12_VD2_AUX_NV			_MMIO(0x4298)
+#define GEN12_VD3_AUX_NV			_MMIO(0x42a8)
+#define GEN12_VE0_AUX_NV			_MMIO(0x4238)
+
+#define BLT_HWS_PGA_GEN7			_MMIO(0x4280)
+
+#define GEN12_VE1_AUX_NV			_MMIO(0x42b8)
+#define   AUX_INV				REG_BIT(0)
+#define VEBOX_HWS_PGA_GEN7			_MMIO(0x4380)
+
+#define GEN12_AUX_ERR_DBG			_MMIO(0x43f4)
+
+#define GEN7_TLB_RD_ADDR			_MMIO(0x4700)
+
+#define GEN12_PAT_INDEX(index)			_MMIO(0x4800 + (index) * 4)
+
+#define GAMTARBMODE				_MMIO(0x4a08)
+#define   ARB_MODE_BWGTLB_DISABLE		(1 << 9)
+#define   ARB_MODE_SWIZZLE_BDW			(1 << 1)
+
+#define GEN9_GAMT_ECO_REG_RW_IA			_MMIO(0x4ab0)
+#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1 << 18)
 
-#define GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON		_MMIO(0x20EC)
-#define   GEN12_REPLAY_MODE_GRANULARITY			REG_BIT(0)
+#define GAMT_CHKN_BIT_REG			_MMIO(0x4ab8)
+#define   GAMT_CHKN_DISABLE_L3_COH_PIPE		(1 << 31)
+#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1 << 28)
+#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1 << 24)
 
-#define GEN8_CS_CHICKEN1		_MMIO(0x2580)
-#define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
-#define GEN9_PREEMPT_GPGPU_LEVEL(hi, lo)	(((hi) << 2) | ((lo) << 1))
-#define GEN9_PREEMPT_GPGPU_MID_THREAD_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 0)
-#define GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 1)
-#define GEN9_PREEMPT_GPGPU_COMMAND_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(1, 0)
-#define GEN9_PREEMPT_GPGPU_LEVEL_MASK		GEN9_PREEMPT_GPGPU_LEVEL(1, 1)
+#define GEN8_FAULT_TLB_DATA0			_MMIO(0x4b10)
+#define GEN8_FAULT_TLB_DATA1			_MMIO(0x4b14)
 
-/* GEN7 chicken */
-#define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
-  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	(1 << 10)
-  #define GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
+#define GEN11_GACB_PERF_CTRL			_MMIO(0x4b80)
+#define   GEN11_HASH_CTRL_MASK			(0x3 << 12 | 0xf << 0)
+#define   GEN11_HASH_CTRL_BIT0			(1 << 0)
+#define   GEN11_HASH_CTRL_BIT4			(1 << 12)
 
-#define COMMON_SLICE_CHICKEN2					_MMIO(0x7014)
-  #define GEN9_PBE_COMPRESSED_HASH_SELECTION			(1 << 13)
-  #define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE	(1 << 12)
-  #define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION		(1 << 8)
-  #define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE			(1 << 0)
+/* gamt regs */
+#define GEN8_L3_LRA_1_GPGPU			_MMIO(0x4dd4)
+#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW	0x67F1427F /* max/min for LRA1/2 */
+#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV	0x5FF101FF /* max/min for LRA1/2 */
+#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL	0x67F1427F /*    "        " */
+#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT	0x5FF101FF /*    "        " */
 
-#define GEN8_L3CNTLREG	_MMIO(0x7034)
-  #define GEN8_ERRDETBCTRL (1 << 9)
+#define MMCD_MISC_CTRL				_MMIO(0x4ddc) /* skl+ */
+#define   MMCD_PCLA				(1 << 31)
+#define   MMCD_HOTSPOT_EN			(1 << 27)
 
-#define GEN11_COMMON_SLICE_CHICKEN3			_MMIO(0x7304)
-#define   DG1_FLOAT_POINT_BLEND_OPT_STRICT_MODE_EN	REG_BIT(12)
-#define   XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE		REG_BIT(12)
-#define   GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC		REG_BIT(11)
-#define   GEN12_DISABLE_CPS_AWARE_COLOR_PIPE		REG_BIT(9)
+/* There are the 4 64-bit counter registers, one for each stream output */
+#define GEN7_SO_NUM_PRIMS_WRITTEN(n)		_MMIO(0x5200 + (n) * 8)
+#define GEN7_SO_NUM_PRIMS_WRITTEN_UDW(n)	_MMIO(0x5200 + (n) * 8 + 4)
 
-#define HIZ_CHICKEN					_MMIO(0x7018)
-# define CHV_HZ_8X8_MODE_IN_1X				REG_BIT(15)
-# define DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE   REG_BIT(14)
-# define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	REG_BIT(3)
+#define GEN7_SO_PRIM_STORAGE_NEEDED(n)		_MMIO(0x5240 + (n) * 8)
+#define GEN7_SO_PRIM_STORAGE_NEEDED_UDW(n)	_MMIO(0x5240 + (n) * 8 + 4)
 
-#define GEN9_SLICE_COMMON_ECO_CHICKEN0		_MMIO(0x7308)
-#define  DISABLE_PIXEL_MASK_CAMMING		(1 << 14)
+#define GEN9_WM_CHICKEN3			_MMIO(0x5588)
+#define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
 
-#define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
-#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
+#define VFLSKPD					_MMIO(0x62a8)
+#define   DIS_OVER_FETCH_CACHE			REG_BIT(1)
+#define   DIS_MULT_MISS_RD_SQUASH		REG_BIT(0)
 
-#define GEN7_SARCHKMD				_MMIO(0xB000)
-#define GEN7_DISABLE_DEMAND_PREFETCH		(1 << 31)
-#define GEN7_DISABLE_SAMPLER_PREFETCH           (1 << 30)
+#define FF_MODE2				_MMIO(0x6604)
+#define   FF_MODE2_GS_TIMER_MASK		REG_GENMASK(31, 24)
+#define   FF_MODE2_GS_TIMER_224			REG_FIELD_PREP(FF_MODE2_GS_TIMER_MASK, 224)
+#define   FF_MODE2_TDS_TIMER_MASK		REG_GENMASK(23, 16)
+#define   FF_MODE2_TDS_TIMER_128		REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
 
-#define GEN7_L3SQCREG1				_MMIO(0xB010)
-#define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
+#define XEHPG_INSTDONE_GEOM_SVG			_MMIO(0x666c)
 
-#define GEN8_L3SQCREG1				_MMIO(0xB100)
-/*
- * Note that on CHV the following has an off-by-one error wrt. to BSpec.
- * Using the formula in BSpec leads to a hang, while the formula here works
- * fine and matches the formulas for all other platforms. A BSpec change
- * request has been filed to clarify this.
- */
-#define  L3_GENERAL_PRIO_CREDITS(x)		(((x) >> 1) << 19)
-#define  L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
-#define  L3_PRIO_CREDITS_MASK			((0x1f << 19) | (0x1f << 14))
+#define CACHE_MODE_0_GEN7			_MMIO(0x7000) /* IVB+ */
+#define   RC_OP_FLUSH_ENABLE			(1 << 0)
+#define   HIZ_RAW_STALL_OPT_DISABLE		(1 << 2)
+#define CACHE_MODE_1				_MMIO(0x7004) /* IVB+ */
+#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1 << 6)
+#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
+#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
 
-#define GEN7_L3CNTLREG1				_MMIO(0xB01C)
-#define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
-#define  GEN7_L3AGDIS				(1 << 19)
-#define GEN7_L3CNTLREG2				_MMIO(0xB020)
-#define GEN7_L3CNTLREG3				_MMIO(0xB024)
+#define GEN7_GT_MODE				_MMIO(0x7008)
+#define   GEN9_IZ_HASHING_MASK(slice)		(0x3 << ((slice) * 2))
+#define   GEN9_IZ_HASHING(slice, val)		((val) << ((slice) * 2))
 
-#define GEN7_L3_CHICKEN_MODE_REGISTER		_MMIO(0xB030)
-#define   GEN7_WA_L3_CHICKEN_MODE		0x20000000
-#define GEN10_L3_CHICKEN_MODE_REGISTER		_MMIO(0xB114)
-#define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
+/* GEN7 chicken */
+#define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
+#define   GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	(1 << 10)
+#define   GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
 
-#define GEN7_L3SQCREG4				_MMIO(0xb034)
-#define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1 << 27)
+#define COMMON_SLICE_CHICKEN2			_MMIO(0x7014)
+#define   GEN9_PBE_COMPRESSED_HASH_SELECTION	(1 << 13)
+#define   GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE	(1 << 12)
+#define   GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION	(1 << 8)
+#define   GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1 << 0)
 
-#define GEN11_SCRATCH2					_MMIO(0xb140)
-#define  GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE	(1 << 19)
+#define HIZ_CHICKEN				_MMIO(0x7018)
+#define   CHV_HZ_8X8_MODE_IN_1X			REG_BIT(15)
+#define   DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE	REG_BIT(14)
+#define   BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	REG_BIT(3)
 
-#define GEN8_L3SQCREG4				_MMIO(0xb118)
-#define  GEN11_LQSC_CLEAN_EVICT_DISABLE		(1 << 6)
-#define  GEN8_LQSC_RO_PERF_DIS			(1 << 27)
-#define  GEN8_LQSC_FLUSH_COHERENT_LINES		(1 << 21)
-#define  GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(22)
+#define GEN8_L3CNTLREG				_MMIO(0x7034)
+#define   GEN8_ERRDETBCTRL			(1 << 9)
 
-#define GEN11_L3SQCREG5				_MMIO(0xb158)
-#define   L3_PWM_TIMER_INIT_VAL_MASK		REG_GENMASK(9, 0)
-
-#define XEHP_L3SCQREG7				_MMIO(0xb188)
-#define   BLEND_FILL_CACHING_OPT_DIS		REG_BIT(3)
+#define GEN7_SC_INSTDONE			_MMIO(0x7100)
+#define GEN12_SC_INSTDONE_EXTRA			_MMIO(0x7104)
+#define GEN12_SC_INSTDONE_EXTRA2		_MMIO(0x7108)
 
 /* GEN8 chicken */
 #define HDC_CHICKEN0				_MMIO(0x7300)
-#define ICL_HDC_MODE				_MMIO(0xE5F4)
-#define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1 << 15)
-#define  HDC_FENCE_DEST_SLM_DISABLE		(1 << 14)
-#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1 << 11)
-#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1 << 5)
-#define  HDC_FORCE_NON_COHERENT			(1 << 4)
-#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1 << 10)
-
-#define GEN12_HDC_CHICKEN0					_MMIO(0xE5F0)
-#define   LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK	REG_GENMASK(13, 11)
-
-#define SARB_CHICKEN1				_MMIO(0xe90c)
-#define   COMP_CKN_IN				REG_GENMASK(30, 29)
+#define   HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1 << 15)
+#define   HDC_FENCE_DEST_SLM_DISABLE		(1 << 14)
+#define   HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1 << 11)
+#define   HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1 << 5)
+#define   HDC_FORCE_NON_COHERENT		(1 << 4)
+#define   HDC_BARRIER_PERFORMANCE_DISABLE	(1 << 10)
 
 #define GEN8_HDC_CHICKEN1			_MMIO(0x7304)
 
+#define GEN11_COMMON_SLICE_CHICKEN3		_MMIO(0x7304)
+#define   DG1_FLOAT_POINT_BLEND_OPT_STRICT_MODE_EN	REG_BIT(12)
+#define   XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE	REG_BIT(12)
+#define   GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	REG_BIT(11)
+#define   GEN12_DISABLE_CPS_AWARE_COLOR_PIPE	REG_BIT(9)
+
 /* GEN9 chicken */
 #define SLICE_ECO_CHICKEN0			_MMIO(0x7308)
 #define   PIXEL_MASK_CAMMING_DISABLE		(1 << 14)
 
-#define GEN9_WM_CHICKEN3			_MMIO(0x5588)
-#define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
+#define GEN9_SLICE_COMMON_ECO_CHICKEN0		_MMIO(0x7308)
+#define   DISABLE_PIXEL_MASK_CAMMING		(1 << 14)
+
+#define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
+#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
+
+#define SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
+#define   MSC_MSAA_REODER_BUF_BYPASS_DISABLE	REG_BIT(14)
+
+#define GEN9_SLICE_PGCTL_ACK(slice)		_MMIO(0x804c + (slice) * 0x4)
+#define GEN10_SLICE_PGCTL_ACK(slice)		_MMIO(0x804c + ((slice) / 3) * 0x34 + \
+						      ((slice) % 3) * 0x4)
+#define   GEN9_PGCTL_SLICE_ACK			(1 << 0)
+#define   GEN9_PGCTL_SS_ACK(subslice)		(1 << (2 + (subslice) * 2))
+#define   GEN10_PGCTL_VALID_SS_MASK(slice)	((slice) == 0 ? 0x7F : 0x1F)
+
+#define GEN9_SS01_EU_PGCTL_ACK(slice)		_MMIO(0x805c + (slice) * 0x8)
+#define GEN10_SS01_EU_PGCTL_ACK(slice)		_MMIO(0x805c + ((slice) / 3) * 0x30 + \
+						      ((slice) % 3) * 0x8)
+#define GEN9_SS23_EU_PGCTL_ACK(slice)		_MMIO(0x8060 + (slice) * 0x8)
+#define GEN10_SS23_EU_PGCTL_ACK(slice)		_MMIO(0x8060 + ((slice) / 3) * 0x30 + \
+						      ((slice) % 3) * 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)
+#define   GEN9_PGCTL_SSA_EU311_ACK		(1 << 6)
+#define   GEN9_PGCTL_SSB_EU08_ACK		(1 << 8)
+#define   GEN9_PGCTL_SSB_EU19_ACK		(1 << 10)
+#define   GEN9_PGCTL_SSB_EU210_ACK		(1 << 12)
+#define   GEN9_PGCTL_SSB_EU311_ACK		(1 << 14)
+
+#define GEN8_RC6_CTX_INFO			_MMIO(0x8504)
+
+#define GEN12_SQCM				_MMIO(0x8724)
+#define   EN_32B_ACCESS				REG_BIT(30)
+
+#define HSW_IDICR				_MMIO(0x9008)
+#define   IDIHASHMSK(x)				(((x) & 0x3f) << 16)
+
+#define GEN6_MBCUNIT_SNPCR			_MMIO(0x900c) /* for LLC config */
+#define   GEN6_MBC_SNPCR_SHIFT			21
+#define   GEN6_MBC_SNPCR_MASK			(3 << 21)
+#define   GEN6_MBC_SNPCR_MAX			(0 << 21)
+#define   GEN6_MBC_SNPCR_MED			(1 << 21)
+#define   GEN6_MBC_SNPCR_LOW			(2 << 21)
+#define   GEN6_MBC_SNPCR_MIN			(3 << 21) /* only 1/16th of the cache is shared */
+
+#define VLV_G3DCTL				_MMIO(0x9024)
+#define VLV_GSCKGCTL				_MMIO(0x9028)
 
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		_MMIO(0x9030)
-#define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1 << 11)
+#define   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1 << 11)
 
-#define HSW_SCRATCH1				_MMIO(0xb038)
-#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1 << 27)
-
-#define BDW_SCRATCH1					_MMIO(0xb11c)
-#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
-
-#define VFLSKPD				_MMIO(0x62a8)
-#define   DIS_OVER_FETCH_CACHE		REG_BIT(1)
-#define   DIS_MULT_MISS_RD_SQUASH	REG_BIT(0)
-
-#define FF_MODE2			_MMIO(0x6604)
-#define   FF_MODE2_GS_TIMER_MASK	REG_GENMASK(31, 24)
-#define   FF_MODE2_GS_TIMER_224		REG_FIELD_PREP(FF_MODE2_GS_TIMER_MASK, 224)
-#define   FF_MODE2_TDS_TIMER_MASK	REG_GENMASK(23, 16)
-#define   FF_MODE2_TDS_TIMER_128	REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
-
-#define  RC6_LOCATION				_MMIO(0xD40)
-#define	   RC6_CTX_IN_DRAM			(1 << 0)
-#define  RC6_CTX_BASE				_MMIO(0xD48)
-#define    RC6_CTX_BASE_MASK			0xFFFFFFF0
-#define  FORCEWAKE				_MMIO(0xA18C)
-#define  FORCEWAKE_VLV				_MMIO(0x1300b0)
-#define  FORCEWAKE_ACK_VLV			_MMIO(0x1300b4)
-#define  FORCEWAKE_MEDIA_VLV			_MMIO(0x1300b8)
-#define  FORCEWAKE_ACK_MEDIA_VLV		_MMIO(0x1300bc)
-#define  FORCEWAKE_ACK_HSW			_MMIO(0x130044)
-#define  FORCEWAKE_ACK				_MMIO(0x130090)
-#define  VLV_GTLC_WAKE_CTRL			_MMIO(0x130090)
-#define   VLV_GTLC_RENDER_CTX_EXISTS		(1 << 25)
-#define   VLV_GTLC_MEDIA_CTX_EXISTS		(1 << 24)
-#define   VLV_GTLC_ALLOWWAKEREQ			(1 << 0)
+#define FBC_LLC_READ_CTRL			_MMIO(0x9044)
+#define   FBC_LLC_FULLY_OPEN			REG_BIT(30)
 
-#define  VLV_GTLC_PW_STATUS			_MMIO(0x130094)
-#define   VLV_GTLC_ALLOWWAKEACK			(1 << 0)
-#define   VLV_GTLC_ALLOWWAKEERR			(1 << 1)
-#define   VLV_GTLC_PW_MEDIA_STATUS_MASK		(1 << 5)
-#define   VLV_GTLC_PW_RENDER_STATUS_MASK	(1 << 7)
-#define  FORCEWAKE_MT				_MMIO(0xa188) /* multi-threaded */
-#define  FORCEWAKE_MEDIA_GEN9			_MMIO(0xa270)
-#define  FORCEWAKE_MEDIA_VDBOX_GEN11(n)		_MMIO(0xa540 + (n) * 4)
-#define  FORCEWAKE_MEDIA_VEBOX_GEN11(n)		_MMIO(0xa560 + (n) * 4)
-#define  FORCEWAKE_RENDER_GEN9			_MMIO(0xa278)
-#define  FORCEWAKE_GT_GEN9			_MMIO(0xa188)
-#define  FORCEWAKE_ACK_MEDIA_GEN9		_MMIO(0x0D88)
-#define  FORCEWAKE_ACK_MEDIA_VDBOX_GEN11(n)	_MMIO(0x0D50 + (n) * 4)
-#define  FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(n)	_MMIO(0x0D70 + (n) * 4)
-#define  FORCEWAKE_ACK_RENDER_GEN9		_MMIO(0x0D84)
-#define  FORCEWAKE_ACK_GT_GEN9			_MMIO(0x130044)
-#define   FORCEWAKE_KERNEL			BIT(0)
-#define   FORCEWAKE_USER			BIT(1)
-#define   FORCEWAKE_KERNEL_FALLBACK		BIT(15)
-#define  FORCEWAKE_MT_ACK			_MMIO(0x130040)
-#define  ECOBUS					_MMIO(0xa180)
-#define    FORCEWAKE_MT_ENABLE			(1 << 5)
-#define  VLV_SPAREG2H				_MMIO(0xA194)
-#define  GEN9_PWRGT_DOMAIN_STATUS		_MMIO(0xA2A0)
-#define   GEN9_PWRGT_MEDIA_STATUS_MASK		(1 << 0)
-#define   GEN9_PWRGT_RENDER_STATUS_MASK		(1 << 1)
+#define GEN6_MBCTL				_MMIO(0x907c)
+#define   GEN6_MBCTL_ENABLE_BOOT_FETCH		(1 << 4)
+#define   GEN6_MBCTL_CTX_FETCH_NEEDED		(1 << 3)
+#define   GEN6_MBCTL_BME_UPDATE_ENABLE		(1 << 2)
+#define   GEN6_MBCTL_MAE_UPDATE_ENABLE		(1 << 1)
+#define   GEN6_MBCTL_BOOT_FETCH_MECH		(1 << 0)
 
-#define  GTFIFODBG				_MMIO(0x120000)
-#define    GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV	(0x1f << 20)
-#define    GT_FIFO_FREE_ENTRIES_CHV		(0x7f << 13)
-#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  GTFIFOCTL				_MMIO(0x120008)
-#define    GT_FIFO_FREE_ENTRIES_MASK		0x7f
-#define    GT_FIFO_NUM_RESERVED_ENTRIES		20
-#define    GT_FIFO_CTL_BLOCK_ALL_POLICY_STALL	(1 << 12)
-#define    GT_FIFO_CTL_RC6_POLICY_STALL		(1 << 11)
-
-#define  HSW_IDICR				_MMIO(0x9008)
-#define    IDIHASHMSK(x)			(((x) & 0x3f) << 16)
+/* Fuse readout registers for GT */
+#define	GEN10_MIRROR_FUSE3			_MMIO(0x9118)
+#define   GEN10_L3BANK_PAIR_COUNT		4
+#define   GEN10_L3BANK_MASK			0x0F
+/* on Xe_HP the same fuses indicates mslices instead of L3 banks */
+#define   GEN12_MAX_MSLICES			4
+#define   GEN12_MEML3_EN_MASK			0x0F
+
+#define HSW_PAVP_FUSE1				_MMIO(0x911c)
+#define   XEHP_SFC_ENABLE_MASK			REG_GENMASK(27, 24)
+#define   HSW_F1_EU_DIS_MASK			REG_GENMASK(17, 16)
+#define   HSW_F1_EU_DIS_10EUS			0
+#define   HSW_F1_EU_DIS_8EUS			1
+#define   HSW_F1_EU_DIS_6EUS			2
+
+#define GEN8_FUSE2				_MMIO(0x9120)
+#define   GEN8_F2_SS_DIS_SHIFT			21
+#define   GEN8_F2_SS_DIS_MASK			(0x7 << GEN8_F2_SS_DIS_SHIFT)
+#define   GEN8_F2_S_ENA_SHIFT			25
+#define   GEN8_F2_S_ENA_MASK			(0x7 << GEN8_F2_S_ENA_SHIFT)
+#define   GEN9_F2_SS_DIS_SHIFT			20
+#define   GEN9_F2_SS_DIS_MASK			(0xf << GEN9_F2_SS_DIS_SHIFT)
+#define   GEN10_F2_S_ENA_SHIFT			22
+#define   GEN10_F2_S_ENA_MASK			(0x3f << GEN10_F2_S_ENA_SHIFT)
+#define   GEN10_F2_SS_DIS_SHIFT			18
+#define   GEN10_F2_SS_DIS_MASK			(0xf << GEN10_F2_SS_DIS_SHIFT)
+
+#define GEN8_EU_DISABLE0			_MMIO(0x9134)
+#define GEN9_EU_DISABLE(slice)			_MMIO(0x9134 + (slice) * 0x4)
+#define GEN11_EU_DISABLE			_MMIO(0x9134)
+#define   GEN8_EU_DIS0_S0_MASK			0xffffff
+#define   GEN8_EU_DIS0_S1_SHIFT			24
+#define   GEN8_EU_DIS0_S1_MASK			(0xff << GEN8_EU_DIS0_S1_SHIFT)
+#define   GEN11_EU_DIS_MASK			0xFF
+#define XEHP_EU_ENABLE				_MMIO(0x9134)
+#define   XEHP_EU_ENA_MASK			0xFF
+
+#define GEN8_EU_DISABLE1			_MMIO(0x9138)
+#define   GEN8_EU_DIS1_S1_MASK			0xffff
+#define   GEN8_EU_DIS1_S2_SHIFT			16
+#define   GEN8_EU_DIS1_S2_MASK			(0xffff << GEN8_EU_DIS1_S2_SHIFT)
+
+#define GEN11_GT_SLICE_ENABLE			_MMIO(0x9138)
+#define   GEN11_GT_S_ENA_MASK			0xFF
+
+#define GEN8_EU_DISABLE2			_MMIO(0x913c)
+#define   GEN8_EU_DIS2_S2_MASK			0xff
+
+#define GEN11_GT_SUBSLICE_DISABLE		_MMIO(0x913c)
+#define GEN12_GT_GEOMETRY_DSS_ENABLE		_MMIO(0x913c)
+
+#define GEN10_EU_DISABLE3			_MMIO(0x9140)
+#define   GEN10_EU_DIS_SS_MASK			0xff
+#define GEN11_GT_VEBOX_VDBOX_DISABLE		_MMIO(0x9140)
+#define   GEN11_GT_VDBOX_DISABLE_MASK		0xff
+#define   GEN11_GT_VEBOX_DISABLE_SHIFT		16
+#define   GEN11_GT_VEBOX_DISABLE_MASK		(0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT)
+
+#define GEN12_GT_COMPUTE_DSS_ENABLE		_MMIO(0x9144)
 
 #define GEN6_UCGCTL1				_MMIO(0x9400)
-# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE		(1 << 22)
-# define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE		(1 << 16)
-# define GEN6_BLBUNIT_CLOCK_GATE_DISABLE		(1 << 5)
-# define GEN6_CSUNIT_CLOCK_GATE_DISABLE			(1 << 7)
+#define   GEN6_GAMUNIT_CLOCK_GATE_DISABLE	(1 << 22)
+#define   GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE	(1 << 16)
+#define   GEN6_BLBUNIT_CLOCK_GATE_DISABLE	(1 << 5)
+#define   GEN6_CSUNIT_CLOCK_GATE_DISABLE		(1 << 7)
 
 #define GEN6_UCGCTL2				_MMIO(0x9404)
-# define GEN6_VFUNIT_CLOCK_GATE_DISABLE			(1 << 31)
-# define GEN7_VDSUNIT_CLOCK_GATE_DISABLE		(1 << 30)
-# define GEN7_TDLUNIT_CLOCK_GATE_DISABLE		(1 << 22)
-# define GEN6_RCZUNIT_CLOCK_GATE_DISABLE		(1 << 13)
-# define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE		(1 << 12)
-# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
+#define   GEN6_VFUNIT_CLOCK_GATE_DISABLE	(1 << 31)
+#define   GEN7_VDSUNIT_CLOCK_GATE_DISABLE	(1 << 30)
+#define   GEN7_TDLUNIT_CLOCK_GATE_DISABLE	(1 << 22)
+#define   GEN6_RCZUNIT_CLOCK_GATE_DISABLE	(1 << 13)
+#define   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE	(1 << 12)
+#define   GEN6_RCCUNIT_CLOCK_GATE_DISABLE	(1 << 11)
 
 #define GEN6_UCGCTL3				_MMIO(0x9408)
-# define GEN6_OACSUNIT_CLOCK_GATE_DISABLE		(1 << 20)
+#define   GEN6_OACSUNIT_CLOCK_GATE_DISABLE	(1 << 20)
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
-#define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1 << 25)
-#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1 << 14)
+#define   GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1 << 25)
+#define   GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1 << 14)
 
 #define GEN6_RCGCTL1				_MMIO(0x9410)
 #define GEN6_RCGCTL2				_MMIO(0x9414)
+
+#define GEN6_GDRST				_MMIO(0x941c)
+#define   GEN6_GRDOM_FULL			(1 << 0)
+#define   GEN6_GRDOM_RENDER			(1 << 1)
+#define   GEN6_GRDOM_MEDIA			(1 << 2)
+#define   GEN6_GRDOM_BLT			(1 << 3)
+#define   GEN6_GRDOM_VECS			(1 << 4)
+#define   GEN9_GRDOM_GUC			(1 << 5)
+#define   GEN8_GRDOM_MEDIA2			(1 << 7)
+/* GEN11 changed all bit defs except for FULL & RENDER */
+#define   GEN11_GRDOM_FULL			GEN6_GRDOM_FULL
+#define   GEN11_GRDOM_RENDER			GEN6_GRDOM_RENDER
+#define   GEN11_GRDOM_BLT			(1 << 2)
+#define   GEN11_GRDOM_GUC			(1 << 3)
+#define   GEN11_GRDOM_MEDIA			(1 << 5)
+#define   GEN11_GRDOM_MEDIA2			(1 << 6)
+#define   GEN11_GRDOM_MEDIA3			(1 << 7)
+#define   GEN11_GRDOM_MEDIA4			(1 << 8)
+#define   GEN11_GRDOM_MEDIA5			(1 << 9)
+#define   GEN11_GRDOM_MEDIA6			(1 << 10)
+#define   GEN11_GRDOM_MEDIA7			(1 << 11)
+#define   GEN11_GRDOM_MEDIA8			(1 << 12)
+#define   GEN11_GRDOM_VECS			(1 << 13)
+#define   GEN11_GRDOM_VECS2			(1 << 14)
+#define   GEN11_GRDOM_VECS3			(1 << 15)
+#define   GEN11_GRDOM_VECS4			(1 << 16)
+#define   GEN11_GRDOM_SFC0			(1 << 17)
+#define   GEN11_GRDOM_SFC1			(1 << 18)
+#define   GEN11_GRDOM_SFC2			(1 << 19)
+#define   GEN11_GRDOM_SFC3			(1 << 20)
+#define   GEN11_VCS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << ((instance) >> 1))
+#define   GEN11_VECS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << (instance))
+
 #define GEN6_RSTCTL				_MMIO(0x9420)
 
+#define GEN7_MISCCPCTL				_MMIO(0x9424)
+#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1 << 0)
+#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1 << 2)
+#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1 << 4)
+#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE	(1 << 6)
+
 #define GEN8_UCGCTL6				_MMIO(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   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ	(1 << 28)
 
 #define UNSLCGCTL9430				_MMIO(0x9430)
 #define   MSQDUNIT_CLKGATE_DIS			REG_BIT(3)
 
-#define GEN6_GFXPAUSE				_MMIO(0xA000)
-#define GEN6_RPNSWREQ				_MMIO(0xA008)
+#define UNSLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x9434)
+#define   VFUNIT_CLKGATE_DIS			REG_BIT(20)
+#define   TSGUNIT_CLKGATE_DIS			REG_BIT(17) /* XEHPSDV */
+#define   CG3DDISCFEG_CLKGATE_DIS		REG_BIT(17) /* DG2 */
+#define   GAMEDIA_CLKGATE_DIS			REG_BIT(11)
+#define   HSUNIT_CLKGATE_DIS			REG_BIT(8)
+#define   VSUNIT_CLKGATE_DIS			REG_BIT(3)
+
+#define UNSLCGCTL9440				_MMIO(0x9440)
+#define   GAMTLBOACS_CLKGATE_DIS		REG_BIT(28)
+#define   GAMTLBVDBOX5_CLKGATE_DIS		REG_BIT(27)
+#define   GAMTLBVDBOX6_CLKGATE_DIS		REG_BIT(26)
+#define   GAMTLBVDBOX3_CLKGATE_DIS		REG_BIT(24)
+#define   GAMTLBVDBOX4_CLKGATE_DIS		REG_BIT(23)
+#define   GAMTLBVDBOX7_CLKGATE_DIS		REG_BIT(22)
+#define   GAMTLBVDBOX2_CLKGATE_DIS		REG_BIT(21)
+#define   GAMTLBVDBOX0_CLKGATE_DIS		REG_BIT(17)
+#define   GAMTLBKCR_CLKGATE_DIS			REG_BIT(16)
+#define   GAMTLBGUC_CLKGATE_DIS			REG_BIT(15)
+#define   GAMTLBBLT_CLKGATE_DIS			REG_BIT(14)
+#define   GAMTLBVDBOX1_CLKGATE_DIS		REG_BIT(6)
+
+#define UNSLCGCTL9444				_MMIO(0x9444)
+#define   GAMTLBGFXA0_CLKGATE_DIS		REG_BIT(30)
+#define   GAMTLBGFXA1_CLKGATE_DIS		REG_BIT(29)
+#define   GAMTLBCOMPA0_CLKGATE_DIS		REG_BIT(28)
+#define   GAMTLBCOMPA1_CLKGATE_DIS		REG_BIT(27)
+#define   GAMTLBCOMPB0_CLKGATE_DIS		REG_BIT(26)
+#define   GAMTLBCOMPB1_CLKGATE_DIS		REG_BIT(25)
+#define   GAMTLBCOMPC0_CLKGATE_DIS		REG_BIT(24)
+#define   GAMTLBCOMPC1_CLKGATE_DIS		REG_BIT(23)
+#define   GAMTLBCOMPD0_CLKGATE_DIS		REG_BIT(22)
+#define   GAMTLBCOMPD1_CLKGATE_DIS		REG_BIT(21)
+#define   GAMTLBMERT_CLKGATE_DIS		REG_BIT(20)
+#define   GAMTLBVEBOX3_CLKGATE_DIS		REG_BIT(19)
+#define   GAMTLBVEBOX2_CLKGATE_DIS		REG_BIT(18)
+#define   GAMTLBVEBOX1_CLKGATE_DIS		REG_BIT(17)
+#define   GAMTLBVEBOX0_CLKGATE_DIS		REG_BIT(16)
+#define   LTCDD_CLKGATE_DIS			REG_BIT(10)
+
+#define SLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x94d4)
+#define   SARBUNIT_CLKGATE_DIS			(1 << 5)
+#define   RCCUNIT_CLKGATE_DIS			(1 << 7)
+#define   MSCUNIT_CLKGATE_DIS			(1 << 10)
+#define   NODEDSS_CLKGATE_DIS			REG_BIT(12)
+#define   L3_CLKGATE_DIS			REG_BIT(16)
+#define   L3_CR2X_CLKGATE_DIS			REG_BIT(17)
+
+#define SCCGCTL94DC				_MMIO(0x94dc)
+#define   CG3DDISURB				REG_BIT(14)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2		_MMIO(0x94e4)
+#define   VSUNIT_CLKGATE_DIS_TGL		REG_BIT(19)
+#define   PSDUNIT_CLKGATE_DIS			REG_BIT(5)
+
+#define SUBSLICE_UNIT_LEVEL_CLKGATE		_MMIO(0x9524)
+#define   DSS_ROUTER_CLKGATE_DIS		REG_BIT(28)
+#define   GWUNIT_CLKGATE_DIS			REG_BIT(16)
+
+#define SUBSLICE_UNIT_LEVEL_CLKGATE2		_MMIO(0x9528)
+#define   CPSSUNIT_CLKGATE_DIS			REG_BIT(9)
+
+#define SSMCGCTL9530				_MMIO(0x9530)
+#define   RTFUNIT_CLKGATE_DIS			REG_BIT(18)
+
+#define GEN10_DFR_RATIO_EN_AND_CHICKEN		_MMIO(0x9550)
+#define   DFR_DISABLE				(1 << 9)
+
+#define INF_UNIT_LEVEL_CLKGATE			_MMIO(0x9560)
+#define   CGPSF_CLKGATE_DIS			(1 << 3)
+
+#define MICRO_BP0_0				_MMIO(0x9800)
+#define MICRO_BP0_2				_MMIO(0x9804)
+#define MICRO_BP0_1				_MMIO(0x9808)
+#define MICRO_BP1_0				_MMIO(0x980c)
+#define MICRO_BP1_2				_MMIO(0x9810)
+#define MICRO_BP1_1				_MMIO(0x9814)
+#define MICRO_BP2_0				_MMIO(0x9818)
+#define MICRO_BP2_2				_MMIO(0x981c)
+#define MICRO_BP2_1				_MMIO(0x9820)
+#define MICRO_BP3_0				_MMIO(0x9824)
+#define MICRO_BP3_2				_MMIO(0x9828)
+#define MICRO_BP3_1				_MMIO(0x982c)
+#define MICRO_BP_TRIGGER			_MMIO(0x9830)
+#define MICRO_BP3_COUNT_STATUS01		_MMIO(0x9834)
+#define MICRO_BP3_COUNT_STATUS23		_MMIO(0x9838)
+#define MICRO_BP_FIRED_ARMED			_MMIO(0x983c)
+
+#define GEN6_GFXPAUSE				_MMIO(0xa000)
+#define GEN6_RPNSWREQ				_MMIO(0xa008)
 #define   GEN6_TURBO_DISABLE			(1 << 31)
 #define   GEN6_FREQUENCY(x)			((x) << 25)
 #define   HSW_FREQUENCY(x)			((x) << 24)
@@ -1228,8 +726,7 @@ enum {
 #define   GEN9_SW_REQ_UNSLICE_RATIO_SHIFT	23
 #define   GEN9_IGNORE_SLICE_RATIO		(0 << 0)
 
-#define GEN6_RC_VIDEO_FREQ			_MMIO(0xA00C)
-#define GEN6_RC_CONTROL				_MMIO(0xA090)
+#define GEN6_RC_VIDEO_FREQ			_MMIO(0xa00c)
 #define   GEN6_RC_CTL_RC6pp_ENABLE		(1 << 16)
 #define   GEN6_RC_CTL_RC6p_ENABLE		(1 << 17)
 #define   GEN6_RC_CTL_RC6_ENABLE		(1 << 18)
@@ -1239,16 +736,16 @@ enum {
 #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)
-#define GEN6_RP_DOWN_TIMEOUT			_MMIO(0xA010)
-#define GEN6_RP_INTERRUPT_LIMITS		_MMIO(0xA014)
-#define GEN6_RPSTAT1				_MMIO(0xA01C)
+#define GEN6_RP_DOWN_TIMEOUT			_MMIO(0xa010)
+#define GEN6_RP_INTERRUPT_LIMITS		_MMIO(0xa014)
+#define GEN6_RPSTAT1				_MMIO(0xa01c)
 #define   GEN6_CAGF_SHIFT			8
 #define   HSW_CAGF_SHIFT			7
 #define   GEN9_CAGF_SHIFT			23
 #define   GEN6_CAGF_MASK			(0x7f << GEN6_CAGF_SHIFT)
 #define   HSW_CAGF_MASK				(0x7f << HSW_CAGF_SHIFT)
 #define   GEN9_CAGF_MASK			(0x1ff << GEN9_CAGF_SHIFT)
-#define GEN6_RP_CONTROL				_MMIO(0xA024)
+#define GEN6_RP_CONTROL				_MMIO(0xa024)
 #define   GEN6_RP_MEDIA_TURBO			(1 << 11)
 #define   GEN6_RP_MEDIA_MODE_MASK		(3 << 9)
 #define   GEN6_RP_MEDIA_HW_TURBO_MODE		(3 << 9)
@@ -1265,193 +762,294 @@ enum {
 #define   GEN6_RPSWCTL_SHIFT			9
 #define   GEN9_RPSWCTL_ENABLE			(0x2 << GEN6_RPSWCTL_SHIFT)
 #define   GEN9_RPSWCTL_DISABLE			(0x0 << GEN6_RPSWCTL_SHIFT)
-#define GEN6_RP_UP_THRESHOLD			_MMIO(0xA02C)
-#define GEN6_RP_DOWN_THRESHOLD			_MMIO(0xA030)
-#define GEN6_RP_CUR_UP_EI			_MMIO(0xA050)
+#define GEN6_RP_UP_THRESHOLD			_MMIO(0xa02c)
+#define GEN6_RP_DOWN_THRESHOLD			_MMIO(0xa030)
+#define GEN6_RP_CUR_UP_EI			_MMIO(0xa050)
 #define   GEN6_RP_EI_MASK			0xffffff
 #define   GEN6_CURICONT_MASK			GEN6_RP_EI_MASK
-#define GEN6_RP_CUR_UP				_MMIO(0xA054)
+#define GEN6_RP_CUR_UP				_MMIO(0xa054)
 #define   GEN6_CURBSYTAVG_MASK			GEN6_RP_EI_MASK
-#define GEN6_RP_PREV_UP				_MMIO(0xA058)
-#define GEN6_RP_CUR_DOWN_EI			_MMIO(0xA05C)
+#define GEN6_RP_PREV_UP				_MMIO(0xa058)
+#define GEN6_RP_CUR_DOWN_EI			_MMIO(0xa05c)
 #define   GEN6_CURIAVG_MASK			GEN6_RP_EI_MASK
-#define GEN6_RP_CUR_DOWN			_MMIO(0xA060)
-#define GEN6_RP_PREV_DOWN			_MMIO(0xA064)
-#define GEN6_RP_UP_EI				_MMIO(0xA068)
-#define GEN6_RP_DOWN_EI				_MMIO(0xA06C)
-#define GEN6_RP_IDLE_HYSTERSIS			_MMIO(0xA070)
-#define GEN6_RPDEUHWTC				_MMIO(0xA080)
-#define GEN6_RPDEUC				_MMIO(0xA084)
-#define GEN6_RPDEUCSW				_MMIO(0xA088)
-#define GEN6_RC_STATE				_MMIO(0xA094)
+#define GEN6_RP_CUR_DOWN			_MMIO(0xa060)
+#define GEN6_RP_PREV_DOWN			_MMIO(0xa064)
+#define GEN6_RP_UP_EI				_MMIO(0xa068)
+#define GEN6_RP_DOWN_EI				_MMIO(0xa06c)
+#define GEN6_RP_IDLE_HYSTERSIS			_MMIO(0xa070)
+#define GEN6_RPDEUHWTC				_MMIO(0xa080)
+#define GEN6_RPDEUC				_MMIO(0xa084)
+#define GEN6_RPDEUCSW				_MMIO(0xa088)
+#define GEN6_RC_CONTROL				_MMIO(0xa090)
+#define GEN6_RC_STATE				_MMIO(0xa094)
 #define   RC_SW_TARGET_STATE_SHIFT		16
 #define   RC_SW_TARGET_STATE_MASK		(7 << RC_SW_TARGET_STATE_SHIFT)
-#define GEN6_RC1_WAKE_RATE_LIMIT		_MMIO(0xA098)
-#define GEN6_RC6_WAKE_RATE_LIMIT		_MMIO(0xA09C)
-#define GEN6_RC6pp_WAKE_RATE_LIMIT		_MMIO(0xA0A0)
-#define GEN10_MEDIA_WAKE_RATE_LIMIT		_MMIO(0xA0A0)
-#define GEN6_RC_EVALUATION_INTERVAL		_MMIO(0xA0A8)
-#define GEN6_RC_IDLE_HYSTERSIS			_MMIO(0xA0AC)
-#define GEN6_RC_SLEEP				_MMIO(0xA0B0)
-#define GEN6_RCUBMABDTMR			_MMIO(0xA0B0)
-#define GEN6_RC1e_THRESHOLD			_MMIO(0xA0B4)
-#define GEN6_RC6_THRESHOLD			_MMIO(0xA0B8)
-#define GEN6_RC6p_THRESHOLD			_MMIO(0xA0BC)
-#define VLV_RCEDATA				_MMIO(0xA0BC)
-#define GEN6_RC6pp_THRESHOLD			_MMIO(0xA0C0)
-#define GEN6_PMINTRMSK				_MMIO(0xA168)
+#define GEN6_RC1_WAKE_RATE_LIMIT		_MMIO(0xa098)
+#define GEN6_RC6_WAKE_RATE_LIMIT		_MMIO(0xa09c)
+#define GEN6_RC6pp_WAKE_RATE_LIMIT		_MMIO(0xa0a0)
+#define GEN10_MEDIA_WAKE_RATE_LIMIT		_MMIO(0xa0a0)
+#define GEN6_RC_EVALUATION_INTERVAL		_MMIO(0xa0a8)
+#define GEN6_RC_IDLE_HYSTERSIS			_MMIO(0xa0ac)
+#define GEN6_RC_SLEEP				_MMIO(0xa0b0)
+#define GEN6_RCUBMABDTMR			_MMIO(0xa0b0)
+#define GEN6_RC1e_THRESHOLD			_MMIO(0xa0b4)
+#define GEN6_RC6_THRESHOLD			_MMIO(0xa0b8)
+#define GEN6_RC6p_THRESHOLD			_MMIO(0xa0bc)
+#define VLV_RCEDATA				_MMIO(0xa0bc)
+#define GEN6_RC6pp_THRESHOLD			_MMIO(0xa0c0)
+#define GEN9_MEDIA_PG_IDLE_HYSTERESIS		_MMIO(0xa0c4)
+#define GEN9_RENDER_PG_IDLE_HYSTERESIS		_MMIO(0xa0c8)
+
+#define GEN6_PMINTRMSK				_MMIO(0xa168)
 #define   GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC	(1 << 31)
 #define   ARAT_EXPIRED_INTRMSK			(1 << 9)
-#define GEN8_MISC_CTRL0				_MMIO(0xA180)
-#define VLV_PWRDWNUPCTL				_MMIO(0xA294)
-#define GEN9_MEDIA_PG_IDLE_HYSTERESIS		_MMIO(0xA0C4)
-#define GEN9_RENDER_PG_IDLE_HYSTERESIS		_MMIO(0xA0C8)
-#define GEN9_PG_ENABLE				_MMIO(0xA210)
+
+#define GEN8_MISC_CTRL0				_MMIO(0xa180)
+
+#define ECOBUS					_MMIO(0xa180)
+#define    FORCEWAKE_MT_ENABLE			(1 << 5)
+
+#define FORCEWAKE_MT				_MMIO(0xa188) /* multi-threaded */
+#define FORCEWAKE_GT_GEN9			_MMIO(0xa188)
+#define FORCEWAKE				_MMIO(0xa18c)
+
+#define VLV_SPAREG2H				_MMIO(0xa194)
+
+#define GEN9_PG_ENABLE				_MMIO(0xa210)
 #define   GEN9_RENDER_PG_ENABLE			REG_BIT(0)
 #define   GEN9_MEDIA_PG_ENABLE			REG_BIT(1)
 #define   GEN11_MEDIA_SAMPLER_PG_ENABLE		REG_BIT(2)
 #define   VDN_HCP_POWERGATE_ENABLE(n)		REG_BIT(3 + 2 * (n))
 #define   VDN_MFX_POWERGATE_ENABLE(n)		REG_BIT(4 + 2 * (n))
-#define GEN8_PUSHBUS_CONTROL			_MMIO(0xA248)
-#define GEN8_PUSHBUS_ENABLE			_MMIO(0xA250)
-#define GEN8_PUSHBUS_SHIFT			_MMIO(0xA25C)
 
-#define GEN6_PMISR				_MMIO(0x44020)
-#define GEN6_PMIMR				_MMIO(0x44024) /* rps_lock */
-#define GEN6_PMIIR				_MMIO(0x44028)
-#define GEN6_PMIER				_MMIO(0x4402C)
-#define  GEN6_PM_MBOX_EVENT			(1 << 25)
-#define  GEN6_PM_THERMAL_EVENT			(1 << 24)
+#define GEN8_PUSHBUS_CONTROL			_MMIO(0xa248)
+#define GEN8_PUSHBUS_ENABLE			_MMIO(0xa250)
+#define GEN8_PUSHBUS_SHIFT			_MMIO(0xa25c)
 
-/*
- * For Gen11 these are in the upper word of the GPM_WGBOXPERF
- * registers. Shifting is handled on accessing the imr and ier.
- */
-#define  GEN6_PM_RP_DOWN_TIMEOUT		(1 << 6)
-#define  GEN6_PM_RP_UP_THRESHOLD		(1 << 5)
-#define  GEN6_PM_RP_DOWN_THRESHOLD		(1 << 4)
-#define  GEN6_PM_RP_UP_EI_EXPIRED		(1 << 2)
-#define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1 << 1)
-#define  GEN6_PM_RPS_EVENTS			(GEN6_PM_RP_UP_EI_EXPIRED   | \
-						 GEN6_PM_RP_UP_THRESHOLD    | \
-						 GEN6_PM_RP_DOWN_EI_EXPIRED | \
-						 GEN6_PM_RP_DOWN_THRESHOLD  | \
-						 GEN6_PM_RP_DOWN_TIMEOUT)
+/* GPM unit config (Gen9+) */
+#define CTC_MODE				_MMIO(0xa26c)
+#define   CTC_SOURCE_PARAMETER_MASK		1
+#define   CTC_SOURCE_CRYSTAL_CLOCK		0
+#define   CTC_SOURCE_DIVIDE_LOGIC		1
+#define   CTC_SHIFT_PARAMETER_SHIFT		1
+#define   CTC_SHIFT_PARAMETER_MASK		(0x3 << CTC_SHIFT_PARAMETER_SHIFT)
 
-#define GEN7_GT_SCRATCH(i)			_MMIO(0x4F100 + (i) * 4)
-#define GEN7_GT_SCRATCH_REG_NUM			8
+#define FORCEWAKE_MEDIA_GEN9			_MMIO(0xa270)
+#define FORCEWAKE_RENDER_GEN9			_MMIO(0xa278)
 
-#define VLV_GTLC_SURVIVABILITY_REG              _MMIO(0x130098)
-#define VLV_GFX_CLK_STATUS_BIT			(1 << 3)
-#define VLV_GFX_CLK_FORCE_ON_BIT		(1 << 2)
+#define VLV_PWRDWNUPCTL				_MMIO(0xa294)
 
-#define GEN6_GT_GFX_RC6_LOCKED			_MMIO(0x138104)
-#define VLV_COUNTER_CONTROL			_MMIO(0x138104)
-#define   VLV_COUNT_RANGE_HIGH			(1 << 15)
-#define   VLV_MEDIA_RC0_COUNT_EN		(1 << 5)
-#define   VLV_RENDER_RC0_COUNT_EN		(1 << 4)
-#define   VLV_MEDIA_RC6_COUNT_EN		(1 << 1)
-#define   VLV_RENDER_RC6_COUNT_EN		(1 << 0)
-#define GEN6_GT_GFX_RC6				_MMIO(0x138108)
-#define VLV_GT_RENDER_RC6			_MMIO(0x138108)
-#define VLV_GT_MEDIA_RC6			_MMIO(0x13810C)
+#define GEN9_PWRGT_DOMAIN_STATUS		_MMIO(0xa2a0)
+#define   GEN9_PWRGT_MEDIA_STATUS_MASK		(1 << 0)
+#define   GEN9_PWRGT_RENDER_STATUS_MASK		(1 << 1)
 
-#define GEN6_GT_GFX_RC6p			_MMIO(0x13810C)
-#define GEN6_GT_GFX_RC6pp			_MMIO(0x138110)
-#define VLV_RENDER_C0_COUNT			_MMIO(0x138118)
-#define VLV_MEDIA_C0_COUNT			_MMIO(0x13811C)
-
-#define GEN6_GT_CORE_STATUS		_MMIO(0x138060)
-#define   GEN6_CORE_CPD_STATE_MASK	(7 << 4)
-#define   GEN6_RCn_MASK			7
-#define   GEN6_RC0			0
-#define   GEN6_RC3			2
-#define   GEN6_RC6			3
-#define   GEN6_RC7			4
-
-#define GEN8_GT_SLICE_INFO		_MMIO(0x138064)
-#define   GEN8_LSLICESTAT_MASK		0x7
-
-#define CHV_POWER_SS0_SIG1		_MMIO(0xa720)
-#define CHV_POWER_SS1_SIG1		_MMIO(0xa728)
-#define   CHV_SS_PG_ENABLE		(1 << 1)
-#define   CHV_EU08_PG_ENABLE		(1 << 9)
-#define   CHV_EU19_PG_ENABLE		(1 << 17)
-#define   CHV_EU210_PG_ENABLE		(1 << 25)
-
-#define CHV_POWER_SS0_SIG2		_MMIO(0xa724)
-#define CHV_POWER_SS1_SIG2		_MMIO(0xa72c)
-#define   CHV_EU311_PG_ENABLE		(1 << 1)
-
-#define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice) * 0x4)
-#define GEN10_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + ((slice) / 3) * 0x34 + \
-					      ((slice) % 3) * 0x4)
-#define   GEN9_PGCTL_SLICE_ACK		(1 << 0)
-#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice) * 2))
-#define   GEN10_PGCTL_VALID_SS_MASK(slice) ((slice) == 0 ? 0x7F : 0x1F)
-
-#define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice) * 0x8)
-#define GEN10_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + ((slice) / 3) * 0x30 + \
-					      ((slice) % 3) * 0x8)
-#define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice) * 0x8)
-#define GEN10_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + ((slice) / 3) * 0x30 + \
-					      ((slice) % 3) * 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)
-#define   GEN9_PGCTL_SSA_EU311_ACK	(1 << 6)
-#define   GEN9_PGCTL_SSB_EU08_ACK	(1 << 8)
-#define   GEN9_PGCTL_SSB_EU19_ACK	(1 << 10)
-#define   GEN9_PGCTL_SSB_EU210_ACK	(1 << 12)
-#define   GEN9_PGCTL_SSB_EU311_ACK	(1 << 14)
+#define MISC_STATUS0				_MMIO(0xa500)
+#define MISC_STATUS1				_MMIO(0xa504)
 
-#define GEN7_MISCCPCTL				_MMIO(0x9424)
-#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1 << 0)
-#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1 << 2)
-#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1 << 4)
-#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1 << 6)
+#define FORCEWAKE_MEDIA_VDBOX_GEN11(n)		_MMIO(0xa540 + (n) * 4)
+#define FORCEWAKE_MEDIA_VEBOX_GEN11(n)		_MMIO(0xa560 + (n) * 4)
+
+#define CHV_POWER_SS0_SIG1			_MMIO(0xa720)
+#define CHV_POWER_SS0_SIG2			_MMIO(0xa724)
+#define CHV_POWER_SS1_SIG1			_MMIO(0xa728)
+#define   CHV_SS_PG_ENABLE			(1 << 1)
+#define   CHV_EU08_PG_ENABLE			(1 << 9)
+#define   CHV_EU19_PG_ENABLE			(1 << 17)
+#define   CHV_EU210_PG_ENABLE			(1 << 25)
+#define CHV_POWER_SS1_SIG2			_MMIO(0xa72c)
+#define   CHV_EU311_PG_ENABLE			(1 << 1)
 
-#define GEN8_GARBCNTL				_MMIO(0xB004)
+#define GEN7_SARCHKMD				_MMIO(0xb000)
+#define   GEN7_DISABLE_DEMAND_PREFETCH		(1 << 31)
+#define   GEN7_DISABLE_SAMPLER_PREFETCH		(1 << 30)
+
+#define GEN8_GARBCNTL				_MMIO(0xb004)
 #define   GEN9_GAPS_TSV_CREDIT_DISABLE		(1 << 7)
 #define   GEN11_ARBITRATION_PRIO_ORDER_MASK	(0x3f << 22)
 #define   GEN11_HASH_CTRL_EXCL_MASK		(0x7f << 0)
 #define   GEN11_HASH_CTRL_EXCL_BIT0		(1 << 0)
 
-#define GEN11_GLBLINVL				_MMIO(0xB404)
-#define   GEN11_BANK_HASH_ADDR_EXCL_MASK	(0x7f << 5)
-#define   GEN11_BANK_HASH_ADDR_EXCL_BIT0	(1 << 5)
+#define GEN9_SCRATCH_LNCF1			_MMIO(0xb008)
+#define   GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE	REG_BIT(0)
 
-#define GEN10_DFR_RATIO_EN_AND_CHICKEN	_MMIO(0x9550)
-#define   DFR_DISABLE			(1 << 9)
+#define GEN7_L3SQCREG1				_MMIO(0xb010)
+#define   VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
 
-#define GEN11_GACB_PERF_CTRL			_MMIO(0x4B80)
-#define   GEN11_HASH_CTRL_MASK			(0x3 << 12 | 0xf << 0)
-#define   GEN11_HASH_CTRL_BIT0			(1 << 0)
-#define   GEN11_HASH_CTRL_BIT4			(1 << 12)
+#define GEN7_L3CNTLREG1				_MMIO(0xb01c)
+#define   GEN7_WA_FOR_GEN7_L3_CONTROL		0x3C47FF8C
+#define   GEN7_L3AGDIS				(1 << 19)
+#define GEN7_L3CNTLREG2				_MMIO(0xb020)
+
+/* MOCS (Memory Object Control State) registers */
+#define GEN9_LNCFCMOCS(i)			_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
+#define GEN9_LNCFCMOCS_REG_COUNT		32
+
+#define GEN7_L3CNTLREG3				_MMIO(0xb024)
+
+#define GEN7_L3_CHICKEN_MODE_REGISTER		_MMIO(0xb030)
+#define   GEN7_WA_L3_CHICKEN_MODE		0x20000000
+
+#define GEN7_L3SQCREG4				_MMIO(0xb034)
+#define   L3SQ_URB_READ_CAM_MATCH_DISABLE	(1 << 27)
+
+#define HSW_SCRATCH1				_MMIO(0xb038)
+#define   HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1 << 27)
+
+#define GEN7_L3LOG(slice, i)			_MMIO(0xb070 + (slice) * 0x200 + (i) * 4)
+#define   GEN7_L3LOG_SIZE			0x80
 
-#define GEN11_LSN_UNSLCVC				_MMIO(0xB43C)
+#define GEN10_SCRATCH_LNCF2			_MMIO(0xb0a0)
+#define   PMFLUSHDONE_LNICRSDROP		(1 << 20)
+#define   PMFLUSH_GAPL3UNBLOCK			(1 << 21)
+#define   PMFLUSHDONE_LNEBLK			(1 << 22)
+
+#define XEHP_L3NODEARBCFG			_MMIO(0xb0b4)
+#define   XEHP_LNESPARE				REG_BIT(19)
+
+#define GEN8_L3SQCREG1				_MMIO(0xb100)
+/*
+ * Note that on CHV the following has an off-by-one error wrt. to BSpec.
+ * Using the formula in BSpec leads to a hang, while the formula here works
+ * fine and matches the formulas for all other platforms. A BSpec change
+ * request has been filed to clarify this.
+ */
+#define   L3_GENERAL_PRIO_CREDITS(x)		(((x) >> 1) << 19)
+#define   L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
+#define   L3_PRIO_CREDITS_MASK			((0x1f << 19) | (0x1f << 14))
+
+#define GEN10_L3_CHICKEN_MODE_REGISTER		_MMIO(0xb114)
+#define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
+
+#define GEN8_L3SQCREG4				_MMIO(0xb118)
+#define   GEN11_LQSC_CLEAN_EVICT_DISABLE	(1 << 6)
+#define   GEN8_LQSC_RO_PERF_DIS			(1 << 27)
+#define   GEN8_LQSC_FLUSH_COHERENT_LINES	(1 << 21)
+#define   GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE	REG_BIT(22)
+
+#define GEN9_SCRATCH1				_MMIO(0xb11c)
+#define   EVICTION_PERF_FIX_ENABLE		REG_BIT(8)
+
+#define BDW_SCRATCH1				_MMIO(0xb11c)
+#define   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
+
+#define GEN11_SCRATCH2				_MMIO(0xb140)
+#define   GEN11_COHERENT_PARTIAL_WRITE_MERGE_ENABLE	(1 << 19)
+
+#define GEN11_L3SQCREG5				_MMIO(0xb158)
+#define   L3_PWM_TIMER_INIT_VAL_MASK		REG_GENMASK(9, 0)
+
+#define MLTICTXCTL				_MMIO(0xb170)
+#define   TDONRENDER				REG_BIT(2)
+
+#define XEHP_L3SCQREG7				_MMIO(0xb188)
+#define   BLEND_FILL_CACHING_OPT_DIS		REG_BIT(3)
+
+#define L3SQCREG1_CCS0				_MMIO(0xb200)
+#define   FLUSHALLNONCOH			REG_BIT(5)
+
+#define GEN11_GLBLINVL				_MMIO(0xb404)
+#define   GEN11_BANK_HASH_ADDR_EXCL_MASK	(0x7f << 5)
+#define   GEN11_BANK_HASH_ADDR_EXCL_BIT0	(1 << 5)
+
+#define GEN11_LSN_UNSLCVC			_MMIO(0xb43c)
 #define   GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC	(1 << 9)
 #define   GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC	(1 << 7)
 
-#define GEN10_SAMPLER_MODE		_MMIO(0xE18C)
-#define   ENABLE_SMALLPL			REG_BIT(15)
-#define   GEN11_SAMPLER_ENABLE_HEADLESS_MSG	REG_BIT(5)
+#define __GEN9_RCS0_MOCS0			0xc800
+#define GEN9_GFX_MOCS(i)			_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS0_MOCS0			0xc900
+#define GEN9_MFX0_MOCS(i)			_MMIO(__GEN9_VCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS1_MOCS0			0xca00
+#define GEN9_MFX1_MOCS(i)			_MMIO(__GEN9_VCS1_MOCS0 + (i) * 4)
+#define __GEN9_VECS0_MOCS0			0xcb00
+#define GEN9_VEBOX_MOCS(i)			_MMIO(__GEN9_VECS0_MOCS0 + (i) * 4)
+#define __GEN9_BCS0_MOCS0			0xcc00
+#define GEN9_BLT_MOCS(i)			_MMIO(__GEN9_BCS0_MOCS0 + (i) * 4)
+
+#define GEN12_FAULT_TLB_DATA0			_MMIO(0xceb8)
+#define GEN12_FAULT_TLB_DATA1			_MMIO(0xcebc)
+#define   FAULT_VA_HIGH_BITS			(0xf << 0)
+#define   FAULT_GTT_SEL				(1 << 4)
+
+#define GEN12_RING_FAULT_REG			_MMIO(0xcec4)
+#define   GEN8_RING_FAULT_ENGINE_ID(x)		(((x) >> 12) & 0x7)
+#define   RING_FAULT_GTTSEL_MASK		(1 << 11)
+#define   RING_FAULT_SRCID(x)			(((x) >> 3) & 0xff)
+#define   RING_FAULT_FAULT_TYPE(x)		(((x) >> 1) & 0x3)
+#define   RING_FAULT_VALID			(1 << 0)
+
+#define GEN12_GFX_TLB_INV_CR			_MMIO(0xced8)
+#define GEN12_VD_TLB_INV_CR			_MMIO(0xcedc)
+#define GEN12_VE_TLB_INV_CR			_MMIO(0xcee0)
+#define GEN12_BLT_TLB_INV_CR			_MMIO(0xcee4)
+
+#define GEN12_MERT_MOD_CTRL			_MMIO(0xcf28)
+#define RENDER_MOD_CTRL				_MMIO(0xcf2c)
+#define COMP_MOD_CTRL				_MMIO(0xcf30)
+#define VDBX_MOD_CTRL				_MMIO(0xcf34)
+#define VEBX_MOD_CTRL				_MMIO(0xcf38)
+#define   FORCE_MISS_FTLB			REG_BIT(3)
+
+#define GEN12_GAMSTLB_CTRL			_MMIO(0xcf4c)
+#define   CONTROL_BLOCK_CLKGATE_DIS		REG_BIT(12)
+#define   EGRESS_BLOCK_CLKGATE_DIS		REG_BIT(11)
+#define   TAG_BLOCK_CLKGATE_DIS			REG_BIT(7)
+
+#define GEN12_GAMCNTRL_CTRL			_MMIO(0xcf54)
+#define   INVALIDATION_BROADCAST_MODE_DIS	REG_BIT(12)
+#define   GLOBAL_INVALIDATION_MODE		REG_BIT(2)
 
-#define GEN7_L3LOG(slice, i)		_MMIO(0xB070 + (slice) * 0x200 + (i) * 4)
-#define GEN7_L3LOG_SIZE			0x80
+#define GEN12_GAM_DONE				_MMIO(0xcf68)
 
-#define GEN7_HALF_SLICE_CHICKEN1	_MMIO(0xe100) /* IVB GT1 + VLV */
-#define GEN7_HALF_SLICE_CHICKEN1_GT2	_MMIO(0xf100)
+#define GEN7_HALF_SLICE_CHICKEN1		_MMIO(0xe100) /* IVB GT1 + VLV */
 #define   GEN7_MAX_PS_THREAD_DEP		(8 << 12)
 #define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1 << 10)
 #define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1 << 4)
 #define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1 << 3)
 
-#define GEN9_HALF_SLICE_CHICKEN5	_MMIO(0xe188)
-#define   GEN9_DG_MIRROR_FIX_ENABLE	(1 << 5)
-#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1 << 3)
+#define GEN7_SAMPLER_INSTDONE			_MMIO(0xe160)
+#define GEN7_ROW_INSTDONE			_MMIO(0xe164)
+
+#define HALF_SLICE_CHICKEN2			_MMIO(0xe180)
+#define   GEN8_ST_PO_DISABLE			(1 << 13)
+
+#define HALF_SLICE_CHICKEN3			_MMIO(0xe184)
+#define   HSW_SAMPLE_C_PERFORMANCE		(1 << 9)
+#define   GEN8_CENTROID_PIXEL_OPT_DIS		(1 << 8)
+#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
+#define   GEN8_SAMPLER_POWER_BYPASS_DIS		(1 << 1)
+
+#define GEN9_HALF_SLICE_CHICKEN5		_MMIO(0xe188)
+#define   GEN9_DG_MIRROR_FIX_ENABLE		(1 << 5)
+#define   GEN9_CCS_TLB_PREFETCH_ENABLE		(1 << 3)
+
+#define GEN10_SAMPLER_MODE			_MMIO(0xe18c)
+#define   ENABLE_SMALLPL			REG_BIT(15)
+#define   GEN11_SAMPLER_ENABLE_HEADLESS_MSG	REG_BIT(5)
+
+#define GEN9_HALF_SLICE_CHICKEN7		_MMIO(0xe194)
+#define   DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA	REG_BIT(15)
+#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	REG_BIT(8)
+#define   GEN9_ENABLE_YV12_BUGFIX		REG_BIT(4)
+#define   GEN9_ENABLE_GPGPU_PREEMPTION		REG_BIT(2)
+
+#define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
+#define   ENABLE_PREFETCH_INTO_IC		REG_BIT(3)
+#define   FLOAT_BLEND_OPTIMIZATION_ENABLE	REG_BIT(4)
+
+#define EU_PERF_CNTL0				_MMIO(0xe458)
+#define EU_PERF_CNTL4				_MMIO(0xe45c)
+
+#define GEN9_ROW_CHICKEN4			_MMIO(0xe48c)
+#define   GEN12_DISABLE_GRF_CLEAR		REG_BIT(13)
+#define   GEN12_DISABLE_TDL_PUSH		REG_BIT(9)
+#define   GEN11_DIS_PICK_2ND_EU			REG_BIT(7)
+#define   GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX	REG_BIT(4)
+
+#define HSW_ROW_CHICKEN3			_MMIO(0xe49c)
+#define   HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE	(1 << 6)
 
-#define GEN8_ROW_CHICKEN		_MMIO(0xe4f0)
+#define GEN8_ROW_CHICKEN			_MMIO(0xe4f0)
 #define   FLOW_CONTROL_ENABLE			REG_BIT(15)
 #define   UGM_BACKUP_MODE			REG_BIT(13)
 #define   MDQ_ARBITRATION_MODE			REG_BIT(12)
@@ -1466,6 +1064,20 @@ enum {
 #define   GEN12_ENABLE_LARGE_GRF_MODE		REG_BIT(12)
 #define   GEN12_PUSH_CONST_DEREF_HOLD_DIS	REG_BIT(8)
 
+#define RT_CTRL					_MMIO(0xe530)
+#define   DIS_NULL_QUERY			REG_BIT(10)
+
+#define EU_PERF_CNTL1				_MMIO(0xe558)
+#define EU_PERF_CNTL5				_MMIO(0xe55c)
+
+#define GEN12_HDC_CHICKEN0			_MMIO(0xe5f0)
+#define   LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK	REG_GENMASK(13, 11)
+#define ICL_HDC_MODE				_MMIO(0xe5f4)
+
+#define EU_PERF_CNTL2				_MMIO(0xe658)
+#define EU_PERF_CNTL6				_MMIO(0xe65c)
+#define EU_PERF_CNTL3				_MMIO(0xe758)
+
 #define LSC_CHICKEN_BIT_0			_MMIO(0xe7c8)
 #define   FORCE_1_SUB_MESSAGE_PER_FRAGMENT	REG_BIT(15)
 #define LSC_CHICKEN_BIT_0_UDW			_MMIO(0xe7c8 + 4)
@@ -1475,80 +1087,436 @@ enum {
 #define   MAXREQS_PER_BANK			REG_GENMASK(39 - 32, 37 - 32)
 #define   DISABLE_128B_EVICTION_COMMAND_UDW	REG_BIT(36 - 32)
 
-#define GEN7_ROW_CHICKEN2_GT2		_MMIO(0xf4f4)
-#define   DOP_CLOCK_GATING_DISABLE	(1 << 0)
-#define   PUSH_CONSTANT_DEREF_DISABLE	(1 << 8)
-#define   GEN11_TDL_CLOCK_GATING_FIX_DISABLE	(1 << 1)
+#define SARB_CHICKEN1				_MMIO(0xe90c)
+#define   COMP_CKN_IN				REG_GENMASK(30, 29)
 
-#define GEN9_ROW_CHICKEN4				_MMIO(0xe48c)
-#define   GEN12_DISABLE_GRF_CLEAR			REG_BIT(13)
-#define   GEN12_DISABLE_TDL_PUSH			REG_BIT(9)
-#define   GEN11_DIS_PICK_2ND_EU				REG_BIT(7)
-#define   GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX	REG_BIT(4)
+#define GEN7_HALF_SLICE_CHICKEN1_GT2		_MMIO(0xf100)
 
-#define HSW_ROW_CHICKEN3		_MMIO(0xe49c)
-#define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
+#define GEN7_ROW_CHICKEN2_GT2			_MMIO(0xf4f4)
+#define   DOP_CLOCK_GATING_DISABLE		(1 << 0)
+#define   PUSH_CONSTANT_DEREF_DISABLE		(1 << 8)
+#define   GEN11_TDL_CLOCK_GATING_FIX_DISABLE	(1 << 1)
 
-#define HALF_SLICE_CHICKEN2		_MMIO(0xe180)
-#define   GEN8_ST_PO_DISABLE		(1 << 13)
+#define __GEN11_VCS2_MOCS0			0x10000
+#define GEN11_MFX2_MOCS(i)			_MMIO(__GEN11_VCS2_MOCS0 + (i) * 4)
+
+#define CRSTANDVID				_MMIO(0x11100)
+#define PXVFREQ(fstart)				_MMIO(0x11110 + (fstart) * 4)  /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */
+#define   PXVFREQ_PX_MASK			0x7f000000
+#define   PXVFREQ_PX_SHIFT			24
+#define VIDFREQ_BASE				_MMIO(0x11110)
+#define VIDFREQ1				_MMIO(0x11110) /* VIDFREQ1-4 (0x1111c) (Cantiga) */
+#define VIDFREQ2				_MMIO(0x11114)
+#define VIDFREQ3				_MMIO(0x11118)
+#define VIDFREQ4				_MMIO(0x1111c)
+#define   VIDFREQ_P0_MASK			0x1f000000
+#define   VIDFREQ_P0_SHIFT			24
+#define   VIDFREQ_P0_CSCLK_MASK			0x00f00000
+#define   VIDFREQ_P0_CSCLK_SHIFT		20
+#define   VIDFREQ_P0_CRCLK_MASK			0x000f0000
+#define   VIDFREQ_P0_CRCLK_SHIFT		16
+#define   VIDFREQ_P1_MASK			0x00001f00
+#define   VIDFREQ_P1_SHIFT			8
+#define   VIDFREQ_P1_CSCLK_MASK			0x000000f0
+#define   VIDFREQ_P1_CSCLK_SHIFT		4
+#define   VIDFREQ_P1_CRCLK_MASK			0x0000000f
+#define INTTOEXT_BASE				_MMIO(0x11120) /* INTTOEXT1-8 (0x1113c) */
+#define   INTTOEXT_MAP3_SHIFT			24
+#define   INTTOEXT_MAP3_MASK			(0x1f << INTTOEXT_MAP3_SHIFT)
+#define   INTTOEXT_MAP2_SHIFT			16
+#define   INTTOEXT_MAP2_MASK			(0x1f << INTTOEXT_MAP2_SHIFT)
+#define   INTTOEXT_MAP1_SHIFT			8
+#define   INTTOEXT_MAP1_MASK			(0x1f << INTTOEXT_MAP1_SHIFT)
+#define   INTTOEXT_MAP0_SHIFT			0
+#define   INTTOEXT_MAP0_MASK			(0x1f << INTTOEXT_MAP0_SHIFT)
+#define MEMSWCTL				_MMIO(0x11170) /* Ironlake only */
+#define   MEMCTL_CMD_MASK			0xe000
+#define   MEMCTL_CMD_SHIFT			13
+#define   MEMCTL_CMD_RCLK_OFF			0
+#define   MEMCTL_CMD_RCLK_ON			1
+#define   MEMCTL_CMD_CHFREQ			2
+#define   MEMCTL_CMD_CHVID			3
+#define   MEMCTL_CMD_VMMOFF			4
+#define   MEMCTL_CMD_VMMON			5
+#define   MEMCTL_CMD_STS			(1 << 12) /* write 1 triggers command, clears
+							     when command complete */
+#define   MEMCTL_FREQ_MASK			0x0f00 /* jitter, from 0-15 */
+#define   MEMCTL_FREQ_SHIFT			8
+#define   MEMCTL_SFCAVM				(1 << 7)
+#define   MEMCTL_TGT_VID_MASK			0x007f
+#define MEMIHYST				_MMIO(0x1117c)
+#define MEMINTREN				_MMIO(0x11180) /* 16 bits */
+#define   MEMINT_RSEXIT_EN			(1 << 8)
+#define   MEMINT_CX_SUPR_EN			(1 << 7)
+#define   MEMINT_CONT_BUSY_EN			(1 << 6)
+#define   MEMINT_AVG_BUSY_EN			(1 << 5)
+#define   MEMINT_EVAL_CHG_EN			(1 << 4)
+#define   MEMINT_MON_IDLE_EN			(1 << 3)
+#define   MEMINT_UP_EVAL_EN			(1 << 2)
+#define   MEMINT_DOWN_EVAL_EN			(1 << 1)
+#define   MEMINT_SW_CMD_EN			(1 << 0)
+#define MEMINTRSTR				_MMIO(0x11182) /* 16 bits */
+#define   MEM_RSEXIT_MASK			0xc000
+#define   MEM_RSEXIT_SHIFT			14
+#define   MEM_CONT_BUSY_MASK			0x3000
+#define   MEM_CONT_BUSY_SHIFT			12
+#define   MEM_AVG_BUSY_MASK			0x0c00
+#define   MEM_AVG_BUSY_SHIFT			10
+#define   MEM_EVAL_CHG_MASK			0x0300
+#define   MEM_EVAL_BUSY_SHIFT			8
+#define   MEM_MON_IDLE_MASK			0x00c0
+#define   MEM_MON_IDLE_SHIFT			6
+#define   MEM_UP_EVAL_MASK			0x0030
+#define   MEM_UP_EVAL_SHIFT			4
+#define   MEM_DOWN_EVAL_MASK			0x000c
+#define   MEM_DOWN_EVAL_SHIFT			2
+#define   MEM_SW_CMD_MASK			0x0003
+#define   MEM_INT_STEER_GFX			0
+#define   MEM_INT_STEER_CMR			1
+#define   MEM_INT_STEER_SMI			2
+#define   MEM_INT_STEER_SCI			3
+#define MEMINTRSTS				_MMIO(0x11184)
+#define   MEMINT_RSEXIT				(1 << 7)
+#define   MEMINT_CONT_BUSY			(1 << 6)
+#define   MEMINT_AVG_BUSY			(1 << 5)
+#define   MEMINT_EVAL_CHG			(1 << 4)
+#define   MEMINT_MON_IDLE			(1 << 3)
+#define   MEMINT_UP_EVAL			(1 << 2)
+#define   MEMINT_DOWN_EVAL			(1 << 1)
+#define   MEMINT_SW_CMD				(1 << 0)
+#define MEMMODECTL				_MMIO(0x11190)
+#define   MEMMODE_BOOST_EN			(1 << 31)
+#define   MEMMODE_BOOST_FREQ_MASK		0x0f000000 /* jitter for boost, 0-15 */
+#define   MEMMODE_BOOST_FREQ_SHIFT		24
+#define   MEMMODE_IDLE_MODE_MASK		0x00030000
+#define   MEMMODE_IDLE_MODE_SHIFT		16
+#define   MEMMODE_IDLE_MODE_EVAL		0
+#define   MEMMODE_IDLE_MODE_CONT		1
+#define   MEMMODE_HWIDLE_EN			(1 << 15)
+#define   MEMMODE_SWMODE_EN			(1 << 14)
+#define   MEMMODE_RCLK_GATE			(1 << 13)
+#define   MEMMODE_HW_UPDATE			(1 << 12)
+#define   MEMMODE_FSTART_MASK			0x00000f00 /* starting jitter, 0-15 */
+#define   MEMMODE_FSTART_SHIFT			8
+#define   MEMMODE_FMAX_MASK			0x000000f0 /* max jitter, 0-15 */
+#define   MEMMODE_FMAX_SHIFT			4
+#define   MEMMODE_FMIN_MASK			0x0000000f /* min jitter, 0-15 */
+#define RCBMAXAVG				_MMIO(0x1119c)
+#define MEMSWCTL2				_MMIO(0x1119e) /* Cantiga only */
+#define   SWMEMCMD_RENDER_OFF			(0 << 13)
+#define   SWMEMCMD_RENDER_ON			(1 << 13)
+#define   SWMEMCMD_SWFREQ			(2 << 13)
+#define   SWMEMCMD_TARVID			(3 << 13)
+#define   SWMEMCMD_VRM_OFF			(4 << 13)
+#define   SWMEMCMD_VRM_ON			(5 << 13)
+#define   CMDSTS				(1 << 12)
+#define   SFCAVM				(1 << 11)
+#define   SWFREQ_MASK				0x0380 /* P0-7 */
+#define   SWFREQ_SHIFT				7
+#define   TARVID_MASK				0x001f
+#define MEMSTAT_CTG				_MMIO(0x111a0)
+#define RCBMINAVG				_MMIO(0x111a0)
+#define RCUPEI					_MMIO(0x111b0)
+#define RCDNEI					_MMIO(0x111b4)
+#define RSTDBYCTL				_MMIO(0x111b8)
+#define   RS1EN					(1 << 31)
+#define   RS2EN					(1 << 30)
+#define   RS3EN					(1 << 29)
+#define   D3RS3EN				(1 << 28) /* Display D3 imlies RS3 */
+#define   SWPROMORSX				(1 << 27) /* RSx promotion timers ignored */
+#define   RCWAKERW				(1 << 26) /* Resetwarn from PCH causes wakeup */
+#define   DPRSLPVREN				(1 << 25) /* Fast voltage ramp enable */
+#define   GFXTGHYST				(1 << 24) /* Hysteresis to allow trunk gating */
+#define   RCX_SW_EXIT				(1 << 23) /* Leave RSx and prevent re-entry */
+#define   RSX_STATUS_MASK			(7 << 20)
+#define   RSX_STATUS_ON				(0 << 20)
+#define   RSX_STATUS_RC1			(1 << 20)
+#define   RSX_STATUS_RC1E			(2 << 20)
+#define   RSX_STATUS_RS1			(3 << 20)
+#define   RSX_STATUS_RS2			(4 << 20) /* aka rc6 */
+#define   RSX_STATUS_RSVD			(5 << 20) /* deep rc6 unsupported on ilk */
+#define   RSX_STATUS_RS3			(6 << 20) /* rs3 unsupported on ilk */
+#define   RSX_STATUS_RSVD2			(7 << 20)
+#define   UWRCRSXE				(1 << 19) /* wake counter limit prevents rsx */
+#define   RSCRP					(1 << 18) /* rs requests control on rs1/2 reqs */
+#define   JRSC					(1 << 17) /* rsx coupled to cpu c-state */
+#define   RS2INC0				(1 << 16) /* allow rs2 in cpu c0 */
+#define   RS1CONTSAV_MASK			(3 << 14)
+#define   RS1CONTSAV_NO_RS1			(0 << 14) /* rs1 doesn't save/restore context */
+#define   RS1CONTSAV_RSVD			(1 << 14)
+#define   RS1CONTSAV_SAVE_RS1			(2 << 14) /* rs1 saves context */
+#define   RS1CONTSAV_FULL_RS1			(3 << 14) /* rs1 saves and restores context */
+#define   NORMSLEXLAT_MASK			(3 << 12)
+#define   SLOW_RS123				(0 << 12)
+#define   SLOW_RS23				(1 << 12)
+#define   SLOW_RS3				(2 << 12)
+#define   NORMAL_RS123				(3 << 12)
+#define   RCMODE_TIMEOUT			(1 << 11) /* 0 is eval interval method */
+#define   IMPROMOEN				(1 << 10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
+#define   RCENTSYNC				(1 << 9) /* rs coupled to cpu c-state (3/6/7) */
+#define   STATELOCK				(1 << 7) /* locked to rs_cstate if 0 */
+#define   RS_CSTATE_MASK			(3 << 4)
+#define   RS_CSTATE_C367_RS1			(0 << 4)
+#define   RS_CSTATE_C36_RS1_C7_RS2		(1 << 4)
+#define   RS_CSTATE_RSVD			(2 << 4)
+#define   RS_CSTATE_C367_RS2			(3 << 4)
+#define   REDSAVES				(1 << 3) /* no context save if was idle during rs0 */
+#define   REDRESTORES				(1 << 2) /* no restore if was idle during rs0 */
+#define VIDCTL					_MMIO(0x111c0)
+#define VIDSTS					_MMIO(0x111c8)
+#define VIDSTART				_MMIO(0x111cc) /* 8 bits */
+#define MEMSTAT_ILK				_MMIO(0x111f8)
+#define   MEMSTAT_VID_MASK			0x7f00
+#define   MEMSTAT_VID_SHIFT			8
+#define   MEMSTAT_PSTATE_MASK			0x00f8
+#define   MEMSTAT_PSTATE_SHIFT			3
+#define   MEMSTAT_MON_ACTV			(1 << 2)
+#define   MEMSTAT_SRC_CTL_MASK			0x0003
+#define   MEMSTAT_SRC_CTL_CORE			0
+#define   MEMSTAT_SRC_CTL_TRB			1
+#define   MEMSTAT_SRC_CTL_THM			2
+#define   MEMSTAT_SRC_CTL_STDBY			3
+#define PMMISC					_MMIO(0x11214)
+#define   MCPPCE_EN				(1 << 0) /* enable PM_MSG from PCH->MPC */
+#define SDEW					_MMIO(0x1124c)
+#define CSIEW0					_MMIO(0x11250)
+#define CSIEW1					_MMIO(0x11254)
+#define CSIEW2					_MMIO(0x11258)
+#define PEW(i)					_MMIO(0x1125c + (i) * 4) /* 5 registers */
+#define DEW(i)					_MMIO(0x11270 + (i) * 4) /* 3 registers */
+#define MCHAFE					_MMIO(0x112c0)
+#define CSIEC					_MMIO(0x112e0)
+#define DMIEC					_MMIO(0x112e4)
+#define DDREC					_MMIO(0x112e8)
+#define PEG0EC					_MMIO(0x112ec)
+#define PEG1EC					_MMIO(0x112f0)
+#define GFXEC					_MMIO(0x112f4)
+#define INTTOEXT_BASE_ILK			_MMIO(0x11300)
+#define RPPREVBSYTUPAVG				_MMIO(0x113b8)
+#define RCPREVBSYTUPAVG				_MMIO(0x113b8)
+#define RCPREVBSYTDNAVG				_MMIO(0x113bc)
+#define RPPREVBSYTDNAVG				_MMIO(0x113bc)
+#define ECR					_MMIO(0x11600)
+#define   ECR_GPFE				(1 << 31)
+#define   ECR_IMONE				(1 << 30)
+#define   ECR_CAP_MASK				0x0000001f /* Event range, 0-31 */
+#define OGW0					_MMIO(0x11608)
+#define OGW1					_MMIO(0x1160c)
+#define EG0					_MMIO(0x11610)
+#define EG1					_MMIO(0x11614)
+#define EG2					_MMIO(0x11618)
+#define EG3					_MMIO(0x1161c)
+#define EG4					_MMIO(0x11620)
+#define EG5					_MMIO(0x11624)
+#define EG6					_MMIO(0x11628)
+#define EG7					_MMIO(0x1162c)
+#define PXW(i)					_MMIO(0x11664 + (i) * 4) /* 4 registers */
+#define PXWL(i)					_MMIO(0x11680 + (i) * 8) /* 8 registers */
+#define LCFUSE02				_MMIO(0x116c0)
+#define   LCFUSE_HIV_MASK			0x000000ff
+
+#define GAC_ECO_BITS				_MMIO(0x14090)
+#define   ECOBITS_SNB_BIT			(1 << 13)
+#define   ECOBITS_PPGTT_CACHE64B		(3 << 8)
+#define   ECOBITS_PPGTT_CACHE4B			(0 << 8)
+
+#define CHV_FUSE_GT				_MMIO(VLV_DISPLAY_BASE + 0x2168)
+#define   CHV_FGT_DISABLE_SS0			(1 << 10)
+#define   CHV_FGT_DISABLE_SS1			(1 << 11)
+#define   CHV_FGT_EU_DIS_SS0_R0_SHIFT		16
+#define   CHV_FGT_EU_DIS_SS0_R0_MASK		(0xf << CHV_FGT_EU_DIS_SS0_R0_SHIFT)
+#define   CHV_FGT_EU_DIS_SS0_R1_SHIFT		20
+#define   CHV_FGT_EU_DIS_SS0_R1_MASK		(0xf << CHV_FGT_EU_DIS_SS0_R1_SHIFT)
+#define   CHV_FGT_EU_DIS_SS1_R0_SHIFT		24
+#define   CHV_FGT_EU_DIS_SS1_R0_MASK		(0xf << CHV_FGT_EU_DIS_SS1_R0_SHIFT)
+#define   CHV_FGT_EU_DIS_SS1_R1_SHIFT		28
+#define   CHV_FGT_EU_DIS_SS1_R1_MASK		(0xf << CHV_FGT_EU_DIS_SS1_R1_SHIFT)
+
+#define BCS_SWCTRL				_MMIO(0x22200)
+#define   BCS_SRC_Y				REG_BIT(0)
+#define   BCS_DST_Y				REG_BIT(1)
+
+#define GAB_CTL					_MMIO(0x24000)
+#define   GAB_CTL_CONT_AFTER_PAGEFAULT		(1 << 8)
 
-#define HALF_SLICE_CHICKEN3		_MMIO(0xe184)
-#define   HSW_SAMPLE_C_PERFORMANCE	(1 << 9)
-#define   GEN8_CENTROID_PIXEL_OPT_DIS	(1 << 8)
-#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
-#define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1 << 1)
+#define GEN6_PMISR				_MMIO(0x44020)
+#define GEN6_PMIMR				_MMIO(0x44024) /* rps_lock */
+#define GEN6_PMIIR				_MMIO(0x44028)
+#define GEN6_PMIER				_MMIO(0x4402c)
+#define   GEN6_PM_MBOX_EVENT			(1 << 25)
+#define   GEN6_PM_THERMAL_EVENT			(1 << 24)
+/*
+ * For Gen11 these are in the upper word of the GPM_WGBOXPERF
+ * registers. Shifting is handled on accessing the imr and ier.
+ */
+#define   GEN6_PM_RP_DOWN_TIMEOUT		(1 << 6)
+#define   GEN6_PM_RP_UP_THRESHOLD		(1 << 5)
+#define   GEN6_PM_RP_DOWN_THRESHOLD		(1 << 4)
+#define   GEN6_PM_RP_UP_EI_EXPIRED		(1 << 2)
+#define   GEN6_PM_RP_DOWN_EI_EXPIRED		(1 << 1)
+#define   GEN6_PM_RPS_EVENTS			(GEN6_PM_RP_UP_EI_EXPIRED   | \
+						 GEN6_PM_RP_UP_THRESHOLD    | \
+						 GEN6_PM_RP_DOWN_EI_EXPIRED | \
+						 GEN6_PM_RP_DOWN_THRESHOLD  | \
+						 GEN6_PM_RP_DOWN_TIMEOUT)
 
-#define GEN9_HALF_SLICE_CHICKEN7	_MMIO(0xe194)
-#define   DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA	REG_BIT(15)
-#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	REG_BIT(8)
-#define   GEN9_ENABLE_YV12_BUGFIX			REG_BIT(4)
-#define   GEN9_ENABLE_GPGPU_PREEMPTION			REG_BIT(2)
+#define GEN7_GT_SCRATCH(i)			_MMIO(0x4f100 + (i) * 4)
+#define   GEN7_GT_SCRATCH_REG_NUM		8
+
+#define GFX_FLSH_CNTL_GEN6			_MMIO(0x101008)
+#define   GFX_FLSH_CNTL_EN			(1 << 0)
+
+#define GTFIFODBG				_MMIO(0x120000)
+#define   GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV	(0x1f << 20)
+#define   GT_FIFO_FREE_ENTRIES_CHV		(0x7f << 13)
+#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 GTFIFOCTL				_MMIO(0x120008)
+#define   GT_FIFO_FREE_ENTRIES_MASK		0x7f
+#define   GT_FIFO_NUM_RESERVED_ENTRIES		20
+#define   GT_FIFO_CTL_BLOCK_ALL_POLICY_STALL	(1 << 12)
+#define   GT_FIFO_CTL_RC6_POLICY_STALL		(1 << 11)
+
+#define FORCEWAKE_MT_ACK			_MMIO(0x130040)
+#define FORCEWAKE_ACK_HSW			_MMIO(0x130044)
+#define FORCEWAKE_ACK_GT_GEN9			_MMIO(0x130044)
+#define   FORCEWAKE_KERNEL			BIT(0)
+#define   FORCEWAKE_USER			BIT(1)
+#define   FORCEWAKE_KERNEL_FALLBACK		BIT(15)
+#define FORCEWAKE_ACK				_MMIO(0x130090)
+#define VLV_GTLC_WAKE_CTRL			_MMIO(0x130090)
+#define   VLV_GTLC_RENDER_CTX_EXISTS		(1 << 25)
+#define   VLV_GTLC_MEDIA_CTX_EXISTS		(1 << 24)
+#define   VLV_GTLC_ALLOWWAKEREQ			(1 << 0)
+#define VLV_GTLC_PW_STATUS			_MMIO(0x130094)
+#define   VLV_GTLC_ALLOWWAKEACK			(1 << 0)
+#define   VLV_GTLC_ALLOWWAKEERR			(1 << 1)
+#define   VLV_GTLC_PW_MEDIA_STATUS_MASK		(1 << 5)
+#define   VLV_GTLC_PW_RENDER_STATUS_MASK	(1 << 7)
+#define VLV_GTLC_SURVIVABILITY_REG		_MMIO(0x130098)
+#define   VLV_GFX_CLK_STATUS_BIT		(1 << 3)
+#define   VLV_GFX_CLK_FORCE_ON_BIT		(1 << 2)
+#define FORCEWAKE_VLV				_MMIO(0x1300b0)
+#define FORCEWAKE_ACK_VLV			_MMIO(0x1300b4)
+#define FORCEWAKE_MEDIA_VLV			_MMIO(0x1300b8)
+#define FORCEWAKE_ACK_MEDIA_VLV			_MMIO(0x1300bc)
+
+#define GEN6_GT_THREAD_STATUS_REG		_MMIO(0x13805c)
+#define   GEN6_GT_THREAD_STATUS_CORE_MASK	0x7
+
+#define GEN6_GT_CORE_STATUS			_MMIO(0x138060)
+#define   GEN6_CORE_CPD_STATE_MASK		(7 << 4)
+#define   GEN6_RCn_MASK				7
+#define   GEN6_RC0				0
+#define   GEN6_RC3				2
+#define   GEN6_RC6				3
+#define   GEN6_RC7				4
+
+#define GEN8_GT_SLICE_INFO			_MMIO(0x138064)
+#define   GEN8_LSLICESTAT_MASK			0x7
 
-/* MOCS (Memory Object Control State) registers */
-#define GEN9_LNCFCMOCS(i)	_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
-#define GEN9_LNCFCMOCS_REG_COUNT	32
-
-#define __GEN9_RCS0_MOCS0	0xc800
-#define GEN9_GFX_MOCS(i)	_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
-#define __GEN9_VCS0_MOCS0	0xc900
-#define GEN9_MFX0_MOCS(i)	_MMIO(__GEN9_VCS0_MOCS0 + (i) * 4)
-#define __GEN9_VCS1_MOCS0	0xca00
-#define GEN9_MFX1_MOCS(i)	_MMIO(__GEN9_VCS1_MOCS0 + (i) * 4)
-#define __GEN9_VECS0_MOCS0	0xcb00
-#define GEN9_VEBOX_MOCS(i)	_MMIO(__GEN9_VECS0_MOCS0 + (i) * 4)
-#define __GEN9_BCS0_MOCS0	0xcc00
-#define GEN9_BLT_MOCS(i)	_MMIO(__GEN9_BCS0_MOCS0 + (i) * 4)
-#define __GEN11_VCS2_MOCS0	0x10000
-#define GEN11_MFX2_MOCS(i)	_MMIO(__GEN11_VCS2_MOCS0 + (i) * 4)
-
-#define GEN9_SCRATCH_LNCF1		_MMIO(0xb008)
-#define   GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(0)
-
-#define GEN9_SCRATCH1			_MMIO(0xb11c)
-#define   EVICTION_PERF_FIX_ENABLE	REG_BIT(8)
-
-#define GEN10_SCRATCH_LNCF2		_MMIO(0xb0a0)
-#define   PMFLUSHDONE_LNICRSDROP	(1 << 20)
-#define   PMFLUSH_GAPL3UNBLOCK		(1 << 21)
-#define   PMFLUSHDONE_LNEBLK		(1 << 22)
-
-#define XEHP_L3NODEARBCFG		_MMIO(0xb0b4)
-#define   XEHP_LNESPARE			REG_BIT(19)
-
-#define GEN12_GLOBAL_MOCS(i)	_MMIO(0x4000 + (i) * 4) /* Global MOCS regs */
+#define GEN6_GT_GFX_RC6_LOCKED			_MMIO(0x138104)
+#define VLV_COUNTER_CONTROL			_MMIO(0x138104)
+#define   VLV_COUNT_RANGE_HIGH			(1 << 15)
+#define   VLV_MEDIA_RC0_COUNT_EN		(1 << 5)
+#define   VLV_RENDER_RC0_COUNT_EN		(1 << 4)
+#define   VLV_MEDIA_RC6_COUNT_EN		(1 << 1)
+#define   VLV_RENDER_RC6_COUNT_EN		(1 << 0)
+#define GEN6_GT_GFX_RC6				_MMIO(0x138108)
+#define VLV_GT_RENDER_RC6			_MMIO(0x138108)
+#define VLV_GT_MEDIA_RC6			_MMIO(0x13810c)
 
-/* gamt regs */
-#define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4)
-#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW  0x67F1427F /* max/min for LRA1/2 */
-#define   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV  0x5FF101FF /* max/min for LRA1/2 */
-#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL  0x67F1427F /*    "        " */
-#define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT  0x5FF101FF /*    "        " */
+#define GEN6_GT_GFX_RC6p			_MMIO(0x13810c)
+#define GEN6_GT_GFX_RC6pp			_MMIO(0x138110)
+#define VLV_RENDER_C0_COUNT			_MMIO(0x138118)
+#define VLV_MEDIA_C0_COUNT			_MMIO(0x13811c)
+
+#define GEN11_GT_INTR_DW(x)			_MMIO(0x190018 + ((x) * 4))
+#define   GEN11_CSME				(31)
+#define   GEN11_GUNIT				(28)
+#define   GEN11_GUC				(25)
+#define   GEN11_WDPERF				(20)
+#define   GEN11_KCR				(19)
+#define   GEN11_GTPM				(16)
+#define   GEN11_BCS				(15)
+#define   GEN11_RCS0				(0)
+#define   GEN11_VECS(x)				(31 - (x))
+#define   GEN11_VCS(x)				(x)
+
+#define GEN11_RENDER_COPY_INTR_ENABLE		_MMIO(0x190030)
+#define GEN11_VCS_VECS_INTR_ENABLE		_MMIO(0x190034)
+#define GEN11_GUC_SG_INTR_ENABLE		_MMIO(0x190038)
+#define   ENGINE1_MASK				REG_GENMASK(31, 16)
+#define   ENGINE0_MASK				REG_GENMASK(15, 0)
+#define GEN11_GPM_WGBOXPERF_INTR_ENABLE		_MMIO(0x19003c)
+#define GEN11_CRYPTO_RSVD_INTR_ENABLE		_MMIO(0x190040)
+#define GEN11_GUNIT_CSME_INTR_ENABLE		_MMIO(0x190044)
+
+#define GEN11_INTR_IDENTITY_REG(x)		_MMIO(0x190060 + ((x) * 4))
+#define   GEN11_INTR_DATA_VALID			(1 << 31)
+#define   GEN11_INTR_ENGINE_CLASS(x)		(((x) & GENMASK(18, 16)) >> 16)
+#define   GEN11_INTR_ENGINE_INSTANCE(x)		(((x) & GENMASK(25, 20)) >> 20)
+#define   GEN11_INTR_ENGINE_INTR(x)		((x) & 0xffff)
+/* irq instances for OTHER_CLASS */
+#define   OTHER_GUC_INSTANCE			0
+#define   OTHER_GTPM_INSTANCE			1
+#define   OTHER_KCR_INSTANCE			4
+
+#define GEN11_IIR_REG_SELECTOR(x)		_MMIO(0x190070 + ((x) * 4))
+
+#define GEN11_RCS0_RSVD_INTR_MASK		_MMIO(0x190090)
+#define GEN11_BCS_RSVD_INTR_MASK		_MMIO(0x1900a0)
+#define GEN11_VCS0_VCS1_INTR_MASK		_MMIO(0x1900a8)
+#define GEN11_VCS2_VCS3_INTR_MASK		_MMIO(0x1900ac)
+#define GEN12_VCS4_VCS5_INTR_MASK		_MMIO(0x1900b0)
+#define GEN12_VCS6_VCS7_INTR_MASK		_MMIO(0x1900b4)
+#define GEN11_VECS0_VECS1_INTR_MASK		_MMIO(0x1900d0)
+#define GEN12_VECS2_VECS3_INTR_MASK		_MMIO(0x1900d4)
+#define GEN11_GUC_SG_INTR_MASK			_MMIO(0x1900e8)
+#define GEN11_GPM_WGBOXPERF_INTR_MASK		_MMIO(0x1900ec)
+#define GEN11_CRYPTO_RSVD_INTR_MASK		_MMIO(0x1900f0)
+#define GEN11_GUNIT_CSME_INTR_MASK		_MMIO(0x1900f4)
+
+#define GEN12_SFC_DONE(n)			_MMIO(0x1cc000 + (n) * 0x1000)
+
+enum {
+	INTEL_ADVANCED_CONTEXT = 0,
+	INTEL_LEGACY_32B_CONTEXT,
+	INTEL_ADVANCED_AD_CONTEXT,
+	INTEL_LEGACY_64B_CONTEXT
+};
 
-#define MMCD_MISC_CTRL		_MMIO(0x4ddc) /* skl+ */
-#define  MMCD_PCLA		(1 << 31)
-#define  MMCD_HOTSPOT_EN	(1 << 27)
+enum {
+	FAULT_AND_HANG = 0,
+	FAULT_AND_HALT, /* Debug only */
+	FAULT_AND_STREAM,
+	FAULT_AND_CONTINUE /* Unsupported */
+};
 
-#define SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731C)
-#define   MSC_MSAA_REODER_BUF_BYPASS_DISABLE	REG_BIT(14)
+#define   CTX_GTT_ADDRESS_MASK			GENMASK(31, 12)
+#define   GEN8_CTX_VALID			(1 << 0)
+#define   GEN8_CTX_FORCE_PD_RESTORE		(1 << 1)
+#define   GEN8_CTX_FORCE_RESTORE		(1 << 2)
+#define   GEN8_CTX_L3LLC_COHERENT		(1 << 5)
+#define   GEN8_CTX_PRIVILEGE			(1 << 8)
+#define   GEN8_CTX_ADDRESSING_MODE_SHIFT	3
+#define   GEN8_CTX_ID_SHIFT			32
+#define   GEN8_CTX_ID_WIDTH			21
+#define   GEN11_SW_CTX_ID_SHIFT			37
+#define   GEN11_SW_CTX_ID_WIDTH			11
+#define   GEN11_ENGINE_CLASS_SHIFT		61
+#define   GEN11_ENGINE_CLASS_WIDTH		3
+#define   GEN11_ENGINE_INSTANCE_SHIFT		48
+#define   GEN11_ENGINE_INSTANCE_WIDTH		6
+#define   XEHP_SW_CTX_ID_SHIFT			39
+#define   XEHP_SW_CTX_ID_WIDTH			16
+#define   XEHP_SW_COUNTER_SHIFT			58
+#define   XEHP_SW_COUNTER_WIDTH			6
 
 #endif /* __INTEL_GT_REGS__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index b5d3cde08aac..8506db9983da 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -10,6 +10,7 @@
 
 #include <drm/drm_cache.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_lmem.h"
 #include "i915_trace.h"
 #include "intel_gt.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c
index 335c65758d6f..40e2e28ee6c7 100644
--- a/drivers/gpu/drm/i915/gt/intel_llc.c
+++ b/drivers/gpu/drm/i915/gt/intel_llc.c
@@ -10,6 +10,7 @@
 #include "i915_reg.h"
 #include "intel_gt.h"
 #include "intel_llc.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 
 struct ia_constants {
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e46bf1429f2c..91c87a3a8e0b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -8,6 +8,8 @@
 #include "gen8_engine_cs.h"
 #include "i915_drv.h"
 #include "i915_perf.h"
+#include "i915_reg.h"
+#include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_regs.h"
 #include "intel_gpu_commands.h"
@@ -1688,6 +1690,17 @@ static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
 #endif
 }
 
+static u32 lrc_get_runtime(const struct intel_context *ce)
+{
+	/*
+	 * We can use either ppHWSP[16] which is recorded before the context
+	 * switch (and so excludes the cost of context switches) or use the
+	 * value from the context image itself, which is saved/restored earlier
+	 * and so includes the cost of the save.
+	 */
+	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
+}
+
 void lrc_update_runtime(struct intel_context *ce)
 {
 	u32 old;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 7f697845c4cf..0b76f096b559 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -8,12 +8,12 @@
 
 #include <linux/types.h>
 
-#include "intel_context.h"
-#include "intel_lrc_reg.h"
-
 struct drm_i915_gem_object;
+struct i915_gem_ww_ctx;
+struct intel_context;
 struct intel_engine_cs;
 struct intel_ring;
+struct kref;
 
 /* At the start of the context image is its per-process HWS page */
 #define LRC_PPHWSP_PN	(0)
@@ -68,15 +68,5 @@ void lrc_check_regs(const struct intel_context *ce,
 		    const char *when);
 
 void lrc_update_runtime(struct intel_context *ce);
-static inline u32 lrc_get_runtime(const struct intel_context *ce)
-{
-	/*
-	 * We can use either ppHWSP[16] which is recorded before the context
-	 * switch (and so excludes the cost of context switches) or use the
-	 * value from the context image itself, which is saved/restored earlier
-	 * and so includes the cost of the save.
-	 */
-	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
-}
 
 #endif /* __INTEL_LRC_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index b575cd6e0b7a..5121e6dc2fa5 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -3,6 +3,8 @@
  * Copyright © 2014 Intel Corporation
  */
 
+#include "gem/i915_gem_internal.h"
+
 #include "i915_drv.h"
 #include "intel_renderstate.h"
 #include "intel_context.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 59beb69ff6f2..ae7542f70afb 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -14,6 +14,7 @@
 #include "gt/intel_gt_regs.h"
 
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_gpu_error.h"
 #include "i915_irq.h"
 #include "intel_breadcrumbs.h"
@@ -22,6 +23,7 @@
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pci_config.h"
 #include "intel_reset.h"
 
@@ -347,25 +349,25 @@ static void get_sfc_forced_lock_data(struct intel_engine_cs *engine,
 		MISSING_CASE(engine->class);
 		fallthrough;
 	case VIDEO_DECODE_CLASS:
-		sfc_lock->lock_reg = GEN11_VCS_SFC_FORCED_LOCK(engine);
+		sfc_lock->lock_reg = GEN11_VCS_SFC_FORCED_LOCK(engine->mmio_base);
 		sfc_lock->lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
 
-		sfc_lock->ack_reg = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_lock->ack_reg = GEN11_VCS_SFC_LOCK_STATUS(engine->mmio_base);
 		sfc_lock->ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
 
-		sfc_lock->usage_reg = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_lock->usage_reg = GEN11_VCS_SFC_LOCK_STATUS(engine->mmio_base);
 		sfc_lock->usage_bit = GEN11_VCS_SFC_USAGE_BIT;
 		sfc_lock->reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
 
 		break;
 	case VIDEO_ENHANCEMENT_CLASS:
-		sfc_lock->lock_reg = GEN11_VECS_SFC_FORCED_LOCK(engine);
+		sfc_lock->lock_reg = GEN11_VECS_SFC_FORCED_LOCK(engine->mmio_base);
 		sfc_lock->lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
 
-		sfc_lock->ack_reg = GEN11_VECS_SFC_LOCK_ACK(engine);
+		sfc_lock->ack_reg = GEN11_VECS_SFC_LOCK_ACK(engine->mmio_base);
 		sfc_lock->ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
 
-		sfc_lock->usage_reg = GEN11_VECS_SFC_USAGE(engine);
+		sfc_lock->usage_reg = GEN11_VECS_SFC_USAGE(engine->mmio_base);
 		sfc_lock->usage_bit = GEN11_VECS_SFC_USAGE_BIT;
 		sfc_lock->reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
 
@@ -412,7 +414,7 @@ static int gen11_lock_sfc(struct intel_engine_cs *engine,
 		 * forced lock on the VE engine that shares the same SFC.
 		 */
 		if (!(intel_uncore_read_fw(uncore,
-					   GEN12_HCP_SFC_LOCK_STATUS(engine)) &
+					   GEN12_HCP_SFC_LOCK_STATUS(engine->mmio_base)) &
 		      GEN12_HCP_SFC_USAGE_BIT))
 			return 0;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 723055340c9b..40ffcb94e379 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -3,6 +3,7 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_object.h"
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 8362eb09092e..6d7ec3bf1f32 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -3,6 +3,10 @@
  * Copyright © 2008-2021 Intel Corporation
  */
 
+#include <drm/drm_cache.h>
+
+#include "gem/i915_gem_internal.h"
+
 #include "gen2_engine_cs.h"
 #include "gen6_engine_cs.h"
 #include "gen6_ppgtt.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 0cb299cdfc8f..fd95449ed46d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -13,6 +13,7 @@
 #include "intel_gt_irq.h"
 #include "intel_gt_pm_irq.h"
 #include "intel_gt_regs.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 #include "intel_rps.h"
 #include "vlv_sideband.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 438bbc7b8147..b9640212d659 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -3,9 +3,12 @@
  * Copyright © 2016-2018 Intel Corporation
  */
 
-#include "i915_drv.h"
+#include <drm/drm_cache.h>
+
+#include "gem/i915_gem_internal.h"
 
 #include "i915_active.h"
+#include "i915_drv.h"
 #include "i915_syncmap.h"
 #include "intel_gt.h"
 #include "intel_ring.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 59ad23118875..eeda1692d845 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -237,7 +237,7 @@ static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, INSTPM, INSTPM_FORCE_ORDERING);
 
 	/* WaDisableAsyncFlipPerfMode:bdw,chv */
-	wa_masked_en(wal, MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+	wa_masked_en(wal, RING_MI_MODE(RENDER_RING_BASE), ASYNC_FLIP_PERF_DISABLE);
 
 	/* WaDisablePartialInstShootdown:bdw,chv */
 	wa_masked_en(wal, GEN8_ROW_CHICKEN,
@@ -2463,7 +2463,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 		 */
 		wa_masked_en(wal,
-			     MI_MODE,
+			     RING_MI_MODE(RENDER_RING_BASE),
 			     ASYNC_FLIP_PERF_DISABLE);
 
 	if (GRAPHICS_VER(i915) == 6) {
@@ -2522,7 +2522,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 
 	if (IS_GRAPHICS_VER(i915, 4, 6))
 		/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
-		wa_add(wal, MI_MODE,
+		wa_add(wal, RING_MI_MODE(RENDER_RING_BASE),
 		       0, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH),
 		       /* XXX bit doesn't stick on Broadwater */
 		       IS_I965G(i915) ? 0 : VS_TIMER_DISPATCH, true);
diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
index e10da897e07a..72d5faab8f9a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_execlists.c
+++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c
@@ -5,6 +5,7 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_reset.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 4a20ba63446c..9e9ccb139ba7 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -6,6 +6,7 @@
 #include <linux/kthread.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 
 #include "i915_gem_evict.h"
 #include "intel_gt.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 618c905daa19..21c29d315cc0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -5,6 +5,8 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_internal.h"
+
 #include "i915_selftest.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c
index fa4293d2944f..c9c4f391c5cc 100644
--- a/drivers/gpu/drm/i915/gt/selftest_migrate.c
+++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c
@@ -5,6 +5,8 @@
 
 #include <linux/sort.h>
 
+#include "gem/i915_gem_internal.h"
+
 #include "selftests/i915_random.h"
 
 static const unsigned int sizes[] = {
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index e1e5dd5f7638..6a69ac0184ad 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -6,6 +6,8 @@
 #include <linux/pm_qos.h>
 #include <linux/sort.h>
 
+#include "gem/i915_gem_internal.h"
+
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 #include "intel_engine_regs.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 0287c2573c51..67a9aab801dd 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -3,6 +3,7 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index ddbea939b1dc..b3d28b003b73 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -3,9 +3,12 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include <drm/drm_cache.h>
+
 #include "i915_drv.h"
 #include "i915_reg.h"
 #include "intel_guc_slpc.h"
+#include "intel_mchbar_regs.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_regs.h"
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index dd588ecf048a..549d5919dc70 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -5,6 +5,8 @@
 
 #include <linux/bitfield.h>
 #include <linux/firmware.h>
+
+#include <drm/drm_cache.h>
 #include <drm/drm_print.h>
 
 #include "gem/i915_gem_lmem.h"
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index d02a48a5335a..12b7c36d8e8f 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -31,6 +31,11 @@
 #include <linux/dma-buf.h>
 #include <linux/vfio.h>
 
+#include <drm/drm_fourcc.h>
+#include <drm/drm_plane.h>
+
+#include "gem/i915_gem_dmabuf.h"
+
 #include "i915_drv.h"
 #include "i915_reg.h"
 #include "gvt.h"
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index c8dcda6d4f0d..66d354c4195b 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -163,7 +163,7 @@ static void emulate_csb_update(struct intel_vgpu_execlist *execlist,
 					       hwsp_gpa + I915_HWS_CSB_BUF0_INDEX * 4 + write_pointer * 8,
 					       status, 8);
 		intel_gvt_hypervisor_write_gpa(vgpu,
-					       hwsp_gpa + intel_hws_csb_write_index(execlist->engine->i915) * 4,
+					       hwsp_gpa + INTEL_HWS_CSB_WRITE_INDEX(execlist->engine->i915) * 4,
 					       &write_pointer, 4);
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index c2ae79092b14..5e3ae5970c6b 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -40,6 +40,7 @@
 #include "i915_reg.h"
 #include "gvt.h"
 #include "i915_pvinfo.h"
+#include "intel_mchbar_regs.h"
 #include "display/intel_display_types.h"
 #include "display/intel_fbc.h"
 #include "gt/intel_gt_regs.h"
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 20b82fb036f8..e8d6c76e9234 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -46,6 +46,8 @@
 
 #include <linux/nospec.h>
 
+#include <drm/drm_edid.h>
+
 #include "i915_drv.h"
 #include "gvt.h"
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index aea4c30645ff..5f6e41636655 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -25,6 +25,8 @@
  *
  */
 
+#include <drm/drm_cache.h>
+
 #include "gt/intel_engine.h"
 #include "gt/intel_engine_regs.h"
 #include "gt/intel_gpu_commands.h"
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 4fe1ce1433fe..54c66d4b6887 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -49,6 +49,7 @@
 #include "i915_debugfs_params.h"
 #include "i915_irq.h"
 #include "i915_scheduler.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pm.h"
 
 static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
@@ -137,6 +138,17 @@ static const char *stringify_vma_type(const struct i915_vma *vma)
 	return "ppgtt";
 }
 
+static const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
+{
+	switch (type) {
+	case I915_CACHE_NONE: return " uncached";
+	case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
+	case I915_CACHE_L3_LLC: return " L3+LLC";
+	case I915_CACHE_WT: return " WT";
+	default: return "";
+	}
+}
+
 void
 i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 4b56d4d83e75..a892a1b546a8 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -62,6 +62,8 @@
 #include "display/intel_vga.h"
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_create.h"
+#include "gem/i915_gem_dmabuf.h"
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_mman.h"
 #include "gem/i915_gem_pm.h"
@@ -71,6 +73,7 @@
 
 #include "pxp/intel_pxp_pm.h"
 
+#include "i915_file_private.h"
 #include "i915_debugfs.h"
 #include "i915_driver.h"
 #include "i915_drv.h"
@@ -1821,6 +1824,21 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_VM_DESTROY, i915_gem_vm_destroy_ioctl, DRM_RENDER_ALLOW),
 };
 
+/*
+ * Interface history:
+ *
+ * 1.1: Original.
+ * 1.2: Add Power Management
+ * 1.3: Add vblank support
+ * 1.4: Fix cmdbuffer path, add heap destroy
+ * 1.5: Add vblank pipe configuration
+ * 1.6: - New ioctl for scheduling buffer swaps on vertical blank
+ *      - Support vertical blank on secondary display pipe
+ */
+#define DRIVER_MAJOR		1
+#define DRIVER_MINOR		6
+#define DRIVER_PATCHLEVEL	0
+
 static const struct drm_driver i915_drm_driver = {
 	/* Don't use MTRRs here; the Xserver or userspace app should
 	 * deal with them for Intel hardware.
diff --git a/drivers/gpu/drm/i915/i915_driver.h b/drivers/gpu/drm/i915/i915_driver.h
index 9ef8db4aa0a6..9d11de65daaf 100644
--- a/drivers/gpu/drm/i915/i915_driver.h
+++ b/drivers/gpu/drm/i915/i915_driver.h
@@ -12,6 +12,11 @@ struct pci_dev;
 struct pci_device_id;
 struct drm_i915_private;
 
+#define DRIVER_NAME		"i915"
+#define DRIVER_DESC		"Intel Graphics"
+#define DRIVER_DATE		"20201103"
+#define DRIVER_TIMESTAMP	1604406085
+
 extern const struct dev_pm_ops i915_pm_ops;
 
 int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f7bdb973c880..ffde71b6b3f1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -31,38 +31,17 @@
 #define _I915_DRV_H_
 
 #include <uapi/drm/i915_drm.h>
-#include <uapi/drm/drm_fourcc.h>
 
 #include <asm/hypervisor.h>
 
-#include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
-#include <linux/backlight.h>
-#include <linux/hash.h>
 #include <linux/intel-iommu.h>
-#include <linux/kref.h>
-#include <linux/mm_types.h>
-#include <linux/perf_event.h>
 #include <linux/pm_qos.h>
-#include <linux/dma-resv.h>
-#include <linux/shmem_fs.h>
-#include <linux/stackdepot.h>
-#include <linux/xarray.h>
-
-#include <drm/drm_gem.h>
-#include <drm/drm_auth.h>
-#include <drm/drm_cache.h>
-#include <drm/drm_util.h>
-#include <drm/drm_dsc.h>
-#include <drm/drm_atomic.h>
+
 #include <drm/drm_connector.h>
-#include <drm/i915_mei_hdcp_interface.h>
 #include <drm/ttm/ttm_device.h>
 
-#include "i915_params.h"
-#include "i915_utils.h"
-
 #include "display/intel_bios.h"
 #include "display/intel_cdclk.h"
 #include "display/intel_display.h"
@@ -77,9 +56,9 @@
 #include "display/intel_opregion.h"
 
 #include "gem/i915_gem_context_types.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_shrinker.h"
 #include "gem/i915_gem_stolen.h"
-#include "gem/i915_gem_lmem.h"
 
 #include "gt/intel_engine.h"
 #include "gt/intel_gt_types.h"
@@ -87,6 +66,12 @@
 #include "gt/intel_workarounds.h"
 #include "gt/uc/intel_uc.h"
 
+#include "i915_gem.h"
+#include "i915_gpu_error.h"
+#include "i915_params.h"
+#include "i915_perf_types.h"
+#include "i915_scheduler.h"
+#include "i915_utils.h"
 #include "intel_device_info.h"
 #include "intel_memory_region.h"
 #include "intel_pch.h"
@@ -94,28 +79,32 @@
 #include "intel_runtime_pm.h"
 #include "intel_step.h"
 #include "intel_uncore.h"
-#include "intel_wakeref.h"
 #include "intel_wopcm.h"
 
-#include "i915_gem.h"
-#include "i915_gem_gtt.h"
-#include "i915_gpu_error.h"
-#include "i915_perf_types.h"
-#include "i915_request.h"
-#include "i915_scheduler.h"
-#include "gt/intel_timeline.h"
-#include "i915_vma.h"
-
-
-/* General customization:
- */
-
-#define DRIVER_NAME		"i915"
-#define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20201103"
-#define DRIVER_TIMESTAMP	1604406085
-
+struct dpll;
+struct drm_i915_clock_gating_funcs;
 struct drm_i915_gem_object;
+struct drm_i915_private;
+struct intel_atomic_state;
+struct intel_audio_funcs;
+struct intel_cdclk_config;
+struct intel_cdclk_funcs;
+struct intel_cdclk_state;
+struct intel_cdclk_vals;
+struct intel_color_funcs;
+struct intel_connector;
+struct intel_crtc;
+struct intel_dp;
+struct intel_dpll_funcs;
+struct intel_encoder;
+struct intel_fbdev;
+struct intel_fdi_funcs;
+struct intel_hotplug_funcs;
+struct intel_initial_plane_config;
+struct intel_limit;
+struct intel_overlay;
+struct intel_overlay_error_state;
+struct vlv_s0ix_state;
 
 /* Threshold == 5 for long IRQs, 50 for short */
 #define HPD_STORM_DEFAULT_THRESHOLD 50
@@ -166,117 +155,6 @@ struct i915_hotplug {
 	 I915_GEM_DOMAIN_INSTRUCTION | \
 	 I915_GEM_DOMAIN_VERTEX)
 
-struct drm_i915_private;
-
-struct drm_i915_file_private {
-	struct drm_i915_private *dev_priv;
-
-	union {
-		struct drm_file *file;
-		struct rcu_head rcu;
-	};
-
-	/** @proto_context_lock: Guards all struct i915_gem_proto_context
-	 * operations
-	 *
-	 * This not only guards @proto_context_xa, but is always held
-	 * whenever we manipulate any struct i915_gem_proto_context,
-	 * including finalizing it on first actual use of the GEM context.
-	 *
-	 * See i915_gem_proto_context.
-	 */
-	struct mutex proto_context_lock;
-
-	/** @proto_context_xa: xarray of struct i915_gem_proto_context
-	 *
-	 * Historically, the context uAPI allowed for two methods of
-	 * setting context parameters: SET_CONTEXT_PARAM and
-	 * CONTEXT_CREATE_EXT_SETPARAM.  The former is allowed to be called
-	 * at any time while the later happens as part of
-	 * GEM_CONTEXT_CREATE.  Everything settable via one was settable
-	 * via the other.  While some params are fairly simple and setting
-	 * them on a live context is harmless such as the context priority,
-	 * others are far trickier such as the VM or the set of engines.
-	 * In order to swap out the VM, for instance, we have to delay
-	 * until all current in-flight work is complete, swap in the new
-	 * VM, and then continue.  This leads to a plethora of potential
-	 * race conditions we'd really rather avoid.
-	 *
-	 * We have since disallowed setting these more complex parameters
-	 * on active contexts.  This works by delaying the creation of the
-	 * actual context until after the client is done configuring it
-	 * with SET_CONTEXT_PARAM.  From the perspective of the client, it
-	 * has the same u32 context ID the whole time.  From the
-	 * perspective of i915, however, it's a struct i915_gem_proto_context
-	 * right up until the point where we attempt to do something which
-	 * the proto-context can't handle.  Then the struct i915_gem_context
-	 * gets created.
-	 *
-	 * This is accomplished via a little xarray dance.  When
-	 * GEM_CONTEXT_CREATE is called, we create a struct
-	 * i915_gem_proto_context, reserve a slot in @context_xa but leave
-	 * it NULL, and place the proto-context in the corresponding slot
-	 * in @proto_context_xa.  Then, in i915_gem_context_lookup(), we
-	 * first check @context_xa.  If it's there, we return the struct
-	 * i915_gem_context and we're done.  If it's not, we look in
-	 * @proto_context_xa and, if we find it there, we create the actual
-	 * context and kill the proto-context.
-	 *
-	 * In order for this dance to work properly, everything which ever
-	 * touches a struct i915_gem_proto_context is guarded by
-	 * @proto_context_lock, including context creation.  Yes, this
-	 * means context creation now takes a giant global lock but it
-	 * can't really be helped and that should never be on any driver's
-	 * fast-path anyway.
-	 */
-	struct xarray proto_context_xa;
-
-	/** @context_xa: xarray of fully created i915_gem_context
-	 *
-	 * Write access to this xarray is guarded by @proto_context_lock.
-	 * Otherwise, writers may race with finalize_create_context_locked().
-	 *
-	 * See @proto_context_xa.
-	 */
-	struct xarray context_xa;
-	struct xarray vm_xa;
-
-	unsigned int bsd_engine;
-
-/*
- * Every context ban increments per client ban score. Also
- * hangs in short succession increments ban score. If ban threshold
- * is reached, client is considered banned and submitting more work
- * will fail. This is a stop gap measure to limit the badly behaving
- * clients access to gpu. Note that unbannable contexts never increment
- * the client ban score.
- */
-#define I915_CLIENT_SCORE_HANG_FAST	1
-#define   I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
-#define I915_CLIENT_SCORE_CONTEXT_BAN   3
-#define I915_CLIENT_SCORE_BANNED	9
-	/** ban_score: Accumulated score of all ctx bans and fast hangs. */
-	atomic_t ban_score;
-	unsigned long hang_timestamp;
-};
-
-/* Interface history:
- *
- * 1.1: Original.
- * 1.2: Add Power Management
- * 1.3: Add vblank support
- * 1.4: Fix cmdbuffer path, add heap destroy
- * 1.5: Add vblank pipe configuration
- * 1.6: - New ioctl for scheduling buffer swaps on vertical blank
- *      - Support vertical blank on secondary display pipe
- */
-#define DRIVER_MAJOR		1
-#define DRIVER_MINOR		6
-#define DRIVER_PATCHLEVEL	0
-
-struct intel_overlay;
-struct intel_overlay_error_state;
-
 struct sdvo_device_mapping {
 	u8 initialized;
 	u8 dvo_port;
@@ -286,23 +164,6 @@ struct sdvo_device_mapping {
 	u8 ddc_pin;
 };
 
-struct intel_connector;
-struct intel_encoder;
-struct intel_atomic_state;
-struct intel_cdclk_config;
-struct intel_cdclk_funcs;
-struct intel_cdclk_state;
-struct intel_cdclk_vals;
-struct intel_initial_plane_config;
-struct intel_crtc;
-struct intel_limit;
-struct dpll;
-
-/* functions used internal in intel_pm.c */
-struct drm_i915_clock_gating_funcs {
-	void (*init_clock_gating)(struct drm_i915_private *dev_priv);
-};
-
 /* functions used for watermark calcs for display. */
 struct drm_i915_wm_disp_funcs {
 	/* update_wm is for legacy wm management */
@@ -320,38 +181,6 @@ struct drm_i915_wm_disp_funcs {
 	int (*compute_global_watermarks)(struct intel_atomic_state *state);
 };
 
-struct intel_color_funcs {
-	int (*color_check)(struct intel_crtc_state *crtc_state);
-	/*
-	 * Program double buffered color management registers during
-	 * vblank evasion. The registers should then latch during the
-	 * next vblank start, alongside any other double buffered registers
-	 * involved with the same commit.
-	 */
-	void (*color_commit)(const struct intel_crtc_state *crtc_state);
-	/*
-	 * Load LUTs (and other single buffered color management
-	 * registers). Will (hopefully) be called during the vblank
-	 * following the latching of any double buffered registers
-	 * involved with the same commit.
-	 */
-	void (*load_luts)(const struct intel_crtc_state *crtc_state);
-	void (*read_luts)(struct intel_crtc_state *crtc_state);
-};
-
-struct intel_hotplug_funcs {
-	void (*hpd_irq_setup)(struct drm_i915_private *dev_priv);
-};
-
-struct intel_fdi_funcs {
-	void (*fdi_link_train)(struct intel_crtc *crtc,
-			       const struct intel_crtc_state *crtc_state);
-};
-
-struct intel_dpll_funcs {
-	int (*crtc_compute_clock)(struct intel_crtc_state *crtc_state);
-};
-
 struct drm_i915_display_funcs {
 	/* Returns the active state of the crtc, and if the crtc is active,
 	 * fills out the pipe-config with the hw state. */
@@ -385,7 +214,6 @@ enum drrs_support_type {
 	SEAMLESS_DRRS_SUPPORT = 2
 };
 
-struct intel_dp;
 struct i915_drrs {
 	struct mutex mutex;
 	struct delayed_work work;
@@ -403,8 +231,6 @@ struct i915_drrs {
 #define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
 #define QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK (1<<8)
 
-struct intel_fbdev;
-
 struct intel_gmbus {
 	struct i2c_adapter adapter;
 #define GMBUS_FORCE_BIT_RETRY (1U << 31)
@@ -423,8 +249,6 @@ struct i915_suspend_saved_registers {
 	u16 saveGCDGMBUS;
 };
 
-struct vlv_s0ix_state;
-
 #define MAX_L3_SLICES 2
 struct intel_l3_parity {
 	u32 *remap_info[MAX_L3_SLICES];
@@ -533,6 +357,9 @@ struct intel_vbt_data {
 	unsigned int bios_lvds_val; /* initial [PCH_]LVDS reg val in VBIOS */
 	enum drm_panel_orientation orientation;
 
+	bool override_afc_startup;
+	u8 override_afc_startup_val;
+
 	enum drrs_support_type drrs_type;
 
 	struct {
@@ -613,7 +440,6 @@ struct i915_selftest_stash {
 };
 
 /* intel_audio.c private */
-struct intel_audio_funcs;
 struct intel_audio_private {
 	/* Display internal audio functions */
 	const struct intel_audio_funcs *funcs;
@@ -1657,65 +1483,16 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
-int i915_gem_dumb_create(struct drm_file *file_priv,
-			 struct drm_device *dev,
-			 struct drm_mode_create_dumb *args);
-
 int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
-static inline u32 i915_reset_count(struct i915_gpu_error *error)
-{
-	return atomic_read(&error->reset_count);
-}
-
-static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
-					  const struct intel_engine_cs *engine)
-{
-	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
-}
-
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
 void i915_gem_driver_register(struct drm_i915_private *i915);
 void i915_gem_driver_unregister(struct drm_i915_private *i915);
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv);
 void i915_gem_driver_release(struct drm_i915_private *dev_priv);
-void i915_gem_suspend(struct drm_i915_private *dev_priv);
-void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
-void i915_gem_resume(struct drm_i915_private *dev_priv);
 
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file);
 
-int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
-				    enum i915_cache_level cache_level);
-
-struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
-				struct dma_buf *dma_buf);
-
-struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags);
-
-static inline struct i915_address_space *
-i915_gem_vm_lookup(struct drm_i915_file_private *file_priv, u32 id)
-{
-	struct i915_address_space *vm;
-
-	xa_lock(&file_priv->vm_xa);
-	vm = xa_load(&file_priv->vm_xa, id);
-	if (vm)
-		kref_get(&vm->ref);
-	xa_unlock(&file_priv->vm_xa);
-
-	return vm;
-}
-
-/* i915_gem_internal.c */
-struct drm_i915_gem_object *
-i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
-				phys_addr_t size);
-struct drm_i915_gem_object *
-__i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
-				  const struct drm_i915_gem_object_ops *ops,
-				  phys_addr_t size);
-
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 {
@@ -1725,8 +1502,6 @@ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_objec
 		i915_gem_object_is_tiled(obj);
 }
 
-const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
-
 /* intel_device_info.c */
 static inline struct intel_device_info *
 mkwrite_device_info(struct drm_i915_private *dev_priv)
@@ -1734,14 +1509,6 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
 	return (struct intel_device_info *)INTEL_INFO(dev_priv);
 }
 
-static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
-{
-	if (GRAPHICS_VER(i915) >= 11)
-		return ICL_HWS_CSB_WRITE_INDEX;
-	else
-		return I915_HWS_CSB_WRITE_INDEX;
-}
-
 static inline enum i915_map_type
 i915_coherent_map_type(struct drm_i915_private *i915,
 		       struct drm_i915_gem_object *obj, bool always_coherent)
diff --git a/drivers/gpu/drm/i915/i915_file_private.h b/drivers/gpu/drm/i915/i915_file_private.h
new file mode 100644
index 000000000000..fb16cc431b2a
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_file_private.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_FILE_PRIVATE_H__
+#define __I915_FILE_PRIVATE_H__
+
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/xarray.h>
+
+struct drm_i915_private;
+struct drm_file;
+
+struct drm_i915_file_private {
+	struct drm_i915_private *dev_priv;
+
+	union {
+		struct drm_file *file;
+		struct rcu_head rcu;
+	};
+
+	/** @proto_context_lock: Guards all struct i915_gem_proto_context
+	 * operations
+	 *
+	 * This not only guards @proto_context_xa, but is always held
+	 * whenever we manipulate any struct i915_gem_proto_context,
+	 * including finalizing it on first actual use of the GEM context.
+	 *
+	 * See i915_gem_proto_context.
+	 */
+	struct mutex proto_context_lock;
+
+	/** @proto_context_xa: xarray of struct i915_gem_proto_context
+	 *
+	 * Historically, the context uAPI allowed for two methods of
+	 * setting context parameters: SET_CONTEXT_PARAM and
+	 * CONTEXT_CREATE_EXT_SETPARAM.  The former is allowed to be called
+	 * at any time while the later happens as part of
+	 * GEM_CONTEXT_CREATE.  Everything settable via one was settable
+	 * via the other.  While some params are fairly simple and setting
+	 * them on a live context is harmless such as the context priority,
+	 * others are far trickier such as the VM or the set of engines.
+	 * In order to swap out the VM, for instance, we have to delay
+	 * until all current in-flight work is complete, swap in the new
+	 * VM, and then continue.  This leads to a plethora of potential
+	 * race conditions we'd really rather avoid.
+	 *
+	 * We have since disallowed setting these more complex parameters
+	 * on active contexts.  This works by delaying the creation of the
+	 * actual context until after the client is done configuring it
+	 * with SET_CONTEXT_PARAM.  From the perspective of the client, it
+	 * has the same u32 context ID the whole time.  From the
+	 * perspective of i915, however, it's a struct i915_gem_proto_context
+	 * right up until the point where we attempt to do something which
+	 * the proto-context can't handle.  Then the struct i915_gem_context
+	 * gets created.
+	 *
+	 * This is accomplished via a little xarray dance.  When
+	 * GEM_CONTEXT_CREATE is called, we create a struct
+	 * i915_gem_proto_context, reserve a slot in @context_xa but leave
+	 * it NULL, and place the proto-context in the corresponding slot
+	 * in @proto_context_xa.  Then, in i915_gem_context_lookup(), we
+	 * first check @context_xa.  If it's there, we return the struct
+	 * i915_gem_context and we're done.  If it's not, we look in
+	 * @proto_context_xa and, if we find it there, we create the actual
+	 * context and kill the proto-context.
+	 *
+	 * In order for this dance to work properly, everything which ever
+	 * touches a struct i915_gem_proto_context is guarded by
+	 * @proto_context_lock, including context creation.  Yes, this
+	 * means context creation now takes a giant global lock but it
+	 * can't really be helped and that should never be on any driver's
+	 * fast-path anyway.
+	 */
+	struct xarray proto_context_xa;
+
+	/** @context_xa: xarray of fully created i915_gem_context
+	 *
+	 * Write access to this xarray is guarded by @proto_context_lock.
+	 * Otherwise, writers may race with finalize_create_context_locked().
+	 *
+	 * See @proto_context_xa.
+	 */
+	struct xarray context_xa;
+	struct xarray vm_xa;
+
+	unsigned int bsd_engine;
+
+/*
+ * Every context ban increments per client ban score. Also
+ * hangs in short succession increments ban score. If ban threshold
+ * is reached, client is considered banned and submitting more work
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
+ */
+#define I915_CLIENT_SCORE_HANG_FAST	1
+#define   I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN   3
+#define I915_CLIENT_SCORE_BANNED	9
+	/** ban_score: Accumulated score of all ctx bans and fast hangs. */
+	atomic_t ban_score;
+	unsigned long hang_timestamp;
+};
+
+#endif /* __I915_FILE_PRIVATE_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5ef959a9f594..db897fb11f9b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -25,7 +25,6 @@
  *
  */
 
-#include <drm/drm_vma_manager.h>
 #include <linux/dma-fence-array.h>
 #include <linux/kthread.h>
 #include <linux/dma-resv.h>
@@ -37,6 +36,9 @@
 #include <linux/dma-buf.h>
 #include <linux/mman.h>
 
+#include <drm/drm_cache.h>
+#include <drm/drm_vma_manager.h>
+
 #include "display/intel_display.h"
 #include "display/intel_frontbuffer.h"
 
@@ -44,6 +46,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_mman.h"
+#include "gem/i915_gem_pm.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_userptr.h"
 #include "gt/intel_engine_user.h"
@@ -52,9 +55,9 @@
 #include "gt/intel_workarounds.h"
 
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
-
 #include "intel_pm.h"
 
 static int
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 102c7bb747f8..79ef0e21d71a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -34,6 +34,7 @@
 #include <linux/utsname.h>
 #include <linux/zlib.h>
 
+#include <drm/drm_cache.h>
 #include <drm/drm_print.h>
 
 #include "display/intel_dmc.h"
@@ -46,6 +47,7 @@
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_gt_regs.h"
 
+#include "i915_driver.h"
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
 #include "i915_memcpy.h"
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 5aedf5129814..903d838e2e63 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -210,6 +210,17 @@ struct drm_i915_error_state_buf {
 	int err;
 };
 
+static inline u32 i915_reset_count(struct i915_gpu_error *error)
+{
+	return atomic_read(&error->reset_count);
+}
+
+static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
+					  const struct intel_engine_cs *engine)
+{
+	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 
 __printf(2, 3)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c05eb09d8a66..fdd568ba4a16 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -49,6 +49,7 @@
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_rps.h"
 
+#include "i915_driver.h"
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "intel_pm.h"
@@ -4347,6 +4348,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 	return ret;
 }
 
+struct intel_hotplug_funcs {
+	void (*hpd_irq_setup)(struct drm_i915_private *i915);
+};
+
 #define HPD_FUNCS(platform)					 \
 static const struct intel_hotplug_funcs platform##_hpd_funcs = { \
 	.hpd_irq_setup = platform##_hpd_irq_setup,		 \
@@ -4361,6 +4366,12 @@ HPD_FUNCS(spt);
 HPD_FUNCS(ilk);
 #undef HPD_FUNCS
 
+void intel_hpd_irq_setup(struct drm_i915_private *i915)
+{
+	if (i915->display_irqs_enabled && i915->hotplug_funcs)
+		i915->hotplug_funcs->hpd_irq_setup(i915);
+}
+
 /**
  * intel_irq_init - initializes irq support
  * @dev_priv: i915 device instance
diff --git a/drivers/gpu/drm/i915/i915_irq.h b/drivers/gpu/drm/i915/i915_irq.h
index 0eb90d271fa7..82639d9d7e82 100644
--- a/drivers/gpu/drm/i915/i915_irq.h
+++ b/drivers/gpu/drm/i915/i915_irq.h
@@ -37,6 +37,7 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv);
 void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv);
 
+void intel_hpd_irq_setup(struct drm_i915_private *i915);
 void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv,
 				   u32 mask,
 				   u32 bits);
diff --git a/drivers/gpu/drm/i915/i915_mitigations.c b/drivers/gpu/drm/i915/i915_mitigations.c
index 84f12598d145..def7302ef7fe 100644
--- a/drivers/gpu/drm/i915/i915_mitigations.c
+++ b/drivers/gpu/drm/i915/i915_mitigations.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+#include "i915_driver.h"
 #include "i915_drv.h"
 #include "i915_mitigations.h"
 
diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c
index 8451822637f0..f276005b8070 100644
--- a/drivers/gpu/drm/i915/i915_module.c
+++ b/drivers/gpu/drm/i915/i915_module.c
@@ -9,6 +9,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_object.h"
 #include "i915_active.h"
+#include "i915_driver.h"
 #include "i915_params.h"
 #include "i915_pci.h"
 #include "i915_perf.h"
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 189d3bb8955a..76e590fcb903 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -22,6 +22,7 @@
  *
  */
 
+#include <drm/drm_color_mgmt.h>
 #include <drm/drm_drv.h>
 #include <drm/i915_pciids.h>
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 590efdb9de8d..3ecb89e96fb6 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -196,6 +196,7 @@
 #include <linux/uuid.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_regs.h"
 #include "gt/intel_engine_user.h"
@@ -205,9 +206,11 @@
 #include "gt/intel_gt_clock_utils.h"
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_lrc.h"
+#include "gt/intel_lrc_reg.h"
 #include "gt/intel_ring.h"
 
 #include "i915_drv.h"
+#include "i915_file_private.h"
 #include "i915_perf.h"
 #include "i915_perf_oa_regs.h"
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 87c92314ee26..de403ee18bc7 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1830,117 +1830,8 @@
 					    _PALETTE_B, _CHV_PALETTE_C) + \
 				      (i) * 4)
 
-/* MCH MMIO space */
-
-/*
- * MCHBAR mirror.
- *
- * This mirrors the MCHBAR MMIO space whose location is determined by
- * device 0 function 0's pci config register 0x44 or 0x48 and matches it in
- * every way.  It is not accessible from the CP register read instructions.
- *
- * Starting from Haswell, you can't write registers using the MCHBAR mirror,
- * just read.
- */
-#define MCHBAR_MIRROR_BASE	0x10000
-
-#define MCHBAR_MIRROR_BASE_SNB	0x140000
-
-#define CTG_STOLEN_RESERVED		_MMIO(MCHBAR_MIRROR_BASE + 0x34)
-#define ELK_STOLEN_RESERVED		_MMIO(MCHBAR_MIRROR_BASE + 0x48)
-#define G4X_STOLEN_RESERVED_ADDR1_MASK	(0xFFFF << 16)
-#define G4X_STOLEN_RESERVED_ADDR2_MASK	(0xFFF << 4)
-#define G4X_STOLEN_RESERVED_ENABLE	(1 << 0)
-
-/* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */
-#define DCLK _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5e04)
-
-/* 915-945 and GM965 MCH register controlling DRAM channel access */
-#define DCC			_MMIO(MCHBAR_MIRROR_BASE + 0x200)
-#define DCC_ADDRESSING_MODE_SINGLE_CHANNEL		(0 << 0)
-#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC	(1 << 0)
-#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED	(2 << 0)
-#define DCC_ADDRESSING_MODE_MASK			(3 << 0)
-#define DCC_CHANNEL_XOR_DISABLE				(1 << 10)
-#define DCC_CHANNEL_XOR_BIT_17				(1 << 9)
-#define DCC2			_MMIO(MCHBAR_MIRROR_BASE + 0x204)
-#define DCC2_MODIFIED_ENHANCED_DISABLE			(1 << 20)
-
-/* Pineview MCH register contains DDR3 setting */
-#define CSHRDDR3CTL            _MMIO(MCHBAR_MIRROR_BASE + 0x1a8)
-#define CSHRDDR3CTL_DDR3       (1 << 2)
-
-/* 965 MCH register controlling DRAM channel configuration */
-#define C0DRB3_BW		_MMIO(MCHBAR_MIRROR_BASE + 0x206)
-#define C1DRB3_BW		_MMIO(MCHBAR_MIRROR_BASE + 0x606)
-
-/* snb MCH registers for reading the DRAM channel configuration */
-#define MAD_DIMM_C0			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5004)
-#define MAD_DIMM_C1			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5008)
-#define MAD_DIMM_C2			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x500C)
-#define   MAD_DIMM_ECC_MASK		(0x3 << 24)
-#define   MAD_DIMM_ECC_OFF		(0x0 << 24)
-#define   MAD_DIMM_ECC_IO_ON_LOGIC_OFF	(0x1 << 24)
-#define   MAD_DIMM_ECC_IO_OFF_LOGIC_ON	(0x2 << 24)
-#define   MAD_DIMM_ECC_ON		(0x3 << 24)
-#define   MAD_DIMM_ENH_INTERLEAVE	(0x1 << 22)
-#define   MAD_DIMM_RANK_INTERLEAVE	(0x1 << 21)
-#define   MAD_DIMM_B_WIDTH_X16		(0x1 << 20) /* X8 chips if unset */
-#define   MAD_DIMM_A_WIDTH_X16		(0x1 << 19) /* X8 chips if unset */
-#define   MAD_DIMM_B_DUAL_RANK		(0x1 << 18)
-#define   MAD_DIMM_A_DUAL_RANK		(0x1 << 17)
-#define   MAD_DIMM_A_SELECT		(0x1 << 16)
-/* DIMM sizes are in multiples of 256mb. */
-#define   MAD_DIMM_B_SIZE_SHIFT		8
-#define   MAD_DIMM_B_SIZE_MASK		(0xff << MAD_DIMM_B_SIZE_SHIFT)
-#define   MAD_DIMM_A_SIZE_SHIFT		0
-#define   MAD_DIMM_A_SIZE_MASK		(0xff << MAD_DIMM_A_SIZE_SHIFT)
-
-/* snb MCH registers for priority tuning */
-#define MCH_SSKPD			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5d10)
-#define   MCH_SSKPD_WM0_MASK		0x3f
-#define   MCH_SSKPD_WM0_VAL		0xc
-
-/* Clocking configuration register */
-#define CLKCFG			_MMIO(MCHBAR_MIRROR_BASE + 0xc00)
-#define CLKCFG_FSB_400					(0 << 0)	/* hrawclk 100 */
-#define CLKCFG_FSB_400_ALT				(5 << 0)	/* hrawclk 100 */
-#define CLKCFG_FSB_533					(1 << 0)	/* hrawclk 133 */
-#define CLKCFG_FSB_667					(3 << 0)	/* hrawclk 166 */
-#define CLKCFG_FSB_800					(2 << 0)	/* hrawclk 200 */
-#define CLKCFG_FSB_1067					(6 << 0)	/* hrawclk 266 */
-#define CLKCFG_FSB_1067_ALT				(0 << 0)	/* hrawclk 266 */
-#define CLKCFG_FSB_1333					(7 << 0)	/* hrawclk 333 */
-#define CLKCFG_FSB_1333_ALT				(4 << 0)	/* hrawclk 333 */
-#define CLKCFG_FSB_1600_ALT				(6 << 0)	/* hrawclk 400 */
-#define CLKCFG_FSB_MASK					(7 << 0)
-#define CLKCFG_MEM_533					(1 << 4)
-#define CLKCFG_MEM_667					(2 << 4)
-#define CLKCFG_MEM_800					(3 << 4)
-#define CLKCFG_MEM_MASK					(7 << 4)
-
-#define HPLLVCO                 _MMIO(MCHBAR_MIRROR_BASE + 0xc38)
-#define HPLLVCO_MOBILE          _MMIO(MCHBAR_MIRROR_BASE + 0xc0f)
-
-#define TSC1			_MMIO(0x11001)
-#define   TSE			(1 << 0)
-#define TR1			_MMIO(0x11006)
-#define TSFS			_MMIO(0x11020)
-#define   TSFS_SLOPE_MASK	0x0000ff00
-#define   TSFS_SLOPE_SHIFT	8
-#define   TSFS_INTR_MASK	0x000000ff
-
-#define CSIPLL0			_MMIO(0x12c10)
-#define DDRMPLL1		_MMIO(0X12c20)
 #define PEG_BAND_GAP_DATA	_MMIO(0x14d68)
 
-#define GEN6_GT_PERF_STATUS	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5948)
-#define BXT_GT_PERF_STATUS      _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7070)
-#define GEN6_RP_STATE_LIMITS	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
-#define GEN6_RP_STATE_CAP	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
-#define   RP0_CAP_MASK		REG_GENMASK(7, 0)
-#define   RP1_CAP_MASK		REG_GENMASK(15, 8)
-#define   RPN_CAP_MASK		REG_GENMASK(23, 16)
 #define BXT_RP_STATE_CAP        _MMIO(0x138170)
 #define GEN9_RP_STATE_LIMITS	_MMIO(0x138148)
 #define XEHPSDV_RP_STATE_CAP	_MMIO(0x250014)
@@ -4291,49 +4182,32 @@
 #define _WM0_PIPEC_IVB		0x45200
 #define WM0_PIPE_ILK(pipe)	_MMIO_PIPE3((pipe), _WM0_PIPEA_ILK, \
 					    _WM0_PIPEB_ILK, _WM0_PIPEC_IVB)
-#define  WM0_PIPE_PLANE_MASK	(0xffff << 16)
-#define  WM0_PIPE_PLANE_SHIFT	16
-#define  WM0_PIPE_SPRITE_MASK	(0xff << 8)
-#define  WM0_PIPE_SPRITE_SHIFT	8
-#define  WM0_PIPE_CURSOR_MASK	(0xff)
+#define  WM0_PIPE_PRIMARY_MASK	REG_GENMASK(31, 16)
+#define  WM0_PIPE_SPRITE_MASK	REG_GENMASK(15, 8)
+#define  WM0_PIPE_CURSOR_MASK	REG_GENMASK(7, 0)
+#define  WM0_PIPE_PRIMARY(x)	REG_FIELD_PREP(WM0_PIPE_PRIMARY_MASK, (x))
+#define  WM0_PIPE_SPRITE(x)	REG_FIELD_PREP(WM0_PIPE_SPRITE_MASK, (x))
+#define  WM0_PIPE_CURSOR(x)	REG_FIELD_PREP(WM0_PIPE_CURSOR_MASK, (x))
 #define WM1_LP_ILK		_MMIO(0x45108)
-#define  WM1_LP_SR_EN		(1 << 31)
-#define  WM1_LP_LATENCY_SHIFT	24
-#define  WM1_LP_LATENCY_MASK	(0x7f << 24)
-#define  WM1_LP_FBC_MASK	(0xf << 20)
-#define  WM1_LP_FBC_SHIFT	20
-#define  WM1_LP_FBC_SHIFT_BDW	19
-#define  WM1_LP_SR_MASK		(0x7ff << 8)
-#define  WM1_LP_SR_SHIFT	8
-#define  WM1_LP_CURSOR_MASK	(0xff)
 #define WM2_LP_ILK		_MMIO(0x4510c)
-#define  WM2_LP_EN		(1 << 31)
 #define WM3_LP_ILK		_MMIO(0x45110)
-#define  WM3_LP_EN		(1 << 31)
+#define  WM_LP_ENABLE		REG_BIT(31)
+#define  WM_LP_LATENCY_MASK	REG_GENMASK(30, 24)
+#define  WM_LP_FBC_MASK_BDW	REG_GENMASK(23, 19)
+#define  WM_LP_FBC_MASK_ILK	REG_GENMASK(23, 20)
+#define  WM_LP_PRIMARY_MASK	REG_GENMASK(18, 8)
+#define  WM_LP_CURSOR_MASK	REG_GENMASK(7, 0)
+#define  WM_LP_LATENCY(x)	REG_FIELD_PREP(WM_LP_LATENCY_MASK, (x))
+#define  WM_LP_FBC_BDW(x)	REG_FIELD_PREP(WM_LP_FBC_MASK_BDW, (x))
+#define  WM_LP_FBC_ILK(x)	REG_FIELD_PREP(WM_LP_FBC_MASK_ILK, (x))
+#define  WM_LP_PRIMARY(x)	REG_FIELD_PREP(WM_LP_PRIMARY_MASK, (x))
+#define  WM_LP_CURSOR(x)	REG_FIELD_PREP(WM_LP_CURSOR_MASK, (x))
 #define WM1S_LP_ILK		_MMIO(0x45120)
 #define WM2S_LP_IVB		_MMIO(0x45124)
 #define WM3S_LP_IVB		_MMIO(0x45128)
-#define  WM1S_LP_EN		(1 << 31)
-
-#define HSW_WM_LP_VAL(lat, fbc, pri, cur) \
-	(WM3_LP_EN | ((lat) << WM1_LP_LATENCY_SHIFT) | \
-	 ((fbc) << WM1_LP_FBC_SHIFT) | ((pri) << WM1_LP_SR_SHIFT) | (cur))
-
-/* Memory latency timer register */
-#define MLTR_ILK		_MMIO(0x11222)
-#define  MLTR_WM1_SHIFT		0
-#define  MLTR_WM2_SHIFT		8
-/* the unit of memory self-refresh latency time is 0.5us */
-#define  ILK_SRLT_MASK		0x3f
-
-
-/* the address where we get all kinds of latency value */
-#define SSKPD			_MMIO(0x5d10)
-#define SSKPD_WM_MASK		0x3f
-#define SSKPD_WM0_SHIFT		0
-#define SSKPD_WM1_SHIFT		8
-#define SSKPD_WM2_SHIFT		16
-#define SSKPD_WM3_SHIFT		24
+#define  WM_LP_SPRITE_ENABLE	REG_BIT(31) /* ilk/snb WM1S only */
+#define  WM_LP_SPRITE_MASK	REG_GENMASK(10, 0)
+#define  WM_LP_SPRITE(x)	REG_FIELD_PREP(WM_LP_SPRITE_MASK, (x))
 
 /*
  * The two pipe frame counter registers are not synchronized, so
@@ -5632,7 +5506,8 @@
 #define TGL_DMC_DEBUG_DC6_COUNT	_MMIO(0x101088)
 #define DG1_DMC_DEBUG_DC5_COUNT	_MMIO(0x134154)
 
-#define DMC_DEBUG3		_MMIO(0x101090)
+#define TGL_DMC_DEBUG3		_MMIO(0x101090)
+#define DG1_DMC_DEBUG3		_MMIO(0x13415c)
 
 /* Display Internal Timeout Register */
 #define RM_TIMEOUT		_MMIO(0x42060)
@@ -6040,11 +5915,14 @@
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1 << 4)
 
-#define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
-#define   SKL_SELECT_ALTERNATE_DC_EXIT	REG_BIT(30)
-#define   ICL_DELAY_PMRSP		REG_BIT(22)
-#define   DISABLE_FLR_SRC		REG_BIT(15)
-#define   MASK_WAKEMEM			REG_BIT(13)
+#define GEN8_CHICKEN_DCPR_1			_MMIO(0x46430)
+#define   SKL_SELECT_ALTERNATE_DC_EXIT		REG_BIT(30)
+#define   LATENCY_REPORTING_REMOVED_PIPE_C	REG_BIT(25)
+#define   LATENCY_REPORTING_REMOVED_PIPE_B	REG_BIT(24)
+#define   LATENCY_REPORTING_REMOVED_PIPE_A	REG_BIT(23)
+#define   ICL_DELAY_PMRSP			REG_BIT(22)
+#define   DISABLE_FLR_SRC			REG_BIT(15)
+#define   MASK_WAKEMEM				REG_BIT(13)
 
 #define GEN11_CHICKEN_DCPR_2			_MMIO(0x46434)
 #define   DCPR_MASK_MAXLATENCY_MEMUP_CLR	REG_BIT(27)
@@ -7986,6 +7864,12 @@ enum skl_power_gate {
 #define RKL_DPLL_CFGCR0(pll)		_MMIO_PLL(pll, _TGL_DPLL0_CFGCR0, \
 						  _TGL_DPLL1_CFGCR0)
 
+#define _TGL_DPLL0_DIV0					0x164B00
+#define _TGL_DPLL1_DIV0					0x164C00
+#define TGL_DPLL0_DIV0(pll)				_MMIO_PLL(pll, _TGL_DPLL0_DIV0, _TGL_DPLL1_DIV0)
+#define   TGL_DPLL0_DIV0_AFC_STARTUP_MASK		REG_GENMASK(27, 25)
+#define   TGL_DPLL0_DIV0_AFC_STARTUP(val)		REG_FIELD_PREP(TGL_DPLL0_DIV0_AFC_STARTUP_MASK, (val))
+
 #define _TGL_DPLL0_CFGCR1		0x164288
 #define _TGL_DPLL1_CFGCR1		0x164290
 #define _TGL_TBTPLL_CFGCR1		0x1642A0
@@ -8033,6 +7917,8 @@ enum skl_power_gate {
 
 /* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */
 #define _DKL_PLL_DIV0			0x200
+#define   DKL_PLL_DIV0_AFC_STARTUP_MASK	REG_GENMASK(27, 25)
+#define   DKL_PLL_DIV0_AFC_STARTUP(val)	REG_FIELD_PREP(DKL_PLL_DIV0_AFC_STARTUP_MASK, (val))
 #define   DKL_PLL_DIV0_INTEG_COEFF(x)	((x) << 16)
 #define   DKL_PLL_DIV0_INTEG_COEFF_MASK	(0x1F << 16)
 #define   DKL_PLL_DIV0_PROP_COEFF(x)	((x) << 12)
@@ -8042,6 +7928,10 @@ enum skl_power_gate {
 #define   DKL_PLL_DIV0_FBPREDIV_MASK	(0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT)
 #define   DKL_PLL_DIV0_FBDIV_INT(x)	((x) << 0)
 #define   DKL_PLL_DIV0_FBDIV_INT_MASK	(0xFF << 0)
+#define   DKL_PLL_DIV0_MASK		(DKL_PLL_DIV0_INTEG_COEFF_MASK | \
+					 DKL_PLL_DIV0_PROP_COEFF_MASK | \
+					 DKL_PLL_DIV0_FBPREDIV_MASK | \
+					 DKL_PLL_DIV0_FBDIV_INT_MASK)
 #define DKL_PLL_DIV0(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
 						    _DKL_PHY2_BASE) + \
 						    _DKL_PLL_DIV0)
@@ -8215,93 +8105,7 @@ enum skl_power_gate {
 #define  DC_STATE_DEBUG_MASK_CORES	(1 << 0)
 #define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1 << 1)
 
-#define BXT_D_CR_DRP0_DUNIT8			0x1000
-#define BXT_D_CR_DRP0_DUNIT9			0x1200
-#define  BXT_D_CR_DRP0_DUNIT_START		8
-#define  BXT_D_CR_DRP0_DUNIT_END		11
-#define BXT_D_CR_DRP0_DUNIT(x)	_MMIO(MCHBAR_MIRROR_BASE_SNB + \
-				      _PICK_EVEN((x) - 8, BXT_D_CR_DRP0_DUNIT8,\
-						 BXT_D_CR_DRP0_DUNIT9))
-#define  BXT_DRAM_RANK_MASK			0x3
-#define  BXT_DRAM_RANK_SINGLE			0x1
-#define  BXT_DRAM_RANK_DUAL			0x3
-#define  BXT_DRAM_WIDTH_MASK			(0x3 << 4)
-#define  BXT_DRAM_WIDTH_SHIFT			4
-#define  BXT_DRAM_WIDTH_X8			(0x0 << 4)
-#define  BXT_DRAM_WIDTH_X16			(0x1 << 4)
-#define  BXT_DRAM_WIDTH_X32			(0x2 << 4)
-#define  BXT_DRAM_WIDTH_X64			(0x3 << 4)
-#define  BXT_DRAM_SIZE_MASK			(0x7 << 6)
-#define  BXT_DRAM_SIZE_SHIFT			6
-#define  BXT_DRAM_SIZE_4GBIT			(0x0 << 6)
-#define  BXT_DRAM_SIZE_6GBIT			(0x1 << 6)
-#define  BXT_DRAM_SIZE_8GBIT			(0x2 << 6)
-#define  BXT_DRAM_SIZE_12GBIT			(0x3 << 6)
-#define  BXT_DRAM_SIZE_16GBIT			(0x4 << 6)
-#define  BXT_DRAM_TYPE_MASK			(0x7 << 22)
-#define  BXT_DRAM_TYPE_SHIFT			22
-#define  BXT_DRAM_TYPE_DDR3			(0x0 << 22)
-#define  BXT_DRAM_TYPE_LPDDR3			(0x1 << 22)
-#define  BXT_DRAM_TYPE_LPDDR4			(0x2 << 22)
-#define  BXT_DRAM_TYPE_DDR4			(0x4 << 22)
-
-#define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5E04)
-#define  DG1_GEAR_TYPE				REG_BIT(16)
-
-#define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000)
-#define  SKL_DRAM_DDR_TYPE_MASK			(0x3 << 0)
-#define  SKL_DRAM_DDR_TYPE_DDR4			(0 << 0)
-#define  SKL_DRAM_DDR_TYPE_DDR3			(1 << 0)
-#define  SKL_DRAM_DDR_TYPE_LPDDR3		(2 << 0)
-#define  SKL_DRAM_DDR_TYPE_LPDDR4		(3 << 0)
-
-#define SKL_MAD_DIMM_CH0_0_0_0_MCHBAR_MCMAIN	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x500C)
-#define SKL_MAD_DIMM_CH1_0_0_0_MCHBAR_MCMAIN	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5010)
-#define  SKL_DRAM_S_SHIFT			16
-#define  SKL_DRAM_SIZE_MASK			0x3F
-#define  SKL_DRAM_WIDTH_MASK			(0x3 << 8)
-#define  SKL_DRAM_WIDTH_SHIFT			8
-#define  SKL_DRAM_WIDTH_X8			(0x0 << 8)
-#define  SKL_DRAM_WIDTH_X16			(0x1 << 8)
-#define  SKL_DRAM_WIDTH_X32			(0x2 << 8)
-#define  SKL_DRAM_RANK_MASK			(0x1 << 10)
-#define  SKL_DRAM_RANK_SHIFT			10
-#define  SKL_DRAM_RANK_1			(0x0 << 10)
-#define  SKL_DRAM_RANK_2			(0x1 << 10)
-#define  SKL_DRAM_RANK_MASK			(0x1 << 10)
-#define  ICL_DRAM_SIZE_MASK			0x7F
-#define  ICL_DRAM_WIDTH_MASK			(0x3 << 7)
-#define  ICL_DRAM_WIDTH_SHIFT			7
-#define  ICL_DRAM_WIDTH_X8			(0x0 << 7)
-#define  ICL_DRAM_WIDTH_X16			(0x1 << 7)
-#define  ICL_DRAM_WIDTH_X32			(0x2 << 7)
-#define  ICL_DRAM_RANK_MASK			(0x3 << 9)
-#define  ICL_DRAM_RANK_SHIFT			9
-#define  ICL_DRAM_RANK_1			(0x0 << 9)
-#define  ICL_DRAM_RANK_2			(0x1 << 9)
-#define  ICL_DRAM_RANK_3			(0x2 << 9)
-#define  ICL_DRAM_RANK_4			(0x3 << 9)
-
-#define SA_PERF_STATUS_0_0_0_MCHBAR_PC		_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5918)
-#define  DG1_QCLK_RATIO_MASK			REG_GENMASK(9, 2)
-#define  DG1_QCLK_REFERENCE			REG_BIT(10)
-
-#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4000)
-#define   DG1_DRAM_T_RDPRE_MASK			REG_GENMASK(16, 11)
-#define   DG1_DRAM_T_RP_MASK			REG_GENMASK(6, 0)
-#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR_HIGH	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4004)
-#define   DG1_DRAM_T_RCD_MASK			REG_GENMASK(15, 9)
-#define   DG1_DRAM_T_RAS_MASK			REG_GENMASK(8, 1)
-
-/*
- * Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
- * since on HSW we can't write to it using intel_uncore_write.
- */
-#define D_COMP_HSW			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5F0C)
 #define D_COMP_BDW			_MMIO(0x138144)
-#define  D_COMP_RCOMP_IN_PROGRESS	(1 << 9)
-#define  D_COMP_COMP_FORCE		(1 << 8)
-#define  D_COMP_COMP_DISABLE		(1 << 0)
 
 /* Pipe WM_LINETIME - watermark line time */
 #define _WM_LINETIME_A		0x45270
diff --git a/drivers/gpu/drm/i915/i915_reg_defs.h b/drivers/gpu/drm/i915/i915_reg_defs.h
index 34d37bbf08cd..d78d78fce431 100644
--- a/drivers/gpu/drm/i915/i915_reg_defs.h
+++ b/drivers/gpu/drm/i915/i915_reg_defs.h
@@ -37,6 +37,21 @@
 				 __is_constexpr(__low) &&		\
 				 ((__low) < 0 || (__high) > 31 || (__low) > (__high)))))
 
+/**
+ * REG_GENMASK64() - Prepare a continuous u64 bitmask
+ * @__high: 0-based high bit
+ * @__low: 0-based low bit
+ *
+ * Local wrapper for GENMASK_ULL() to force u64, with compile time checks.
+ *
+ * @return: Continuous bitmask from @__high to @__low, inclusive.
+ */
+#define REG_GENMASK64(__high, __low)					\
+	((u64)(GENMASK_ULL(__high, __low) +				\
+	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&		\
+				 __is_constexpr(__low) &&		\
+				 ((__low) < 0 || (__high) > 63 || (__low) > (__high)))))
+
 /*
  * Local integer constant expression version of is_power_of_2().
  */
@@ -71,6 +86,18 @@
  */
 #define REG_FIELD_GET(__mask, __val)	((u32)FIELD_GET(__mask, __val))
 
+/**
+ * REG_FIELD_GET64() - Extract a u64 bitfield value
+ * @__mask: shifted mask defining the field's length and position
+ * @__val: value to extract the bitfield value from
+ *
+ * Local wrapper for FIELD_GET() to force u64 and for consistency with
+ * REG_GENMASK64().
+ *
+ * @return: Masked and shifted value of the field defined by @__mask in @__val.
+ */
+#define REG_FIELD_GET64(__mask, __val)	((u64)FIELD_GET(__mask, __val))
+
 typedef struct {
 	u32 reg;
 } i915_reg_t;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 5d94f86940f7..505276373cc2 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -44,6 +44,7 @@
 
 #include "i915_active.h"
 #include "i915_deps.h"
+#include "i915_driver.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_pm.h"
diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c
index 723bd0411a0e..174c95c3e10f 100644
--- a/drivers/gpu/drm/i915/intel_dram.c
+++ b/drivers/gpu/drm/i915/intel_dram.c
@@ -6,6 +6,7 @@
 #include "i915_drv.h"
 #include "i915_reg.h"
 #include "intel_dram.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 
 struct dram_dimm_info {
diff --git a/drivers/gpu/drm/i915/intel_mchbar_regs.h b/drivers/gpu/drm/i915/intel_mchbar_regs.h
new file mode 100644
index 000000000000..2aad2f0cc8db
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_mchbar_regs.h
@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_MCHBAR_REGS__
+#define __INTEL_MCHBAR_REGS__
+
+#include "i915_reg_defs.h"
+
+/*
+ * MCHBAR mirror.
+ *
+ * This mirrors the MCHBAR MMIO space whose location is determined by
+ * device 0 function 0's pci config register 0x44 or 0x48 and matches it in
+ * every way.  It is not accessible from the CP register read instructions.
+ *
+ * Starting from Haswell, you can't write registers using the MCHBAR mirror,
+ * just read.
+ */
+
+#define MCHBAR_MIRROR_BASE			0x10000
+#define MCHBAR_MIRROR_BASE_SNB			0x140000
+
+#define CTG_STOLEN_RESERVED			_MMIO(MCHBAR_MIRROR_BASE + 0x34)
+#define ELK_STOLEN_RESERVED			_MMIO(MCHBAR_MIRROR_BASE + 0x48)
+#define   G4X_STOLEN_RESERVED_ADDR1_MASK	(0xFFFF << 16)
+#define   G4X_STOLEN_RESERVED_ADDR2_MASK	(0xFFF << 4)
+#define   G4X_STOLEN_RESERVED_ENABLE		(1 << 0)
+
+/* Pineview MCH register contains DDR3 setting */
+#define CSHRDDR3CTL				_MMIO(MCHBAR_MIRROR_BASE + 0x1a8)
+#define   CSHRDDR3CTL_DDR3			(1 << 2)
+
+/* 915-945 and GM965 MCH register controlling DRAM channel access */
+#define DCC					_MMIO(MCHBAR_MIRROR_BASE + 0x200)
+#define   DCC_ADDRESSING_MODE_SINGLE_CHANNEL	(0 << 0)
+#define   DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC	(1 << 0)
+#define   DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED	(2 << 0)
+#define   DCC_ADDRESSING_MODE_MASK		(3 << 0)
+#define   DCC_CHANNEL_XOR_DISABLE		(1 << 10)
+#define   DCC_CHANNEL_XOR_BIT_17		(1 << 9)
+#define DCC2					_MMIO(MCHBAR_MIRROR_BASE + 0x204)
+#define   DCC2_MODIFIED_ENHANCED_DISABLE	(1 << 20)
+
+/* 965 MCH register controlling DRAM channel configuration */
+#define C0DRB3_BW				_MMIO(MCHBAR_MIRROR_BASE + 0x206)
+#define C1DRB3_BW				_MMIO(MCHBAR_MIRROR_BASE + 0x606)
+
+/* Clocking configuration register */
+#define CLKCFG					_MMIO(MCHBAR_MIRROR_BASE + 0xc00)
+#define CLKCFG_FSB_400				(0 << 0)	/* hrawclk 100 */
+#define CLKCFG_FSB_400_ALT			(5 << 0)	/* hrawclk 100 */
+#define CLKCFG_FSB_533				(1 << 0)	/* hrawclk 133 */
+#define CLKCFG_FSB_667				(3 << 0)	/* hrawclk 166 */
+#define CLKCFG_FSB_800				(2 << 0)	/* hrawclk 200 */
+#define CLKCFG_FSB_1067				(6 << 0)	/* hrawclk 266 */
+#define CLKCFG_FSB_1067_ALT			(0 << 0)	/* hrawclk 266 */
+#define CLKCFG_FSB_1333				(7 << 0)	/* hrawclk 333 */
+#define CLKCFG_FSB_1333_ALT			(4 << 0)	/* hrawclk 333 */
+#define CLKCFG_FSB_1600_ALT			(6 << 0)	/* hrawclk 400 */
+#define CLKCFG_FSB_MASK				(7 << 0)
+#define CLKCFG_MEM_533				(1 << 4)
+#define CLKCFG_MEM_667				(2 << 4)
+#define CLKCFG_MEM_800				(3 << 4)
+#define CLKCFG_MEM_MASK				(7 << 4)
+
+#define HPLLVCO_MOBILE				_MMIO(MCHBAR_MIRROR_BASE + 0xc0f)
+#define HPLLVCO					_MMIO(MCHBAR_MIRROR_BASE + 0xc38)
+
+#define TSC1					_MMIO(MCHBAR_MIRROR_BASE + 0x1001)
+#define   TSE					(1 << 0)
+#define TR1					_MMIO(MCHBAR_MIRROR_BASE + 0x1006)
+#define TSFS					_MMIO(MCHBAR_MIRROR_BASE + 0x1020)
+#define   TSFS_SLOPE_MASK			0x0000ff00
+#define   TSFS_SLOPE_SHIFT			8
+#define   TSFS_INTR_MASK			0x000000ff
+
+/* Memory latency timer register */
+#define MLTR_ILK				_MMIO(MCHBAR_MIRROR_BASE + 0x1222)
+/* the unit of memory self-refresh latency time is 0.5us */
+#define   MLTR_WM2_MASK				REG_GENMASK(13, 8)
+#define   MLTR_WM1_MASK				REG_GENMASK(5, 0)
+
+#define CSIPLL0					_MMIO(MCHBAR_MIRROR_BASE + 0x2c10)
+#define DDRMPLL1				_MMIO(MCHBAR_MIRROR_BASE + 0x2c20)
+
+#define ILK_GDSR				_MMIO(MCHBAR_MIRROR_BASE + 0x2ca4)
+#define  ILK_GRDOM_FULL				(0 << 1)
+#define  ILK_GRDOM_RENDER			(1 << 1)
+#define  ILK_GRDOM_MEDIA			(3 << 1)
+#define  ILK_GRDOM_MASK				(3 << 1)
+#define  ILK_GRDOM_RESET_ENABLE			(1 << 0)
+
+#define BXT_D_CR_DRP0_DUNIT8			0x1000
+#define BXT_D_CR_DRP0_DUNIT9			0x1200
+#define   BXT_D_CR_DRP0_DUNIT_START		8
+#define   BXT_D_CR_DRP0_DUNIT_END		11
+#define BXT_D_CR_DRP0_DUNIT(x)			_MMIO(MCHBAR_MIRROR_BASE_SNB + \
+						      _PICK_EVEN((x) - 8, BXT_D_CR_DRP0_DUNIT8,\
+								 BXT_D_CR_DRP0_DUNIT9))
+#define   BXT_DRAM_RANK_MASK			0x3
+#define   BXT_DRAM_RANK_SINGLE			0x1
+#define   BXT_DRAM_RANK_DUAL			0x3
+#define   BXT_DRAM_WIDTH_MASK			(0x3 << 4)
+#define   BXT_DRAM_WIDTH_SHIFT			4
+#define   BXT_DRAM_WIDTH_X8			(0x0 << 4)
+#define   BXT_DRAM_WIDTH_X16			(0x1 << 4)
+#define   BXT_DRAM_WIDTH_X32			(0x2 << 4)
+#define   BXT_DRAM_WIDTH_X64			(0x3 << 4)
+#define   BXT_DRAM_SIZE_MASK			(0x7 << 6)
+#define   BXT_DRAM_SIZE_SHIFT			6
+#define   BXT_DRAM_SIZE_4GBIT			(0x0 << 6)
+#define   BXT_DRAM_SIZE_6GBIT			(0x1 << 6)
+#define   BXT_DRAM_SIZE_8GBIT			(0x2 << 6)
+#define   BXT_DRAM_SIZE_12GBIT			(0x3 << 6)
+#define   BXT_DRAM_SIZE_16GBIT			(0x4 << 6)
+#define   BXT_DRAM_TYPE_MASK			(0x7 << 22)
+#define   BXT_DRAM_TYPE_SHIFT			22
+#define   BXT_DRAM_TYPE_DDR3			(0x0 << 22)
+#define   BXT_DRAM_TYPE_LPDDR3			(0x1 << 22)
+#define   BXT_DRAM_TYPE_LPDDR4			(0x2 << 22)
+#define   BXT_DRAM_TYPE_DDR4			(0x4 << 22)
+
+#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4000)
+#define   DG1_DRAM_T_RDPRE_MASK			REG_GENMASK(16, 11)
+#define   DG1_DRAM_T_RP_MASK			REG_GENMASK(6, 0)
+#define MCHBAR_CH0_CR_TC_PRE_0_0_0_MCHBAR_HIGH	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4004)
+#define   DG1_DRAM_T_RCD_MASK			REG_GENMASK(15, 9)
+#define   DG1_DRAM_T_RAS_MASK			REG_GENMASK(8, 1)
+
+#define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000)
+#define   SKL_DRAM_DDR_TYPE_MASK		(0x3 << 0)
+#define   SKL_DRAM_DDR_TYPE_DDR4		(0 << 0)
+#define   SKL_DRAM_DDR_TYPE_DDR3		(1 << 0)
+#define   SKL_DRAM_DDR_TYPE_LPDDR3		(2 << 0)
+#define   SKL_DRAM_DDR_TYPE_LPDDR4		(3 << 0)
+
+/* snb MCH registers for reading the DRAM channel configuration */
+#define MAD_DIMM_C0				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5004)
+#define MAD_DIMM_C1				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5008)
+#define MAD_DIMM_C2				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x500C)
+#define   MAD_DIMM_ECC_MASK			(0x3 << 24)
+#define   MAD_DIMM_ECC_OFF			(0x0 << 24)
+#define   MAD_DIMM_ECC_IO_ON_LOGIC_OFF		(0x1 << 24)
+#define   MAD_DIMM_ECC_IO_OFF_LOGIC_ON		(0x2 << 24)
+#define   MAD_DIMM_ECC_ON			(0x3 << 24)
+#define   MAD_DIMM_ENH_INTERLEAVE		(0x1 << 22)
+#define   MAD_DIMM_RANK_INTERLEAVE		(0x1 << 21)
+#define   MAD_DIMM_B_WIDTH_X16			(0x1 << 20) /* X8 chips if unset */
+#define   MAD_DIMM_A_WIDTH_X16			(0x1 << 19) /* X8 chips if unset */
+#define   MAD_DIMM_B_DUAL_RANK			(0x1 << 18)
+#define   MAD_DIMM_A_DUAL_RANK			(0x1 << 17)
+#define   MAD_DIMM_A_SELECT			(0x1 << 16)
+/* DIMM sizes are in multiples of 256mb. */
+#define   MAD_DIMM_B_SIZE_SHIFT			8
+#define   MAD_DIMM_B_SIZE_MASK			(0xff << MAD_DIMM_B_SIZE_SHIFT)
+#define   MAD_DIMM_A_SIZE_SHIFT			0
+#define   MAD_DIMM_A_SIZE_MASK			(0xff << MAD_DIMM_A_SIZE_SHIFT)
+
+#define SKL_MAD_DIMM_CH0_0_0_0_MCHBAR_MCMAIN	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x500C)
+#define SKL_MAD_DIMM_CH1_0_0_0_MCHBAR_MCMAIN	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5010)
+#define   SKL_DRAM_S_SHIFT			16
+#define   SKL_DRAM_SIZE_MASK			0x3F
+#define   SKL_DRAM_WIDTH_MASK			(0x3 << 8)
+#define   SKL_DRAM_WIDTH_SHIFT			8
+#define   SKL_DRAM_WIDTH_X8			(0x0 << 8)
+#define   SKL_DRAM_WIDTH_X16			(0x1 << 8)
+#define   SKL_DRAM_WIDTH_X32			(0x2 << 8)
+#define   SKL_DRAM_RANK_MASK			(0x1 << 10)
+#define   SKL_DRAM_RANK_SHIFT			10
+#define   SKL_DRAM_RANK_1			(0x0 << 10)
+#define   SKL_DRAM_RANK_2			(0x1 << 10)
+#define   SKL_DRAM_RANK_MASK			(0x1 << 10)
+#define   ICL_DRAM_SIZE_MASK			0x7F
+#define   ICL_DRAM_WIDTH_MASK			(0x3 << 7)
+#define   ICL_DRAM_WIDTH_SHIFT			7
+#define   ICL_DRAM_WIDTH_X8			(0x0 << 7)
+#define   ICL_DRAM_WIDTH_X16			(0x1 << 7)
+#define   ICL_DRAM_WIDTH_X32			(0x2 << 7)
+#define   ICL_DRAM_RANK_MASK			(0x3 << 9)
+#define   ICL_DRAM_RANK_SHIFT			9
+#define   ICL_DRAM_RANK_1			(0x0 << 9)
+#define   ICL_DRAM_RANK_2			(0x1 << 9)
+#define   ICL_DRAM_RANK_3			(0x2 << 9)
+#define   ICL_DRAM_RANK_4			(0x3 << 9)
+
+#define SA_PERF_STATUS_0_0_0_MCHBAR_PC		_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5918)
+#define  DG1_QCLK_RATIO_MASK			REG_GENMASK(9, 2)
+#define  DG1_QCLK_REFERENCE			REG_BIT(10)
+
+#define GEN6_GT_PERF_STATUS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5948)
+#define GEN6_RP_STATE_LIMITS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
+#define GEN6_RP_STATE_CAP			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
+#define   RP0_CAP_MASK				REG_GENMASK(7, 0)
+#define   RP1_CAP_MASK				REG_GENMASK(15, 8)
+#define   RPN_CAP_MASK				REG_GENMASK(23, 16)
+
+/* snb MCH registers for priority tuning */
+#define MCH_SSKPD				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5d10)
+#define   SSKPD_NEW_WM0_MASK_HSW		REG_GENMASK64(63, 56)
+#define   SSKPD_WM4_MASK_HSW			REG_GENMASK64(40, 32)
+#define   SSKPD_WM3_MASK_HSW			REG_GENMASK64(28, 20)
+#define   SSKPD_WM2_MASK_HSW			REG_GENMASK64(19, 12)
+#define   SSKPD_WM1_MASK_HSW			REG_GENMASK64(11, 4)
+#define   SSKPD_OLD_WM0_MASK_HSW		REG_GENMASK64(3, 0)
+#define   SSKPD_WM3_MASK_SNB			REG_GENMASK(29, 24)
+#define   SSKPD_WM2_MASK_SNB			REG_GENMASK(21, 16)
+#define   SSKPD_WM1_MASK_SNB			REG_GENMASK(13, 8)
+#define   SSKPD_WM0_MASK_SNB			REG_GENMASK(5, 0)
+
+/* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */
+#define DCLK					_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5e04)
+#define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5e04)
+#define   DG1_GEAR_TYPE				REG_BIT(16)
+
+/*
+ * Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
+ * since on HSW we can't write to it using intel_uncore_write.
+ */
+#define D_COMP_HSW				_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5f0c)
+#define  D_COMP_RCOMP_IN_PROGRESS		(1 << 9)
+#define  D_COMP_COMP_FORCE			(1 << 8)
+#define  D_COMP_COMP_DISABLE			(1 << 0)
+
+#define BXT_GT_PERF_STATUS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7070)
+
+#endif /* __INTEL_MCHBAR_REGS */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 23d4bb011fc8..113537343461 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -50,11 +50,16 @@
 #include "i915_drv.h"
 #include "i915_fixed.h"
 #include "i915_irq.h"
+#include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
 #include "intel_pm.h"
 #include "vlv_sideband.h"
 #include "../../../platform/x86/intel_ips.h"
 
+struct drm_i915_clock_gating_funcs {
+	void (*init_clock_gating)(struct drm_i915_private *i915);
+};
+
 /* Stores plane specific WM parameters */
 struct skl_wm_params {
 	bool x_tiled, y_tiled;
@@ -2942,27 +2947,27 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		u64 sskpd = intel_uncore_read64(uncore, MCH_SSKPD);
 
-		wm[0] = (sskpd >> 56) & 0xFF;
+		wm[0] = REG_FIELD_GET64(SSKPD_NEW_WM0_MASK_HSW, sskpd);
 		if (wm[0] == 0)
-			wm[0] = sskpd & 0xF;
-		wm[1] = (sskpd >> 4) & 0xFF;
-		wm[2] = (sskpd >> 12) & 0xFF;
-		wm[3] = (sskpd >> 20) & 0x1FF;
-		wm[4] = (sskpd >> 32) & 0x1FF;
+			wm[0] = REG_FIELD_GET64(SSKPD_OLD_WM0_MASK_HSW, sskpd);
+		wm[1] = REG_FIELD_GET64(SSKPD_WM1_MASK_HSW, sskpd);
+		wm[2] = REG_FIELD_GET64(SSKPD_WM2_MASK_HSW, sskpd);
+		wm[3] = REG_FIELD_GET64(SSKPD_WM3_MASK_HSW, sskpd);
+		wm[4] = REG_FIELD_GET64(SSKPD_WM4_MASK_HSW, sskpd);
 	} else if (DISPLAY_VER(dev_priv) >= 6) {
 		u32 sskpd = intel_uncore_read(uncore, MCH_SSKPD);
 
-		wm[0] = (sskpd >> SSKPD_WM0_SHIFT) & SSKPD_WM_MASK;
-		wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
-		wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
-		wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
+		wm[0] = REG_FIELD_GET(SSKPD_WM0_MASK_SNB, sskpd);
+		wm[1] = REG_FIELD_GET(SSKPD_WM1_MASK_SNB, sskpd);
+		wm[2] = REG_FIELD_GET(SSKPD_WM2_MASK_SNB, sskpd);
+		wm[3] = REG_FIELD_GET(SSKPD_WM3_MASK_SNB, sskpd);
 	} else if (DISPLAY_VER(dev_priv) >= 5) {
 		u32 mltr = intel_uncore_read(uncore, MLTR_ILK);
 
 		/* ILK primary LP0 latency is 700 ns */
 		wm[0] = 7;
-		wm[1] = (mltr >> MLTR_WM1_SHIFT) & ILK_SRLT_MASK;
-		wm[2] = (mltr >> MLTR_WM2_SHIFT) & ILK_SRLT_MASK;
+		wm[1] = REG_FIELD_GET(MLTR_WM1_MASK, mltr);
+		wm[2] = REG_FIELD_GET(MLTR_WM2_MASK, mltr);
 	} else {
 		MISSING_CASE(INTEL_DEVID(dev_priv));
 	}
@@ -3175,12 +3180,8 @@ static int ilk_compute_pipe_wm(struct intel_atomic_state *state,
 	}
 
 	pipe_wm->pipe_enabled = crtc_state->hw.active;
-	if (sprstate) {
-		pipe_wm->sprites_enabled = sprstate->uapi.visible;
-		pipe_wm->sprites_scaled = sprstate->uapi.visible &&
-			(drm_rect_width(&sprstate->uapi.dst) != drm_rect_width(&sprstate->uapi.src) >> 16 ||
-			 drm_rect_height(&sprstate->uapi.dst) != drm_rect_height(&sprstate->uapi.src) >> 16);
-	}
+	pipe_wm->sprites_enabled = crtc_state->active_planes & BIT(PLANE_SPRITE0);
+	pipe_wm->sprites_scaled = crtc_state->scaled_planes & BIT(PLANE_SPRITE0);
 
 	usable_level = max_level;
 
@@ -3409,29 +3410,28 @@ static void ilk_compute_wm_results(struct drm_i915_private *dev_priv,
 		 * disabled. Doing otherwise could cause underruns.
 		 */
 		results->wm_lp[wm_lp - 1] =
-			(ilk_wm_lp_latency(dev_priv, level) << WM1_LP_LATENCY_SHIFT) |
-			(r->pri_val << WM1_LP_SR_SHIFT) |
-			r->cur_val;
+			WM_LP_LATENCY(ilk_wm_lp_latency(dev_priv, level)) |
+			WM_LP_PRIMARY(r->pri_val) |
+			WM_LP_CURSOR(r->cur_val);
 
 		if (r->enable)
-			results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN;
+			results->wm_lp[wm_lp - 1] |= WM_LP_ENABLE;
 
 		if (DISPLAY_VER(dev_priv) >= 8)
-			results->wm_lp[wm_lp - 1] |=
-				r->fbc_val << WM1_LP_FBC_SHIFT_BDW;
+			results->wm_lp[wm_lp - 1] |= WM_LP_FBC_BDW(r->fbc_val);
 		else
-			results->wm_lp[wm_lp - 1] |=
-				r->fbc_val << WM1_LP_FBC_SHIFT;
+			results->wm_lp[wm_lp - 1] |= WM_LP_FBC_ILK(r->fbc_val);
+
+		results->wm_lp_spr[wm_lp - 1] = WM_LP_SPRITE(r->spr_val);
 
 		/*
-		 * Always set WM1S_LP_EN when spr_val != 0, even if the
+		 * Always set WM_LP_SPRITE_EN when spr_val != 0, even if the
 		 * level is disabled. Doing otherwise could cause underruns.
 		 */
 		if (DISPLAY_VER(dev_priv) <= 6 && r->spr_val) {
 			drm_WARN_ON(&dev_priv->drm, 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;
+			results->wm_lp_spr[wm_lp - 1] |= WM_LP_SPRITE_ENABLE;
+		}
 	}
 
 	/* LP0 register values */
@@ -3444,9 +3444,9 @@ static void ilk_compute_wm_results(struct drm_i915_private *dev_priv,
 			continue;
 
 		results->wm_pipe[pipe] =
-			(r->pri_val << WM0_PIPE_PLANE_SHIFT) |
-			(r->spr_val << WM0_PIPE_SPRITE_SHIFT) |
-			r->cur_val;
+			WM0_PIPE_PRIMARY(r->pri_val) |
+			WM0_PIPE_SPRITE(r->spr_val) |
+			WM0_PIPE_CURSOR(r->cur_val);
 	}
 }
 
@@ -3538,24 +3538,24 @@ static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv,
 	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;
+	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] & WM_LP_ENABLE) {
+		previous->wm_lp[2] &= ~WM_LP_ENABLE;
 		intel_uncore_write(&dev_priv->uncore, 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;
+	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] & WM_LP_ENABLE) {
+		previous->wm_lp[1] &= ~WM_LP_ENABLE;
 		intel_uncore_write(&dev_priv->uncore, 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;
+	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] & WM_LP_ENABLE) {
+		previous->wm_lp[0] &= ~WM_LP_ENABLE;
 		intel_uncore_write(&dev_priv->uncore, WM1_LP_ILK, previous->wm_lp[0]);
 		changed = true;
 	}
 
 	/*
-	 * Don't touch WM1S_LP_EN here.
+	 * Don't touch WM_LP_SPRITE_ENABLE here.
 	 * Doing so could cause underruns.
 	 */
 
@@ -3802,8 +3802,9 @@ void intel_sagv_pre_plane_update(struct intel_atomic_state *state)
 	if (!new_bw_state)
 		return;
 
-	if (DISPLAY_VER(dev_priv) < 11 && !intel_can_enable_sagv(dev_priv, new_bw_state)) {
-		intel_disable_sagv(dev_priv);
+	if (DISPLAY_VER(dev_priv) < 11) {
+		if (!intel_can_enable_sagv(dev_priv, new_bw_state))
+			intel_disable_sagv(dev_priv);
 		return;
 	}
 
@@ -3853,8 +3854,9 @@ void intel_sagv_post_plane_update(struct intel_atomic_state *state)
 	if (!new_bw_state)
 		return;
 
-	if (DISPLAY_VER(dev_priv) < 11 && intel_can_enable_sagv(dev_priv, new_bw_state)) {
-		intel_enable_sagv(dev_priv);
+	if (DISPLAY_VER(dev_priv) < 11) {
+		if (intel_can_enable_sagv(dev_priv, new_bw_state))
+			intel_enable_sagv(dev_priv);
 		return;
 	}
 
@@ -4034,6 +4036,15 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state)
 	return 0;
 }
 
+static u16 skl_ddb_entry_init(struct skl_ddb_entry *entry,
+			      u16 start, u16 end)
+{
+	entry->start = start;
+	entry->end = end;
+
+	return end;
+}
+
 static int intel_dbuf_slice_size(struct drm_i915_private *dev_priv)
 {
 	return INTEL_INFO(dev_priv)->dbuf.size /
@@ -4172,8 +4183,7 @@ skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc)
 	int ret;
 
 	if (new_dbuf_state->weight[pipe] == 0) {
-		new_dbuf_state->ddb[pipe].start = 0;
-		new_dbuf_state->ddb[pipe].end = 0;
+		skl_ddb_entry_init(&new_dbuf_state->ddb[pipe], 0, 0);
 		goto out;
 	}
 
@@ -4189,8 +4199,10 @@ skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc)
 	start = ddb_range_size * weight_start / weight_total;
 	end = ddb_range_size * weight_end / weight_total;
 
-	new_dbuf_state->ddb[pipe].start = ddb_slices.start - mbus_offset + start;
-	new_dbuf_state->ddb[pipe].end = ddb_slices.start - mbus_offset + end;
+	skl_ddb_entry_init(&new_dbuf_state->ddb[pipe],
+			   ddb_slices.start - mbus_offset + start,
+			   ddb_slices.start - mbus_offset + end);
+
 out:
 	if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe] &&
 	    skl_ddb_entry_equal(&old_dbuf_state->ddb[pipe],
@@ -4268,11 +4280,11 @@ skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
 	return max(num_active == 1 ? 32 : 8, min_ddb_alloc);
 }
 
-static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv,
-				       struct skl_ddb_entry *entry, u32 reg)
+static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg)
 {
-	entry->start = REG_FIELD_GET(PLANE_BUF_START_MASK, reg);
-	entry->end = REG_FIELD_GET(PLANE_BUF_END_MASK, reg);
+	skl_ddb_entry_init(entry,
+			   REG_FIELD_GET(PLANE_BUF_START_MASK, reg),
+			   REG_FIELD_GET(PLANE_BUF_END_MASK, reg));
 	if (entry->end)
 		entry->end++;
 }
@@ -4290,7 +4302,7 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
 	/* Cursor doesn't support NV12/planar, so no extra calculation needed */
 	if (plane_id == PLANE_CURSOR) {
 		val = intel_uncore_read(&dev_priv->uncore, CUR_BUF_CFG(pipe));
-		skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
+		skl_ddb_entry_init_from_hw(ddb_y, val);
 		return;
 	}
 
@@ -4304,7 +4316,7 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
 
 	if (DISPLAY_VER(dev_priv) >= 11) {
 		val = intel_uncore_read(&dev_priv->uncore, PLANE_BUF_CFG(pipe, plane_id));
-		skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
+		skl_ddb_entry_init_from_hw(ddb_y, val);
 	} else {
 		val = intel_uncore_read(&dev_priv->uncore, PLANE_BUF_CFG(pipe, plane_id));
 		val2 = intel_uncore_read(&dev_priv->uncore, PLANE_NV12_BUF_CFG(pipe, plane_id));
@@ -4313,8 +4325,8 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
 		    drm_format_info_is_yuv_semiplanar(drm_format_info(fourcc)))
 			swap(val, val2);
 
-		skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
-		skl_ddb_entry_init_from_hw(dev_priv, ddb_uv, val2);
+		skl_ddb_entry_init_from_hw(ddb_y, val);
+		skl_ddb_entry_init_from_hw(ddb_uv, val2);
 	}
 }
 
@@ -4342,55 +4354,6 @@ void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
 	intel_display_power_put(dev_priv, power_domain, wakeref);
 }
 
-/*
- * Determines the downscale amount of a plane for the purposes of watermark calculations.
- * The bspec defines downscale amount as:
- *
- * """
- * Horizontal down scale amount = maximum[1, Horizontal source size /
- *                                           Horizontal destination size]
- * Vertical down scale amount = maximum[1, Vertical source size /
- *                                         Vertical destination size]
- * Total down scale amount = Horizontal down scale amount *
- *                           Vertical down scale amount
- * """
- *
- * Return value is provided in 16.16 fixed point form to retain fractional part.
- * Caller should take care of dividing & rounding off the value.
- */
-static uint_fixed_16_16_t
-skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
-			   const struct intel_plane_state *plane_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
-	u32 src_w, src_h, dst_w, dst_h;
-	uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
-	uint_fixed_16_16_t downscale_h, downscale_w;
-
-	if (drm_WARN_ON(&dev_priv->drm,
-			!intel_wm_plane_visible(crtc_state, plane_state)))
-		return u32_to_fixed16(0);
-
-	/*
-	 * Src coordinates are already rotated by 270 degrees for
-	 * the 90/270 degree plane rotation cases (to match the
-	 * GTT mapping), hence no need to account for rotation here.
-	 *
-	 * n.b., src is 16.16 fixed point, dst is whole integer.
-	 */
-	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
-	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->uapi.dst);
-	dst_h = drm_rect_height(&plane_state->uapi.dst);
-
-	fp_w_ratio = div_fixed16(src_w, dst_w);
-	fp_h_ratio = div_fixed16(src_h, dst_h);
-	downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
-	downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));
-
-	return mul_fixed16(downscale_w, downscale_h);
-}
-
 struct dbuf_slice_conf_entry {
 	u8 active_pipes;
 	u8 dbuf_mask[I915_MAX_PIPES];
@@ -4946,10 +4909,7 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
-	u32 data_rate;
-	u32 width = 0, height = 0;
-	uint_fixed_16_16_t down_scale_amount;
-	u64 rate;
+	int width, height;
 
 	if (!plane_state->uapi.visible)
 		return 0;
@@ -4983,14 +4943,7 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 		height /= 2;
 	}
 
-	data_rate = width * height;
-
-	down_scale_amount = skl_plane_downscale_amount(crtc_state, plane_state);
-
-	rate = mul_round_up_u32_fixed16(data_rate, down_scale_amount);
-
-	rate *= fb->format->cpp[color_plane];
-	return rate;
+	return width * height * fb->format->cpp[color_plane];
 }
 
 static u64
@@ -5147,9 +5100,31 @@ static bool icl_need_wm1_wa(struct drm_i915_private *i915,
 	       (IS_DISPLAY_VER(i915, 12, 13) && plane_id == PLANE_CURSOR);
 }
 
+struct skl_plane_ddb_iter {
+	u64 data_rate;
+	u16 total[I915_MAX_PLANES];
+	u16 uv_total[I915_MAX_PLANES];
+	u16 start, size;
+};
+
+static u16
+skl_allocate_plane_ddb(struct skl_plane_ddb_iter *iter,
+		       const struct skl_wm_level *wm,
+		       u64 data_rate)
+{
+	u16 extra;
+
+	extra = min_t(u16, iter->size,
+		      DIV64_U64_ROUND_UP(iter->size * data_rate, iter->data_rate));
+	iter->size -= extra;
+	iter->data_rate -= data_rate;
+
+	return wm->min_ddb_alloc + extra;
+}
+
 static int
-skl_allocate_plane_ddb(struct intel_atomic_state *state,
-		       struct intel_crtc *crtc)
+skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *crtc_state =
@@ -5158,10 +5133,7 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 		intel_atomic_get_new_dbuf_state(state);
 	const struct skl_ddb_entry *alloc = &dbuf_state->ddb[crtc->pipe];
 	int num_active = hweight8(dbuf_state->active_pipes);
-	u16 alloc_size, start = 0;
-	u16 total[I915_MAX_PLANES] = {};
-	u16 uv_total[I915_MAX_PLANES] = {};
-	u64 total_data_rate;
+	struct skl_plane_ddb_iter iter = {};
 	enum plane_id plane_id;
 	u32 blocks;
 	int level;
@@ -5174,24 +5146,21 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 		return 0;
 
 	if (DISPLAY_VER(dev_priv) >= 11)
-		total_data_rate =
-			icl_get_total_relative_data_rate(state, crtc);
+		iter.data_rate = icl_get_total_relative_data_rate(state, crtc);
 	else
-		total_data_rate =
-			skl_get_total_relative_data_rate(state, crtc);
+		iter.data_rate = skl_get_total_relative_data_rate(state, crtc);
 
-	alloc_size = skl_ddb_entry_size(alloc);
-	if (alloc_size == 0)
+	iter.size = skl_ddb_entry_size(alloc);
+	if (iter.size == 0)
 		return 0;
 
 	/* Allocate fixed number of blocks for cursor. */
-	total[PLANE_CURSOR] = skl_cursor_allocation(crtc_state, num_active);
-	alloc_size -= total[PLANE_CURSOR];
-	crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR].start =
-		alloc->end - total[PLANE_CURSOR];
-	crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR].end = alloc->end;
+	iter.total[PLANE_CURSOR] = skl_cursor_allocation(crtc_state, num_active);
+	iter.size -= iter.total[PLANE_CURSOR];
+	skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR],
+			   alloc->end - iter.total[PLANE_CURSOR], alloc->end);
 
-	if (total_data_rate == 0)
+	if (iter.data_rate == 0)
 		return 0;
 
 	/*
@@ -5205,7 +5174,7 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 				&crtc_state->wm.skl.optimal.planes[plane_id];
 
 			if (plane_id == PLANE_CURSOR) {
-				if (wm->wm[level].min_ddb_alloc > total[PLANE_CURSOR]) {
+				if (wm->wm[level].min_ddb_alloc > iter.total[PLANE_CURSOR]) {
 					drm_WARN_ON(&dev_priv->drm,
 						    wm->wm[level].min_ddb_alloc != U16_MAX);
 					blocks = U32_MAX;
@@ -5218,8 +5187,8 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 			blocks += wm->uv_wm[level].min_ddb_alloc;
 		}
 
-		if (blocks <= alloc_size) {
-			alloc_size -= blocks;
+		if (blocks <= iter.size) {
+			iter.size -= blocks;
 			break;
 		}
 	}
@@ -5228,7 +5197,7 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 		drm_dbg_kms(&dev_priv->drm,
 			    "Requested display configuration exceeds system DDB limitations");
 		drm_dbg_kms(&dev_priv->drm, "minimum required %d/%d\n",
-			    blocks, alloc_size);
+			    blocks, iter.size);
 		return -EINVAL;
 	}
 
@@ -5240,8 +5209,6 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 	for_each_plane_id_on_crtc(crtc, plane_id) {
 		const struct skl_plane_wm *wm =
 			&crtc_state->wm.skl.optimal.planes[plane_id];
-		u64 rate;
-		u16 extra;
 
 		if (plane_id == PLANE_CURSOR)
 			continue;
@@ -5250,32 +5217,24 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 		 * We've accounted for all active planes; remaining planes are
 		 * all disabled.
 		 */
-		if (total_data_rate == 0)
+		if (iter.data_rate == 0)
 			break;
 
-		rate = crtc_state->plane_data_rate[plane_id];
-		extra = min_t(u16, alloc_size,
-			      DIV64_U64_ROUND_UP(alloc_size * rate,
-						 total_data_rate));
-		total[plane_id] = wm->wm[level].min_ddb_alloc + extra;
-		alloc_size -= extra;
-		total_data_rate -= rate;
+		iter.total[plane_id] =
+			skl_allocate_plane_ddb(&iter, &wm->wm[level],
+					       crtc_state->plane_data_rate[plane_id]);
 
-		if (total_data_rate == 0)
+		if (iter.data_rate == 0)
 			break;
 
-		rate = crtc_state->uv_plane_data_rate[plane_id];
-		extra = min_t(u16, alloc_size,
-			      DIV64_U64_ROUND_UP(alloc_size * rate,
-						 total_data_rate));
-		uv_total[plane_id] = wm->uv_wm[level].min_ddb_alloc + extra;
-		alloc_size -= extra;
-		total_data_rate -= rate;
+		iter.uv_total[plane_id] =
+			skl_allocate_plane_ddb(&iter, &wm->uv_wm[level],
+					       crtc_state->uv_plane_data_rate[plane_id]);
 	}
-	drm_WARN_ON(&dev_priv->drm, alloc_size != 0 || total_data_rate != 0);
+	drm_WARN_ON(&dev_priv->drm, iter.size != 0 || iter.data_rate != 0);
 
 	/* Set the actual DDB start/end points for each plane */
-	start = alloc->start;
+	iter.start = alloc->start;
 	for_each_plane_id_on_crtc(crtc, plane_id) {
 		struct skl_ddb_entry *plane_alloc =
 			&crtc_state->wm.skl.plane_ddb_y[plane_id];
@@ -5287,20 +5246,16 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 
 		/* Gen11+ uses a separate plane for UV watermarks */
 		drm_WARN_ON(&dev_priv->drm,
-			    DISPLAY_VER(dev_priv) >= 11 && uv_total[plane_id]);
+			    DISPLAY_VER(dev_priv) >= 11 && iter.uv_total[plane_id]);
 
 		/* Leave disabled planes at (0,0) */
-		if (total[plane_id]) {
-			plane_alloc->start = start;
-			start += total[plane_id];
-			plane_alloc->end = start;
-		}
+		if (iter.total[plane_id])
+			iter.start = skl_ddb_entry_init(plane_alloc, iter.start,
+							iter.start + iter.total[plane_id]);
 
-		if (uv_total[plane_id]) {
-			uv_plane_alloc->start = start;
-			start += uv_total[plane_id];
-			uv_plane_alloc->end = start;
-		}
+		if (iter.uv_total[plane_id])
+			iter.start = skl_ddb_entry_init(uv_plane_alloc, iter.start,
+							iter.start + iter.uv_total[plane_id]);
 	}
 
 	/*
@@ -5315,7 +5270,8 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 				&crtc_state->wm.skl.optimal.planes[plane_id];
 
 			skl_check_nv12_wm_level(&wm->wm[level], &wm->uv_wm[level],
-						total[plane_id], uv_total[plane_id]);
+						iter.total[plane_id],
+						iter.uv_total[plane_id]);
 
 			if (icl_need_wm1_wa(dev_priv, plane_id) &&
 			    level == 1 && wm->wm[0].enable) {
@@ -5334,9 +5290,9 @@ skl_allocate_plane_ddb(struct intel_atomic_state *state,
 		struct skl_plane_wm *wm =
 			&crtc_state->wm.skl.optimal.planes[plane_id];
 
-		skl_check_wm_level(&wm->trans_wm, total[plane_id]);
-		skl_check_wm_level(&wm->sagv.wm0, total[plane_id]);
-		skl_check_wm_level(&wm->sagv.trans_wm, total[plane_id]);
+		skl_check_wm_level(&wm->trans_wm, iter.total[plane_id]);
+		skl_check_wm_level(&wm->sagv.wm0, iter.total[plane_id]);
+		skl_check_wm_level(&wm->sagv.trans_wm, iter.total[plane_id]);
 	}
 
 	return 0;
@@ -6226,7 +6182,7 @@ skl_compute_ddb(struct intel_atomic_state *state)
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		ret = skl_allocate_plane_ddb(state, crtc);
+		ret = skl_crtc_allocate_plane_ddb(state, crtc);
 		if (ret)
 			return ret;
 
@@ -6803,9 +6759,9 @@ static void ilk_pipe_wm_get_hw_state(struct intel_crtc *crtc)
 		 * multiple pipes are active.
 		 */
 		active->wm[0].enable = true;
-		active->wm[0].pri_val = (tmp & WM0_PIPE_PLANE_MASK) >> WM0_PIPE_PLANE_SHIFT;
-		active->wm[0].spr_val = (tmp & WM0_PIPE_SPRITE_MASK) >> WM0_PIPE_SPRITE_SHIFT;
-		active->wm[0].cur_val = tmp & WM0_PIPE_CURSOR_MASK;
+		active->wm[0].pri_val = REG_FIELD_GET(WM0_PIPE_PRIMARY_MASK, tmp);
+		active->wm[0].spr_val = REG_FIELD_GET(WM0_PIPE_SPRITE_MASK, tmp);
+		active->wm[0].cur_val = REG_FIELD_GET(WM0_PIPE_CURSOR_MASK, tmp);
 	} else {
 		int level, max_level = ilk_wm_max_level(dev_priv);
 
@@ -7229,12 +7185,12 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
  */
 static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv)
 {
-	intel_uncore_write(&dev_priv->uncore, WM3_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM3_LP_ILK) & ~WM1_LP_SR_EN);
-	intel_uncore_write(&dev_priv->uncore, WM2_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM2_LP_ILK) & ~WM1_LP_SR_EN);
-	intel_uncore_write(&dev_priv->uncore, WM1_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM1_LP_ILK) & ~WM1_LP_SR_EN);
+	intel_uncore_write(&dev_priv->uncore, WM3_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM3_LP_ILK) & ~WM_LP_ENABLE);
+	intel_uncore_write(&dev_priv->uncore, WM2_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM2_LP_ILK) & ~WM_LP_ENABLE);
+	intel_uncore_write(&dev_priv->uncore, WM1_LP_ILK, intel_uncore_read(&dev_priv->uncore, WM1_LP_ILK) & ~WM_LP_ENABLE);
 
 	/*
-	 * Don't touch WM1S_LP_EN here.
+	 * Don't touch WM_LP_SPRITE_ENABLE here.
 	 * Doing so could cause underruns.
 	 */
 }
@@ -7437,7 +7393,7 @@ static void gen6_check_mch_setup(struct drm_i915_private *dev_priv)
 	u32 tmp;
 
 	tmp = intel_uncore_read(&dev_priv->uncore, MCH_SSKPD);
-	if ((tmp & MCH_SSKPD_WM0_MASK) != MCH_SSKPD_WM0_VAL)
+	if (REG_FIELD_GET(SSKPD_WM0_MASK_SNB, tmp) != 12)
 		drm_dbg_kms(&dev_priv->drm,
 			    "Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
 			    tmp);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 3293ac71bcf8..6ed5786bcd29 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -77,6 +77,9 @@ track_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 	depot_stack_handle_t stack, *stacks;
 	unsigned long flags;
 
+	if (rpm->no_wakeref_tracking)
+		return -1;
+
 	stack = __save_depot_stack();
 	if (!stack)
 		return -1;
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h
index 47a85fab4130..d9160e3ff4af 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.h
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.h
@@ -51,6 +51,7 @@ struct intel_runtime_pm {
 	bool available;
 	bool suspended;
 	bool irqs_enabled;
+	bool no_wakeref_tracking;
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 	/*
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 850ebfae31af..dd8fdd5863de 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1496,7 +1496,7 @@ ilk_dummy_write(struct intel_uncore *uncore)
 	/* WaIssueDummyWriteToWakeupFromRC6:ilk Issue a dummy write to wake up
 	 * the chip from rc6 before touching it for real. MI_MODE is masked,
 	 * hence harmless to write 0 into. */
-	__raw_uncore_write32(uncore, MI_MODE, 0);
+	__raw_uncore_write32(uncore, RING_MI_MODE(RENDER_RING_BASE), 0);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index b5576888cd78..6a7328d9c361 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -6,9 +6,10 @@
 
 #include <linux/random.h>
 
+#include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_pm.h"
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
-#include "gem/i915_gem_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 75b709c26dd3..74a1b2ecf48f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -22,6 +22,7 @@
  *
  */
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 575705c3bce9..1b508c89468c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -26,6 +26,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_context.h"
 #include "gt/intel_gpu_commands.h"
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 92a859b34190..3e673fd1ea4f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -26,6 +26,7 @@
 #include <linux/pm_qos.h>
 #include <linux/sort.h>
 
+#include "gem/i915_gem_internal.h"
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/mock_context.h"
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index 2d6d7bd13c3c..c4e932368b37 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -24,6 +24,7 @@
 #include <linux/random.h>
 
 #include "gt/intel_gt_pm.h"
+#include "i915_driver.h"
 #include "i915_drv.h"
 #include "i915_selftest.h"
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 5c5809dfe9b2..cc6f9af679fb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -25,6 +25,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_internal.h"
 #include "gem/selftests/mock_context.h"
 
 #include "i915_scatterlist.h"
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index 24d87d0fc747..0c22594ae274 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -6,6 +6,7 @@
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 
+#include "gem/i915_gem_internal.h"
 #include "gem/selftests/igt_gem_utils.h"
 
 #include "igt_spinner.h"
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 8aa7b1d33865..79e819334b4e 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -161,6 +161,8 @@ struct drm_i915_private *mock_gem_device(void)
 	i915_params_copy(&i915->params, &i915_modparams);
 
 	intel_runtime_pm_init_early(&i915->runtime_pm);
+	/* wakeref tracking has significant overhead */
+	i915->runtime_pm.no_wakeref_tracking = true;
 
 	/* Using the global GTT may ask questions about KMS users, so prepare */
 	drm_mode_config_init(&i915->drm);
diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h
index 98d020835b49..69487bd8ed56 100644
--- a/include/drm/dp/drm_dp_helper.h
+++ b/include/drm/dp/drm_dp_helper.h
@@ -560,6 +560,7 @@ struct drm_panel;
 # define DP_TRAINING_PATTERN_DISABLE	    0
 # define DP_TRAINING_PATTERN_1		    1
 # define DP_TRAINING_PATTERN_2		    2
+# define DP_TRAINING_PATTERN_2_CDS	    3	    /* 2.0 E11 */
 # define DP_TRAINING_PATTERN_3		    3	    /* 1.2 */
 # define DP_TRAINING_PATTERN_4              7       /* 1.4 */
 # define DP_TRAINING_PATTERN_MASK	    0x3
@@ -738,11 +739,13 @@ struct drm_panel;
 			    DP_LANE_CHANNEL_EQ_DONE |	\
 			    DP_LANE_SYMBOL_LOCKED)
 
-#define DP_LANE_ALIGN_STATUS_UPDATED	    0x204
-
-#define DP_INTERLANE_ALIGN_DONE		    (1 << 0)
-#define DP_DOWNSTREAM_PORT_STATUS_CHANGED   (1 << 6)
-#define DP_LINK_STATUS_UPDATED		    (1 << 7)
+#define DP_LANE_ALIGN_STATUS_UPDATED                    0x204
+#define  DP_INTERLANE_ALIGN_DONE                        (1 << 0)
+#define  DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE       (1 << 2) /* 2.0 E11 */
+#define  DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE      (1 << 3) /* 2.0 E11 */
+#define  DP_128B132B_LT_FAILED                          (1 << 4) /* 2.0 E11 */
+#define  DP_DOWNSTREAM_PORT_STATUS_CHANGED              (1 << 6)
+#define  DP_LINK_STATUS_UPDATED                         (1 << 7)
 
 #define DP_SINK_STATUS			    0x205
 # define DP_RECEIVE_PORT_0_STATUS	    (1 << 0)
@@ -1112,6 +1115,7 @@ struct drm_panel;
 # define DP_UHBR13_5                           (1 << 2)
 
 #define DP_128B132B_TRAINING_AUX_RD_INTERVAL                    0x2216 /* 2.0 */
+# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT          (1 << 7)
 # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK              0x7f
 # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US            0x00
 # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS              0x01
@@ -1347,6 +1351,7 @@ struct drm_panel;
 # define DP_PHY_REPEATER_128B132B_SUPPORTED		    (1 << 0)
 /* See DP_128B132B_SUPPORTED_LINK_RATES for values */
 #define DP_PHY_REPEATER_128B132B_RATES			    0xf0007 /* 2.0 */
+#define DP_PHY_REPEATER_EQ_DONE                             0xf0008 /* 2.0 E11 */
 
 enum drm_dp_phy {
 	DP_PHY_DPRX,
@@ -1549,6 +1554,15 @@ void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux,
 void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux,
 					      const u8 caps[DP_LTTPR_PHY_CAP_SIZE]);
 
+int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux);
+bool drm_dp_128b132b_lane_channel_eq_done(const u8 link_status[DP_LINK_STATUS_SIZE],
+					  int lane_count);
+bool drm_dp_128b132b_lane_symbol_locked(const u8 link_status[DP_LINK_STATUS_SIZE],
+					int lane_count);
+bool drm_dp_128b132b_eq_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]);
+bool drm_dp_128b132b_cds_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]);
+bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SIZE]);
+
 u8 drm_dp_link_rate_to_bw_code(int link_rate);
 int drm_dp_bw_code_to_link_rate(u8 link_bw);