Merge tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a huge amount of big things here, AMD has support for a few new HW
  variants (vangogh, green sardine, dimgrey cavefish), Intel has some
  more DG1 enablement. We have a few big reworks of the TTM layers and
  interfaces, GEM and atomic internal API reworks cross tree. fbdev is
  marked orphaned in here as well to reflect the current reality.

  core:
   - documentation updates
   - deprecate DRM_FORMAT_MOD_NONE
   - atomic crtc enable/disable rework
   - GEM convert drivers to gem object functions
   - remove SCATTER_LIST_MAX_SEGMENT

  sched:
   - avoid infinite waits

  ttm:
   - remove AGP support
   - don't modify caching for swapout
   - ttm pinning rework
   - major TTM reworks
   - new backend allocator
   - multihop support

  vram-helper:
   - top down BO placement fix
   - TTM changes
   - GEM object support

  displayport:
   - DP 2.0 DPCD prep work
   - DP MST extended DPCD caps

  fbdev:
   - mark as orphaned

  amdgpu:
   - Initial Vangogh support
   - Green Sardine support
   - Dimgrey Cavefish support
   - SG display support for renoir
   - SMU7 improvements
   - gfx9+ modiifier support
   - CI BACO fixes

  radeon:
   - expose voltage via hwmon on SUMO

  amdkfd:
   - fix unique id handling

  i915:
   - more DG1 enablement
   - bigjoiner support
   - integer scaling filter support
   - async flip support
   - ICL+ DSI command mode
   - Improve display shutdown
   - Display refactoring
   - eLLC machine fbdev loading fix
   - dma scatterlist fixes
   - TGL hang fixes
   - eLLC display buffer caching on SKL+
   - MOCS PTE seeting for gen9+

  msm:
   - Shutdown hook
   - GPU cooling device support
   - DSI 7nm and 10nm phy/pll updates
   - sm8150/sm2850 DPU support
   - GEM locking re-work
   - LLCC system cache support

  aspeed:
   - sysfs output config support

  ast:
   - LUT fix
   - new display mode

  gma500:
   - remove 2d framebuffer accel

  panfrost:
   - move gpu reset to a worker

  exynos:
   - new HDMI mode support

  mediatek:
   - MT8167 support
   - yaml bindings
   - MIPI DSI phy code moved

  etnaviv:
   - new perf counter
   - more lockdep annotation

  hibmc:
   - i2c DDC support

  ingenic:
   - pixel clock reset fix
   - reserved memory support
   - allow both DMA channels at once
   - different pixel format support
   - 30/24/8-bit palette modes

  tilcdc:
   - don't keep vblank irq enabled

  vc4:
   - new maintainer added
   - DSI registration fix

  virtio:
   - blob resource support
   - host visible and cross-device support
   - uuid api support"

* tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm: (1754 commits)
  drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs
  drm/amdgpu: fix size calculation with stolen vga memory
  drm/amdgpu: remove amdgpu_ttm_late_init  and amdgpu_bo_late_init
  drm/amdgpu: free the pre-OS console framebuffer after the first modeset
  drm/amdgpu: enable runtime pm using BACO on CI dGPUs
  drm/amdgpu/cik: enable BACO reset on Bonaire
  drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven
  drm/amd/pm: remove one unsupported smu function for vangogh
  drm/amd/display: setup system context for APUs
  drm/amd/display: add S/G support for Vangogh
  drm/amdkfd: Fix leak in dmabuf import
  drm/amdgpu: use AMDGPU_NUM_VMID when possible
  drm/amdgpu: fix sdma instance fw version and feature version init
  drm/amd/pm: update driver if version for dimgrey_cavefish
  drm/amd/display: 3.2.115
  drm/amd/display: [FW Promotion] Release 0.0.45
  drm/amd/display: Revert DCN2.1 dram_clock_change_latency update
  drm/amd/display: Enable gpu_vm_support for dcn3.01
  drm/amd/display: Fixed the audio noise during mode switching with HDCP mode on
  drm/amd/display: Add wm table for Renoir
  ...

1 files changed, 157 insertions, 152 deletions

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cfb806767fc5..a20b5051f18c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -33,6 +33,7 @@
 #include <drm/drm_plane_helper.h>
 
 #include "display/intel_atomic.h"
+#include "display/intel_atomic_plane.h"
 #include "display/intel_bw.h"
 #include "display/intel_display_types.h"
 #include "display/intel_fbc.h"
@@ -899,12 +900,12 @@ static void pnv_update_wm(struct intel_crtc *unused_crtc)
 
 	crtc = single_enabled_crtc(dev_priv);
 	if (crtc) {
-		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&crtc->config->hw.pipe_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp = fb->format->cpp[0];
-		int clock = adjusted_mode->crtc_clock;
+		int clock = pipe_mode->crtc_clock;
 
 		/* Display SR */
 		wm = intel_calculate_wm(clock, &pnv_display_wm,
@@ -1135,8 +1136,8 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->hw.adjusted_mode;
+	const struct drm_display_mode *pipe_mode =
+		&crtc_state->hw.pipe_mode;
 	unsigned int latency = dev_priv->wm.pri_latency[level] * 10;
 	unsigned int clock, htotal, cpp, width, wm;
 
@@ -1163,8 +1164,8 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	    level != G4X_WM_LEVEL_NORMAL)
 		cpp = max(cpp, 4u);
 
-	clock = adjusted_mode->crtc_clock;
-	htotal = adjusted_mode->crtc_htotal;
+	clock = pipe_mode->crtc_clock;
+	htotal = pipe_mode->crtc_htotal;
 
 	width = drm_rect_width(&plane_state->uapi.dst);
 
@@ -1660,8 +1661,8 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->hw.adjusted_mode;
+	const struct drm_display_mode *pipe_mode =
+		&crtc_state->hw.pipe_mode;
 	unsigned int clock, htotal, cpp, width, wm;
 
 	if (dev_priv->wm.pri_latency[level] == 0)
@@ -1671,8 +1672,8 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 		return 0;
 
 	cpp = plane_state->hw.fb->format->cpp[0];
-	clock = adjusted_mode->crtc_clock;
-	htotal = adjusted_mode->crtc_htotal;
+	clock = pipe_mode->crtc_clock;
+	htotal = pipe_mode->crtc_htotal;
 	width = crtc_state->pipe_src_w;
 
 	if (plane->id == PLANE_CURSOR) {
@@ -2261,12 +2262,12 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 	if (crtc) {
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 12000;
-		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&crtc->config->hw.pipe_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
-		int clock = adjusted_mode->crtc_clock;
-		int htotal = adjusted_mode->crtc_htotal;
+		int clock = pipe_mode->crtc_clock;
+		int htotal = pipe_mode->crtc_htotal;
 		int hdisplay = crtc->config->pipe_src_w;
 		int cpp = fb->format->cpp[0];
 		int entries;
@@ -2345,8 +2346,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_A);
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A);
 	if (intel_crtc_active(crtc)) {
-		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&crtc->config->hw.pipe_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2356,7 +2357,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		else
 			cpp = fb->format->cpp[0];
 
-		planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
+		planea_wm = intel_calculate_wm(pipe_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
 					       pessimal_latency_ns);
 		enabled = crtc;
@@ -2372,8 +2373,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_B);
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B);
 	if (intel_crtc_active(crtc)) {
-		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&crtc->config->hw.pipe_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2383,7 +2384,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		else
 			cpp = fb->format->cpp[0];
 
-		planeb_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
+		planeb_wm = intel_calculate_wm(pipe_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
 					       pessimal_latency_ns);
 		if (enabled == NULL)
@@ -2421,12 +2422,12 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	if (HAS_FW_BLC(dev_priv) && enabled) {
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 6000;
-		const struct drm_display_mode *adjusted_mode =
-			&enabled->config->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&enabled->config->hw.pipe_mode;
 		const struct drm_framebuffer *fb =
 			enabled->base.primary->state->fb;
-		int clock = adjusted_mode->crtc_clock;
-		int htotal = adjusted_mode->crtc_htotal;
+		int clock = pipe_mode->crtc_clock;
+		int htotal = pipe_mode->crtc_htotal;
 		int hdisplay = enabled->config->pipe_src_w;
 		int cpp;
 		int entries;
@@ -2474,7 +2475,7 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
 	struct intel_crtc *crtc;
-	const struct drm_display_mode *adjusted_mode;
+	const struct drm_display_mode *pipe_mode;
 	u32 fwater_lo;
 	int planea_wm;
 
@@ -2482,8 +2483,8 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 	if (crtc == NULL)
 		return;
 
-	adjusted_mode = &crtc->config->hw.adjusted_mode;
-	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
+	pipe_mode = &crtc->config->hw.pipe_mode;
+	planea_wm = intel_calculate_wm(pipe_mode->crtc_clock,
 				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev_priv, PLANE_A),
 				       4, pessimal_latency_ns);
@@ -2573,7 +2574,7 @@ static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
 		return method1;
 
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 crtc_state->hw.pipe_mode.crtc_htotal,
 				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 
@@ -2601,7 +2602,7 @@ static u32 ilk_compute_spr_wm(const struct intel_crtc_state *crtc_state,
 
 	method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 crtc_state->hw.pipe_mode.crtc_htotal,
 				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 	return min(method1, method2);
@@ -2626,7 +2627,7 @@ static u32 ilk_compute_cur_wm(const struct intel_crtc_state *crtc_state,
 	cpp = plane_state->hw.fb->format->cpp[0];
 
 	return ilk_wm_method2(crtc_state->pixel_rate,
-			      crtc_state->hw.adjusted_mode.crtc_htotal,
+			      crtc_state->hw.pipe_mode.crtc_htotal,
 			      drm_rect_width(&plane_state->uapi.dst),
 			      cpp, mem_value);
 }
@@ -3573,11 +3574,11 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	_ilk_disable_lp_wm(dev_priv, dirty);
 
 	if (dirty & WM_DIRTY_PIPE(PIPE_A))
-		I915_WRITE(WM0_PIPEA_ILK, results->wm_pipe[0]);
+		I915_WRITE(WM0_PIPE_ILK(PIPE_A), results->wm_pipe[0]);
 	if (dirty & WM_DIRTY_PIPE(PIPE_B))
-		I915_WRITE(WM0_PIPEB_ILK, results->wm_pipe[1]);
+		I915_WRITE(WM0_PIPE_ILK(PIPE_B), results->wm_pipe[1]);
 	if (dirty & WM_DIRTY_PIPE(PIPE_C))
-		I915_WRITE(WM0_PIPEC_IVB, results->wm_pipe[2]);
+		I915_WRITE(WM0_PIPE_ILK(PIPE_C), results->wm_pipe[2]);
 
 	if (dirty & WM_DIRTY_DDB) {
 		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
@@ -3706,7 +3707,7 @@ skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
  *  - All planes can enable watermarks for latencies >= SAGV engine block time
  *  - We're not using an interlaced display configuration
  */
-int
+static int
 intel_enable_sagv(struct drm_i915_private *dev_priv)
 {
 	int ret;
@@ -3740,7 +3741,7 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-int
+static int
 intel_disable_sagv(struct drm_i915_private *dev_priv)
 {
 	int ret;
@@ -3873,9 +3874,7 @@ static bool skl_crtc_can_enable_sagv(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);
-	struct intel_plane *plane;
-	const struct intel_plane_state *plane_state;
-	int level, latency;
+	enum plane_id plane_id;
 
 	if (!intel_has_sagv(dev_priv))
 		return false;
@@ -3883,12 +3882,13 @@ static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
 	if (!crtc_state->hw.active)
 		return true;
 
-	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.pipe_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
-	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+	for_each_plane_id_on_crtc(crtc, plane_id) {
 		const struct skl_plane_wm *wm =
-			&crtc_state->wm.skl.optimal.planes[plane->id];
+			&crtc_state->wm.skl.optimal.planes[plane_id];
+		int level;
 
 		/* Skip this plane if it's not enabled */
 		if (!wm->wm[0].plane_en)
@@ -3899,19 +3899,12 @@ static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state)
 		     !wm->wm[level].plane_en; --level)
 		     { }
 
-		latency = dev_priv->wm.skl_latency[level];
-
-		if (skl_needs_memory_bw_wa(dev_priv) &&
-		    plane_state->uapi.fb->modifier ==
-		    I915_FORMAT_MOD_X_TILED)
-			latency += 15;
-
 		/*
 		 * If any of the planes on this pipe don't enable wm levels that
 		 * incur memory latencies higher than sagv_block_time_us we
 		 * can't enable SAGV.
 		 */
-		if (latency < dev_priv->sagv_block_time_us)
+		if (!wm->wm[level].can_sagv)
 			return false;
 	}
 
@@ -4174,8 +4167,8 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 	 */
 	total_slice_mask = dbuf_slice_mask;
 	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
-		const struct drm_display_mode *adjusted_mode =
-			&crtc_state->hw.adjusted_mode;
+		const struct drm_display_mode *pipe_mode =
+			&crtc_state->hw.pipe_mode;
 		enum pipe pipe = crtc->pipe;
 		int hdisplay, vdisplay;
 		u32 pipe_dbuf_slice_mask;
@@ -4205,7 +4198,7 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 		if (dbuf_slice_mask != pipe_dbuf_slice_mask)
 			continue;
 
-		drm_mode_get_hv_timing(adjusted_mode, &hdisplay, &vdisplay);
+		drm_mode_get_hv_timing(pipe_mode, &hdisplay, &vdisplay);
 
 		total_width_in_range += hdisplay;
 
@@ -4704,50 +4697,63 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 }
 
 static u64
-skl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
-				 u64 *plane_data_rate,
-				 u64 *uv_plane_data_rate)
+skl_get_total_relative_data_rate(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc)
 {
-	struct intel_plane *plane;
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	const struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
 	u64 total_data_rate = 0;
+	enum plane_id plane_id;
+	int i;
 
 	/* Calculate and cache data rate for each plane */
-	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
-		enum plane_id plane_id = plane->id;
-		u64 rate;
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		if (plane->pipe != crtc->pipe)
+			continue;
+
+		plane_id = plane->id;
 
 		/* packed/y */
-		rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
-		plane_data_rate[plane_id] = rate;
-		total_data_rate += rate;
+		crtc_state->plane_data_rate[plane_id] =
+			skl_plane_relative_data_rate(crtc_state, plane_state, 0);
 
 		/* uv-plane */
-		rate = skl_plane_relative_data_rate(crtc_state, plane_state, 1);
-		uv_plane_data_rate[plane_id] = rate;
-		total_data_rate += rate;
+		crtc_state->uv_plane_data_rate[plane_id] =
+			skl_plane_relative_data_rate(crtc_state, plane_state, 1);
+	}
+
+	for_each_plane_id_on_crtc(crtc, plane_id) {
+		total_data_rate += crtc_state->plane_data_rate[plane_id];
+		total_data_rate += crtc_state->uv_plane_data_rate[plane_id];
 	}
 
 	return total_data_rate;
 }
 
 static u64
-icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
-				 u64 *plane_data_rate)
+icl_get_total_relative_data_rate(struct intel_atomic_state *state,
+				 struct intel_crtc *crtc)
 {
-	struct intel_plane *plane;
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	const struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
 	u64 total_data_rate = 0;
+	enum plane_id plane_id;
+	int i;
 
 	/* Calculate and cache data rate for each plane */
-	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
-		enum plane_id plane_id = plane->id;
-		u64 rate;
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		if (plane->pipe != crtc->pipe)
+			continue;
+
+		plane_id = plane->id;
 
 		if (!plane_state->planar_linked_plane) {
-			rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
-			plane_data_rate[plane_id] = rate;
-			total_data_rate += rate;
+			crtc_state->plane_data_rate[plane_id] =
+				skl_plane_relative_data_rate(crtc_state, plane_state, 0);
 		} else {
 			enum plane_id y_plane_id;
 
@@ -4762,17 +4768,18 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 				continue;
 
 			/* Y plane rate is calculated on the slave */
-			rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
 			y_plane_id = plane_state->planar_linked_plane->id;
-			plane_data_rate[y_plane_id] = rate;
-			total_data_rate += rate;
+			crtc_state->plane_data_rate[y_plane_id] =
+				skl_plane_relative_data_rate(crtc_state, plane_state, 0);
 
-			rate = skl_plane_relative_data_rate(crtc_state, plane_state, 1);
-			plane_data_rate[plane_id] = rate;
-			total_data_rate += rate;
+			crtc_state->plane_data_rate[plane_id] =
+				skl_plane_relative_data_rate(crtc_state, plane_state, 1);
 		}
 	}
 
+	for_each_plane_id_on_crtc(crtc, plane_id)
+		total_data_rate += crtc_state->plane_data_rate[plane_id];
+
 	return total_data_rate;
 }
 
@@ -4791,9 +4798,11 @@ skl_plane_wm_level(const struct intel_crtc_state *crtc_state,
 }
 
 static int
-skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
+skl_allocate_pipe_ddb(struct intel_atomic_state *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 skl_ddb_entry *alloc = &crtc_state->wm.skl.ddb;
 	u16 alloc_size, start = 0;
@@ -4802,8 +4811,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 	u64 total_data_rate;
 	enum plane_id plane_id;
 	int num_active;
-	u64 plane_data_rate[I915_MAX_PLANES] = {};
-	u64 uv_plane_data_rate[I915_MAX_PLANES] = {};
 	u32 blocks;
 	int level;
 	int ret;
@@ -4843,13 +4850,10 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		total_data_rate =
-			icl_get_total_relative_data_rate(crtc_state,
-							 plane_data_rate);
+			icl_get_total_relative_data_rate(state, crtc);
 	else
 		total_data_rate =
-			skl_get_total_relative_data_rate(crtc_state,
-							 plane_data_rate,
-							 uv_plane_data_rate);
+			skl_get_total_relative_data_rate(state, crtc);
 
 	ret = skl_ddb_get_pipe_allocation_limits(dev_priv, crtc_state,
 						 total_data_rate,
@@ -4930,7 +4934,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 		if (total_data_rate == 0)
 			break;
 
-		rate = plane_data_rate[plane_id];
+		rate = crtc_state->plane_data_rate[plane_id];
 		extra = min_t(u16, alloc_size,
 			      DIV64_U64_ROUND_UP(alloc_size * rate,
 						 total_data_rate));
@@ -4941,7 +4945,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 		if (total_data_rate == 0)
 			break;
 
-		rate = uv_plane_data_rate[plane_id];
+		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));
@@ -5093,36 +5097,12 @@ intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
 	if (drm_WARN_ON(&dev_priv->drm, pixel_rate == 0))
 		return u32_to_fixed16(0);
 
-	crtc_htotal = crtc_state->hw.adjusted_mode.crtc_htotal;
+	crtc_htotal = crtc_state->hw.pipe_mode.crtc_htotal;
 	linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);
 
 	return linetime_us;
 }
 
-static u32
-skl_adjusted_plane_pixel_rate(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);
-	u64 adjusted_pixel_rate;
-	uint_fixed_16_16_t downscale_amount;
-
-	/* Shouldn't reach here on disabled planes... */
-	if (drm_WARN_ON(&dev_priv->drm,
-			!intel_wm_plane_visible(crtc_state, plane_state)))
-		return 0;
-
-	/*
-	 * Adjusted plane pixel rate is just the pipe's adjusted pixel rate
-	 * with additional adjustments for plane-specific scaling.
-	 */
-	adjusted_pixel_rate = crtc_state->pixel_rate;
-	downscale_amount = skl_plane_downscale_amount(crtc_state, plane_state);
-
-	return mul_round_up_u32_fixed16(adjusted_pixel_rate,
-					    downscale_amount);
-}
-
 static int
 skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 		      int width, const struct drm_format_info *format,
@@ -5235,7 +5215,7 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 	return skl_compute_wm_params(crtc_state, width,
 				     fb->format, fb->modifier,
 				     plane_state->hw.rotation,
-				     skl_adjusted_plane_pixel_rate(crtc_state, plane_state),
+				     intel_plane_pixel_rate(crtc_state, plane_state),
 				     wp, color_plane);
 }
 
@@ -5282,14 +5262,14 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
 				 wp->cpp, latency, wp->dbuf_block_size);
 	method2 = skl_wm_method2(wp->plane_pixel_rate,
-				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 crtc_state->hw.pipe_mode.crtc_htotal,
 				 latency,
 				 wp->plane_blocks_per_line);
 
 	if (wp->y_tiled) {
 		selected_result = max_fixed16(method2, wp->y_tile_minimum);
 	} else {
-		if ((wp->cpp * crtc_state->hw.adjusted_mode.crtc_htotal /
+		if ((wp->cpp * crtc_state->hw.pipe_mode.crtc_htotal /
 		     wp->dbuf_block_size < 1) &&
 		     (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) {
 			selected_result = method2;
@@ -5373,6 +5353,9 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	/* Bspec says: value >= plane ddb allocation -> invalid, hence the +1 here */
 	result->min_ddb_alloc = max(min_ddb_alloc, res_blocks) + 1;
 	result->plane_en = true;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		result->can_sagv = latency >= dev_priv->sagv_block_time_us;
 }
 
 static void
@@ -5478,7 +5461,7 @@ static int skl_build_plane_wm_single(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);
-	struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id];
+	struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
 	struct skl_wm_params wm_params;
 	int ret;
 
@@ -5501,7 +5484,7 @@ static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state,
 				 const struct intel_plane_state *plane_state,
 				 enum plane_id plane_id)
 {
-	struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id];
+	struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
 	struct skl_wm_params wm_params;
 	int ret;
 
@@ -5522,10 +5505,13 @@ static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
-	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum plane_id plane_id = plane->id;
+	struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
 
+	memset(wm, 0, sizeof(*wm));
+
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
@@ -5547,10 +5533,14 @@ static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 static int icl_build_plane_wm(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);
-	enum plane_id plane_id = to_intel_plane(plane_state->uapi.plane)->id;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	enum plane_id plane_id = plane->id;
+	struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
 	int ret;
 
+	memset(wm, 0, sizeof(*wm));
+
 	/* Watermarks calculated in master */
 	if (plane_state->planar_slave)
 		return 0;
@@ -5583,22 +5573,24 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
+static int skl_build_pipe_wm(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
-	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
-	struct intel_plane *plane;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	const struct intel_plane_state *plane_state;
-	int ret;
-
-	/*
-	 * We'll only calculate watermarks for planes that are actually
-	 * enabled, so make sure all other planes are set as disabled.
-	 */
-	memset(pipe_wm->planes, 0, sizeof(pipe_wm->planes));
+	struct intel_plane *plane;
+	int ret, i;
 
-	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state,
-						     crtc_state) {
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		/*
+		 * FIXME should perhaps check {old,new}_plane_crtc->hw.crtc
+		 * instead but we don't populate that correctly for NV12 Y
+		 * planes so for now hack this.
+		 */
+		if (plane->pipe != crtc->pipe)
+			continue;
 
 		if (INTEL_GEN(dev_priv) >= 11)
 			ret = icl_build_plane_wm(crtc_state, plane_state);
@@ -5608,6 +5600,8 @@ static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
 			return ret;
 	}
 
+	crtc_state->wm.skl.optimal = crtc_state->wm.skl.raw;
+
 	return 0;
 }
 
@@ -5794,7 +5788,7 @@ 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_pipe_ddb(new_crtc_state);
+		ret = skl_allocate_pipe_ddb(state, crtc);
 		if (ret)
 			return ret;
 
@@ -6092,7 +6086,6 @@ skl_compute_wm(struct intel_atomic_state *state)
 {
 	struct intel_crtc *crtc;
 	struct intel_crtc_state *new_crtc_state;
-	struct intel_crtc_state *old_crtc_state;
 	int ret, i;
 
 	ret = skl_ddb_add_affected_pipes(state);
@@ -6104,9 +6097,8 @@ skl_compute_wm(struct intel_atomic_state *state)
 	 * Note that skl_ddb_add_affected_pipes may have added more CRTC's that
 	 * weren't otherwise being modified if pipe allocations had to change.
 	 */
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
-					    new_crtc_state, i) {
-		ret = skl_build_pipe_wm(new_crtc_state);
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		ret = skl_build_pipe_wm(state, crtc);
 		if (ret)
 			return ret;
 	}
@@ -6124,8 +6116,7 @@ skl_compute_wm(struct intel_atomic_state *state)
 	 * based on how much ddb is available. Now we can actually
 	 * check if the final watermarks changed.
 	 */
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
-					    new_crtc_state, i) {
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		ret = skl_wm_add_affected_planes(state, crtc);
 		if (ret)
 			return ret;
@@ -6271,6 +6262,7 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		crtc_state = to_intel_crtc_state(crtc->base.state);
 
 		skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
+		crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal;
 	}
 
 	if (dev_priv->active_pipes) {
@@ -6287,13 +6279,8 @@ static void ilk_pipe_wm_get_hw_state(struct intel_crtc *crtc)
 	struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
 	struct intel_pipe_wm *active = &crtc_state->wm.ilk.optimal;
 	enum pipe pipe = crtc->pipe;
-	static const i915_reg_t wm0_pipe_reg[] = {
-		[PIPE_A] = WM0_PIPEA_ILK,
-		[PIPE_B] = WM0_PIPEB_ILK,
-		[PIPE_C] = WM0_PIPEC_IVB,
-	};
 
-	hw->wm_pipe[pipe] = I915_READ(wm0_pipe_reg[pipe]);
+	hw->wm_pipe[pipe] = I915_READ(WM0_PIPE_ILK(pipe));
 
 	memset(active, 0, sizeof(*active));
 
@@ -7132,6 +7119,14 @@ static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
 			 0, DFR_DISABLE);
 }
 
+static void dg1_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	/* Wa_1409836686:dg1[a0] */
+	if (IS_DG1_REVID(dev_priv, DG1_REVID_A0, DG1_REVID_A0))
+		I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) |
+			   DPT_GATING_DIS);
+}
+
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	if (!HAS_PCH_CNP(dev_priv))
@@ -7184,6 +7179,10 @@ static void cfl_init_clock_gating(struct drm_i915_private *dev_priv)
 	cnp_init_clock_gating(dev_priv);
 	gen9_init_clock_gating(dev_priv);
 
+	/* WAC6entrylatency:cfl */
+	I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
+		   FBC_LLC_FULLY_OPEN);
+
 	/*
 	 * WaFbcTurnOffFbcWatermark:cfl
 	 * Display WA #0562: cfl
@@ -7203,6 +7202,10 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	gen9_init_clock_gating(dev_priv);
 
+	/* WAC6entrylatency:kbl */
+	I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
+		   FBC_LLC_FULLY_OPEN);
+
 	/* WaDisableSDEUnitClockGating:kbl */
 	if (IS_KBL_GT_REVID(dev_priv, 0, KBL_REVID_B0))
 		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
@@ -7577,7 +7580,9 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
  */
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
-	if (IS_GEN(dev_priv, 12))
+	if (IS_DG1(dev_priv))
+		dev_priv->display.init_clock_gating = dg1_init_clock_gating;
+	else if (IS_GEN(dev_priv, 12))
 		dev_priv->display.init_clock_gating = tgl_init_clock_gating;
 	else if (IS_GEN(dev_priv, 11))
 		dev_priv->display.init_clock_gating = icl_init_clock_gating;