diff mbox

[2/6] drm/i915: Add render decompression support

Message ID 20170726180802.23817-2-ben@bwidawsk.net (mailing list archive)
State New, archived
Headers show

Commit Message

Ben Widawsky July 26, 2017, 6:07 p.m. UTC
From: Ville Syrjälä <ville.syrjala@linux.intel.com>

SKL+ display engine can scan out certain kinds of compressed surfaces
produced by the render engine. This involved telling the display engine
the location of the color control surfae (CCS) which describes
which parts of the main surface are compressed and which are not. The
location of CCS is provided by userspace as just another plane with its
own offset.

Add the required stuff to validate the user provided AUX plane metadata
and convert the user provided linear offset into something the hardware
can consume.

Due to hardware limitations we require that the main surface and
the AUX surface (CCS) be part of the same bo. The hardware also
makes life hard by not allowing you to provide separate x/y offsets
for the main and AUX surfaces (excpet with NV12), so finding suitable
offsets for both requires a bit of work. Assuming we still want keep
playing tricks with the offsets. I've just gone with a dumb "search
backward for suitable offsets" approach, which is far from optimal,
		 but it works.

		 Also not all planes will be capable of scanning out compressed surfaces,
		 and eg. 90/270 degree rotation is not supported in combination with
		 decompression either.

		 This patch may contain work from at least the following people:
		 * Vandana Kannan <vandana.kannan@intel.com>
		 * Daniel Vetter <daniel@ffwll.ch>
		 * Ben Widawsky <ben@bwidawsk.net>

	v2: Deal with display workarounds 0390, 0531, 1125 (Paulo)
v3: Pretend CCS tiles are regular 128 byte wide Y tiles (Jason)
	Put the AUX register defines to the correct place
	Fix up the slightly bogus rotation check
	v4: Use I915_WRITE_FW() due to plane update locking changes
s/return -EINVAL/goto err/ in intel_framebuffer_init()
	Eliminate a bunch hardcoded numbers in CCS code

v5: (By Ben)
conflict resolution +
-               res_blocks += fixed_16_16_to_u32_round_up(y_tile_minimum);
+               res_blocks += fixed16_to_u32_round_up(y_tile_minimum);

Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Ville Syrjä <ville.syrjala@linux.intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_reg.h      |  23 ++++
 drivers/gpu/drm/i915/intel_display.c | 233 ++++++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_pm.c      |  29 ++++-
 drivers/gpu/drm/i915/intel_sprite.c  |   5 +
 4 files changed, 272 insertions(+), 18 deletions(-)

Comments

Daniel Stone July 31, 2017, 4:14 p.m. UTC | #1
Hi,

On 26 July 2017 at 19:07, Ben Widawsky <ben@bwidawsk.net> wrote:
> Due to hardware limitations we require that the main surface and
> the AUX surface (CCS) be part of the same bo. The hardware also
> makes life hard by not allowing you to provide separate x/y offsets
> for the main and AUX surfaces (excpet with NV12), so finding suitable
> offsets for both requires a bit of work. Assuming we still want keep
> playing tricks with the offsets. I've just gone with a dumb "search
> backward for suitable offsets" approach, which is far from optimal,
>                  but it works.
>
>                  Also not all planes will be capable of scanning out compressed surfaces,
>                  and eg. 90/270 degree rotation is not supported in combination with
>                  decompression either.
>
>                  This patch may contain work from at least the following people:
>                  * Vandana Kannan <vandana.kannan@intel.com>
>                  * Daniel Vetter <daniel@ffwll.ch>
>                  * Ben Widawsky <ben@bwidawsk.net>
>
>         v2: Deal with display workarounds 0390, 0531, 1125 (Paulo)
> v3: Pretend CCS tiles are regular 128 byte wide Y tiles (Jason)
>         Put the AUX register defines to the correct place
>         Fix up the slightly bogus rotation check
>         v4: Use I915_WRITE_FW() due to plane update locking changes
> s/return -EINVAL/goto err/ in intel_framebuffer_init()
>         Eliminate a bunch hardcoded numbers in CCS code
>
> v5: (By Ben)
> conflict resolution +
> -               res_blocks += fixed_16_16_to_u32_round_up(y_tile_minimum);
> +               res_blocks += fixed16_to_u32_round_up(y_tile_minimum);

':set paste' is your friend :P

Cheers,
Daniel
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1dc7e7a2a23b..c2a6c107f551 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6134,6 +6134,10 @@  enum {
 #define _PLANE_KEYMSK_2_A			0x70298
 #define _PLANE_KEYMAX_1_A			0x701a0
 #define _PLANE_KEYMAX_2_A			0x702a0
+#define _PLANE_AUX_DIST_1_A			0x701c0
+#define _PLANE_AUX_DIST_2_A			0x702c0
+#define _PLANE_AUX_OFFSET_1_A			0x701c4
+#define _PLANE_AUX_OFFSET_2_A			0x702c4
 #define _PLANE_COLOR_CTL_1_A			0x701CC /* GLK+ */
 #define _PLANE_COLOR_CTL_2_A			0x702CC /* GLK+ */
 #define _PLANE_COLOR_CTL_3_A			0x703CC /* GLK+ */
@@ -6240,6 +6244,24 @@  enum {
 #define PLANE_NV12_BUF_CFG(pipe, plane)	\
 	_MMIO_PLANE(plane, _PLANE_NV12_BUF_CFG_1(pipe), _PLANE_NV12_BUF_CFG_2(pipe))
 
+#define _PLANE_AUX_DIST_1_B		0x711c0
+#define _PLANE_AUX_DIST_2_B		0x712c0
+#define _PLANE_AUX_DIST_1(pipe) \
+			_PIPE(pipe, _PLANE_AUX_DIST_1_A, _PLANE_AUX_DIST_1_B)
+#define _PLANE_AUX_DIST_2(pipe) \
+			_PIPE(pipe, _PLANE_AUX_DIST_2_A, _PLANE_AUX_DIST_2_B)
+#define PLANE_AUX_DIST(pipe, plane)     \
+	_MMIO_PLANE(plane, _PLANE_AUX_DIST_1(pipe), _PLANE_AUX_DIST_2(pipe))
+
+#define _PLANE_AUX_OFFSET_1_B		0x711c4
+#define _PLANE_AUX_OFFSET_2_B		0x712c4
+#define _PLANE_AUX_OFFSET_1(pipe)       \
+		_PIPE(pipe, _PLANE_AUX_OFFSET_1_A, _PLANE_AUX_OFFSET_1_B)
+#define _PLANE_AUX_OFFSET_2(pipe)       \
+		_PIPE(pipe, _PLANE_AUX_OFFSET_2_A, _PLANE_AUX_OFFSET_2_B)
+#define PLANE_AUX_OFFSET(pipe, plane)   \
+	_MMIO_PLANE(plane, _PLANE_AUX_OFFSET_1(pipe), _PLANE_AUX_OFFSET_2(pipe))
+
 #define _PLANE_COLOR_CTL_1_B			0x711CC
 #define _PLANE_COLOR_CTL_2_B			0x712CC
 #define _PLANE_COLOR_CTL_3_B			0x713CC
@@ -6723,6 +6745,7 @@  enum {
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
 #define CHICKEN_PAR1_1		_MMIO(0x42080)
+#define  SKL_RC_HASH_OUTSIDE	(1 << 15)
 #define  DPA_MASK_VBLANK_SRD	(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES	(1 << 14)
 #define  SKL_EDP_PSR_FIX_RDWRAP	(1 << 3)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 0e71c7207258..27cde89c157d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1994,11 +1994,19 @@  intel_tile_width_bytes(const struct drm_framebuffer *fb, int plane)
 			return 128;
 		else
 			return 512;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+		if (plane == 1)
+			return 128;
+		/* fall through */
 	case I915_FORMAT_MOD_Y_TILED:
 		if (IS_GEN2(dev_priv) || HAS_128_BYTE_Y_TILING(dev_priv))
 			return 128;
 		else
 			return 512;
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		if (plane == 1)
+			return 128;
+		/* fall through */
 	case I915_FORMAT_MOD_Yf_TILED:
 		switch (cpp) {
 		case 1:
@@ -2105,7 +2113,7 @@  static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 
 	/* AUX_DIST needs only 4K alignment */
-	if (fb->format->format == DRM_FORMAT_NV12 && plane == 1)
+	if (plane == 1)
 		return 4096;
 
 	switch (fb->modifier) {
@@ -2115,6 +2123,8 @@  static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 		if (INTEL_GEN(dev_priv) >= 9)
 			return 256 * 1024;
 		return 0;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Yf_TILED:
 		return 1 * 1024 * 1024;
@@ -2422,6 +2432,7 @@  static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier)
 	case I915_FORMAT_MOD_X_TILED:
 		return I915_TILING_X;
 	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Y_TILED_CCS:
 		return I915_TILING_Y;
 	default:
 		return I915_TILING_NONE;
@@ -2487,6 +2498,36 @@  intel_fill_fb_info(struct drm_i915_private *dev_priv,
 
 		intel_fb_offset_to_xy(&x, &y, fb, i);
 
+		if ((fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+		     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS) && i == 1) {
+			int hsub = fb->format->hsub;
+			int vsub = fb->format->vsub;
+			int tile_width, tile_height;
+			int main_x, main_y;
+			int ccs_x, ccs_y;
+
+			intel_tile_dims(fb, i, &tile_width, &tile_height);
+
+			ccs_x = (x * hsub) % (tile_width * hsub);
+			ccs_y = (y * vsub) % (tile_height * vsub);
+			main_x = intel_fb->normal[0].x % (tile_width * hsub);
+			main_y = intel_fb->normal[0].y % (tile_height * vsub);
+
+			/*
+			 * CCS doesn't have its own x/y offset register, so the intra CCS tile
+			 * x/y offsets must match between CCS and the main surface.
+			 */
+			if (main_x != ccs_x || main_y != ccs_y) {
+				DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
+					      main_x, main_y,
+					      ccs_x, ccs_y,
+					      intel_fb->normal[0].x,
+					      intel_fb->normal[0].y,
+					      x, y);
+				return -EINVAL;
+			}
+		}
+
 		/*
 		 * The fence (if used) is aligned to the start of the object
 		 * so having the framebuffer wrap around across the edge of the
@@ -2847,6 +2888,9 @@  static int skl_max_plane_width(const struct drm_framebuffer *fb, int plane,
 			break;
 		}
 		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		/* FIXME AUX plane? */
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Yf_TILED:
 		switch (cpp) {
@@ -2869,6 +2913,44 @@  static int skl_max_plane_width(const struct drm_framebuffer *fb, int plane,
 	return 2048;
 }
 
+static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
+					   int main_x, int main_y, u32 main_offset)
+{
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	int hsub = fb->format->hsub;
+	int vsub = fb->format->vsub;
+	int aux_x = plane_state->aux.x;
+	int aux_y = plane_state->aux.y;
+	u32 aux_offset = plane_state->aux.offset;
+	u32 alignment = intel_surf_alignment(fb, 1);
+
+	while (aux_offset >= main_offset && aux_y <= main_y) {
+		int x, y;
+
+		if (aux_x == main_x && aux_y == main_y)
+			break;
+
+		if (aux_offset == 0)
+			break;
+
+		x = aux_x / hsub;
+		y = aux_y / vsub;
+		aux_offset = intel_adjust_tile_offset(&x, &y, plane_state, 1,
+						      aux_offset, aux_offset - alignment);
+		aux_x = x * hsub + aux_x % hsub;
+		aux_y = y * vsub + aux_y % vsub;
+	}
+
+	if (aux_x != main_x || aux_y != main_y)
+		return false;
+
+	plane_state->aux.offset = aux_offset;
+	plane_state->aux.x = aux_x;
+	plane_state->aux.y = aux_y;
+
+	return true;
+}
+
 static int skl_check_main_surface(struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->base.fb;
@@ -2911,7 +2993,7 @@  static int skl_check_main_surface(struct intel_plane_state *plane_state)
 
 		while ((x + w) * cpp > fb->pitches[0]) {
 			if (offset == 0) {
-				DRM_DEBUG_KMS("Unable to find suitable display surface offset\n");
+				DRM_DEBUG_KMS("Unable to find suitable display surface offset due to X-tiling\n");
 				return -EINVAL;
 			}
 
@@ -2920,6 +3002,26 @@  static int skl_check_main_surface(struct intel_plane_state *plane_state)
 		}
 	}
 
+	/*
+	 * CCS AUX surface doesn't have its own x/y offsets, we must make sure
+	 * they match with the main surface x/y offsets.
+	 */
+	if (fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+	    fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS) {
+		while (!skl_check_main_ccs_coordinates(plane_state, x, y, offset)) {
+			if (offset == 0)
+				break;
+
+			offset = intel_adjust_tile_offset(&x, &y, plane_state, 0,
+							  offset, offset - alignment);
+		}
+
+		if (x != plane_state->aux.x || y != plane_state->aux.y) {
+			DRM_DEBUG_KMS("Unable to find suitable display surface offset due to CCS\n");
+			return -EINVAL;
+		}
+	}
+
 	plane_state->main.offset = offset;
 	plane_state->main.x = x;
 	plane_state->main.y = y;
@@ -2956,6 +3058,49 @@  static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 	return 0;
 }
 
+static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
+{
+	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	int src_x = plane_state->base.src.x1 >> 16;
+	int src_y = plane_state->base.src.y1 >> 16;
+	int hsub = fb->format->hsub;
+	int vsub = fb->format->vsub;
+	int x = src_x / hsub;
+	int y = src_y / vsub;
+	u32 offset;
+
+	switch (plane->id) {
+	case PLANE_PRIMARY:
+	case PLANE_SPRITE0:
+		break;
+	default:
+		DRM_DEBUG_KMS("RC support only on plane 1 and 2\n");
+		return -EINVAL;
+	}
+
+	if (crtc->pipe == PIPE_C) {
+		DRM_DEBUG_KMS("No RC support on pipe C\n");
+		return -EINVAL;
+	}
+
+	if (plane_state->base.rotation & ~(DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180)) {
+		DRM_DEBUG_KMS("RC support only with 0/180 degree rotation %x\n",
+			      plane_state->base.rotation);
+		return -EINVAL;
+	}
+
+	intel_add_fb_offsets(&x, &y, plane_state, 1);
+	offset = intel_compute_tile_offset(&x, &y, plane_state, 1);
+
+	plane_state->aux.offset = offset;
+	plane_state->aux.x = x * hsub + src_x % hsub;
+	plane_state->aux.y = y * vsub + src_y % vsub;
+
+	return 0;
+}
+
 int skl_check_plane_surface(struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->base.fb;
@@ -2979,6 +3124,11 @@  int skl_check_plane_surface(struct intel_plane_state *plane_state)
 		ret = skl_check_nv12_aux_surface(plane_state);
 		if (ret)
 			return ret;
+	} else if (fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+		   fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS) {
+		ret = skl_check_ccs_aux_surface(plane_state);
+		if (ret)
+			return ret;
 	} else {
 		plane_state->aux.offset = ~0xfff;
 		plane_state->aux.x = 0;
@@ -3285,8 +3435,12 @@  static u32 skl_plane_ctl_tiling(uint64_t fb_modifier)
 		return PLANE_CTL_TILED_X;
 	case I915_FORMAT_MOD_Y_TILED:
 		return PLANE_CTL_TILED_Y;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+		return PLANE_CTL_TILED_Y | PLANE_CTL_DECOMPRESSION_ENABLE;
 	case I915_FORMAT_MOD_Yf_TILED:
 		return PLANE_CTL_TILED_YF;
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		return PLANE_CTL_TILED_YF | PLANE_CTL_DECOMPRESSION_ENABLE;
 	default:
 		MISSING_CASE(fb_modifier);
 	}
@@ -3359,6 +3513,7 @@  static void skylake_update_primary_plane(struct intel_plane *plane,
 	u32 plane_ctl = plane_state->ctl;
 	unsigned int rotation = plane_state->base.rotation;
 	u32 stride = skl_plane_stride(fb, 0, rotation);
+	u32 aux_stride = skl_plane_stride(fb, 1, rotation);
 	u32 surf_addr = plane_state->main.offset;
 	int scaler_id = plane_state->scaler_id;
 	int src_x = plane_state->main.x;
@@ -3395,6 +3550,10 @@  static void skylake_update_primary_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_OFFSET(pipe, plane_id), (src_y << 16) | src_x);
 	I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride);
 	I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w);
+	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id),
+		      (plane_state->aux.offset - surf_addr) | aux_stride);
+	I915_WRITE_FW(PLANE_AUX_OFFSET(pipe, plane_id),
+		      (plane_state->aux.y << 16) | plane_state->aux.x);
 
 	if (scaler_id >= 0) {
 		uint32_t ps_ctrl = 0;
@@ -8338,10 +8497,16 @@  skylake_get_initial_plane_config(struct intel_crtc *crtc,
 		fb->modifier = I915_FORMAT_MOD_X_TILED;
 		break;
 	case PLANE_CTL_TILED_Y:
-		fb->modifier = I915_FORMAT_MOD_Y_TILED;
+		if (val & PLANE_CTL_DECOMPRESSION_ENABLE)
+			fb->modifier = I915_FORMAT_MOD_Y_TILED_CCS;
+		else
+			fb->modifier = I915_FORMAT_MOD_Y_TILED;
 		break;
 	case PLANE_CTL_TILED_YF:
-		fb->modifier = I915_FORMAT_MOD_Yf_TILED;
+		if (val & PLANE_CTL_DECOMPRESSION_ENABLE)
+			fb->modifier = I915_FORMAT_MOD_Yf_TILED_CCS;
+		else
+			fb->modifier = I915_FORMAT_MOD_Yf_TILED;
 		break;
 	default:
 		MISSING_CASE(tiling);
@@ -13509,10 +13674,12 @@  static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 				  struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_framebuffer *fb = &intel_fb->base;
 	struct drm_format_name_buf format_name;
-	u32 pitch_limit, stride_alignment;
+	u32 pitch_limit;
 	unsigned int tiling, stride;
 	int ret = -EINVAL;
+	int i;
 
 	i915_gem_object_lock(obj);
 	obj->framebuffer_references++;
@@ -13541,6 +13708,19 @@  static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 
 	/* Passed in modifier sanity checking. */
 	switch (mode_cmd->modifier[0]) {
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		switch (mode_cmd->pixel_format) {
+		case DRM_FORMAT_XBGR8888:
+		case DRM_FORMAT_ABGR8888:
+		case DRM_FORMAT_XRGB8888:
+		case DRM_FORMAT_ARGB8888:
+			break;
+		default:
+			DRM_DEBUG_KMS("RC supported only with RGB8888 formats\n");
+			goto err;
+		}
+		/* fall through */
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Yf_TILED:
 		if (INTEL_GEN(dev_priv) < 9) {
@@ -13645,25 +13825,46 @@  static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	if (mode_cmd->offsets[0] != 0)
 		goto err;
 
-	drm_helper_mode_fill_fb_struct(&dev_priv->drm,
-				       &intel_fb->base, mode_cmd);
+	drm_helper_mode_fill_fb_struct(&dev_priv->drm, fb, mode_cmd);
 
-	stride_alignment = intel_fb_stride_alignment(&intel_fb->base, 0);
-	if (mode_cmd->pitches[0] & (stride_alignment - 1)) {
-		DRM_DEBUG_KMS("pitch (%d) must be at least %u byte aligned\n",
-			      mode_cmd->pitches[0], stride_alignment);
-		goto err;
+	for (i = 0; i < fb->format->num_planes; i++) {
+		u32 stride_alignment;
+
+		if (mode_cmd->handles[i] != mode_cmd->handles[0]) {
+			DRM_DEBUG_KMS("bad plane %d handle\n", i);
+			return -EINVAL;
+		}
+
+		stride_alignment = intel_fb_stride_alignment(fb, i);
+
+		/*
+		 * Display WA #0531: skl,bxt,kbl,glk
+		 *
+		 * Render decompression and plane width > 3840
+		 * combined with horizontal panning requires the
+		 * plane stride to be a multiple of 4. We'll just
+		 * require the entire fb to accommodate that to avoid
+		 * potential runtime errors at plane configuration time.
+		 */
+		if (IS_GEN9(dev_priv) && i == 0 && fb->width > 3840 &&
+		    (fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+		     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS))
+			stride_alignment *= 4;
+
+		if (fb->pitches[i] & (stride_alignment - 1)) {
+			DRM_DEBUG_KMS("plane %d pitch (%d) must be at least %u byte aligned\n",
+				      i, fb->pitches[i], stride_alignment);
+			goto err;
+		}
 	}
 
 	intel_fb->obj = obj;
 
-	ret = intel_fill_fb_info(dev_priv, &intel_fb->base);
+	ret = intel_fill_fb_info(dev_priv, fb);
 	if (ret)
 		goto err;
 
-	ret = drm_framebuffer_init(obj->base.dev,
-				   &intel_fb->base,
-				   &intel_fb_funcs);
+	ret = drm_framebuffer_init(&dev_priv->drm, fb, &intel_fb_funcs);
 	if (ret) {
 		DRM_ERROR("framebuffer init failed %d\n", ret);
 		goto err;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 48785ef75d33..85ee779c2942 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -62,6 +62,20 @@  static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(CHICKEN_PAR1_1,
 		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
 
+	/*
+	 * Display WA#0390: skl,bxt,kbl,glk
+	 *
+	 * Must match Sampler, Pixel Back End, and Media
+	 * (0xE194 bit 8, 0x7014 bit 13, 0x4DDC bits 27 and 31).
+	 *
+	 * Including bits outside the page in the hash would
+	 * require 2 (or 4?) MiB alignment of resources. Just
+	 * assume the defaul hashing mode which only uses bits
+	 * within the page.
+	 */
+	I915_WRITE(CHICKEN_PAR1_1,
+		   I915_READ(CHICKEN_PAR1_1) & ~SKL_RC_HASH_OUTSIDE);
+
 	I915_WRITE(GEN8_CONFIG0,
 		   I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES);
 
@@ -4071,7 +4085,9 @@  skl_ddb_min_alloc(const struct drm_plane_state *pstate,
 
 	/* For Non Y-tile return 8-blocks */
 	if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
-	    fb->modifier != I915_FORMAT_MOD_Yf_TILED)
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED &&
+	    fb->modifier != I915_FORMAT_MOD_Y_TILED_CCS &&
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED_CCS)
 		return 8;
 
 	/*
@@ -4377,7 +4393,9 @@  static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	}
 
 	y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
-		  fb->modifier == I915_FORMAT_MOD_Yf_TILED;
+		  fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
+		  fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+		  fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
 	x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;
 
 	/* Display WA #1141: kbl,cfl */
@@ -4472,6 +4490,13 @@  static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	res_lines = div_round_up_fixed16(selected_result,
 					 plane_blocks_per_line);
 
+	/* Display WA #1125: skl,bxt,kbl,glk */
+	if (level == 0 &&
+	    (fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS))
+		res_blocks += fixed16_to_u32_round_up(y_tile_minimum);
+
+	/* Display WA #1126: skl,bxt,kbl,glk */
 	if (level >= 1 && level <= 7) {
 		if (y_tiled) {
 			res_blocks += fixed16_to_u32_round_up(y_tile_minimum);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 8e25694a1508..3d704bd72e2a 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -238,6 +238,7 @@  skl_update_plane(struct intel_plane *plane,
 	u32 surf_addr = plane_state->main.offset;
 	unsigned int rotation = plane_state->base.rotation;
 	u32 stride = skl_plane_stride(fb, 0, rotation);
+	u32 aux_stride = skl_plane_stride(fb, 1, rotation);
 	int crtc_x = plane_state->base.dst.x1;
 	int crtc_y = plane_state->base.dst.y1;
 	uint32_t crtc_w = drm_rect_width(&plane_state->base.dst);
@@ -272,6 +273,10 @@  skl_update_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_OFFSET(pipe, plane_id), (y << 16) | x);
 	I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride);
 	I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w);
+	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id),
+		      (plane_state->aux.offset - surf_addr) | aux_stride);
+	I915_WRITE_FW(PLANE_AUX_OFFSET(pipe, plane_id),
+		      (plane_state->aux.y << 16) | plane_state->aux.x);
 
 	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {