diff mbox

[v5,2/2] drm/i915: Add render decompression support

Message ID 20170613151244.31609-3-ville.syrjala@linux.intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Ville Syrjälä June 13, 2017, 3:12 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: Switch to the LLC/eLLC hotspot avoidance hash mode
    Skip fence alignemnt check for CCS
    Treat fb->offsets[] as a raw byte offset instead of
    a linear offset

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>
Cc: Daniel Stone <daniels@collabora.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
---
 drivers/gpu/drm/i915/i915_reg.h        |  29 +++
 drivers/gpu/drm/i915/intel_display.c   | 343 +++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_engine_cs.c |  13 ++
 drivers/gpu/drm/i915/intel_pm.c        |  29 ++-
 drivers/gpu/drm/i915/intel_sprite.c    |   5 +
 5 files changed, 359 insertions(+), 60 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b6d69e289974..877c425ef5c5 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5909,6 +5909,10 @@  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+ */
@@ -6015,6 +6019,24 @@  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
@@ -6498,6 +6520,7 @@  enum {
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
 #define CHICKEN_PAR1_1		_MMIO(0x42080)
+#define  SKL_DE_COMPRESSED_HASH_MODE	(1 << 15)
 #define  DPA_MASK_VBLANK_SRD	(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES	(1 << 14)
 #define  SKL_EDP_PSR_FIX_RDWRAP	(1 << 3)
@@ -6566,6 +6589,7 @@  enum {
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
 # define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
 #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)
@@ -7653,6 +7677,7 @@  enum {
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
 
 #define GEN9_HALF_SLICE_CHICKEN7	_MMIO(0xe194)
+#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	(1<<8)
 #define   GEN9_ENABLE_YV12_BUGFIX	(1<<4)
 #define   GEN9_ENABLE_GPGPU_PREEMPTION	(1<<2)
 
@@ -8869,4 +8894,8 @@  enum {
 #define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL  0x67F1427F /*    "        " */
 #define   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT  0x5FF101FF /*    "        " */
 
+#define MMCD_MISC_CTRL		_MMIO(0x4ddc) /* skl+ */
+#define  MMCD_PCLA		(1 << 31)
+#define  MMCD_HOTSPOT_EN	(1 << 27)
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index bb7851c70f90..1f1b877abdfa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2004,11 +2004,19 @@  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:
@@ -2115,7 +2123,7 @@  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) {
@@ -2125,6 +2133,8 @@  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;
@@ -2255,17 +2265,13 @@  void intel_add_fb_offsets(int *x, int *y,
 	}
 }
 
-/*
- * Input tile dimensions and pitch must already be
- * rotated to match x and y, and in pixel units.
- */
-static u32 _intel_adjust_tile_offset(int *x, int *y,
-				     unsigned int tile_width,
-				     unsigned int tile_height,
-				     unsigned int tile_size,
-				     unsigned int pitch_tiles,
-				     u32 old_offset,
-				     u32 new_offset)
+static u32 __intel_adjust_tile_offset(int *x, int *y,
+				      unsigned int tile_width,
+				      unsigned int tile_height,
+				      unsigned int tile_size,
+				      unsigned int pitch_tiles,
+				      u32 old_offset,
+				      u32 new_offset)
 {
 	unsigned int pitch_pixels = pitch_tiles * tile_width;
 	unsigned int tiles;
@@ -2286,18 +2292,13 @@  static u32 _intel_adjust_tile_offset(int *x, int *y,
 	return new_offset;
 }
 
-/*
- * Adjust the tile offset by moving the difference into
- * the x/y offsets.
- */
-static u32 intel_adjust_tile_offset(int *x, int *y,
-				    const struct intel_plane_state *state, int plane,
-				    u32 old_offset, u32 new_offset)
+static u32 _intel_adjust_tile_offset(int *x, int *y,
+				     const struct drm_framebuffer *fb, int plane,
+				     unsigned int rotation,
+				     u32 old_offset, u32 new_offset)
 {
-	const struct drm_i915_private *dev_priv = to_i915(state->base.plane->dev);
-	const struct drm_framebuffer *fb = state->base.fb;
+	const struct drm_i915_private *dev_priv = to_i915(fb->dev);
 	unsigned int cpp = fb->format->cpp[plane];
-	unsigned int rotation = state->base.rotation;
 	unsigned int pitch = intel_fb_pitch(fb, plane, rotation);
 
 	WARN_ON(new_offset > old_offset);
@@ -2316,9 +2317,9 @@  static u32 intel_adjust_tile_offset(int *x, int *y,
 			pitch_tiles = pitch / (tile_width * cpp);
 		}
 
-		_intel_adjust_tile_offset(x, y, tile_width, tile_height,
-					  tile_size, pitch_tiles,
-					  old_offset, new_offset);
+		__intel_adjust_tile_offset(x, y, tile_width, tile_height,
+					   tile_size, pitch_tiles,
+					   old_offset, new_offset);
 	} else {
 		old_offset += *y * pitch + *x * cpp;
 
@@ -2330,6 +2331,19 @@  static u32 intel_adjust_tile_offset(int *x, int *y,
 }
 
 /*
+ * Adjust the tile offset by moving the difference into
+ * the x/y offsets.
+ */
+static u32 intel_adjust_tile_offset(int *x, int *y,
+				    const struct intel_plane_state *state, int plane,
+				    u32 old_offset, u32 new_offset)
+{
+	return _intel_adjust_tile_offset(x, y, state->base.fb, plane,
+					 state->base.rotation,
+					 old_offset, new_offset);
+}
+
+/*
  * Computes the linear offset to the base tile and adjusts
  * x, y. bytes per pixel is assumed to be a power-of-two.
  *
@@ -2380,9 +2394,9 @@  static u32 _intel_compute_tile_offset(const struct drm_i915_private *dev_priv,
 		offset = (tile_rows * pitch_tiles + tiles) * tile_size;
 		offset_aligned = offset & ~alignment;
 
-		_intel_adjust_tile_offset(x, y, tile_width, tile_height,
-					  tile_size, pitch_tiles,
-					  offset, offset_aligned);
+		__intel_adjust_tile_offset(x, y, tile_width, tile_height,
+					   tile_size, pitch_tiles,
+					   offset, offset_aligned);
 	} else {
 		offset = *y * pitch + *x * cpp;
 		offset_aligned = offset & ~alignment;
@@ -2414,16 +2428,24 @@  u32 intel_compute_tile_offset(int *x, int *y,
 					  rotation, alignment);
 }
 
-/* Convert the fb->offset[] linear offset into x/y offsets */
-static void intel_fb_offset_to_xy(int *x, int *y,
-				  const struct drm_framebuffer *fb, int plane)
+/* Convert the fb->offset[] into x/y offsets */
+static int intel_fb_offset_to_xy(int *x, int *y,
+				 const struct drm_framebuffer *fb, int plane)
 {
-	unsigned int cpp = fb->format->cpp[plane];
-	unsigned int pitch = fb->pitches[plane];
-	u32 linear_offset = fb->offsets[plane];
+	struct drm_i915_private *dev_priv = to_i915(fb->dev);
+
+	if (fb->modifier != DRM_FORMAT_MOD_LINEAR &&
+	    fb->offsets[plane] % intel_tile_size(dev_priv))
+		return -EINVAL;
 
-	*y = linear_offset / pitch;
-	*x = linear_offset % pitch / cpp;
+	*x = 0;
+	*y = 0;
+
+	_intel_adjust_tile_offset(x, y,
+				  fb, plane, DRM_MODE_ROTATE_0,
+				  fb->offsets[plane], 0);
+
+	return 0;
 }
 
 static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier)
@@ -2432,6 +2454,7 @@  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;
@@ -2496,12 +2519,50 @@  intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		unsigned int cpp, size;
 		u32 offset;
 		int x, y;
+		int ret;
 
 		cpp = fb->format->cpp[i];
 		width = drm_framebuffer_plane_width(fb->width, fb, i);
 		height = drm_framebuffer_plane_height(fb->height, fb, i);
 
-		intel_fb_offset_to_xy(&x, &y, fb, i);
+		ret = intel_fb_offset_to_xy(&x, &y, fb, i);
+		if (ret) {
+			DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n",
+				      i, fb->offsets[i]);
+			return ret;
+		}
+
+		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);
+			tile_width *= hsub;
+			tile_height *= vsub;
+
+			ccs_x = (x * hsub) % tile_width;
+			ccs_y = (y * vsub) % tile_height;
+			main_x = intel_fb->normal[0].x % tile_width;
+			main_y = intel_fb->normal[0].y % tile_height;
+
+			/*
+			 * 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
@@ -2512,7 +2573,7 @@  intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		 * fb layout agrees with the fence layout. We already check that the
 		 * fb stride matches the fence stride elsewhere.
 		 */
-		if (i915_gem_object_is_tiled(intel_fb->obj) &&
+		if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) &&
 		    (x + width) * cpp > fb->pitches[i]) {
 			DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n",
 				      i, fb->offsets[i]);
@@ -2575,10 +2636,10 @@  intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			 * We only keep the x/y offsets, so push all of the
 			 * gtt offset into the x/y offsets.
 			 */
-			_intel_adjust_tile_offset(&x, &y,
-						  tile_width, tile_height,
-						  tile_size, pitch_tiles,
-						  gtt_offset_rotated * tile_size, 0);
+			__intel_adjust_tile_offset(&x, &y,
+						   tile_width, tile_height,
+						   tile_size, pitch_tiles,
+						   gtt_offset_rotated * tile_size, 0);
 
 			gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
 
@@ -2877,6 +2938,9 @@  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) {
@@ -2899,6 +2963,44 @@  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;
@@ -2941,7 +3043,7 @@  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;
 			}
 
@@ -2950,6 +3052,26 @@  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;
@@ -2986,6 +3108,49 @@  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;
@@ -3009,6 +3174,11 @@  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;
@@ -3315,8 +3485,12 @@  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);
 	}
@@ -3389,6 +3563,7 @@  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;
@@ -3425,6 +3600,10 @@  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;
@@ -8452,10 +8631,16 @@  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);
@@ -10592,7 +10777,7 @@  static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
 	u32 ctl, stride = skl_plane_stride(fb, 0, rotation);
 
 	ctl = I915_READ(PLANE_CTL(pipe, 0));
-	ctl &= ~PLANE_CTL_TILED_MASK;
+	ctl &= ~(PLANE_CTL_TILED_MASK | PLANE_CTL_DECOMPRESSION_ENABLE);
 	switch (fb->modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
 		break;
@@ -10602,9 +10787,15 @@  static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
 	case I915_FORMAT_MOD_Y_TILED:
 		ctl |= PLANE_CTL_TILED_Y;
 		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+		ctl |= PLANE_CTL_TILED_Y | PLANE_CTL_DECOMPRESSION_ENABLE;
+		break;
 	case I915_FORMAT_MOD_Yf_TILED:
 		ctl |= PLANE_CTL_TILED_YF;
 		break;
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		ctl |= PLANE_CTL_TILED_YF | PLANE_CTL_DECOMPRESSION_ENABLE;
+		break;
 	default:
 		MISSING_CASE(fb->modifier);
 	}
@@ -14430,10 +14621,12 @@  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++;
@@ -14462,6 +14655,19 @@  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) {
@@ -14566,25 +14772,46 @@  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_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index bc38bd128b76..a529d273f583 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -825,6 +825,19 @@  static int gen9_init_workarounds(struct intel_engine_cs *engine)
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
 		   ECOCHK_DIS_TLB);
 
+	if (HAS_LLC(dev_priv)) {
+		/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
+		 *
+		 * Must match Display Engine. See
+		 * WaCompressedResourceDisplayNewHashMode.
+		 */
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN9_PBE_COMPRESSED_HASH_SELECTION);
+		WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
+				  GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
+		WA_SET_BIT(MMCD_MISC_CTRL, MMCD_PCLA | MMCD_HOTSPOT_EN);
+	}
+
 	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk */
 	/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0aed13dcedf0..52e2961452bc 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -58,10 +58,24 @@ 
 
 static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	if (HAS_LLC(dev_priv)) {
+		/*
+		 * WaCompressedResourceDisplayNewHashMode:skl,kbl
+		 * Display WA#0390: skl,kbl
+		 *
+		 * Must match Sampler, Pixel Back End, and Media. See
+		 * WaCompressedResourceSamplerPbeMediaNewHashMode.
+		 */
+		I915_WRITE(CHICKEN_PAR1_1,
+			   I915_READ(CHICKEN_PAR1_1) |
+			   SKL_DE_COMPRESSED_HASH_MODE);
+	}
+
 	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
 	I915_WRITE(CHICKEN_PAR1_1,
 		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
 
+
 	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;
 
 	/*
@@ -4456,7 +4472,9 @@  static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 		return 0;
 
 	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 */
@@ -4552,6 +4570,13 @@  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 += fixed_16_16_to_u32_round_up(y_tile_minimum);
+
+	/* Display WA #1126: skl,bxt,kbl,glk */
 	if (level >= 1 && level <= 7) {
 		if (y_tiled) {
 			res_blocks += fixed_16_16_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 0c650c2cbca8..3e4549a101f8 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -244,6 +244,7 @@  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);
@@ -278,6 +279,10 @@  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) {