[Intel-gfx] [RFC PATCH 2/3] drm/i915: Implement .get_format_info() hook for CCS

[Daniel Stone]

From: Ville Syrjälä <ville.syrjala at 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.

By providing our own format information for the CCS formats, we should
be able to make framebuffer_check() do the right thing for the CCS
surface as well.

Note that we'll return the same format info for both Y and Yf tiled
format as that's what happens with the non-CCS Y vs. Yf as well. If
desired, we could potentially return a unique pointer for each
pixel_format+tiling+ccs combination, in which case we immediately be
able to tell if any of that stuff changed by just comparing the
pointers. But that does sound a bit wasteful space wise.

v2: Drop the 'dev' argument from the hook
v3: Include the description of the CCS surface layout
v4: Pretend CCS tiles are regular 128 byte wide Y tiles (Jason)

Cc: Daniel Vetter <daniel at ffwll.ch>
Cc: Ben Widawsky <ben at bwidawsk.net>
Cc: Jason Ekstrand <jason at jlekstrand.net>
Reviewed-by: Ben Widawsky <ben at bwidawsk.net> (v3)
Signed-off-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
Signed-off-by: Daniel Stone <daniels at collabora.com>
---
 drivers/gpu/drm/i915/intel_display.c | 51 ++++++++++++++++++++++++++++++++++++
 include/uapi/drm/drm_fourcc.h        | 20 ++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 847064152563..b20e89396e04 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2452,6 +2452,56 @@ static unsigned int intel_fb_modifier_to_tiling(uint64_t fb_modifier)
 	}
 }
 
+/*
+ * 1 byte of CCS actually corresponds to 16x8 pixels on the main
+ * surface, and the memory layout for the CCS tile us 64x64 bytes.
+ * But since we're pretending the CCS tile is 128 bytes wide we
+ * adjust hsub/vsub here accordingly to 8x16 so that the
+ * bytes<->x/y conversions come out correct. We don't require any
+ * CCS block size alignment of the fb under the assumption that the
+ * hardware will handle things correctly of only a single pixel
+ * gets touched. The compression should be lossless so any garbage
+ * pixels as part of the same block shouldn't cause visual artifacts.
+ */
+static const struct drm_format_info ccs_formats[] = {
+	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2, .cpp = { 4, 1, },
+	  .hsub = 8, .vsub = 16, .halign =  1, .valign = 1, },
+	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2, .cpp = { 4, 1, },
+	  .hsub = 8, .vsub = 16, .halign = 1, .valign = 1, },
+	{ .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2, .cpp = { 4, 1, },
+	  .hsub = 8, .vsub = 16, .halign = 1, .valign = 1, },
+	{ .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2, .cpp = { 4, 1, },
+	  .hsub = 8, .vsub = 16, .halign = 1, .valign = 1, },
+};
+
+static const struct drm_format_info *
+lookup_format_info(const struct drm_format_info formats[],
+		   int num_formats, u32 format)
+{
+	int i;
+
+	for (i = 0; i < num_formats; i++) {
+		if (formats[i].format == format)
+			return &formats[i];
+	}
+
+	return NULL;
+}
+
+static const struct drm_format_info *
+intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
+{
+	switch (cmd->modifier[0]) {
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		return lookup_format_info(ccs_formats,
+					  ARRAY_SIZE(ccs_formats),
+					  cmd->pixel_format);
+	default:
+		return NULL;
+	}
+}
+
 static int
 intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		   struct drm_framebuffer *fb)
@@ -14725,6 +14775,7 @@ static void intel_atomic_state_free(struct drm_atomic_state *state)
 
 static const struct drm_mode_config_funcs intel_mode_funcs = {
 	.fb_create = intel_user_framebuffer_create,
+	.get_format_info = intel_get_format_info,
 	.output_poll_changed = intel_fbdev_output_poll_changed,
 	.atomic_check = intel_atomic_check,
 	.atomic_commit = intel_atomic_commit,
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 47f0175e29c0..500c4c7ba5a9 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -263,6 +263,26 @@ extern "C" {
 #define I915_FORMAT_MOD_Yf_TILED fourcc_mod_code(INTEL, 3)
 
 /*
+ * Intel color control surface (CCS) for render compression
+ *
+ * The framebuffer format must be one of the 8:8:8:8 RGB formats.
+ * The main surface will be plane index 0 and must be Y/Yf-tiled,
+ * the CCS will be plane index 1.
+ *
+ * Each CCS tile matches a 1024x512 pixel area of the main surface.
+ * To match certain aspects of the 3D hardware the CCS is
+ * considered to be made up of normal 128Bx32 Y tiles, Thus
+ * the CCS pitch must be specified in multiples of 128 bytes.
+ *
+ * In reality the CCS tile appears to be a 64Bx64 Y tile, composed
+ * of QWORD (8 bytes) chunks instead of OWORD (16 bytes) chunks.
+ * But that fact is not relevant unless the memory is accessed
+ * directly.
+ */
+#define I915_FORMAT_MOD_Y_TILED_CCS	fourcc_mod_code(INTEL, 4)
+#define I915_FORMAT_MOD_Yf_TILED_CCS	fourcc_mod_code(INTEL, 5)
+
+/*
  * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
  *
  * Macroblocks are laid in a Z-shape, and each pixel data is following the
-- 
2.11.0