All of lore.kernel.org
 help / color / mirror / Atom feed
From: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: nanley.g.chery@intel.com,
	Lucas De Marchi <lucas.demarchi@intel.com>,
	Daniel Vetter <daniel.vetter@intel.com>,
	dhinakaran.pandiyan@intel.com, ville.syrjala@intel.com
Subject: [PATCH 2/6] drm/i915/tgl: Gen-12 render decompression
Date: Tue, 17 Sep 2019 05:11:51 -0700	[thread overview]
Message-ID: <20190917121155.13197-3-radhakrishna.sripada@intel.com> (raw)
In-Reply-To: <20190917121155.13197-1-radhakrishna.sripada@intel.com>

From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>

Gen-12 decompression is supported with Y-tiled main surface. The CCS is
linear and has 4 bits of data for each main surface cache line pair, a
ratio of 1:256. Gen-12 display decompression is incompatible with buffers
compressed by earlier GPUs, so make use of a new modifier to identify
gen-12 compression. Another notable change is that decompression is
supported on all planes except cursor and on all pipes. This patch adds
decompression support for [A,X]BGR888 pixel formats.

Bspec: 18437

v2: Fix checkpatch warnings (Lucas)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 63 +++++++++++++++++---
 drivers/gpu/drm/i915/display/intel_sprite.c  | 23 ++++---
 2 files changed, 71 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1cc74844d3ea..69b187c49a70 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -1911,6 +1911,10 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 		if (color_plane == 1)
 			return 128;
 		/* fall through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		if (color_plane == 1)
+			return cpp;
+		/* fall through */
 	case I915_FORMAT_MOD_Y_TILED:
 		if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv))
 			return 128;
@@ -2044,6 +2048,8 @@ 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_GEN12_RC_CCS:
+		return 4 * 4 * 1024;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 	case I915_FORMAT_MOD_Y_TILED:
@@ -2243,7 +2249,8 @@ static u32 intel_adjust_tile_offset(int *x, int *y,
 
 static bool is_surface_linear(u64 modifier, int color_plane)
 {
-	return modifier == DRM_FORMAT_MOD_LINEAR;
+	return modifier == DRM_FORMAT_MOD_LINEAR ||
+	       (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS && color_plane == 1);
 }
 
 static u32 intel_adjust_aligned_offset(int *x, int *y,
@@ -2430,6 +2437,7 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
 		return I915_TILING_X;
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		return I915_TILING_Y;
 	default:
 		return I915_TILING_NONE;
@@ -2450,7 +2458,7 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
  * us a ratio of one byte in the CCS for each 8x16 pixels in the
  * main surface.
  */
-static const struct drm_format_info ccs_formats[] = {
+static const struct drm_format_info skl_ccs_formats[] = {
 	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, },
 	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
@@ -2461,6 +2469,24 @@ static const struct drm_format_info ccs_formats[] = {
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, },
 };
 
+/*
+ * Gen-12 compression uses 4 bits of CCS data for each cache line pair in the
+ * main surface. And each 64B CCS cache line represents an area of 4x1 Y-tiles
+ * in the main surface. With 4 byte pixels and each Y-tile having dimensions of
+ * 32x32 pixels, the ratio turns out to 1B in the CCS for every 2 x 32 pixels in
+ * the main surface.
+ */
+static const struct drm_format_info gen12_ccs_formats[] = {
+	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
+	  .cpp = { 4, 1, }, .hsub = 2, .vsub = 32, },
+	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
+	  .cpp = { 4, 1, }, .hsub = 2, .vsub = 32, },
+	{ .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2,
+	  .cpp = { 4, 1, }, .hsub = 2, .vsub = 32, .has_alpha = true },
+	{ .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2,
+	  .cpp = { 4, 1, }, .hsub = 2, .vsub = 32, .has_alpha = true },
+};
+
 static const struct drm_format_info *
 lookup_format_info(const struct drm_format_info formats[],
 		   int num_formats, u32 format)
@@ -2481,8 +2507,12 @@ 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),
+		return lookup_format_info(skl_ccs_formats,
+					  ARRAY_SIZE(skl_ccs_formats),
+					  cmd->pixel_format);
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		return lookup_format_info(gen12_ccs_formats,
+					  ARRAY_SIZE(gen12_ccs_formats),
 					  cmd->pixel_format);
 	default:
 		return NULL;
@@ -2491,7 +2521,8 @@ intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
 
 bool is_ccs_modifier(u64 modifier)
 {
-	return modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+	return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 	       modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
 }
 
@@ -2660,7 +2691,13 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			int main_x, main_y;
 			int ccs_x, ccs_y;
 
-			intel_tile_dims(fb, i, &tile_width, &tile_height);
+			if (!is_surface_linear(fb->modifier, i)) {
+				intel_tile_dims(fb, i, &tile_width, &tile_height);
+			} else {
+				tile_width = 64 / cpp;
+				tile_height = 1;
+			}
+
 			tile_width *= hsub;
 			tile_height *= vsub;
 
@@ -4069,6 +4106,8 @@ static u32 skl_plane_ctl_tiling(u64 fb_modifier)
 	case I915_FORMAT_MOD_Y_TILED:
 		return PLANE_CTL_TILED_Y;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
+		/* fall through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		return PLANE_CTL_TILED_Y | PLANE_CTL_RENDER_DECOMPRESSION_ENABLE;
 	case I915_FORMAT_MOD_Yf_TILED:
 		return PLANE_CTL_TILED_YF;
@@ -9844,7 +9883,9 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	case PLANE_CTL_TILED_Y:
 		plane_config->tiling = I915_TILING_Y;
 		if (val & PLANE_CTL_RENDER_DECOMPRESSION_ENABLE)
-			fb->modifier = I915_FORMAT_MOD_Y_TILED_CCS;
+			fb->modifier = INTEL_GEN(dev_priv) >= 12 ?
+				I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS :
+				I915_FORMAT_MOD_Y_TILED_CCS;
 		else
 			fb->modifier = I915_FORMAT_MOD_Y_TILED;
 		break;
@@ -15647,6 +15688,14 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		    is_ccs_modifier(fb->modifier))
 			stride_alignment *= 4;
 
+		/*
+		 * The main surface pitch must be paded to a multiple of four
+		 * tile widths.
+		 */
+		if (fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS &&
+		    i == 0)
+			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);
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 7a7078d0ba23..866d25d38d04 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -535,6 +535,7 @@ skl_program_plane(struct intel_plane *plane,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 surf_addr = plane_state->color_plane[color_plane].offset;
 	u32 stride = skl_plane_stride(plane_state, color_plane);
+	u32 aux_dist = plane_state->color_plane[1].offset - surf_addr;
 	u32 aux_stride = skl_plane_stride(plane_state, 1);
 	int crtc_x = plane_state->base.dst.x1;
 	int crtc_y = plane_state->base.dst.y1;
@@ -576,8 +577,10 @@ skl_program_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride);
 	I915_WRITE_FW(PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x);
 	I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w);
-	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id),
-		      (plane_state->color_plane[1].offset - surf_addr) | aux_stride);
+
+	if (INTEL_GEN(dev_priv) < 12)
+		aux_dist |= aux_stride;
+	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id), aux_dist);
 
 	if (icl_is_hdr_plane(dev_priv, plane_id)) {
 		u32 cus_ctl = 0;
@@ -1733,7 +1736,8 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 	    (fb->modifier == I915_FORMAT_MOD_Y_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS)) {
+	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS)) {
 		DRM_DEBUG_KMS("Y/Yf tiling not supported in IF-ID mode\n");
 		return -EINVAL;
 	}
@@ -2145,7 +2149,8 @@ static const u64 skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
-static const u64 gen12_plane_format_modifiers_noccs[] = {
+static const u64 gen12_plane_format_modifiers_ccs[] = {
+	I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS,
 	I915_FORMAT_MOD_Y_TILED,
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
@@ -2307,6 +2312,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
 	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		break;
 	default:
 		return false;
@@ -2317,6 +2323,9 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_ABGR8888:
+		if (is_ccs_modifier(modifier))
+			return true;
+		/* fall through */
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
@@ -2525,13 +2534,11 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 		formats = skl_get_plane_formats(dev_priv, pipe,
 						plane_id, &num_formats);
 
+	plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 	if (INTEL_GEN(dev_priv) >= 12) {
-		/* TODO: Implement support for gen-12 CCS modifiers */
-		plane->has_ccs = false;
-		modifiers = gen12_plane_format_modifiers_noccs;
+		modifiers = gen12_plane_format_modifiers_ccs;
 		plane_funcs = &gen12_plane_funcs;
 	} else {
-		plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 		if (plane->has_ccs)
 			modifiers = skl_plane_format_modifiers_ccs;
 		else
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2019-09-17 12:10 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-17 12:11 [PATCH 0/6] Clear Color Support for TGL Render Decompression Radhakrishna Sripada
2019-09-17 12:11 ` [PATCH 1/6] drm/framebuffer/tgl: Format modifier for Intel Gen-12 render compression Radhakrishna Sripada
2019-09-17 12:11 ` Radhakrishna Sripada [this message]
2019-09-17 12:11 ` [PATCH 3/6] drm/framebuffer/tgl: Format modifier for Intel Gen-12 media compression Radhakrishna Sripada
2019-09-17 12:11 ` [PATCH 4/6] drm/i915/tgl: " Radhakrishna Sripada
2019-09-17 12:11 ` [PATCH 5/6] drm/framebuffer/tgl: Format modifier for Intel Gen 12 render compression with Clear Color Radhakrishna Sripada
2019-09-17 12:11 ` [PATCH 6/6] drm/i915/tgl: Add Clear Color supoort for TGL Render Decompression Radhakrishna Sripada
2019-09-17 21:52   ` Matt Roper
2019-09-19 22:16     ` Sripada, Radhakrishna
2019-09-19 22:38       ` Matt Roper
2019-09-19  0:53   ` Jordan Justen
2019-09-17 15:05 ` ✗ Fi.CI.CHECKPATCH: warning for Clear Color Support " Patchwork
2019-09-17 15:27 ` ✓ Fi.CI.BAT: success " Patchwork
2019-09-18  2:09 ` ✓ Fi.CI.IGT: " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190917121155.13197-3-radhakrishna.sripada@intel.com \
    --to=radhakrishna.sripada@intel.com \
    --cc=daniel.vetter@intel.com \
    --cc=dhinakaran.pandiyan@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    --cc=nanley.g.chery@intel.com \
    --cc=ville.syrjala@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.