drm/i915: Adding dbuf support for skl nv12 format.

Skylake nv12 format requires dbuf (aka. ddb) calculations
and programming for each of y and uv sub-planes. Made minor
changes to reuse current dbuf calculations and programming
for uv plane. i.e., with this change, existing computation
is used for either packed format or uv portion of nv12
depending on incoming format. Added new code for dbuf
computation and programming for y plane.

This patch is a pre-requisite for adding NV12 format support.
Actual nv12 support is coming in later patches.
Signed-off-by: Chandra Konduru <chandra.konduru@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_drv.h

@@ -1468,7 +1468,8 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1,
 
 struct skl_ddb_allocation {
 	struct skl_ddb_entry pipe[I915_MAX_PIPES];
-	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES];
+	struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */
+	struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* y-plane */
 	struct skl_ddb_entry cursor[I915_MAX_PIPES];
 };
 

drivers/gpu/drm/i915/i915_reg.h

@@ -5167,6 +5167,8 @@ enum skl_disp_power_wells {
 #define _PLANE_KEYMAX_2_A			0x702a0
 #define _PLANE_BUF_CFG_1_A			0x7027c
 #define _PLANE_BUF_CFG_2_A			0x7037c
+#define _PLANE_NV12_BUF_CFG_1_A		0x70278
+#define _PLANE_NV12_BUF_CFG_2_A		0x70378
 
 #define _PLANE_CTL_1_B				0x71180
 #define _PLANE_CTL_2_B				0x71280
@@ -5253,6 +5255,15 @@ enum skl_disp_power_wells {
 #define PLANE_BUF_CFG(pipe, plane)	\
 	_PLANE(plane, _PLANE_BUF_CFG_1(pipe), _PLANE_BUF_CFG_2(pipe))
 
+#define _PLANE_NV12_BUF_CFG_1_B		0x71278
+#define _PLANE_NV12_BUF_CFG_2_B		0x71378
+#define _PLANE_NV12_BUF_CFG_1(pipe)	\
+	_PIPE(pipe, _PLANE_NV12_BUF_CFG_1_A, _PLANE_NV12_BUF_CFG_1_B)
+#define _PLANE_NV12_BUF_CFG_2(pipe)	\
+	_PIPE(pipe, _PLANE_NV12_BUF_CFG_2_A, _PLANE_NV12_BUF_CFG_2_B)
+#define PLANE_NV12_BUF_CFG(pipe, plane)	\
+	_PLANE(plane, _PLANE_NV12_BUF_CFG_1(pipe), _PLANE_NV12_BUF_CFG_2(pipe))
+
 /* SKL new cursor registers */
 #define _CUR_BUF_CFG_A				0x7017c
 #define _CUR_BUF_CFG_B				0x7117c

drivers/gpu/drm/i915/intel_drv.h

@@ -555,7 +555,15 @@ struct intel_crtc {
 struct intel_plane_wm_parameters {
 	uint32_t horiz_pixels;
 	uint32_t vert_pixels;
+	/*
+	 *   For packed pixel formats:
+	 *     bytes_per_pixel - holds bytes per pixel
+	 *   For planar pixel formats:
+	 *     bytes_per_pixel - holds bytes per pixel for uv-plane
+	 *     y_bytes_per_pixel - holds bytes per pixel for y-plane
+	 */
 	uint8_t bytes_per_pixel;
+	uint8_t y_bytes_per_pixel;
 	bool enabled;
 	bool scaled;
 	u64 tiling;

drivers/gpu/drm/i915/intel_pm.c

@@ -2639,8 +2639,18 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 }
 
 static unsigned int
-skl_plane_relative_data_rate(const struct intel_plane_wm_parameters *p)
+skl_plane_relative_data_rate(const struct intel_plane_wm_parameters *p, int y)
 {
+
+	/* for planar format */
+	if (p->y_bytes_per_pixel) {
+		if (y)  /* y-plane data rate */
+			return p->horiz_pixels * p->vert_pixels * p->y_bytes_per_pixel;
+		else    /* uv-plane data rate */
+			return (p->horiz_pixels/2) * (p->vert_pixels/2) * p->bytes_per_pixel;
+	}
+
+	/* for packed formats */
 	return p->horiz_pixels * p->vert_pixels * p->bytes_per_pixel;
 }
 
@@ -2663,7 +2673,10 @@ skl_get_total_relative_data_rate(struct intel_crtc *intel_crtc,
 		if (!p->enabled)
 			continue;
 
-		total_data_rate += skl_plane_relative_data_rate(p);
+		total_data_rate += skl_plane_relative_data_rate(p, 0); /* packed/uv */
+		if (p->y_bytes_per_pixel) {
+			total_data_rate += skl_plane_relative_data_rate(p, 1); /* y-plane */
+		}
 	}
 
 	return total_data_rate;
@@ -2682,6 +2695,7 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc,
 	struct skl_ddb_entry *alloc = &ddb->pipe[pipe];
 	uint16_t alloc_size, start, cursor_blocks;
 	uint16_t minimum[I915_MAX_PLANES];
+	uint16_t y_minimum[I915_MAX_PLANES];
 	unsigned int total_data_rate;
 	int plane;
 
@@ -2710,6 +2724,8 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc,
 
 		minimum[plane] = 8;
 		alloc_size -= minimum[plane];
+		y_minimum[plane] = p->y_bytes_per_pixel ? 8 : 0;
+		alloc_size -= y_minimum[plane];
 	}
 
 	/*
@@ -2723,16 +2739,17 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc,
 	start = alloc->start;
 	for (plane = 0; plane < intel_num_planes(intel_crtc); plane++) {
 		const struct intel_plane_wm_parameters *p;
-		unsigned int data_rate;
-		uint16_t plane_blocks;
+		unsigned int data_rate, y_data_rate;
+		uint16_t plane_blocks, y_plane_blocks = 0;
 
 		p = &params->plane[plane];
 		if (!p->enabled)
 			continue;
 
-		data_rate = skl_plane_relative_data_rate(p);
+		data_rate = skl_plane_relative_data_rate(p, 0);
 
 		/*
+		 * allocation for (packed formats) or (uv-plane part of planar format):
 		 * promote the expression to 64 bits to avoid overflowing, the
 		 * result is < available as data_rate / total_data_rate < 1
 		 */
@@ -2744,6 +2761,22 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc,
 		ddb->plane[pipe][plane].end = start + plane_blocks;
 
 		start += plane_blocks;
+
+		/*
+		 * allocation for y_plane part of planar format:
+		 */
+		if (p->y_bytes_per_pixel) {
+			y_data_rate = skl_plane_relative_data_rate(p, 1);
+			y_plane_blocks = y_minimum[plane];
+			y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
+						total_data_rate);
+
+			ddb->y_plane[pipe][plane].start = start;
+			ddb->y_plane[pipe][plane].end = start + y_plane_blocks;
+
+			start += y_plane_blocks;
+		}
+
 	}
 
 }
@@ -2856,13 +2889,18 @@ static void skl_compute_wm_pipe_parameters(struct drm_crtc *crtc,
 		p->pixel_rate = skl_pipe_pixel_rate(intel_crtc->config);
 
 		fb = crtc->primary->state->fb;
+		/* For planar: Bpp is for uv plane, y_Bpp is for y plane */
 		if (fb) {
 			p->plane[0].enabled = true;
-			p->plane[0].bytes_per_pixel = fb->bits_per_pixel / 8;
+			p->plane[0].bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
+				drm_format_plane_cpp(fb->pixel_format, 1) : fb->bits_per_pixel / 8;
+			p->plane[0].y_bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
+				drm_format_plane_cpp(fb->pixel_format, 0) : 0;
 			p->plane[0].tiling = fb->modifier[0];
 		} else {
 			p->plane[0].enabled = false;
 			p->plane[0].bytes_per_pixel = 0;
+			p->plane[0].y_bytes_per_pixel = 0;
 			p->plane[0].tiling = DRM_FORMAT_MOD_NONE;
 		}
 		p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w;
@@ -2870,6 +2908,7 @@ static void skl_compute_wm_pipe_parameters(struct drm_crtc *crtc,
 		p->plane[0].rotation = crtc->primary->state->rotation;
 
 		fb = crtc->cursor->state->fb;
+		p->cursor.y_bytes_per_pixel = 0;
 		if (fb) {
 			p->cursor.enabled = true;
 			p->cursor.bytes_per_pixel = fb->bits_per_pixel / 8;
@@ -2905,22 +2944,25 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
 	uint32_t res_blocks, res_lines;
 	uint32_t selected_result;
+	uint8_t bytes_per_pixel;
 
 	if (latency == 0 || !p->active || !p_params->enabled)
 		return false;
 
+	bytes_per_pixel = p_params->y_bytes_per_pixel ?
+		p_params->y_bytes_per_pixel :
+		p_params->bytes_per_pixel;
 	method1 = skl_wm_method1(p->pixel_rate,
-				 p_params->bytes_per_pixel,
+				 bytes_per_pixel,
 				 latency);
 	method2 = skl_wm_method2(p->pixel_rate,
 				 p->pipe_htotal,
 				 p_params->horiz_pixels,
-				 p_params->bytes_per_pixel,
+				 bytes_per_pixel,
 				 p_params->tiling,
 				 latency);
 
-	plane_bytes_per_line = p_params->horiz_pixels *
-					p_params->bytes_per_pixel;
+	plane_bytes_per_line = p_params->horiz_pixels * bytes_per_pixel;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (p_params->tiling == I915_FORMAT_MOD_Y_TILED ||
@@ -3137,10 +3179,14 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv,
 				   new->plane_trans[pipe][i]);
 		I915_WRITE(CUR_WM_TRANS(pipe), new->cursor_trans[pipe]);
 
-		for (i = 0; i < intel_num_planes(crtc); i++)
+		for (i = 0; i < intel_num_planes(crtc); i++) {
 			skl_ddb_entry_write(dev_priv,
 					    PLANE_BUF_CFG(pipe, i),
 					    &new->ddb.plane[pipe][i]);
+			skl_ddb_entry_write(dev_priv,
+					    PLANE_NV12_BUF_CFG(pipe, i),
+					    &new->ddb.y_plane[pipe][i]);
+		}
 
 		skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
 				    &new->ddb.cursor[pipe]);
@@ -3298,6 +3344,7 @@ static bool skl_update_pipe_wm(struct drm_crtc *crtc,
 		return false;
 
 	intel_crtc->wm.skl_active = *pipe_wm;
+
 	return true;
 }
 
@@ -3391,8 +3438,16 @@ skl_update_sprite_wm(struct drm_plane *plane, struct drm_crtc *crtc,
 	intel_plane->wm.scaled = scaled;
 	intel_plane->wm.horiz_pixels = sprite_width;
 	intel_plane->wm.vert_pixels = sprite_height;
-	intel_plane->wm.bytes_per_pixel = pixel_size;
 	intel_plane->wm.tiling = DRM_FORMAT_MOD_NONE;
+
+	/* For planar: Bpp is for UV plane, y_Bpp is for Y plane */
+	intel_plane->wm.bytes_per_pixel =
+		(fb && fb->pixel_format == DRM_FORMAT_NV12) ?
+		drm_format_plane_cpp(plane->state->fb->pixel_format, 1) : pixel_size;
+	intel_plane->wm.y_bytes_per_pixel =
+		(fb && fb->pixel_format == DRM_FORMAT_NV12) ?
+		drm_format_plane_cpp(plane->state->fb->pixel_format, 0) : 0;
+
 	/*
 	 * Framebuffer can be NULL on plane disable, but it does not
 	 * matter for watermarks if we assume no tiling in that case.