drm/komeda: Add format support for Y0L2, P010, YUV420_8/10BIT

- Y0L2 and P010 are block (tiled) format, Update the kemeda logic to
compatible with such block format.
- Since DRM introduced a general block information to drm_format_info,
  the format_caps->tiled_size no long needed, delete it.
- Build some fb utils functions for code sharing.
Signed-off-by: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>

drivers/gpu/drm/arm/display/include/malidp_io.h

@@ -21,6 +21,13 @@ malidp_write32(u32 __iomem *base, u32 offset, u32 v)
 	writel(v, (base + (offset >> 2)));
 }
 
+static inline void
+malidp_write64(u32 __iomem *base, u32 offset, u64 v)
+{
+	writel(lower_32_bits(v), (base + (offset >> 2)));
+	writel(upper_32_bits(v), (base + (offset >> 2) + 1));
+}
+
 static inline void
 malidp_write32_mask(u32 __iomem *base, u32 offset, u32 m, u32 v)
 {

drivers/gpu/drm/arm/display/komeda/d71/d71_component.c

@@ -163,6 +163,30 @@ static inline u32 to_d71_input_id(struct komeda_component_output *output)
 	return comp ? (comp->hw_id + output->output_port) : 0;
 }
 
+static void d71_layer_update_fb(struct komeda_component *c,
+				struct komeda_fb *kfb,
+				dma_addr_t *addr)
+{
+	struct drm_framebuffer *fb = &kfb->base;
+	const struct drm_format_info *info = fb->format;
+	u32 __iomem *reg = c->reg;
+	int block_h;
+
+	if (info->num_planes > 2)
+		malidp_write64(reg, BLK_P2_PTR_LOW, addr[2]);
+
+	if (info->num_planes > 1) {
+		block_h = drm_format_info_block_height(info, 1);
+		malidp_write32(reg, BLK_P1_STRIDE, fb->pitches[1] * block_h);
+		malidp_write64(reg, BLK_P1_PTR_LOW, addr[1]);
+	}
+
+	block_h = drm_format_info_block_height(info, 0);
+	malidp_write32(reg, BLK_P0_STRIDE, fb->pitches[0] * block_h);
+	malidp_write64(reg, BLK_P0_PTR_LOW, addr[0]);
+	malidp_write32(reg, LAYER_FMT, kfb->format_caps->hw_id);
+}
+
 static void d71_layer_disable(struct komeda_component *c)
 {
 	malidp_write32_mask(c->reg, BLK_CONTROL, L_EN, 0);
@@ -178,22 +202,8 @@ static void d71_layer_update(struct komeda_component *c,
 	u32 __iomem *reg = c->reg;
 	u32 ctrl_mask = L_EN | L_ROT(L_ROT_R270) | L_HFLIP | L_VFLIP | L_TBU_EN;
 	u32 ctrl = L_EN | to_rot_ctrl(st->rot);
-	int i;
 
-	for (i = 0; i < fb->format->num_planes; i++) {
-		malidp_write32(reg,
-			       BLK_P0_PTR_LOW + i * LAYER_PER_PLANE_REGS * 4,
-			       lower_32_bits(st->addr[i]));
-		malidp_write32(reg,
-			       BLK_P0_PTR_HIGH + i * LAYER_PER_PLANE_REGS * 4,
-			       upper_32_bits(st->addr[i]));
-		if (i >= 2)
-			break;
-
-		malidp_write32(reg,
-			       BLK_P0_STRIDE + i * LAYER_PER_PLANE_REGS * 4,
-			       fb->pitches[i] & 0xFFFF);
-	}
+	d71_layer_update_fb(c, kfb, st->addr);
 
 	malidp_write32(reg, AD_CONTROL, to_ad_ctrl(fb->modifier));
 	if (fb->modifier) {
@@ -247,7 +257,6 @@ static void d71_layer_update(struct komeda_component *c,
 					plane_st->color_range));
 	}
 
-	malidp_write32(reg, LAYER_FMT, kfb->format_caps->hw_id);
 	malidp_write32(reg, BLK_IN_SIZE, HV_SIZE(st->hsize, st->vsize));
 
 	if (kfb->is_va)
@@ -369,26 +378,15 @@ static void d71_wb_layer_update(struct komeda_component *c,
 {
 	struct komeda_layer_state *st = to_layer_st(state);
 	struct drm_connector_state *conn_st = state->wb_conn->state;
-	struct drm_framebuffer *fb = conn_st->writeback_job->fb;
-	struct komeda_fb *kfb = to_kfb(fb);
-	u32 __iomem *reg = c->reg;
+	struct komeda_fb *kfb = to_kfb(conn_st->writeback_job->fb);
 	u32 ctrl = L_EN | LW_OFM, mask = L_EN | LW_OFM | LW_TBU_EN;
-	int i;
+	u32 __iomem *reg = c->reg;
 
-	for (i = 0; i < fb->format->num_planes; i++) {
-		malidp_write32(reg + i * LAYER_PER_PLANE_REGS, BLK_P0_PTR_LOW,
-			       lower_32_bits(st->addr[i]));
-		malidp_write32(reg + i * LAYER_PER_PLANE_REGS, BLK_P0_PTR_HIGH,
-			       upper_32_bits(st->addr[i]));
-
-		malidp_write32(reg + i * LAYER_PER_PLANE_REGS, BLK_P0_STRIDE,
-			       fb->pitches[i] & 0xFFFF);
-	}
+	d71_layer_update_fb(c, kfb, st->addr);
 
 	if (kfb->is_va)
 		ctrl |= LW_TBU_EN;
 
-	malidp_write32(reg, LAYER_FMT, kfb->format_caps->hw_id);
 	malidp_write32(reg, BLK_IN_SIZE, HV_SIZE(st->hsize, st->vsize));
 	malidp_write32(reg, BLK_INPUT_ID0, to_d71_input_id(&state->inputs[0]));
 	malidp_write32_mask(reg, BLK_CONTROL, mask, ctrl);

drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c

@@ -447,51 +447,47 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 #define AFB_TH_SC_YTR_BS AFBC(_TILED | _SC | _SPARSE | _YTR | _SPLIT)
 
 static struct komeda_format_caps d71_format_caps_table[] = {
-	/*   HW_ID    |        fourcc        | tile_sz |   layer_types |   rots    | afbc_layouts | afbc_features */
+	/*   HW_ID    |        fourcc         |   layer_types |   rots    | afbc_layouts | afbc_features */
 	/* ABGR_2101010*/
-	{__HW_ID(0, 0),	DRM_FORMAT_ARGB2101010,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(0, 1),	DRM_FORMAT_ABGR2101010,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(0, 1),	DRM_FORMAT_ABGR2101010,	1,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
-	{__HW_ID(0, 2),	DRM_FORMAT_RGBA1010102,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(0, 3),	DRM_FORMAT_BGRA1010102,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(0, 0),	DRM_FORMAT_ARGB2101010,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(0, 1),	DRM_FORMAT_ABGR2101010,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(0, 1),	DRM_FORMAT_ABGR2101010,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
+	{__HW_ID(0, 2),	DRM_FORMAT_RGBA1010102,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(0, 3),	DRM_FORMAT_BGRA1010102,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
 	/* ABGR_8888*/
-	{__HW_ID(1, 0),	DRM_FORMAT_ARGB8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(1, 1),	DRM_FORMAT_ABGR8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(1, 1),	DRM_FORMAT_ABGR8888,	1,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
-	{__HW_ID(1, 2),	DRM_FORMAT_RGBA8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(1, 3),	DRM_FORMAT_BGRA8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(1, 0),	DRM_FORMAT_ARGB8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(1, 1),	DRM_FORMAT_ABGR8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(1, 1),	DRM_FORMAT_ABGR8888,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
+	{__HW_ID(1, 2),	DRM_FORMAT_RGBA8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(1, 3),	DRM_FORMAT_BGRA8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
 	/* XBGB_8888 */
-	{__HW_ID(2, 0),	DRM_FORMAT_XRGB8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(2, 1),	DRM_FORMAT_XBGR8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(2, 2),	DRM_FORMAT_RGBX8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
-	{__HW_ID(2, 3),	DRM_FORMAT_BGRX8888,	1,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(2, 0),	DRM_FORMAT_XRGB8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(2, 1),	DRM_FORMAT_XBGR8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(2, 2),	DRM_FORMAT_RGBX8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
+	{__HW_ID(2, 3),	DRM_FORMAT_BGRX8888,	RICH_SIMPLE_WB,	Flip_H_V,		0, 0},
 	/* BGR_888 */ /* none-afbc RGB888 doesn't support rotation and flip */
-	{__HW_ID(3, 0),	DRM_FORMAT_RGB888,	1,	RICH_SIMPLE_WB,	Rot_0,			0, 0},
-	{__HW_ID(3, 1),	DRM_FORMAT_BGR888,	1,	RICH_SIMPLE_WB,	Rot_0,			0, 0},
-	{__HW_ID(3, 1),	DRM_FORMAT_BGR888,	1,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
+	{__HW_ID(3, 0),	DRM_FORMAT_RGB888,	RICH_SIMPLE_WB,	Rot_0,			0, 0},
+	{__HW_ID(3, 1),	DRM_FORMAT_BGR888,	RICH_SIMPLE_WB,	Rot_0,			0, 0},
+	{__HW_ID(3, 1),	DRM_FORMAT_BGR888,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR_BS}, /* afbc */
 	/* BGR 16bpp */
-	{__HW_ID(4, 0),	DRM_FORMAT_RGBA5551,	1,	RICH_SIMPLE,	Flip_H_V,		0, 0},
-	{__HW_ID(4, 1),	DRM_FORMAT_ABGR1555,	1,	RICH_SIMPLE,	Flip_H_V,		0, 0},
-	{__HW_ID(4, 1),	DRM_FORMAT_ABGR1555,	1,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR}, /* afbc */
-	{__HW_ID(4, 2),	DRM_FORMAT_RGB565,	1,	RICH_SIMPLE,	Flip_H_V,		0, 0},
-	{__HW_ID(4, 3),	DRM_FORMAT_BGR565,	1,	RICH_SIMPLE,	Flip_H_V,		0, 0},
-	{__HW_ID(4, 3),	DRM_FORMAT_BGR565,	1,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR}, /* afbc */
-	{__HW_ID(4, 4), DRM_FORMAT_R8,		1,	SIMPLE,		Rot_0,			0, 0},
+	{__HW_ID(4, 0),	DRM_FORMAT_RGBA5551,	RICH_SIMPLE,	Flip_H_V,		0, 0},
+	{__HW_ID(4, 1),	DRM_FORMAT_ABGR1555,	RICH_SIMPLE,	Flip_H_V,		0, 0},
+	{__HW_ID(4, 1),	DRM_FORMAT_ABGR1555,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR}, /* afbc */
+	{__HW_ID(4, 2),	DRM_FORMAT_RGB565,	RICH_SIMPLE,	Flip_H_V,		0, 0},
+	{__HW_ID(4, 3),	DRM_FORMAT_BGR565,	RICH_SIMPLE,	Flip_H_V,		0, 0},
+	{__HW_ID(4, 3),	DRM_FORMAT_BGR565,	RICH_SIMPLE,	Rot_ALL_H_V,	LYT_NM_WB, AFB_TH_SC_YTR}, /* afbc */
+	{__HW_ID(4, 4), DRM_FORMAT_R8,		SIMPLE,		Rot_0,			0, 0},
 	/* YUV 444/422/420 8bit  */
-	{__HW_ID(5, 0),	0 /*XYUV8888*/,		1,	0,		0,			0, 0},
-	/* XYUV unsupported*/
-	{__HW_ID(5, 1),	DRM_FORMAT_YUYV,	1,	RICH,		Rot_ALL_H_V,	LYT_NM, AFB_TH}, /* afbc */
-	{__HW_ID(5, 2),	DRM_FORMAT_YUYV,	1,	RICH,		Flip_H_V,		0, 0},
-	{__HW_ID(5, 3),	DRM_FORMAT_UYVY,	1,	RICH,		Flip_H_V,		0, 0},
-	{__HW_ID(5, 4),	0, /*X0L0 */		2,		0,			0, 0}, /* Y0L0 unsupported */
-	{__HW_ID(5, 6),	DRM_FORMAT_NV12,	1,	RICH,		Flip_H_V,		0, 0},
-	{__HW_ID(5, 6),	0/*DRM_FORMAT_YUV420_8BIT*/,	1,	RICH,	Rot_ALL_H_V,	LYT_NM, AFB_TH}, /* afbc */
-	{__HW_ID(5, 7),	DRM_FORMAT_YUV420,	1,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(5, 1),	DRM_FORMAT_YUYV,	RICH,		Rot_ALL_H_V,	LYT_NM, AFB_TH}, /* afbc */
+	{__HW_ID(5, 2),	DRM_FORMAT_YUYV,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(5, 3),	DRM_FORMAT_UYVY,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(5, 6),	DRM_FORMAT_NV12,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(5, 6),	DRM_FORMAT_YUV420_8BIT,	RICH,		Rot_ALL_H_V,	LYT_NM, AFB_TH}, /* afbc */
+	{__HW_ID(5, 7),	DRM_FORMAT_YUV420,	RICH,		Flip_H_V,		0, 0},
 	/* YUV 10bit*/
-	{__HW_ID(6, 0),	0,/*XVYU2101010*/	1,	0,		0,			0, 0},/* VYV30 unsupported */
-	{__HW_ID(6, 6),	0/*DRM_FORMAT_X0L2*/,	2,	RICH,		Flip_H_V,		0, 0},
-	{__HW_ID(6, 7),	0/*DRM_FORMAT_P010*/,	1,	RICH,		Flip_H_V,		0, 0},
-	{__HW_ID(6, 7),	0/*DRM_FORMAT_YUV420_10BIT*/, 1,	RICH,	Rot_ALL_H_V,	LYT_NM, AFB_TH},
+	{__HW_ID(6, 6),	DRM_FORMAT_X0L2,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(6, 7),	DRM_FORMAT_P010,	RICH,		Flip_H_V,		0, 0},
+	{__HW_ID(6, 7),	DRM_FORMAT_YUV420_10BIT, RICH,		Rot_ALL_H_V,	LYT_NM, AFB_TH},
 };
 
 static bool d71_format_mod_supported(const struct komeda_format_caps *caps,

drivers/gpu/drm/arm/display/komeda/komeda_format_caps.h

@@ -50,7 +50,6 @@
  *
  * @hw_id: hw format id, hw specific value.
  * @fourcc: drm fourcc format.
- * @tile_size: format tiled size, used by ARM format X0L0/X0L2
  * @supported_layer_types: indicate which layer supports this format
  * @supported_rots: allowed rotations for this format
  * @supported_afbc_layouts: supported afbc layerout
@@ -59,7 +58,6 @@
 struct komeda_format_caps {
 	u32 hw_id;
 	u32 fourcc;
-	u32 tile_size;
 	u32 supported_layer_types;
 	u32 supported_rots;
 	u32 supported_afbc_layouts;

drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c

@@ -112,46 +112,35 @@ komeda_fb_none_afbc_size_check(struct komeda_dev *mdev, struct komeda_fb *kfb,
 			       const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct drm_framebuffer *fb = &kfb->base;
+	const struct drm_format_info *info = fb->format;
 	struct drm_gem_object *obj;
-	u32 min_size = 0;
-	u32 i;
+	u32 i, min_size, block_h;
 
-	for (i = 0; i < fb->format->num_planes; i++) {
+	if (komeda_fb_check_src_coords(kfb, 0, 0, fb->width, fb->height))
+		return -EINVAL;
+
+	for (i = 0; i < info->num_planes; i++) {
 		obj = drm_gem_object_lookup(file, mode_cmd->handles[i]);
 		if (!obj) {
 			DRM_DEBUG_KMS("Failed to lookup GEM object\n");
-			fb->obj[i] = NULL;
-
 			return -ENOENT;
 		}
+		fb->obj[i] = obj;
 
-		kfb->aligned_w = fb->width / (i ? fb->format->hsub : 1);
-		kfb->aligned_h = fb->height / (i ? fb->format->vsub : 1);
-
-		if (fb->pitches[i] % mdev->chip.bus_width) {
+		block_h = drm_format_info_block_height(info, i);
+		if ((fb->pitches[i] * block_h) % mdev->chip.bus_width) {
 			DRM_DEBUG_KMS("Pitch[%d]: 0x%x doesn't align to 0x%x\n",
 				      i, fb->pitches[i], mdev->chip.bus_width);
-			drm_gem_object_put_unlocked(obj);
-			fb->obj[i] = NULL;
-
 			return -EINVAL;
 		}
 
-		min_size = ((kfb->aligned_h / kfb->format_caps->tile_size - 1)
-			    * fb->pitches[i])
-			    + (kfb->aligned_w * fb->format->cpp[i]
-			       * kfb->format_caps->tile_size)
-			    + fb->offsets[i];
-
+		min_size = komeda_fb_get_pixel_addr(kfb, 0, fb->height, i)
+			 - to_drm_gem_cma_obj(obj)->paddr;
 		if (obj->size < min_size) {
-			DRM_DEBUG_KMS("Fail to check none afbc fb size.\n");
-			drm_gem_object_put_unlocked(obj);
-			fb->obj[i] = NULL;
-
+			DRM_DEBUG_KMS("The fb->obj[%d] size: %ld lower than the minimum requirement: %d.\n",
+				      i, obj->size, min_size);
 			return -EINVAL;
 		}
-
-		fb->obj[i] = obj;
 	}
 
 	if (fb->format->num_planes == 3) {
@@ -219,6 +208,8 @@ int komeda_fb_check_src_coords(const struct komeda_fb *kfb,
 {
 	const struct drm_framebuffer *fb = &kfb->base;
 	const struct drm_format_info *info = fb->format;
+	u32 block_w = drm_format_info_block_width(fb->format, 0);
+	u32 block_h = drm_format_info_block_height(fb->format, 0);
 
 	if ((src_x + src_w > fb->width) || (src_y + src_h > fb->height)) {
 		DRM_DEBUG_ATOMIC("Invalid source coordinate.\n");
@@ -232,6 +223,13 @@ int komeda_fb_check_src_coords(const struct komeda_fb *kfb,
 		return -EINVAL;
 	}
 
+	if ((src_x % block_w) || (src_w % block_w) ||
+	    (src_y % block_h) || (src_h % block_h)) {
+		DRM_DEBUG_ATOMIC("x:%d, y:%d, w:%d, h:%d should be multiple of block_w/h for format: %x.\n",
+				 src_x, src_y, src_w, src_h, info->format);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -240,7 +238,7 @@ komeda_fb_get_pixel_addr(struct komeda_fb *kfb, int x, int y, int plane)
 {
 	struct drm_framebuffer *fb = &kfb->base;
 	const struct drm_gem_cma_object *obj;
-	u32 plane_x, plane_y, cpp, pitch, offset;
+	u32 offset, plane_x, plane_y, block_w, block_sz;
 
 	if (plane >= fb->format->num_planes) {
 		DRM_DEBUG_KMS("Out of max plane num.\n");
@@ -251,12 +249,13 @@ komeda_fb_get_pixel_addr(struct komeda_fb *kfb, int x, int y, int plane)
 
 	offset = fb->offsets[plane];
 	if (!fb->modifier) {
+		block_w = drm_format_info_block_width(fb->format, plane);
+		block_sz = fb->format->char_per_block[plane];
 		plane_x = x / (plane ? fb->format->hsub : 1);
 		plane_y = y / (plane ? fb->format->vsub : 1);
-		cpp = fb->format->cpp[plane];
-		pitch = fb->pitches[plane];
-		offset += plane_x * cpp *  kfb->format_caps->tile_size +
-				(plane_y * pitch) / kfb->format_caps->tile_size;
+
+		offset += (plane_x / block_w) * block_sz
+			+ plane_y * fb->pitches[plane];
 	}
 
 	return obj->paddr + offset;