drm/radeon: allow CMASK and FMASK in the CS checker on r600-r700

MSAA is impossible without them.
Signed-off-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>

drivers/gpu/drm/radeon/r600_cs.c

@@ -47,13 +47,17 @@ struct r600_cs_track {
 	u32			npipes;
 	/* value we track */
 	u32			sq_config;
+	u32			log_nsamples;
 	u32			nsamples;
 	u32			cb_color_base_last[8];
 	struct radeon_bo	*cb_color_bo[8];
 	u64			cb_color_bo_mc[8];
-	u32			cb_color_bo_offset[8];
-	struct radeon_bo	*cb_color_frag_bo[8]; /* unused */
-	struct radeon_bo	*cb_color_tile_bo[8]; /* unused */
+	u64			cb_color_bo_offset[8];
+	struct radeon_bo	*cb_color_frag_bo[8];
+	u64			cb_color_frag_offset[8];
+	struct radeon_bo	*cb_color_tile_bo[8];
+	u64			cb_color_tile_offset[8];
+	u32			cb_color_mask[8];
 	u32			cb_color_info[8];
 	u32			cb_color_view[8];
 	u32			cb_color_size_idx[8]; /* unused */
@@ -349,10 +353,6 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	unsigned array_mode;
 	u32 format;
 
-	if (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
-		dev_warn(p->dev, "FMASK or CMASK buffer are not supported by this kernel\n");
-		return -EINVAL;
-	}
 	size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i];
 	format = G_0280A0_FORMAT(track->cb_color_info[i]);
 	if (!r600_fmt_is_valid_color(format)) {
@@ -441,7 +441,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 			 * broken userspace.
 			 */
 		} else {
-			dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big (%d %d) (%d %d %d)\n",
+			dev_warn(p->dev, "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n",
 				 __func__, i, array_mode,
 				 track->cb_color_bo_offset[i], tmp,
 				 radeon_bo_size(track->cb_color_bo[i]),
@@ -458,6 +458,51 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	tmp = S_028060_PITCH_TILE_MAX((pitch / 8) - 1) |
 		S_028060_SLICE_TILE_MAX(slice_tile_max - 1);
 	ib[track->cb_color_size_idx[i]] = tmp;
+
+	/* FMASK/CMASK */
+	switch (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
+	case V_0280A0_TILE_DISABLE:
+		break;
+	case V_0280A0_FRAG_ENABLE:
+		if (track->nsamples > 1) {
+			uint32_t tile_max = G_028100_FMASK_TILE_MAX(track->cb_color_mask[i]);
+			/* the tile size is 8x8, but the size is in units of bits.
+			 * for bytes, do just * 8. */
+			uint32_t bytes = track->nsamples * track->log_nsamples * 8 * (tile_max + 1);
+
+			if (bytes + track->cb_color_frag_offset[i] >
+			    radeon_bo_size(track->cb_color_frag_bo[i])) {
+				dev_warn(p->dev, "%s FMASK_TILE_MAX too large "
+					 "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+					 __func__, tile_max, bytes,
+					 track->cb_color_frag_offset[i],
+					 radeon_bo_size(track->cb_color_frag_bo[i]));
+				return -EINVAL;
+			}
+		}
+		/* fall through */
+	case V_0280A0_CLEAR_ENABLE:
+	{
+		uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]);
+		/* One block = 128x128 pixels, one 8x8 tile has 4 bits..
+		 * (128*128) / (8*8) / 2 = 128 bytes per block. */
+		uint32_t bytes = (block_max + 1) * 128;
+
+		if (bytes + track->cb_color_tile_offset[i] >
+		    radeon_bo_size(track->cb_color_tile_bo[i])) {
+			dev_warn(p->dev, "%s CMASK_BLOCK_MAX too large "
+				 "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+				 __func__, block_max, bytes,
+				 track->cb_color_tile_offset[i],
+				 radeon_bo_size(track->cb_color_tile_bo[i]));
+			return -EINVAL;
+		}
+		break;
+	}
+	default:
+		dev_warn(p->dev, "%s invalid tile mode\n", __func__);
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -1231,6 +1276,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case R_028C04_PA_SC_AA_CONFIG:
 		tmp = G_028C04_MSAA_NUM_SAMPLES(radeon_get_ib_value(p, idx));
+		track->log_nsamples = tmp;
 		track->nsamples = 1 << tmp;
 		track->cb_dirty = true;
 		break;
@@ -1312,16 +1358,21 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_frag_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_frag_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_frag_bo[tmp] = reloc->robj;
+			track->cb_color_frag_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case R_0280C0_CB_COLOR0_TILE:
@@ -1338,16 +1389,35 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_tile_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_tile_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_tile_bo[tmp] = reloc->robj;
+			track->cb_color_tile_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
+		}
+		break;
+	case R_028100_CB_COLOR0_MASK:
+	case R_028104_CB_COLOR1_MASK:
+	case R_028108_CB_COLOR2_MASK:
+	case R_02810C_CB_COLOR3_MASK:
+	case R_028110_CB_COLOR4_MASK:
+	case R_028114_CB_COLOR5_MASK:
+	case R_028118_CB_COLOR6_MASK:
+	case R_02811C_CB_COLOR7_MASK:
+		tmp = (reg - R_028100_CB_COLOR0_MASK) / 4;
+		track->cb_color_mask[tmp] = ib[idx];
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case CB_COLOR0_BASE:

drivers/gpu/drm/radeon/r600d.h

@@ -92,6 +92,20 @@
 #define R_028094_CB_COLOR5_VIEW                      0x028094
 #define R_028098_CB_COLOR6_VIEW                      0x028098
 #define R_02809C_CB_COLOR7_VIEW                      0x02809C
+#define R_028100_CB_COLOR0_MASK                      0x028100
+#define   S_028100_CMASK_BLOCK_MAX(x)                  (((x) & 0xFFF) << 0)
+#define   G_028100_CMASK_BLOCK_MAX(x)                  (((x) >> 0) & 0xFFF)
+#define   C_028100_CMASK_BLOCK_MAX                     0xFFFFF000
+#define   S_028100_FMASK_TILE_MAX(x)                   (((x) & 0xFFFFF) << 12)
+#define   G_028100_FMASK_TILE_MAX(x)                   (((x) >> 12) & 0xFFFFF)
+#define   C_028100_FMASK_TILE_MAX                      0x00000FFF
+#define R_028104_CB_COLOR1_MASK                      0x028104
+#define R_028108_CB_COLOR2_MASK                      0x028108
+#define R_02810C_CB_COLOR3_MASK                      0x02810C
+#define R_028110_CB_COLOR4_MASK                      0x028110
+#define R_028114_CB_COLOR5_MASK                      0x028114
+#define R_028118_CB_COLOR6_MASK                      0x028118
+#define R_02811C_CB_COLOR7_MASK                      0x02811C
 #define CB_COLOR0_INFO                                  0x280a0
 #	define CB_FORMAT(x)				((x) << 2)
 #       define CB_ARRAY_MODE(x)                         ((x) << 8)
@@ -1400,6 +1414,9 @@
 #define   S_0280A0_TILE_MODE(x)                        (((x) & 0x3) << 18)
 #define   G_0280A0_TILE_MODE(x)                        (((x) >> 18) & 0x3)
 #define   C_0280A0_TILE_MODE                           0xFFF3FFFF
+#define     V_0280A0_TILE_DISABLE			0
+#define     V_0280A0_CLEAR_ENABLE			1
+#define     V_0280A0_FRAG_ENABLE			2
 #define   S_0280A0_BLEND_CLAMP(x)                      (((x) & 0x1) << 20)
 #define   G_0280A0_BLEND_CLAMP(x)                      (((x) >> 20) & 0x1)
 #define   C_0280A0_BLEND_CLAMP                         0xFFEFFFFF

drivers/gpu/drm/radeon/radeon_drv.c

@@ -62,9 +62,10 @@
  *   2.18.0 - r600-eg: allow "invalid" DB formats
  *   2.19.0 - r600-eg: MSAA textures
  *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
+ *   2.21.0 - r600-r700: FMASK and CMASK
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	20
+#define KMS_DRIVER_MINOR	21
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);

drivers/gpu/drm/radeon/reg_srcs/r600

@@ -744,14 +744,6 @@ r600 0x9400
 0x00028C38 CB_CLRCMP_DST
 0x00028C3C CB_CLRCMP_MSK
 0x00028C34 CB_CLRCMP_SRC
-0x00028100 CB_COLOR0_MASK
-0x00028104 CB_COLOR1_MASK
-0x00028108 CB_COLOR2_MASK
-0x0002810C CB_COLOR3_MASK
-0x00028110 CB_COLOR4_MASK
-0x00028114 CB_COLOR5_MASK
-0x00028118 CB_COLOR6_MASK
-0x0002811C CB_COLOR7_MASK
 0x00028808 CB_COLOR_CONTROL
 0x0002842C CB_FOG_BLUE
 0x00028428 CB_FOG_GREEN