drm/radeon/kms: add a CS ioctl flag not to rewrite tiling flags in the CS

This adds a new optional chunk to the CS ioctl that specifies optional flags
to the CS parser. Why this is useful is explained below. Note that some regs
no longer need the NOP relocation packet if this feature is enabled.
Tested on r300g and r600g with this flag disabled and enabled.

Assume there are two contexts sharing the same mipmapped tiled texture.
One context wants to render into the first mipmap and the other one
wants to render into the last mipmap. As you probably know, the hardware
has a MACRO_SWITCH feature, which turns off macro tiling for small mipmaps,
but that only applies to samplers.
(at least on r300-r500, though later hardware likely behaves the same)

So we want to just re-set the tiling flags before rendering (writing
packets), right? ... No. The contexts run in parallel, so they may
set the tiling flags simultaneously and then fire their command streams
also simultaneously. The last one setting the flags wins, the other one
loses.

Another problem is when one context wants to render into the first and
the last mipmap in one CS. Impossible. It must flush before changing
tiling flags and do the rendering into the smaller mipmaps in another CS.

Yet another problem is that writing copy_blit in userspace would be a mess
involving re-setting tiling flags to please the kernel, and causing races
with other contexts at the same time.

The only way out of this is to send tiling flags with each CS, ideally
with each relocation. But we already do that through the registers.
So let's just use what we have in the registers.

Signed-off-by: Marek Olšák <maraeo@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 50 insertions, 42 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7fdfa8e..38e1bda 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -480,21 +480,23 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		}
 		break;
 	case DB_Z_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		track->db_z_info = radeon_get_ib_value(p, idx);
-		ib[idx] &= ~Z_ARRAY_MODE(0xf);
-		track->db_z_info &= ~Z_ARRAY_MODE(0xf);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			ib[idx] &= ~Z_ARRAY_MODE(0xf);
+			track->db_z_info &= ~Z_ARRAY_MODE(0xf);
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else {
+				ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case DB_STENCIL_INFO:
@@ -607,40 +609,44 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR5_INFO:
 	case CB_COLOR6_INFO:
 	case CB_COLOR7_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = (reg - CB_COLOR0_INFO) / 0x3c;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case CB_COLOR8_INFO:
 	case CB_COLOR9_INFO:
 	case CB_COLOR10_INFO:
 	case CB_COLOR11_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+				ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+			}
 		}
 		break;
 	case CB_COLOR0_PITCH:
@@ -1311,10 +1317,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 					return -EINVAL;
 				}
 				ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				if (!p->keep_tiling_flags) {
+					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+						ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
+					else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+						ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				}
 				texture = reloc->robj;
 				/* tex mip base */
 				r = evergreen_cs_packet_next_reloc(p, &reloc);