drm/radeon: fix tiling and command stream checking on evergreen v3

Fix regresson since the introduction of command stream checking on
evergreen (thread referenced below). Issue is cause by ddx allocating
bo with formula width*height*bpp while programming the GPU command
stream with ALIGN(height, 8). In some case (where page alignment does
not hide the extra size bo should be according to height alignment)
the kernel will reject the command stream.

This patch reprogram the command stream to slice - 1 (slice is
a derivative value from height) which avoid rejecting the command
stream while keeping the value of command stream checking from a
security point of view.

This patch also fix wrong computation of layer size for 2D tiled
surface. Which should fix issue when 2D color tiling is enabled.
This dump the radeon KMS_DRIVER_MINOR so userspace can know if
they are on a fixed kernel or not.

https://lkml.org/lkml/2012/6/3/80
https://bugs.freedesktop.org/show_bug.cgi?id=50892
https://bugs.freedesktop.org/show_bug.cgi?id=50857

!!! STABLE need a custom version of this patch for 3.4 !!!

v2: actually bump the minor version and add comment about stable
v3: do compute the height the ddx was trying to use

[airlied: drop left over debug]

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

2 files changed, 47 insertions, 5 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 4e7dd2b..c1655412 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -52,6 +52,7 @@ struct evergreen_cs_track {
 	u32			cb_color_view[12];
 	u32			cb_color_pitch[12];
 	u32			cb_color_slice[12];
+	u32			cb_color_slice_idx[12];
 	u32			cb_color_attrib[12];
 	u32			cb_color_cmask_slice[8];/* unused */
 	u32			cb_color_fmask_slice[8];/* unused */
@@ -127,12 +128,14 @@ static void evergreen_cs_track_init(struct evergreen_cs_track *track)
 		track->cb_color_info[i] = 0;
 		track->cb_color_view[i] = 0xFFFFFFFF;
 		track->cb_color_pitch[i] = 0;
-		track->cb_color_slice[i] = 0;
+		track->cb_color_slice[i] = 0xfffffff;
+		track->cb_color_slice_idx[i] = 0;
 	}
 	track->cb_target_mask = 0xFFFFFFFF;
 	track->cb_shader_mask = 0xFFFFFFFF;
 	track->cb_dirty = true;
 
+	track->db_depth_slice = 0xffffffff;
 	track->db_depth_view = 0xFFFFC000;
 	track->db_depth_size = 0xFFFFFFFF;
 	track->db_depth_control = 0xFFFFFFFF;
@@ -250,10 +253,9 @@ static int evergreen_surface_check_2d(struct radeon_cs_parser *p,
 {
 	struct evergreen_cs_track *track = p->track;
 	unsigned palign, halign, tileb, slice_pt;
+	unsigned mtile_pr, mtile_ps, mtileb;
 
 	tileb = 64 * surf->bpe * surf->nsamples;
-	palign = track->group_size / (8 * surf->bpe * surf->nsamples);
-	palign = MAX(8, palign);
 	slice_pt = 1;
 	if (tileb > surf->tsplit) {
 		slice_pt = tileb / surf->tsplit;
@@ -262,7 +264,10 @@ static int evergreen_surface_check_2d(struct radeon_cs_parser *p,
 	/* macro tile width & height */
 	palign = (8 * surf->bankw * track->npipes) * surf->mtilea;
 	halign = (8 * surf->bankh * surf->nbanks) / surf->mtilea;
-	surf->layer_size = surf->nbx * surf->nby * surf->bpe * slice_pt;
+	mtileb = (palign / 8) * (halign / 8) * tileb;;
+	mtile_pr = surf->nbx / palign;
+	mtile_ps = (mtile_pr * surf->nby) / halign;
+	surf->layer_size = mtile_ps * mtileb * slice_pt;
 	surf->base_align = (palign / 8) * (halign / 8) * tileb;
 	surf->palign = palign;
 	surf->halign = halign;
@@ -434,6 +439,39 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
 
 	offset += surf.layer_size * mslice;
 	if (offset > radeon_bo_size(track->cb_color_bo[id])) {
+		/* old ddx are broken they allocate bo with w*h*bpp but
+		 * program slice with ALIGN(h, 8), catch this and patch
+		 * command stream.
+		 */
+		if (!surf.mode) {
+			volatile u32 *ib = p->ib.ptr;
+			unsigned long tmp, nby, bsize, size, min = 0;
+
+			/* find the height the ddx wants */
+			if (surf.nby > 8) {
+				min = surf.nby - 8;
+			}
+			bsize = radeon_bo_size(track->cb_color_bo[id]);
+			tmp = track->cb_color_bo_offset[id] << 8;
+			for (nby = surf.nby; nby > min; nby--) {
+				size = nby * surf.nbx * surf.bpe * surf.nsamples;
+				if ((tmp + size * mslice) <= bsize) {
+					break;
+				}
+			}
+			if (nby > min) {
+				surf.nby = nby;
+				slice = ((nby * surf.nbx) / 64) - 1;
+				if (!evergreen_surface_check(p, &surf, "cb")) {
+					/* check if this one works */
+					tmp += surf.layer_size * mslice;
+					if (tmp <= bsize) {
+						ib[track->cb_color_slice_idx[id]] = slice;
+						goto old_ddx_ok;
+					}
+				}
+			}
+		}
 		dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, "
 			 "offset %d, max layer %d, bo size %ld, slice %d)\n",
 			 __func__, __LINE__, id, surf.layer_size,
@@ -446,6 +484,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
 			surf.tsplit, surf.mtilea);
 		return -EINVAL;
 	}
+old_ddx_ok:
 
 	return 0;
 }
@@ -1532,6 +1571,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR7_SLICE:
 		tmp = (reg - CB_COLOR0_SLICE) / 0x3c;
 		track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+		track->cb_color_slice_idx[tmp] = idx;
 		track->cb_dirty = true;
 		break;
 	case CB_COLOR8_SLICE:
@@ -1540,6 +1580,7 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR11_SLICE:
 		tmp = ((reg - CB_COLOR8_SLICE) / 0x1c) + 8;
 		track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+		track->cb_color_slice_idx[tmp] = idx;
 		track->cb_dirty = true;
 		break;
 	case CB_COLOR0_ATTRIB:
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f0bb2b5..03e5f5d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -57,9 +57,10 @@
  *   2.13.0 - virtual memory support, streamout
  *   2.14.0 - add evergreen tiling informations
  *   2.15.0 - add max_pipes query
+ *   2.16.0 - fix evergreen 2D tiled surface calculation
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	15
+#define KMS_DRIVER_MINOR	16
 #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);