Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes from Dave Airlie:
 "As per your -rc2 announce, this is small and urgent only,

  The radeon one is for a regression in 3.4 so we need this one in your
  tree so we can send the stable one out, code in 3.4 broke some old
  userspaces.  The max props increase fixes spew being seen on a few
  machines.  And a ttm regression to fix some accounting issues that
  affect vmwgfx."

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/ttm: Fix buffer object metadata accounting regression v2
  drm: increase DRM_OBJECT_MAX_PROPERTY to 24
  drm/radeon: fix tiling and command stream checking on evergreen v3

3 files changed, 50 insertions, 15 deletions

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 4e7dd2b4843d..c16554122ccd 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 f0bb2b543b13..03e5f5df40f1 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);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b67cfcaa661f..36f4b28c1b90 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1204,6 +1204,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 			(*destroy)(bo);
 		else
 			kfree(bo);
+		ttm_mem_global_free(mem_glob, acc_size);
 		return -EINVAL;
 	}
 	bo->destroy = destroy;
@@ -1307,22 +1308,14 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 			struct ttm_buffer_object **p_bo)
 {
 	struct ttm_buffer_object *bo;
-	struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
 	size_t acc_size;
 	int ret;
 
-	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
-	ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
-	if (unlikely(ret != 0))
-		return ret;
-
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-
-	if (unlikely(bo == NULL)) {
-		ttm_mem_global_free(mem_glob, acc_size);
+	if (unlikely(bo == NULL))
 		return -ENOMEM;
-	}
 
+	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
 				buffer_start, interruptible,
 			  persistent_swap_storage, acc_size, NULL, NULL);