Merge branch 'drm-ttm-unmappable' into drm-core-next

* drm-ttm-unmappable:
  drm/radeon/kms: enable use of unmappable VRAM V2
  drm/ttm: remove io_ field from TTM V6
  drm/vmwgfx: add support for new TTM fault callback V5
  drm/nouveau/kms: add support for new TTM fault callback V5
  drm/radeon/kms: add support for new fault callback V7
  drm/ttm: ttm_fault callback to allow driver to handle bo placement V6
  drm/ttm: split no_wait argument in 2 GPU or reserve wait

Conflicts:
	drivers/gpu/drm/nouveau/nouveau_bo.c

18 files changed, 397 insertions, 269 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 957d1762984..fb164efada3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -225,7 +225,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t memtype)
 
 	nouveau_bo_placement_set(nvbo, memtype, 0);
 
-	ret = ttm_bo_validate(bo, &nvbo->placement, false, false);
+	ret = ttm_bo_validate(bo, &nvbo->placement, false, false, false);
 	if (ret == 0) {
 		switch (bo->mem.mem_type) {
 		case TTM_PL_VRAM:
@@ -261,7 +261,7 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo)
 
 	nouveau_bo_placement_set(nvbo, bo->mem.placement, 0);
 
-	ret = ttm_bo_validate(bo, &nvbo->placement, false, false);
+	ret = ttm_bo_validate(bo, &nvbo->placement, false, false, false);
 	if (ret == 0) {
 		switch (bo->mem.mem_type) {
 		case TTM_PL_VRAM:
@@ -391,25 +391,16 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		break;
 	case TTM_PL_VRAM:
 		man->flags = TTM_MEMTYPE_FLAG_FIXED |
-			     TTM_MEMTYPE_FLAG_MAPPABLE |
-			     TTM_MEMTYPE_FLAG_NEEDS_IOREMAP;
+			     TTM_MEMTYPE_FLAG_MAPPABLE;
 		man->available_caching = TTM_PL_FLAG_UNCACHED |
 					 TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
-
-		man->io_addr = NULL;
-		man->io_offset = drm_get_resource_start(dev, 1);
-		man->io_size = drm_get_resource_len(dev, 1);
-		if (man->io_size > dev_priv->vram_size)
-			man->io_size = dev_priv->vram_size;
-
 		man->gpu_offset = dev_priv->vm_vram_base;
 		break;
 	case TTM_PL_TT:
 		switch (dev_priv->gart_info.type) {
 		case NOUVEAU_GART_AGP:
-			man->flags = TTM_MEMTYPE_FLAG_MAPPABLE |
-				     TTM_MEMTYPE_FLAG_NEEDS_IOREMAP;
+			man->flags = TTM_MEMTYPE_FLAG_MAPPABLE;
 			man->available_caching = TTM_PL_FLAG_UNCACHED;
 			man->default_caching = TTM_PL_FLAG_UNCACHED;
 			break;
@@ -424,10 +415,6 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 				 dev_priv->gart_info.type);
 			return -EINVAL;
 		}
-
-		man->io_offset  = dev_priv->gart_info.aper_base;
-		man->io_size    = dev_priv->gart_info.aper_size;
-		man->io_addr   = NULL;
 		man->gpu_offset = dev_priv->vm_gart_base;
 		break;
 	default:
@@ -462,7 +449,8 @@ nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 
 static int
 nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan,
-			      struct nouveau_bo *nvbo, bool evict, bool no_wait,
+			      struct nouveau_bo *nvbo, bool evict,
+			      bool no_wait_reserve, bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_fence *fence = NULL;
@@ -473,7 +461,7 @@ nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan,
 		return ret;
 
 	ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, NULL,
-					evict, no_wait, new_mem);
+					evict, no_wait_reserve, no_wait_gpu, new_mem);
 	if (nvbo->channel && nvbo->channel != chan)
 		ret = nouveau_fence_wait(fence, NULL, false, false);
 	nouveau_fence_unref((void *)&fence);
@@ -497,7 +485,8 @@ nouveau_bo_mem_ctxdma(struct nouveau_bo *nvbo, struct nouveau_channel *chan,
 
 static int
 nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
-		     int no_wait, struct ttm_mem_reg *new_mem)
+		     bool no_wait_reserve, bool no_wait_gpu,
+		     struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev);
@@ -575,12 +564,13 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 		dst_offset += (PAGE_SIZE * line_count);
 	}
 
-	return nouveau_bo_move_accel_cleanup(chan, nvbo, evict, no_wait, new_mem);
+	return nouveau_bo_move_accel_cleanup(chan, nvbo, evict, no_wait_reserve, no_wait_gpu, new_mem);
 }
 
 static int
 nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait, struct ttm_mem_reg *new_mem)
+		      bool no_wait_reserve, bool no_wait_gpu,
+		      struct ttm_mem_reg *new_mem)
 {
 	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
 	struct ttm_placement placement;
@@ -593,7 +583,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait);
+	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_reserve, no_wait_gpu);
 	if (ret)
 		return ret;
 
@@ -601,11 +591,11 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	if (ret)
 		goto out;
 
-	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait, &tmp_mem);
+	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, &tmp_mem);
 	if (ret)
 		goto out;
 
-	ret = ttm_bo_move_ttm(bo, evict, no_wait, new_mem);
+	ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
 out:
 	if (tmp_mem.mm_node) {
 		spin_lock(&bo->bdev->glob->lru_lock);
@@ -618,7 +608,8 @@ out:
 
 static int
 nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait, struct ttm_mem_reg *new_mem)
+		      bool no_wait_reserve, bool no_wait_gpu,
+		      struct ttm_mem_reg *new_mem)
 {
 	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
 	struct ttm_placement placement;
@@ -631,15 +622,15 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait);
+	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_reserve, no_wait_gpu);
 	if (ret)
 		return ret;
 
-	ret = ttm_bo_move_ttm(bo, evict, no_wait, &tmp_mem);
+	ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, &tmp_mem);
 	if (ret)
 		goto out;
 
-	ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait, new_mem);
+	ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
 	if (ret)
 		goto out;
 
@@ -706,7 +697,8 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
 
 static int
 nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
-		bool no_wait, struct ttm_mem_reg *new_mem)
+		bool no_wait_reserve, bool no_wait_gpu,
+		struct ttm_mem_reg *new_mem)
 {
 	struct drm_nouveau_private *dev_priv = nouveau_bdev(bo->bdev);
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
@@ -721,7 +713,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 	/* Software copy if the card isn't up and running yet. */
 	if (dev_priv->init_state != NOUVEAU_CARD_INIT_DONE ||
 	    !dev_priv->channel) {
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait, new_mem);
+		ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
 		goto out;
 	}
 
@@ -735,17 +727,17 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	/* Hardware assisted copy. */
 	if (new_mem->mem_type == TTM_PL_SYSTEM)
-		ret = nouveau_bo_move_flipd(bo, evict, intr, no_wait, new_mem);
+		ret = nouveau_bo_move_flipd(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
 	else if (old_mem->mem_type == TTM_PL_SYSTEM)
-		ret = nouveau_bo_move_flips(bo, evict, intr, no_wait, new_mem);
+		ret = nouveau_bo_move_flips(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
 	else
-		ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait, new_mem);
+		ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
 
 	if (!ret)
 		goto out;
 
 	/* Fallback to software copy. */
-	ret = ttm_bo_move_memcpy(bo, evict, no_wait, new_mem);
+	ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
 
 out:
 	if (ret)
@@ -762,6 +754,55 @@ nouveau_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 	return 0;
 }
 
+static int
+nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct drm_nouveau_private *dev_priv = nouveau_bdev(bdev);
+	struct drm_device *dev = dev_priv->dev;
+
+	mem->bus.addr = NULL;
+	mem->bus.offset = 0;
+	mem->bus.size = mem->num_pages << PAGE_SHIFT;
+	mem->bus.base = 0;
+	mem->bus.is_iomem = false;
+	if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE))
+		return -EINVAL;
+	switch (mem->mem_type) {
+	case TTM_PL_SYSTEM:
+		/* System memory */
+		return 0;
+	case TTM_PL_TT:
+#if __OS_HAS_AGP
+		if (dev_priv->gart_info.type == NOUVEAU_GART_AGP) {
+			mem->bus.offset = mem->mm_node->start << PAGE_SHIFT;
+			mem->bus.base = dev_priv->gart_info.aper_base;
+			mem->bus.is_iomem = true;
+		}
+#endif
+		break;
+	case TTM_PL_VRAM:
+		mem->bus.offset = mem->mm_node->start << PAGE_SHIFT;
+		mem->bus.base = drm_get_resource_start(dev, 1);
+		mem->bus.is_iomem = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void
+nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+}
+
+static int
+nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
+{
+	return 0;
+}
+
 struct ttm_bo_driver nouveau_bo_driver = {
 	.create_ttm_backend_entry = nouveau_bo_create_ttm_backend_entry,
 	.invalidate_caches = nouveau_bo_invalidate_caches,
@@ -774,5 +815,8 @@ struct ttm_bo_driver nouveau_bo_driver = {
 	.sync_obj_flush = nouveau_fence_flush,
 	.sync_obj_unref = nouveau_fence_unref,
 	.sync_obj_ref = nouveau_fence_ref,
+	.fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
+	.io_mem_reserve = &nouveau_ttm_io_mem_reserve,
+	.io_mem_free = &nouveau_ttm_io_mem_free,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 6d1aa89ec87..69c76cf9340 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -385,7 +385,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 
 		nvbo->channel = chan;
 		ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
-				      false, false);
+				      false, false, false);
 		nvbo->channel = NULL;
 		if (unlikely(ret)) {
 			NV_ERROR(dev, "fail ttm_validate\n");
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 3295154e593..b3d168fb89e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1266,11 +1266,6 @@ int evergreen_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
-	/* FIXME remove this once we support unmappable VRAM */
-	if (rdev->mc.mc_vram_size > rdev->mc.aper_size) {
-		rdev->mc.mc_vram_size = rdev->mc.aper_size;
-		rdev->mc.real_vram_size = rdev->mc.aper_size;
-	}
 	r600_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 9d3b47deecb..9bdccb96499 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2036,11 +2036,6 @@ void r100_vram_init_sizes(struct radeon_device *rdev)
 		else
 			rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
 	}
-	/* FIXME remove this once we support unmappable VRAM */
-	if (rdev->mc.mc_vram_size > rdev->mc.aper_size) {
-		rdev->mc.mc_vram_size = rdev->mc.aper_size;
-		rdev->mc.real_vram_size = rdev->mc.aper_size;
-	}
 }
 
 void r100_vga_set_state(struct radeon_device *rdev, bool state)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 9b08c5743c8..c325cb12105 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -730,11 +730,6 @@ int r600_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
-	/* FIXME remove this once we support unmappable VRAM */
-	if (rdev->mc.mc_vram_size > rdev->mc.aper_size) {
-		rdev->mc.mc_vram_size = rdev->mc.aper_size;
-		rdev->mc.real_vram_size = rdev->mc.aper_size;
-	}
 	r600_vram_gtt_location(rdev, &rdev->mc);
 
 	if (rdev->flags & RADEON_IS_IGP)
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 122774742bd..6a8617bac14 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -192,7 +192,7 @@ int radeon_bo_pin(struct radeon_bo *bo, u32 domain, u64 *gpu_addr)
 	}
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false, false);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
 		if (gpu_addr != NULL)
@@ -216,7 +216,7 @@ int radeon_bo_unpin(struct radeon_bo *bo)
 		return 0;
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false, false);
 	if (unlikely(r != 0))
 		dev_err(bo->rdev->dev, "%p validate failed for unpin\n", bo);
 	return r;
@@ -331,7 +331,7 @@ int radeon_bo_list_validate(struct list_head *head)
 								lobj->rdomain);
 			}
 			r = ttm_bo_validate(&bo->tbo, &bo->placement,
-						true, false);
+						true, false, false);
 			if (unlikely(r))
 				return r;
 		}
@@ -499,11 +499,33 @@ void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 	radeon_bo_check_tiling(rbo, 0, 1);
 }
 
-void radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
+int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
+	struct radeon_device *rdev;
 	struct radeon_bo *rbo;
+	unsigned long offset, size;
+	int r;
+
 	if (!radeon_ttm_bo_is_radeon_bo(bo))
-		return;
+		return 0;
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	radeon_bo_check_tiling(rbo, 0, 0);
+	rdev = rbo->rdev;
+	if (bo->mem.mem_type == TTM_PL_VRAM) {
+		size = bo->mem.num_pages << PAGE_SHIFT;
+		offset = bo->mem.mm_node->start << PAGE_SHIFT;
+		if ((offset + size) > rdev->mc.visible_vram_size) {
+			/* hurrah the memory is not visible ! */
+			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
+			rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+			r = ttm_bo_validate(bo, &rbo->placement, false, true, false);
+			if (unlikely(r != 0))
+				return r;
+			offset = bo->mem.mm_node->start << PAGE_SHIFT;
+			/* this should not happen */
+			if ((offset + size) > rdev->mc.visible_vram_size)
+				return -EINVAL;
+		}
+	}
+	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 7ab43de1e24..353998dc2c0 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -168,6 +168,6 @@ extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
 				bool force_drop);
 extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 					struct ttm_mem_reg *mem);
-extern void radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
+extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index f06533676e7..af98f45954b 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -163,34 +163,21 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 					  (unsigned)type);
 				return -EINVAL;
 			}
-			man->io_offset = rdev->mc.agp_base;
-			man->io_size = rdev->mc.gtt_size;
-			man->io_addr = NULL;
 			if (!rdev->ddev->agp->cant_use_aperture)
-				man->flags = TTM_MEMTYPE_FLAG_NEEDS_IOREMAP |
-					     TTM_MEMTYPE_FLAG_MAPPABLE;
+				man->flags = TTM_MEMTYPE_FLAG_MAPPABLE;
 			man->available_caching = TTM_PL_FLAG_UNCACHED |
 						 TTM_PL_FLAG_WC;
 			man->default_caching = TTM_PL_FLAG_WC;
-		} else
-#endif
-		{
-			man->io_offset = 0;
-			man->io_size = 0;
-			man->io_addr = NULL;
 		}
+#endif
 		break;
 	case TTM_PL_VRAM:
 		/* "On-card" video ram */
 		man->gpu_offset = rdev->mc.vram_start;
 		man->flags = TTM_MEMTYPE_FLAG_FIXED |
-			     TTM_MEMTYPE_FLAG_NEEDS_IOREMAP |
 			     TTM_MEMTYPE_FLAG_MAPPABLE;
 		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
-		man->io_addr = NULL;
-		man->io_offset = rdev->mc.aper_base;
-		man->io_size = rdev->mc.aper_size;
 		break;
 	default:
 		DRM_ERROR("Unsupported memory type %u\n", (unsigned)type);
@@ -245,9 +232,9 @@ static void radeon_move_null(struct ttm_buffer_object *bo,
 }
 
 static int radeon_move_blit(struct ttm_buffer_object *bo,
-			    bool evict, int no_wait,
-			    struct ttm_mem_reg *new_mem,
-			    struct ttm_mem_reg *old_mem)
+			bool evict, int no_wait_reserve, bool no_wait_gpu,
+			struct ttm_mem_reg *new_mem,
+			struct ttm_mem_reg *old_mem)
 {
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
@@ -291,13 +278,14 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	r = radeon_copy(rdev, old_start, new_start, new_mem->num_pages, fence);
 	/* FIXME: handle copy error */
 	r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
-				      evict, no_wait, new_mem);
+				      evict, no_wait_reserve, no_wait_gpu, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
 }
 
 static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible, bool no_wait,
+				bool evict, bool interruptible,
+				bool no_wait_reserve, bool no_wait_gpu,
 				struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
@@ -318,7 +306,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	placement.busy_placement = &placements;
 	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
-			     interruptible, no_wait);
+			     interruptible, no_wait_reserve, no_wait_gpu);
 	if (unlikely(r)) {
 		return r;
 	}
@@ -332,11 +320,11 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = radeon_move_blit(bo, true, no_wait, &tmp_mem, old_mem);
+	r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = ttm_bo_move_ttm(bo, true, no_wait, new_mem);
+	r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem);
 out_cleanup:
 	if (tmp_mem.mm_node) {
 		struct ttm_bo_global *glob = rdev->mman.bdev.glob;
@@ -350,7 +338,8 @@ out_cleanup:
 }
 
 static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible, bool no_wait,
+				bool evict, bool interruptible,
+				bool no_wait_reserve, bool no_wait_gpu,
 				struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
@@ -370,15 +359,15 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
 	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, interruptible, no_wait);
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, interruptible, no_wait_reserve, no_wait_gpu);
 	if (unlikely(r)) {
 		return r;
 	}
-	r = ttm_bo_move_ttm(bo, true, no_wait, &tmp_mem);
+	r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = radeon_move_blit(bo, true, no_wait, new_mem, old_mem);
+	r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -395,8 +384,9 @@ out_cleanup:
 }
 
 static int radeon_bo_move(struct ttm_buffer_object *bo,
-			  bool evict, bool interruptible, bool no_wait,
-			  struct ttm_mem_reg *new_mem)
+			bool evict, bool interruptible,
+			bool no_wait_reserve, bool no_wait_gpu,
+			struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
@@ -423,23 +413,66 @@ static int radeon_bo_move(struct ttm_buffer_object *bo,
 	if (old_mem->mem_type == TTM_PL_VRAM &&
 	    new_mem->mem_type == TTM_PL_SYSTEM) {
 		r = radeon_move_vram_ram(bo, evict, interruptible,
-					    no_wait, new_mem);
+					no_wait_reserve, no_wait_gpu, new_mem);
 	} else if (old_mem->mem_type == TTM_PL_SYSTEM &&
 		   new_mem->mem_type == TTM_PL_VRAM) {
 		r = radeon_move_ram_vram(bo, evict, interruptible,
-					    no_wait, new_mem);
+					    no_wait_reserve, no_wait_gpu, new_mem);
 	} else {
-		r = radeon_move_blit(bo, evict, no_wait, new_mem, old_mem);
+		r = radeon_move_blit(bo, evict, no_wait_reserve, no_wait_gpu, new_mem, old_mem);
 	}
 
 	if (r) {
 memcpy:
-		r = ttm_bo_move_memcpy(bo, evict, no_wait, new_mem);
+		r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
 	}
-
 	return r;
 }
 
+static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
+
+	mem->bus.addr = NULL;
+	mem->bus.offset = 0;
+	mem->bus.size = mem->num_pages << PAGE_SHIFT;
+	mem->bus.base = 0;
+	mem->bus.is_iomem = false;
+	if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE))
+		return -EINVAL;
+	switch (mem->mem_type) {
+	case TTM_PL_SYSTEM:
+		/* system memory */
+		return 0;
+	case TTM_PL_TT:
+#if __OS_HAS_AGP
+		if (rdev->flags & RADEON_IS_AGP) {
+			/* RADEON_IS_AGP is set only if AGP is active */
+			mem->bus.offset = mem->mm_node->start << PAGE_SHIFT;
+			mem->bus.base = rdev->mc.agp_base;
+			mem->bus.is_iomem = true;
+		}
+#endif
+		break;
+	case TTM_PL_VRAM:
+		mem->bus.offset = mem->mm_node->start << PAGE_SHIFT;
+		/* check if it's visible */
+		if ((mem->bus.offset + mem->bus.size) > rdev->mc.visible_vram_size)
+			return -EINVAL;
+		mem->bus.base = rdev->mc.aper_base;
+		mem->bus.is_iomem = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+}
+
 static int radeon_sync_obj_wait(void *sync_obj, void *sync_arg,
 				bool lazy, bool interruptible)
 {
@@ -480,6 +513,8 @@ static struct ttm_bo_driver radeon_bo_driver = {
 	.sync_obj_ref = &radeon_sync_obj_ref,
 	.move_notify = &radeon_bo_move_notify,
 	.fault_reserve_notify = &radeon_bo_fault_reserve_notify,
+	.io_mem_reserve = &radeon_ttm_io_mem_reserve,
+	.io_mem_free = &radeon_ttm_io_mem_free,
 };
 
 int radeon_ttm_init(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index c14f3be25b4..a74683e1861 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -910,11 +910,6 @@ int rv770_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
-	/* FIXME remove this once we support unmappable VRAM */
-	if (rdev->mc.mc_vram_size > rdev->mc.aper_size) {
-		rdev->mc.mc_vram_size = rdev->mc.aper_size;
-		rdev->mc.real_vram_size = rdev->mc.aper_size;
-	}
 	r600_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index dd47b2a9a79..3b5b094b139 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -79,8 +79,6 @@ static void ttm_mem_type_debug(struct ttm_bo_device *bdev, int mem_type)
 	printk(KERN_ERR TTM_PFX "    use_type: %d\n", man->use_type);
 	printk(KERN_ERR TTM_PFX "    flags: 0x%08X\n", man->flags);
 	printk(KERN_ERR TTM_PFX "    gpu_offset: 0x%08lX\n", man->gpu_offset);
-	printk(KERN_ERR TTM_PFX "    io_offset: 0x%08lX\n", man->io_offset);
-	printk(KERN_ERR TTM_PFX "    io_size: %ld\n", man->io_size);
 	printk(KERN_ERR TTM_PFX "    size: %llu\n", man->size);
 	printk(KERN_ERR TTM_PFX "    available_caching: 0x%08X\n",
 		man->available_caching);
@@ -357,7 +355,8 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 
 static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem,
-				  bool evict, bool interruptible, bool no_wait)
+				  bool evict, bool interruptible,
+				  bool no_wait_reserve, bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	bool old_is_pci = ttm_mem_reg_is_pci(bdev, &bo->mem);
@@ -402,12 +401,12 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
 	    !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
-		ret = ttm_bo_move_ttm(bo, evict, no_wait, mem);
+		ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, mem);
 	else if (bdev->driver->move)
 		ret = bdev->driver->move(bo, evict, interruptible,
-					 no_wait, mem);
+					 no_wait_reserve, no_wait_gpu, mem);
 	else
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait, mem);
+		ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, mem);
 
 	if (ret)
 		goto out_err;
@@ -606,7 +605,7 @@ void ttm_bo_unref(struct ttm_buffer_object **p_bo)
 EXPORT_SYMBOL(ttm_bo_unref);
 
 static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
-			bool no_wait)
+			bool no_wait_reserve, bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bo->glob;
@@ -615,7 +614,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	int ret = 0;
 
 	spin_lock(&bo->lock);
-	ret = ttm_bo_wait(bo, false, interruptible, no_wait);
+	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
 	spin_unlock(&bo->lock);
 
 	if (unlikely(ret != 0)) {
@@ -631,6 +630,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
+	evict_mem.bus.io_reserved = false;
 
 	placement.fpfn = 0;
 	placement.lpfn = 0;
@@ -638,7 +638,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	placement.num_busy_placement = 0;
 	bdev->driver->evict_flags(bo, &placement);
 	ret = ttm_bo_mem_space(bo, &placement, &evict_mem, interruptible,
-				no_wait);
+				no_wait_reserve, no_wait_gpu);
 	if (ret) {
 		if (ret != -ERESTARTSYS) {
 			printk(KERN_ERR TTM_PFX
@@ -650,7 +650,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	}
 
 	ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, interruptible,
-				     no_wait);
+				     no_wait_reserve, no_wait_gpu);
 	if (ret) {
 		if (ret != -ERESTARTSYS)
 			printk(KERN_ERR TTM_PFX "Buffer eviction failed\n");
@@ -670,7 +670,8 @@ out:
 
 static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 				uint32_t mem_type,
-				bool interruptible, bool no_wait)
+				bool interruptible, bool no_wait_reserve,
+				bool no_wait_gpu)
 {
 	struct ttm_bo_global *glob = bdev->glob;
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
@@ -687,11 +688,11 @@ retry:
 	bo = list_first_entry(&man->lru, struct ttm_buffer_object, lru);
 	kref_get(&bo->list_kref);
 
-	ret = ttm_bo_reserve_locked(bo, false, true, false, 0);
+	ret = ttm_bo_reserve_locked(bo, false, no_wait_reserve, false, 0);
 
 	if (unlikely(ret == -EBUSY)) {
 		spin_unlock(&glob->lru_lock);
-		if (likely(!no_wait))
+		if (likely(!no_wait_gpu))
 			ret = ttm_bo_wait_unreserved(bo, interruptible);
 
 		kref_put(&bo->list_kref, ttm_bo_release_list);
@@ -713,7 +714,7 @@ retry:
 	while (put_count--)
 		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
-	ret = ttm_bo_evict(bo, interruptible, no_wait);
+	ret = ttm_bo_evict(bo, interruptible, no_wait_reserve, no_wait_gpu);
 	ttm_bo_unreserve(bo);
 
 	kref_put(&bo->list_kref, ttm_bo_release_list);
@@ -764,7 +765,9 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 					uint32_t mem_type,
 					struct ttm_placement *placement,
 					struct ttm_mem_reg *mem,
-					bool interruptible, bool no_wait)
+					bool interruptible,
+					bool no_wait_reserve,
+					bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bdev->glob;
@@ -785,7 +788,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 		}
 		spin_unlock(&glob->lru_lock);
 		ret = ttm_mem_evict_first(bdev, mem_type, interruptible,
-						no_wait);
+						no_wait_reserve, no_wait_gpu);
 		if (unlikely(ret != 0))
 			return ret;
 	} while (1);
@@ -855,7 +858,8 @@ static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
 int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
 			struct ttm_mem_reg *mem,
-			bool interruptible, bool no_wait)
+			bool interruptible, bool no_wait_reserve,
+			bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_type_manager *man;
@@ -952,7 +956,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		}
 
 		ret = ttm_bo_mem_force_space(bo, mem_type, placement, mem,
-						interruptible, no_wait);
+						interruptible, no_wait_reserve, no_wait_gpu);
 		if (ret == 0 && mem->mm_node) {
 			mem->placement = cur_flags;
 			mem->mm_node->private = bo;
@@ -978,7 +982,8 @@ EXPORT_SYMBOL(ttm_bo_wait_cpu);
 
 int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
-			bool interruptible, bool no_wait)
+			bool interruptible, bool no_wait_reserve,
+			bool no_wait_gpu)
 {
 	struct ttm_bo_global *glob = bo->glob;
 	int ret = 0;
@@ -992,20 +997,21 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	 * instead of doing it here.
 	 */
 	spin_lock(&bo->lock);
-	ret = ttm_bo_wait(bo, false, interruptible, no_wait);
+	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
 	spin_unlock(&bo->lock);
 	if (ret)
 		return ret;
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
+	mem.bus.io_reserved = false;
 	/*
 	 * Determine where to move the buffer.
 	 */
-	ret = ttm_bo_mem_space(bo, placement, &mem, interruptible, no_wait);
+	ret = ttm_bo_mem_space(bo, placement, &mem, interruptible, no_wait_reserve, no_wait_gpu);
 	if (ret)
 		goto out_unlock;
-	ret = ttm_bo_handle_move_mem(bo, &mem, false, interruptible, no_wait);
+	ret = ttm_bo_handle_move_mem(bo, &mem, false, interruptible, no_wait_reserve, no_wait_gpu);
 out_unlock:
 	if (ret && mem.mm_n