Merge tag 'drm-misc-next-2020-10-27' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 5.11:

UAPI Changes:

  - doc: rules for EBUSY on non-blocking commits; requirements for fourcc
    modifiers; on parsing EDID
  - fbdev/sbuslib: Remove unused FBIOSCURSOR32
  - fourcc: deprecate DRM_FORMAT_MOD_NONE
  - virtio: Support blob resources for memory allocations; Expose host-visible
    and cross-device features

Cross-subsystem Changes:

  - devicetree: Add vendor Prefix for Yes Optoelectronics, Shanghai Top Display
    Optoelectronics
  - dma-buf: Add struct dma_buf_map that stores DMA pointer and I/O-memory flag;
    dma_buf_vmap()/vunmap() return address in dma_buf_map; Use struct_size() macro

Core Changes:

  - atomic: pass full state to CRTC atomic enable/disable; warn for EBUSY during
    non-blocking commits
  - dp: Prepare for DP 2.0 DPCD
  - dp_mst: Receive extended DPCD caps
  - dma-buf: Documentation
  - doc: Format modifiers; dma-buf-map; Cleanups
  - fbdev: Don't use compat_alloc_user_space(); mark as orphaned
  - fb-helper: Take lock in drm_fb_helper_restore_work_fb()
  - gem: Convert implementation and drivers to GEM object functions, remove
    GEM callbacks from struct drm_driver (expect gem_prime_mmap)
  - panel: Cleanups
  - pci: Add legacy infix to drm_irq_by_busid()
  - sched: Avoid infinite waits in drm_sched_entity_destroy()
  - switcheroo: Cleanups
  - ttm: Remove AGP support; Don't modify caching during swapout; Major
    refactoring of the implementation and API that affects all depending
    drivers; Add ttm_bo_wait_ctx(); Add ttm_bo_pin()/unpin() in favor of
    TTM_PL_FLAG_NO_EVICT; Remove ttm_bo_create(); Remove fault_reserve_notify()
    callback; Push move() implementation into drivers; Remove TTM_PAGE_FLAG_WRITE;
    Replace caching flags with init-time cache setting; Push ttm_tt_bind() into
    drivers; Replace move_notify() with delete_mem_notify(); No overlapping memcpy();
    no more ttm_set_populated()
  - vram-helper: Fix BO top-down placement; TTM-related changes; Init GEM
    object functions with defaults; Default placement in system memory; Cleanups

Driver Changes:

  - amdgpu: Use GEM object functions
  - armada: Use GEM object functions
  - aspeed: Configure output via sysfs; Init struct drm_driver with
  - ast: Reload LUT after FB format changes
  - bridge: Add driver and DT bindings for anx7625; Cleanups
  - bridge/dw-hdmi: Constify ops
  - bridge/ti-sn65dsi86: Add retries for link training
  - bridge/lvds-codec: Add support for regulator
  - bridge/tc358768: Restore connector support DRM_GEM_CMA_DRIVEROPS; Cleanups
  - display/ti,j721e-dss: Add DT properies assigned-clocks, assigned-clocks-parent and
    dma-coherent
  - display/ti,am65s-dss: Add DT properies assigned-clocks, assigned-clocks-parent and
    dma-coherent
  - etnaviv: Use GEM object functions
  - exynos: Use GEM object functions
  - fbdev: Cleanups and compiler fixes throughout framebuffer drivers
  - fbdev/cirrusfb: Avoid division by 0
  - gma500: Use GEM object functions; Fix double-free of connector; Cleanups
  - hisilicon/hibmc: I2C-based DDC support; Use to_hibmc_drm_device(); Cleanups
  - i915: Use GEM object functions
  - imx/dcss: Init driver with DRM_GEM_CMA_DRIVER_OPS; Cleanups
  - ingenic: Reset pixel clock when parent clock changes; support reserved
    memory; Alloc F0 and F1 DMA channels at once; Support different pixel formats;
    Revert support for cached mmap buffers
    on F0/F1; support 30-bit/24-bit/8-bit-palette modes
  - komeda: Use DEFINE_SHOW_ATTRIBUTE
  - mcde: Detect platform_get_irq() errors
  - mediatek: Use GEM object functions
  - msm: Use GEM object functions
  - nouveau: Cleanups; TTM-related changes; Use GEM object functions
  - omapdrm: Use GEM object functions
  - panel: Add driver and DT bindings for Novatak nt36672a; Add driver and DT
    bindings for YTC700TLAG-05-201C; Add driver and DT bindings for TDO TL070WSH30;
    Cleanups
  - panel/mantix: Fix reset; Fix deref of NULL pointer in mantix_get_modes()
  - panel/otm8009a: Allow non-continuous dsi clock; Cleanups
  - panel/rm68200: Allow non-continuous dsi clock; Fix mode to 50 FPS
  - panfrost: Fix job timeout handling; Cleanups
  - pl111: Use GEM object functions
  - qxl: Cleanups; TTM-related changes; Pin new BOs with ttm_bo_init_reserved()
  - radeon: Cleanups; TTM-related changes; Use GEM object functions
  - rockchip: Use GEM object functions
  - shmobile: Cleanups
  - tegra: Use GEM object functions
  - tidss: Set drm_plane_helper_funcs.prepare_fb
  - tilcdc: Don't keep vblank interrupt enabled all the time
  - tve200: Detect platform_get_irq() errors
  - vc4: Use GEM object functions; Only register components once DSI is attached;
    Add Maxime as maintainer
  - vgem: Use GEM object functions
  - via: Simplify critical section in via_mem_alloc()
  - virtgpu: Use GEM object functions
  - virtio: Implement blob resources, host-visible and cross-device features;
    Support mapping of host-allocated resources; Use UUID APi; Cleanups
  - vkms: Use GEM object functions; Switch to SHMEM
  - vmwgfx: TTM-related changes; Inline ttm_bo_swapout_all()
  - xen: Use GEM object functions
  - xlnx: Use GEM object functions

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

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20201027100936.GA4858@linux-uq9g

7 files changed, 178 insertions, 195 deletions

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a6d8de01194a..5d54bccebd4d 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -497,7 +497,6 @@ struct radeon_bo {
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
 	u32				flags;
-	unsigned			pin_count;
 	void				*kptr;
 	u32				tiling_flags;
 	u32				pitch;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index e0ae911ef427..b79686cf8bdb 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -273,10 +273,7 @@ static void radeon_unpin_work_func(struct work_struct *__work)
 	/* unpin of the old buffer */
 	r = radeon_bo_reserve(work->old_rbo, false);
 	if (likely(r == 0)) {
-		r = radeon_bo_unpin(work->old_rbo);
-		if (unlikely(r != 0)) {
-			DRM_ERROR("failed to unpin buffer after flip\n");
-		}
+		radeon_bo_unpin(work->old_rbo);
 		radeon_bo_unreserve(work->old_rbo);
 	} else
 		DRM_ERROR("failed to reserve buffer after flip\n");
@@ -607,9 +604,7 @@ pflip_cleanup:
 		DRM_ERROR("failed to reserve new rbo in error path\n");
 		goto cleanup;
 	}
-	if (unlikely(radeon_bo_unpin(new_rbo) != 0)) {
-		DRM_ERROR("failed to unpin new rbo in error path\n");
-	}
+	radeon_bo_unpin(new_rbo);
 	radeon_bo_unreserve(new_rbo);
 
 cleanup:
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 4cd30613fa1d..65061c949aee 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -124,13 +124,6 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev);
 int radeon_driver_irq_postinstall_kms(struct drm_device *dev);
 void radeon_driver_irq_uninstall_kms(struct drm_device *dev);
 irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg);
-void radeon_gem_object_free(struct drm_gem_object *obj);
-int radeon_gem_object_open(struct drm_gem_object *obj,
-				struct drm_file *file_priv);
-void radeon_gem_object_close(struct drm_gem_object *obj,
-				struct drm_file *file_priv);
-struct dma_buf *radeon_gem_prime_export(struct drm_gem_object *gobj,
-					int flags);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int crtc,
 				      unsigned int flags, int *vpos, int *hpos,
 				      ktime_t *stime, ktime_t *etime,
@@ -145,14 +138,9 @@ int radeon_mode_dumb_mmap(struct drm_file *filp,
 int radeon_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_device *dev,
 			    struct drm_mode_create_dumb *args);
-struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
 							struct dma_buf_attachment *,
 							struct sg_table *sg);
-int radeon_gem_prime_pin(struct drm_gem_object *obj);
-void radeon_gem_prime_unpin(struct drm_gem_object *obj);
-void *radeon_gem_prime_vmap(struct drm_gem_object *obj);
-void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)
@@ -550,7 +538,7 @@ long radeon_drm_ioctl(struct file *filp,
 	}
 
 	ret = drm_ioctl(filp, cmd, arg);
-	
+
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
@@ -609,22 +597,13 @@ static struct drm_driver kms_driver = {
 	.irq_uninstall = radeon_driver_irq_uninstall_kms,
 	.irq_handler = radeon_driver_irq_handler_kms,
 	.ioctls = radeon_ioctls_kms,
-	.gem_free_object_unlocked = radeon_gem_object_free,
-	.gem_open_object = radeon_gem_object_open,
-	.gem_close_object = radeon_gem_object_close,
 	.dumb_create = radeon_mode_dumb_create,
 	.dumb_map_offset = radeon_mode_dumb_mmap,
 	.fops = &radeon_driver_kms_fops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-	.gem_prime_export = radeon_gem_prime_export,
-	.gem_prime_pin = radeon_gem_prime_pin,
-	.gem_prime_unpin = radeon_gem_prime_unpin,
-	.gem_prime_get_sg_table = radeon_gem_prime_get_sg_table,
 	.gem_prime_import_sg_table = radeon_gem_prime_import_sg_table,
-	.gem_prime_vmap = radeon_gem_prime_vmap,
-	.gem_prime_vunmap = radeon_gem_prime_vunmap,
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index e5c4271e64ed..0ccd7213e41f 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -35,7 +35,17 @@
 
 #include "radeon.h"
 
-void radeon_gem_object_free(struct drm_gem_object *gobj)
+struct dma_buf *radeon_gem_prime_export(struct drm_gem_object *gobj,
+					int flags);
+struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
+int radeon_gem_prime_pin(struct drm_gem_object *obj);
+void radeon_gem_prime_unpin(struct drm_gem_object *obj);
+void *radeon_gem_prime_vmap(struct drm_gem_object *obj);
+void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
+
+static const struct drm_gem_object_funcs radeon_gem_object_funcs;
+
+static void radeon_gem_object_free(struct drm_gem_object *gobj)
 {
 	struct radeon_bo *robj = gem_to_radeon_bo(gobj);
 
@@ -85,6 +95,7 @@ retry:
 		return r;
 	}
 	*obj = &robj->tbo.base;
+	(*obj)->funcs = &radeon_gem_object_funcs;
 	robj->pid = task_pid_nr(current);
 
 	mutex_lock(&rdev->gem.mutex);
@@ -146,7 +157,7 @@ void radeon_gem_fini(struct radeon_device *rdev)
  * Call from drm_gem_handle_create which appear in both new and open ioctl
  * case.
  */
-int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv)
+static int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 {
 	struct radeon_bo *rbo = gem_to_radeon_bo(obj);
 	struct radeon_device *rdev = rbo->rdev;
@@ -176,8 +187,8 @@ int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
 	return 0;
 }
 
-void radeon_gem_object_close(struct drm_gem_object *obj,
-			     struct drm_file *file_priv)
+static void radeon_gem_object_close(struct drm_gem_object *obj,
+				    struct drm_file *file_priv)
 {
 	struct radeon_bo *rbo = gem_to_radeon_bo(obj);
 	struct radeon_device *rdev = rbo->rdev;
@@ -216,6 +227,18 @@ static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r)
 	return r;
 }
 
+static const struct drm_gem_object_funcs radeon_gem_object_funcs = {
+	.free = radeon_gem_object_free,
+	.open = radeon_gem_object_open,
+	.close = radeon_gem_object_close,
+	.export = radeon_gem_prime_export,
+	.pin = radeon_gem_prime_pin,
+	.unpin = radeon_gem_prime_unpin,
+	.get_sg_table = radeon_gem_prime_get_sg_table,
+	.vmap = radeon_gem_prime_vmap,
+	.vunmap = radeon_gem_prime_vunmap,
+};
+
 /*
  * GEM ioctls.
  */
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 316e35d3f8a9..ab81e35cb060 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -113,57 +113,29 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 			rbo->placements[c].fpfn =
 				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
 			rbo->placements[c].mem_type = TTM_PL_VRAM;
-			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-						     TTM_PL_FLAG_UNCACHED;
+			rbo->placements[c++].flags = 0;
 		}
 
 		rbo->placements[c].fpfn = 0;
 		rbo->placements[c].mem_type = TTM_PL_VRAM;
-		rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-					     TTM_PL_FLAG_UNCACHED;
+		rbo->placements[c++].flags = 0;
 	}
 
 	if (domain & RADEON_GEM_DOMAIN_GTT) {
-		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_TT;
-			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED;
-
-		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
-			   (rbo->rdev->flags & RADEON_IS_AGP)) {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_TT;
-			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-				TTM_PL_FLAG_UNCACHED;
-		} else {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_TT;
-			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED;
-		}
+		rbo->placements[c].fpfn = 0;
+		rbo->placements[c].mem_type = TTM_PL_TT;
+		rbo->placements[c++].flags = 0;
 	}
 
 	if (domain & RADEON_GEM_DOMAIN_CPU) {
-		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
-			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED;
-
-		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
-		    rbo->rdev->flags & RADEON_IS_AGP) {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
-			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-				TTM_PL_FLAG_UNCACHED;
-		} else {
-			rbo->placements[c].fpfn = 0;
-			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
-			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED;
-		}
+		rbo->placements[c].fpfn = 0;
+		rbo->placements[c].mem_type = TTM_PL_SYSTEM;
+		rbo->placements[c++].flags = 0;
 	}
 	if (!c) {
 		rbo->placements[c].fpfn = 0;
 		rbo->placements[c].mem_type = TTM_PL_SYSTEM;
-		rbo->placements[c++].flags = TTM_PL_MASK_CACHING;
+		rbo->placements[c++].flags = 0;
 	}
 
 	rbo->placement.num_placement = c;
@@ -334,8 +306,8 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 	if (radeon_ttm_tt_has_userptr(bo->rdev, bo->tbo.ttm))
 		return -EPERM;
 
-	if (bo->pin_count) {
-		bo->pin_count++;
+	if (bo->tbo.pin_count) {
+		ttm_bo_pin(&bo->tbo);
 		if (gpu_addr)
 			*gpu_addr = radeon_bo_gpu_offset(bo);
 
@@ -367,13 +339,11 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 				bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
 		else
 			bo->placements[i].lpfn = max_offset >> PAGE_SHIFT;
-
-		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	}
 
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (likely(r == 0)) {
-		bo->pin_count = 1;
+		ttm_bo_pin(&bo->tbo);
 		if (gpu_addr != NULL)
 			*gpu_addr = radeon_bo_gpu_offset(bo);
 		if (domain == RADEON_GEM_DOMAIN_VRAM)
@@ -391,36 +361,22 @@ int radeon_bo_pin(struct radeon_bo *bo, u32 domain, u64 *gpu_addr)
 	return radeon_bo_pin_restricted(bo, domain, 0, gpu_addr);
 }
 
-int radeon_bo_unpin(struct radeon_bo *bo)
+void radeon_bo_unpin(struct radeon_bo *bo)
 {
-	struct ttm_operation_ctx ctx = { false, false };
-	int r, i;
-
-	if (!bo->pin_count) {
-		dev_warn(bo->rdev->dev, "%p unpin not necessary\n", bo);
-		return 0;
-	}
-	bo->pin_count--;
-	if (bo->pin_count)
-		return 0;
-	for (i = 0; i < bo->placement.num_placement; i++) {
-		bo->placements[i].lpfn = 0;
-		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-	}
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-	if (likely(r == 0)) {
+	ttm_bo_unpin(&bo->tbo);
+	if (!bo->tbo.pin_count) {
 		if (bo->tbo.mem.mem_type == TTM_PL_VRAM)
 			bo->rdev->vram_pin_size -= radeon_bo_size(bo);
 		else
 			bo->rdev->gart_pin_size -= radeon_bo_size(bo);
-	} else {
-		dev_err(bo->rdev->dev, "%p validate failed for unpin\n", bo);
 	}
-	return r;
 }
 
 int radeon_bo_evict_vram(struct radeon_device *rdev)
 {
+	struct ttm_bo_device *bdev = &rdev->mman.bdev;
+	struct ttm_resource_manager *man;
+
 	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
 #ifndef CONFIG_HIBERNATION
 	if (rdev->flags & RADEON_IS_IGP) {
@@ -429,7 +385,8 @@ int radeon_bo_evict_vram(struct radeon_device *rdev)
 			return 0;
 	}
 #endif
-	return ttm_bo_evict_mm(&rdev->mman.bdev, TTM_PL_VRAM);
+	man = ttm_manager_type(bdev, TTM_PL_VRAM);
+	return ttm_resource_manager_evict_all(bdev, man);
 }
 
 void radeon_bo_force_delete(struct radeon_device *rdev)
@@ -549,7 +506,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 
 	list_for_each_entry(lobj, head, tv.head) {
 		struct radeon_bo *bo = lobj->robj;
-		if (!bo->pin_count) {
+		if (!bo->tbo.pin_count) {
 			u32 domain = lobj->preferred_domains;
 			u32 allowed = lobj->allowed_domains;
 			u32 current_domain =
@@ -629,7 +586,7 @@ int radeon_bo_get_surface_reg(struct radeon_bo *bo)
 			break;
 
 		old_object = reg->bo;
-		if (old_object->pin_count == 0)
+		if (old_object->tbo.pin_count == 0)
 			steal = i;
 	}
 
@@ -794,7 +751,7 @@ void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 	radeon_update_memory_usage(rbo, new_mem->mem_type, 1);
 }
 
-int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
+vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct ttm_operation_ctx ctx = { false, false };
 	struct radeon_device *rdev;
@@ -816,8 +773,8 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 		return 0;
 
 	/* Can't move a pinned BO to visible VRAM */
-	if (rbo->pin_count > 0)
-		return -EINVAL;
+	if (rbo->tbo.pin_count > 0)
+		return VM_FAULT_SIGBUS;
 
 	/* hurrah the memory is not visible ! */
 	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
@@ -831,34 +788,23 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	r = ttm_bo_validate(bo, &rbo->placement, &ctx);
 	if (unlikely(r == -ENOMEM)) {
 		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
-		return ttm_bo_validate(bo, &rbo->placement, &ctx);
-	} else if (unlikely(r != 0)) {
-		return r;
+		r = ttm_bo_validate(bo, &rbo->placement, &ctx);
+	} else if (likely(!r)) {
+		offset = bo->mem.start << PAGE_SHIFT;
+		/* this should never happen */
+		if ((offset + size) > rdev->mc.visible_vram_size)
+			return VM_FAULT_SIGBUS;
 	}
 
-	offset = bo->mem.start << PAGE_SHIFT;
-	/* this should never happen */
-	if ((offset + size) > rdev->mc.visible_vram_size)
-		return -EINVAL;
+	if (unlikely(r == -EBUSY || r == -ERESTARTSYS))
+		return VM_FAULT_NOPAGE;
+	else if (unlikely(r))
+		return VM_FAULT_SIGBUS;
 
+	ttm_bo_move_to_lru_tail_unlocked(bo);
 	return 0;
 }
 
-int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
-{
-	int r;
-
-	r = ttm_bo_reserve(&bo->tbo, true, no_wait, NULL);
-	if (unlikely(r != 0))
-		return r;
-	if (mem_type)
-		*mem_type = bo->tbo.mem.mem_type;
-
-	r = ttm_bo_wait(&bo->tbo, true, no_wait);
-	ttm_bo_unreserve(&bo->tbo);
-	return r;
-}
-
 /**
  * radeon_bo_fence - add fence to buffer object
  *
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 44b47241ee42..d606e9a935e3 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -133,9 +133,6 @@ static inline u64 radeon_bo_mmap_offset(struct radeon_bo *bo)
 	return drm_vma_node_offset_addr(&bo->tbo.base.vma_node);
 }
 
-extern int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
-			  bool no_wait);
-
 extern int radeon_bo_create(struct radeon_device *rdev,
 			    unsigned long size, int byte_align,
 			    bool kernel, u32 domain, u32 flags,
@@ -149,7 +146,7 @@ extern void radeon_bo_unref(struct radeon_bo **bo);
 extern int radeon_bo_pin(struct radeon_bo *bo, u32 domain, u64 *gpu_addr);
 extern int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain,
 				    u64 max_offset, u64 *gpu_addr);
-extern int radeon_bo_unpin(struct radeon_bo *bo);
+extern void radeon_bo_unpin(struct radeon_bo *bo);
 extern int radeon_bo_evict_vram(struct radeon_device *rdev);
 extern void radeon_bo_force_delete(struct radeon_device *rdev);
 extern int radeon_bo_init(struct radeon_device *rdev);
@@ -166,7 +163,7 @@ extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
 extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 				  bool evict,
 				  struct ttm_resource *new_mem);
-extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
+extern vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
 extern void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence,
 			    bool shared);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 36150b7f31a9..0a6d7ea847db 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -59,6 +59,8 @@ static void radeon_ttm_debugfs_fini(struct radeon_device *rdev);
 static int radeon_ttm_tt_bind(struct ttm_bo_device *bdev,
 			      struct ttm_tt *ttm,
 			      struct ttm_resource *bo_mem);
+static void radeon_ttm_tt_unbind(struct ttm_bo_device *bdev,
+				 struct ttm_tt *ttm);
 
 struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev)
 {
@@ -89,7 +91,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 		.fpfn = 0,
 		.lpfn = 0,
 		.mem_type = TTM_PL_SYSTEM,
-		.flags = TTM_PL_MASK_CACHING
+		.flags = 0
 	};
 
 	struct radeon_bo *rbo;
@@ -151,7 +153,7 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 }
 
 static int radeon_move_blit(struct ttm_buffer_object *bo,
-			bool evict, bool no_wait_gpu,
+			bool evict,
 			struct ttm_resource *new_mem,
 			struct ttm_resource *old_mem)
 {
@@ -206,11 +208,10 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 }
 
 static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible,
-				bool no_wait_gpu,
+				bool evict,
+				struct ttm_operation_ctx *ctx,
 				struct ttm_resource *new_mem)
 {
-	struct ttm_operation_ctx ctx = { interruptible, no_wait_gpu };
 	struct ttm_resource *old_mem = &bo->mem;
 	struct ttm_resource tmp_mem;
 	struct ttm_place placements;
@@ -226,18 +227,13 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	placements.fpfn = 0;
 	placements.lpfn = 0;
 	placements.mem_type = TTM_PL_TT;
-	placements.flags = TTM_PL_MASK_CACHING;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, &ctx);
+	placements.flags = 0;
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		return r;
 	}
 
-	r = ttm_tt_set_placement_caching(bo->ttm, tmp_mem.placement);
-	if (unlikely(r)) {
-		goto out_cleanup;
-	}
-
-	r = ttm_tt_populate(bo->bdev, bo->ttm, &ctx);
+	r = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -246,22 +242,27 @@ 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_gpu, &tmp_mem, old_mem);
+	r = radeon_move_blit(bo, true, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = ttm_bo_move_ttm(bo, &ctx, new_mem);
+	r = ttm_bo_wait_ctx(bo, ctx);
+	if (unlikely(r))
+		goto out_cleanup;
+
+	radeon_ttm_tt_unbind(bo->bdev, bo->ttm);
+	ttm_resource_free(bo, &bo->mem);
+	ttm_bo_assign_mem(bo, new_mem);
 out_cleanup:
 	ttm_resource_free(bo, &tmp_mem);
 	return r;
 }
 
 static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
-				bool evict, bool interruptible,
-				bool no_wait_gpu,
+				bool evict,
+				struct ttm_operation_ctx *ctx,
 				struct ttm_resource *new_mem)
 {
-	struct ttm_operation_ctx ctx = { interruptible, no_wait_gpu };
 	struct ttm_resource *old_mem = &bo->mem;
 	struct ttm_resource tmp_mem;
 	struct ttm_placement placement;
@@ -277,16 +278,22 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	placements.fpfn = 0;
 	placements.lpfn = 0;
 	placements.mem_type = TTM_PL_TT;
-	placements.flags = TTM_PL_MASK_CACHING;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, &ctx);
+	placements.flags = 0;
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		return r;
 	}
-	r = ttm_bo_move_ttm(bo, &ctx, &tmp_mem);
-	if (unlikely(r)) {
+
+	r = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
+	if (unlikely(r))
 		goto out_cleanup;
-	}
-	r = radeon_move_blit(bo, true, no_wait_gpu, new_mem, old_mem);
+
+	r = radeon_ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem);
+	if (unlikely(r))
+		goto out_cleanup;
+
+	ttm_bo_assign_mem(bo, &tmp_mem);
+	r = radeon_move_blit(bo, true, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -304,13 +311,20 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 	struct ttm_resource *old_mem = &bo->mem;
 	int r;
 
-	r = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
+	if (new_mem->mem_type == TTM_PL_TT) {
+		r = radeon_ttm_tt_bind(bo->bdev, bo->ttm, new_mem);
+		if (r)
+			return r;
+	}
+	radeon_bo_move_notify(bo, evict, new_mem);
+
+	r = ttm_bo_wait_ctx(bo, ctx);
 	if (r)
-		return r;
+		goto fail;
 
 	/* Can't move a pinned BO */
 	rbo = container_of(bo, struct radeon_bo, tbo);
-	if (WARN_ON_ONCE(rbo->pin_count > 0))
+	if (WARN_ON_ONCE(rbo->tbo.pin_count > 0))
 		return -EINVAL;
 
 	rdev = radeon_get_rdev(bo->bdev);
@@ -318,14 +332,19 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
-	if ((old_mem->mem_type == TTM_PL_TT &&
-	     new_mem->mem_type == TTM_PL_SYSTEM) ||
-	    (old_mem->mem_type == TTM_PL_SYSTEM &&
-	     new_mem->mem_type == TTM_PL_TT)) {
-		/* bind is enough */
+	if (old_mem->mem_type == TTM_PL_SYSTEM &&
+	    new_mem->mem_type == TTM_PL_TT) {
 		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
+
+	if (old_mem->mem_type == TTM_PL_TT &&
+	    new_mem->mem_type == TTM_PL_SYSTEM) {
+		radeon_ttm_tt_unbind(bo->bdev, bo->ttm);
+		ttm_resource_free(bo, &bo->mem);
+		ttm_bo_assign_mem(bo, new_mem);
+		return 0;
+	}
 	if (!rdev->ring[radeon_copy_ring_index(rdev)].ready ||
 	    rdev->asic->copy.copy == NULL) {
 		/* use memcpy */
@@ -334,14 +353,12 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	if (old_mem->mem_type == TTM_PL_VRAM &&
 	    new_mem->mem_type == TTM_PL_SYSTEM) {
-		r = radeon_move_vram_ram(bo, evict, ctx->interruptible,
-					ctx->no_wait_gpu, new_mem);
+		r = radeon_move_vram_ram(bo, evict, ctx, 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, ctx->interruptible,
-					    ctx->no_wait_gpu, new_mem);
+		r = radeon_move_ram_vram(bo, evict, ctx, new_mem);
 	} else {
-		r = radeon_move_blit(bo, evict, ctx->no_wait_gpu,
+		r = radeon_move_blit(bo, evict,
 				     new_mem, old_mem);
 	}
 
@@ -349,13 +366,18 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 memcpy:
 		r = ttm_bo_move_memcpy(bo, ctx, new_mem);
 		if (r) {
-			return r;
+			goto fail;
 		}
 	}
 
 	/* update statistics */
 	atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &rdev->num_bytes_moved);
 	return 0;
+fail:
+	swap(*new_mem, bo->mem);
+	radeon_bo_move_notify(bo, false, new_mem);
+	swap(*new_mem, bo->mem);
+	return r;
 }
 
 static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *mem)
@@ -374,6 +396,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 			mem->bus.offset = (mem->start << PAGE_SHIFT) +
 				rdev->mc.agp_base;
 			mem->bus.is_iomem = !rdev->ddev->agp->cant_use_aperture;
+			mem->bus.caching = ttm_write_combined;
 		}
 #endif
 		break;
@@ -384,17 +407,13 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 			return -EINVAL;
 		mem->bus.offset += rdev->mc.aper_base;
 		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_write_combined;
 #ifdef __alpha__
 		/*
 		 * Alpha: use bus.addr to hold the ioremap() return,
 		 * so we can modify bus.base below.
 		 */
-		if (mem->placement & TTM_PL_FLAG_WC)
-			mem->bus.addr =
-				ioremap_wc(mem->bus.offset, bus_size);
-		else
-			mem->bus.addr =
-				ioremap(mem->bus.offset, bus_size);
+		mem->bus.addr = ioremap_wc(mem->bus.offset, bus_size);
 		if (!mem->bus.addr)
 			return -ENOMEM;
 
@@ -418,7 +437,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
  * TTM backend functions.
  */
 struct radeon_ttm_tt {
-	struct ttm_dma_tt		ttm;
+	struct ttm_tt		ttm;
 	u64				offset;
 
 	uint64_t			userptr;
@@ -545,15 +564,15 @@ static int radeon_ttm_backend_bind(struct ttm_bo_device *bdev,
 
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
 	if (!ttm->num_pages) {
-		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
+		WARN(1, "nothing to bind %u pages for mreg %p back %p!\n",
 		     ttm->num_pages, bo_mem, ttm);
 	}
-	if (ttm->caching_state == tt_cached)
+	if (ttm->caching == ttm_cached)
 		flags |= RADEON_GART_PAGE_SNOOP;
 	r = radeon_gart_bind(rdev, gtt->offset, ttm->num_pages,
 			     ttm->pages, gtt->ttm.dma_address, flags);
 	if (r) {
-		DRM_ERROR("failed to bind %lu pages at 0x%08X\n",
+		DRM_ERROR("failed to bind %u pages at 0x%08X\n",
 			  ttm->num_pages, (unsigned)gtt->offset);
 		return r;
 	}
@@ -583,7 +602,7 @@ static void radeon_ttm_backend_destroy(struct ttm_bo_device *bdev, struct ttm_tt
 	radeon_ttm_backend_unbind(bdev, ttm);
 	ttm_tt_destroy_common(bdev, ttm);
 
-	ttm_dma_tt_fini(&gtt->ttm);
+	ttm_tt_fini(&gtt->ttm);
 	kfree(gtt);
 }
 
@@ -592,6 +611,10 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_buffer_object *bo,
 {
 	struct radeon_device *rdev;
 	struct radeon_ttm_tt *gtt;
+	enum ttm_caching caching;
+	struct radeon_bo *rbo;
+
+	rbo = container_of(bo, struct radeon_bo, tbo);
 
 	rdev = radeon_get_rdev(bo->bdev);
 #if IS_ENABLED(CONFIG_AGP)
@@ -605,11 +628,19 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_buffer_object *bo,
 	if (gtt == NULL) {
 		return NULL;
 	}
-	if (ttm_dma_tt_init(&gtt->ttm, bo, page_flags)) {
+
+	if (rbo->flags & RADEON_GEM_GTT_UC)
+		caching = ttm_uncached;
+	else if (rbo->flags & RADEON_GEM_GTT_WC)
+		caching = ttm_write_combined;
+	else
+		caching = ttm_cached;
+
+	if (ttm_dma_tt_init(&gtt->ttm, bo, page_flags, caching)) {
 		kfree(gtt);
 		return NULL;
 	}
-	return &gtt->ttm.ttm;
+	return &gtt->ttm;
 }
 
 static struct radeon_ttm_tt *radeon_ttm_tt_to_gtt(struct radeon_device *rdev,
@@ -622,7 +653,7 @@ static struct radeon_ttm_tt *radeon_ttm_tt_to_gtt(struct radeon_device *rdev,
 
 	if (!ttm)
 		return NULL;
-	return container_of(ttm, struct radeon_ttm_tt, ttm.ttm);
+	return container_of(ttm, struct radeon_ttm_tt, ttm);
 }
 
 static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev,
@@ -639,14 +670,12 @@ static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev,
 			return -ENOMEM;
 
 		ttm->page_flags |= TTM_PAGE_FLAG_SG;
-		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
 	if (slave && ttm->sg) {
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address, ttm->num_pages);
-		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
@@ -793,19 +822,22 @@ bool radeon_ttm_tt_is_readonly(struct radeon_device *rdev,
 	return !!(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
 }
 
+static void
+radeon_bo_delete_mem_notify(struct ttm_buffer_object *bo)
+{
+	radeon_bo_move_notify(bo, false, NULL);
+}
+
 static struct ttm_bo_driver radeon_bo_driver = {
 	.ttm_tt_create = &radeon_ttm_tt_create,
 	.ttm_tt_populate = &radeon_ttm_tt_populate,
 	.ttm_tt_unpopulate = &radeon_ttm_tt_unpopulate,
-	.ttm_tt_bind = &radeon_ttm_tt_bind,
-	.ttm_tt_unbind = &radeon_ttm_tt_unbind,
 	.ttm_tt_destroy = &radeon_ttm_tt_destroy,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = &radeon_evict_flags,
 	.move = &radeon_bo_move,
 	.verify_access = &radeon_verify_access,
-	.move_notify = &radeon_bo_move_notify,
-	.fault_reserve_notify = &radeon_bo_fault_reserve_notify,
+	.delete_mem_notify = &radeon_bo_delete_mem_notify,
 	.io_mem_reserve = &radeon_ttm_io_mem_reserve,
 };
 
@@ -906,17 +938,29 @@ void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
 
 static vm_fault_t radeon_ttm_fault(struct vm_fault *vmf)
 {
-	struct ttm_buffer_object *bo;
-	struct radeon_device *rdev;
+	struct ttm_buffer_object *bo = vmf->vma->vm_private_data;
+	struct radeon_device *rdev = radeon_get_rdev(bo->bdev);
 	vm_fault_t ret;
 
-	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
-	if (bo == NULL)
-		return VM_FAULT_NOPAGE;
-
-	rdev = radeon_get_rdev(bo->bdev);
 	down_read(&rdev->pm.mclk_lock);
-	ret = ttm_bo_vm_fault(vmf);
+
+	ret = ttm_bo_vm_reserve(bo, vmf);
+	if (ret)
+		goto unlock_mclk;
+
+	ret = radeon_bo_fault_reserve_notify(bo);
+	if (ret)
+		goto unlock_resv;
+
+	ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+				       TTM_BO_VM_NUM_PREFAULT, 1);
+	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
+		goto unlock_mclk;
+
+unlock_resv:
+	dma_resv_unlock(bo->base.resv);
+
+unlock_mclk:
 	up_read(&rdev->pm.mclk_lock);
 	return ret;
 }