drm/ttm: remove ttm_bo_wait_unreserved

With nouveau fixed all ttm-using drives have the correct nesting of
mmap_sem vs dma_resv, and we can just lock the buffer.

Assuming I didn't screw up anything with my audit of course.

v2:
- Dont forget wu_mutex (Christian König)
- Keep the mmap_sem-less wait optimization (Thomas)
- Use _lock_interruptible to be good citizens (Thomas)

v3: Rebase over fault handler helperification.

Reviewed-by: Christian König <christian.koenig@amd.com> (v2)
Reviewed-by: Thomas Hellström <thellstrom@vmware.com> (v2)
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: "VMware Graphics" <linux-graphics-maintainer@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191104173801.2972-3-daniel.vetter@ffwll.ch

drivers/gpu/drm/ttm/ttm_bo.c

@@ -161,7 +161,6 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	dma_fence_put(bo->moving);
 	if (!ttm_bo_uses_embedded_gem_object(bo))
 		dma_resv_fini(&bo->base._resv);
-	mutex_destroy(&bo->wu_mutex);
 	bo->destroy(bo);
 	ttm_mem_global_free(&ttm_mem_glob, acc_size);
 }
@@ -1291,7 +1290,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
 	INIT_LIST_HEAD(&bo->io_reserve_lru);
-	mutex_init(&bo->wu_mutex);
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->num_pages = num_pages;
@@ -1895,37 +1893,3 @@ void ttm_bo_swapout_all(struct ttm_bo_device *bdev)
 	while (ttm_bo_swapout(&ttm_bo_glob, &ctx) == 0);
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
-
-/**
- * ttm_bo_wait_unreserved - interruptible wait for a buffer object to become
- * unreserved
- *
- * @bo: Pointer to buffer
- */
-int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
-{
-	int ret;
-
-	/*
-	 * In the absense of a wait_unlocked API,
-	 * Use the bo::wu_mutex to avoid triggering livelocks due to
-	 * concurrent use of this function. Note that this use of
-	 * bo::wu_mutex can go away if we change locking order to
-	 * mmap_sem -> bo::reserve.
-	 */
-	ret = mutex_lock_interruptible(&bo->wu_mutex);
-	if (unlikely(ret != 0))
-		return -ERESTARTSYS;
-	if (!dma_resv_is_locked(bo->base.resv))
-		goto out_unlock;
-	ret = dma_resv_lock_interruptible(bo->base.resv, NULL);
-	if (ret == -EINTR)
-		ret = -ERESTARTSYS;
-	if (unlikely(ret != 0))
-		goto out_unlock;
-	dma_resv_unlock(bo->base.resv);
-
-out_unlock:
-	mutex_unlock(&bo->wu_mutex);
-	return ret;
-}

drivers/gpu/drm/ttm/ttm_bo_util.c

@@ -504,7 +504,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->base.lru);
 	INIT_LIST_HEAD(&fbo->base.swap);
 	INIT_LIST_HEAD(&fbo->base.io_reserve_lru);
-	mutex_init(&fbo->base.wu_mutex);
 	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -128,29 +128,21 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
 vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 			     struct vm_fault *vmf)
 {
-	/*
-	 * Work around locking order reversal in fault / nopfn
-	 * between mmap_sem and bo_reserve: Perform a trylock operation
-	 * for reserve, and if it fails, retry the fault after waiting
-	 * for the buffer to become unreserved.
-	 */
 	if (unlikely(!dma_resv_trylock(bo->base.resv))) {
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
-				(void) ttm_bo_wait_unreserved(bo);
+				if (!dma_resv_lock_interruptible(bo->base.resv,
+								 NULL))
+					dma_resv_unlock(bo->base.resv);
 				ttm_bo_put(bo);
 			}
 
 			return VM_FAULT_RETRY;
 		}
 
-		/*
-		 * If we'd want to change locking order to
-		 * mmap_sem -> bo::reserve, we'd use a blocking reserve here
-		 * instead of retrying the fault...
-		 */
+		if (dma_resv_lock_interruptible(bo->base.resv, NULL))
 			return VM_FAULT_NOPAGE;
 	}
 

include/drm/ttm/ttm_bo_api.h

@@ -154,7 +154,6 @@ struct ttm_tt;
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
  * @cur_placement: Hint of current placement.
- * @wu_mutex: Wait unreserved mutex.
  *
  * Base class for TTM buffer object, that deals with data placement and CPU
  * mappings. GPU mappings are really up to the driver, but for simpler GPUs
@@ -222,8 +221,6 @@ struct ttm_buffer_object {
 	uint64_t offset; /* GPU address space is independent of CPU word size */
 
 	struct sg_table *sg;
-
-	struct mutex wu_mutex;
 };
 
 /**
@@ -707,7 +704,6 @@ ssize_t ttm_bo_io(struct ttm_bo_device *bdev, struct file *filp,
 int ttm_bo_swapout(struct ttm_bo_global *glob,
 			struct ttm_operation_ctx *ctx);
 void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
-int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo);
 
 /**
  * ttm_bo_uses_embedded_gem_object - check if the given bo uses the