Merge tag 'drm-misc-fixes-2021-11-11' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

 * dma-buf: name_lock fixes
 * prime: Keep object ref during mmap
 * nouveau: Fix a refcount issue; Fix device removal; Protect client
   list with dedicated mutex; Fix address CE0 address calculation
 * ttm: Fix race condition during BO eviction

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

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/YYzY6jeox9EeI15i@linux-uq9g.fritz.box

5 files changed, 48 insertions, 8 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6109cd9e3399..e7efd9ede8e4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -562,6 +562,7 @@ nouveau_drm_device_init(struct drm_device *dev)
 		nvkm_dbgopt(nouveau_debug, "DRM");
 
 	INIT_LIST_HEAD(&drm->clients);
+	mutex_init(&drm->clients_lock);
 	spin_lock_init(&drm->tile.lock);
 
 	/* workaround an odd issue on nvc1 by disabling the device's
@@ -632,6 +633,7 @@ fail_alloc:
 static void
 nouveau_drm_device_fini(struct drm_device *dev)
 {
+	struct nouveau_cli *cli, *temp_cli;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
 	if (nouveau_pmops_runtime()) {
@@ -656,9 +658,28 @@ nouveau_drm_device_fini(struct drm_device *dev)
 	nouveau_ttm_fini(drm);
 	nouveau_vga_fini(drm);
 
+	/*
+	 * There may be existing clients from as-yet unclosed files. For now,
+	 * clean them up here rather than deferring until the file is closed,
+	 * but this likely not correct if we want to support hot-unplugging
+	 * properly.
+	 */
+	mutex_lock(&drm->clients_lock);
+	list_for_each_entry_safe(cli, temp_cli, &drm->clients, head) {
+		list_del(&cli->head);
+		mutex_lock(&cli->mutex);
+		if (cli->abi16)
+			nouveau_abi16_fini(cli->abi16);
+		mutex_unlock(&cli->mutex);
+		nouveau_cli_fini(cli);
+		kfree(cli);
+	}
+	mutex_unlock(&drm->clients_lock);
+
 	nouveau_cli_fini(&drm->client);
 	nouveau_cli_fini(&drm->master);
 	nvif_parent_dtor(&drm->parent);
+	mutex_destroy(&drm->clients_lock);
 	kfree(drm);
 }
 
@@ -796,7 +817,7 @@ nouveau_drm_device_remove(struct drm_device *dev)
 	struct nvkm_client *client;
 	struct nvkm_device *device;
 
-	drm_dev_unregister(dev);
+	drm_dev_unplug(dev);
 
 	client = nvxx_client(&drm->client.base);
 	device = nvkm_device_find(client->device);
@@ -1090,9 +1111,9 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 
 	fpriv->driver_priv = cli;
 
-	mutex_lock(&drm->client.mutex);
+	mutex_lock(&drm->clients_lock);
 	list_add(&cli->head, &drm->clients);
-	mutex_unlock(&drm->client.mutex);
+	mutex_unlock(&drm->clients_lock);
 
 done:
 	if (ret && cli) {
@@ -1110,6 +1131,16 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct nouveau_cli *cli = nouveau_cli(fpriv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
+	int dev_index;
+
+	/*
+	 * The device is gone, and as it currently stands all clients are
+	 * cleaned up in the removal codepath. In the future this may change
+	 * so that we can support hot-unplugging, but for now we immediately
+	 * return to avoid a double-free situation.
+	 */
+	if (!drm_dev_enter(dev, &dev_index))
+		return;
 
 	pm_runtime_get_sync(dev->dev);
 
@@ -1118,14 +1149,15 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv)
 		nouveau_abi16_fini(cli->abi16);
 	mutex_unlock(&cli->mutex);
 
-	mutex_lock(&drm->client.mutex);
+	mutex_lock(&drm->clients_lock);
 	list_del(&cli->head);
-	mutex_unlock(&drm->client.mutex);
+	mutex_unlock(&drm->clients_lock);
 
 	nouveau_cli_fini(cli);
 	kfree(cli);
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
+	drm_dev_exit(dev_index);
 }
 
 static const struct drm_ioctl_desc
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index ba65f136cf48..b2a970aa9bf4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -139,6 +139,11 @@ struct nouveau_drm {
 
 	struct list_head clients;
 
+	/**
+	 * @clients_lock: Protects access to the @clients list of &struct nouveau_cli.
+	 */
+	struct mutex clients_lock;
+
 	u8 old_pm_cap;
 
 	struct {
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index b0c3422cb01f..9985bfde015a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -162,10 +162,14 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	 */
 
 	mm = get_task_mm(current);
+	if (!mm) {
+		return -EINVAL;
+	}
 	mmap_read_lock(mm);
 
 	if (!cli->svm.svmm) {
 		mmap_read_unlock(mm);
+		mmput(mm);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c
index 704df0f2d1f1..09a112af2f89 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gt215.c
@@ -78,6 +78,6 @@ int
 gt215_ce_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
 	     struct nvkm_engine **pengine)
 {
-	return nvkm_falcon_new_(&gt215_ce, device, type, inst,
+	return nvkm_falcon_new_(&gt215_ce, device, type, -1,
 				(device->chipset != 0xaf), 0x104000, pengine);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index ca75c5f6ecaf..b51d690f375f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -3147,8 +3147,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	WARN_ON(device->chip->ptr.inst & ~((1 << ARRAY_SIZE(device->ptr)) - 1));             \
 	for (j = 0; device->chip->ptr.inst && j < ARRAY_SIZE(device->ptr); j++) {            \
 		if ((device->chip->ptr.inst & BIT(j)) && (subdev_mask & BIT_ULL(type))) {    \
-			int inst = (device->chip->ptr.inst == 1) ? -1 : (j);                 \
-			ret = device->chip->ptr.ctor(device, (type), inst, &device->ptr[j]); \
+			ret = device->chip->ptr.ctor(device, (type), (j), &device->ptr[j]);  \
 			subdev = nvkm_device_subdev(device, (type), (j));                    \
 			if (ret) {                                                           \
 				nvkm_subdev_del(&subdev);                                    \