drm: Update file owner during use

With the typical model where the display server opens the file descriptor
and then hands it over to the client(*), we were showing stale data in
debugfs.

Fix it by updating the drm_file->pid on ioctl access from a different
process.

The field is also made RCU protected to allow for lockless readers. Update
side is protected with dev->filelist_mutex.

Before:

$ cat /sys/kernel/debug/dri/0/clients
             command   pid dev master a   uid      magic
                Xorg  2344   0   y    y     0          0
                Xorg  2344   0   n    y     0          2
                Xorg  2344   0   n    y     0          3
                Xorg  2344   0   n    y     0          4

After:

$ cat /sys/kernel/debug/dri/0/clients
             command  tgid dev master a   uid      magic
                Xorg   830   0   y    y     0          0
       xfce4-session   880   0   n    y     0          1
               xfwm4   943   0   n    y     0          2
           neverball  1095   0   n    y     0          3

*)
More detailed and historically accurate description of various handover
implementation kindly provided by Emil Velikov:

"""
The traditional model, the server was the orchestrator managing the
primary device node. From the fd, to the master status and
authentication. But looking at the fd alone, this has varied across
the years.

IIRC in the DRI1 days, Xorg (libdrm really) would have a list of open
fd(s) and reuse those whenever needed, DRI2 the client was responsible
for open() themselves and with DRI3 the fd was passed to the client.

Around the inception of DRI3 and systemd-logind, the latter became
another possible orchestrator. Whereby Xorg and Wayland compositors
could ask it for the fd. For various reasons (hysterical and genuine
ones) Xorg has a fallback path going the open(), whereas Wayland
compositors are moving to solely relying on logind... some never had
fallback even.

Over the past few years, more projects have emerged which provide
functionality similar (be that on API level, Dbus, or otherwise) to
systemd-logind.
"""

v2:
 * Fixed typo in commit text and added a fine historical explanation
   from Emil.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230621094824.2348732-1-tvrtko.ursulin@linux.intel.com
Signed-off-by: Christian König <christian.koenig@amd.com>

Author: tursulin

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -958,6 +958,7 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused)
 	list_for_each_entry(file, &dev->filelist, lhead) {
 		struct task_struct *task;
 		struct drm_gem_object *gobj;
+		struct pid *pid;
 		int id;
 
 		/*
@@ -967,8 +968,9 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused)
 		 * Therefore, we need to protect this ->comm access using RCU.
 		 */
 		rcu_read_lock();
-		task = pid_task(file->pid, PIDTYPE_TGID);
-		seq_printf(m, "pid %8d command %s:\n", pid_nr(file->pid),
+		pid = rcu_dereference(file->pid);
+		task = pid_task(pid, PIDTYPE_TGID);
+		seq_printf(m, "pid %8d command %s:\n", pid_nr(pid),
 			   task ? task->comm : "<unknown>");
 		rcu_read_unlock();
 

drivers/gpu/drm/drm_auth.c

@@ -235,7 +235,8 @@ static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
 static int
 drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv)
 {
-	if (file_priv->pid == task_pid(current) && file_priv->was_master)
+	if (file_priv->was_master &&
+	    rcu_access_pointer(file_priv->pid) == task_pid(current))
 		return 0;
 
 	if (!capable(CAP_SYS_ADMIN))

drivers/gpu/drm/drm_debugfs.c

@@ -92,15 +92,17 @@ static int drm_clients_info(struct seq_file *m, void *data)
 	 */
 	mutex_lock(&dev->filelist_mutex);
 	list_for_each_entry_reverse(priv, &dev->filelist, lhead) {
-		struct task_struct *task;
 		bool is_current_master = drm_is_current_master(priv);
+		struct task_struct *task;
+		struct pid *pid;
 
-		rcu_read_lock(); /* locks pid_task()->comm */
-		task = pid_task(priv->pid, PIDTYPE_TGID);
+		rcu_read_lock(); /* Locks priv->pid and pid_task()->comm! */
+		pid = rcu_dereference(priv->pid);
+		task = pid_task(pid, PIDTYPE_TGID);
 		uid = task ? __task_cred(task)->euid : GLOBAL_ROOT_UID;
 		seq_printf(m, "%20s %5d %3d   %c    %c %5d %10u\n",
 			   task ? task->comm : "<unknown>",
-			   pid_vnr(priv->pid),
+			   pid_vnr(pid),
 			   priv->minor->index,
 			   is_current_master ? 'y' : 'n',
 			   priv->authenticated ? 'y' : 'n',

drivers/gpu/drm/drm_file.c

@@ -160,7 +160,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
 
 	/* Get a unique identifier for fdinfo: */
 	file->client_id = atomic64_inc_return(&ident);
-	file->pid = get_pid(task_tgid(current));
+	rcu_assign_pointer(file->pid, get_pid(task_tgid(current)));
 	file->minor = minor;
 
 	/* for compatibility root is always authenticated */
@@ -200,7 +200,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
 		drm_syncobj_release(file);
 	if (drm_core_check_feature(dev, DRIVER_GEM))
 		drm_gem_release(dev, file);
-	put_pid(file->pid);
+	put_pid(rcu_access_pointer(file->pid));
 	kfree(file);
 
 	return ERR_PTR(ret);
@@ -291,7 +291,7 @@ void drm_file_free(struct drm_file *file)
 
 	WARN_ON(!list_empty(&file->event_list));
 
-	put_pid(file->pid);
+	put_pid(rcu_access_pointer(file->pid));
 	kfree(file);
 }
 
@@ -505,6 +505,40 @@ int drm_release(struct inode *inode, struct file *filp)
 }
 EXPORT_SYMBOL(drm_release);
 
+void drm_file_update_pid(struct drm_file *filp)
+{
+	struct drm_device *dev;
+	struct pid *pid, *old;
+
+	/*
+	 * Master nodes need to keep the original ownership in order for
+	 * drm_master_check_perm to keep working correctly. (See comment in
+	 * drm_auth.c.)
+	 */
+	if (filp->was_master)
+		return;
+
+	pid = task_tgid(current);
+
+	/*
+	 * Quick unlocked check since the model is a single handover followed by
+	 * exclusive repeated use.
+	 */
+	if (pid == rcu_access_pointer(filp->pid))
+		return;
+
+	dev = filp->minor->dev;
+	mutex_lock(&dev->filelist_mutex);
+	old = rcu_replace_pointer(filp->pid, pid, 1);
+	mutex_unlock(&dev->filelist_mutex);
+
+	if (pid != old) {
+		get_pid(pid);
+		synchronize_rcu();
+		put_pid(old);
+	}
+}
+
 /**
  * drm_release_noglobal - release method for DRM file
  * @inode: device inode

drivers/gpu/drm/drm_ioctl.c

@@ -776,6 +776,9 @@ long drm_ioctl_kernel(struct file *file, drm_ioctl_t *func, void *kdata,
 	struct drm_device *dev = file_priv->minor->dev;
 	int retcode;
 
+	/* Update drm_file owner if fd was passed along. */
+	drm_file_update_pid(file_priv);
+
 	if (drm_dev_is_unplugged(dev))
 		return -ENODEV;
 

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -1133,7 +1133,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	}
 
 	get_task_comm(tmpname, current);
-	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
+	rcu_read_lock();
+	snprintf(name, sizeof(name), "%s[%d]",
+		 tmpname, pid_nr(rcu_dereference(fpriv->pid)));
+	rcu_read_unlock();
 
 	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) {
 		ret = -ENOMEM;

drivers/gpu/drm/vmwgfx/vmwgfx_gem.c

@@ -232,6 +232,7 @@ static int vmw_debugfs_gem_info_show(struct seq_file *m, void *unused)
 	list_for_each_entry(file, &dev->filelist, lhead) {
 		struct task_struct *task;
 		struct drm_gem_object *gobj;
+		struct pid *pid;
 		int id;
 
 		/*
@@ -241,8 +242,9 @@ static int vmw_debugfs_gem_info_show(struct seq_file *m, void *unused)
 		 * Therefore, we need to protect this ->comm access using RCU.
 		 */
 		rcu_read_lock();
-		task = pid_task(file->pid, PIDTYPE_TGID);
-		seq_printf(m, "pid %8d command %s:\n", pid_nr(file->pid),
+		pid = rcu_dereference(file->pid);
+		task = pid_task(pid, PIDTYPE_TGID);
+		seq_printf(m, "pid %8d command %s:\n", pid_nr(pid),
 			   task ? task->comm : "<unknown>");
 		rcu_read_unlock();
 

include/drm/drm_file.h

@@ -254,8 +254,15 @@ struct drm_file {
 	/** @master_lookup_lock: Serializes @master. */
 	spinlock_t master_lookup_lock;
 
-	/** @pid: Process that opened this file. */
-	struct pid *pid;
+	/**
+	 * @pid: Process that is using this file.
+	 *
+	 * Must only be dereferenced under a rcu_read_lock or equivalent.
+	 *
+	 * Updates are guarded with dev->filelist_mutex and reference must be
+	 * dropped after a RCU grace period to accommodate lockless readers.
+	 */
+	struct pid __rcu *pid;
 
 	/** @client_id: A unique id for fdinfo */
 	u64 client_id;
@@ -418,6 +425,8 @@ static inline bool drm_is_accel_client(const struct drm_file *file_priv)
 	return file_priv->minor->type == DRM_MINOR_ACCEL;
 }
 
+void drm_file_update_pid(struct drm_file *);
+
 int drm_open(struct inode *inode, struct file *filp);
 int drm_open_helper(struct file *filp, struct drm_minor *minor);
 ssize_t drm_read(struct file *filp, char __user *buffer,