introduce __fcheck_files() to fix rcu_dereference_check_fdtable(), kill rcu_my_thread_group_empty()

rcu_dereference_check_fdtable() looks very wrong,

1. rcu_my_thread_group_empty() was added by 844b9a8707f1 "vfs: fix
   RCU-lockdep false positive due to /proc" but it doesn't really
   fix the problem. A CLONE_THREAD (without CLONE_FILES) task can
   hit the same race with get_files_struct().

   And otoh rcu_my_thread_group_empty() can suppress the correct
   warning if the caller is the CLONE_FILES (without CLONE_THREAD)
   task.

2. files->count == 1 check is not really right too. Even if this
   files_struct is not shared it is not safe to access it lockless
   unless the caller is the owner.

   Otoh, this check is sub-optimal. files->count == 0 always means
   it is safe to use it lockless even if files != current->files,
   but put_files_struct() has to take rcu_read_lock(). See the next
   patch.

This patch removes the buggy checks and turns fcheck_files() into
__fcheck_files() which uses rcu_dereference_raw(), the "unshared"
callers, fget_light() and fget_raw_light(), can use it to avoid
the warning from RCU-lockdep.

fcheck_files() is trivially reimplemented as rcu_lockdep_assert()
plus __fcheck_files().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

4 files changed, 23 insertions, 29 deletions

diff --git a/fs/file.c b/fs/file.c
index 4a78f981557a..957cbc09b0db 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -707,7 +707,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
-		file = fcheck_files(files, fd);
+		file = __fcheck_files(files, fd);
 		if (file && (file->f_mode & FMODE_PATH))
 			file = NULL;
 	} else {
@@ -735,7 +735,7 @@ struct file *fget_raw_light(unsigned int fd, int *fput_needed)
 
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
-		file = fcheck_files(files, fd);
+		file = __fcheck_files(files, fd);
 	} else {
 		rcu_read_lock();
 		file = fcheck_files(files, fd);
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 085197bd8812..70e8e21c0a30 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -59,29 +59,36 @@ struct files_struct {
 	struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };
 
-#define rcu_dereference_check_fdtable(files, fdtfd) \
-	(rcu_dereference_check((fdtfd), \
-			       lockdep_is_held(&(files)->file_lock) || \
-			       atomic_read(&(files)->count) == 1 || \
-			       rcu_my_thread_group_empty()))
-
-#define files_fdtable(files) \
-		(rcu_dereference_check_fdtable((files), (files)->fdt))
-
 struct file_operations;
 struct vfsmount;
 struct dentry;
 
 extern void __init files_defer_init(void);
 
-static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd)
+#define rcu_dereference_check_fdtable(files, fdtfd) \
+	rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock))
+
+#define files_fdtable(files) \
+	rcu_dereference_check_fdtable((files), (files)->fdt)
+
+/*
+ * The caller must ensure that fd table isn't shared or hold rcu or file lock
+ */
+static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd)
 {
-	struct file * file = NULL;
-	struct fdtable *fdt = files_fdtable(files);
+	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 
 	if (fd < fdt->max_fds)
-		file = rcu_dereference_check_fdtable(files, fdt->fd[fd]);
-	return file;
+		return rcu_dereference_raw(fdt->fd[fd]);
+	return NULL;
+}
+
+static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd)
+{
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&files->file_lock),
+			   "suspicious rcu_dereference_check() usage");
+	return __fcheck_files(files, fd);
 }
 
 /*
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 39cbb889e20d..a2482cf90b6b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -448,8 +448,6 @@ static inline int rcu_read_lock_sched_held(void)
 
 #ifdef CONFIG_PROVE_RCU
 
-extern int rcu_my_thread_group_empty(void);
-
 /**
  * rcu_lockdep_assert - emit lockdep splat if specified condition not met
  * @c: condition to check
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff89e2b..a3596c8ec9e4 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -195,17 +195,6 @@ void wait_rcu_gp(call_rcu_func_t crf)
 }
 EXPORT_SYMBOL_GPL(wait_rcu_gp);
 
-#ifdef CONFIG_PROVE_RCU
-/*
- * wrapper function to avoid #include problems.
- */
-int rcu_my_thread_group_empty(void)
-{
-	return thread_group_empty(current);
-}
-EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 static inline void debug_init_rcu_head(struct rcu_head *head)
 {