Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more vfs updates from Al Viro:
 "Assorted VFS fixes and related cleanups (IMO the most interesting in
  that part are f_path-related things and Eric's descriptor-related
  stuff).  UFS regression fixes (it got broken last cycle).  9P fixes.
  fs-cache series, DAX patches, Jan's file_remove_suid() work"

[ I'd say this is much more than "fixes and related cleanups".  The
  file_table locking rule change by Eric Dumazet is a rather big and
  fundamental update even if the patch isn't huge.   - Linus ]

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (49 commits)
  9p: cope with bogus responses from server in p9_client_{read,write}
  p9_client_write(): avoid double p9_free_req()
  9p: forgetting to cancel request on interrupted zero-copy RPC
  dax: bdev_direct_access() may sleep
  block: Add support for DAX reads/writes to block devices
  dax: Use copy_from_iter_nocache
  dax: Add block size note to documentation
  fs/file.c: __fget() and dup2() atomicity rules
  fs/file.c: don't acquire files->file_lock in fd_install()
  fs:super:get_anon_bdev: fix race condition could cause dev exceed its upper limitation
  vfs: avoid creation of inode number 0 in get_next_ino
  namei: make set_root_rcu() return void
  make simple_positive() public
  ufs: use dir_pages instead of ufs_dir_pages()
  pagemap.h: move dir_pages() over there
  remove the pointless include of lglock.h
  fs: cleanup slight list_entry abuse
  xfs: Correctly lock inode when removing suid and file capabilities
  fs: Call security_ops->inode_killpriv on truncate
  fs: Provide function telling whether file_remove_privs() will do anything
  ...

1 files changed, 56 insertions, 21 deletions

diff --git a/fs/file.c b/fs/file.c
index 93c5f89..6c672ad 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -147,6 +147,13 @@ static int expand_fdtable(struct files_struct *files, int nr)
 
 	spin_unlock(&files->file_lock);
 	new_fdt = alloc_fdtable(nr);
+
+	/* make sure all __fd_install() have seen resize_in_progress
+	 * or have finished their rcu_read_lock_sched() section.
+	 */
+	if (atomic_read(&files->count) > 1)
+		synchronize_sched();
+
 	spin_lock(&files->file_lock);
 	if (!new_fdt)
 		return -ENOMEM;
@@ -158,21 +165,14 @@ static int expand_fdtable(struct files_struct *files, int nr)
 		__free_fdtable(new_fdt);
 		return -EMFILE;
 	}
-	/*
-	 * Check again since another task may have expanded the fd table while
-	 * we dropped the lock
-	 */
 	cur_fdt = files_fdtable(files);
-	if (nr >= cur_fdt->max_fds) {
-		/* Continue as planned */
-		copy_fdtable(new_fdt, cur_fdt);
-		rcu_assign_pointer(files->fdt, new_fdt);
-		if (cur_fdt != &files->fdtab)
-			call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
-	} else {
-		/* Somebody else expanded, so undo our attempt */
-		__free_fdtable(new_fdt);
-	}
+	BUG_ON(nr < cur_fdt->max_fds);
+	copy_fdtable(new_fdt, cur_fdt);
+	rcu_assign_pointer(files->fdt, new_fdt);
+	if (cur_fdt != &files->fdtab)
+		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
+	/* coupled with smp_rmb() in __fd_install() */
+	smp_wmb();
 	return 1;
 }
 
@@ -185,21 +185,38 @@ static int expand_fdtable(struct files_struct *files, int nr)
  * The files->file_lock should be held on entry, and will be held on exit.
  */
 static int expand_files(struct files_struct *files, int nr)
+	__releases(files->file_lock)
+	__acquires(files->file_lock)
 {
 	struct fdtable *fdt;
+	int expanded = 0;
 
+repeat:
 	fdt = files_fdtable(files);
 
 	/* Do we need to expand? */
 	if (nr < fdt->max_fds)
-		return 0;
+		return expanded;
 
 	/* Can we expand? */
 	if (nr >= sysctl_nr_open)
 		return -EMFILE;
 
+	if (unlikely(files->resize_in_progress)) {
+		spin_unlock(&files->file_lock);
+		expanded = 1;
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		spin_lock(&files->file_lock);
+		goto repeat;
+	}
+
 	/* All good, so we try */
-	return expand_fdtable(files, nr);
+	files->resize_in_progress = true;
+	expanded = expand_fdtable(files, nr);
+	files->resize_in_progress = false;
+
+	wake_up_all(&files->resize_wait);
+	return expanded;
 }
 
 static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
@@ -256,6 +273,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	atomic_set(&newf->count, 1);
 
 	spin_lock_init(&newf->file_lock);
+	newf->resize_in_progress = false;
+	init_waitqueue_head(&newf->resize_wait);
 	newf->next_fd = 0;
 	new_fdt = &newf->fdtab;
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
@@ -553,11 +572,21 @@ void __fd_install(struct files_struct *files, unsigned int fd,
 		struct file *file)
 {
 	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
+
+	might_sleep();
+	rcu_read_lock_sched();
+
+	while (unlikely(files->resize_in_progress)) {
+		rcu_read_unlock_sched();
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		rcu_read_lock_sched();
+	}
+	/* coupled with smp_wmb() in expand_fdtable() */
+	smp_rmb();
+	fdt = rcu_dereference_sched(files->fdt);
 	BUG_ON(fdt->fd[fd] != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock_sched();
 }
 
 void fd_install(unsigned int fd, struct file *file)
@@ -635,11 +664,17 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
 	struct file *file;
 
 	rcu_read_lock();
+loop:
 	file = fcheck_files(files, fd);
 	if (file) {
-		/* File object ref couldn't be taken */
-		if ((file->f_mode & mask) || !get_file_rcu(file))
+		/* File object ref couldn't be taken.
+		 * dup2() atomicity guarantee is the reason
+		 * we loop to catch the new file (or NULL pointer)
+		 */
+		if (file->f_mode & mask)
 			file = NULL;
+		else if (!get_file_rcu(file))
+			goto loop;
 	}
 	rcu_read_unlock();