vfs: don't unnecessarily clone write access for writable fds
There's no need for mnt_want_write_file() to increment mnt_writers when
the file is already open for writing, provided that
mnt_drop_write_file() is changed to conditionally decrement it.
We seem to have ended up in the current situation because
mnt_want_write_file() used to be paired with mnt_drop_write(), due to
mnt_drop_write_file() not having been added yet. So originally
mnt_want_write_file() had to always increment mnt_writers.
But later mnt_drop_write_file() was added, and all callers of
mnt_want_write_file() were paired with it. This makes the compatibility
between mnt_want_write_file() and mnt_drop_write() no longer necessary.
Therefore, make __mnt_want_write_file() and __mnt_drop_write_file() skip
incrementing mnt_writers on files already open for writing. This
removes the only caller of mnt_clone_write(), so remove that too.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/namespace.c b/fs/namespace.c
index d2db7df..9f2d94e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -360,50 +360,36 @@ int mnt_want_write(struct vfsmount *m)
EXPORT_SYMBOL_GPL(mnt_want_write);
/**
- * mnt_clone_write - get write access to a mount
- * @mnt: the mount on which to take a write
- *
- * This is effectively like mnt_want_write, except
- * it must only be used to take an extra write reference
- * on a mountpoint that we already know has a write reference
- * on it. This allows some optimisation.
- *
- * After finished, mnt_drop_write must be called as usual to
- * drop the reference.
- */
-int mnt_clone_write(struct vfsmount *mnt)
-{
- /* superblock may be r/o */
- if (__mnt_is_readonly(mnt))
- return -EROFS;
- preempt_disable();
- mnt_inc_writers(real_mount(mnt));
- preempt_enable();
- return 0;
-}
-EXPORT_SYMBOL_GPL(mnt_clone_write);
-
-/**
* __mnt_want_write_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
- * This is like __mnt_want_write, but it takes a file and can
- * do some optimisations if the file is open for write already
+ * This is like __mnt_want_write, but if the file is already open for writing it
+ * skips incrementing mnt_writers (since the open file already has a reference)
+ * and instead only does the check for emergency r/o remounts. This must be
+ * paired with __mnt_drop_write_file.
*/
int __mnt_want_write_file(struct file *file)
{
- if (!(file->f_mode & FMODE_WRITER))
- return __mnt_want_write(file->f_path.mnt);
- else
- return mnt_clone_write(file->f_path.mnt);
+ if (file->f_mode & FMODE_WRITER) {
+ /*
+ * Superblock may have become readonly while there are still
+ * writable fd's, e.g. due to a fs error with errors=remount-ro
+ */
+ if (__mnt_is_readonly(file->f_path.mnt))
+ return -EROFS;
+ return 0;
+ }
+ return __mnt_want_write(file->f_path.mnt);
}
/**
* mnt_want_write_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
- * This is like mnt_want_write, but it takes a file and can
- * do some optimisations if the file is open for write already
+ * This is like mnt_want_write, but if the file is already open for writing it
+ * skips incrementing mnt_writers (since the open file already has a reference)
+ * and instead only does the freeze protection and the check for emergency r/o
+ * remounts. This must be paired with mnt_drop_write_file.
*/
int mnt_want_write_file(struct file *file)
{
@@ -449,7 +435,8 @@ EXPORT_SYMBOL_GPL(mnt_drop_write);
void __mnt_drop_write_file(struct file *file)
{
- __mnt_drop_write(file->f_path.mnt);
+ if (!(file->f_mode & FMODE_WRITER))
+ __mnt_drop_write(file->f_path.mnt);
}
void mnt_drop_write_file(struct file *file)