[PATCH] r/o bind mounts: elevate write count for open()s
This is the first really tricky patch in the series. It elevates the writer
count on a mount each time a non-special file is opened for write.
We used to do this in may_open(), but Miklos pointed out that __dentry_open()
is used as well to create filps. This will cover even those cases, while a
call in may_open() would not have.
There is also an elevated count around the vfs_create() call in open_namei().
See the comments for more details, but we need this to fix a 'create, remount,
fail r/w open()' race.
Some filesystems forego the use of normal vfs calls to create
struct files. Make sure that these users elevate the mnt
writer count because they will get __fput(), and we need
to make sure they're balanced.
Acked-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/open.c b/fs/open.c
index 8111947..e12f170 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -730,6 +730,35 @@
return error;
}
+/*
+ * You have to be very careful that these write
+ * counts get cleaned up in error cases and
+ * upon __fput(). This should probably never
+ * be called outside of __dentry_open().
+ */
+static inline int __get_file_write_access(struct inode *inode,
+ struct vfsmount *mnt)
+{
+ int error;
+ error = get_write_access(inode);
+ if (error)
+ return error;
+ /*
+ * Do not take mount writer counts on
+ * special files since no writes to
+ * the mount itself will occur.
+ */
+ if (!special_file(inode->i_mode)) {
+ /*
+ * Balanced in __fput()
+ */
+ error = mnt_want_write(mnt);
+ if (error)
+ put_write_access(inode);
+ }
+ return error;
+}
+
static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
int flags, struct file *f,
int (*open)(struct inode *, struct file *))
@@ -742,7 +771,7 @@
FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
- error = get_write_access(inode);
+ error = __get_file_write_access(inode, mnt);
if (error)
goto cleanup_file;
}
@@ -784,8 +813,11 @@
cleanup_all:
fops_put(f->f_op);
- if (f->f_mode & FMODE_WRITE)
+ if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
+ if (!special_file(inode->i_mode))
+ mnt_drop_write(mnt);
+ }
file_kill(f);
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;