[PATCH] r/o bind mounts: debugging for missed calls

There have been a few oopses caused by 'struct file's with NULL f_vfsmnts.
There was also a set of potentially missed mnt_want_write()s from
dentry_open() calls.

This patch provides a very simple debugging framework to catch these kinds of
bugs.  It will WARN_ON() them, but should stop us from having any oopses or
mnt_writer count imbalances.

I'm quite convinced that this is a good thing because it found bugs in the
stuff I was working on as soon as I wrote it.

[hch: made it conditional on a debug option.
      But it's still a little bit too ugly]

[hch: merged forced remount r/o fix from Dave and akpm's fix for the fix]

Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Acked-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 23 insertions, 3 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 71efc7000226..7a0a9b872251 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -42,6 +42,7 @@ static inline void file_free_rcu(struct rcu_head *head)
 static inline void file_free(struct file *f)
 {
         percpu_counter_dec(&nr_files);
+        file_check_state(f);
         call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
 
@@ -207,6 +208,7 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
          * that we can do debugging checks at __fput()
          */
         if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+                file_take_write(file);
                 error = mnt_want_write(mnt);
                 WARN_ON(error);
         }
@@ -237,8 +239,13 @@ void drop_file_write_access(struct file *file)
         struct inode *inode = dentry->d_inode;
 
         put_write_access(inode);
-        if (!special_file(inode->i_mode))
-                mnt_drop_write(mnt);
+
+        if (special_file(inode->i_mode))
+                return;
+        if (file_check_writeable(file) != 0)
+                return;
+        mnt_drop_write(mnt);
+        file_release_write(file);
 }
 EXPORT_SYMBOL_GPL(drop_file_write_access);
 
diff --git a/fs/open.c b/fs/open.c
index e58382d57e72..b70e7666bb2c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -806,6 +806,8 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
                 error = __get_file_write_access(inode, mnt);
                 if (error)
                         goto cleanup_file;
+                if (!special_file(inode->i_mode))
+                        file_take_write(f);
         }
 
         f->f_mapping = inode->i_mapping;
@@ -847,8 +849,16 @@ cleanup_all:
         fops_put(f->f_op);
         if (f->f_mode & FMODE_WRITE) {
                 put_write_access(inode);
-                if (!special_file(inode->i_mode))
+                if (!special_file(inode->i_mode)) {
+                        /*
+                         * We don't consider this a real
+                         * mnt_want/drop_write() pair
+                         * because it all happenend right
+                         * here, so just reset the state.
+                         */
+                        file_reset_write(f);
                         mnt_drop_write(mnt);
+                }
         }
         file_kill(f);
         f->f_path.dentry = NULL;
diff --git a/fs/super.c b/fs/super.c
index 01d5c40e9119..1f8f05ede437 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -579,6 +579,9 @@ retry:
                 if (!(f->f_mode & FMODE_WRITE))
                         continue;
                 f->f_mode &= ~FMODE_WRITE;
+                if (file_check_writeable(f) != 0)
+                        continue;
+                file_release_write(f);
                 mnt = mntget(f->f_path.mnt);
                 file_list_unlock();
                 /*