Merge branch 'ro-bind.b6' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'ro-bind.b6' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (24 commits)
  [PATCH] r/o bind mounts: debugging for missed calls
  [PATCH] r/o bind mounts: honor mount writer counts at remount
  [PATCH] r/o bind mounts: track numbers of writers to mounts
  [PATCH] r/o bind mounts: check mnt instead of superblock directly
  [PATCH] r/o bind mounts: elevate count for xfs timestamp updates
  [PATCH] r/o bind mounts: make access() use new r/o helper
  [PATCH] r/o bind mounts: write counts for truncate()
  [PATCH] r/o bind mounts: elevate write count for chmod/chown callers
  [PATCH] r/o bind mounts: elevate write count for open()s
  [PATCH] r/o bind mounts: elevate write count for ioctls()
  [PATCH] r/o bind mounts: write count for file_update_time()
  [PATCH] r/o bind mounts: elevate write count for do_utimes()
  [PATCH] r/o bind mounts: write counts for touch_atime()
  [PATCH] r/o bind mounts: elevate write count for ncp_ioctl()
  [PATCH] r/o bind mounts: elevate write count for xattr_permission() callers
  [PATCH] r/o bind mounts: get write access for vfs_rename() callers
  [PATCH] r/o bind mounts: write counts for link/symlink
  [PATCH] r/o bind mounts: get callers of vfs_mknod/create/mkdir()
  [PATCH] r/o bind mounts: elevate write count for rmdir and unlink.
  [PATCH] r/o bind mounts: drop write during emergency remount
  ...

3 files changed, 63 insertions, 1 deletions

diff --git a/include/linux/file.h b/include/linux/file.h
index 7239baac81a9..653477021e4c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -61,6 +61,7 @@ extern struct kmem_cache *filp_cachep;
 
 extern void __fput(struct file *);
 extern void fput(struct file *);
+extern void drop_file_write_access(struct file *file);
 
 struct file_operations;
 struct vfsmount;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b84b848431f2..d1eeea669d2c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -776,6 +776,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
+#define FILE_MNT_WRITE_TAKEN	1
+#define FILE_MNT_WRITE_RELEASED	2
+
 struct file {
 	/*
 	 * fu_list becomes invalid after file_free is called and queued via
@@ -810,6 +813,9 @@ struct file {
 	spinlock_t		f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
+#ifdef CONFIG_DEBUG_WRITECOUNT
+	unsigned long f_mnt_write_state;
+#endif
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);
@@ -818,6 +824,49 @@ extern spinlock_t files_lock;
 #define get_file(x)	atomic_inc(&(x)->f_count)
 #define file_count(x)	atomic_read(&(x)->f_count)
 
+#ifdef CONFIG_DEBUG_WRITECOUNT
+static inline void file_take_write(struct file *f)
+{
+	WARN_ON(f->f_mnt_write_state != 0);
+	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
+}
+static inline void file_release_write(struct file *f)
+{
+	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
+}
+static inline void file_reset_write(struct file *f)
+{
+	f->f_mnt_write_state = 0;
+}
+static inline void file_check_state(struct file *f)
+{
+	/*
+	 * At this point, either both or neither of these bits
+	 * should be set.
+	 */
+	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
+	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
+}
+static inline int file_check_writeable(struct file *f)
+{
+	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
+		return 0;
+	printk(KERN_WARNING "writeable file with no "
+			    "mnt_want_write()\n");
+	WARN_ON(1);
+	return -EINVAL;
+}
+#else /* !CONFIG_DEBUG_WRITECOUNT */
+static inline void file_take_write(struct file *filp) {}
+static inline void file_release_write(struct file *filp) {}
+static inline void file_reset_write(struct file *filp) {}
+static inline void file_check_state(struct file *filp) {}
+static inline int file_check_writeable(struct file *filp)
+{
+	return 0;
+}
+#endif /* CONFIG_DEBUG_WRITECOUNT */
+
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
@@ -1735,7 +1784,8 @@ extern struct file *create_read_pipe(struct file *f);
 extern struct file *create_write_pipe(void);
 extern void free_write_pipe(struct file *);
 
-extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
+extern struct file *do_filp_open(int dfd, const char *pathname,
+		int open_flag, int mode);
 extern int may_open(struct nameidata *, int, int);
 
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 5ee2df217cdf..d6600e3f7e45 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/list.h>
+#include <linux/nodemask.h>
 #include <linux/spinlock.h>
 #include <asm/atomic.h>
 
@@ -28,8 +29,10 @@ struct mnt_namespace;
 #define MNT_NOATIME	0x08
 #define MNT_NODIRATIME	0x10
 #define MNT_RELATIME	0x20
+#define MNT_READONLY	0x40	/* does the user want this to be r/o? */
 
 #define MNT_SHRINKABLE	0x100
+#define MNT_IMBALANCED_WRITE_COUNT	0x200 /* just for debugging */
 
 #define MNT_SHARED	0x1000	/* if the vfsmount is a shared mount */
 #define MNT_UNBINDABLE	0x2000	/* if the vfsmount is a unbindable mount */
@@ -62,6 +65,11 @@ struct vfsmount {
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
 	int mnt_ghosts;
+	/*
+	 * This value is not stable unless all of the mnt_writers[] spinlocks
+	 * are held, and all mnt_writer[]s on this mount have 0 as their ->count
+	 */
+	atomic_t __mnt_writers;
 };
 
 static inline struct vfsmount *mntget(struct vfsmount *mnt)
@@ -71,9 +79,12 @@ static inline struct vfsmount *mntget(struct vfsmount *mnt)
 	return mnt;
 }
 
+extern int mnt_want_write(struct vfsmount *mnt);
+extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mntput_no_expire(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
 extern void mnt_unpin(struct vfsmount *mnt);
+extern int __mnt_is_readonly(struct vfsmount *mnt);
 
 static inline void mntput(struct vfsmount *mnt)
 {