This patch adds two function mnt_want_write() and
mnt_drop_write(). These are used like a lock pair around
and fs operations that might cause a write to the filesystem.
Before these can become useful, we must first cover each
place in the VFS where writes are performed with a
want/drop pair. When that is complete, we can actually
introduce code that will safely check the counts before
allowing r/w<->r/o transitions to occur.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
---
lxc-dave/fs/namespace.c | 46 +++++++++++++++++++++++++++++++++++++++++
lxc-dave/include/linux/mount.h | 3 ++
2 files changed, 49 insertions(+)
diff -puN fs/namespace.c~add-vfsmount-writer-count fs/namespace.c
--- lxc/fs/namespace.c~add-vfsmount-writer-count 2007-09-17 09:43:57.000000000 -0700
+++ lxc-dave/fs/namespace.c 2007-09-17 09:43:57.000000000 -0700
@@ -80,6 +80,52 @@ struct vfsmount *alloc_vfsmnt(const char
return mnt;
}
+/*
+ * Most r/o checks on a fs are for operations that take
+ * discrete amounts of time, like a write() or unlink().
+ * We must keep track of when those operations start
+ * (for permission checks) and when they end, so that
+ * we can determine when writes are able to occur to
+ * a filesystem.
+ */
+/*
+ * This tells the low-level filesystem that a write is
+ * about to be performed to it, and makes sure that
+ * writes are allowed before returning success. When
+ * the write operation is finished, mnt_drop_write()
+ * must be called. This is effectively a refcount.
+ */
+int mnt_want_write(struct vfsmount *mnt)
+{
+ if (__mnt_is_readonly(mnt))
+ return -EROFS;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mnt_want_write);
+
+/*
+ * Tells the low-level filesystem that we are done
+ * performing a write to it. Must be matched with
+ * mnt_want_write() call above.
+ */
+void mnt_drop_write(struct vfsmount *mnt)
+{
+}
+EXPORT_SYMBOL_GPL(mnt_drop_write);
+
+/*
+ * This shouldn't be used directly ouside of the VFS.
+ * It does not guarantee that the filesystem will stay
+ * r/w, just that it is right *now*e
+ * mnt_want/drop_write() will _keep_ the filesystem
+ * r/w.
+ */
+int __mnt_is_readonly(struct vfsmount *mnt)
+{
+ return (mnt->mnt_sb->s_flags & MS_RDONLY);
+}
+EXPORT_SYMBOL_GPL(__mnt_is_readonly);
+
int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
{
mnt->mnt_sb = sb;
diff -puN include/linux/mount.h~add-vfsmount-writer-count include/linux/mount.h
--- lxc/include/linux/mount.h~add-vfsmount-writer-count 2007-09-17 09:43:57.000000000 -0700
+++ lxc-dave/include/linux/mount.h 2007-09-17 09:43:57.000000000 -0700
@@ -74,9 +74,12 @@ static inline struct vfsmount *mntget(st
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)
{
_
-
