The patch titled
r/o bind mounts: debugging for missed calls
has been added to the -mm tree. Its filename is
r-o-bind-mounts-debugging-for-missed-calls.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: r/o bind mounts: debugging for missed calls
From: Dave Hansen <haveblue@xxxxxxxxxx>
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@xxxxxxxxxx>
Acked-by: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/file_table.c | 11 +++++++--
fs/open.c | 12 +++++++++-
fs/super.c | 3 ++
include/linux/fs.h | 49 +++++++++++++++++++++++++++++++++++++++++++
lib/Kconfig.debug | 10 ++++++++
5 files changed, 82 insertions(+), 3 deletions(-)
diff -puN fs/file_table.c~r-o-bind-mounts-debugging-for-missed-calls fs/file_table.c
--- a/fs/file_table.c~r-o-bind-mounts-debugging-for-missed-calls
+++ a/fs/file_table.c
@@ -42,6 +42,7 @@ static inline void file_free_rcu(struct
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
* 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
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 -puN fs/open.c~r-o-bind-mounts-debugging-for-missed-calls fs/open.c
--- a/fs/open.c~r-o-bind-mounts-debugging-for-missed-calls
+++ a/fs/open.c
@@ -806,6 +806,8 @@ static struct file *__dentry_open(struct
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 -puN fs/super.c~r-o-bind-mounts-debugging-for-missed-calls fs/super.c
--- a/fs/super.c~r-o-bind-mounts-debugging-for-missed-calls
+++ a/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 = f->f_path.mnt;
file_list_unlock();
/*
diff -puN include/linux/fs.h~r-o-bind-mounts-debugging-for-missed-calls include/linux/fs.h
--- a/include/linux/fs.h~r-o-bind-mounts-debugging-for-missed-calls
+++ a/include/linux/fs.h
@@ -776,6 +776,9 @@ static inline int ra_has_index(struct fi
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
diff -puN lib/Kconfig.debug~r-o-bind-mounts-debugging-for-missed-calls lib/Kconfig.debug
--- a/lib/Kconfig.debug~r-o-bind-mounts-debugging-for-missed-calls
+++ a/lib/Kconfig.debug
@@ -434,6 +434,16 @@ config DEBUG_VM
If unsure, say N.
+config DEBUG_WRITECOUNT
+ bool "Debug filesystem writers count"
+ depends on DEBUG_KERNEL
+ help
+ Enable this to catch wrong use of the writers count in struct
+ vfsmount. This will increase the size of each file struct by
+ 32 bits.
+
+ If unsure, say N.
+
config DEBUG_LIST
bool "Debug linked list manipulation"
depends on DEBUG_KERNEL
_
Patches currently in -mm which might be from haveblue@xxxxxxxxxx are
enable-hotplug-memory-remove-for-ppc64.patch
reiserfs-eliminate-private-use-of-struct-file-in-xattr.patch
hppfs-pass-vfsmount-to-dentry_open.patch
check-for-null-vfsmount-in-dentry_open.patch
fix-up-new-filp-allocators.patch
do-namei_flags-calculation-inside-open_namei.patch
merge-open_namei-and-do_filp_open.patch
r-o-bind-mounts-stub-functions.patch
r-o-bind-mounts-create-helper-to-drop-file-write-access.patch
r-o-bind-mounts-drop-write-during-emergency-remount.patch
r-o-bind-mounts-elevate-write-count-for-vfs_rmdir.patch
r-o-bind-mounts-elevate-write-count-for-callers-of-vfs_mkdir.patch
r-o-bind-mounts-elevate-mnt_writers-for-unlink-callers.patch
r-o-bind-mounts-elevate-write-count-for-xattr_permission-callers.patch
r-o-bind-mounts-elevate-write-count-for-ncp_ioctl.patch
r-o-bind-mounts-write-counts-for-time-functions.patch
r-o-bind-mounts-elevate-write-count-for-do_utimes.patch
r-o-bind-mounts-write-count-for-file_update_time.patch
r-o-bind-mounts-write-counts-for-link-symlink.patch
r-o-bind-mounts-elevate-write-count-for-ioctls.patch
r-o-bind-mounts-elevate-write-count-for-opens.patch
r-o-bind-mounts-get-write-access-for-vfs_rename-callers.patch
r-o-bind-mounts-elevate-write-count-for-chmod-chown-callers.patch
r-o-bind-mounts-write-counts-for-truncate.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-check-mnt-instead-of-superblock-directly.patch
r-o-bind-mounts-get-callers-of-vfs_mknod-create.patch
r-o-bind-mounts-track-numbers-of-writers-to-mounts.patch
r-o-bind-mounts-honor-mount-writer-counts-at-remount.patch
r-o-bind-mounts-debugging-for-missed-calls.patch
reiser4.patch
page-owner-tracking-leak-detector.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
