Something has changed in the core kernel such that we now get concurrent
inode write outs, one e.g via pdflush and one via sys_sync or whatever.
This causes a nasty deadlock in ntfs. The only clean solution
unfortunately requires a minor vfs api extension.
First the deadlock analysis:
Prerequisive knowledge: NTFS has a file $MFT (inode 0) loaded at mount
time. The NTFS driver uses the page cache for storing the file contents as
usual. More interestingly this file contains the table of on-disk inodes
as a sequence of MFT_RECORDs. Thus NTFS driver accesses the on-disk inodes
by accessing the MFT_RECORDs in the page cache pages of the loaded inode
$MFT.
The situation: VFS inode X on a mounted ntfs volume is dirty. For same
inode X, the ntfs_inode is dirty and thus corresponding on-disk inode,
which is as explained above in a dirty PAGE_CACHE_PAGE belonging to the
table of inodes ($MFT, inode 0).
What happens:
Process 1: sys_sync()/umount()/whatever... calls __sync_single_inode() for
$MFT -> do_writepages() -> write_page for the dirty page containing the
on-disk inode X, the page is now locked -> ntfs_write_mst_block() which
clears PageUptodate() on the page to prevent anyone else getting hold of it
whilst it does the write out (this is necessary as the on-disk inode needs
"fixups" applied before the write to disk which are removed again after the
write and PageUptodate is then set again). It then analyses the page
looking for dirty on-disk inodes and when it finds one it calls
ntfs_may_write_mft_record() to see if it is safe to write this on-disk
inode. This then calls ilookup5() to check if the corresponding VFS inode
is in icache(). This in turn calls ifind() which waits on the inode lock
via wait_on_inode whilst holding the global inode_lock.
Process 2: pdflush results in a call to __sync_single_inode for the same
VFS inode X on the ntfs volume. This locks the inode (I_LOCK) then calls
write-inode -> ntfs_write_inode -> map_mft_record() -> read_cache_page() of
the page (in page cache of table of inodes $MFT, inode 0) containing the
on-disk inode. This page has PageUptodate() clear because of Process 1
(see above) so read_cache_page() blocks when tries to take the page lock
for the page so it can call ntfs_read_page().
Thus Process 1 is holding the page lock on the page containing the on-disk
inode X and it is waiting on the inode X to be unlocked in ifind() so it
can write the page out and then unlock the page.
And Process 2 is holding the inode lock on inode X and is waiting for the
page to be unlocked so it can call ntfs_readpage() or discover that
Process 1 set PageUptodate() again and use the page.
Thus we have a deadlock due to ifind() waiting on the inode lock.
The only sensible solution: NTFS does not care whether the VFS inode is
locked or not when it calls ilookup5() (it doesn't use the VFS inode at
all, it just uses it to find the corresponding ntfs_inode which is of
course attached to the VFS inode (both are one single struct); and it uses
the ntfs_inode which is subject to its own locking so I_LOCK is irrelevant)
hence we want a modified ilookup5_nowait() which is the same as ilookup5()
but it does not wait on the inode lock.
Without such functionality I would have to keep my own ntfs_inode cache in
the NTFS driver just so I can find ntfs_inodes independent of their VFS
inodes which would be slow, memory and cpu cycle wasting, and incredibly
stupid given the icache already exists in the VFS.
Below is a patch that does the ilookup5_nowait() implementation in
fs/inode.c and exports it.
ilookup5_nowait.diff:
Introduce ilookup5_nowait() which is basically the same as ilookup5() but
it does not wait on the inode's lock (i.e. it omits the wait_on_inode()
done in ifind()).
This is needed to avoid a nasty deadlock in NTFS.
Signed-off-by: Anton Altaparmakov <aia21@cantab.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Bug symptoms
~~~~~~~~~~~~
For the same inode VFS calls read_inode() twice and doesn't call
clear_inode() between the two read_inode() invocations.
Bug description
~~~~~~~~~~~~~~~
Suppose we have an inode which has zero reference count but is still in
the inode cache. Suppose kswapd invokes shrink_icache_memory() to free
some RAM. In prune_icache() inodes are removed from i_hash. prune_icache
() is then going to call clear_inode(), but drops the inode_lock
spinlock before this. If in this moment another task calls iget() for an
inode which was just removed from i_hash by prune_icache(), then iget()
invokes read_inode() for this inode, because it is *already removed*
from i_hash.
The end result is: we call iget(#N) then iput(#N); inode #N has zero
i_count now and is in the inode cache; kswapd starts. kswapd removes the
inode #N from i_hash ans is preempted; we call iget(#N) again;
read_inode() is invoked as the result; but we expect clear_inode()
before.
Fix
~~~~~~~
To fix the bug I remove inodes from i_hash later, when clear_inode() is
actually called. I remove them from i_hash under spinlock protection.
Since the i_state is set to I_FREEING, it is safe to do this. The others
will sleep waiting for the inode state change.
I also postpone removing inodes from i_sb_list. It is not compulsory to
do so but I do it for readability reasons. Inodes are added/removed to
the lists together everywhere in the code and there is no point to
change this rule. This is harmless because the only user of i_sb_list
which somehow may interfere with me (invalidate_list()) is excluded by
the iprune_sem mutex.
The same race is possible in invalidate_list() so I do the same for it.
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch fixes queer behavior in __wait_on_freeing_inode().
If I_LOCK was not set it called yield(), effectively busy waiting for the
removal of the inode from the hash. This change was introduced within
"[PATCH] eliminate inode waitqueue hashtable" Changeset 1.1938.166.16 last
october by wli.
The solution is to restore the old behavior, of unconditionally waiting on
the waitqueue. It doesn't matter if I_LOCK is not set initally, the task
will go to sleep, and wake up when wake_up_inode() is called from
generic_delete_inode() after removing the inode from the hash chain.
Comment is also updated to better reflect current behavior.
This condition is very hard to trigger normally (simultaneous clear_inode()
with iget()) so probably only heavy stress testing can reveal any change of
behavior.
Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
OCFS2 wants to mark an inode which has been orphaned by another node so
that during final iput it takes the correct path through the VFS and can
pass through the OCFS2 delete_inode callback. Since i_nlink can get out of
date with other nodes, the best way I see to accomplish this is by clearing
i_nlink on those inodes at drop_inode time. Other than this small amount
of work, nothing different needs to happen, so I think it would be cleanest
to be able to just call generic_drop_inode at the end of the OCFS2
drop_inode callback.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Based on analysis and a patch from Russ Weight <rweight@us.ibm.com>
There is a race condition that can occur if an inode is allocated and then
released (using iput) during the ->fill_super functions. The race
condition is between kswapd and mount.
For most filesystems this can only happen in an error path when kswapd is
running concurrently. For isofs, however, the error can occur in a more
common code path (which is how the bug was found).
The logic here is "we want final iput() to free inode *now* instead of
letting it sit in cache if fs is going down or had not quite come up". The
problem is with kswapd seeing such inodes in the middle of being killed and
happily taking over.
The clean solution would be to tell kswapd to leave those inodes alone and
let our final iput deal with them. I.e. add a new flag
(I_FORCED_FREEING), set it before write_inode_now() there and make
prune_icache() leave those alone.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The only caller that ever sets it can call fsync_bdev itself easily. Also
update some comments.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: <viro@parcelfarce.linux.theplanet.co.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This makes sure that reclaimable buffer headers and reclaimable inodes
are accounted properly during the overcommit checks.
Signed-off-by: Andrea Arcangeli <andrea@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Anton Altaparmakov