This patch creates a way for fsnotify groups to attach marks to inodes.
These marks have little meaning to the generic fsnotify infrastructure
and thus their meaning should be interpreted by the group that attached
them to the inode's list.
dnotify and inotify will make use of these markings to indicate which
inodes are of interest to their respective groups. But this implementation
has the useful property that in the future other listeners could actually
use the marks for the exact opposite reason, aka to indicate which inodes
it had NO interest in.
Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
fsnotify is a backend for filesystem notification. fsnotify does
not provide any userspace interface but does provide the basis
needed for other notification schemes such as dnotify. fsnotify
can be extended to be the backend for inotify or the upcoming
fanotify. fsnotify provides a mechanism for "groups" to register for
some set of filesystem events and to then deliver those events to
those groups for processing.
fsnotify has a number of benefits, the first being actually shrinking the size
of an inode. Before fsnotify to support both dnotify and inotify an inode had
unsigned long i_dnotify_mask; /* Directory notify events */
struct dnotify_struct *i_dnotify; /* for directory notifications */
struct list_head inotify_watches; /* watches on this inode */
struct mutex inotify_mutex; /* protects the watches list
But with fsnotify this same functionallity (and more) is done with just
__u32 i_fsnotify_mask; /* all events for this inode */
struct hlist_head i_fsnotify_mark_entries; /* marks on this inode */
That's right, inotify, dnotify, and fanotify all in 64 bits. We used that
much space just in inotify_watches alone, before this patch set.
fsnotify object lifetime and locking is MUCH better than what we have today.
inotify locking is incredibly complex. See 8f7b0ba1c8 as an example of
what's been busted since inception. inotify needs to know internal semantics
of superblock destruction and unmounting to function. The inode pinning and
vfs contortions are horrible.
no fsnotify implementers do allocation under locks. This means things like
f04b30de3 which (due to an overabundance of caution) changes GFP_KERNEL to
GFP_NOFS can be reverted. There are no longer any allocation rules when using
or implementing your own fsnotify listener.
fsnotify paves the way for fanotify. In brief fanotify is a notification
mechanism that delivers the lisener both an 'event' and an open file descriptor
to the object in question. This means that fanotify is pathname agnostic.
Some on lkml may not care for the original companies or users that pushed for
TALPA, but fanotify was designed with flexibility and input for other users in
mind. The readahead group expressed interest in fanotify as it could be used
to profile disk access on boot without breaking the audit system. The desktop
search groups have also expressed interest in fanotify as it solves a number
of the race conditions and problems present with managing inotify when more
than a limited number of specific files are of interest. fanotify can provide
for a userspace access control system which makes it a clean interface for AV
vendors to hook without trying to do binary patching on the syscall table,
LSM, and everywhere else they do their things today. With this patch series
fanotify can be implemented in less than 1200 lines of easy to review code.
Almost all of which is the socket based user interface.
This patch series builds fsnotify to the point that it can implement
dnotify and inotify_user. Patches exist and will be sent soon after
acceptance to finish the in kernel inotify conversion (audit) and implement
fanotify.
Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
There is what we believe to be a false positive reported by lockdep.
inotify_inode_queue_event() => take inotify_mutex => kernel_event() =>
kmalloc() => SLOB => alloc_pages_node() => page reclaim => slab reclaim =>
dcache reclaim => inotify_inode_is_dead => take inotify_mutex => deadlock
The plan is to fix this via lockdep annotation, but that is proving to be
quite involved.
The patch flips the allocation over to GFP_NFS to shut the warning up, for
the 2.6.30 release.
Hopefully we will fix this for real in 2.6.31. I'll queue a patch in -mm
to switch it back to GFP_KERNEL so we don't forget.
=================================
[ INFO: inconsistent lock state ]
2.6.30-rc2-next-20090417 #203
---------------------------------
inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
kswapd0/380 [HC0[0]:SC0[0]:HE1:SE1] takes:
(&inode->inotify_mutex){+.+.?.}, at: [<ffffffff8112f1b5>] inotify_inode_is_dead+0x35/0xb0
{RECLAIM_FS-ON-W} state was registered at:
[<ffffffff81079188>] mark_held_locks+0x68/0x90
[<ffffffff810792a5>] lockdep_trace_alloc+0xf5/0x100
[<ffffffff810f5261>] __kmalloc_node+0x31/0x1e0
[<ffffffff81130652>] kernel_event+0xe2/0x190
[<ffffffff81130826>] inotify_dev_queue_event+0x126/0x230
[<ffffffff8112f096>] inotify_inode_queue_event+0xc6/0x110
[<ffffffff8110444d>] vfs_create+0xcd/0x140
[<ffffffff8110825d>] do_filp_open+0x88d/0xa20
[<ffffffff810f6b68>] do_sys_open+0x98/0x140
[<ffffffff810f6c50>] sys_open+0x20/0x30
[<ffffffff8100c272>] system_call_fastpath+0x16/0x1b
[<ffffffffffffffff>] 0xffffffffffffffff
irq event stamp: 690455
hardirqs last enabled at (690455): [<ffffffff81564fe4>] _spin_unlock_irqrestore+0x44/0x80
hardirqs last disabled at (690454): [<ffffffff81565372>] _spin_lock_irqsave+0x32/0xa0
softirqs last enabled at (690178): [<ffffffff81052282>] __do_softirq+0x202/0x220
softirqs last disabled at (690157): [<ffffffff8100d50c>] call_softirq+0x1c/0x50
other info that might help us debug this:
2 locks held by kswapd0/380:
#0: (shrinker_rwsem){++++..}, at: [<ffffffff810d0bd7>] shrink_slab+0x37/0x180
#1: (&type->s_umount_key#17){++++..}, at: [<ffffffff8110cfbf>] shrink_dcache_memory+0x11f/0x1e0
stack backtrace:
Pid: 380, comm: kswapd0 Not tainted 2.6.30-rc2-next-20090417 #203
Call Trace:
[<ffffffff810789ef>] print_usage_bug+0x19f/0x200
[<ffffffff81018bff>] ? save_stack_trace+0x2f/0x50
[<ffffffff81078f0b>] mark_lock+0x4bb/0x6d0
[<ffffffff810799e0>] ? check_usage_forwards+0x0/0xc0
[<ffffffff8107b142>] __lock_acquire+0xc62/0x1ae0
[<ffffffff810f478c>] ? slob_free+0x10c/0x370
[<ffffffff8107c0a1>] lock_acquire+0xe1/0x120
[<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
[<ffffffff81562d43>] mutex_lock_nested+0x63/0x420
[<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
[<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
[<ffffffff81012fe9>] ? sched_clock+0x9/0x10
[<ffffffff81077165>] ? lock_release_holdtime+0x35/0x1c0
[<ffffffff8112f1b5>] inotify_inode_is_dead+0x35/0xb0
[<ffffffff8110c9dc>] dentry_iput+0xbc/0xe0
[<ffffffff8110cb23>] d_kill+0x33/0x60
[<ffffffff8110ce23>] __shrink_dcache_sb+0x2d3/0x350
[<ffffffff8110cffa>] shrink_dcache_memory+0x15a/0x1e0
[<ffffffff810d0cc5>] shrink_slab+0x125/0x180
[<ffffffff810d1540>] kswapd+0x560/0x7a0
[<ffffffff810ce160>] ? isolate_pages_global+0x0/0x2c0
[<ffffffff81065a30>] ? autoremove_wake_function+0x0/0x40
[<ffffffff8107953d>] ? trace_hardirqs_on+0xd/0x10
[<ffffffff810d0fe0>] ? kswapd+0x0/0x7a0
[<ffffffff8106555b>] kthread+0x5b/0xa0
[<ffffffff8100d40a>] child_rip+0xa/0x20
[<ffffffff8100cdd0>] ? restore_args+0x0/0x30
[<ffffffff81065500>] ? kthread+0x0/0xa0
[<ffffffff8100d400>] ? child_rip+0x0/0x20
[eparis@redhat.com: fix audit too]
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
To be on the safe side, it should be less fragile to exclude I_NEW inodes
from inode list scans by default (unless there is an important reason to
have them).
Normally they will get excluded (eg. by zero refcount or writecount etc),
however it is a bit fragile for list walkers to know exactly what parts of
the inode state is set up and valid to test when in I_NEW. So along these
lines, move I_NEW checks upward as well (sometimes taking I_FREEING etc
checks with them too -- this shouldn't be a problem should it?)
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
If userspace supplies an invalid pointer to a read() of an inotify
instance, the inotify device's event list mutex is unlocked twice.
This causes an unbalance which effectively leaves the data structure
unprotected, and we can trigger oopses by accessing the inotify
instance from different tasks concurrently.
The best fix (contributed largely by Linus) is a total rewrite
of the function in question:
On Thu, Jan 22, 2009 at 7:05 AM, Linus Torvalds wrote:
> The thing to notice is that:
>
> - locking is done in just one place, and there is no question about it
> not having an unlock.
>
> - that whole double-while(1)-loop thing is gone.
>
> - use multiple functions to make nesting and error handling sane
>
> - do error testing after doing the things you always need to do, ie do
> this:
>
> mutex_lock(..)
> ret = function_call();
> mutex_unlock(..)
>
> .. test ret here ..
>
> instead of doing conditional exits with unlocking or freeing.
>
> So if the code is written in this way, it may still be buggy, but at least
> it's not buggy because of subtle "forgot to unlock" or "forgot to free"
> issues.
>
> This _always_ unlocks if it locked, and it always frees if it got a
> non-error kevent.
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Robert Love <rlove@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The problems lie in the types used for some inotify interfaces, both at the kernel level and at the glibc level. This mail addresses the kernel problem. I will follow up with some suggestions for glibc changes.
For the sys_inotify_rm_watch() interface, the type of the 'wd' argument is
currently 'u32', it should be '__s32' . That is Robert's suggestion, and
is consistent with the other declarations of watch descriptors in the
kernel source, in particular, the inotify_event structure in
include/linux/inotify.h:
struct inotify_event {
__s32 wd; /* watch descriptor */
__u32 mask; /* watch mask */
__u32 cookie; /* cookie to synchronize two events */
__u32 len; /* length (including nulls) of name */
char name[0]; /* stub for possible name */
};
The patch makes the changes needed for inotify_rm_watch().
Signed-off-by: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Robert Love <rlove@google.com>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Creating a generic filesystem notification interface, fsnotify, which will be
used by inotify, dnotify, and eventually fanotify is really starting to
clutter the fs directory. This patch simply moves inotify and dnotify into
fs/notify/inotify and fs/notify/dnotify respectively to make both current fs/
and future notification tidier.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
