Nilfs2 eventually hangs in a stress test with fsstress program. This
issue was caused by the following deadlock over I_SYNC flag between
nilfs_segctor_thread() and writeback_sb_inodes():
nilfs_segctor_thread()
nilfs_segctor_thread_construct()
nilfs_segctor_unlock()
nilfs_dispose_list()
iput()
iput_final()
evict()
inode_wait_for_writeback() * wait for I_SYNC flag
writeback_sb_inodes()
* set I_SYNC flag on inode->i_state
__writeback_single_inode()
do_writepages()
nilfs_writepages()
nilfs_construct_dsync_segment()
nilfs_segctor_sync()
* wait for completion of segment constructor
inode_sync_complete()
* clear I_SYNC flag after __writeback_single_inode() completed
writeback_sb_inodes() calls do_writepages() for dirty inodes after
setting I_SYNC flag on inode->i_state. do_writepages() in turn calls
nilfs_writepages(), which can run segment constructor and wait for its
completion. On the other hand, segment constructor calls iput(), which
can call evict() and wait for the I_SYNC flag on
inode_wait_for_writeback().
Since segment constructor doesn't know when I_SYNC will be set, it
cannot know whether iput() will block or not unless inode->i_nlink has a
non-zero count. We can prevent evict() from being called in iput() by
implementing sop->drop_inode(), but it's not preferable to leave inodes
with i_nlink == 0 for long periods because it even defers file
truncation and inode deallocation. So, this instead resolves the
deadlock by calling iput() asynchronously with a workqueue for inodes
with i_nlink == 0.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Tested-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Support for fdatasync() has been implemented in NILFS2 for a long time,
but whenever the corresponding inode is dirty the implementation falls
back to a full-flegded sync(). Since every write operation has to
update the modification time of the file, the inode will almost always
be dirty and fdatasync() will fall back to sync() most of the time. But
this fallback is only necessary for a change of the file size and not
for a change of the various timestamps.
This patch adds a new flag NILFS_I_INODE_SYNC to differentiate between
those two situations.
* If it is set the file size was changed and a full sync is necessary.
* If it is not set then only the timestamps were updated and
fdatasync() can go ahead.
There is already a similar flag I_DIRTY_DATASYNC on the VFS layer with
the exact same semantics. Unfortunately it cannot be used directly,
because NILFS2 doesn't implement write_inode() and doesn't clear the VFS
flags when inodes are written out. So the VFS writeback thread can
clear I_DIRTY_DATASYNC at any time without notifying NILFS2. So
I_DIRTY_DATASYNC has to be mapped onto NILFS_I_INODE_SYNC in
nilfs_update_inode().
Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch integrates creation of sysfs groups and
attributes into NILFS file system driver.
It was found the issue with nilfs_sysfs_{create/delete}_snapshot_group
functions by Michael L Semon <mlsemon35@gmail.com> in the first
version of the patch:
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:579
in_atomic(): 1, irqs_disabled(): 0, pid: 32676, name: umount.nilfs2
2 locks held by umount.nilfs2/32676:
#0: (&type->s_umount_key#21){++++..}, at: [<790c18e2>] deactivate_super+0x37/0x58
#1: (&(&nilfs->ns_cptree_lock)->rlock){+.+...}, at: [<791bf659>] nilfs_put_root+0x23/0x5a
Preemption disabled at:[<791bf659>] nilfs_put_root+0x23/0x5a
CPU: 0 PID: 32676 Comm: umount.nilfs2 Not tainted 3.14.0+ #2
Hardware name: Dell Computer Corporation Dimension 2350/07W080, BIOS A01 12/17/2002
Call Trace:
dump_stack+0x4b/0x75
__might_sleep+0x111/0x16f
mutex_lock_nested+0x1e/0x3ad
kernfs_remove+0x12/0x26
sysfs_remove_dir+0x3d/0x62
kobject_del+0x13/0x38
nilfs_sysfs_delete_snapshot_group+0xb/0xd
nilfs_put_root+0x2a/0x5a
nilfs_detach_log_writer+0x1ab/0x2c1
nilfs_put_super+0x13/0x68
generic_shutdown_super+0x60/0xd1
kill_block_super+0x1d/0x60
deactivate_locked_super+0x22/0x3f
deactivate_super+0x3e/0x58
mntput_no_expire+0xe2/0x141
SyS_oldumount+0x70/0xa5
syscall_call+0x7/0xb
The reason of the issue was placement of
nilfs_sysfs_{create/delete}_snapshot_group() call under
nilfs->ns_cptree_lock protection. But this protection is unnecessary and
wrong solution. The second version of the patch fixes this issue.
[fengguang.wu@intel.com: nilfs_sysfs_create_mounted_snapshots_group can be static]
Reported-by: Michael L. Semon <mlsemon35@gmail.com>
Signed-off-by: Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com>
Cc: Vyacheslav Dubeyko <slava@dubeyko.com>
Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Tested-by: Michael L. Semon <mlsemon35@gmail.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Btrfs needs to be able to control how filemap_write_and_wait_range() is called
in fsync to make it less of a painful operation, so push down taking i_mutex and
the calling of filemap_write_and_wait() down into the ->fsync() handlers. Some
file systems can drop taking the i_mutex altogether it seems, like ext3 and
ocfs2. For correctness sake I just pushed everything down in all cases to make
sure that we keep the current behavior the same for everybody, and then each
individual fs maintainer can make up their mind about what to do from there.
Thanks,
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Tell the filesystem if we just updated timestamp (I_DIRTY_SYNC) or
anything else, so that the filesystem can track internally if it
needs to push out a transaction for fdatasync or not.
This is just the prototype change with no user for it yet. I plan
to push large XFS changes for the next merge window, and getting
this trivial infrastructure in this window would help a lot to avoid
tree interdependencies.
Also remove incorrect comments that ->dirty_inode can't block. That
has been changed a long time ago, and many implementations rely on it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
In the current nilfs, page cache for btree nodes and meta data files
do not set a valid back pointer to the host inode in mapping->host.
This will change it so that every address space in nilfs uses
mapping->host to hold its host inode.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This directly uses sb->s_fs_info to keep a nilfs filesystem object and
fully removes the intermediate nilfs_sb_info structure. With this
change, the hierarchy of on-memory structures of nilfs will be
simplified as follows:
Before:
super_block
-> nilfs_sb_info
-> the_nilfs
-> cptree --+-> nilfs_root (current file system)
+-> nilfs_root (snapshot A)
+-> nilfs_root (snapshot B)
:
-> nilfs_sc_info (log writer structure)
After:
super_block
-> the_nilfs
-> cptree --+-> nilfs_root (current file system)
+-> nilfs_root (snapshot A)
+-> nilfs_root (snapshot B)
:
-> nilfs_sc_info (log writer structure)
The reason why we didn't design so from the beginning is because the
initial shape also differed from the above. The early hierachy was
composed of "per-mount-point" super_block -> nilfs_sb_info pairs and a
shared nilfs object. On the kernel 2.6.37, it was changed to the
current shape in order to unify super block instances into one per
device, and this cleanup became applicable as the result.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This records the number of used blocks per checkpoint in each
checkpoint entry of cpfile. Even though userland tools can get the
block count via nilfs_get_cpinfo ioctl, it was not updated by the
nilfs2 kernel code. This fixes the issue and makes it available for
userland tools to calculate used amount per checkpoint.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Jiro SEKIBA <jir@unicus.jp>
The current FS_IOC_GETFLAGS/SETFLAGS/GETVERSION will fail if
application is 32 bit and kernel is 64 bit.
This issue is avoidable by adding compat_ioctl method.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Nilfs has few rectrictions on which flags may be set on which inodes
like ext2/3/4 filesystems used to be. Specifically DIRSYNC may only
be set on directories and IMMUTABLE and APPEND may not be set on
links. Tighten that to disallow TOPDIR being set on non-directories
and only NODUMP and NOATIME to be set on non-regular file,
non-directories.
This introduces a flags masking function like those of extN and uses
it during inode creation.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
nilfs_dat_inode function was a wrapper to switch between normal dat
inode and gcdat, a clone of the dat inode for garbage collection.
This function got obsolete when the gcdat inode was removed, and now
we can access the dat inode directly from a nilfs object. So, we will
unfold the wrapper and remove it.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This removes argument for passing nilfs_sb_info structure from
nilfs_set_file_dirty and nilfs_load_inode_block functions. We can get
a pointer to the structure from inodes.
[Stephen Rothwell <sfr@canb.auug.org.au>: fix conflict with commit
b74c79e993]
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This adds fiemap to nilfs. Two new functions, nilfs_fiemap and
nilfs_find_uncommitted_extent are added.
nilfs_fiemap() implements the fiemap inode operation, and
nilfs_find_uncommitted_extent() helps to get a range of data blocks
whose physical location has not been determined.
nilfs_fiemap() collects extent information by looping through
nilfs_bmap_lookup_contig and nilfs_find_uncommitted_extent routines.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This finally removes own inode allocator and destructor functions for
metadata files. Several routines, nilfs_mdt_new(),
nilfs_mdt_new_common(), nilfs_mdt_clear(), nilfs_mdt_destroy(), and
nilfs_alloc_inode_common() will be gone.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
After applied the patch that unified sb instances, root dentry of
snapshots can be left in dcache even after their trees are unmounted.
The orphan root dentry/inode keeps a root object, and this causes
false positive of nilfs_checkpoint_is_mounted function.
This resolves the issue by having nilfs_checkpoint_is_mounted test
whether the root dentry is busy or not.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This makes use of iget5_locked to allocate or get inode for metadata
files to stop using own inode allocator.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This applies prepared rollback function and redirect function of
metadata file to DAT file, and eliminates GCDAT inode.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Snapshots of nilfs are read-only.
After super block instances (sb) will be unified, nilfs will need to
check write access by a way other than implicit test with
IS_RDONLY(inode). This is because IS_RDONLY() refers to MS_RDONLY bit
of inode->i_sb->s_flags and it will become inaccurate after the
unification of sb.
To prepare for the issue, this uses i_op->permission to deny write
access to inodes in snapshots.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This rewrites functions using ifile so that they get ifile from
nilfs_root object, and will remove sbi->s_ifile. Some functions that
don't know the root object are extended to receive it from caller.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
The previous export operations cannot handle multiple versions of
a filesystem if they belong to the same sb instance.
This adds a new type of file handle and extends export operations so
that they can get the inode specified by a checkpoint number as well
as an inode number and a generation number.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This puts a pointer to nilfs_root object in the private part of
on-memory inode, and makes nilfs_iget function pick up the inode with
the same root object.
Non-root inodes inherit its nilfs_root object from parent inode. That
of the root inode is allocated through nilfs_attach_checkpoint()
function.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This uses inode hash function that vfs provides instead of the own
hash table for caching gc inodes. This finally removes the own inode
hash from nilfs.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (96 commits)
no need for list_for_each_entry_safe()/resetting with superblock list
Fix sget() race with failing mount
vfs: don't hold s_umount over close_bdev_exclusive() call
sysv: do not mark superblock dirty on remount
sysv: do not mark superblock dirty on mount
btrfs: remove junk sb_dirt change
BFS: clean up the superblock usage
AFFS: wait for sb synchronization when needed
AFFS: clean up dirty flag usage
cifs: truncate fallout
mbcache: fix shrinker function return value
mbcache: Remove unused features
add f_flags to struct statfs(64)
pass a struct path to vfs_statfs
update VFS documentation for method changes.
All filesystems that need invalidate_inode_buffers() are doing that explicitly
convert remaining ->clear_inode() to ->evict_inode()
Make ->drop_inode() just return whether inode needs to be dropped
fs/inode.c:clear_inode() is gone
fs/inode.c:evict() doesn't care about delete vs. non-delete paths now
...
Fix up trivial conflicts in fs/nilfs2/super.c
This forces nilfs to check compatibility of feature flags so as to
reject a filesystem with unknown features when it mounts or remounts
the filesystem.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This removes nilfs_bmap_union and finally unifies three structures and
the union in bmap/btree code into one.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This will sync super blocks in turns instead of syncing duplicate
super blocks at the time. This will help searching valid super root
when super block is written into disk before log is written, which is
happen when barrier-less block devices are unmounted uncleanly. In
the situation, old super block likely points to valid log.
This patch introduces ns_sbwcount member to the nilfs object and adds
nilfs_sb_will_flip() function; ns_sbwcount counts how many times super
blocks write back to the disk. And, nilfs_sb_will_flip() decides
whether flipping required or not based on the count of ns_sbwcount to
sync super blocks asymmetrically.
The following functions are also changed:
- nilfs_prepare_super(): flips super blocks according to the
argument. The argument is calculated by nilfs_sb_will_flip()
function.
- nilfs_cleanup_super(): sets "clean" flag to both super blocks if
they point to the same checkpoint.
To update both of super block information, caller of
nilfs_commit_super must set the information on both super blocks.
Signed-off-by: Jiro SEKIBA <jir@unicus.jp>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This function checks validity of super block pointers.
If first super block is invalid, it will swap the super blocks.
The function should be called before any super block information updates.
Caller must obtain nilfs->ns_sem.
Signed-off-by: Jiro SEKIBA <jir@unicus.jp>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This moves out section that updates information of the recent log
position stored in super blocks from nilfs_commit_super to a new
routine named nilfs_set_log_cursor.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This function write out filesystem state to super blocks in order to
share the same cleanup work. This is a preparation for making super
block writeback alternately.
Cc: Jiro SEKIBA <jir@unicus.jp>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Previously, default_backing_dev_info was used for the mapping of btree
node caches. This uses device dependent backing_dev_info to allow
detailed control of the device for the btree node pages.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This is a companion patch to ("nilfs2: fix possible circular locking
for get information ioctls").
This corrects lock order reversal between mm->mmap_sem and
nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by
lockdep check:
=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.30-rc3-nilfs-00003-g360bdc1 #7
-------------------------------------------------------
mmap/5294 is trying to acquire lock:
(&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2]
but task is already holding lock:
(&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&mm->mmap_sem){++++++}:
[<c01470a5>] __lock_acquire+0x1066/0x13b0
[<c01474a9>] lock_acquire+0xba/0xdd
[<c01836bc>] might_fault+0x68/0x88
[<c023c61d>] copy_from_user+0x2a/0x111
[<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2]
[<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2]
[<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2]
[<c01a3be7>] vfs_ioctl+0x22/0x69
[<c01a408e>] do_vfs_ioctl+0x460/0x499
[<c01a4107>] sys_ioctl+0x40/0x5a
[<c01031a4>] sysenter_do_call+0x12/0x38
[<ffffffff>] 0xffffffff
-> #0 (&nilfs->ns_segctor_sem){++++.+}:
[<c0146e0b>] __lock_acquire+0xdcc/0x13b0
[<c01474a9>] lock_acquire+0xba/0xdd
[<c0433f1d>] down_read+0x2a/0x3e
[<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2]
[<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2]
[<c0183b0b>] __do_fault+0x165/0x376
[<c01855cd>] handle_mm_fault+0x287/0x5d1
[<c043712d>] do_page_fault+0x2fb/0x30a
[<c0435462>] error_code+0x72/0x78
[<ffffffff>] 0xffffffff
where nilfs_clean_segments() holds:
nilfs->ns_segctor_sem -> copy_from_user()
--> page fault -> mm->mmap_sem
And, page fault path may hold:
page fault -> mm->mmap_sem
--> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem
Even though nilfs_clean_segments() does not perform write access on
given user pages, it may cause deadlock because nilfs->ns_segctor_sem
is shared per device and mm->mmap_sem can be shared with other tasks.
To avoid this problem, this patch moves all calls of copy_from_user()
outside the nilfs->ns_segctor_sem lock in the ioctl.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
A MODULE_VERSION() macro has been used in out-of-tree nilfs modules,
but it's needless and not updated in tree. So, this removes it along
with the version declaration.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
After a review of user's feedback for finding out other compatibility
issues, I found nilfs improperly initializes timestamps in inode;
CURRENT_TIME was used there instead of CURRENT_TIME_SEC even though nilfs
didn't have nanosecond timestamps on disk. A few users gave us the report
that the tar program sometimes failed to expand symbolic links on nilfs,
and it turned out to be the cause.
Instead of applying the above displacement, I've decided to support
nanosecond timestamps on this occation. Fortunetaly, a needless 64-bit
field was in the nilfs_inode struct, and I found it's available for this
purpose without impact for the users.
So, this will do the enhancement and resolve the tar problem.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The former versions didn't have extra super blocks. This improves the
weak point by introducing another super block at unused region in tail of
the partition.
This doesn't break disk format compatibility; older versions just ingore
the secondary super block, and new versions just recover it if it doesn't
exist. The partition created by an old mkfs may not have unused region,
but in that case, the secondary super block will not be added.
This doesn't make more redundant copies of the super block; it is a future
work.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ryusuke Konishi