Add a new xfs_alloc_find_best_extent that does a forward/backward
search in the allocation btree.  That code previously was existed
two times in xfs_alloc_ag_vextent_near, once for each search
direction.

Based on an earlier patch from Dave Chinner.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Use a goto label to consolidate all block not found cases, and add a
tracepoint for them.  Also clean up a few whitespace issues.

Based on an earlier patch from Dave Chinner.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Move the buffer locking into the callers as they need to do it
wether they call xfs_map_at_offset or not.  Remove the b_bdev
assignment, which is already done by get_blocks.  Remove the
duplicate extent type asserts in xfs_convert_page just before
calling xfs_map_at_offset.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

After the last patches the code for overwrites is the same as for
delayed and unwritten extents except that it doesn't need to call
xfs_map_at_offset.  Take care of that fact to simplify
xfs_vm_writepage.

The buffer loop now first checks the type of buffer and checks/sets
the ioend type, or continues to the next buffer if it's not
interesting to us.  Only after that we validate the iomap and
perform the block mapping if needed, all in common code for the
cases where we have to do work.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The all_bh flag is always set when entering the page clustering
machinery with a regular written extent, which means the check for
it is superflous.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

xfs_map_blocks always calls xfs_bmapi with the XFS_BMAPI_ENTIRE
entire flag, which tells it to not cap the extent at the passed in
size, but just treat the size as an minimum to map.  This means
xfs_probe_cluster is entirely useless as we'll always get the whole
extent back anyway.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

No need to lock the extent map exclusive when performing an
overwrite, we know the extent map must already have been loaded by
get_blocks.  Apply the non-blocking inode semantics to all mapping
types instead of just delayed allocations.  Remove the handling of
not yet allocated blocks for the IO_UNWRITTEN case - if an extent is
marked as unwritten allocated in the buffer it must already have an
extent on disk.

Add asserts to verify all the assumptions above in debug builds.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Opencode the xfs_iomap code in it's two callers.  The overlap of
passed flags already was minimal and will be further reduced in the
next patch.

As a side effect the BMAPI_* flags for xfs_bmapi and the IO_* flags
for I/O end processing are merged into a single set of flags, which
should be a bit more descriptive of the operation we perform.

Also improve the tracing by giving each caller it's own type set of
tracepoints.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Remove passing the BMAPI_* flags to these helpers, in
xfs_iomap_write_direct the check BMAPI_DIRECT was always true, and
in the xfs_iomap_write_delay path is was never checked at all.
Remove the nmap return value as we never make use of it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Don't trylock the buffer.  We are the only one ever locking it for a
regular file address space, and trylock was only copied from the
generic code which did it due to the old buffer based writeout in
jbd.  Also make sure to only write out the buffer if the iomap
actually is valid, because we wouldn't have a proper mapping
otherwise.  In practice we will never get an invalid mapping here as
the page lock guarantees truncate doesn't race with us, but better
be safe than sorry.  Also make sure we allocate a new ioend when
crossing boundaries between mappings, just like we do for delalloc
and unwritten extents.  Again this currently doesn't matter as the
I/O end handler only cares for the boundaries for unwritten extents,
but this makes the code fully correct and the same as for
delalloc/unwritten extents.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

We'll never have BIO_EOPNOTSUPP set after calling submit_bio as this
can only happen for discards, and used to happen for barriers, none
of which is every submitted by xfs_submit_ioend_bio.  Also remove
the loop around bio_alloc as it will never fail due to it's mempool
backing.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Currently we only refuse a "read-only" mapping for writing out
unwritten and delayed buffers, and refuse any other for overwrites.
Improve the checks to require delalloc mappings for delayed buffers,
and unwritten extent mappings for unwritten extents.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Dispatch to a different helper for phase1 vs phase2 in
xlog_recover_commit_trans instead of doing it in all the
low-level functions.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Merge the call to xlog_recover_reorder_trans and the loop over the
recovery items from xlog_recover_do_trans into xlog_recover_commit_trans,
and keep the switch statement over the log item types as a separate helper.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

XFS used to support different types of buffer log items long time
ago.  Remove the switch statements checking the log item type in
various buffer recovery helpers that were left over from those days
and the rather useless xlog_recover_do_buffer_pass2 wrapper.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

We now support mounting and using filesystems with 64-bit inodes
even when not mounted with the inode64 option (which now only
controls if we allocate new inodes in that space or not).  Make sure
we always use large NFS file handles when exporting a filesystem
that may contain 64-bit inodes.  Note that this only affects newly
generated file handles, any outstanding 32-bit file handle is still
accepted.

[hch: the comment and commit log are mine, the rest is from a patch
 snipplet from Samuel]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Now that we don't mark VFS inodes dirty anymore for internal
timestamp changes, but rely on the transaction subsystem to push
them out, we need to explicitly log the source inode in rename after
updating it's timestamps to make sure the changes actually get
forced out by sync/fsync or an AIL push.

We already account for the fourth inode in the log reservation, as a
rename of directories needs to update the nlink field, so just
adding the xfs_trans_log_inode call is enough.

This fixes the xfsqa 065 regression introduced by:

	"xfs: don't use vfs writeback for pure metadata modifications"
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Recent tests writing lots of small files showed the flusher thread
being CPU bound and taking a long time to do allocations on a debug
kernel. perf showed this as the prime reason:

             samples  pcnt function                    DSO
             _______ _____ ___________________________ _________________

           224648.00 36.8% xfs_error_test              [kernel.kallsyms]
            86045.00 14.1% xfs_btree_check_sblock      [kernel.kallsyms]
            39778.00  6.5% prandom32                   [kernel.kallsyms]
            37436.00  6.1% xfs_btree_increment         [kernel.kallsyms]
            29278.00  4.8% xfs_btree_get_rec           [kernel.kallsyms]
            27717.00  4.5% random32                    [kernel.kallsyms]

Walking btree blocks during allocation checking them requires each
block (a cache hit, so no I/O) call xfs_error_test(), which then
does a random32() call as the first operation.  IOWs, ~50% of the
CPU is being consumed just testing whether we need to inject an
error, even though error injection is not active.

Kill this overhead when error injection is not active by adding a
global counter of active error traps and only calling into
xfs_error_test when fault injection is active.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

When an inode has been marked stale because the cluster is being
freed, we don't want to (re-)insert this inode into the AIL. There
is a race condition where the cluster buffer may be unpinned before
the inode is inserted into the AIL during transaction committed
processing. If the buffer is unpinned before the inode item has been
committed and inserted, then it is possible for the buffer to be
released and hence processthe stale inode callbacks before the inode
is inserted into the AIL.

In this case, we then insert a clean, stale inode into the AIL which
will never get removed by an IO completion. It will, however, get
reclaimed and that triggers an assert in xfs_inode_free()
complaining about freeing an inode still in the AIL.

This race can be avoided by not moving stale inodes forward in the AIL
during transaction commit completion processing. This closes the
race condition by ensuring we never insert clean stale inodes into
the AIL. It is safe to do this because a dirty stale inode, by
definition, must already be in the AIL.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

There is an assumption in the parts of XFS that flushing a dirty
file will make all the delayed allocation blocks disappear from an
inode. That is, that after calling xfs_flush_pages() then
ip->i_delayed_blks will be zero.

This is an invalid assumption as we may have specualtive
preallocation beyond EOF and they are recorded in
ip->i_delayed_blks. A flush of the dirty pages of an inode will not
change the state of these blocks beyond EOF, so a non-zero
deeelalloc block count after a flush is valid.

The bmap code has an invalid ASSERT() that needs to be removed, and
the swapext code has a bug in that while it swaps the data forks
around, it fails to swap the i_delayed_blks counter associated with
the fork and hence can get the block accounting wrong.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

As reported by Nick Piggin, XFS is suffering from long pauses under
highly concurrent workloads when hosted on ramdisks. The problem is
that an inode buffer is stuck in the pinned state in memory and as a
result either the inode buffer or one of the inodes within the
buffer is stopping the tail of the log from being moved forward.

The system remains in this state until a periodic log force issued
by xfssyncd causes the buffer to be unpinned. The main problem is
that these are stale buffers, and are hence held locked until the
transaction/checkpoint that marked them state has been committed to
disk. When the filesystem gets into this state, only the xfssyncd
can cause the async transactions to be committed to disk and hence
unpin the inode buffer.

This problem was encountered when scaling the busy extent list, but
only the blocking lock interface was fixed to solve the problem.
Extend the same fix to the buffer trylock operations - if we fail to
lock a pinned, stale buffer, then force the log immediately so that
when the next attempt to lock it comes around, it will have been
unpinned.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

Since the move to the new truncate sequence we call xfs_setattr to
truncate down excessively instanciated blocks.  As shown by the testcase
in kernel.org BZ #22452 that doesn't work too well.  Due to the confusion
of the internal inode size, and the VFS inode i_size it zeroes data that
it shouldn't.

But full blown truncate seems like overkill here.  We only instanciate
delayed allocations in the write path, and given that we never released
the iolock we can't have converted them to real allocations yet either.

The only nasty case is pre-existing preallocation which we need to skip.
We already do this for page discard during writeback, so make the delayed
allocation block punching a generic function and call it from the failed
write path as well as xfs_aops_discard_page. The callers are
responsible for ensuring that partial blocks are not truncated away,
and that they hold the ilock.

Based on a fix originally from Christoph Hellwig. This version used
filesystem blocks as the range unit.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

In commit 20cb52eb, titled
"xfs: simplify xfs_vm_writepage" I added an assert that any !mapped and
uptodate buffers are not dirty.  That asserts turns out to trigger a lot
when running fsx on filesystems with small block sizes.  The reason for
that is that the assert is simply incorrect.  !mapped and uptodate
just mean this buffer covers a hole, and whenever we do a set_page_dirty
we mark all blocks in the page dirty, no matter if they have data or
not.  So remove the assert, and update the comment above the condition
to match reality.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

XFS does not need it's inodes to actuall be hashed in the VFS inode
cache, but we require the inode to be marked hashed for the
writeback code to work.

Insted of using insert_inode_hash, which requires a second
inode_lock roundtrip after the partial merge of the inode
scalability patches in 2.6.37-rc simply use the new hlist_add_fake
helper to mark it hashed without requiring a lock or touching a
global cache line.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Andi Kleen reported that gcc-4.5 gives lots of warnings for him
inside the XFS code.  It turned out most of them are due to the
quota stubs beeing macros, and gcc now complaining about macros
evaluating to 0 that are not assigned to variables.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The filestreams code may take the iolock on the parent inode while
holding it on a child.  This is the only place in XFS where we take
both the child and parent iolock, so just telling lockdep about it
is enough.  The lock flag required for that was already added as
part of the ilock lockdep annotations and unused so far.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The delayed write buffer split trace currently issues a trace for
every buffer it scans. These buffers are not necessarily queued for
delayed write. Indeed, when buffers are pinned, there can be
thousands of traces of buffers that aren't actually queued for
delayed write and the ones that are are lost in the noise. Move the
trace point to record only buffers that are split out for IO to be
issued on.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The walk fails to decrement the per-ag reference count when the
non-blocking walk fails to obtain the per-ag reclaim lock, leading
to an assert failure on debug kernels when unmounting a filesystem.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

al_hreq is copied from userland.  If al_hreq.buflen is not properly aligned
then xfs_attr_list will ignore the last bytes of kbuf.  These bytes are
unitialized.  It leads to leaking of contents of kernel stack memory.
Signed-off-by: NVasiliy Kulikov <segooon@gmail.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

We promised to do this for 2.6.37, and the code looks stable enough to
keep that promise.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

... and switch of the obvious get_sb_bdev() users to ->mount()
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

This removes more dead code that was somehow missed by commit 0d99519e
(writeback: remove unused nonblocking and congestion checks).  There are
no behavior change except for the removal of two entries from one of the
ext4 tracing interface.

The nonblocking checks in ->writepages are no longer used because the
flusher now prefer to block on get_request_wait() than to skip inodes on
IO congestion.  The latter will lead to more seeky IO.

The nonblocking checks in ->writepage are no longer used because it's
redundant with the WB_SYNC_NONE check.

We no long set ->nonblocking in VM page out and page migration, because
a) it's effectively redundant with WB_SYNC_NONE in current code
b) it's old semantic of "Don't get stuck on request queues" is mis-behavior:
   that would skip some dirty inodes on congestion and page out others, which
   is unfair in terms of LRU age.

Inspired by Christoph Hellwig. Thanks!
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: David Howells <dhowells@redhat.com>
Cc: Sage Weil <sage@newdream.net>
Cc: Steve French <sfrench@samba.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Instead of always assigning an increasing inode number in new_inode
move the call to assign it into those callers that actually need it.
For now callers that need it is estimated conservatively, that is
the call is added to all filesystems that do not assign an i_ino
by themselves.  For a few more filesystems we can avoid assigning
any inode number given that they aren't user visible, and for others
it could be done lazily when an inode number is actually needed,
but that's left for later patches.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Clones an existing reference to inode; caller must already hold one.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Split up inode_add_to_list/__inode_add_to_list.  Locking for the two
lists will be split soon so these helpers really don't buy us much
anymore.

The __ prefixes for the sb list helpers will go away soon, but until
inode_lock is gone we'll need them to distinguish between the locked
and unlocked variants.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

__block_write_begin and block_prepare_write are identical except for slightly
different calling conventions.  Convert all callers to the __block_write_begin
calling conventions and drop block_prepare_write.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Get rid of init_MUTEX[_LOCKED]() and use sema_init() instead.

(Ported to current XFS code by <aelder@sgi.com>.)
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

This patch adds support for 32bit project quota identifiers.

On disk format is backward compatible with 16bit projid numbers. projid
on disk is now kept in two 16bit values - di_projid_lo (which holds the
same position as old 16bit projid value) and new di_projid_hi (takes
existing padding) and converts from/to 32bit value on the fly.

xfs_admin (for existing fs), mkfs.xfs (for new fs) needs to be used
to enable PROJID32BIT support.
Signed-off-by: NArkadiusz Miśkiewicz <arekm@maven.pl>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Stop having two different names for many buffer functions and use
the more descriptive xfs_buf_* names directly.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>