There is a window on small filesytsems where specualtive
preallocation can be larger than that ENOSPC throttling thresholds,
resulting in specualtive preallocation trying to reserve more space
than there is space available. This causes immediate ENOSPC to be
triggered, prealloc to be turned off and flushing to occur. One the
next write (i.e. next 4k page), we do exactly the same thing, and so
effective drive into synchronous 4k writes by triggering ENOSPC
flushing on every page while in the window between the prealloc size
and the ENOSPC prealloc throttle threshold.

Fix this by checking to see if the prealloc size would consume all
free space, and throttle it appropriately to avoid premature
ENOSPC...
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NBrian Foster <bfoster@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Add the XFS_ICI_EOFBLOCKS_TAG inode tag to identify inodes with
speculatively preallocated blocks beyond EOF. An inode is tagged
when speculative preallocation occurs and untagged either via
truncate down or when post-EOF blocks are freed via release or
reclaim.

The tag management is intentionally not aggressive to prefer
simplicity over the complexity of handling all the corner cases
under which post-EOF blocks could be freed (i.e., forward
truncation, fallocate, write error conditions, etc.). This means
that a tagged inode may or may not have post-EOF blocks after a
period of time. The tag is eventually cleared when the inode is
released or reclaimed.
Signed-off-by: NBrian Foster <bfoster@redhat.com>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Certain allocation paths through xfs_bmapi_write() are in situations
where we have limited stack available. These are almost always in
the buffered IO writeback path when convertion delayed allocation
extents to real extents.

The current stack switch occurs for userdata allocations, which
means we also do stack switches for preallocation, direct IO and
unwritten extent conversion, even those these call chains have never
been implicated in a stack overrun.

Hence, let's target just the single stack overun offended for stack
switches. To do that, introduce a XFS_BMAPI_STACK_SWITCH flag that
the caller can pass xfs_bmapi_write() to indicate it should switch
stacks if it needs to do allocation.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Certain allocation paths through xfs_bmapi_write() are in situations
where we have limited stack available. These are almost always in
the buffered IO writeback path when convertion delayed allocation
extents to real extents.

The current stack switch occurs for userdata allocations, which
means we also do stack switches for preallocation, direct IO and
unwritten extent conversion, even those these call chains have never
been implicated in a stack overrun.

Hence, let's target just the single stack overun offended for stack
switches. To do that, introduce a XFS_BMAPI_STACK_SWITCH flag that
the caller can pass xfs_bmapi_write() to indicate it should switch
stacks if it needs to do allocation.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

We don't do any data writeback from XFS any more - the VFS is
completely responsible for that, including for freeze. We can
replace the remaining caller with a VFS level function that
achieves the same thing, but without conflicting with current
writeback work.

This means we can remove the flush_work and xfs_flush_inodes() - the
VFS functionality completely replaces the internal flush queue for
doing this writeback work in a separate context to avoid stack
overruns.

This does have one complication - it cannot be called with page
locks held.  Hence move the flushing of delalloc space when ENOSPC
occurs back up into xfs_file_aio_buffered_write when we don't hold
any locks that will stall writeback.

Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to
trigger delalloc conversion fast enough to prevent spurious ENOSPC
whent here are hundreds of writers, thousands of small files and GBs
of free RAM.  Hence we need to use sync_sb_inodes() to block callers
while we wait for writeback like the previous xfs_flush_inodes
implementation did.

That means we have to hold the s_umount lock here, but because this
call can nest inside i_mutex (the parent directory in the create
case, held by the VFS), we have to use down_read_trylock() to avoid
potential deadlocks. In practice, this trylock will succeed on
almost every attempt as unmount/remount type operations are
exceedingly rare.

Note: we always need to pass a count of zero to
generic_file_buffered_write() as the previously written byte count.
We only do this by accident before this patch by the virtue of ret
always being zero when there are no errors. Make this explicit
rather than needing to specifically zero ret in the ENOSPC retry
case.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Tested-by: NBrian Foster <bfoster@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NBen Myers <bpm@sgi.com>

Generic code now blocks all writers from standard write paths. So we add
blocking of all writers coming from ioctl (we get a protection of ioctl against
racing remount read-only as a bonus) and convert xfs_file_aio_write() to a
non-racy freeze protection. We also keep freeze protection on transaction
start to block internal filesystem writes such as removal of preallocated
blocks.

CC: Ben Myers <bpm@sgi.com>
CC: Alex Elder <elder@kernel.org>
CC: xfs@oss.sgi.com
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

XFS_MAXIOFFSET() is just a simple macro that resolves to
mp->m_maxioffset. It doesn't need to exist, and it just makes the
code unnecessarily loud and shouty.

Make it quiet and easy to read.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

The m_maxioffset field in the struct xfs_mount contains the same
value as the superblock s_maxbytes field. There is no need to carry
two copies of this limit around, so use the VFS superblock version.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

xfstest 270 was causing quota reservations way beyond what was sane
(ten to hundreds of TB) for a 4GB filesystem. There's a sign problem
in the error handling path of xfs_bmapi_reserve_delalloc() because
xfs_trans_unreserve_quota_nblks() simple negates the value passed -
which doesn't work for an unsigned variable. This causes
reservations of close to 2^32 block instead of removing a
reservation of a handful of blocks.

Fix the same problem in the other xfs_trans_unreserve_quota_nblks()
callers where unsigned integer variables are used, too.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

With the removal of xfs_rw.h and other changes over time, xfs_bit.h
is being included in many files that don't actually need it. Clean
up the includes as necessary.

Also move the only-used-once xfs_ialloc_find_free() static inline
function out of a header file that is widely included to reduce
the number of needless dependencies on xfs_bit.h.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

The only thing left in xfs_rw.h is a function prototype for an inode
function.  Move that to xfs_inode.h, and kill xfs_rw.h.

Also move the function implementing the prototype from xfs_rw.c to
xfs_inode.c so we only have one function left in xfs_rw.c
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NBen Myers <bpm@sgi.com>

Untangle the header file includes a bit by moving the definition of
xfs_agino_t to xfs_types.h. This removes the dependency that xfs_ag.h has on
xfs_inum.h, meaning we don't need to include xfs_inum.h everywhere we include
xfs_ag.h.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Speculative delayed allocation beyond EOF near the maximum supported
file offset can result in creating delalloc extents beyond
mp->m_maxioffset (8EB). These can never be trimmed during
xfs_free_eof_blocks() because they are beyond mp->m_maxioffset, and
that results in assert failures in xfs_fs_destroy_inode() due to
delalloc blocks still being present. xfstests 071 exposes this
problem.

Limit speculative delalloc to mp->m_maxioffset to avoid this
problem.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

For the direct IO write path, we only really need the ilock to be taken in
exclusive mode during IO submission if we need to do extent allocation
instead of all the time.

Change the block mapping code to take the ilock in shared mode for the
initial block mapping, and only retake it exclusively when we actually
have to perform extent allocations.  We were already dropping the ilock
for the transaction allocation, so this doesn't introduce new race windows.

Based on an earlier patch from Dave Chinner.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

If we convert and unwritten extent past the current i_size log the size update
as part of the extent manipulation transactions instead of doing an unlogged
metadata update later.
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

There is no fundamental need to keep an in-memory inode size copy in the XFS
inode.  We already have the on-disk value in the dinode, and the separate
in-memory copy that we need for regular files only in the XFS inode.

Remove the xfs_inode i_size field and change the XFS_ISIZE macro to use the
VFS inode i_size field for regular files.  Switch code that was directly
accessing the i_size field in the xfs_inode to XFS_ISIZE, or in cases where
we are limited to regular files direct access of the VFS inode i_size field.

This also allows dropping some fairly complicated code in the write path
which dealt with keeping the xfs_inode i_size uptodate with the VFS i_size
that is getting updated inside ->write_end.

Note that we do not bother resetting the VFS i_size when truncating a file
that gets freed to zero as there is no point in doing so because the VFS inode
is no longer in use at this point.  Just relax the assert in xfs_ifree to
only check the on-disk size instead.
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NBen Myers <bpm@sgi.com>

Replace the nasty if, else if, elseif condition with more natural C flow
that expressed the logic we want here better.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

There is no reason to keep a reference to the inode even if we unlock
it during transaction commit because we never drop a reference between
the ijoin and commit.  Also use this fact to merge xfs_trans_ijoin_ref
back into xfs_trans_ijoin - the third argument decides if an unlock
is needed now.

I'm actually starting to wonder if allowing inodes to be unlocked
at transaction commit really is worth the effort.  The only real
benefit is that they can be unlocked earlier when commiting a
synchronous transactions, but that could be solved by doing the
log force manually after the unlock, too.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Now that all the read-only users of xfs_bmapi have been converted to
use xfs_bmapi_read(), we can remove all the read-only handling cases
from xfs_bmapi().

Once this is done, rename xfs_bmapi to xfs_bmapi_write to reflect
the fact it is for allocation only. This enables us to kill the
XFS_BMAPI_WRITE flag as well.

Also clean up xfs_bmapi_write to the style used in the newly added
xfs_bmapi_read/delay functions.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Delalloc reservations are much simpler than allocations, so give
them a separate bmapi-level interface.  Using the previously added
xfs_bmapi_reserve_delalloc we get a function that is only minimally
more complicated than xfs_bmapi_read, which is far from the complexity
in xfs_bmapi.  Also remove the XFS_BMAPI_DELAY code after switching
over the only user to xfs_bmapi_delay.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

xfs_bmapi() currently handles both extent map reading and
allocation. As a result, the code is littered with "if (wr)"
branches to conditionally do allocation operations if required.
This makes the code much harder to follow and causes significant
indent issues with the code.

Given that read mapping is much simpler than allocation, we can
split out read mapping from xfs_bmapi() and reuse the logic that
we have already factored out do do all the hard work of handling the
extent map manipulations. The results in a much simpler function for
the common extent read operations, and will allow the allocation
code to be simplified in another commit.

Once xfs_bmapi_read() is implemented, convert all the callers of
xfs_bmapi() that are only reading extents to use the new function.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

This reverts commit 7a249cf8.

That commit created a situation that could lead to a filesystem
hang.  As Dave Chinner pointed out, xfs_trans_alloc() could hold a
reference to m_active_trans (i.e., keep it non-zero) and then wait
for SB_FREEZE_TRANS to complete.  Meanwhile a filesystem freeze
request could set SB_FREEZE_TRANS and then wait for m_active_trans
to drop to zero.  Nobody benefits from this sequence of events...
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

As pointed out by Jan xfs_trans_alloc can race with a concurrent filesystem
freeze when it sleeps during the memory allocation.  Fix this by moving the
wait_for_freeze call after the memory allocation.  This means moving the
freeze into the low-level _xfs_trans_alloc helper, which thus grows a new
argument.  Also fix up some comments in that area while at it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NDave Chinner <david@fromorbit.com>

The "cmn_err" part of the function name is no longer relevant. Rename
the function to xfs_alert_fsblock_zero() to match the new logging
API.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

Continue the conversion of the old cmn_err interface be converting
all the conditional panic tag errors to xfs_alert_tag() and then
removing xfs_cmn_err().
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

rounddown_power_of_2() returns an undefined result when passed a
value of zero. The specualtive delayed allocation code is doing this
when the inode is zero length. Hence occasionally the preallocation
is much, much larger than is necessary (e.g. 8GB for a 270 _byte_
file). Ensure we don't even pass a zero value to this function so
the result of preallocation is always the desired size.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Currently the size of the speculative preallocation during delayed
allocation is fixed by either the allocsize mount option of a
default size. We are seeing a lot of cases where we need to
recommend using the allocsize mount option to prevent fragmentation
when buffered writes land in the same AG.

Rather than using a fixed preallocation size by default (up to 64k),
make it dynamic by basing it on the current inode size. That way the
EOF preallocation will increase as the file size increases.  Hence
for streaming writes we are much more likely to get large
preallocations exactly when we need it to reduce fragementation.

For default settings, the size of the initial extents is determined
by the number of parallel writers and the amount of memory in the
machine. For 4GB RAM and 4 concurrent 32GB file writes:

EXT: FILE-OFFSET           BLOCK-RANGE          AG AG-OFFSET                 TOTAL
   0: [0..1048575]:         1048672..2097247      0 (1048672..2097247)      1048576
   1: [1048576..2097151]:   5242976..6291551      0 (5242976..6291551)      1048576
   2: [2097152..4194303]:   12583008..14680159    0 (12583008..14680159)    2097152
   3: [4194304..8388607]:   25165920..29360223    0 (25165920..29360223)    4194304
   4: [8388608..16777215]:  58720352..67108959    0 (58720352..67108959)    8388608
   5: [16777216..33554423]: 117440584..134217791  0 (117440584..134217791) 16777208
   6: [33554424..50331511]: 184549056..201326143  0 (184549056..201326143) 16777088
   7: [50331512..67108599]: 251657408..268434495  0 (251657408..268434495) 16777088

and for 16 concurrent 16GB file writes:

 EXT: FILE-OFFSET           BLOCK-RANGE          AG AG-OFFSET                 TOTAL
   0: [0..262143]:          2490472..2752615      0 (2490472..2752615)       262144
   1: [262144..524287]:     6291560..6553703      0 (6291560..6553703)       262144
   2: [524288..1048575]:    13631592..14155879    0 (13631592..14155879)     524288
   3: [1048576..2097151]:   30408808..31457383    0 (30408808..31457383)    1048576
   4: [2097152..4194303]:   52428904..54526055    0 (52428904..54526055)    2097152
   5: [4194304..8388607]:   104857704..109052007  0 (104857704..109052007)  4194304
   6: [8388608..16777215]:  209715304..218103911  0 (209715304..218103911)  8388608
   7: [16777216..33554423]: 452984848..469762055  0 (452984848..469762055) 16777208

Because it is hard to take back specualtive preallocation, cases
where there are large slow growing log files on a nearly full
filesystem may cause premature ENOSPC. Hence as the filesystem nears
full, the maximum dynamic prealloc size іs reduced according to this
table (based on 4k block size):

freespace       max prealloc size
  >5%             full extent (8GB)
  4-5%             2GB (8GB >> 2)
  3-4%             1GB (8GB >> 3)
  2-3%           512MB (8GB >> 4)
  1-2%           256MB (8GB >> 5)
  <1%            128MB (8GB >> 6)

This should reduce the amount of space held in speculative
preallocation for such cases.

The allocsize mount option turns off the dynamic behaviour and fixes
the prealloc size to whatever the mount option specifies. i.e. the
behaviour is unchanged.
Signed-off-by: NDave Chinner <dchinner@redhat.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>

Remove the flags argument to  __xfs_get_blocks as we can easily derive
it from the direct argument, and remove the unused BMAPI_MMAP flag.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

xfs_iomap passes a xfs_bmbt_irec pointer to xfs_iomap_write_direct and
xfs_iomap_write_allocate to give them the results of our read-only
xfs_bmapi query.  Instead of allocating a new xfs_bmbt_irec on stack
for the next call to xfs_bmapi re use the one we got passed as it's not
used after this point.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

This code was introduced four years ago in commit
3e57ecf6 without any review and has
been unused since.  Remove it just as the rest of the code introduced
in that commit to reduce that stack usage and complexity in this central
piece of code.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

Currently we need to either call IHOLD or xfs_trans_ihold on an inode when
joining it to a transaction via xfs_trans_ijoin.

This patches instead makes xfs_trans_ijoin usable on it's own by doing
an implicity xfs_trans_ihold, which also allows us to drop the third
argument.  For the case where we want to hold a reference on the inode
a xfs_trans_ijoin_ref wrapper is added which does the IHOLD and marks
the inode for needing an xfs_iput.  In addition to the cleaner interface
to the caller this also simplifies the implementation.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <david@fromorbit.com>

Dmapi support was never merged upstream, but we still have a lot of hooks
bloating XFS for it, all over the fast pathes of the filesystem.

This patch drops over 700 lines of dmapi overhead.  If we'll ever get HSM
support in mainline at least the namespace events can be done much saner
in the VFS instead of the individual filesystem, so it's not like this
is much help for future work.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

And also drop a useless argument to xfs_iomap_write_direct.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Now that struct xfs_iomap contains exactly the same units as struct
xfs_bmbt_irec we can just use the latter directly in the aops code.
Replace the missing IOMAP_NEW flag with a new boolean output
parameter to xfs_iomap.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Report the iomap_bn field of struct xfs_iomap in terms of filesystem
blocks instead of in terms of bytes.  Shift the byte conversions
into the caller, and replace the IOMAP_DELAY and IOMAP_HOLE flag
checks with checks for HOLESTARTBLOCK and DELAYSTARTBLOCK.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Report the iomap_offset and iomap_bsize fields of struct xfs_iomap
in terms of fsblocks instead of in terms of disk blocks.  Shift the
byte conversions into the callers temporarily, but they will
disappear or get cleaned up later.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The iomap_delta field in struct xfs_iomap just contains the
difference between the offset passed to xfs_iomap and the
iomap_offset.  Just calculate it in the only caller that cares.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>