Export xfs_icsb_modify_counters and always use it for modifying
the per-cpu counters.  Remove support for per-cpu counters from
xfs_mod_incore_sb to simplify it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Fail the mount if we can't allocate memory for the per-CPU counters.
This is consistent with how we handle everything else in the mount
path and makes the superblock counter modification a lot simpler.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

pahole reports the struct xfs_buf has quite a few holes in it, so
packing the structure better will reduce the size of it by 16 bytes.
Also, move all the fields used in cache lookups into the first
cacheline.

Before on x86_64:

        /* size: 320, cachelines: 5 */
	/* sum members: 298, holes: 6, sum holes: 22 */

After on x86_64:

        /* size: 304, cachelines: 5 */
	/* padding: 6 */
	/* last cacheline: 48 bytes */
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

The buffer cache hash is showing typical hash scalability problems.
In large scale testing the number of cached items growing far larger
than the hash can efficiently handle. Hence we need to move to a
self-scaling cache indexing mechanism.

I have selected rbtrees for indexing becuse they can have O(log n)
search scalability, and insert and remove cost is not excessive,
even on large trees. Hence we should be able to cache large numbers
of buffers without incurring the excessive cache miss search
penalties that the hash is imposing on us.

To ensure we still have parallel access to the cache, we need
multiple trees. Rather than hashing the buffers by disk address to
select a tree, it seems more sensible to separate trees by typical
access patterns. Most operations use buffers from within a single AG
at a time, so rather than searching lots of different lists,
separate the buffer indexes out into per-AG rbtrees. This means that
searches during metadata operation have a much higher chance of
hitting cache resident nodes, and that updates of the tree are less
likely to disturb trees being accessed on other CPUs doing
independent operations.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Memory reclaim via shrinkers has a terrible habit of having N+M
concurrent shrinker executions (N = num CPUs, M = num kswapds) all
trying to shrink the same cache. When the cache they are all working
on is protected by a single spinlock, massive contention an
slowdowns occur.

Wrap the per-ag inode caches with a reclaim mutex to serialise
reclaim access to the AG. This will block concurrent reclaim in each
AG but still allow reclaim to scan multiple AGs concurrently. Allow
shrinkers to move on to the next AG if it can't get the lock, and if
we can't get any AG, then start blocking on locks.

To prevent reclaimers from continually scanning the same inodes in
each AG, add a cursor that tracks where the last reclaim got up to
and start from that point on the next reclaim. This should avoid
only ever scanning a small number of inodes at the satart of each AG
and not making progress. If we have a non-shrinker based reclaim
pass, ignore the cursor and reset it to zero once we are done.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Batch and optimise the per-ag inode lookup for reclaim to minimise
scanning overhead. This involves gang lookups on the radix trees to
get multiple inodes during each tree walk, and tighter validation of
what inodes can be reclaimed without blocking befor we take any
locks.

This is based on ideas suggested in a proof-of-concept patch
posted by Nick Piggin.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

With the reclaim code separated from the generic walking code, it is
simple to implement batched lookups for the generic walk code.
Separate out the inode validation from the execute operations and
modify the tree lookups to get a batch of inodes at a time.

Reclaim operations will be optimised separately.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

When doing read side inode cache walks, the code to validate and
grab an inode is common to all callers. Split it out of the execute
callbacks in preparation for batching lookups. Similarly, split out
the inode reference dropping from the execute callbacks into the
main lookup look to be symmetric with the grab.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

The reclaim walk requires different locking and has a slightly
different walk algorithm, so separate it out so that it can be
optimised separately.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

For RT and external log devices, we never use hashed buffers on them
now.  Remove the buftarg hash tables that are set up for them.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

When we are checking we can access the last block of each device, we
do not need to use cached buffers as they will be tossed away
immediately. Use uncached buffers for size checks so that all IO
prior to full in-memory structure initialisation does not use the
buffer cache.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Filesystem level managed buffers are buffers that have their
lifecycle controlled by the filesystem layer, not the buffer cache.
We currently cache these buffers, which makes cleanup and cache
walking somewhat troublesome. Convert the fs managed buffers to
uncached buffers obtained by via xfs_buf_get_uncached(), and remove
the XBF_FS_MANAGED special cases from the buffer cache.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Each buffer contains both a buftarg pointer and a mount pointer. If
we add a mount pointer into the buftarg, we can avoid needing the
b_mount field in every buffer and grab it from the buftarg when
needed instead. This shrinks the xfs_buf by 8 bytes.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

To avoid the need to use cached buffers for single-shot or buffers
cached at the filesystem level, introduce a new buffer read
primitive that bypasses the cache an reads directly from disk.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

xfs_buf_get_nodaddr() is really used to allocate a buffer that is
uncached. While it is not directly assigned a disk address, the fact
that they are not cached is a more important distinction. With the
upcoming uncached buffer read primitive, we should be consistent
with this disctinction.

While there, make page allocation in xfs_buf_get_nodaddr() safe
against memory reclaim re-entrancy into the filesystem by allowing
a flags parameter to be passed.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Under heavy multi-way parallel create workloads, the VFS struggles
to write back all the inodes that have been changed in age order.
The bdi flusher thread becomes CPU bound, spending 85% of it's time
in the VFS code, mostly traversing the superblock dirty inode list
to separate dirty inodes old enough to flush.

We already keep an index of all metadata changes in age order - in
the AIL - and continued log pressure will do age ordered writeback
without any extra overhead at all. If there is no pressure on the
log, the xfssyncd will periodically write back metadata in ascending
disk address offset order so will be very efficient.

Hence we can stop marking VFS inodes dirty during transaction commit
or when changing timestamps during transactions. This will keep the
inodes in the superblock dirty list to those containing data or
unlogged metadata changes.

However, the timstamp changes are slightly more complex than this -
there are a couple of places that do unlogged updates of the
timestamps, and the VFS need to be informed of these. Hence add a
new function xfs_trans_ichgtime() for transactional changes,
and leave xfs_ichgtime() for the non-transactional changes.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

When we start taking a reference to the per-ag for every cached
buffer in the system, kernel lockstat profiling on an 8-way create
workload shows the mp->m_perag_lock has higher acquisition rates
than the inode lock and has significantly more contention. That is,
it becomes the highest contended lock in the system.

The perag lookup is trivial to convert to lock-less RCU lookups
because perag structures never go away. Hence the only thing we need
to protect against is tree structure changes during a grow. This can
be done simply by replacing the locking in xfs_perag_get() with RCU
read locking. This removes the mp->m_perag_lock completely from this
path.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

When we start taking references per cached buffer to the the perag
it is cached on, it will blow the current debug maximum reference
count assert out of the water. The assert has never caught a bug,
and we have tracing to track changes if there ever is a problem,
so just remove it.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

When commiting a transaction, we do a lock CIL state lock round trip
on every single log vector we insert into the CIL. This is resulting
in the lock being as hot as the inode and dcache locks on 8-way
create workloads. Rework the insertion loops to bring the number
of lock round trips to one per transaction for log vectors, and one
more do the busy extents.

Also change the allocation of the log vector buffer not to zero it
as we copy over the entire allocated buffer anyway.

This patch also includes a structural cleanup to the CIL item
insertion provided by Christoph Hellwig.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Ionut Gabriel Popescu <poyo_vl@yahoo.com> submitted a simple change
to eliminate some "may be used uninitialized" warnings when building
XFS.  The reported condition seems to be something that GCC did not
used to recognize or report.  The warnings were produced by:

    gcc version 4.5.0 20100604
    [gcc-4_5-branch revision 160292] (SUSE Linux)
Signed-off-by: NIonut Gabriel Popescu <poyo_vl@yahoo.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The implementation os ->kill_root only differ by either simply
zeroing out the now unused buffer in the btree cursor in the inode
allocation btree or using xfs_btree_setbuf in the allocation btree.

Initially both of them used xfs_btree_setbuf, but the use in the
ialloc btree was removed early on because it interacted badly with
xfs_trans_binval.

In addition to zeroing out the buffer in the cursor xfs_btree_setbuf
updates the bc_ra array in the btree cursor, and calls
xfs_trans_brelse on the buffer previous occupying the slot.

The bc_ra update should be done for the alloc btree updated too,
although the lack of it does not cause serious problems.  The
xfs_trans_brelse call on the other hand is effectively a no-op in
the end - it keeps decrementing the bli_recur refcount until it hits
zero, and then just skips out because the buffer will always be
dirty at this point.  So removing it for the allocation btree is
just fine.

So unify the code and move it to xfs_btree.c.  While we're at it
also replace the call to xfs_btree_setbuf with a NULL bp argument in
xfs_btree_del_cursor with a direct call to xfs_trans_brelse given
that the cursor is beeing freed just after this and the state
updates are superflous.  After this xfs_btree_setbuf is only used
with a non-NULL bp argument and can thus be simplified.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

In xfs_qm_dqflush we know that q_blkno must be initialized already from a
previous xfs_qm_dqread.  So instead of calling xfs_qm_dqtobp we can
simply read the quota buffer directly.  This also saves us from a duplicate
xfs_qm_dqcheck call check and allows xfs_qm_dqtobp to be simplified now
that it is always called for a newly initialized inode.  In addition to
that properly unwind all locks in xfs_qm_dqflush when xfs_qm_dqcheck
fails.

This mirrors a similar cleanup in the inode lookup done earlier.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

There is no need to have the users and group/project quota locked at the
same time.  Get rid of xfs_qm_dqget_noattach and just do a xfs_qm_dqget
inside xfs_qm_quotacheck_dqadjust for the quota we are operating on
right now.  The new version of xfs_qm_quotacheck_dqadjust holds the
inode lock over it's operations, which is not a problem as it simply
increments counters and there is no concern about log contention
during mount time.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

XFS_IOC_ZERO_RANGE is the equivalent of an atomic XFS_IOC_UNRESVSP/
XFS_IOC_RESVSP call pair. It enabled ranges of written data to be
turned into zeroes without requiring IO or having to free and
reallocate the extents in the range given as would occur if we had
to punch and then preallocate them separately.  This enables
applications to zero parts of files very quickly without changing
the layout of the files in any way.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

While XFS passes ranges to operate on from the core code, the
functions being called ignore the either the entire range or the end
of the range. This is historical because when the function were
written linux didn't have the necessary range operations. Update the
functions to use the correct operations.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

Tony Luck reports that the addition of the access_ok() check in commit
0eead9ab ("Don't dump task struct in a.out core-dumps") broke the
ia64 compile due to missing the necessary header file includes.

Rather than add yet another include (<asm/unistd.h>) to make everything
happy, just uninline the silly core dump helper functions and move the
bodies to fs/exec.c where they make a lot more sense.

dump_seek() in particular was too big to be an inline function anyway,
and none of them are in any way performance-critical.  And we really
don't need to mess up our include file headers more than they already
are.
Reported-and-tested-by: NTony Luck <tony.luck@gmail.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
  ehea: Fix a checksum issue on the receive path
  net: allow FEC driver to use fixed PHY support
  tg3: restore rx_dropped accounting
  b44: fix carrier detection on bind
  net: clear heap allocations for privileged ethtool actions
  NET: wimax, fix use after free
  ATM: iphase, remove sleep-inside-atomic
  ATM: mpc, fix use after free
  ATM: solos-pci, remove use after free
  net/fec: carrier off initially to avoid root mount failure
  r8169: use device model DMA API
  r8169: allocate with GFP_KERNEL flag when able to sleep

akiphie points out that a.out core-dumps have that odd task struct
dumping that was never used and was never really a good idea (it goes
back into the mists of history, probably the original core-dumping
code).  Just remove it.

Also do the access_ok() check on dump_write().  It probably doesn't
matter (since normal filesystems all seem to do it anyway), but he
points out that it's normally done by the VFS layer, so ...

[ I suspect that we should possibly do "vfs_write()" instead of
  calling ->write directly.  That also does the whole fsnotify and write
  statistics thing, which may or may not be a good idea. ]

And just to be anal, do this all for the x86-64 32-bit a.out emulation
code too, even though it's not enabled (and won't currently even
compile)
Reported-by: Nakiphie <akiphie@lavabit.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx:
  ioat2: fix performance regression

* 'for-2.6.36' of git://linux-nfs.org/~bfields/linux:
  nfsd: fix BUG at fs/nfsd/nfsfh.h:199 on unlink

Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  ring-buffer: Fix typo of time extends per page
  perf, MIPS: Support cross compiling of tools/perf for MIPS
  perf: Fix incorrect copy_from_user() usage

* master.kernel.org:/home/rmk/linux-2.6-arm:
  ARM: relax ioremap prohibition (309caa9c) for -final and -stable
  ARM: 6440/1: ep93xx: DMA: fix channel_disable
  cpuimx27: fix i2c bus selection
  cpuimx27: fix compile when ULPI is selected
  ARM: 6435/1: Fix HWCAP_TLS flag for ARM11MPCore/Cortex-A9
  ARM: 6436/1: AT91: Fix power-saving in idle-mode on 926T processors
  ARM: fix section mismatch warnings in Versatile Express
  ARM: 6412/1: kprobes-decode: add support for MOVW instruction
  ARM: 6419/1: mmu: Fix MT_MEMORY and MT_MEMORY_NONCACHED pte flags
  ARM: 6416/1: errata: faulty hazard checking in the Store Buffer may lead to data corruption

Merge branch 'omap-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6

* 'omap-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6:
  omap: iommu-load cam register before flushing the entry

* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm/radeon/kms: Silent spurious error message
  drm/radeon/kms: fix bad cast/shift in evergreen.c
  drm/radeon/kms: make TV/DFP table info less verbose
  drm/radeon/kms: leave certain CP int bits enabled
  drm/radeon/kms: avoid corner case issue with unmappable vram V2

Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, numa: For each node, register the memory blocks actually used
  x86, AMD, MCE thresholding: Fix the MCi_MISCj iteration order
  x86, mce, therm_throt.c: Fix missing curly braces in error handling logic

Commit 07934481 "DMAENGINE: generic channel status v2" changed the interface for
how dma channel progress is retrieved.  It inadvertently exported an internal
helper function ioat_tx_status() instead of ioat_dma_tx_status().  The latter
polls the hardware to get the latest completion state, while the helper just
evaluates the current state without touching hardware.  The effect is that we
end up waiting for completion timeouts or descriptor allocation errors before
the completion state is updated.

iperf (before fix):
[SUM]  0.0-41.3 sec   364 MBytes  73.9 Mbits/sec

iperf (after fix):
[SUM]  0.0- 4.5 sec   499 MBytes   940 Mbits/sec

This is a regression starting with 2.6.35.

Cc: <stable@kernel.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Linus Walleij <linus.walleij@stericsson.com>
Cc: Maciej Sosnowski <maciej.sosnowski@intel.com>
Reported-by: NRichard Scobie <richard@sauce.co.nz>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Currently we set all skbs with CHECKSUM_UNNECESSARY, even
those whose protocol we don't know. This patch just
add the CHECKSUM_COMPLETE tag for non TCP/UDP packets.
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NBreno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: NJay Vosburgh <fubar@us.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As of commit 43a9aa64 "NFSD:
Fill in WCC data for REMOVE, RMDIR, MKNOD, and MKDIR", we sometimes call
fh_unlock on a filehandle that isn't fully initialized.

We should fix up the callers, but as a quick fix it is also sufficient
just to remove this assertion.
Reported-by: NMarius Tolzmann <tolzmann@molgen.mpg.de>
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>

At least one board using the FEC driver does not have a conventional
PHY attached to it, it is directly connected to a somewhat simple
ethernet switch (the board is the SnapGear/LITE, and the attached
4-port ethernet switch is a RealTek RTL8305). This switch does not
present the usual register interface of a PHY, it presents nothing.
So a PHY scan will find nothing - it finds ID's of 0 for each PHY
on the attached MII bus.

After the FEC driver was changed to use phylib for supporting PHYs
it no longer works on this particular board/switch setup.

Add code support to use a fixed phy if no PHY is found on the MII bus.
This is based on the way the cpmac.c driver solved this same problem.
Signed-off-by: NGreg Ungerer <gerg@uclinux.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>