Queue delwri buffers on a local on-stack list instead of a per-buftarg one,
and write back the buffers per-process instead of by waking up xfsbufd.

This is now easily doable given that we have very few places left that write
delwri buffers:

 - log recovery:
	Only done at mount time, and already forcing out the buffers
	synchronously using xfs_flush_buftarg

 - quotacheck:
	Same story.

 - dquot reclaim:
	Writes out dirty dquots on the LRU under memory pressure.  We might
	want to look into doing more of this via xfsaild, but it's already
	more optimal than the synchronous inode reclaim that writes each
	buffer synchronously.

 - xfsaild:
	This is the main beneficiary of the change.  By keeping a local list
	of buffers to write we reduce latency of writing out buffers, and
	more importably we can remove all the delwri list promotions which
	were hitting the buffer cache hard under sustained metadata loads.

The implementation is very straight forward - xfs_buf_delwri_queue now gets
a new list_head pointer that it adds the delwri buffers to, and all callers
need to eventually submit the list using xfs_buf_delwi_submit or
xfs_buf_delwi_submit_nowait.  Buffers that already are on a delwri list are
skipped in xfs_buf_delwri_queue, assuming they already are on another delwri
list.  The biggest change to pass down the buffer list was done to the AIL
pushing. Now that we operate on buffers the trylock, push and pushbuf log
item methods are merged into a single push routine, which tries to lock the
item, and if possible add the buffer that needs writeback to the buffer list.
This leads to much simpler code than the previous split but requires the
individual IOP_PUSH instances to unlock and reacquire the AIL around calls
to blocking routines.

Given that xfsailds now also handle writing out buffers, the conditions for
log forcing and the sleep times needed some small changes.  The most
important one is that we consider an AIL busy as long we still have buffers
to push, and the other one is that we do increment the pushed LSN for
buffers that are under flushing at this moment, but still count them towards
the stuck items for restart purposes.  Without this we could hammer on stuck
items without ever forcing the log and not make progress under heavy random
delete workloads on fast flash storage devices.

[ Dave Chinner:
	- rebase on previous patches.
	- improved comments for XBF_DELWRI_Q handling
	- fix XBF_ASYNC handling in queue submission (test 106 failure)
	- rename delwri submit function buffer list parameters for clarity
	- xfs_efd_item_push() should return XFS_ITEM_PINNED ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Instead of adding buffers to the delwri list as soon as they are logged,
even if they can't be written until commited because they are pinned
defer adding them to the delwri list until xfsaild pushes them.  This
makes the code more similar to other log items and prepares for writing
buffers directly from xfsaild.

The complication here is that we need to fail buffers that were added
but not logged yet in xfs_buf_item_unpin, borrowing code from
xfs_bioerror.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Instead of writing the buffer directly from inside xfs_qm_dqflush return it
to the caller and let the caller decide what to do with the buffer.  Also
remove the pincount check in xfs_qm_dqflush that all non-blocking callers
already implement and the now unused flags parameter and the XFS_DQ_IS_DIRTY
check that all callers already perform.

[ Dave Chinner: fixed build error cause by missing '{'. ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Instead of writing the buffer directly from inside xfs_iflush return it to
the caller and let the caller decide what to do with the buffer.  Also
remove the pincount check in xfs_iflush that all non-blocking callers already
implement and the now unused flags parameter.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

We already flush dirty inodes throug the AIL regularly, there is no reason
to have second thread compete with it and disturb the I/O pattern.  We still
do write inodes when doing a synchronous reclaim from the shrinker or during
unmount for now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Now that we write back all metadata either synchronously or through
the AIL we can simply implement metadata freezing in terms of
emptying the AIL.

The implementation for this is fairly simply and straight-forward:
A new routine is added that asks the xfsaild to push the AIL to the
end and waits for it to complete and send a wakeup. The routine will
then loop if the AIL is not actually empty, and continue to do so
until the AIL is compeltely empty.

We keep an inode reclaim pass in the freeze process to avoid having
memory pressure have to reclaim inodes that require dirtying the
filesystem to be reclaimed after the freeze has completed. This
means we can also treat unmount in the exact same way as freeze.

As an upside we can now remove the radix tree based inode writeback
and xfs_unmountfs_writesb.

[ Dave Chinner:
	- Cleaned up commit message.
	- Added inode reclaim passes back into freeze.
	- Cleaned up wakeup mechanism to avoid the use of a new
	  sleep counter variable. ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Provide a variant of xlog_assign_tail_lsn that has the AIL lock already
held.  By doing so we do an additional atomic_read + atomic_set under
the lock, which comes down to two instructions.

Switch xfs_trans_ail_update_bulk and xfs_trans_ail_delete_bulk to the
new version to reduce the number of lock roundtrips, and prepare for
a new addition that would require a third lock roundtrip in
xfs_trans_ail_delete_bulk.  This addition is also the reason for
slightly rearranging the conditionals and relying on xfs_log_space_wake
for checking that the filesystem has been shut down internally.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

If a filesystem has been forced shutdown we are never going to write inodes
to disk, which means the inode items will stay in the AIL until we free
the inode. Currently that is not a problem, but a pending change requires us
to empty the AIL before shutting down the filesystem. In that case leaving
the inode in the AIL is lethal. Make sure to remove the log item from the AIL
to allow emptying the AIL on shutdown filesystems.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

If a filesystem has been forced shutdown we are never going to write dquots
to disk, which means the dquot items will stay in the AIL forever.
Currently that is not a problem, but a pending chance requires us to
empty the AIL before shutting down the filesystem, in which case this
behaviour is lethal.  Make sure to remove the log item from the AIL
to allow emptying the AIL on shutdown filesystems.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Issuing a block device flush request in transaction context using GFP_KERNEL
directly can cause deadlocks due to memory reclaim recursion. Use GFP_NOFS to
avoid recursion from reclaim context.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

I've been seeing regular ASSERT failures in xfstests when running
fsstress based tests over the past month. xfs_getbmap() has been
failing this test:

XFS: Assertion failed: ((iflags & BMV_IF_DELALLOC) != 0) ||
(map[i].br_startblock != DELAYSTARTBLOCK), file: fs/xfs/xfs_bmap.c,
line: 5650

where it is encountering a delayed allocation extent after writing
all the dirty data to disk and then walking the extent map
atomically by holding the XFS_IOLOCK_SHARED to prevent new delayed
allocation extents from being created.

Test 083 on a 512 byte block size filesystem was used to reproduce
the problem, because it only had a 5s run timeand would usually fail
every 3-4 runs. This test is exercising ENOSPC behaviour by running
fsstress on a nearly full filesystem. The following trace extract
shows the final few events on the inode that tripped the assert:

 xfs_ilock:             flags ILOCK_EXCL caller xfs_setfilesize
 xfs_setfilesize:       isize 0x180000 disize 0x12d400 offset 0x17e200 count 7680

file size updated to 0x180000 by IO completion

 xfs_ilock:             flags ILOCK_EXCL caller xfs_iomap_write_delay
 xfs_iext_insert:       state  idx 3 offset 3072 block 4503599627239432 count 1 flag 0 caller xfs_bmap_add_extent_hole_delay
 xfs_get_blocks_alloc:  size 0x180000 offset 0x180000 count 512 type  startoff 0xc00 startblock -1 blockcount 0x1
 xfs_ilock:             flags ILOCK_EXCL caller __xfs_get_blocks

delalloc write, adding a single block at offset 0x180000

 xfs_delalloc_enospc:   isize 0x180000 disize 0x180000 offset 0x180200 count 512

ENOSPC trying to allocate a dellalloc block at offset 0x180200

 xfs_ilock:             flags ILOCK_EXCL caller xfs_iomap_write_delay
 xfs_get_blocks_alloc:  size 0x180000 offset 0x180200 count 512 type  startoff 0xc00 startblock -1 blockcount 0x2

And succeeding on retry after flushing dirty inodes.

 xfs_ilock:             flags ILOCK_EXCL caller __xfs_get_blocks
 xfs_delalloc_enospc:   isize 0x180000 disize 0x180000 offset 0x180400 count 512

ENOSPC trying to allocate a dellalloc block at offset 0x180400

 xfs_ilock:             flags ILOCK_EXCL caller xfs_iomap_write_delay
 xfs_delalloc_enospc:   isize 0x180000 disize 0x180000 offset 0x180400 count 512

And failing the retry, giving a real ENOSPC error.

 xfs_ilock:             flags ILOCK_EXCL caller xfs_vm_write_failed
                                                ^^^^^^^^^^^^^^^^^^^
The smoking gun - the write being failed and cleaning up delalloc
blocks beyond EOF allocated by the failed write.

 xfs_getattr:
 xfs_ilock:             flags IOLOCK_SHARED caller xfs_getbmap
 xfs_ilock:             flags ILOCK_SHARED caller xfs_ilock_map_shared

And that's where we died almost immediately afterwards.
xfs_bmapi_read() found delalloc extent beyond current file in memory
file size. Some debug I added to xfs_getbmap() showed the state just
before the assert failure:

 ino 0x80e48: off 0xc00, fsb 0xffffffffffffffff, len 0x1, size 0x180000
 start_fsb 0x106, end_fsb 0x638
 ino flags 0x2 nex 0xd bmvcnt 0x555, len 0x3c58a6f23c0bf1, start 0xc00
 ext 0: off 0x1fc, fsb 0x24782, len 0x254
 ext 1: off 0x450, fsb 0x40851, len 0x30
 ext 2: off 0x480, fsb 0xd99, len 0x1b8
 ext 3: off 0x92f, fsb 0x4099a, len 0x3b
 ext 4: off 0x96d, fsb 0x41844, len 0x98
 ext 5: off 0xbf1, fsb 0x408ab, len 0xf

which shows that we found a single delalloc block beyond EOF (first
line of output) when we were returning the map for a length
somewhere around 10^16 bytes long (second line), and the on-disk
extents showed they didn't go past EOF (last lines).

Further debug added to xfs_vm_write_failed() showed this happened
when punching out delalloc blocks beyond the end of the file after
the failed write:

[  132.606693] ino 0x80e48: vwf to 0x181000, sze 0x180000
[  132.609573] start_fsb 0xc01, end_fsb 0xc08

It punched the range 0xc01 -> 0xc08, but the range we really need to
punch is 0xc00 -> 0xc07 (8 blocks from 0xc00) as this testing was
run on a 512 byte block size filesystem (8 blocks per page).
the punch from is 0xc00. So end_fsb is correct, but start_fsb is
wrong as we punch from start_fsb for (end_fsb - start_fsb) blocks.
Hence we are not punching the delalloc block beyond EOF in the case.

The fix is simple - it's a silly off-by-one mistake in calculating
the range. It's especially silly because the macro used to calculate
the start_fsb already takes into account the case where the inode
size is an exact multiple of the filesystem block size...
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Ben 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: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Instead of calling xfs_zero_eof with the ilock held only take it internally
for the minimall required critical section around xfs_bmapi_read.  This
also requires changing the calling convention for xfs_zero_last_block
slightly.  The actual zeroing operation is still serialized by the iolock,
which must be taken exclusively over the call to xfs_zero_eof.

We could in fact use a shared lock for the xfs_bmapi_read calls as long as
the extent list has been read in, but given that we already hold the iolock
exclusively there is little reason to micro optimize this further.
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

We do not need the ilock for most checks done in the beginning of
xfs_setattr_size.  Replace the long critical section before starting the
transaction with a smaller one around xfs_zero_eof and an optional one
inside xfs_qm_dqattach that isn't entered unless using quotas.  While
this isn't a big optimization for xfs_setattr_size itself it will allow
pushing the ilock into xfs_zero_eof itself later.
Signed-off-by: Christoph Hellwig <hch@lst.de>

We do not need the ilock for generic_write_checks and the i_size_read,
which are protected by i_mutex and/or iolock, so reduce the ilock
critical section to just the call to xfs_zero_eof.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Check if we actually need to attach a dquot before taking the ilock in
xfs_qm_dqattach.  This avoid superflous lock roundtrips for the common cases
of quota support compiled in but not activated on a filesystem and an
inode that already has the dquots attached.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Because the mount process can run a quotacheck and consume lots of
inodes, we need to be able to run periodic inode reclaim during the
mount process. This will prevent running the system out of memory
during quota checks.

This essentially reverts 2bcf6e97, but that is safe to do now that
the quota sync code that was causing problems during long quotacheck
executions is now gone.

The reclaim work is currently protected from running during the
unmount process by a check against MS_ACTIVE. Unfortunately, this
also means that the reclaim work cannot run during mount.  The
unmount process should stop the reclaim cleanly before freeing
anything that the reclaim work depends on, so there is no need to
have this guard in place.

Also, the inode reclaim work is demand driven, so there is no need
to start it immediately during mount. It will be started the moment
an inode is queued for reclaim, so qutoacheck will trigger it just
fine.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

Check if the project quota is running or not before performing
xfs_qm_statvfs(), just return if not.  Otherwise the ASSERT
XFS_IS_QUOTA_RUNNING in xfs_qm_dqget will be popped.
Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

xfs-masters@oss.sgi.com will be retired in favor of xfs@oss.sgi.com
sometime soon.
Signed-off-by: Ben Myers <bpm@sgi.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

Pull two more small regmap fixes from Mark Brown:
 - Now we have users for it that aren't running Android it turns out
   that regcache_sync_region() is much more useful to drivers if it's
   exported for use by modules.  Who knew?
 - Make sure we don't divide by zero when doing debugfs dumps of
   rbtrees, not visible up until now because everything was providing at
   least some cache on startup.

* tag 'regmap-3.4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap:
  regmap: prevent division by zero in rbtree_show
  regmap: Export regcache_sync_region()

Pull a few KVM fixes from Avi Kivity:
 "A bunch of powerpc KVM fixes, a guest and a host RCU fix (unrelated),
  and a small build fix."

* 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Resolve RCU vs. async page fault problem
  KVM: VMX: vmx_set_cr0 expects kvm->srcu locked
  KVM: PMU: Fix integer constant is too large warning in kvm_pmu_set_msr()
  KVM: PPC: Book3S: PR: Fix preemption
  KVM: PPC: Save/Restore CR over vcpu_run
  KVM: PPC: Book3S HV: Save and restore CR in __kvmppc_vcore_entry
  KVM: PPC: Book3S HV: Fix kvm_alloc_linear in case where no linears exist
  KVM: PPC: Book3S: Compile fix for ppc32 in HIOR access code

Pull SuperH fixes from Paul Mundt.

* tag 'sh-for-linus' of git://github.com/pmundt/linux-sh:
  sh: fix clock-sh7757 for the latest sh_mobile_sdhi driver
  serial: sh-sci: use serial_port_in/out vs sci_in/out.
  sh: vsyscall: Fix up .eh_frame generation.
  sh: dma: Fix up device attribute mismatch from sysdev fallout.
  sh: dwarf unwinder depends on SHcompact.
  sh: fix up fallout from system.h disintegration.

Pull security layer fixlet from James Morris.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
  sysctl: fix write access to dmesg_restrict/kptr_restrict

Pull ACPI & Power Management patches from Len Brown:
 "Two fixes for cpuidle merge-window changes, plus a URL fix in
  MAINTAINERS"

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
  MAINTAINERS: Update git url for ACPI
  cpuidle: Fix panic in CPU off-lining with no idle driver
  ACPI processor: Use safe_halt() rather than halt() in acpi_idle_play_dead()

Pull target fixes from Nicholas Bellinger:
 "Pull two tcm_fc fabric related fixes for -rc2:

  Note that both have been CC'ed to stable, and patch #1 is the
  important one that addresses a memory corruption bug related to FC
  exchange timeouts + command abort.

  Thanks again to MDR for tracking down this issue!"

* '3.4-rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
  tcm_fc: Do not free tpg structure during wq allocation failure
  tcm_fc: Add abort flag for gracefully handling exchange timeout

Avoid freeing a registered tpg structure if an alloc_workqueue call
fails.  This fixes a bug where the failure was leaking memory associated
with se_portal_group setup during the original core_tpg_register() call.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Acked-by: Kiran Patil <Kiran.patil@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

Add abort flag and use it to terminate processing when an exchange
is timed out or is reset. The abort flag is used in place of the
transport_generic_free_cmd function call in the reset and timeout
cases, because calling that function in that context would free
memory that was in use. The aborted flag allows the lifetime to
be managed in a more normal way, while truncating the processing.

This change eliminates a source of memory corruption which
manifested in a variety of ugly ways.

(nab: Drop unused struct fc_exch *ep in ft_recv_seq)
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Acked-by: Kiran Patil <Kiran.patil@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

Signed-off-by: Igor Murzov <e-mail@date.by>
Signed-off-by: Len Brown <len.brown@intel.com>

Pull arch/tile bug fixes from Chris Metcalf:
 "This includes Paul Gortmaker's change to fix the <asm/system.h>
  disintegration issues on tile, a fix to unbreak the tilepro ethernet
  driver, and a backlog of bugfix-only changes from internal Tilera
  development over the last few months.

  They have all been to LKML and on linux-next for the last few days.
  The EDAC change to MAINTAINERS is an oddity but discussion on the
  linux-edac list suggested I ask you to pull that change through my
  tree since they don't have a tree to pull edac changes from at the
  moment."

* 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile: (39 commits)
  drivers/net/ethernet/tile: fix netdev_alloc_skb() bombing
  MAINTAINERS: update EDAC information
  tilepro ethernet driver: fix a few minor issues
  tile-srom.c driver: minor code cleanup
  edac: say "TILEGx" not "TILEPro" for the tilegx edac driver
  arch/tile: avoid accidentally unmasking NMI-type interrupt accidentally
  arch/tile: remove bogus performance optimization
  arch/tile: return SIGBUS for addresses that are unaligned AND invalid
  arch/tile: fix finv_buffer_remote() for tilegx
  arch/tile: use atomic exchange in arch_write_unlock()
  arch/tile: stop mentioning the "kvm" subdirectory
  arch/tile: export the page_home() function.
  arch/tile: fix pointer cast in cacheflush.c
  arch/tile: fix single-stepping over swint1 instructions on tilegx
  arch/tile: implement panic_smp_self_stop()
  arch/tile: add "nop" after "nap" to help GX idle power draw
  arch/tile: use proper memparse() for "maxmem" options
  arch/tile: fix up locking in pgtable.c slightly
  arch/tile: don't leak kernel memory when we unload modules
  arch/tile: fix bug in delay_backoff()
  ...

Merge tag 'stable/for-linus-3.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull xen fixes from Konrad Rzeszutek Wilk:
 "Two fixes for regressions:
   * one is a workaround that will be removed in v3.5 with proper fix in
     the tip/x86 tree,
   * the other is to fix drivers to load on PV (a previous patch made
     them only load in PVonHVM mode).

  The rest are just minor fixes in the various drivers and some cleanup
  in the core code."

* tag 'stable/for-linus-3.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/pcifront: avoid pci_frontend_enable_msix() falsely returning success
  xen/pciback: fix XEN_PCI_OP_enable_msix result
  xen/smp: Remove unnecessary call to smp_processor_id()
  xen/x86: Workaround 'x86/ioapic: Add register level checks to detect bogus io-apic entries'
  xen: only check xen_platform_pci_unplug if hvm

Pull MMC fixes from Chris Ball:
 - Disable use of MSI in sdhci-pci, which caused multiple chipsets to
   stop working in 3.4-rc1.  I'll wait to turn this on again until we
   have a chipset whitelist for it.
 - Fix a libertas SDIO powered-resume regression introduced in 3.3;
   thanks to Neil Brown and Rafael Wysocki for this fix.
 - Fix module reloading on omap_hsmmc.
 - Stop trusting the spec/card's specified maximum data timeout length,
   and use three seconds instead.  Previously we used 300ms.

Also cleanups and fixes for s3c, atmel, sh_mmcif and omap_hsmmc.

* tag 'mmc-fixes-for-3.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc: (28 commits)
  mmc: use really long write timeout to deal with crappy cards
  mmc: sdhci-dove: Fix compile error by including module.h
  mmc: Prevent 1.8V switch for SD hosts that don't support UHS modes.
  Revert "mmc: sdhci-pci: Add MSI support"
  Revert "mmc: sdhci-pci: add quirks for broken MSI on O2Micro controllers"
  mmc: core: fix power class selection
  mmc: omap_hsmmc: fix module re-insertion
  mmc: omap_hsmmc: convert to module_platform_driver
  mmc: omap_hsmmc: make it behave well as a module
  mmc: omap_hsmmc: trivial cleanups
  mmc: omap_hsmmc: context save after enabling runtime pm
  mmc: omap_hsmmc: use runtime put sync in probe error patch
  mmc: sdio: Use empty system suspend/resume callbacks at the bus level
  mmc: bus: print bus speed mode of UHS-I card
  mmc: sdhci-pci: add quirks for broken MSI on O2Micro controllers
  mmc: sh_mmcif: Simplify calculation of mmc->f_min
  mmc: sh_mmcif: mmc->f_max should be half of the bus clock
  mmc: sh_mmcif: double clock speed
  mmc: block: Remove use of mmc_blk_set_blksize
  mmc: atmel-mci: add support for odd clock dividers
  ...

I have a new optimized x86 "strncpy_from_user()" that will use these
same helper functions for all the same reasons the name lookup code uses
them.  This is preparation for that.

This moves them into an architecture-specific header file.  It's
architecture-specific for two reasons:

 - some of the functions are likely to want architecture-specific
   implementations.  Even if the current code happens to be "generic" in
   the sense that it should work on any little-endian machine, it's
   likely that the "multiply by a big constant and shift" implementation
   is less than optimal for an architecture that has a guaranteed fast
   bit count instruction, for example.

 - I expect that if architectures like sparc want to start playing
   around with this, we'll need to abstract out a few more details (in
   particular the actual unaligned accesses).  So we're likely to have
   more architecture-specific stuff if non-x86 architectures start using
   this.

   (and if it turns out that non-x86 architectures don't start using
   this, then having it in an architecture-specific header is still the
   right thing to do, of course)
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Fix a NULL pointer dereference panic in cpuidle_play_dead() during
CPU off-lining when no cpuidle driver is registered.  A cpuidle
driver may be registered at boot-time based on CPU type.  This patch
allows an off-lined CPU to enter HLT-based idle in this condition.
Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Cc: Boris Ostrovsky <boris.ostrovsky@amd.com>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Tested-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Len Brown <len.brown@intel.com>

Pull networking updates from David Miller:

 1) Fix inaccuracies in network driver interface documentation, from Ben
    Hutchings.

 2) Fix handling of negative offsets in BPF JITs, from Jan Seiffert.

 3) Compile warning, locking, and refcounting fixes in netfilter's
    xt_CT, from Pablo Neira Ayuso.

 4) phonet sendmsg needs to validate user length just like any other
    datagram protocol, fix from Sasha Levin.

 5) Ipv6 multicast code uses wrong loop index, from RongQing Li.

 6) Link handling and firmware fixes in bnx2x driver from Yaniv Rosner
    and Yuval Mintz.

 7) mlx4 erroneously allocates 4 pages at a time, regardless of page
    size, fix from Thadeu Lima de Souza Cascardo.

 8) SCTP socket option wasn't extended in a backwards compatible way,
    fix from Thomas Graf.

 9) Add missing address change event emissions to bonding, from Shlomo
    Pongratz.

10) /proc/net/dev regressed because it uses a private offset to track
    where we are in the hash table, but this doesn't track the offset
    pullback that the seq_file code does resulting in some entries being
    missed in large dumps.

    Fix from Eric Dumazet.

11) do_tcp_sendpage() unloads the send queue way too fast, because it
    invokes tcp_push() when it shouldn't.  Let the natural sequence
    generated by the splice paths, and the assosciated MSG_MORE
    settings, guide the tcp_push() calls.

    Otherwise what goes out of TCP is spaghetti and doesn't batch
    effectively into GSO/TSO clusters.

    From Eric Dumazet.

12) Once we put a SKB into either the netlink receiver's queue or a
    socket error queue, it can be consumed and freed up, therefore we
    cannot touch it after queueing it like that.

    Fixes from Eric Dumazet.

13) PPP has this annoying behavior in that for every transmit call it
    immediately stops the TX queue, then calls down into the next layer
    to transmit the PPP frame.

    But if that next layer can take it immediately, it just un-stops the
    TX queue right before returning from the transmit method.

    Besides being useless work, it makes several facilities unusable, in
    particular things like the equalizers.  Well behaved devices should
    only stop the TX queue when they really are full, and in PPP's case
    when it gets backlogged to the downstream device.

    David Woodhouse therefore fixed PPP to not stop the TX queue until
    it's downstream can't take data any more.

14) IFF_UNICAST_FLT got accidently lost in some recent stmmac driver
    changes, re-add.  From Marc Kleine-Budde.

15) Fix link flaps in ixgbe, from Eric W. Multanen.

16) Descriptor writeback fixes in e1000e from Matthew Vick.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (47 commits)
  net: fix a race in sock_queue_err_skb()
  netlink: fix races after skb queueing
  doc, net: Update ndo_start_xmit return type and values
  doc, net: Remove instruction to set net_device::trans_start
  doc, net: Update netdev operation names
  doc, net: Update documentation of synchronisation for TX multiqueue
  doc, net: Remove obsolete reference to dev->poll
  ethtool: Remove exception to the requirement of holding RTNL lock
  MAINTAINERS: update for Marvell Ethernet drivers
  bonding: properly unset current_arp_slave on slave link up
  phonet: Check input from user before allocating
  tcp: tcp_sendpages() should call tcp_push() once
  ipv6: fix array index in ip6_mc_add_src()
  mlx4: allocate just enough pages instead of always 4 pages
  stmmac: re-add IFF_UNICAST_FLT for dwmac1000
  bnx2x: Clear MDC/MDIO warning message
  bnx2x: Fix BCM57711+BCM84823 link issue
  bnx2x: Clear BCM84833 LED after fan failure
  bnx2x: Fix BCM84833 PHY FW version presentation
  bnx2x: Fix link issue for BCM8727 boards.
  ...

The original XenoLinux code has always had things this way, and for
compatibility reasons (in particular with a subsequent pciback
adjustment) upstream Linux should behave the same way (allowing for two
distinct error indications to be returned by the backend).
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Prior to 2.6.19 and as of 2.6.31, pci_enable_msix() can return a
positive value to indicate the number of vectors (less than the amount
requested) that can be set up for a given device. Returning this as an
operation value (secondary result) is fine, but (primary) operation
results are expected to be negative (error) or zero (success) according
to the protocol. With the frontend fixed to match the XenoLinux
behavior, the backend can now validly return zero (success) here,
passing the upper limit on the number of vectors in op->value.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

There is an extra and unnecessary call to smp_processor_id()
in cpu_bringup(). Remove it.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

The above mentioned patch checks the IOAPIC and if it contains
-1, then it unmaps said IOAPIC. But under Xen we get this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000040
IP: [<ffffffff8134e51f>] xen_irq_init+0x1f/0xb0
PGD 0
Oops: 0002 [#1] SMP
CPU 0
Modules linked in:

Pid: 1, comm: swapper/0 Not tainted 3.2.10-3.fc16.x86_64 #1 Dell Inc. Inspiron
1525                  /0U990C
RIP: e030:[<ffffffff8134e51f>]  [<ffffffff8134e51f>] xen_irq_init+0x1f/0xb0
RSP: e02b: ffff8800d42cbb70  EFLAGS: 00010202
RAX: 0000000000000000 RBX: 00000000ffffffef RCX: 0000000000000001
RDX: 0000000000000040 RSI: 00000000ffffffef RDI: 0000000000000001
RBP: ffff8800d42cbb80 R08: ffff8800d6400000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000ffffffef
R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000010
FS:  0000000000000000(0000) GS:ffff8800df5fe000(0000) knlGS:0000000000000000
CS:  e033 DS: 0000 ES: 0000 CR0:000000008005003b
CR2: 0000000000000040 CR3: 0000000001a05000 CR4: 0000000000002660
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process swapper/0 (pid: 1, threadinfo ffff8800d42ca000, task ffff8800d42d0000)
Stack:
 00000000ffffffef 0000000000000010 ffff8800d42cbbe0 ffffffff8134f157
 ffffffff8100a9b2 ffffffff8182ffd1 00000000000000a0 00000000829e7384
 0000000000000002 0000000000000010 00000000ffffffff 0000000000000000
Call Trace:
 [<ffffffff8134f157>] xen_bind_pirq_gsi_to_irq+0x87/0x230
 [<ffffffff8100a9b2>] ? check_events+0x12+0x20
 [<ffffffff814bab42>] xen_register_pirq+0x82/0xe0
 [<ffffffff814bac1a>] xen_register_gsi.part.2+0x4a/0xd0
 [<ffffffff814bacc0>] acpi_register_gsi_xen+0x20/0x30
 [<ffffffff8103036f>] acpi_register_gsi+0xf/0x20
 [<ffffffff8131abdb>] acpi_pci_irq_enable+0x12e/0x202
 [<ffffffff814bc849>] pcibios_enable_device+0x39/0x40
 [<ffffffff812dc7ab>] do_pci_enable_device+0x4b/0x70
 [<ffffffff812dc878>] __pci_enable_device_flags+0xa8/0xf0
 [<ffffffff812dc8d3>] pci_enable_device+0x13/0x20

The reason we are dying is b/c the call acpi_get_override_irq() is used,
which returns the polarity and trigger for the IRQs. That function calls
mp_find_ioapics to get the 'struct ioapic' structure - which along with the
mp_irq[x] is used to figure out the default values and the polarity/trigger
overrides. Since the mp_find_ioapics now returns -1 [b/c the IOAPIC is filled
with 0xffffffff], the acpi_get_override_irq() stops trying to lookup in the
mp_irq[x] the proper INT_SRV_OVR and we can't install the SCI interrupt.

The proper fix for this is going in v3.5 and adds an x86_io_apic_ops
struct so that platforms can override it. But for v3.4 lets carry this
work-around. This patch does that by providing a slightly different variant
of the fake IOAPIC entries.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>