some people report atl1c could cause system hang with following
kernel trace info:
---------------------------------------
WARNING: at.../net/sched/sch_generic.c:258 dev_watchdog+0x1db/0x1d0()
...
NETDEV WATCHDOG: eth0 (atl1c): transmit queue 0 timed out
...
---------------------------------------
This is caused by netif_stop_queue calling when cable Link is down.
So remove netif_stop_queue, because link_watch will take it over.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Cloud Ren <cjren@qca.qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

commit a1c7fff7 (net: netdev_alloc_skb() use build_skb()) broke b44 on
some 64bit machines.

It appears b44 and b43 use __netdev_alloc_skb() instead of alloc_skb()
for their bounce buffers.

There is no need to add an extra NET_SKB_PAD reservation for bounce
buffers :

- In TX path, NET_SKB_PAD is useless

- In RX path in b44, we force a copy of incoming frames if
  GFP_DMA allocations were needed.
Reported-and-bisected-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently when sending data over datagram, the send function will attempt to
allocate any size passed on from the userspace.

We should make sure that this size is checked and limited. We'll limit it
to the MTU of the device, which is checked later anyway.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull fix to common clk framework from Michael Turquette:
 "The previous set of common clk fixes for -rc5 left an uninitialized
  int which could lead to bad array indexing when switching clock
  parents.  The issue is fixed with a trivial change to the code flow in
  __clk_set_parent."

* tag 'clk-fixes-for-linus' of git://git.linaro.org/people/mturquette/linux:
  clk: fix parent validation in __clk_set_parent()

Pull raid10 build failure fix from NeilBrown:
 "I really shouldn't do important things late in the day.  It seems that
  I get careless."

* tag 'md-3.5-fixes' of git://neil.brown.name/md:
  md/raid10: fix careless build error

Pull networking update from David Miller:

 1) Fix RX sequence number handling in mwifiex, from Stone Piao.

 2) Netfilter ipset mis-compares device names, fix from Florian
    Westphal.

 3) Fix route leak in ipv6 IPVS, from Eric Dumazet.

 4) NFS fixes.  Several buffer overflows in NCI layer from Dan
    Rosenberg, and release sock OOPS'er fix from Eric Dumazet.

 5) Fix WEP handling ath9k, we started using a bit the chip provides to
    indicate undecrypted packets but that bit turns out to be unreliable
    in certain configurations.  Fix from Felix Fietkau.

 6) Fix Kconfig dependency bug in wlcore, from Randy Dunlap.

 7) New USB IDs for rtlwifi driver from Larry Finger.

 8) Fix crashes in qmi_wwan usbnet driver when disconnecting, from Bjørn
    Mork.

 9) Gianfar driver programs coalescing settings properly in single queue
    mode, but does not do so in multi-queue mode.  Fix from Claudiu
    Manoil.

10) Missing module.h include in davinci_cpdma.c, from Daniel Mack.

11) Need dummy handler for IPSET_CMD_NONE otherwise we crash in ipset if
    we get this via nfnetlink, fix from Tomasz Bursztyka.

12) Missing RCU unlock in nfnetlink error path, also from Tomasz.

13) Fix divide by zero in igbvf when the user tries to set an RX
    coalescing value of 0 usecs, from Mitch A Williams.

14) We can process SCTP sacks for the wrong transport, oops.  Fix from
    Neil Horman.

15) Remove hw IP payload checksumming from e1000e driver.  This has zery
    value in our stack, and turning it on creates a very unintuitive
    restriction for users when using jumbo MTUs.

    Specifically, when IP payload checksums are on you cannot use both
    receive hashing offload and jumbo MTU.  Fix from Bruce Allan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (27 commits)
  e1000e: remove use of IP payload checksum
  sctp: be more restrictive in transport selection on bundled sacks
  igbvf: fix divide by zero
  netfilter: nfnetlink: fix missing rcu_read_unlock in nfnetlink_rcv_msg
  netfilter: ipset: fix crash if IPSET_CMD_NONE command is sent
  davinci_cpdma: include linux/module.h
  gianfar: Fix RXICr/TXICr programming for multi-queue mode
  net: Downgrade CAP_SYS_MODULE deprecated message from error to warning.
  net: qmi_wwan: fix Oops while disconnecting
  mwifiex: fix memory leak associated with IE manamgement
  ath9k: fix panic caused by returning a descriptor we have queued for reuse
  mac80211: correct behaviour on unrecognised action frames
  ath9k: enable serialize_regmode for non-PCIE AR9287
  rtlwifi: rtl8192cu: New USB IDs
  NFC: Return from rawsock_release when sk is NULL
  iwlwifi: fix activating inactive stations
  wlcore: drop INET dependency
  ath9k: fix dynamic WEP related regression
  NFC: Prevent multiple buffer overflows in NCI
  netfilter: update location of my trees
  ...

build error introduced by commit b357f04a

That function doesn't get extra args until a later patch.  Bother.

Reported-by: Fengguang Wu <wfg@linux.intel.com> 
Reported-by: Simon Kirby <sim@hostway.ca>
Reported-by: Tobias Klausmann <tobias.johannes.klausmann@mni.thm.de>
Signed-off-by: NeilBrown <neilb@suse.de>

In commit 070ad7e7 ("floppy: convert to delayed work and
single-thread wq") the 'fd_timeout' timer was converted to a delayed
work.  However, the "del_timer(&fd_timeout)" was lost in the process,
and any previous pending timeouts would stay active when we then
re-queued the timeout.

This resulted in the floppy probe sequence having a (stale) 20s timeout
rather than the intended 3s timeout, and thus made booting with the
floppy driver (but no actual floppy controller) take much longer than it
should.

Of course, there's little reason for most people to compile the floppy
driver into the kernel at all, which is why most people never noticed.

Canceling the delayed work where we used to do the del_timer() fixes the
issue, and makes the floppy probing use the proper new timeout instead.
The three second timeout is still very wasteful, but better than the 20s
one.
Reported-and-tested-by: Andi Kleen <ak@linux.intel.com>
Reported-and-tested-by: Calvin Walton <calvin.walton@kepstin.ca>
Cc: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull block bits from Jens Axboe:
 "As vacation is coming up, thought I'd better get rid of my pending
  changes in my for-linus branch for this iteration.  It contains:

   - Two patches for mtip32xx.  Killing a non-compliant sysfs interface
     and moving it to debugfs, where it belongs.

   - A few patches from Asias.  Two legit bug fixes, and one killing an
     interface that is no longer in use.

   - A patch from Jan, making the annoying partition ioctl warning a bit
     less annoying, by restricting it to !CAP_SYS_RAWIO only.

   - Three bug fixes for drbd from Lars Ellenberg.

   - A fix for an old regression for umem, it hasn't really worked since
     the plugging scheme was changed in 3.0.

   - A few fixes from Tejun.

   - A splice fix from Eric Dumazet, fixing an issue with pipe
     resizing."

* 'for-linus' of git://git.kernel.dk/linux-block:
  scsi: Silence unnecessary warnings about ioctl to partition
  block: Drop dead function blk_abort_queue()
  block: Mitigate lock unbalance caused by lock switching
  block: Avoid missed wakeup in request waitqueue
  umem: fix up unplugging
  splice: fix racy pipe->buffers uses
  drbd: fix null pointer dereference with on-congestion policy when diskless
  drbd: fix list corruption by failing but already aborted reads
  drbd: fix access of unallocated pages and kernel panic
  xen/blkfront: Add WARN to deal with misbehaving backends.
  blkcg: drop local variable @q from blkg_destroy()
  mtip32xx: Create debugfs entries for troubleshooting
  mtip32xx: Remove 'registers' and 'flags' from sysfs
  blkcg: fix blkg_alloc() failure path
  block: blkcg_policy_cfq shouldn't be used if !CONFIG_CFQ_GROUP_IOSCHED
  block: fix return value on cfq_init() failure
  mtip32xx: Remove version.h header file inclusion
  xen/blkback: Copy id field when doing BLKIF_DISCARD.

The below commit introduced a bug in __clk_set_parent()
which could cause it to *skip* the parent validation
which makes sure the parent passed to the api is a valid
one.

    commit 7975059d
    Author: Rajendra Nayak <rnayak@ti.com>
    Date:   Wed Jun 6 14:41:31 2012 +0530

        clk: Allow late cache allocation for clk->parents

This was identified by the following compiler warning..

    drivers/clk/clk.c: In function '__clk_set_parent':
    drivers/clk/clk.c:1083:5: warning: 'i' may be used uninitialized in this function [-Wuninitialized]

.. as reported by Marc Kleine-Budde.

There were various options discussed on how to fix this, one
being initing 'i' to clk->num_parents, but the below approach
was found to be more appropriate as it also makes the 'parent
validation' code simpler to read.
Reported-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Rajendra Nayak <rnayak@ti.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
Cc: stable@kernel.org

Pull sound fixes from Takashi Iwai:
 "Just a few driver-specific fixes for ASoC and HD-audio."

* tag 'sound-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ALSA: hda - Fix no sound from ALC662 after Windows reboot
  ASoC: tlv320aic3x: Fix codec pll configure bug
  ASoC: wm2200: Add missing BCLK rate

Pull device-mapper fixes from Alasdair G Kergon:
 "Four minor thin provisioning fixes and correct and update dm-verity
  documentation."

* tag 'dm-3.5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm:
  dm: verity fix documentation
  dm persistent data: fix allocation failure in space map checker init
  dm persistent data: handle space map checker creation failure
  dm persistent data: fix shadow_info_leak on dm_tm_destroy
  dm thin: commit metadata before creating metadata snapshot

Pull drm fixes from Dave Airlie:
 "One regression fix, two radeon fixes (one for an oops), and an i915
  fix to unload framebuffers earlier.

  We originally were going to leave the i915 fix until -next, but grub2
  in some situations causes vesafb/efifb to be loaded now, and this
  causes big slowdowns, and I have reports in rawhide I'd like to have
  fixed."

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/i915: kick any firmware framebuffers before claiming the gtt
  drm: edid: Don't add inferred modes with higher resolution
  drm/radeon: fix rare segfault
  drm/radeon: fix VM page table setup on SI

Pull md fixes from NeilBrown:
 "md: collection of bug fixes for 3.5

  You go away for 2 weeks vacation and what do you get when you come
  back? Piles of bugs :-)

  Some found by inspection, some by testing, some during use in the
  field, and some while developing for the next window..."

* tag 'md-3.5-fixes' of git://neil.brown.name/md:
  md: fix up plugging (again).
  md: support re-add of recovering devices.
  md/raid1: fix bug in read_balance introduced by hot-replace
  raid5: delayed stripe fix
  md/raid456: When read error cannot be recovered, record bad block
  md: make 'name' arg to md_register_thread non-optional.
  md/raid10: fix failure when trying to repair a read error.
  md/raid5: fix refcount problem when blocked_rdev is set.
  md:Add blk_plug in sync_thread.
  md/raid5: In ops_run_io, inc nr_pending before calling md_wait_for_blocked_rdev
  md/raid5: Do not add data_offset before call to is_badblock
  md/raid5: prefer replacing failed devices over want-replacement devices.
  md/raid10: Don't try to recovery unmatched (and unused) chunks.

Pull security layer fixes from James Morris.

A documentation update, and a nommu build fix.

* 'for-linus2' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
  security: Fix nommu build.
  security: document no_new_privs

Veritysetup is now part of cryptsetup package.
Remove on-disk header description (which is not parsed in kernel)
and point users to cryptsetup where it the format is documented.
Mention units for block size paramaters.
Fix target line specification and dmsetup parameters.
Signed-off-by: Milan Broz <mbroz@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

If CONFIG_DM_DEBUG_SPACE_MAPS is enabled and memory is fragmented and a
sufficiently-large metadata device is used in a thin pool then the space
map checker will fail to allocate the memory it requires.

Switch from kmalloc to vmalloc to allow larger virtually contiguous
allocations for the space map checker's internal count arrays.
Reported-by: Vivek Goyal <vgoyal@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

If CONFIG_DM_DEBUG_SPACE_MAPS is enabled and dm_sm_checker_create()
fails, dm_tm_create_internal() would still return success even though it
cleaned up all resources it was supposed to have created.  This will
lead to a kernel crash:

general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
...
RIP: 0010:[<ffffffff81593659>]  [<ffffffff81593659>] dm_bufio_get_block_size+0x9/0x20
Call Trace:
  [<ffffffff81599bae>] dm_bm_block_size+0xe/0x10
  [<ffffffff8159b8b8>] sm_ll_init+0x78/0xd0
  [<ffffffff8159c1a6>] sm_ll_new_disk+0x16/0xa0
  [<ffffffff8159c98e>] dm_sm_disk_create+0xfe/0x160
  [<ffffffff815abf6e>] dm_pool_metadata_open+0x16e/0x6a0
  [<ffffffff815aa010>] pool_ctr+0x3f0/0x900
  [<ffffffff8158d565>] dm_table_add_target+0x195/0x450
  [<ffffffff815904c4>] table_load+0xe4/0x330
  [<ffffffff815917ea>] ctl_ioctl+0x15a/0x2c0
  [<ffffffff81591963>] dm_ctl_ioctl+0x13/0x20
  [<ffffffff8116a4f8>] do_vfs_ioctl+0x98/0x560
  [<ffffffff8116aa51>] sys_ioctl+0x91/0xa0
  [<ffffffff81869f52>] system_call_fastpath+0x16/0x1b

Fix the space map checker code to return an appropriate ERR_PTR and have
dm_sm_disk_create() and dm_tm_create_internal() check for it with
IS_ERR.
Reported-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

Cleanup the shadow table before destroying the transaction manager.

Reference: leak was identified with kmemleak when running
test_discard_random_sectors in the thinp-test-suite.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

Userland sometimes sees a corrupt metadata block if metadata is changing
rapidly when a metadata snapshot is reserved for userland,  To make the
problem go away, commit before we take the metadata snapshot (which is a
sensible thing to do anyway).

The checksums mean userland spots this corruption immediately so there's
no risk of acting on incorrect data.  No corruption exists from the
kernel's point of view, and thin_check passes after pool shutdown.

I believe this is to do with shared blocks at the first level of the
{device, mapping} btree.  Prior to the metadata-snap support no sharing
at this level was possible, so this patch is only required after commit
cc8394d8 ("dm thin: provide userspace
access to pool metadata").
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

The security + nommu configuration presently blows up with an undefined
reference to BDI_CAP_EXEC_MAP:

security/security.c: In function 'mmap_prot':
security/security.c:687:36: error: dereferencing pointer to incomplete type
security/security.c:688:16: error: 'BDI_CAP_EXEC_MAP' undeclared (first use in this function)
security/security.c:688:16: note: each undeclared identifier is reported only once for each function it appears in

include backing-dev.h directly to fix it up.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: James Morris <james.l.morris@oracle.com>

Especially vesafb likes to map everything as uc- (yikes), and if that
mapping hangs around still while we try to map the gtt as wc the
kernel will downgrade our request to uc-, resulting in abyssal
performance.

Unfortunately we can't do this as early as readon does (i.e. as the
first thing we do when initializing the hw) because our fb/mmio space
region moves around on a per-gen basis. So I've had to move it below
the gtt initialization, but that seems to work, too. The important
thing is that we do this before we set up the gtt wc mapping.

Now an altogether different question is why people compile their
kernels with vesafb enabled, but I guess making things just work isn't
bad per se ...

v2:
- s/radeondrmfb/inteldrmfb/
- fix up error handling

v3: Kill #ifdef X86, this is Intel after all. Noticed by Ben Widawsky.

v4: Jani Nikula complained about the pointless bool primary
initialization.

v5: Don't oops if we can't allocate, noticed by Chris Wilson.

v6: Resolve conflicts with agp rework and fixup whitespace.

This is commit e188719a in drm-next.

Backport to 3.5 -fixes queue requested by Dave Airlie - due to grub
using vesa on fedora their initrd seems to load vesafb before loading
the real kms driver. So tons more people actually experience a
dead-slow gpu. Hence also the Cc: stable.

Cc: stable@vger.kernel.org
Reported-and-tested-by: "Kilarski, Bernard R" <bernard.r.kilarski@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>

When a monitor EDID doesn't give the preferred bit, driver assumes
that the mode with the higest resolution and rate is the preferred
mode.  Meanwhile the recent changes for allowing more modes in the
GFT/CVT ranges give actually more modes, and some modes may be over
the native size.  Thus such a mode would be picked up as the preferred
mode although it's no native resolution.

For avoiding such a problem, this patch limits the addition of
inferred modes by checking not to be greater than other modes.
Also, it checks the duplicated mode entry at the same time.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>

In gem idle/busy ioctl the radeon object was derefenced after
drm_gem_object_unreference_unlocked which in case the object
have been destroyed lead to use of a possibly free pointer with
possibly wrong data.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

The value returned by "mddev_check_plug" is only valid until the
next 'schedule' as that will unplug things.  This could happen at any
call to mempool_alloc.
So just calling mddev_check_plug at the start doesn't really make
sense.

So call it just before, or just after, queuing things for the thread.
As the action that happens at unplug is to wake the thread, this makes
lots of sense.
If we cannot add a plug (which requires a small GFP_ATOMIC alloc) we
wake thread immediately.

RAID5 is a bit different.  Requests are queued for the thread and the
thread is woken by release_stripe.  So we don't need to wake the
thread on failure.
However the thread doesn't perform certain actions when there is any
active plug, so it is important to install a plug before waking the
thread.  So for RAID5 we install the plug *before* queuing the request
and waking the thread.

Without this patch it is possible for raid1 or raid10 to queue a
request without then waking the thread, resulting in the array locking
up.

Also change raid10 to only flush_pending_write when there are not
active plugs, just like raid1.

This patch is suitable for 3.0 or later.  I plan to submit it to
-stable, but I'll like to let it spend a few weeks in mainline
first to be sure it is completely safe.
Signed-off-by: NeilBrown <neilb@suse.de>

We currently only allow a device to be re-added if it appear to be
in-sync.  This is overly restrictive as it may be desirable to re-add
a device that is in the middle of recovery.

So remove the test for "InSync" - the test on rdev->raid_disk is
sufficient to ensure that the re-add will succeed.
Reported-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Tested-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

When we added hot_replace we doubled the number of devices
that could be in a RAID1 array.  So we doubled how far read_balance
would search.  Unfortunately we didn't double the point at which
it looped back to the beginning - so it effectively loops over
all non-replacement disks twice.
This doesn't cause bad behaviour, but it pointless and means we
never read from replacement devices.
Signed-off-by: NeilBrown <neilb@suse.de>

There isn't locking setting STRIPE_DELAYED and STRIPE_PREREAD_ACTIVE bits, but
the two bits have relationship. A delayed stripe can be moved to hold list only
when preread active stripe count is below IO_THRESHOLD. If a stripe has both
the bits set, such stripe will be in delayed list and preread count not 0,
which will make such stripe never leave delayed list.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>

We may not be able to fix a bad block if:
 - the array is degraded
 - the over-write fails.

In these cases we currently eject the device, but we should
record a bad block if possible.
Signed-off-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

Having the 'name' arg optional and defaulting to the current
personality name is no necessary and leads to errors, as when
changing the level of an array we can end up using the
name of the old level instead of the new one.

So make it non-optional and always explicitly pass the name
of the level that the array will be.
Reported-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

commit 58c54fcc
     md/raid10: handle further errors during fix_read_error better.

in 3.1 added "r10_sync_page_io" which takes an IO size in sectors.
But we were passing the IO size in bytes!!!
This resulting in bio_add_page failing, and empty request being sent
down, and a consequent BUG_ON in scsi_lib.

[fix missing space in error message at same time]

This fix is suitable for 3.1.y and later.

Cc: stable@vger.kernel.org
Reported-by: Christian Balzer <chibi@gol.com>
Signed-off-by: NeilBrown <neilb@suse.de>

Pull a couple more powerpc fixes from Benjamin Herrenschmidt:
 "Here are two more fixes that I "missed" when scrubbing patchwork last
  week which are worth still having in 3.5."

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/kvm: sldi should be sld
  powerpc/xmon: Use cpumask iterator to avoid warning

Document no_new_privs.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.l.morris@oracle.com>

commit 43220aa0
    md/raid5: fix a hang on device failure.

fixed a hang, but introduced a refcounting in-balance so
that if the presence of bad-blocks ever caused an rdev to
be 'blocked' we would increment the refcount on the rdev and
never decrement it.

So added the needed rdev_dec_pending when md_wait_for_blocked_rdev
is not called.
Reported-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

Add blk_plug in sync_thread will increase the performance of sync.
Because sync_thread did not blk_plug,so when raid sync, the bio merge
not well.

Testing environment:
SATA controller: Intel Corporation 82801JI (ICH10 Family) SATA AHCI
Controller.
OS:Linux xxx 3.5.0-rc2+ #340 SMP Tue Jun 12 09:00:25 CST 2012
x86_64 x86_64 x86_64 GNU/Linux.
RAID5: four ST31000524NS disk.

Without blk_plug:recovery speed about 63M/Sec;
Add blk_plug:recovery speed about 120M/Sec.

Using blktrace:
blktrace -d /dev/sdb -w 60  -o -|blkparse -i -

without blk_plug:
Total (8,16):
 Reads Queued:      309811,     1239MiB	 Writes Queued:           0,        0KiB
 Read Dispatches:   283583,     1189MiB	 Write Dispatches:        0,        0KiB
 Reads Requeued:         0		 Writes Requeued:         0
 Reads Completed:   273351,     1149MiB	 Writes Completed:        0,        0KiB
 Read Merges:        23533,    94132KiB	 Write Merges:            0,        0KiB
 IO unplugs:             0        	 Timer unplugs:           0

add blk_plug:
Total (8,16):
 Reads Queued:      428697,     1714MiB	 Writes Queued:           0,        0KiB
 Read Dispatches:     3954,     1714MiB	 Write Dispatches:        0,        0KiB
 Reads Requeued:         0		 Writes Requeued:         0
 Reads Completed:     3956,     1715MiB	 Writes Completed:        0,        0KiB
 Read Merges:       424743,     1698MiB	 Write Merges:            0,        0KiB
 IO unplugs:             0        	 Timer unplugs:        3384

The ratio of merge will be markedly increased.
Signed-off-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

In ops_run_io(), the call to md_wait_for_blocked_rdev will decrement
nr_pending so we lose the reference we hold on the rdev.
So atomic_inc it first to maintain the reference.

This bug was introduced by commit  73e92e51
    md/raid5.  Don't write to known bad block on doubtful devices.

which appeared in 3.0, so patch is suitable for stable kernels since
then.

Cc: stable@vger.kernel.org
Signed-off-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

In chunk_aligned_read() we are adding data_offset before calling
is_badblock.  But is_badblock also adds data_offset, so that is bad.

So move the addition of data_offset to after the call to
is_badblock.

This bug was introduced by commit 31c176ec
     md/raid5: avoid reading from known bad blocks.
which first appeared in 3.0.  So that patch is suitable for any
-stable kernel from 3.0.y onwards.  However it will need minor
revision for most of those (as the comment didn't appear until
recently).

Cc: stable@vger.kernel.org
Signed-off-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

If a RAID5 has both a failed device and a device marked as
'WantReplacement', then we should preferentially replace the failed
device.
However the current code replaces whichever is found first.
So split into 2 loops, check fail failed/missing first, and only check
for WantReplacement if nothing is failed or missing.
Reported-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

If a RAID10 has an odd number of chunks - as might happen when there
are an odd number of devices - the last chunk has no pair and so is
not mirrored.  We don't store data there, but when recovering the last
device in an array we retry to recover that last chunk from a
non-existent location.  This results in an error, and the recovery
aborts.

When we get to that last chunk we should just stop - there is nothing
more to do anyway.

This bug has been present since the introduction of RAID10, so the
patch is appropriate for any -stable kernel.

Cc: stable@vger.kernel.org
Reported-by: Christian Balzer <chibi@gol.com>
Tested-by: Christian Balzer <chibi@gol.com>
Signed-off-by: NeilBrown <neilb@suse.de>

Since we are taking a registers, this should never have been an sldi.
Talking to paulus offline, this is the correct fix.

Was introduced by:
 commit 19ccb76a
 Author: Paul Mackerras <paulus@samba.org>
 Date:   Sat Jul 23 17:42:46 2011 +1000

Talking to paulus, this shouldn't be a literal.
Signed-off-by: Michael Neuling <mikey@neuling.org>
CC: <stable@kernel.org> [v3.2+]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>