Pull x86 fixes from Peter Anvin:
 "A couple of crash fixes, plus a fix that on 32 bits would cause a
  missing -ENOSYS for nonexistent system calls"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, cpu: Fix cache topology for early P4-SMT
  x86_32, entry: Store badsys error code in %eax
  x86, MCE: Robustify mcheck_init_device

Pull vfs fixes from Christoph Hellwig:
 "A vfsmount leak fix, and a compile warning fix"

* 'vfs-for-3.16' of git://git.infradead.org/users/hch/vfs:
  fs: umount on symlink leaks mnt count
  direct-io: fix uninitialized warning in do_direct_IO()

Pull firewire regression fix from Stefan Richter:
 "IEEE 1394 (FireWire) subsystem fix: MSI don't work on VIA PCIe
  controllers with some isochronous workloads (regression since
  v3.16-rc1)"

* tag 'firewire-fix-vt6315' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394:
  firewire: ohci: disable MSI for VIA VT6315 again

Michel Dänzer and a couple of other people reported inexplicable random
oopses in the scheduler, and the cause turns out to be gcc mis-compiling
the load_balance() function when debugging is enabled.  The gcc bug
apparently goes back to gcc-4.5, but slight optimization changes means
that it now showed up as a problem in 4.9.0 and 4.9.1.

The instruction scheduling problem causes gcc to schedule a spill
operation to before the stack frame has been created, which in turn can
corrupt the spilled value if an interrupt comes in.  There may be other
effects of this bug too, but that's the code generation problem seen in
Michel's case.

This is fixed in current gcc HEAD, but the workaround as suggested by
Markus Trippelsdorf is pretty simple: use -fno-var-tracking-assignments
when compiling the kernel, which disables the gcc code that causes the
problem.  This can result in slightly worse debug information for
variable accesses, but that is infinitely preferable to actual code
generation problems.

Doing this unconditionally (not just for CONFIG_DEBUG_INFO) also allows
non-debug builds to verify that the debug build would be identical: we
can do

    export GCC_COMPARE_DEBUG=1

to make gcc internally verify that the result of the build is
independent of the "-g" flag (it will make the compiler build everything
twice, toggling the debug flag, and compare the results).

Without the "-fno-var-tracking-assignments" option, the build would fail
(even with 4.8.3 that didn't show the actual stack frame bug) with a gcc
compare failure.

See also gcc bugzilla:

  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61801Reported-by: NMichel Dänzer <michel@daenzer.net>
Suggested-by: NMarkus Trippelsdorf <markus@trippelsdorf.de>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Shortly before 3.16-rc1, Dave Jones reported:

  WARNING: CPU: 3 PID: 19721 at fs/xfs/xfs_aops.c:971
           xfs_vm_writepage+0x5ce/0x630 [xfs]()
  CPU: 3 PID: 19721 Comm: trinity-c61 Not tainted 3.15.0+ #3
  Call Trace:
    xfs_vm_writepage+0x5ce/0x630 [xfs]
    shrink_page_list+0x8f9/0xb90
    shrink_inactive_list+0x253/0x510
    shrink_lruvec+0x563/0x6c0
    shrink_zone+0x3b/0x100
    shrink_zones+0x1f1/0x3c0
    try_to_free_pages+0x164/0x380
    __alloc_pages_nodemask+0x822/0xc90
    alloc_pages_vma+0xaf/0x1c0
    handle_mm_fault+0xa31/0xc50
  etc.

 970   if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
 971                   PF_MEMALLOC))

I did not respond at the time, because a glance at the PageDirty block
in shrink_page_list() quickly shows that this is impossible: we don't do
writeback on file pages (other than tmpfs) from direct reclaim nowadays.
Dave was hallucinating, but it would have been disrespectful to say so.

However, my own /var/log/messages now shows similar complaints

  WARNING: CPU: 1 PID: 28814 at fs/ext4/inode.c:1881 ext4_writepage+0xa7/0x38b()
  WARNING: CPU: 0 PID: 27347 at fs/ext4/inode.c:1764 ext4_writepage+0xa7/0x38b()

from stressing some mmotm trees during July.

Could a dirty xfs or ext4 file page somehow get marked PageSwapBacked,
so fail shrink_page_list()'s page_is_file_cache() test, and so proceed
to mapping->a_ops->writepage()?

Yes, 3.16-rc1's commit 68711a74 ("mm, migration: add destination
page freeing callback") has provided such a way to compaction: if
migrating a SwapBacked page fails, its newpage may be put back on the
list for later use with PageSwapBacked still set, and nothing will clear
it.

Whether that can do anything worse than issue WARN_ON_ONCEs, and get
some statistics wrong, is unclear: easier to fix than to think through
the consequences.

Fixing it here, before the put_new_page(), addresses the bug directly,
but is probably the worst place to fix it.  Page migration is doing too
many parts of the job on too many levels: fixing it in
move_to_new_page() to complement its SetPageSwapBacked would be
preferable, except why is it (and newpage->mapping and newpage->index)
done there, rather than down in migrate_page_move_mapping(), once we are
sure of success? Not a cleanup to get into right now, especially not
with memcg cleanups coming in 3.17.
Reported-by: NDave Jones <davej@redhat.com>
Signed-off-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Pull drm fixes from Dave Airlie:
 "This is radeon and intel fixes, and is a small bit larger than I'm
  guessing you'd like it to be.

   - i915: fixes 32-bit highmem i915 blank screen, semaphore hang and
     runtime pm fix

   - radeon: gpuvm stability fix for hangs since 3.15, and hang/reboot
     regression on TN/RL devices,

  The only slightly controversial one is the change to use GB for the
  vm_size, which I'm letting through as its a new interface we defined
  in this merge window, and I'd prefer to have the released kernel have
  the final interface rather than changing it later"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/radeon: fix cut and paste issue for hawaii.
  drm/radeon: fix irq ring buffer overflow handling
  drm/i915: Simplify i915_gem_release_all_mmaps()
  drm/radeon: fix error handling in radeon_vm_bo_set_addr
  drm/i915: fix freeze with blank screen booting highmem
  drm/i915: Reorder the semaphore deadlock check, again
  drm/radeon/TN: only enable bapm on MSI systems
  drm/radeon: fix VM IB handling
  drm/radeon: fix handling of radeon_vm_bo_rmv v3
  drm/radeon: let's use GB for vm_size (v2)

Pull sound fixes from Takashi Iwai:
 "Here contains only the fixes for the new FireWire bebob driver.  All
  fairly trivial and local fixes, so safe to apply"

* tag 'sound-3.16-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ALSA: bebob: Correction for return value of special_clk_ctl_put() in error
  ALSA: bebob: Correction for return value of .put callback
  ALSA: bebob: Use different labels for digital input/output
  ALSA: bebob: Fix a missing to unlock mutex in error handling case

Pull hwmon fix from Guenter Roeck:
 "Fixes to temperature limit and vrm write operations in smsc47m192
  driver"

* tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
  hwmon: (smsc47m192) Fix temperature limit and vrm write operations

Do not split the PARPORT-related symbols with the new kconfig
symbol ARCH_MIGHT_HAVE_PC_PARPORT. The split was causing incorrect
display of these symbols -- they were not being displayed together
as they should be.

Fixes: d90c3eb3 "Kconfig cleanup (PARPORT_PC dependencies)"
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: stable@vger.kernel.org # for 3.13, 3.14, 3.15
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Merge tag 'blackfin-3.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/realmz6/blackfin-linux

Pull blackfin fixes from Steven Miao:
 "smc nor flash PM fix, pinctrl group fix, update defconfig, and build
  fixes"

* tag 'blackfin-3.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/realmz6/blackfin-linux:
  blackfin: vmlinux.lds.S: reserve 32 bytes space at the end of data section for XIP kernel
  defconfig: BF609: update spi config name
  irq: blackfin sec: drop duplicated sec priority set
  blackfin: bind different groups of one pinmux function to different state name
  blackfin: fix some bf5xx boards build for missing <linux/gpio.h>
  pm: bf609: cleanup smc nor flash

to collect some undefined section to the end of the data section and avoid section overlap
Signed-off-by: NSteven Miao <realmz6@gmail.com>

Signed-off-by: NSteven Miao <realmz6@gmail.com>

Signed-off-by: NSteven Miao <realmz6@gmail.com>

Signed-off-by: NSonic Zhang <sonic.zhang@analog.com>
Signed-off-by: NSteven Miao <realmz6@gmail.com>

Signed-off-by: NSteven Miao <realmz6@gmail.com>

drop smc pin state change code, pin state will be saved in pinctrl-adi2 driver
cleanup nor flash init/exit for pm suspend/resume
Signed-off-by: NSteven Miao <realmz6@gmail.com>

Pull parisc fixes from Helge Deller:
 "We have two trivial patches in here.  One removes the SA_RESTORER
  #define since on parisc we don't have the sa_restorer field in struct
  sigaction, the other patch removes an unnecessary memset().

  The SA_RESTORER removal patch is scheduled for stable trees, since
  without it some userspace apps don't build"

* 'parisc-3.16-6' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
  parisc: Eliminate memset after alloc_bootmem_pages
  parisc: Remove SA_RESTORER define

Pull fuse fixes from Miklos Szeredi:
 "These two pathes fix issues with the kernel-userspace protocol changes
  in v3.15"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  fuse: add FUSE_NO_OPEN_SUPPORT flag to INIT
  fuse: s_time_gran fix

Promote one fix for 3.16

This fix was necessary after

9c15a24b ("x86/mce: Improve mcheck_init_device() error handling")

went in. What this patch did was, among others, check the return value
of misc_register and exit early if it encountered an error. Original
code sloppily didn't do that.

However,

        cef12ee5 ("xen/mce: Add mcelog support for Xen platform")

made it so that xen's init routine xen_late_init_mcelog runs first. This
was needed for the xen mcelog device which is supposed to be independent
from the baremetal one.

Initially it was reported that misc_register() fails often on xen and
that's why it needed fixing. However, it is *supposed* to fail by
design, when running in dom0 so that the xen mcelog device file gets
registered first.

And *then* you need the notifier *not* unregistered on the error path so
that the timer does get deleted properly in the CPU hotplug notifier.

Btw, this fix is needed also on baremetal in the unlikely event that
misc_register(&mce_chrdev_device) fails there too.

I was unsure whether to rush it in now and decided to delay it to 3.17.
However, xen people wanted it promoted as it breaks xen when doing cpu
hotplug there. So, after a bit of simmering in tip/master for initial
smoke testing, let's move it to 3.16. It fixes a semi-regression which
got introduced in 3.16 so no need for stable tagging.

tip/x86/ras contains that exact same commit but we can't remove it
there as it is not the last one. It won't cause any merge issues, as I
confirmed locally but I should state here the special situation of this
one fix explicitly anyway.

Thanks.
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

This is a halfway fix for hawaii acceleration. More fixes to come
but hopefully isolated to userspace.
Signed-off-by: NJérôme Glisse <jglisse@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: NDave Airlie <airlied@redhat.com>

two more radeon fixes.

* 'drm-fixes-3.16' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: fix irq ring buffer overflow handling
  drm/radeon: fix error handling in radeon_vm_bo_set_addr

This time in time! Just 32bit-pae fix from Hugh, semaphores fun from Chris
and a fix for runtime pm cherry-picked from next.

Paulo is still working on a fix for runtime pm when X does cursor fun when
the display is off, but that one isn't ready yet.

* tag 'drm-intel-fixes-2014-07-24' of git://anongit.freedesktop.org/drm-intel:
  drm/i915: Simplify i915_gem_release_all_mmaps()
  drm/i915: fix freeze with blank screen booting highmem
  drm/i915: Reorder the semaphore deadlock check, again

alloc_bootmem and related function always return zeroed region of
memory. Thus a memset after calls to these functions is unnecessary.

The following Coccinelle semantic patch was used for making the change:

@@
expression E,E1;
@@

E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\)(...)
... when != E
- memset(E,0,E1);
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NHelge Deller <deller@gmx.de>

The sa_restorer field in struct sigaction is obsolete and no longer in
the parisc implementation.  However, the core code assumes the field is
present if SA_RESTORER is defined. So, the define needs to be removed.
Signed-off-by: NJohn David Anglin <dave.anglin@bell.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: NHelge Deller <deller@gmx.de>

Temperature limit clamps are applied after converting the temperature
from milli-degrees C to degrees C, so either the clamp limit needs
to be specified in degrees C, not milli-degrees C, or clamping must
happen before converting to degrees C. Use the latter method to avoid
overflows.

vrm is an u8, so the written value needs to be limited to [0, 255].

Cc: Axel Lin <axel.lin@ingics.com>
Cc: stable@vger.kernel.org
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>
Reviewed-by: NJean Delvare <jdelvare@suse.de>

Currently umount on symlink blocks following umount:

/vz is separate mount

# ls /vz/ -al | grep test
drwxr-xr-x.  2 root root       4096 Jul 19 01:14 testdir
lrwxrwxrwx.  1 root root         11 Jul 19 01:16 testlink -> /vz/testdir
# umount -l /vz/testlink
umount: /vz/testlink: not mounted (expected)

# lsof /vz
# umount /vz
umount: /vz: device is busy. (unexpected)

In this case mountpoint_last() gets an extra refcount on path->mnt
Signed-off-by: NVasily Averin <vvs@openvz.org>
Acked-by: NIan Kent <raven@themaw.net>
Acked-by: NJeff Layton <jlayton@primarydata.com>
Cc: stable@vger.kernel.org
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The following warnings:

  fs/direct-io.c: In function ‘__blockdev_direct_IO’:
  fs/direct-io.c:1011:12: warning: ‘to’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  fs/direct-io.c:913:16: note: ‘to’ was declared here
  fs/direct-io.c:1011:12: warning: ‘from’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  fs/direct-io.c:913:10: note: ‘from’ was declared here

are false positive because dio_get_page() either fails, or sets both
'from' and 'to'.

Paul Bolle said ...
Maybe it's better to move initializing "to" and "from" out of
dio_get_page(). That _might_ make it easier for both the the reader and
the compiler to understand what's going on. Something like this:

Christoph Hellwig said ...
The fix of moving the code definitively looks nicer, while I think
uninitialized_var is horrible wart that won't get anywhere near my code.

Boaz Harrosh: I agree with Christoph and Paul
Signed-off-by: NBoaz Harrosh <boaz@plexistor.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Pull nfsd bugfix from Bruce Fields:
 "Another regression from the xdr encoding rewrite"

* 'for-3.16' of git://linux-nfs.org/~bfields/linux:
  NFSD: Fix crash encoding lock reply on 32-bit

Pull arm64 fix from Catalin Marinas:
 "Fix arm64 regression introduced by limiting the CMA buffer to ZONE_DMA
  on platforms where RAM starts above 4GB (and ZONE_DMA becoming 0)"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Create non-empty ZONE_DMA when DRAM starts above 4GB

Pull Xtensa fixes from Chris Zankel:
 - resolve FIXMEs in double exception handler for window overflow. This
   fix makes native building of linux on xtensa host possible;
 - fix sysmem region removal issue introduced in 3.15.

* tag 'xtensa-next-20140721' of git://github.com/czankel/xtensa-linux:
  xtensa: fix sysmem reservation at the end of existing block
  xtensa: add fixup for double exception raised in window overflow

Pull pin control fixes from Linus Walleij:
 "Here are three pin control fixes for the v3.16 series.  Sorry that
  some of these arrive late, the summer heat in Sweden makes me slow.

   - an IRQ handling fix for the STi driver, also for stable
   - another IRQ fix for the RCAR GPIO driver
   - a MAINTAINERS entry"

* tag 'pinctrl-v3.16-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  gpio: rcar: Add support for DT IRQ flags
  MAINTAINERS: Add entry for the Renesas pin controller driver
  pinctrl: st: Fix irqmux handler

Pull libata regression fix from Tejun Heo:
 "The last libata/for-3.16-fixes pull contained a regression introduced
  by 1871ee13 ("libata: support the ata host which implements a
  queue depth less than 32") which in turn was a fix for a regression
  introduced earlier while changing queue tag order to accomodate hard
  drives which perform poorly if tags are not allocated in circular
  order (ugh...).

  The regression happens only for SAS controllers making use of libata
  to serve ATA devices.  They don't fill an ata_host field which is used
  by the new tag allocation function leading to NULL dereference.

  This patch adds a new intermediate field ata_host->n_tags which is
  initialized for both SAS and !SAS cases to fix the issue"

* 'for-3.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata:
  libata: introduce ata_host->n_tags to avoid oops on SAS controllers

Pull input layer fixes from Dmitry Torokhov:
 "A few fixups for the input subsystem"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: document INPUT_PROP_TOPBUTTONPAD
  Input: fix defuzzing logic
  Input: sirfsoc-onkey - fix GPL v2 license string typo
  Input: st-keyscan - fix 'defined but not used' compiler warnings
  Input: synaptics - add min/max quirk for pnp-id LEN2002 (Edge E531)
  Input: i8042 - add Acer Aspire 5710 to nomux blacklist
  Input: ti_am335x_tsc - warn about incorrect spelling
  Input: wacom - cleanup multitouch code when touch_max is 2

Pull powerpc fixes from Ben Herrenschmidt:
 "Here is a handful of powerpc fixes for 3.16.  They are all pretty
  simple and self contained and should still make this release"

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: use _GLOBAL_TOC for memmove
  powerpc/pseries: dynamically added OF nodes need to call of_node_init
  powerpc: subpage_protect: Increase the array size to take care of 64TB
  powerpc: Fix bugs in emulate_step()
  powerpc: Disable doorbells on Power8 DD1.x

Pull slab fix from Mike Snitzer:
 "This fixes the broken duplicate slab name check in
  kmem_cache_sanity_check() that has been repeatedly reported (as
  recently as today against Fedora rawhide).

  Pekka seemed to have it staged for a late 3.15-rc in his 'slab/urgent'
  branch but never sent a pull request, see:
      https://lkml.org/lkml/2014/5/23/648"

* tag 'urgent-slab-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  slab_common: fix the check for duplicate slab names

Merge fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: hugetlb: fix copy_hugetlb_page_range()
  simple_xattr: permit 0-size extended attributes
  mm/fs: fix pessimization in hole-punching pagecache
  shmem: fix splicing from a hole while it's punched
  shmem: fix faulting into a hole, not taking i_mutex
  mm: do not call do_fault_around for non-linear fault
  sh: also try passing -m4-nofpu for SH2A builds
  zram: avoid lockdep splat by revalidate_disk
  mm/rmap.c: fix pgoff calculation to handle hugepage correctly
  coredump: fix the setting of PF_DUMPCORE

Commit 4a705fef ("hugetlb: fix copy_hugetlb_page_range() to handle
migration/hwpoisoned entry") changed the order of
huge_ptep_set_wrprotect() and huge_ptep_get(), which leads to breakage
in some workloads like hugepage-backed heap allocation via libhugetlbfs.
This patch fixes it.

The test program for the problem is shown below:

  $ cat heap.c
  #include <unistd.h>
  #include <stdlib.h>
  #include <string.h>

  #define HPS 0x200000

  int main() {
  	int i;
  	char *p = malloc(HPS);
  	memset(p, '1', HPS);
  	for (i = 0; i < 5; i++) {
  		if (!fork()) {
  			memset(p, '2', HPS);
  			p = malloc(HPS);
  			memset(p, '3', HPS);
  			free(p);
  			return 0;
  		}
  	}
  	sleep(1);
  	free(p);
  	return 0;
  }

  $ export HUGETLB_MORECORE=yes ; export HUGETLB_NO_PREFAULT= ; hugectl --heap ./heap

Fixes 4a705fef ("hugetlb: fix copy_hugetlb_page_range() to handle
migration/hwpoisoned entry"), so is applicable to -stable kernels which
include it.
Signed-off-by: NNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: NGuillaume Morin <guillaume@morinfr.org>
Suggested-by: NGuillaume Morin <guillaume@morinfr.org>
Acked-by: NHugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>	[2.6.37+]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If a filesystem uses simple_xattr to support user extended attributes,
LTP setxattr01 and xfstests generic/062 fail with "Cannot allocate
memory": simple_xattr_alloc()'s wrap-around test mistakenly excludes
values of zero size.  Fix that off-by-one (but apparently no filesystem
needs them yet).
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: Aristeu Rozanski <aris@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

I wanted to revert my v3.1 commit d0823576 ("mm: pincer in
truncate_inode_pages_range"), to keep truncate_inode_pages_range() in
synch with shmem_undo_range(); but have stepped back - a change to
hole-punching in truncate_inode_pages_range() is a change to
hole-punching in every filesystem (except tmpfs) that supports it.

If there's a logical proof why no filesystem can depend for its own
correctness on the pincer guarantee in truncate_inode_pages_range() - an
instant when the entire hole is removed from pagecache - then let's
revisit later.  But the evidence is that only tmpfs suffered from the
livelock, and we have no intention of extending hole-punch to ramfs.  So
for now just add a few comments (to match or differ from those in
shmem_undo_range()), and fix one silliness noticed in d0823576...

Its "index == start" addition to the hole-punch termination test was
incomplete: it opened a way for the end condition to be missed, and the
loop go on looking through the radix_tree, all the way to end of file.
Fix that pessimization by resetting index when detected in inner loop.

Note that it's actually hard to hit this case, without the obsessive
concurrent faulting that trinity does: normally all pages are removed in
the initial trylock_page() pass, and this loop finds nothing to do.  I
had to "#if 0" out the initial pass to reproduce bug and test fix.
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Lukas Czerner <lczerner@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

shmem_fault() is the actual culprit in trinity's hole-punch starvation,
and the most significant cause of such problems: since a page faulted is
one that then appears page_mapped(), needing unmap_mapping_range() and
i_mmap_mutex to be unmapped again.

But it is not the only way in which a page can be brought into a hole in
the radix_tree while that hole is being punched; and Vlastimil's testing
implies that if enough other processors are busy filling in the hole,
then shmem_undo_range() can be kept from completing indefinitely.

shmem_file_splice_read() is the main other user of SGP_CACHE, which can
instantiate shmem pagecache pages in the read-only case (without holding
i_mutex, so perhaps concurrently with a hole-punch).  Probably it's
silly not to use SGP_READ already (using the ZERO_PAGE for holes): which
ought to be safe, but might bring surprises - not a change to be rushed.

shmem_read_mapping_page_gfp() is an internal interface used by
drivers/gpu/drm GEM (and next by uprobes): it should be okay.  And
shmem_file_read_iter() uses the SGP_DIRTY variant of SGP_CACHE, when
called internally by the kernel (perhaps for a stacking filesystem,
which might rely on holes to be reserved): it's unclear whether it could
be provoked to keep hole-punch busy or not.

We could apply the same umbrella as now used in shmem_fault() to
shmem_file_splice_read() and the others; but it looks ugly, and use over
a range raises questions - should it actually be per page? can these get
starved themselves?

The origin of this part of the problem is my v3.1 commit d0823576
("mm: pincer in truncate_inode_pages_range"), once it was duplicated
into shmem.c.  It seemed like a nice idea at the time, to ensure
(barring RCU lookup fuzziness) that there's an instant when the entire
hole is empty; but the indefinitely repeated scans to ensure that make
it vulnerable.

Revert that "enhancement" to hole-punch from shmem_undo_range(), but
retain the unproblematic rescanning when it's truncating; add a couple
of comments there.

Remove the "indices[0] >= end" test: that is now handled satisfactorily
by the inner loop, and mem_cgroup_uncharge_start()/end() are too light
to be worth avoiding here.

But if we do not always loop indefinitely, we do need to handle the case
of swap swizzled back to page before shmem_free_swap() gets it: add a
retry for that case, as suggested by Konstantin Khlebnikov; and for the
case of page swizzled back to swap, as suggested by Johannes Weiner.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reported-by: NSasha Levin <sasha.levin@oracle.com>
Suggested-by: NVlastimil Babka <vbabka@suse.cz>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Lukas Czerner <lczerner@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: <stable@vger.kernel.org>	[3.1+]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>