Commit fe97b47c ("xprtrdma: Use workqueue to process RPC/RDMA
replies") replaced the reply tasklet with a workqueue that allows
RPC replies to be processed in parallel. Thus the credit values in
RPC-over-RDMA replies can be applied in a different order than in
which the server sent them.

To fix this, revert commit eba8ff66 ("xprtrdma: Move credit
update to RPC reply handler"). Reverting is done by hand to
accommodate code changes that have occurred since then.

Fixes: fe97b47c ("xprtrdma: Use workqueue to process . . .")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

These are shorter than RPCRDMA_HDRLEN_MIN, and they need to
complete the waiting RPC.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Error headers are shorter than either RDMA_MSG or RDMA_NOMSG.

Since HDRLEN_MIN is already used in several other places that would
be annoying to change, add RPCRDMA_HDRLEN_ERR for the one or two
spots where the shorter length is needed.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

If ib_post_send() in ro_unmap_sync() fails, the WRs have not been
posted, no completions will fire, and wait_for_completion() will
wait forever. Skip the wait in that case.

To ensure the MRs are invalid, disconnect.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

A single memory allocation is used for the pair of buffers wherein
the RPC client builds an RPC call message and decodes its matching
reply. These buffers are sized based on the maximum possible size
of the RPC call and reply messages for the operation in progress.

This means that as the call buffer increases in size, the start of
the reply buffer is pushed farther into the memory allocation.

RPC requests are growing in size. It used to be that both the call
and reply buffers fit inside a single page.

But these days, thanks to NFSv4 (and especially security labels in
NFSv4.2) the maximum call and reply sizes are large. NFSv4.0 OPEN,
for example, now requires a 6KB allocation for a pair of call and
reply buffers, and NFSv4 LOOKUP is not far behind.

As the maximum size of a call increases, the reply buffer is pushed
far enough into the buffer's memory allocation that a page boundary
can appear in the middle of it.

When the maximum possible reply size is larger than the client's
RDMA receive buffers (currently 1KB), the client has to register a
Reply chunk for the server to RDMA Write the reply into.

The logic in rpcrdma_convert_iovs() assumes that xdr_buf head and
tail buffers would always be contained on a single page. It supplies
just one segment for the head and one for the tail.

FMR, for example, registers up to a page boundary (only a portion of
the reply buffer in the OPEN case above). But without additional
segments, it doesn't register the rest of the buffer.

When the server tries to write the OPEN reply, the RDMA Write fails
with a remote access error since the client registered only part of
the Reply chunk.

rpcrdma_convert_iovs() must split the XDR buffer into multiple
segments, each of which are guaranteed not to contain a page
boundary. That way fmr_op_map is given the proper number of segments
to register the whole reply buffer.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

physical_op_unmap{_sync} don't use mr_nsegs, so don't bother to set
it in physical_op_map.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Fixes: b3221d6a ('xprtrdma: Remove logic that constructs...')
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Pull perf fixes from Thomas Gleixner:
 "A rather largish series of 12 patches addressing a maze of race
  conditions in the perf core code from Peter Zijlstra"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Robustify task_function_call()
  perf: Fix scaling vs. perf_install_in_context()
  perf: Fix scaling vs. perf_event_enable()
  perf: Fix scaling vs. perf_event_enable_on_exec()
  perf: Fix ctx time tracking by introducing EVENT_TIME
  perf: Cure event->pending_disable race
  perf: Fix race between event install and jump_labels
  perf: Fix cloning
  perf: Only update context time when active
  perf: Allow perf_release() with !event->ctx
  perf: Do not double free
  perf: Close install vs. exit race

Pull x86 fixes from Thomas Gleixner:
 "This update contains:

   - Hopefully the last ASM CLAC fixups

   - A fix for the Quark family related to the IMR lock which makes
     kexec work again

   - A off-by-one fix in the MPX code.  Ironic, isn't it?

   - A fix for X86_PAE which addresses once more an unsigned long vs
     phys_addr_t hickup"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mpx: Fix off-by-one comparison with nr_registers
  x86/mm: Fix slow_virt_to_phys() for X86_PAE again
  x86/entry/compat: Add missing CLAC to entry_INT80_32
  x86/entry/32: Add an ASM_CLAC to entry_SYSENTER_32
  x86/platform/intel/quark: Change the kernel's IMR lock bit to false

Pull scheduler fixlet from Thomas Gleixner:
 "A trivial printk typo fix"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Fix trivial typo in printk() message

Pull irq fixes from Thomas Gleixner:
 "Four small fixes for irqchip drivers:

   - Add missing low level irq handler initialization on mxs, so
     interrupts can acutally be delivered

   - Add a missing barrier to the GIC driver

   - Two fixes for the GIC-V3-ITS driver, addressing a double EOI write
     and a cache flush beyond the actual region"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip/gic-v3: Add missing barrier to 32bit version of gic_read_iar()
  irqchip/mxs: Add missing set_handle_irq()
  irqchip/gicv3-its: Avoid cache flush beyond ITS_BASERn memory size
  irqchip/gic-v3-its: Fix double ICC_EOIR write for LPI in EOImode==1

Pull staging/android fix from Greg KH:
 "Here is one patch, for the android binder driver, to resolve a
  reported problem.  Turns out it has been around for a while (since
  3.15), so it is good to finally get it resolved.

  It has been in linux-next for a while with no reported issues"

* tag 'staging-4.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE

Pull USB fixes from Greg KH:
 "Here are a few USB fixes for 4.5-rc6

  They fix a reported bug for some USB 3 devices by reverting the recent
  patch, a MAINTAINERS change for some drivers, some new device ids, and
  of course, the usual bunch of USB gadget driver fixes.

  All have been in linux-next for a while with no reported issues"

* tag 'usb-4.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  MAINTAINERS: drop OMAP USB and MUSB maintainership
  usb: musb: fix DMA for host mode
  usb: phy: msm: Trigger USB state detection work in DRD mode
  usb: gadget: net2280: fix endpoint max packet for super speed connections
  usb: gadget: gadgetfs: unregister gadget only if it got successfully registered
  usb: gadget: remove driver from pending list on probe error
  Revert "usb: hub: do not clear BOS field during reset device"
  usb: chipidea: fix return value check in ci_hdrc_pci_probe()
  usb: chipidea: error on overflow for port_test_write
  USB: option: add "4G LTE usb-modem U901"
  USB: cp210x: add IDs for GE B650V3 and B850V3 boards
  USB: option: add support for SIM7100E
  usb: musb: Fix DMA desired mode for Mentor DMA engine
  usb: gadget: fsl_qe_udc: fix IS_ERR_VALUE usage
  usb: dwc2: USB_DWC2 should depend on HAS_DMA
  usb: dwc2: host: fix the data toggle error in full speed descriptor dma
  usb: dwc2: host: fix logical omissions in dwc2_process_non_isoc_desc
  usb: dwc3: Fix assignment of EP transfer resources
  usb: dwc2: Add extra delay when forcing dr_mode

Pull vfs fixes from Al Viro.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  do_last(): ELOOP failure exit should be done after leaving RCU mode
  should_follow_link(): validate ->d_seq after having decided to follow
  namei: ->d_inode of a pinned dentry is stable only for positives
  do_last(): don't let a bogus return value from ->open() et.al. to confuse us
  fs: return -EOPNOTSUPP if clone is not supported
  hpfs: don't truncate the file when delete fails

Pull ARM SoC fixes from Olof Johansson:
 "We didn't have a batch last week, so this one is slightly larger.

  None of them are scary though, a handful of fixes for small DT pieces,
  replacing properties with newer conventions.

  Highlights:
   - N900 fix for setting system revision
   - onenand init fix to avoid filesystem corruption
   - Clock fix for audio on Beaglebone-x15
   - Fixes on shmobile to deal with CONFIG_DEBUG_RODATA (default y in 4.6)

  + misc smaller stuff"

* tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
  MAINTAINERS: Extend info, add wiki and ml for meson arch
  MAINTAINERS: alpine: add a new maintainer and update the entry
  ARM: at91/dt: fix typo in sama5d2 pinmux descriptions
  ARM: OMAP2+: Fix onenand initialization to avoid filesystem corruption
  Revert "regulator: tps65217: remove tps65217.dtsi file"
  ARM: shmobile: Remove shmobile_boot_arg
  ARM: shmobile: Move shmobile_smp_{mpidr, fn, arg}[] from .text to .bss
  ARM: shmobile: r8a7779: Remove remainings of removed SCU boot setup code
  ARM: shmobile: Move shmobile_scu_base from .text to .bss
  ARM: OMAP2+: Fix omap_device for module reload on PM runtime forbid
  ARM: OMAP2+: Improve omap_device error for driver writers
  ARM: DTS: am57xx-beagle-x15: Select SYS_CLK2 for audio clocks
  ARM: dts: am335x/am57xx: replace gpio-key,wakeup with wakeup-source property
  ARM: OMAP2+: Set system_rev from ATAGS for n900
  ARM: dts: orion5x: fix the missing mtd flash on linkstation lswtgl
  ARM: dts: kirkwood: use unique machine name for ds112
  ARM: dts: imx6: remove bogus interrupt-parent from CAAM node

... or we risk seeing a bogus value of d_is_symlink() there.

Cc: stable@vger.kernel.org # v4.2+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

... otherwise d_is_symlink() above might have nothing to do with
the inode value we've got.

Cc: stable@vger.kernel.org # v4.2+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

both do_last() and walk_component() risk picking a NULL inode out
of dentry about to become positive, *then* checking its flags and
seeing that it's not negative anymore and using (already stale by
then) value they'd fetched earlier.  Usually ends up oopsing soon
after that...

Cc: stable@vger.kernel.org # v3.13+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

... into returning a positive to path_openat(), which would interpret that
as "symlink had been encountered" and proceed to corrupt memory, etc.
It can only happen due to a bug in some ->open() instance or in some LSM
hook, etc., so we report any such event *and* make sure it doesn't trick
us into further unpleasantness.

Cc: stable@vger.kernel.org # v3.6+, at least
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

-EBADF is a rather confusing error if an operations is not supported,
and nfsd gets rather upset about it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

The delete opration can allocate additional space on the HPFS filesystem
due to btree split. The HPFS driver checks in advance if there is
available space, so that it won't corrupt the btree if we run out of space
during splitting.

If there is not enough available space, the HPFS driver attempted to
truncate the file, but this results in a deadlock since the commit
7dd29d8d ("HPFS: Introduce a global mutex
and lock it on every callback from VFS").

This patch removes the code that tries to truncate the file and -ENOSPC is
returned instead. If the user hits -ENOSPC on delete, he should try to
delete other files (that are stored in a leaf btree node), so that the
delete operation will make some space for deleting the file stored in
non-leaf btree node.
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
Cc: stable@vger.kernel.org	# 2.6.39+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Merge fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  dax: move writeback calls into the filesystems
  dax: give DAX clearing code correct bdev
  ext4: online defrag not supported with DAX
  ext2, ext4: only set S_DAX for regular inodes
  block: disable block device DAX by default
  ocfs2: unlock inode if deleting inode from orphan fails
  mm: ASLR: use get_random_long()
  drivers: char: random: add get_random_long()
  mm: numa: quickly fail allocations for NUMA balancing on full nodes
  mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED

Pull ext2/4 DAX fix from Ted Ts'o:
 "This fixes a file system corruption bug with DAX"

* tag 'tags/ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext2, ext4: fix issue with missing journal entry in ext4_dax_mkwrite()

Pull PCI fixes from Bjorn Helgaas:
 "Enumeration:
    Revert x86 pcibios_alloc_irq() to fix regression (Bjorn Helgaas)

  Marvell MVEBU host bridge driver:
    Restrict build to 32-bit ARM (Thierry Reding)"

* tag 'pci-v4.5-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
  PCI: mvebu: Restrict build to 32-bit ARM
  Revert "PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()"
  Revert "PCI: Add helpers to manage pci_dev->irq and pci_dev->irq_managed"
  Revert "x86/PCI: Don't alloc pcibios-irq when MSI is enabled"

As it is currently written ext4_dax_mkwrite() assumes that the call into
__dax_mkwrite() will not have to do a block allocation so it doesn't create
a journal entry.  For a read that creates a zero page to cover a hole
followed by a write that actually allocates storage this is incorrect.  The
ext4_dax_mkwrite() -> __dax_mkwrite() -> __dax_fault() path calls
get_blocks() to allocate storage.

Fix this by having the ->page_mkwrite fault handler call ext4_dax_fault()
as this function already has all the logic needed to allocate a journal
entry and call __dax_fault().

Also update the ext2 fault handlers in this same way to remove duplicate
code and keep the logic between ext2 and ext4 the same.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

Pull clk fix from Stephen Boyd:
 "One small fix to keep OMAP platforms working across a suspend/resume
  cycle"

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
  clk: ti: omap3+: dpll: use non-locking version of clk_get_rate

Previously calls to dax_writeback_mapping_range() for all DAX filesystems
(ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range().

dax_writeback_mapping_range() needs a struct block_device, and it used
to get that from inode->i_sb->s_bdev.  This is correct for normal inodes
mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw
block devices and for XFS real-time files.

Instead, call dax_writeback_mapping_range() directly from the filesystem
->writepages function so that it can supply us with a valid block
device.  This also fixes DAX code to properly flush caches in response
to sync(2).
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

dax_clear_blocks() needs a valid struct block_device and previously it
was using inode->i_sb->s_bdev in all cases.  This is correct for normal
inodes on mounted ext2, ext4 and XFS filesystems, but is incorrect for
DAX raw block devices and for XFS real-time devices.

Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change
its arguments to take a bdev and a sector instead of an inode and a
block.  This better reflects what the function does, and it allows the
filesystem and raw block device code to pass in an appropriate struct
block_device.
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Online defrag operations for ext4 are hard coded to use the page cache.
See ext4_ioctl() -> ext4_move_extents() -> move_extent_per_page()

When combined with DAX I/O, which circumvents the page cache, this can
result in data corruption.  This was observed with xfstests ext4/307 and
ext4/308.

Fix this by only allowing online defrag for non-DAX files.
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

When S_DAX is set on an inode we assume that if there are pages attached
to the mapping (mapping->nrpages != 0), those pages are clean zero pages
that were used to service reads from holes.  Any dirty data associated
with the inode should be in the form of DAX exceptional entries
(mapping->nrexceptional) that is written back via
dax_writeback_mapping_range().

With the current code, though, this isn't always true.  For example,
ext2 and ext4 directory inodes can have S_DAX set, but have their dirty
data stored as dirty page cache entries.  For these types of inodes,
having S_DAX set doesn't really make sense since their I/O doesn't
actually happen through the DAX code path.

Instead, only allow S_DAX to be set for regular inodes for ext2 and
ext4.  This allows us to have strict DAX vs non-DAX paths in the
writeback code.
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

The recent *sync enabling discovered that we are inserting into the
block_device pagecache counter to the expectations of the dirty data
tracking for dax mappings.  This can lead to data corruption.

We want to support DAX for block devices eventually, but it requires
wider changes to properly manage the pagecache.

   dump_stack+0x85/0xc2
   dax_writeback_mapping_range+0x60/0xe0
   blkdev_writepages+0x3f/0x50
   do_writepages+0x21/0x30
   __filemap_fdatawrite_range+0xc6/0x100
   filemap_write_and_wait+0x4a/0xa0
   set_blocksize+0x70/0xd0
   sb_set_blocksize+0x1d/0x50
   ext4_fill_super+0x75b/0x3360
   mount_bdev+0x180/0x1b0
   ext4_mount+0x15/0x20
   mount_fs+0x38/0x170

Mark the support broken so its disabled by default, but otherwise still
available for testing.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

When doing append direct io cleanup, if deleting inode fails, it goes
out without unlocking inode, which will cause the inode deadlock.

This issue was introduced by commit cf1776a9 ("ocfs2: fix a tiny
race when truncate dio orohaned entry").
Signed-off-by: Guozhonghua <guozhonghua@h3c.com>
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reviewed-by: Gang He <ghe@suse.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: <stable@vger.kernel.org>	[4.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Replace calls to get_random_int() followed by a cast to (unsigned long)
with calls to get_random_long().  Also address shifting bug which, in
case of x86 removed entropy mask for mmap_rnd_bits values > 31 bits.
Signed-off-by: Daniel Cashman <dcashman@android.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: David S. Miller <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nick Kralevich <nnk@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Mark Salyzyn <salyzyn@android.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Commit d07e2259 ("mm: mmap: add new /proc tunable for mmap_base
ASLR") added the ability to choose from a range of values to use for
entropy count in generating the random offset to the mmap_base address.

The maximum value on this range was set to 32 bits for 64-bit x86
systems, but this value could be increased further, requiring more than
the 32 bits of randomness provided by get_random_int(), as is already
possible for arm64.  Add a new function: get_random_long() which more
naturally fits with the mmap usage of get_random_int() but operates
exactly the same as get_random_int().

Also, fix the shifting constant in mmap_rnd() to be an unsigned long so
that values greater than 31 bits generate an appropriate mask without
overflow.  This is especially important on x86, as its shift instruction
uses a 5-bit mask for the shift operand, which meant that any value for
mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base
randomization.

Finally, replace calls to get_random_int() with get_random_long() where
appropriate.

This patch (of 2):

Add get_random_long().
Signed-off-by: Daniel Cashman <dcashman@android.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: David S. Miller <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nick Kralevich <nnk@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Mark Salyzyn <salyzyn@android.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Commit 4167e9b2 ("mm: remove GFP_THISNODE") removed the GFP_THISNODE
flag combination due to confusing semantics.  It noted that
alloc_misplaced_dst_page() was one such user after changes made by
commit e97ca8e5 ("mm: fix GFP_THISNODE callers and clarify").

Unfortunately when GFP_THISNODE was removed, users of
alloc_misplaced_dst_page() started waking kswapd and entering direct
reclaim because the wrong GFP flags are cleared.  The consequence is
that workloads that used to fit into memory now get reclaimed which is
addressed by this patch.

The problem can be demonstrated with "mutilate" that exercises memcached
which is software dedicated to memory object caching.  The configuration
uses 80% of memory and is run 3 times for varying numbers of clients.
The results on a 4-socket NUMA box are

mutilate
                            4.4.0                 4.4.0
                          vanilla           numaswap-v1
Hmean    1      8394.71 (  0.00%)     8395.32 (  0.01%)
Hmean    4     30024.62 (  0.00%)    34513.54 ( 14.95%)
Hmean    7     32821.08 (  0.00%)    70542.96 (114.93%)
Hmean    12    55229.67 (  0.00%)    93866.34 ( 69.96%)
Hmean    21    39438.96 (  0.00%)    85749.21 (117.42%)
Hmean    30    37796.10 (  0.00%)    50231.49 ( 32.90%)
Hmean    47    18070.91 (  0.00%)    38530.13 (113.22%)

The metric is queries/second with the more the better.  The results are
way outside of the noise and the reason for the improvement is obvious
from some of the vmstats

                                 4.4.0       4.4.0
                               vanillanumaswap-v1r1
Minor Faults                1929399272  2146148218
Major Faults                  19746529        3567
Swap Ins                      57307366        9913
Swap Outs                     50623229       17094
Allocation stalls                35909         443
DMA allocs                           0           0
DMA32 allocs                  72976349   170567396
Normal allocs               5306640898  5310651252
Movable allocs                       0           0
Direct pages scanned         404130893      799577
Kswapd pages scanned         160230174           0
Kswapd pages reclaimed        55928786           0
Direct pages reclaimed         1843936       41921
Page writes file                  2391           0
Page writes anon              50623229       17094

The vanilla kernel is swapping like crazy with large amounts of direct
reclaim and kswapd activity.  The figures are aggregate but it's known
that the bad activity is throughout the entire test.

Note that simple streaming anon/file memory consumers also see this
problem but it's not as obvious.  In those cases, kswapd is awake when
it should not be.

As there are at least two reclaim-related bugs out there, it's worth
spelling out the user-visible impact.  This patch only addresses bugs
related to excessive reclaim on NUMA hardware when the working set is
larger than a NUMA node.  There is a bug related to high kswapd CPU
usage but the reports are against laptops and other UMA hardware and is
not addressed by this patch.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org>	[4.1+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were
introduced to locklessy (but atomically) detect when a pmd is a regular
(stable) pmd or when the pmd is unstable and can infinitely transition
from pmd_none() and pmd_trans_huge() from under us, while only holding
the mmap_sem for reading (for writing not).

While holding the mmap_sem only for reading, MADV_DONTNEED can run from
under us and so before we can assume the pmd to be a regular stable pmd
we need to compare it against pmd_none() and pmd_trans_huge() in an
atomic way, with pmd_trans_unstable().  The old pmd_trans_huge() left a
tiny window for a race.

Useful applications are unlikely to notice the difference as doing
MADV_DONTNEED concurrently with a page fault would lead to undefined
behavior.

[akpm@linux-foundation.org: tidy up comment grammar/layout]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This driver uses PCI glue that is only available on 32-bit ARM.  This used
to work fine as long as ARCH_MVEBU and ARCH_DOVE were exclusively 32-bit,
but there's a patch in the pipe to make ARCH_MVEBU also available on 64-bit
ARM.

[bhelgaas: changelog; patch is coming but not merged yet]
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>

991de2e5 ("PCI, x86: Implement pcibios_alloc_irq() and
pcibios_free_irq()") appeared in v4.3 and helps support IOAPIC hotplug.

Олег reported that the Elcus-1553 TA1-PCI driver worked in v4.2 but not
v4.3 and bisected it to 991de2e5.  Sunjin reported that the RocketRAID
272x driver worked in v4.2 but not v4.3.  In both cases booting with
"pci=routirq" is a workaround.

I think the problem is that after 991de2e5, we no longer call
pcibios_enable_irq() for upstream bridges.  Prior to 991de2e5, when a
driver called pci_enable_device(), we recursively called
pcibios_enable_irq() for upstream bridges via pci_enable_bridge().

After 991de2e5, we call pcibios_enable_irq() from pci_device_probe()
instead of the pci_enable_device() path, which does *not* call
pcibios_enable_irq() for upstream bridges.

Revert 991de2e5 to fix these driver regressions.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211
Fixes: 991de2e5 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()")
Reported-and-tested-by: Олег Мороз <oleg.moroz@mcc.vniiem.ru>
Reported-by: Sunjin Yang <fan4326@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
CC: Jiang Liu <jiang.liu@linux.intel.com>