[3.13.y.z extended stable] Linux 3.13.11.5 stable review

[3.13.y.z extended stable] Linux 3.13.11.5 stable review

[Kamal Mostafa]

This is the start of the review cycle for the Linux 3.13.11.5 stable kernel.

This version contains 198 new patches, summarized below.  The new patches are
posted as replies to this message and also available in this git branch:

http://kernel.ubuntu.com/git?p=ubuntu/linux.git;h=linux-3.13.y-review;a=shortlog

git://kernel.ubuntu.com/ubuntu/linux.git  linux-3.13.y-review

The review period for version 3.13.11.5 will be open for the next three days.
To report a problem, please reply to the relevant follow-up patch message.

For more information about the Linux 3.13.y.z extended stable kernel version,
see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable .

 -Kamal

--
 Documentation/sysctl/vm.txt                        |   3 +-
 Documentation/vm/hwpoison.txt                      |   5 +
 Documentation/x86/x86_64/mm.txt                    |   2 +
 arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts   |   2 +-
 arch/arm/kernel/stacktrace.c                       |  18 +-
 arch/arm/mm/hugetlbpage.c                          |   5 -
 arch/arm64/include/asm/Kbuild                      |   1 -
 arch/arm64/include/asm/dma-mapping.h               |   2 -
 arch/arm64/include/uapi/asm/posix_types.h          |  10 +
 arch/arm64/kernel/entry.S                          |   1 -
 arch/arm64/kernel/ptrace.c                         |  32 ++-
 arch/arm64/mm/hugetlbpage.c                        |   5 -
 arch/ia64/hp/common/sba_iommu.c                    |  64 +++---
 arch/ia64/mm/hugetlbpage.c                         |   5 -
 arch/metag/mm/hugetlbpage.c                        |   5 -
 arch/mips/kernel/irq-msc01.c                       |   2 +-
 arch/mips/kvm/kvm_mips.c                           |   2 +-
 arch/mips/mm/hugetlbpage.c                         |   5 -
 arch/powerpc/include/asm/switch_to.h               |   8 +-
 arch/powerpc/include/asm/systbl.h                  |   2 +-
 arch/powerpc/include/uapi/asm/cputable.h           |   1 +
 arch/powerpc/kernel/cputable.c                     |   3 +-
 arch/powerpc/kernel/entry_64.S                     |   6 -
 arch/powerpc/kernel/legacy_serial.c                |  15 +-
 arch/powerpc/kernel/process.c                      |   8 +-
 arch/powerpc/kernel/setup-common.c                 |  10 +-
 arch/powerpc/mm/hash_utils_64.c                    |  31 ++-
 arch/powerpc/mm/hugetlbpage.c                      |  10 -
 arch/powerpc/platforms/pseries/eeh_pseries.c       |   1 +
 arch/s390/include/asm/lowcore.h                    |  11 +-
 arch/s390/kernel/time.c                            |   2 +-
 arch/s390/mm/hugetlbpage.c                         |   5 -
 arch/sh/mm/hugetlbpage.c                           |   5 -
 arch/sparc/mm/hugetlbpage.c                        |   5 -
 arch/tile/mm/hugetlbpage.c                         |   5 -
 arch/x86/Kconfig                                   |   4 +
 arch/x86/include/asm/pgtable_64_types.h            |   2 +
 arch/x86/include/asm/setup.h                       |   3 +
 arch/x86/kernel/Makefile                           |   1 +
 arch/x86/kernel/entry_32.S                         |  15 +-
 arch/x86/kernel/entry_64.S                         |  73 ++++++-
 arch/x86/kernel/espfix_64.c                        | 208 ++++++++++++++++++
 arch/x86/kernel/ldt.c                              |  11 -
 arch/x86/kernel/smpboot.c                          |   7 +
 arch/x86/kvm/lapic.c                               |  62 ++++--
 arch/x86/mm/dump_pagetables.c                      |  40 +++-
 arch/x86/mm/hugetlbpage.c                          |  10 -
 arch/x86/syscalls/syscall_64.tbl                   |   6 +-
 block/blk-cgroup.c                                 |   7 +-
 block/blk-cgroup.h                                 |  17 +-
 drivers/acpi/acpica/utstring.c                     |   2 +-
 drivers/acpi/bus.c                                 |   7 +
 drivers/acpi/video_detect.c                        |   8 +
 drivers/ata/ahci.c                                 |   4 +
 drivers/base/dma-contiguous.c                      |  12 +-
 drivers/base/power/opp.c                           |   4 +-
 drivers/block/mtip32xx/mtip32xx.c                  | 123 ++++++++---
 drivers/block/rbd.c                                |  19 +-
 drivers/block/virtio_blk.c                         |   9 +-
 drivers/bluetooth/hci_ldisc.c                      |  24 +-
 drivers/bluetooth/hci_uart.h                       |   1 +
 drivers/extcon/extcon-max77693.c                   |   4 +-
 drivers/extcon/extcon-max8997.c                    |   2 +-
 drivers/firmware/efi/efi-pstore.c                  |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |   2 +
 drivers/gpu/drm/i915/i915_irq.c                    |  18 +-
 drivers/gpu/drm/i915/intel_pm.c                    |   3 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h            |   2 +-
 drivers/gpu/drm/i915/intel_sdvo.c                  |   4 +-
 drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c      |   2 +-
 drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c      |   2 +-
 drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c      |   2 +-
 drivers/gpu/drm/nouveau/nouveau_display.c          |  17 +-
 drivers/gpu/drm/radeon/atombios_crtc.c             |  48 ++--
 drivers/gpu/drm/radeon/atombios_dp.c               |  17 +-
 drivers/gpu/drm/radeon/atombios_encoders.c         |   5 +-
 drivers/gpu/drm/radeon/radeon_connectors.c         |   2 +-
 drivers/gpu/vga/vga_switcheroo.c                   |   3 +-
 drivers/hid/hid-core.c                             |  12 +-
 drivers/hv/connection.c                            |   4 +-
 drivers/hv/hv_balloon.c                            |  29 ++-
 drivers/hwmon/ina2xx.c                             |   7 +-
 drivers/iio/adc/at91_adc.c                         |  16 +-
 drivers/iio/adc/max1363.c                          |  16 +-
 drivers/iio/magnetometer/ak8975.c                  |   9 +-
 drivers/infiniband/core/user_mad.c                 |  75 ++++---
 drivers/infiniband/hw/cxgb4/cq.c                   |   3 +-
 drivers/infiniband/hw/cxgb4/user.h                 |   1 +
 drivers/infiniband/hw/ipath/ipath_diag.c           |   4 +
 drivers/infiniband/hw/mlx5/cq.c                    |  13 +-
 drivers/infiniband/hw/mlx5/srq.c                   |  14 +-
 drivers/infiniband/hw/mlx5/user.h                  |   2 +
 drivers/infiniband/hw/qib/qib_mad.c                |   2 +-
 drivers/infiniband/ulp/isert/ib_isert.c            |  61 +++---
 drivers/infiniband/ulp/isert/ib_isert.h            |   2 +-
 drivers/infiniband/ulp/srp/ib_srp.c                |   6 +
 drivers/input/mouse/elantech.c                     |  27 ++-
 drivers/md/dm-thin.c                               |   3 +-
 drivers/media/dvb-core/dvb-usb-ids.h               |   2 +
 drivers/media/pci/ivtv/ivtv-alsa-pcm.c             |   6 +
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c            |   8 +
 drivers/media/usb/uvc/uvc_video.c                  |  15 +-
 drivers/misc/mei/hw-me.c                           |  26 ++-
 drivers/mtd/nand/fsl_elbc_nand.c                   |  14 ++
 drivers/mtd/nand/omap2.c                           |   2 +-
 drivers/mtd/nand/pxa3xx_nand.c                     |   4 +-
 drivers/net/ethernet/allwinner/sun4i-emac.c        |   1 +
 drivers/net/ethernet/intel/igb/igb_main.c          |   4 +-
 drivers/net/wireless/b43/xmit.c                    |  10 +-
 drivers/net/wireless/iwlwifi/pcie/trans.c          |  26 ++-
 drivers/net/wireless/rt2x00/rt2500pci.c            |   7 +-
 drivers/net/wireless/rt2x00/rt2x00.h               |   1 +
 drivers/net/wireless/rt2x00/rt2x00dev.c            |  24 +-
 drivers/net/wireless/rt2x00/rt2x00mac.c            |   2 +
 drivers/pci/quirks.c                               |   1 +
 drivers/rtc/rtc-at91rm9200.c                       |  16 +-
 drivers/scsi/hpsa.c                                |  12 +
 drivers/staging/iio/light/tsl2x7x_core.c           |   8 +-
 drivers/staging/mt29f_spinand/mt29f_spinand.c      |   1 +
 drivers/target/iscsi/iscsi_target.c                |  19 +-
 drivers/target/iscsi/iscsi_target_auth.c           |  10 +
 drivers/target/iscsi/iscsi_target_login.c          |  13 +-
 drivers/target/iscsi/iscsi_target_util.c           |   2 +
 drivers/target/target_core_device.c                |   1 +
 drivers/target/target_core_sbc.c                   |   4 +-
 drivers/target/target_core_spc.c                   |   9 +-
 drivers/target/target_core_transport.c             |  29 ++-
 drivers/usb/dwc3/gadget.c                          |   4 +
 drivers/usb/host/pci-quirks.c                      |  19 +-
 drivers/usb/misc/usbtest.c                         |  10 +
 drivers/usb/serial/qcserial.c                      |  21 ++
 drivers/video/offb.c                               |  11 +-
 drivers/watchdog/ath79_wdt.c                       |  10 +
 drivers/watchdog/kempld_wdt.c                      |   2 +-
 drivers/watchdog/sp805_wdt.c                       |   4 +-
 fs/aio.c                                           |   6 +-
 fs/attr.c                                          |   8 +-
 fs/btrfs/extent_io.c                               |   1 +
 fs/btrfs/ioctl.c                                   |   6 +-
 fs/cifs/cifs_unicode.c                             |   7 +-
 fs/cifs/smb2pdu.c                                  |   7 +-
 fs/eventpoll.c                                     |   4 +-
 fs/ext4/ext4.h                                     |   3 +-
 fs/ext4/inode.c                                    |   6 +-
 fs/ext4/mballoc.c                                  |   2 +-
 fs/ext4/page-io.c                                  |  32 +--
 fs/inode.c                                         |  10 +-
 fs/namei.c                                         |  11 +-
 fs/nfs/inode.c                                     |  26 ++-
 fs/nfs/super.c                                     |   1 +
 fs/nfs/write.c                                     |   4 +-
 fs/nfsd/nfs4state.c                                |   2 +-
 fs/nfsd/nfs4xdr.c                                  |   4 +-
 fs/reiserfs/inode.c                                |   8 +-
 fs/ubifs/file.c                                    |   3 +-
 fs/ubifs/shrinker.c                                |   1 -
 fs/xfs/xfs_bmap_util.c                             |  16 +-
 fs/xfs/xfs_bmap_util.h                             |  13 +-
 fs/xfs/xfs_ioctl.c                                 |   2 +-
 include/linux/capability.h                         |   2 +-
 include/linux/hugetlb.h                            |  13 +-
 include/linux/init_task.h                          |   2 +
 include/linux/irqdesc.h                            |   4 +
 include/linux/mempolicy.h                          |   6 +
 include/linux/mmzone.h                             |   6 +-
 include/linux/page-flags.h                         |  12 +-
 include/linux/pageblock-flags.h                    |  37 +++-
 include/linux/ptrace.h                             |  32 +++
 include/linux/sched.h                              |  12 +
 include/sound/core.h                               |   2 +
 include/target/iscsi/iscsi_transport.h             |   3 +-
 include/target/target_core_backend.h               |   1 +
 include/uapi/sound/compress_offload.h              |   2 +-
 init/main.c                                        |   4 +
 kernel/auditsc.c                                   |  27 ++-
 kernel/capability.c                                |  20 +-
 kernel/exit.c                                      |   1 +
 kernel/fork.c                                      |  17 +-
 kernel/irq/manage.c                                |   4 +-
 kernel/irq/spurious.c                              | 106 ++++++++-
 kernel/kthread.c                                   |   4 +-
 kernel/locking/rtmutex-debug.h                     |   5 +
 kernel/locking/rtmutex.c                           | 243 ++++++++++++++++++---
 kernel/locking/rtmutex.h                           |   5 +
 kernel/sysctl.c                                    |   3 +-
 kernel/watchdog.c                                  |   2 -
 lib/idr.c                                          |   8 +-
 lib/lz4/lz4_decompress.c                           |   6 +-
 lib/lzo/lzo1x_decompress_safe.c                    |  62 ++++--
 mm/Kconfig                                         |   3 +
 mm/hugetlb.c                                       |  71 +++---
 mm/memcontrol.c                                    |   5 +-
 mm/memory-failure.c                                |  73 +++++--
 mm/mempolicy.c                                     |  46 ++--
 mm/page-writeback.c                                |  11 +-
 mm/page_alloc.c                                    |  92 +++++---
 mm/rmap.c                                          |   8 +-
 mm/vmscan.c                                        |  46 +++-
 net/bluetooth/hci_conn.c                           |  11 +-
 net/bluetooth/hci_event.c                          |  11 +-
 net/bluetooth/l2cap_sock.c                         |  10 +-
 net/bluetooth/mgmt.c                               |   7 +-
 net/bluetooth/smp.c                                |   9 +-
 net/ipv6/udp.c                                     |   8 +-
 net/mac80211/debugfs_netdev.c                      |   6 +-
 net/mac80211/ibss.c                                |   1 +
 net/mac80211/sta_info.c                            |   1 +
 net/netfilter/nf_nat_core.c                        |  35 ++-
 net/sunrpc/svc_xprt.c                              |   2 +
 scripts/package/builddeb                           |   6 +-
 scripts/recordmcount.h                             |   4 +-
 security/integrity/evm/evm_main.c                  |  12 +-
 sound/core/control.c                               |  78 ++++---
 sound/core/init.c                                  |   1 +
 sound/pci/hda/hda_intel.c                          |  63 +++++-
 sound/pci/hda/patch_hdmi.c                         |   2 +-
 sound/pci/hda/patch_realtek.c                      |  71 ++++++
 sound/soc/codecs/max98090.c                        |   3 +
 sound/soc/codecs/tlv320aic3x.c                     |   2 +-
 sound/usb/card.c                                   |  13 +-
 sound/usb/endpoint.c                               |  17 +-
 sound/usb/endpoint.h                               |   1 +
 sound/usb/pcm.c                                    |   3 +-
 tools/testing/selftests/powerpc/Makefile           |   2 +-
 tools/testing/selftests/powerpc/tm/Makefile        |  15 ++
 .../testing/selftests/powerpc/tm/tm-resched-dscr.c |  90 ++++++++
 226 files changed, 2571 insertions(+), 877 deletions(-)

Alan Stern (1):
      USB: EHCI: avoid BIOS handover on the HASEE E200

Aleksander Morgado (2):
      usb: qcserial: add Netgear AirCard 341U
      usb: qcserial: add additional Sierra Wireless QMI devices

Alessandro Miceli (2):
      [media] rtl28xxu: add [1b80:d39d] Sveon STV20
      [media] rtl28xxu: add [1b80:d3af] Sveon STV27

Alex Deucher (5):
      vgaswitcheroo: switch the mux to the igp on power down when runpm is enabled
      drm/radeon: fix typo in radeon_connector_is_dp12_capable()
      drm/radeon/dp: fix lane/clock setup for dp 1.2 capable devices
      drm/radeon/atom: fix dithering on certain panels
      drm/radeon: only apply hdmi bpc pll flags when encoder mode is hdmi

Alex Elder (1):
      rbd: use reference counts for image requests

Alex Smith (1):
      recordmcount/MIPS: Fix possible incorrect mcount_loc table entries in modules

Andreas Schrägle (1):
      ahci: add PCI ID for Marvell 88SE91A0 SATA Controller

Andrzej Zaborowski (1):
      efi-pstore: Fix an overflow on 32-bit builds

Andy Lutomirski (3):
      auditsc: audit_krule mask accesses need bounds checking
      fs,userns: Change inode_capable to capable_wrt_inode_uidgid
      x86_32, entry: Do syscall exit work on badsys (CVE-2014-4508)

Anton Blanchard (1):
      powerpc: 64bit sendfile is capped at 2GB

Arik Nemtsov (1):
      mac80211: don't check netdev state for debugfs read/write

Asai Thambi S P (3):
      mtip32xx: Increase timeout for STANDBY IMMEDIATE command
      mtip32xx: Remove dfs_parent after pci unregister
      mtip32xx: Fix ERO and NoSnoop values in PCIe upstream on AMD systems

Bart Van Assche (3):
      IB/srp: Fix a sporadic crash triggered by cable pulling
      IB/umad: Fix error handling
      IB/umad: Fix use-after-free on close

Benjamin Herrenschmidt (3):
      powerpc/serial: Use saner flags when creating legacy ports
      powerpc: Add AT_HWCAP2 to indicate V.CRYPTO category support
      Revert "offb: Add palette hack for little endian"

Benjamin LaHaise (2):
      aio: fix aio request leak when events are reaped by userspace
      aio: fix kernel memory disclosure in io_getevents() introduced in v3.10

Boris BREZILLON (1):
      rtc: rtc-at91rm9200: fix infinite wait for ACKUPD irq

Brian Healy (1):
      [media] rtl28xxu: add 1b80:d395 Peak DVB-T USB

Chander Kashyap (1):
      PM / OPP: fix incorrect OPP count handling in of_init_opp_table

ChiaHao (1):
      arm64: Bug fix in stack alignment exception

Chris Mason (1):
      Btrfs: fix double free in find_lock_delalloc_range

Chris Wilson (3):
      drm/i915: Disable FBC by default also on Haswell and later
      drm/i915: Reorder semaphore deadlock check
      drm/i915: Hold the table lock whilst walking the file's idr and counting the objects in debugfs

Christian Borntraeger (1):
      s390/lowcore: reserve 96 bytes for IRB in lowcore

Christoph Hellwig (1):
      nfsd: getattr for FATTR4_WORD0_FILES_AVAIL needs the statfs buffer

Dan Carpenter (1):
      iio: adc: at91: signedness bug in at91_adc_get_trigger_value_by_name()

Dave Chinner (1):
      xfs: block allocation work needs to be kswapd aware

David Binderman (1):
      ACPICA: utstring: Check array index bound before use.

David Henningsson (1):
      ALSA: hda - Add quirk for external mic on Lifebook U904

David Rientjes (1):
      mm, pcp: allow restoring percpu_pagelist_fraction default

Dennis Dalessandro (1):
      IB/ipath: Translate legacy diagpkt into newer extended diagpkt

Don Zickus (1):
      kernel/watchdog.c: remove preemption restrictions when restarting lockup detector

Edward Lin (1):
      ACPI / video: Add Dell Inspiron 5737 to the blacklist

Emmanuel Grumbach (1):
      iwlwifi: pcie: try to get ownership several times

Fabio Baltieri (1):
      hwmon: (ina2xx) Cast to s16 on shunt and current regs

Fathi Boudra (1):
      builddeb: use $OBJCOPY variable instead of objcopy

Felipe Balbi (2):
      usb: dwc3: gadget: clear stall when disabling endpoint
      bluetooth: hci_ldisc: fix deadlock condition

Felix Fietkau (1):
      mac80211: fix a memory leak on sta rate selection table

Florian Westphal (1):
      netfilter: nf_nat: fix oops on netns removal

Gabor Juhos (1):
      watchdog: ath79_wdt: avoid spurious restarts on AR934x

Gavin Shan (1):
      powerpc/pseries: Fix overwritten PE state

Greg Kroah-Hartman (3):
      lzo: properly check for overruns
      lz4: ensure length does not wrap
      lz4: fix another possible overrun

H. Peter Anvin (2):
      x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack
      x86-32, espfix: Remove filter for espfix32 due to race

Hans de Goede (2):
      Input: elantech - deal with clickpads reporting right button events
      Input: elantech - don't set bit 1 of reg_10 when the no_hw_res quirk is set

Huang Rui (1):
      usb: usbtest: fix unlink write error with pattern 1

Hugh Dickins (2):
      mm: fix sleeping function warning from __put_anon_vma
      mm: fix crashes from mbind() merging vmas

Ilya Dryomov (1):
      rbd: handle parent_overlap on writes correctly

J. Bruce Fields (1):
      nfsd4: fix FREE_STATEID lockowner leak

James Hogan (1):
      MIPS: KVM: Allocate at least 16KB for exception handlers

Jan Kara (1):
      ext4: fix zeroing of page during writeback

Jan Vcelak (1):
      [media] rtl28xxu: add USB ID for Genius TVGo DVB-T03

Jason Cooper (1):
      ARM: mvebu: DT: fix OpenBlocks AX3-4 RAM size

Jeff Mahoney (1):
      reiserfs: call truncate_setsize under tailpack mutex

Joe Handzik (1):
      hpsa: add new Smart Array PCI IDs (May 2014)

Johan Hedberg (6):
      Bluetooth: Fix redundant encryption request for reauthentication
      Bluetooth: Fix check for connection encryption
      Bluetooth: Fix SSP acceptor just-works confirmation without MITM
      Bluetooth: Fix setting correct authentication information for SMP STK
      Bluetooth: Fix indicating discovery state when canceling inquiry
      Bluetooth: Fix locking of hdev when calling into SMP code

Johannes Weiner (1):
      mm: vmscan: clear kswapd's special reclaim powers before exiting

Jonathan Cameron (1):
      iio:adc:max1363 incorrect resolutions for max11604, max11605, max11610 and max11611.

Joonsoo Kim (1):
      DMA, CMA: fix possible memory leak

Jukka Taimisto (1):
      Bluetooth: Fix L2CAP deadlock

Justin Maggard (1):
      btrfs: fix defrag 32-bit integer overflow

Jérôme Carretero (1):
      ahci: Add Device ID for HighPoint RocketRaid 642L

K. Y. Srinivasan (1):
      Drivers: hv: balloon: Ensure pressure reports are posted regularly

Kailang Yang (3):
      ALSA: hda/realtek - Add support of ALC891 codec
      ALSA: hda/realtek - Add more entry for enable HP mute led
      ALSA: hda/realtek - Add more entry for enable HP mute led

Kees Cook (1):
      HID: core: fix validation of report id 0

Konstantin Khlebnikov (1):
      epoll: fix use-after-free in eventpoll_release_file

Krzysztof Hałasa (1):
      mac80211: fix IBSS join by initializing last_scan_completed

Krzysztof Kozlowski (2):
      extcon: max77693: Fix two NULL pointer exceptions on missing pdata
      extcon: max8997: Fix NULL pointer exception on missing pdata

Lai Jiangshan (1):
      idr: fix overflow bug during maximum ID calculation at maximum height

Lars-Peter Clausen (5):
      ALSA: control: Protect user controls against concurrent access
      ALSA: control: Fix replacing user controls
      ALSA: control: Don't access controls outside of protected regions
      ALSA: control: Handle numid overflow
      ALSA: control: Make sure that id->index does not overflow

Liam Girdwood (1):
      ASoC: max98090: Fix reset at resume time

Lukas Czerner (1):
      dm thin: update discard_granularity to reflect the thin-pool blocksize

Lv Zheng (1):
      ACPI: Fix conflict between customized DSDT and DSDT local copy

Marcin Kraglak (1):
      Bluetooth: Allow change security level on ATT_CID in slave role

Mario Kleiner (3):
      drm/nv50-/mc: fix kms pageflip events by reordering irq handling order.
      drm/nouveau/kms/nv04-nv40: fix pageflip events via special case.
      drm/nouveau/kms: reference vblank for crtc during pageflip.

Mario Schuknecht (1):
      staging: iio: tsl2x7x_core: fix proximity treshold

Markos Chandras (1):
      MIPS: MSC: Prevent out-of-bounds writes to MIPS SC ioremap'd region

Martin Schwidefsky (1):
      s390/time: cast tv_nsec to u64 prior to shift in update_vsyscall

Mateusz Guzik (1):
      NFS: populate ->net in mount data when remounting

Matthew Dempsky (1):
      ptrace: fix fork event messages across pid namespaces

Maurizio Lombardi (1):
      ext4: fix wrong assert in ext4_mb_normalize_request()

Maxime Ripard (1):
      net: allwinner: emac: Add missing free_irq

Mel Gorman (2):
      mm: vmscan: do not throttle based on pfmemalloc reserves if node has no ZONE_NORMAL
      mm: page_alloc: use word-based accesses for get/set pageblock bitmaps

Mengdong Lin (1):
      ALSA: hda - restore BCLK M/N values when resuming HSW/BDW display controller

Michael Ellerman (2):
      powerpc/mm: Check paca psize is up to date for huge mappings
      powerpc/perf: Ensure all EBB register state is cleared on fork()

Michael Neuling (1):
      powerpc: Don't setup CPUs with bad status

Michal Hocko (1):
      memcg: do not hang on OOM when killed by userspace OOM access to memory reserves

Mike Frysinger (1):
      x86, x32: Use compat shims for io_{setup,submit}

Mike Marciniszyn (1):
      IB/qib: Fix port in pkey change event

Mikulas Patocka (1):
      iscsi-target: fix iscsit_del_np deadlock on unload

Mimi Zohar (1):
      evm: prohibit userspace writing 'security.evm' HMAC value

Ming Lei (1):
      block: virtio_blk: don't hold spin lock during world switch

Namjae Jeon (1):
      ext4: fix data integrity sync in ordered mode

Naoya Horiguchi (3):
      hugetlb: restrict hugepage_migration_support() to x86_64
      mm/memory-failure.c: support use of a dedicated thread to handle SIGBUS(BUS_MCEERR_AO)
      hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned entry

Nicholas Bellinger (7):
      iscsi-target: Reject mutual authentication with reflected CHAP_C
      target: Set CMD_T_ACTIVE bit for Task Management Requests
      target: Use complete_all for se_cmd->t_transport_stop_comp
      iscsi-target: Fix ABORT_TASK + connection reset iscsi_queue_req memory leak
      target: Fix left-over se_lun->lun_sep pointer OOPs
      iscsi-target: Explicily clear login response PDU in exception path
      iscsi-target: Avoid rejecting incorrect ITT for Data-Out

Oleg Nesterov (1):
      introduce for_each_thread() to replace the buggy while_each_thread()

Olivier Langlois (1):
      [media] uvcvideo: Fix clock param realtime setting

Paolo Bonzini (1):
      KVM: lapic: sync highest ISR to hardware apic on EOI

Pavel Shilovsky (1):
      CIFS: Fix memory leaks in SMB2_open

Pekon Gupta (1):
      mtd: eLBC NAND: fix subpage write support

Peter Meerwald (1):
      iio: Fix endianness issue in ak8975_read_axis()

Peter Ujfalusi (1):
      ASoC: tlv320aci3x: Fix custom snd_soc_dapm_put_volsw_aic3x() function

Pierre Ossman (1):
      ALSA: hda - hdmi: call overridden init on resume

Radim Krčmář (1):
      hv: use correct order when freeing monitor_pages

Rafael J. Wysocki (1):
      ACPI / ia64 / sba_iommu: Restore the working initialization ordering

Rafał Miłecki (1):
      b43: fix frequency reported on G-PHY with /new/ firmware

Roland Dreier (1):
      target: Report correct response length for some commands

Russell King (1):
      ARM: stacktrace: avoid listing stacktrace functions in stacktrace

Sagi Grimberg (5):
      Target/iser: Bail from accept_np if np_thread is trying to close
      Target/iser: Fix hangs in connection teardown
      Target/iser: Improve cm events handling
      Target/iser: Wait for proper cleanup before unloading
      Target/iscsi: Fix sendtargets response pdu for iser transport

Sam bobroff (1):
      powerpc: Correct DSCR during TM context switch

Sander Eikelenboom (1):
      ALSA: usb-audio: Prevent printk ratelimiting from spamming kernel log while DEBUG not defined

Scott Mayhew (1):
      nfs: Fix cache_validity check in nfs_write_pageuptodate()

Scott Wood (1):
      powerpc: Don't skip ePAPR spin-table CPUs

Stanislaw Gruszka (2):
      rt2x00: disable TKIP on USB
      rt2x00: fix rfkill regression on rt2500pci

Stephen Boyd (1):
      staging/mt29f_spinand: Terminate of match table

Steve French (1):
      [CIFS] fix mount failure with broken pathnames when smb3 mount with mapchars option

Suravee Suthikulpanit (1):
      arm64/dma: Removing ARCH_HAS_DMA_GET_REQUIRED_MASK macro

Sven Wegener (1):
      ipv6: Fix regression caused by efe4208 in udp_v6_mcast_next()

Takashi Iwai (2):
      [media] ivtv: Fix Oops when no firmware is loaded
      ALSA: usb-audio: Fix races at disconnection and PCM closing

Tejun Heo (1):
      blkcg: fix use-after-free in __blkg_release_rcu() by making blkcg_gq refcnt an atomic_t

Tetsuo Handa (1):
      kthread: fix return value of kthread_create() upon SIGKILL.

Thomas Gleixner (4):
      genirq: Sanitize spurious interrupt detection of threaded irqs
      rtmutex: Handle deadlock detection smarter
      rtmutex: Detect changes in the pi lock chain
      rtmutex: Plug slow unlock race

Thomas Jarosch (1):
      PCI: Add new ID for Intel GPU "spurious interrupt" quirk

Thomas Petazzoni (1):
      mtd: pxa3xx_nand: make the driver work on big-endian systems

Todd Fujinaka (1):
      igb: fix stats for i210 rx_fifo_errors

Tomas Winkler (3):
      mei: me: fix hw ready reset flow
      mei: me: drop harmful wait optimization
      mei: me: read H_CSR after asserting reset

Tony Luck (2):
      mm/memory-failure.c-failure: send right signal code to correct thread
      mm/memory-failure.c: don't let collect_procs() skip over processes for MF_ACTION_REQUIRED

Trond Myklebust (2):
      NFS: Don't declare inode uptodate unless all attributes were checked
      SUNRPC: Fix a module reference leak in svc_handle_xprt

Victor Kamensky (1):
      arm64: ptrace: fix empty registers set in prstatus of aarch32 process core

Ville Syrjälä (1):
      drm/i915: Avoid div-by-zero when pixel_multiplier is zero

Viresh Kumar (1):
      watchdog: sp805: Set watchdog_device->timeout from ->set_timeout()

Wang, Xiaoming (1):
      ALSA: compress: Cancel the optimization of compiler and fix the size of struct for all platform.

Will Deacon (2):
      arm64: ptrace: change fs when passing kernel pointer to regset code
      arm64: uid16: fix __kernel_old_{gid,uid}_t definitions

Yann Droneaud (3):
      IB/mlx5: add missing padding at end of struct mlx5_ib_create_cq
      IB/mlx5: add missing padding at end of struct mlx5_ib_create_srq
      RDMA/cxgb4: Add missing padding at end of struct c4iw_create_cq_resp

gundberg (1):
      watchdog: kempld-wdt: Use the correct value when configuring the prescaler with the watchdog

hujianyang (2):
      UBIFS: fix an mmap and fsync race condition
      UBIFS: Remove incorrect assertion in shrink_tnc()

pekon gupta (1):
      mtd: nand: omap: fix BCHx ecc.correct to return detected bit-flips in erased-page

[PATCH 3.13 001/198] btrfs: fix defrag 32-bit integer overflow

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Justin Maggard <jmaggard10@gmail.com>

commit c41570c9d29764f797fa35490d72b7395a0105c3 upstream.

When defragging a very large file, the cluster variable can wrap its 32-bit
signed int type and become negative, which eventually gets passed to
btrfs_force_ra() as a very large unsigned long value.  On 32-bit platforms,
this eventually results in an Oops from the SLAB allocator.

Change the cluster and max_cluster signed int variables to unsigned long to
match the readahead functions.  This also allows the min() comparison in
btrfs_defrag_file() to work as intended.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
Cc: Joseph Salisbury <joseph.salisbury@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/btrfs/ioctl.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 9f831bb..043d6cd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1011,7 +1011,7 @@ out:
 static int cluster_pages_for_defrag(struct inode *inode,
 				    struct page **pages,
 				    unsigned long start_index,
-				    int num_pages)
+				    unsigned long num_pages)
 {
 	unsigned long file_end;
 	u64 isize = i_size_read(inode);
@@ -1169,8 +1169,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	int defrag_count = 0;
 	int compress_type = BTRFS_COMPRESS_ZLIB;
 	int extent_thresh = range->extent_thresh;
-	int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
-	int cluster = max_cluster;
+	unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+	unsigned long cluster = max_cluster;
 	u64 new_align = ~((u64)128 * 1024 - 1);
 	struct page **pages = NULL;
 
-- 
1.9.1

[PATCH 3.13 002/198] ALSA: usb-audio: Prevent printk ratelimiting from spamming kernel log while DEBUG not defined

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sander Eikelenboom <linux@eikelenboom.it>

commit b7a7723513dc89f83d6df13206df55d4dc26e825 upstream.

BugLink: http://bugs.launchpad.net/bugs/1319457

This (widely used) construction:

if(printk_ratelimit())
	dev_dbg()

Causes the ratelimiting to spam the kernel log with the "callbacks suppressed"
message below, even while the dev_dbg it is supposed to rate limit wouldn't
print anything because DEBUG is not defined for this device.

[  533.803964] retire_playback_urb: 852 callbacks suppressed
[  538.807930] retire_playback_urb: 852 callbacks suppressed
[  543.811897] retire_playback_urb: 852 callbacks suppressed
[  548.815745] retire_playback_urb: 852 callbacks suppressed
[  553.819826] retire_playback_urb: 852 callbacks suppressed

So use dev_dbg_ratelimited() instead of this construction.

Signed-off-by: Sander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
(backported from commit b7a7723513dc89f83d6df13206df55d4dc26e825)
Signed-off-by: Joseph Salisbury <joseph.salisbury@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/usb/pcm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index ca3256d..ede4b92 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1488,7 +1488,8 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 	 * on two reads of a counter updated every ms.
 	 */
 	if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
-		snd_printk(KERN_DEBUG "delay: estimated %d, actual %d\n",
+		dev_dbg_ratelimited(&subs->dev->dev,
+			"delay: estimated %d, actual %d\n",
 			est_delay, subs->last_delay);
 
 	if (!subs->running) {
-- 
1.9.1

[PATCH 3.13 003/198] ipv6: Fix regression caused by efe4208 in udp_v6_mcast_next()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sven Wegener <sven.wegener@stealer.net>

commit 3bfdc59a6c24608ed23e903f670aaf5f58c7a6f3 upstream.

Commit efe4208 ("ipv6: make lookups simpler and faster") introduced a
regression in udp_v6_mcast_next(), resulting in multicast packets not
reaching the destination sockets under certain conditions.

The packet's IPv6 addresses are wrongly compared to the IPv6 addresses
from the function's socket argument, which indicates the starting point
for looping, instead of the loop variable. If the addresses from the
first socket do not match the packet's addresses, no socket in the list
will match.

Signed-off-by: Sven Wegener <sven.wegener@stealer.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Tim Gardner <tim.gardner@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/ipv6/udp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 089c741..6028bc74 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -711,15 +711,15 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				if (inet->inet_dport != rmt_port)
 					continue;
 			}
-			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
-			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
+			if (!ipv6_addr_any(&s->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&s->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&s->sk_v6_rcv_saddr)) {
+				if (!ipv6_addr_equal(&s->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
 			if (!inet6_mc_check(s, loc_addr, rmt_addr))
-- 
1.9.1

[PATCH 3.13 004/198] Bluetooth: Fix redundant encryption request for reauthentication

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit 09da1f3463eb81d59685df723b1c5950b7570340 upstream.

When we're performing reauthentication (in order to elevate the
security level from an unauthenticated key to an authenticated one) we
do not need to issue any encryption command once authentication
completes. Since the trigger for the encryption HCI command is the
ENCRYPT_PEND flag this flag should not be set in this scenario.
Instead, the REAUTH_PEND flag takes care of all necessary steps for
reauthentication.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/hci_conn.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ba5366c..9a6bc9d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -752,14 +752,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
 		struct hci_cp_auth_requested cp;
 
-		/* encrypt must be pending if auth is also pending */
-		set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
 		cp.handle = cpu_to_le16(conn->handle);
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
+
+		/* If we're already encrypted set the REAUTH_PEND flag,
+		 * otherwise set the ENCRYPT_PEND.
+		 */
 		if (conn->key_type != 0xff)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+		else
+			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
 	return 0;
-- 
1.9.1

[PATCH 3.13 005/198] Bluetooth: Fix check for connection encryption

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit e694788d73efe139b24f78b036deb97fe57fa8cb upstream.

The conn->link_key variable tracks the type of link key in use. It is
set whenever we respond to a link key request as well as when we get a
link key notification event.

These two events do not however always guarantee that encryption is
enabled: getting a link key request and responding to it may only mean
that the remote side has requested authentication but not encryption. On
the other hand, the encrypt change event is a certain guarantee that
encryption is enabled. The real encryption state is already tracked in
the conn->link_mode variable through the HCI_LM_ENCRYPT bit.

This patch fixes a check for encryption in the hci_conn_auth function to
use the proper conn->link_mode value and thereby eliminates the chance
of a false positive result.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/hci_conn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 9a6bc9d..1c6e950 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -759,7 +759,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 		/* If we're already encrypted set the REAUTH_PEND flag,
 		 * otherwise set the ENCRYPT_PEND.
 		 */
-		if (conn->key_type != 0xff)
+		if (conn->link_mode & HCI_LM_ENCRYPT)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
 		else
 			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-- 
1.9.1

[PATCH 3.13 006/198] igb: fix stats for i210 rx_fifo_errors

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Todd Fujinaka <todd.fujinaka@intel.com>

commit e66c083aab32842f225bae2a2c30744bf96abaec upstream.

RQDPC on i210/i211 is R/W not ReadClear. Clear after reading.

Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Tim Gardner <tim.gardner@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 025e5f4..0f42ce8 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4909,8 +4909,10 @@ void igb_update_stats(struct igb_adapter *adapter,
 
 	rcu_read_lock();
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		u32 rqdpc = rd32(E1000_RQDPC(i));
 		struct igb_ring *ring = adapter->rx_ring[i];
+		u32 rqdpc = rd32(E1000_RQDPC(i));
+		if (hw->mac.type >= e1000_i210)
+			wr32(E1000_RQDPC(i), 0);
 
 		if (rqdpc) {
 			ring->rx_stats.drops += rqdpc;
-- 
1.9.1

[PATCH 3.13 007/198] netfilter: nf_nat: fix oops on netns removal

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Florian Westphal <fw@strlen.de>

commit 945b2b2d259d1a4364a2799e80e8ff32f8c6ee6f upstream.

Quoting Samu Kallio:

 Basically what's happening is, during netns cleanup,
 nf_nat_net_exit gets called before ipv4_net_exit. As I understand
 it, nf_nat_net_exit is supposed to kill any conntrack entries which
 have NAT context (through nf_ct_iterate_cleanup), but for some
 reason this doesn't happen (perhaps something else is still holding
 refs to those entries?).

 When ipv4_net_exit is called, conntrack entries (including those
 with NAT context) are cleaned up, but the
 nat_bysource hashtable is long gone - freed in nf_nat_net_exit. The
 bug happens when attempting to free a conntrack entry whose NAT hash
 'prev' field points to a slot in the freed hash table (head for that
 bin).

We ignore conntracks with null nat bindings.  But this is wrong,
as these are in bysource hash table as well.

Restore nat-cleaning for the netns-is-being-removed case.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=65191

Fixes: c2d421e1718 ('netfilter: nf_nat: fix race when unloading protocol modules')
Reported-by: Samu Kallio <samu.kallio@aberdeencloud.com>
Debugged-by: Samu Kallio <samu.kallio@aberdeencloud.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Tested-by: Samu Kallio <samu.kallio@aberdeencloud.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Chris J Arges <chris.j.arges@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/netfilter/nf_nat_core.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 63a8154..14f5968 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -511,6 +511,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -773,7 +806,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
-- 
1.9.1

[PATCH 3.13 008/198] introduce for_each_thread() to replace the buggy while_each_thread()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Oleg Nesterov <oleg@redhat.com>

commit 0c740d0afc3bff0a097ad03a1c8df92757516f5c upstream.

while_each_thread() and next_thread() should die, almost every lockless
usage is wrong.

1. Unless g == current, the lockless while_each_thread() is not safe.

   while_each_thread(g, t) can loop forever if g exits, next_thread()
   can't reach the unhashed thread in this case. Note that this can
   happen even if g is the group leader, it can exec.

2. Even if while_each_thread() itself was correct, people often use
   it wrongly.

   It was never safe to just take rcu_read_lock() and loop unless
   you verify that pid_alive(g) == T, even the first next_thread()
   can point to the already freed/reused memory.

This patch adds signal_struct->thread_head and task->thread_node to
create the normal rcu-safe list with the stable head.  The new
for_each_thread(g, t) helper is always safe under rcu_read_lock() as
long as this task_struct can't go away.

Note: of course it is ugly to have both task_struct->thread_node and the
old task_struct->thread_group, we will kill it later, after we change
the users of while_each_thread() to use for_each_thread().

Perhaps we can kill it even before we convert all users, we can
reimplement next_thread(t) using the new thread_head/thread_node.  But
we can't do this right now because this will lead to subtle behavioural
changes.  For example, do/while_each_thread() always sees at least one
task, while for_each_thread() can do nothing if the whole thread group
has died.  Or thread_group_empty(), currently its semantics is not clear
unless thread_group_leader(p) and we need to audit the callers before we
can change it.

So this patch adds the new interface which has to coexist with the old
one for some time, hopefully the next changes will be more or less
straightforward and the old one will go away soon.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Sergey Dyasly <dserrg@gmail.com>
Tested-by: Sergey Dyasly <dserrg@gmail.com>
Reviewed-by: Sameer Nanda <snanda@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mandeep Singh Baines <msb@chromium.org>
Cc: "Ma, Xindong" <xindong.ma@intel.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: "Tu, Xiaobing" <xiaobing.tu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ kamal: 3.13-stable for backport convenience ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/linux/init_task.h |  2 ++
 include/linux/sched.h     | 12 ++++++++++++
 kernel/exit.c             |  1 +
 kernel/fork.c             |  7 +++++++
 4 files changed, 22 insertions(+)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b0ed422..668aae0 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,6 +40,7 @@ extern struct fs_struct init_fs;
 
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\
@@ -213,6 +214,7 @@ extern struct task_group root_task_group;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),	\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 116e301..c06daac 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -485,6 +485,7 @@ struct signal_struct {
 	atomic_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 
@@ -1160,6 +1161,7 @@ struct task_struct {
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
+	struct list_head thread_node;
 
 	struct completion *vfork_done;		/* for vfork() */
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
@@ -2241,6 +2243,16 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
 static inline int get_nr_threads(struct task_struct *tsk)
 {
 	return tsk->signal->nr_threads;
diff --git a/kernel/exit.c b/kernel/exit.c
index dcde2c4..81b3d67 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		__this_cpu_dec(process_counts);
 	}
 	list_del_rcu(&p->thread_group);
+	list_del_rcu(&p->thread_node);
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index dfa736c..f330664 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1035,6 +1035,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
+
+	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
@@ -1472,6 +1477,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			atomic_inc(&current->signal->sigcnt);
 			list_add_tail_rcu(&p->thread_group,
 					  &p->group_leader->thread_group);
+			list_add_tail_rcu(&p->thread_node,
+					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;
-- 
1.9.1

[PATCH 3.13 009/198] NFS: Don't declare inode uptodate unless all attributes were checked

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <trond.myklebust@primarydata.com>

commit 43b6535e717d2f656f71d9bd16022136b781c934 upstream.

Fix a bug, whereby nfs_update_inode() was declaring the inode to be
up to date despite not having checked all the attributes.
The bug occurs because the temporary variable in which we cache
the validity information is 'sanitised' before reapplying to
nfsi->cache_validity.

Reported-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/nfs/inode.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5d94c02..25063e1 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1503,18 +1503,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_version = fattr->change_attr;
 		}
 	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
-		invalid |= save_cache_validity;
+		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	} else if (server->caps & NFS_CAP_MTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	} else if (server->caps & NFS_CAP_CTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
@@ -1537,7 +1539,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)new_isize);
 		}
 	} else
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
 
@@ -1545,7 +1548,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
 	else if (server->caps & NFS_CAP_ATIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATIME
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1556,7 +1560,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 		}
 	} else if (server->caps & NFS_CAP_MODE)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1567,7 +1572,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_uid = fattr->uid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1578,7 +1584,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_gid = fattr->gid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER_GROUP)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1591,7 +1598,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		}
 	} else if (server->caps & NFS_CAP_NLINK)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
-- 
1.9.1

[PATCH 3.13 010/198] usb: dwc3: gadget: clear stall when disabling endpoint

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Felipe Balbi <balbi@ti.com>

commit 687ef9817df7ed960d14575b9033dde3d04631fe upstream.

so it seems like DWC3 IP doesn't clear stalls
automatically when we disable an endpoint, because
of that, we _must_ make sure stalls are cleared
before clearing the proper bit in DALEPENA register.

Reported-by: Johannes Stezenbach <js@sig21.net>
Signed-off-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/usb/dwc3/gadget.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 02e44fc..c37da0c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -586,6 +586,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 
 	dwc3_remove_requests(dwc, dep);
 
+	/* make sure HW endpoint isn't stalled */
+	if (dep->flags & DWC3_EP_STALL)
+		__dwc3_gadget_ep_set_halt(dep, 0);
+
 	reg = dwc3_readl(dwc->regs, DWC3_DALEPENA);
 	reg &= ~DWC3_DALEPENA_EP(dep->number);
 	dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
-- 
1.9.1

[PATCH 3.13 011/198] ACPICA: utstring: Check array index bound before use.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Binderman <dcb314@hotmail.com>

commit 5d42b0fa25df7ef2f575107597c1aaebe2407d10 upstream.

ACPICA BZ 1077. David Binderman.

References: https://bugs.acpica.org/show_bug.cgi?id=1077
Signed-off-by: David Binderman <dcb314@hotmail.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/acpi/acpica/utstring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 45c0eb2..cd2047a 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -353,7 +353,7 @@ void acpi_ut_print_string(char *string, u16 max_length)
 	}
 
 	acpi_os_printf("\"");
-	for (i = 0; string[i] && (i < max_length); i++) {
+	for (i = 0; (i < max_length) && string[i]; i++) {
 
 		/* Escape sequences */
 
-- 
1.9.1

[PATCH 3.13 012/198] mtip32xx: Increase timeout for STANDBY IMMEDIATE command

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Asai Thambi S P <asamymuthupa@micron.com>

commit 670a641420a3d9586eebe7429dfeec4e7ed447aa upstream.

Increased timeout for STANDBY IMMEDIATE command to 2 minutes.

Signed-off-by: Selvan Mani <smani@micron.com>
Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/mtip32xx/mtip32xx.c | 66 +++++++++++++++++++++------------------
 1 file changed, 35 insertions(+), 31 deletions(-)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index b130353..c03caae 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -1507,6 +1507,37 @@ static inline void ata_swap_string(u16 *buf, unsigned int len)
 		be16_to_cpus(&buf[i]);
 }
 
+static void mtip_set_timeout(struct driver_data *dd,
+					struct host_to_dev_fis *fis,
+					unsigned int *timeout, u8 erasemode)
+{
+	switch (fis->command) {
+	case ATA_CMD_DOWNLOAD_MICRO:
+		*timeout = 120000; /* 2 minutes */
+		break;
+	case ATA_CMD_SEC_ERASE_UNIT:
+	case 0xFC:
+		if (erasemode)
+			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+		else
+			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
+		break;
+	case ATA_CMD_STANDBYNOW1:
+		*timeout = 120000;  /* 2 minutes */
+		break;
+	case 0xF7:
+	case 0xFA:
+		*timeout = 60000;  /* 60 seconds */
+		break;
+	case ATA_CMD_SMART:
+		*timeout = 15000;  /* 15 seconds */
+		break;
+	default:
+		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
+		break;
+	}
+}
+
 /*
  * Request the device identity information.
  *
@@ -1616,6 +1647,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	int rv;
 	struct host_to_dev_fis	fis;
 	unsigned long start;
+	unsigned int timeout;
 
 	/* Build the FIS. */
 	memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -1623,6 +1655,8 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	fis.opts	= 1 << 7;
 	fis.command	= ATA_CMD_STANDBYNOW1;
 
+	mtip_set_timeout(port->dd, &fis, &timeout, 0);
+
 	start = jiffies;
 	rv = mtip_exec_internal_command(port,
 					&fis,
@@ -1631,7 +1665,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 					0,
 					0,
 					GFP_ATOMIC,
-					15000);
+					timeout);
 	dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
 			jiffies_to_msecs(jiffies - start));
 	if (rv)
@@ -2170,36 +2204,6 @@ static unsigned int implicit_sector(unsigned char command,
 	}
 	return rv;
 }
-static void mtip_set_timeout(struct driver_data *dd,
-					struct host_to_dev_fis *fis,
-					unsigned int *timeout, u8 erasemode)
-{
-	switch (fis->command) {
-	case ATA_CMD_DOWNLOAD_MICRO:
-		*timeout = 120000; /* 2 minutes */
-		break;
-	case ATA_CMD_SEC_ERASE_UNIT:
-	case 0xFC:
-		if (erasemode)
-			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
-		else
-			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
-		break;
-	case ATA_CMD_STANDBYNOW1:
-		*timeout = 120000;  /* 2 minutes */
-		break;
-	case 0xF7:
-	case 0xFA:
-		*timeout = 60000;  /* 60 seconds */
-		break;
-	case ATA_CMD_SMART:
-		*timeout = 15000;  /* 15 seconds */
-		break;
-	default:
-		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
-		break;
-	}
-}
 
 /*
  * Executes a taskfile
-- 
1.9.1

[PATCH 3.13 013/198] mtip32xx: Remove dfs_parent after pci unregister

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Asai Thambi S P <asamymuthupa@micron.com>

commit af5ded8ccf21627f9614afc03b356712666ed225 upstream.

In module exit, dfs_parent and it's subtree were removed before
unregistering with pci. When debugfs entry for each device is attempted
to remove in pci_remove() context, they don't exist, as dfs_parent and
its children were already ripped apart.

Modified to first unregister with pci and then remove dfs_parent.

Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/mtip32xx/mtip32xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c03caae..919b0d9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4869,13 +4869,13 @@ static int __init mtip_init(void)
  */
 static void __exit mtip_exit(void)
 {
-	debugfs_remove_recursive(dfs_parent);
-
 	/* Release the allocated major block device number. */
 	unregister_blkdev(mtip_major, MTIP_DRV_NAME);
 
 	/* Unregister the PCI driver. */
 	pci_unregister_driver(&mtip_pci_driver);
+
+	debugfs_remove_recursive(dfs_parent);
 }
 
 MODULE_AUTHOR("Micron Technology, Inc");
-- 
1.9.1

[PATCH 3.13 014/198] mtip32xx: Fix ERO and NoSnoop values in PCIe upstream on AMD systems

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Asai Thambi S P <asamymuthupa@micron.com>

commit d1e714db8129a1d3670e449b87719c78e2c76f9f upstream.

A hardware quirk in P320h/P420m interfere with PCIe transactions on some
AMD chipsets, making P320h/P420m unusable. This workaround is to disable
ERO and NoSnoop bits in the parent and root complex for normal
functioning of these devices

NOTE: This workaround is specific to AMD chipset with a PCIe upstream
device with device id 0x5aXX

Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com>
Signed-off-by: Sam Bradshaw <sbradshaw@micron.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/mtip32xx/mtip32xx.c | 53 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 919b0d9..3ea2bde 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4415,6 +4415,57 @@ static DEFINE_HANDLER(5);
 static DEFINE_HANDLER(6);
 static DEFINE_HANDLER(7);
 
+static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev)
+{
+	int pos;
+	unsigned short pcie_dev_ctrl;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	if (pos) {
+		pci_read_config_word(pdev,
+			pos + PCI_EXP_DEVCTL,
+			&pcie_dev_ctrl);
+		if (pcie_dev_ctrl & (1 << 11) ||
+		    pcie_dev_ctrl & (1 << 4)) {
+			dev_info(&dd->pdev->dev,
+				"Disabling ERO/No-Snoop on bridge device %04x:%04x\n",
+					pdev->vendor, pdev->device);
+			pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN |
+						PCI_EXP_DEVCTL_RELAX_EN);
+			pci_write_config_word(pdev,
+				pos + PCI_EXP_DEVCTL,
+				pcie_dev_ctrl);
+		}
+	}
+}
+
+static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev)
+{
+	/*
+	 * This workaround is specific to AMD/ATI chipset with a PCI upstream
+	 * device with device id 0x5aXX
+	 */
+	if (pdev->bus && pdev->bus->self) {
+		if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI &&
+		    ((pdev->bus->self->device & 0xff00) == 0x5a00)) {
+			mtip_disable_link_opts(dd, pdev->bus->self);
+		} else {
+			/* Check further up the topology */
+			struct pci_dev *parent_dev = pdev->bus->self;
+			if (parent_dev->bus &&
+				parent_dev->bus->parent &&
+				parent_dev->bus->parent->self &&
+				parent_dev->bus->parent->self->vendor ==
+					 PCI_VENDOR_ID_ATI &&
+				(parent_dev->bus->parent->self->device &
+					0xff00) == 0x5a00) {
+				mtip_disable_link_opts(dd,
+					parent_dev->bus->parent->self);
+			}
+		}
+	}
+}
+
 /*
  * Called for each supported PCI device detected.
  *
@@ -4566,6 +4617,8 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 		goto block_initialize_err;
 	}
 
+	mtip_fix_ero_nosnoop(dd, pdev);
+
 	/* Initialize the block layer. */
 	rv = mtip_block_initialize(dd);
 	if (rv < 0) {
-- 
1.9.1

[PATCH 3.13 015/198] extcon: max77693: Fix two NULL pointer exceptions on missing pdata

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <k.kozlowski@samsung.com>

commit d5653f2b7304f05eeb45d84f123cf02f840b8537 upstream.

Fix NULL pointer exceptions when platform data is not supplied.

Trace of one exception:
Unable to handle kernel NULL pointer dereference at virtual address 00000008
pgd = c0004000
[00000008] *pgd=00000000
Internal error: Oops: 5 [#1] PREEMPT SMP ARM
Modules linked in:
CPU: 2 PID: 1 Comm: swapper/0 Not tainted 3.14.0-12045-gead5dd4687a6-dirty #1628
task: eea80000 ti: eea88000 task.ti: eea88000
PC is at max77693_muic_probe+0x27c/0x528
LR is at regmap_write+0x50/0x60
pc : [<c041d1c8>]    lr : [<c02eba60>]    psr: 20000113
sp : eea89e38  ip : 00000000  fp : c098a834
r10: ee1a5a10  r9 : 00000005  r8 : c098a83c
r7 : 0000000a  r6 : c098a774  r5 : 00000005  r4 : eeb006d0
r3 : c0697bd8  r2 : 00000000  r1 : 00000001  r0 : 00000000
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment kernel
Control: 10c5387d  Table: 4000404a  DAC: 00000015
Process swapper/0 (pid: 1, stack limit = 0xeea88240)
Stack: (0xeea89e38 to 0xeea8a000)
9e20:                                                       c08499fc eeb006d0
9e40: 00000000 00000000 c0915f98 00000001 00000000 ee1a5a10 c098a730 c09a88b8
9e60: 00000000 c098a730 c0915f98 00000000 00000000 c02d6aa0 c02d6a88 ee1a5a10
9e80: c0a712c8 c02d54e4 00001204 c0628b00 ee1a5a10 c098a730 ee1a5a44 00000000
9ea0: eea88000 c02d57b4 00000000 c098a730 c02d5728 c02d3a24 ee813e5c eeb9d534
9ec0: c098a730 ee22f700 c097c720 c02d4b14 c08174ec c098a730 00000006 c098a730
9ee0: 00000006 c092fd30 c09b8500 c02d5df8 00000000 c093cbb8 00000006 c0008928
9f00: 000000c3 ef7fc785 00000000 ef7fc794 00000000 c08af968 00000072 eea89f30
9f20: ef7fc85e c065f198 000000c3 c003e87c 00000003 00000000 c092fd3c 00000000
9f40: c08af618 c0826d58 00000006 00000006 c0956f58 c093cbb8 00000006 c092fd30
9f60: c09b8500 000000c3 c092fd3c c08e8510 00000000 c08e8bb0 00000006 00000006
9f80: c08e8510 c0c0c0c0 00000000 c0628fac 00000000 00000000 00000000 00000000
9fa0: 00000000 c0628fb4 00000000 c000f038 00000000 00000000 00000000 00000000
9fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
9fe0: 00000000 00000000 00000000 00000000 00000013 00000000 c0c0c0c0 c0c0c0c0
[<c041d1c8>] (max77693_muic_probe) from [<c02d6aa0>] (platform_drv_probe+0x18/0x48)
[<c02d6aa0>] (platform_drv_probe) from [<c02d54e4>] (driver_probe_device+0x140/0x384)
[<c02d54e4>] (driver_probe_device) from [<c02d57b4>] (__driver_attach+0x8c/0x90)
[<c02d57b4>] (__driver_attach) from [<c02d3a24>] (bus_for_each_dev+0x54/0x88)
[<c02d3a24>] (bus_for_each_dev) from [<c02d4b14>] (bus_add_driver+0xe8/0x204)
[<c02d4b14>] (bus_add_driver) from [<c02d5df8>] (driver_register+0x78/0xf4)
[<c02d5df8>] (driver_register) from [<c0008928>] (do_one_initcall+0xc4/0x174)
[<c0008928>] (do_one_initcall) from [<c08e8bb0>] (kernel_init_freeable+0xfc/0x1c8)
[<c08e8bb0>] (kernel_init_freeable) from [<c0628fb4>] (kernel_init+0x8/0xec)
[<c0628fb4>] (kernel_init) from [<c000f038>] (ret_from_fork+0x14/0x3c)
Code: caffffe7 e59d200c e3550001 b3a05001 (e5923008)
---[ end trace 85db969ce011bde7 ]---

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Fixes: 190d7cfc8632
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/extcon/extcon-max77693.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index da268fb..4657a91 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -1193,7 +1193,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 
 
 	/* Initialize MUIC register by using platform data or default data */
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		init_data = pdata->muic_data->init_data;
 		num_init_data = pdata->muic_data->num_init_data;
 	} else {
@@ -1226,7 +1226,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 				= init_data[i].data;
 	}
 
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		struct max77693_muic_platform_data *muic_pdata
 						   = pdata->muic_data;
 
-- 
1.9.1

[PATCH 3.13 016/198] extcon: max8997: Fix NULL pointer exception on missing pdata

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <k.kozlowski@samsung.com>

commit dfee4111febf3d9ef3a640b2cd6205c75f4e7e3d upstream.

Fix NULL pointer exception when platform data is not supplied. The
driver dereferenced pdata pointer where it could be NULL.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Fixes: 810d601f07c
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/extcon/extcon-max8997.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index 6a00464..5e1b88c 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -715,7 +715,7 @@ static int max8997_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
-	if (pdata->muic_pdata) {
+	if (pdata && pdata->muic_pdata) {
 		struct max8997_muic_platform_data *muic_pdata
 			= pdata->muic_pdata;
 
-- 
1.9.1

[PATCH 3.13 017/198] builddeb: use $OBJCOPY variable instead of objcopy

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Fathi Boudra <fathi.boudra@linaro.org>

commit 6b4a144a92ab81a1f45fb9b12aebaaaee0d08120 upstream.

In cross-build environment, we expect to use the cross-compiler objcopy
instead of the host objcopy.

It fixes following build failures:
objcopy --only-keep-debug lib/modules/3.14/kernel/net/ipv6/xfrm6_mode_tunnel.ko /srv/build/linux/debian/dbgtmp/usr/lib/debug/lib/modules/3.14/kernel/net/ipv6/xfrm6_mode_tunnel.ko
objcopy: Unable to recognise the format of the input file `lib/modules/3.14/kernel/net/ipv6/xfrm6_mode_tunnel.ko'

Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
Fixes: 810e843746b7 ('deb-pkg: split debug symbols in their own package')
Reviewed-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Michal Marek <mmarek@suse.cz>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 scripts/package/builddeb | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index c1bb9be..6d02fd5d 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -155,11 +155,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then
 			for module in $(find lib/modules/ -name *.ko); do
 				mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module)
 				# only keep debug symbols in the debug file
-				objcopy --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
+				$OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
 				# strip original module from debug symbols
-				objcopy --strip-debug $module
+				$OBJCOPY --strip-debug $module
 				# then add a link to those
-				objcopy --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
+				$OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
 			done
 		)
 	fi
-- 
1.9.1

[PATCH 3.13 018/198] bluetooth: hci_ldisc: fix deadlock condition

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Felipe Balbi <balbi@ti.com>

commit da64c27d3c93ee9f89956b9de86c4127eb244494 upstream.

LDISCs shouldn't call tty->ops->write() from within
->write_wakeup().

->write_wakeup() is called with port lock taken and
IRQs disabled, tty->ops->write() will try to acquire
the same port lock and we will deadlock.

Acked-by: Marcel Holtmann <marcel@holtmann.org>
Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
Reported-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
Tested-by: Andreas Bießmann <andreas@biessmann.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/bluetooth/hci_ldisc.c | 24 +++++++++++++++++++-----
 drivers/bluetooth/hci_uart.h  |  1 +
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 6e06f6f..77af52f 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -118,10 +118,6 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 
 int hci_uart_tx_wakeup(struct hci_uart *hu)
 {
-	struct tty_struct *tty = hu->tty;
-	struct hci_dev *hdev = hu->hdev;
-	struct sk_buff *skb;
-
 	if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) {
 		set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 		return 0;
@@ -129,6 +125,22 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 
 	BT_DBG("");
 
+	schedule_work(&hu->write_work);
+
+	return 0;
+}
+
+static void hci_uart_write_work(struct work_struct *work)
+{
+	struct hci_uart *hu = container_of(work, struct hci_uart, write_work);
+	struct tty_struct *tty = hu->tty;
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+
+	/* REVISIT: should we cope with bad skbs or ->write() returning
+	 * and error value ?
+	 */
+
 restart:
 	clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 
@@ -153,7 +165,6 @@ restart:
 		goto restart;
 
 	clear_bit(HCI_UART_SENDING, &hu->tx_state);
-	return 0;
 }
 
 static void hci_uart_init_work(struct work_struct *work)
@@ -281,6 +292,7 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	tty->receive_room = 65536;
 
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
+	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
 	spin_lock_init(&hu->rx_lock);
 
@@ -318,6 +330,8 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 	if (hdev)
 		hci_uart_close(hdev);
 
+	cancel_work_sync(&hu->write_work);
+
 	if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) {
 		if (hdev) {
 			if (test_bit(HCI_UART_REGISTERED, &hu->flags))
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fffa61f..12df101 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -68,6 +68,7 @@ struct hci_uart {
 	unsigned long		hdev_flags;
 
 	struct work_struct	init_ready;
+	struct work_struct	write_work;
 
 	struct hci_uart_proto	*proto;
 	void			*priv;
-- 
1.9.1

[PATCH 3.13 019/198] powerpc/pseries: Fix overwritten PE state

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Gavin Shan <gwshan@linux.vnet.ibm.com>

commit 54f112a3837d4e7532bbedbbbf27c0de277be510 upstream.

In pseries_eeh_get_state(), EEH_STATE_UNAVAILABLE is always
overwritten by EEH_STATE_NOT_SUPPORT because of the missed
"break" there. The patch fixes the issue.

Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/platforms/pseries/eeh_pseries.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ccb633e..c4e1d42 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -464,6 +464,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
 			} else {
 				result = EEH_STATE_NOT_SUPPORT;
 			}
+			break;
 		default:
 			result = EEH_STATE_NOT_SUPPORT;
 		}
-- 
1.9.1

[PATCH 3.13 020/198] PCI: Add new ID for Intel GPU "spurious interrupt" quirk

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Jarosch <thomas.jarosch@intra2net.com>

commit 7c82126a94e69bbbac586f0249e7ef11e681246c upstream.

After a CPU upgrade while keeping the same mainboard, we faced "spurious
interrupt" problems again.

It turned out that the new CPU also featured a new GPU with a different PCI
ID.

Add this PCI ID to the quirk table.  Probably all other Intel GPU PCI IDs
are affected, too, but I don't want to add them without a test system.

See f67fd55fa96f ("PCI: Add quirk for still enabled interrupts on Intel
Sandy Bridge GPUs") for some history.

[bhelgaas: add f67fd55fa96f reference, stable tag]
Signed-off-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/pci/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 3a02717..fbc066d 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2949,6 +2949,7 @@ static void disable_igfx_irq(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
 
 /*
  * PCI devices which are on Intel chips can skip the 10ms delay
-- 
1.9.1

[PATCH 3.13 021/198] x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "H. Peter Anvin" <hpa@linux.intel.com>

commit 3891a04aafd668686239349ea58f3314ea2af86b upstream.

The IRET instruction, when returning to a 16-bit segment, only
restores the bottom 16 bits of the user space stack pointer.  This
causes some 16-bit software to break, but it also leaks kernel state
to user space.  We have a software workaround for that ("espfix") for
the 32-bit kernel, but it relies on a nonzero stack segment base which
is not available in 64-bit mode.

In checkin:

    b3b42ac2cbae x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels

we "solved" this by forbidding 16-bit segments on 64-bit kernels, with
the logic that 16-bit support is crippled on 64-bit kernels anyway (no
V86 support), but it turns out that people are doing stuff like
running old Win16 binaries under Wine and expect it to work.

This works around this by creating percpu "ministacks", each of which
is mapped 2^16 times 64K apart.  When we detect that the return SS is
on the LDT, we copy the IRET frame to the ministack and use the
relevant alias to return to userspace.  The ministacks are mapped
readonly, so if IRET faults we promote #GP to #DF which is an IST
vector and thus has its own stack; we then do the fixup in the #DF
handler.

(Making #GP an IST exception would make the msr_safe functions unsafe
in NMI/MC context, and quite possibly have other effects.)

Special thanks to:

- Andy Lutomirski, for the suggestion of using very small stack slots
  and copy (as opposed to map) the IRET frame there, and for the
  suggestion to mark them readonly and let the fault promote to #DF.
- Konrad Wilk for paravirt fixup and testing.
- Borislav Petkov for testing help and useful comments.

Reported-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Lutomriski <amluto@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dirk Hohndel <dirk@hohndel.org>
Cc: Arjan van de Ven <arjan.van.de.ven@intel.com>
Cc: comex <comexk@gmail.com>
Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
[ kamal: backport to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 Documentation/x86/x86_64/mm.txt         |   2 +
 arch/x86/include/asm/pgtable_64_types.h |   2 +
 arch/x86/include/asm/setup.h            |   3 +
 arch/x86/kernel/Makefile                |   1 +
 arch/x86/kernel/entry_64.S              |  73 ++++++++++-
 arch/x86/kernel/espfix_64.c             | 208 ++++++++++++++++++++++++++++++++
 arch/x86/kernel/ldt.c                   |  11 --
 arch/x86/kernel/smpboot.c               |   7 ++
 arch/x86/mm/dump_pagetables.c           |  40 ++++--
 init/main.c                             |   4 +
 10 files changed, 325 insertions(+), 26 deletions(-)
 create mode 100644 arch/x86/kernel/espfix_64.c

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..bd43704 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d88344..b1609f2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 59bcf4e..edfaf6a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -62,6 +62,9 @@ extern void x86_ce4100_early_setup(void);
 static inline void x86_ce4100_early_setup(void) { }
 #endif
 
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
 #ifndef _SETUP
 
 /*
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e..92450ee 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_64)	+= espfix_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c36..bffaa98 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -1040,8 +1041,16 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 irq_return:
+	/*
+	 * Are we returning to a stack segment from the LDT?  Note: in
+	 * 64-bit mode SS:RSP on the exception stack is always valid.
+	 */
+	testb $4,(SS-RIP)(%rsp)
+	jnz irq_return_ldt
+
+irq_return_iret:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
+	_ASM_EXTABLE(irq_return_iret, bad_iret)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
@@ -1049,6 +1058,30 @@ ENTRY(native_iret)
 	_ASM_EXTABLE(native_iret, bad_iret)
 #endif
 
+irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
+	SWAPGS
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp irq_return_iret
+
 	.section .fixup,"ax"
 bad_iret:
 	/*
@@ -1110,9 +1143,41 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
+	/*
+	 * If IRET takes a fault on the espfix stack, then we
+	 * end up promoting it to a doublefault.  In that case,
+	 * modify the stack to make it look like we just entered
+	 * the #GP handler from user space, similar to bad_iret.
+	 */
+	ALIGN
+__do_double_fault:
+	XCPT_FRAME 1 RDI+8
+	movq RSP(%rdi),%rax		/* Trap on the espfix stack? */
+	sarq $PGDIR_SHIFT,%rax
+	cmpl $ESPFIX_PGD_ENTRY,%eax
+	jne do_double_fault		/* No, just deliver the fault */
+	cmpl $__KERNEL_CS,CS(%rdi)
+	jne do_double_fault
+	movq RIP(%rdi),%rax
+	cmpq $irq_return_iret,%rax
+#ifdef CONFIG_PARAVIRT
+	je 1f
+	cmpq $native_iret,%rax
+#endif
+	jne do_double_fault		/* This shouldn't happen... */
+1:
+	movq PER_CPU_VAR(kernel_stack),%rax
+	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
+	movq %rax,RSP(%rdi)
+	movq $0,(%rax)			/* Missing (lost) #GP error code */
+	movq $general_protection,RIP(%rdi)
+	retq
+	CFI_ENDPROC
+END(__do_double_fault)
+
 /*
  * End of kprobes section
  */
@@ -1314,7 +1379,7 @@ zeroentry overflow do_overflow
 zeroentry bounds do_bounds
 zeroentry invalid_op do_invalid_op
 zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault do_double_fault
+paranoiderrorentry double_fault __do_double_fault
 zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
 errorentry invalid_TSS do_invalid_TSS
 errorentry segment_not_present do_segment_not_present
@@ -1601,7 +1666,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 0000000..8a64da3
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms and conditions of the GNU General Public License,
+ *   version 2, as published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but WITHOUT
+ *   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *   more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer.  This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart.  When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace.  The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables.  The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE	(8*8UL)
+#define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES  DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+	__aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+	unsigned long page, slot;
+	unsigned long addr;
+
+	page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+	slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+	addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+	addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+	addr += ESPFIX_BASE_ADDR;
+	return addr;
+}
+
+#define PTE_STRIDE        (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT	  ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+	unsigned long rand;
+
+	/*
+	 * This is run before the entropy pools are initialized,
+	 * but this is hopefully better than nothing.
+	 */
+	if (!arch_get_random_long(&rand)) {
+		/* The constant is an arbitrary large prime */
+		rdtscll(rand);
+		rand *= 0xc345c6b72fd16123UL;
+	}
+
+	slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+	page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+		& (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+	pgd_t *pgd_p;
+	pteval_t ptemask;
+
+	ptemask = __supported_pte_mask;
+
+	/* Install the espfix pud into the kernel page directory */
+	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+	/* Randomize the locations */
+	init_espfix_random();
+
+	/* The rest is the same as for any other processor */
+	init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+	unsigned int cpu, page;
+	unsigned long addr;
+	pud_t pud, *pud_p;
+	pmd_t pmd, *pmd_p;
+	pte_t pte, *pte_p;
+	int n;
+	void *stack_page;
+	pteval_t ptemask;
+
+	/* We only have to do this once... */
+	if (likely(this_cpu_read(espfix_stack)))
+		return;		/* Already initialized */
+
+	cpu = smp_processor_id();
+	addr = espfix_base_addr(cpu);
+	page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+	/* Did another CPU already set this up? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (likely(stack_page))
+		goto done;
+
+	mutex_lock(&espfix_init_mutex);
+
+	/* Did we race on the lock? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (stack_page)
+		goto unlock_done;
+
+	ptemask = __supported_pte_mask;
+
+	pud_p = &espfix_pud_page[pud_index(addr)];
+	pud = *pud_p;
+	if (!pud_present(pud)) {
+		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+			set_pud(&pud_p[n], pud);
+	}
+
+	pmd_p = pmd_offset(&pud, addr);
+	pmd = *pmd_p;
+	if (!pmd_present(pmd)) {
+		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+			set_pmd(&pmd_p[n], pmd);
+	}
+
+	pte_p = pte_offset_kernel(&pmd, addr);
+	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
+	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+		set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+	/* Job is done for this CPU and any CPU which shares this page */
+	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+	mutex_unlock(&espfix_init_mutex);
+done:
+	this_cpu_write(espfix_stack, addr);
+	this_cpu_write(espfix_waddr, (unsigned long)stack_page
+		       + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index dcbbaa1..f95496a 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -231,17 +231,6 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
-	/*
-	 * On x86-64 we do not support 16-bit segments due to
-	 * IRET leaking the high bits of the kernel stack address.
-	 */
-#ifdef CONFIG_X86_64
-	if (!ldt_info.seg_32bit && !sysctl_ldt16) {
-		error = -EINVAL;
-		goto out_unlock;
-	}
-#endif
-
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85dc05a..b5c176a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -243,6 +243,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold vector_lock so there the set of online cpus
 	 * does not change while we are assigning vectors to cpus.  Holding
 	 * this lock ensures we don't half assign or remove an irq from a cpu.
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a..13f91a7 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned long current_address;
 	const struct addr_marker *marker;
+	unsigned long lines;
 };
 
 struct addr_marker {
 	unsigned long start_address;
 	const char *name;
+	unsigned long max_lines;
 };
 
 /* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+	ESPFIX_START_NR,
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,		"Low Kernel Mapping" },
 	{ VMALLOC_START,        "vmalloc() Area" },
 	{ VMEMMAP_START,        "Vmemmap" },
+	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 	{ __START_KERNEL_map,   "High Kernel Mapping" },
 	{ MODULES_VADDR,        "Modules" },
 	{ MODULES_END,          "End Modules" },
@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		      pgprot_t new_prot, int level)
 {
 	pgprotval_t prot, cur;
-	static const char units[] = "KMGTPE";
+	static const char units[] = "BKMGTPE";
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		st->current_prot = new_prot;
 		st->level = level;
 		st->marker = address_markers;
+		st->lines = 0;
 		seq_printf(m, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != cur || level != st->level ||
 		   st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%0*lx-0x%0*lx   ",
-			   width, st->start_address,
-			   width, st->current_address);
-
-		delta = (st->current_address - st->start_address) >> 10;
-		while (!(delta & 1023) && unit[1]) {
-			delta >>= 10;
-			unit++;
+		if (!st->marker->max_lines ||
+		    st->lines < st->marker->max_lines) {
+			seq_printf(m, "0x%0*lx-0x%0*lx   ",
+					   width, st->start_address,
+					   width, st->current_address);
+
+			delta = st->current_address - st->start_address;
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			seq_printf(m, "%9lu%c ", delta, *unit);
+			printk_prot(m, st->current_prot, st->level);
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
-		printk_prot(m, st->current_prot, st->level);
+		st->lines++;
 
 		/*
 		 * We print markers for special areas of address space,
@@ -206,7 +215,16 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		 * This helps in the interpretation.
 		 */
 		if (st->current_address >= st->marker[1].start_address) {
+			if (st->marker->max_lines &&
+			    st->lines > st->marker->max_lines) {
+				unsigned long nskip =
+					st->lines - st->marker->max_lines;
+				seq_printf(m, "... %lu entr%s skipped ... \n",
+						   nskip,
+						   nskip == 1 ? "y" : "ies");
+			}
 			st->marker++;
+			st->lines = 0;
 			seq_printf(m, "---[ %s ]---\n", st->marker->name);
 		}
 
diff --git a/init/main.c b/init/main.c
index febc511..da5d829 100644
--- a/init/main.c
+++ b/init/main.c
@@ -619,6 +619,10 @@ asmlinkage void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
+#ifdef CONFIG_X86_64
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
-- 
1.9.1

[PATCH 3.13 022/198] x86-32, espfix: Remove filter for espfix32 due to race

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "H. Peter Anvin" <hpa@linux.intel.com>

commit 246f2d2ee1d715e1077fc47d61c394569c8ee692 upstream.

It is not safe to use LAR to filter when to go down the espfix path,
because the LDT is per-process (rather than per-thread) and another
thread might change the descriptors behind our back.  Fortunately it
is always *safe* (if a bit slow) to go down the espfix path, and a
32-bit LDT stack segment is extremely rare.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/x86/kernel/entry_32.S | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f46..2780b8f 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -551,11 +551,6 @@ ENTRY(iret_exc)
 
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
-- 
1.9.1

[PATCH 3.13 023/198] genirq: Sanitize spurious interrupt detection of threaded irqs

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <tglx@linutronix.de>

commit 1e77d0a1ed7417d2a5a52a7b8d32aea1833faa6c upstream.

Till reported that the spurious interrupt detection of threaded
interrupts is broken in two ways:

- note_interrupt() is called for each action thread of a shared
  interrupt line. That's wrong as we are only interested whether none
  of the device drivers felt responsible for the interrupt, but by
  calling multiple times for a single interrupt line we account
  IRQ_NONE even if one of the drivers felt responsible.

- note_interrupt() when called from the thread handler is not
  serialized. That leaves the members of irq_desc which are used for
  the spurious detection unprotected.

To solve this we need to defer the spurious detection of a threaded
interrupt to the next hardware interrupt context where we have
implicit serialization.

If note_interrupt is called with action_ret == IRQ_WAKE_THREAD, we
check whether the previous interrupt requested a deferred check. If
not, we request a deferred check for the next hardware interrupt and
return.

If set, we check whether one of the interrupt threads signaled
success. Depending on this information we feed the result into the
spurious detector.

If one primary handler of a shared interrupt returns IRQ_HANDLED we
disable the deferred check of irq threads on the same line, as we have
found at least one device driver who cared.

Reported-by: Till Straumann <strauman@slac.stanford.edu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Austin Schuh <austin@peloton-tech.com>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: linux-can@vger.kernel.org
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1303071450130.22263@ionos
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/linux/irqdesc.h |   4 ++
 kernel/irq/manage.c     |   4 +-
 kernel/irq/spurious.c   | 106 ++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 108 insertions(+), 6 deletions(-)

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 56fb646..a7b4b61 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -27,6 +27,8 @@ struct irq_desc;
  * @irq_count:		stats field to detect stalled irqs
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
+ * @threads_handled:	stats field for deferred spurious detection of threaded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
  * @lock:		locking for SMP
  * @affinity_hint:	hint to user space for preferred irq affinity
  * @affinity_notify:	context for notification of affinity changes
@@ -52,6 +54,8 @@ struct irq_desc {
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
+	atomic_t		threads_handled;
+	int			threads_handled_last;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 #ifdef CONFIG_SMP
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 66a1b46..ebb8a9e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -856,8 +856,8 @@ static int irq_thread(void *data)
 		irq_thread_check_affinity(desc, action);
 
 		action_ret = handler_fn(desc, action);
-		if (!noirqdebug)
-			note_interrupt(action->irq, desc, action_ret);
+		if (action_ret == IRQ_HANDLED)
+			atomic_inc(&desc->threads_handled);
 
 		wake_threads_waitq(desc);
 	}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index a1d8cc6..e2514b0 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -270,6 +270,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 	return action && (action->flags & IRQF_IRQPOLL);
 }
 
+#define SPURIOUS_DEFERRED	0x80000000
+
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
@@ -277,15 +279,111 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 	    irq_settings_is_polled(desc))
 		return;
 
-	/* we get here again via the threaded handler */
-	if (action_ret == IRQ_WAKE_THREAD)
-		return;
-
 	if (bad_action_ret(action_ret)) {
 		report_bad_irq(irq, desc, action_ret);
 		return;
 	}
 
+	/*
+	 * We cannot call note_interrupt from the threaded handler
+	 * because we need to look at the compound of all handlers
+	 * (primary and threaded). Aside of that in the threaded
+	 * shared case we have no serialization against an incoming
+	 * hardware interrupt while we are dealing with a threaded
+	 * result.
+	 *
+	 * So in case a thread is woken, we just note the fact and
+	 * defer the analysis to the next hardware interrupt.
+	 *
+	 * The threaded handlers store whether they sucessfully
+	 * handled an interrupt and we check whether that number
+	 * changed versus the last invocation.
+	 *
+	 * We could handle all interrupts with the delayed by one
+	 * mechanism, but for the non forced threaded case we'd just
+	 * add pointless overhead to the straight hardirq interrupts
+	 * for the sake of a few lines less code.
+	 */
+	if (action_ret & IRQ_WAKE_THREAD) {
+		/*
+		 * There is a thread woken. Check whether one of the
+		 * shared primary handlers returned IRQ_HANDLED. If
+		 * not we defer the spurious detection to the next
+		 * interrupt.
+		 */
+		if (action_ret == IRQ_WAKE_THREAD) {
+			int handled;
+			/*
+			 * We use bit 31 of thread_handled_last to
+			 * denote the deferred spurious detection
+			 * active. No locking necessary as
+			 * thread_handled_last is only accessed here
+			 * and we have the guarantee that hard
+			 * interrupts are not reentrant.
+			 */
+			if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
+				desc->threads_handled_last |= SPURIOUS_DEFERRED;
+				return;
+			}
+			/*
+			 * Check whether one of the threaded handlers
+			 * returned IRQ_HANDLED since the last
+			 * interrupt happened.
+			 *
+			 * For simplicity we just set bit 31, as it is
+			 * set in threads_handled_last as well. So we
+			 * avoid extra masking. And we really do not
+			 * care about the high bits of the handled
+			 * count. We just care about the count being
+			 * different than the one we saw before.
+			 */
+			handled = atomic_read(&desc->threads_handled);
+			handled |= SPURIOUS_DEFERRED;
+			if (handled != desc->threads_handled_last) {
+				action_ret = IRQ_HANDLED;
+				/*
+				 * Note: We keep the SPURIOUS_DEFERRED
+				 * bit set. We are handling the
+				 * previous invocation right now.
+				 * Keep it for the current one, so the
+				 * next hardware interrupt will
+				 * account for it.
+				 */
+				desc->threads_handled_last = handled;
+			} else {
+				/*
+				 * None of the threaded handlers felt
+				 * responsible for the last interrupt
+				 *
+				 * We keep the SPURIOUS_DEFERRED bit
+				 * set in threads_handled_last as we
+				 * need to account for the current
+				 * interrupt as well.
+				 */
+				action_ret = IRQ_NONE;
+			}
+		} else {
+			/*
+			 * One of the primary handlers returned
+			 * IRQ_HANDLED. So we don't care about the
+			 * threaded handlers on the same line. Clear
+			 * the deferred detection bit.
+			 *
+			 * In theory we could/should check whether the
+			 * deferred bit is set and take the result of
+			 * the previous run into account here as
+			 * well. But it's really not worth the
+			 * trouble. If every other interrupt is
+			 * handled we never trigger the spurious
+			 * detector. And if this is just the one out
+			 * of 100k unhandled ones which is handled
+			 * then we merily delay the spurious detection
+			 * by one hard interrupt. Not a real problem.
+			 */
+			desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
+		}
+	}
+
 	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
-- 
1.9.1

[PATCH 3.13 024/198] Drivers: hv: balloon: Ensure pressure reports are posted regularly

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "K. Y. Srinivasan" <kys@microsoft.com>

commit ae339336dc950b9b05e7ccd3565dd3e8781c06d9 upstream.

The current code posts periodic memory pressure status from a dedicated thread.
Under some conditions, especially when we are releasing a lot of memory into
the guest, we may not send timely pressure reports back to the host. Fix this
issue by reporting pressure in all contexts that can be active in this driver.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/hv/hv_balloon.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 7e17a54..393fd8a 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/jiffies.h>
 #include <linux/mman.h>
 #include <linux/delay.h>
 #include <linux/init.h>
@@ -459,6 +460,11 @@ static bool do_hot_add;
  */
 static uint pressure_report_delay = 45;
 
+/*
+ * The last time we posted a pressure report to host.
+ */
+static unsigned long last_post_time;
+
 module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
 
@@ -542,6 +548,7 @@ struct hv_dynmem_device {
 
 static struct hv_dynmem_device dm_device;
 
+static void post_status(struct hv_dynmem_device *dm);
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
@@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 		 * have not been "onlined" within the allowed time.
 		 */
 		wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
-
+		post_status(&dm_device);
 	}
 
 	return;
@@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm)
 {
 	struct dm_status status;
 	struct sysinfo val;
+	unsigned long now = jiffies;
+	unsigned long last_post = last_post_time;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
 		return;
 	}
+
+	if (!time_after(now, (last_post_time + HZ)))
+		return;
+
 	si_meminfo(&val);
 	memset(&status, 0, sizeof(struct dm_status));
 	status.hdr.type = DM_STATUS_REPORT;
@@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm)
 	if (status.hdr.trans_id != atomic_read(&trans_id))
 		return;
 
+	/*
+	 * If the last post time that we sampled has changed,
+	 * we have raced, don't post the status.
+	 */
+	if (last_post != last_post_time)
+		return;
+
+	last_post_time = jiffies;
 	vmbus_sendpacket(dm->dev->channel, &status,
 				sizeof(struct dm_status),
 				(unsigned long)NULL,
@@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy)
 
 			if (ret == -EAGAIN)
 				msleep(20);
-
+			post_status(&dm_device);
 		} while (ret == -EAGAIN);
 
 		if (ret) {
@@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm,
 	struct dm_unballoon_response resp;
 	int i;
 
-	for (i = 0; i < range_count; i++)
+	for (i = 0; i < range_count; i++) {
 		free_balloon_pages(dm, &range_array[i]);
+		post_status(&dm_device);
+	}
 
 	if (req->more_pages == 1)
 		return;
-- 
1.9.1

[PATCH 3.13 025/198] x86, x32: Use compat shims for io_{setup,submit}

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mike Frysinger <vapier@gentoo.org>

commit 7fd44dacdd803c0bbf38bf478d51d280902bb0f1 upstream.

The io_setup takes a pointer to a context id of type aio_context_t.
This in turn is typed to a __kernel_ulong_t.  We could tweak the
exported headers to define this as a 64bit quantity for specific
ABIs, but since we already have a 32bit compat shim for the x86 ABI,
let's just re-use that logic.  The libaio package is also written to
expect this as a pointer type, so a compat shim would simplify that.

The io_submit func operates on an array of pointers to iocb structs.
Padding out the array to be 64bit aligned is a huge pain, so convert
it over to the existing compat shim too.

We don't convert io_getevents to the compat func as its only purpose
is to handle the timespec struct, and the x32 ABI uses 64bit times.

With this change, the libaio package can now pass its testsuite when
built for the x32 ABI.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Link: http://lkml.kernel.org/r/1399250595-5005-1-git-send-email-vapier@gentoo.org
Cc: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/x86/syscalls/syscall_64.tbl | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65d..63a8993 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -212,10 +212,10 @@
 203	common	sched_setaffinity	sys_sched_setaffinity
 204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	common	io_setup		sys_io_setup
+206	64	io_setup		sys_io_setup
 207	common	io_destroy		sys_io_destroy
 208	common	io_getevents		sys_io_getevents
-209	common	io_submit		sys_io_submit
+209	64	io_submit		sys_io_submit
 210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
 212	common	lookup_dcookie		sys_lookup_dcookie
@@ -356,3 +356,5 @@
 540	x32	process_vm_writev	compat_sys_process_vm_writev
 541	x32	setsockopt		compat_sys_setsockopt
 542	x32	getsockopt		compat_sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
-- 
1.9.1

[PATCH 3.13 026/198] iwlwifi: pcie: try to get ownership several times

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>

commit 501fd9895c1d7d8161ed56698ae2fccb10ef14f5 upstream.

Some races with the hardware can happen when we take
ownership of the device. Don't give up after the first try.

Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/wireless/iwlwifi/pcie/trans.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index f53ef83..f69aeb3 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -348,6 +348,7 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 {
 	int ret;
 	int t = 0;
+	int iter;
 
 	IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n");
 
@@ -356,18 +357,23 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 	if (ret >= 0)
 		return 0;
 
-	/* If HW is not ready, prepare the conditions to check again */
-	iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
-		    CSR_HW_IF_CONFIG_REG_PREPARE);
+	for (iter = 0; iter < 10; iter++) {
+		/* If HW is not ready, prepare the conditions to check again */
+		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+			    CSR_HW_IF_CONFIG_REG_PREPARE);
+
+		do {
+			ret = iwl_pcie_set_hw_ready(trans);
+			if (ret >= 0)
+				return 0;
 
-	do {
-		ret = iwl_pcie_set_hw_ready(trans);
-		if (ret >= 0)
-			return 0;
+			usleep_range(200, 1000);
+			t += 200;
+		} while (t < 150000);
+		msleep(25);
+	}
 
-		usleep_range(200, 1000);
-		t += 200;
-	} while (t < 150000);
+	IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter);
 
 	return ret;
 }
-- 
1.9.1

[PATCH 3.13 027/198] ext4: fix data integrity sync in ordered mode

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Namjae Jeon <namjae.jeon@samsung.com>

commit 1c8349a17137b93f0a83f276c764a6df1b9a116e upstream.

When we perform a data integrity sync we tag all the dirty pages with
PAGECACHE_TAG_TOWRITE at start of ext4_da_writepages.  Later we check
for this tag in write_cache_pages_da and creates a struct
mpage_da_data containing contiguously indexed pages tagged with this
tag and sync these pages with a call to mpage_da_map_and_submit.  This
process is done in while loop until all the PAGECACHE_TAG_TOWRITE
pages are synced. We also do journal start and stop in each iteration.
journal_stop could initiate journal commit which would call
ext4_writepage which in turn will call ext4_bio_write_page even for
delayed OR unwritten buffers. When ext4_bio_write_page is called for
such buffers, even though it does not sync them but it clears the
PAGECACHE_TAG_TOWRITE of the corresponding page and hence these pages
are also not synced by the currently running data integrity sync. We
will end up with dirty pages although sync is completed.

This could cause a potential data loss when the sync call is followed
by a truncate_pagecache call, which is exactly the case in
collapse_range.  (It will cause generic/127 failure in xfstests)

To avoid this issue, we can use set_page_writeback_keepwrite instead of
set_page_writeback, which doesn't clear TOWRITE tag.

Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com>
Signed-off-by: Ashish Sangwan <a.sangwan@samsung.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/ext4/ext4.h             |  3 ++-
 fs/ext4/inode.c            |  6 ++++--
 fs/ext4/page-io.c          |  8 ++++++--
 include/linux/page-flags.h | 12 +++++++++++-
 mm/page-writeback.c        | 11 ++++++-----
 5 files changed, 29 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3a603a8..62f024c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2764,7 +2764,8 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
 			       int len,
-			       struct writeback_control *wbc);
+			       struct writeback_control *wbc,
+			       bool keep_towrite);
 
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4fafd09..0fc189b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1841,6 +1841,7 @@ static int ext4_writepage(struct page *page,
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
 	struct ext4_io_submit io_submit;
+	bool keep_towrite = false;
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
@@ -1871,6 +1872,7 @@ static int ext4_writepage(struct page *page,
 			unlock_page(page);
 			return 0;
 		}
+		keep_towrite = true;
 	}
 
 	if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1887,7 +1889,7 @@ static int ext4_writepage(struct page *page,
 		unlock_page(page);
 		return -ENOMEM;
 	}
-	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+	ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
 	ext4_io_submit(&io_submit);
 	/* Drop io_end reference we got from init */
 	ext4_put_io_end_defer(io_submit.io_end);
@@ -1906,7 +1908,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	else
 		len = PAGE_CACHE_SIZE;
 	clear_page_dirty_for_io(page);
-	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
 	mpd->first_page++;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index bb621a5..d84cc95 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -401,7 +401,8 @@ submit_and_retry:
 int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct page *page,
 			int len,
-			struct writeback_control *wbc)
+			struct writeback_control *wbc,
+			bool keep_towrite)
 {
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, blocksize;
@@ -414,7 +415,10 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 
-	set_page_writeback(page);
+	if (keep_towrite)
+		set_page_writeback_keepwrite(page);
+	else
+		set_page_writeback(page);
 	ClearPageError(page);
 
 	/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 98ada58..198b7e5 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -317,13 +317,23 @@ CLEARPAGEFLAG(Uptodate, uptodate)
 extern void cancel_dirty_page(struct page *page, unsigned int account_size);
 
 int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
+int __test_set_page_writeback(struct page *page, bool keep_write);
+
+#define test_set_page_writeback(page)			\
+	__test_set_page_writeback(page, false)
+#define test_set_page_writeback_keepwrite(page)	\
+	__test_set_page_writeback(page, true)
 
 static inline void set_page_writeback(struct page *page)
 {
 	test_set_page_writeback(page);
 }
 
+static inline void set_page_writeback_keepwrite(struct page *page)
+{
+	test_set_page_writeback_keepwrite(page);
+}
+
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
 /*
  * System with lots of page flags available. This allows separate
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 8f6daa6..d013dba 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page)
 	return ret;
 }
 
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
@@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
-		radix_tree_tag_clear(&mapping->page_tree,
-				     page_index(page),
-				     PAGECACHE_TAG_TOWRITE);
+		if (!keep_write)
+			radix_tree_tag_clear(&mapping->page_tree,
+						page_index(page),
+						PAGECACHE_TAG_TOWRITE);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	} else {
 		ret = TestSetPageWriteback(page);
@@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page)
 	return ret;
 
 }
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
 
 /*
  * Return true if any of the pages in the mapping are marked with the
-- 
1.9.1

[PATCH 3.13 028/198] UBIFS: fix an mmap and fsync race condition

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: hujianyang <hujianyang@huawei.com>

commit 691a7c6f28ac90cccd0dbcf81348ea90b211bdd0 upstream.

There is a race condition in UBIFS:

Thread A (mmap)                        Thread B (fsync)

->__do_fault                           ->write_cache_pages
   -> ubifs_vm_page_mkwrite
       -> budget_space
       -> lock_page
       -> release/convert_page_budget
       -> SetPagePrivate
       -> TestSetPageDirty
       -> unlock_page
                                       -> lock_page
                                           -> TestClearPageDirty
                                           -> ubifs_writepage
                                               -> do_writepage
                                                   -> release_budget
                                                   -> ClearPagePrivate
                                                   -> unlock_page
   -> !(ret & VM_FAULT_LOCKED)
   -> lock_page
   -> set_page_dirty
       -> ubifs_set_page_dirty
           -> TestSetPageDirty (set page dirty without budgeting)
   -> unlock_page

This leads to situation where we have a diry page but no budget allocated for
this page, so further write-back may fail with -ENOSPC.

In this fix we return from page_mkwrite without performing unlock_page. We
return VM_FAULT_LOCKED instead. After doing this, the race above will not
happen.

Signed-off-by: hujianyang <hujianyang@huawei.com>
Tested-by: Laurence Withers <lwithers@guralp.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/ubifs/file.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 123c79b..b56eb62 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1525,8 +1525,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 	}
 
 	wait_for_stable_page(page);
-	unlock_page(page);
-	return 0;
+	return VM_FAULT_LOCKED;
 
 out_unlock:
 	unlock_page(page);
-- 
1.9.1

[PATCH 3.13 029/198] [media] rtl28xxu: add USB ID for Genius TVGo DVB-T03

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jan Vcelak <jv@fcelda.cz>

commit ac298ccdde4fe9b0a966e548a232ff4e8a6b8a31 upstream.

0458:707f KYE Systems Corp. (Mouse Systems) TVGo DVB-T03 [RTL2832]

The USB dongle uses RTL2832U demodulator and FC0012 tuner.

Signed-off-by: Jan Vcelak <jv@fcelda.cz>
Signed-off-by: Antti Palosaari <crope@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index ecca036..70dd3c8 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1427,6 +1427,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "Leadtek WinFast DTV Dongle mini", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_CPYTO_REDI_PC50A,
 		&rtl2832u_props, "Crypto ReDi PC 50 A", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KYE, 0x707f,
+		&rtl2832u_props, "Genius TVGo DVB-T03", NULL) },
 
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
 		&rtl2832u_props, "Astrometa DVB-T2", NULL) },
-- 
1.9.1

[PATCH 3.13 030/198] [media] rtl28xxu: add 1b80:d395 Peak DVB-T USB

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Brian Healy <healybrian@gmail.com>

commit 9ca24ae4083665bda38da45f4b5dc9bbaf936bc0 upstream.

Add USB ID for Peak DVB-T USB.

[crope@iki.fi: fix Brian email address and indentation]
Signed-off-by: Brian Healy <healybrian@gmail.com>
Signed-off-by: Antti Palosaari <crope@iki.fi>

Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 70dd3c8..1bb3030 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1429,6 +1429,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "Crypto ReDi PC 50 A", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_KYE, 0x707f,
 		&rtl2832u_props, "Genius TVGo DVB-T03", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, 0xd395,
+		&rtl2832u_props, "Peak DVB-T USB", NULL) },
 
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
 		&rtl2832u_props, "Astrometa DVB-T2", NULL) },
-- 
1.9.1

[PATCH 3.13 031/198] [media] rtl28xxu: add [1b80:d39d] Sveon STV20

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alessandro Miceli <angelofsky1980@gmail.com>

commit f27f5b0ee4967babfb8b03511f5e76b79d781014 upstream.

Added Sveon STV20 device based on Realtek RTL2832U and FC0012 tuner

Signed-off-by: Alessandro Miceli <angelofsky1980@gmail.com>
Signed-off-by: Antti Palosaari <crope@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/dvb-core/dvb-usb-ids.h    | 1 +
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 7e0f619..4cfb962 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -359,6 +359,7 @@
 #define USB_PID_FRIIO_WHITE				0x0001
 #define USB_PID_TVWAY_PLUS				0x0002
 #define USB_PID_SVEON_STV20				0xe39d
+#define USB_PID_SVEON_STV20_RTL2832U			0xd39d
 #define USB_PID_SVEON_STV22				0xe401
 #define USB_PID_SVEON_STV22_IT9137			0xe411
 #define USB_PID_AZUREWAVE_AZ6027			0x3275
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 1bb3030..42e91ea 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1431,6 +1431,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "Genius TVGo DVB-T03", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, 0xd395,
 		&rtl2832u_props, "Peak DVB-T USB", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV20_RTL2832U,
+		&rtl2832u_props, "Sveon STV20", NULL) },
 
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
 		&rtl2832u_props, "Astrometa DVB-T2", NULL) },
-- 
1.9.1

[PATCH 3.13 032/198] [media] rtl28xxu: add [1b80:d3af] Sveon STV27

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alessandro Miceli <angelofsky1980@gmail.com>

commit 74a86272f05c3dae40f2d7b17ff09a0608cf3304 upstream.

Added support for Sveon STV27 device (rtl2832u + FC0013 tuner)

Signed-off-by: Alessandro Miceli <angelofsky1980@gmail.com>
Signed-off-by: Antti Palosaari <crope@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/dvb-core/dvb-usb-ids.h    | 1 +
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 4cfb962..8bdfad4 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -373,4 +373,5 @@
 #define USB_PID_CTVDIGDUAL_V2				0xe410
 #define USB_PID_PCTV_2002E                              0x025c
 #define USB_PID_PCTV_2002E_SE                           0x025d
+#define USB_PID_SVEON_STV27                             0xd3af
 #endif
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 42e91ea..4043165 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1433,6 +1433,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "Peak DVB-T USB", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV20_RTL2832U,
 		&rtl2832u_props, "Sveon STV20", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV27,
+		&rtl2832u_props, "Sveon STV27", NULL) },
 
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
 		&rtl2832u_props, "Astrometa DVB-T2", NULL) },
-- 
1.9.1

[PATCH 3.13 033/198] ASoC: max98090: Fix reset at resume time

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Liam Girdwood <liam.r.girdwood@linux.intel.com>

commit 25b4ab430f8e166c9b63f4db28e7e812d5a59396 upstream.

Reset needs to wait 20ms before other codec IO is performed. This wait
was not being performed. Fix this by making sure the reset register is not
restored with the cache, but use the manual reset method in resume with
the wait.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/soc/codecs/max98090.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 8bddf3f..9ad8f01 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = {
 static bool max98090_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case M98090_REG_SOFTWARE_RESET:
 	case M98090_REG_DEVICE_STATUS:
 	case M98090_REG_JACK_STATUS:
 	case M98090_REG_REVISION_ID:
@@ -2360,6 +2361,8 @@ static int max98090_runtime_resume(struct device *dev)
 
 	regcache_cache_only(max98090->regmap, false);
 
+	max98090_reset(max98090);
+
 	regcache_sync(max98090->regmap);
 
 	return 0;
-- 
1.9.1

[PATCH 3.13 034/198] ACPI: Fix conflict between customized DSDT and DSDT local copy

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lv Zheng <lv.zheng@intel.com>

commit 73577d1df8e1f31f6b1a5eebcdbc334eb0330e47 upstream.

This patch fixes the following issue:
If DSDT is customized, no local DSDT copy is needed.

References: https://bugzilla.kernel.org/show_bug.cgi?id=69711
Signed-off-by: Enrico Etxe Arte <goitizena.generoa@gmail.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
[rjw: Subject]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/acpi/bus.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 296bec8..249d477 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -57,6 +57,12 @@ EXPORT_SYMBOL(acpi_root_dir);
 
 
 #ifdef CONFIG_X86
+#ifdef CONFIG_ACPI_CUSTOM_DSDT
+static inline int set_copy_dsdt(const struct dmi_system_id *id)
+{
+	return 0;
+}
+#else
 static int set_copy_dsdt(const struct dmi_system_id *id)
 {
 	printk(KERN_NOTICE "%s detected - "
@@ -64,6 +70,7 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	acpi_gbl_copy_dsdt_locally = 1;
 	return 0;
 }
+#endif
 
 static struct dmi_system_id dsdt_dmi_table[] __initdata = {
 	/*
-- 
1.9.1

[PATCH 3.13 035/198] hpsa: add new Smart Array PCI IDs (May 2014)

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Joe Handzik <joseph.t.handzik@hp.com>

commit 3b7a45e5ba85dc79c7714edd9eee9aaed730cd6b upstream.

Signed-off-by: Scott Teel <scott.teel@hp.com>
Signed-off-by: Joe Handzik <joseph.t.handzik@hp.com>
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/scsi/hpsa.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 20a5e6e..ad034ab 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -117,9 +117,15 @@ static const struct pci_device_id hpsa_pci_device_id[] = {
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C3},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C4},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C5},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C6},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C7},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C8},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C9},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CA},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CB},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CC},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CD},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CE},
 	{PCI_VENDOR_ID_HP,     PCI_ANY_ID,	PCI_ANY_ID, PCI_ANY_ID,
 		PCI_CLASS_STORAGE_RAID << 8, 0xffff << 8, 0},
 	{0,}
@@ -163,9 +169,15 @@ static struct board_type products[] = {
 	{0x21C3103C, "Smart Array", &SA5_access},
 	{0x21C4103C, "Smart Array", &SA5_access},
 	{0x21C5103C, "Smart Array", &SA5_access},
+	{0x21C6103C, "Smart Array", &SA5_access},
 	{0x21C7103C, "Smart Array", &SA5_access},
 	{0x21C8103C, "Smart Array", &SA5_access},
 	{0x21C9103C, "Smart Array", &SA5_access},
+	{0x21CA103C, "Smart Array", &SA5_access},
+	{0x21CB103C, "Smart Array", &SA5_access},
+	{0x21CC103C, "Smart Array", &SA5_access},
+	{0x21CD103C, "Smart Array", &SA5_access},
+	{0x21CE103C, "Smart Array", &SA5_access},
 	{0xFFFF103C, "Unknown Smart Array", &SA5_access},
 };
 
-- 
1.9.1

[PATCH 3.13 036/198] PM / OPP: fix incorrect OPP count handling in of_init_opp_table

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chander Kashyap <chander.kashyap@linaro.org>

commit 086abb58590a4df73e8a6ed71fd418826937cd46 upstream.

In of_init_opp_table function, if a failure to add an OPP is
detected, the count of OPPs, yet to be added is not updated.
Fix this by decrementing this count on failure as well.

Signed-off-by: Chander Kashyap <k.chander@samsung.com>
Signed-off-by: Inderpal Singh <inderpal.s@samsung.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/base/power/opp.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index fa41874..08d99ef 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -735,11 +735,9 @@ int of_init_opp_table(struct device *dev)
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (dev_pm_opp_add(dev, freq, volt)) {
+		if (dev_pm_opp_add(dev, freq, volt))
 			dev_warn(dev, "%s: Failed to add OPP %ld\n",
 				 __func__, freq);
-			continue;
-		}
 		nr -= 2;
 	}
 
-- 
1.9.1

[PATCH 3.13 037/198] Target/iser: Bail from accept_np if np_thread is trying to close

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg <sagig@mellanox.com>

commit e346ab343f4f58c12a96725c7b13df9cc2ad56f6 upstream.

In case np_thread state is in RESET/SHUTDOWN/EXIT states,
no point for isert to stall there as we may get a hang in
case no one will wake it up later.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/isert/ib_isert.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 8ed268d..9b5381c 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2701,9 +2701,14 @@ accept_wait:
 		return -ENODEV;
 
 	spin_lock_bh(&np->np_thread_lock);
-	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+	if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_debug("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+		pr_debug("np_thread_state %d for isert_accept_np\n",
+			 np->np_thread_state);
+		/**
+		 * No point in stalling here when np_thread
+		 * is in state RESET/SHUTDOWN/EXIT - bail
+		 **/
 		return -ENODEV;
 	}
 	spin_unlock_bh(&np->np_thread_lock);
-- 
1.9.1

[PATCH 3.13 038/198] Target/iser: Fix hangs in connection teardown

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg <sagig@mellanox.com>

commit 9d49f5e284e700576f3b65f1e28dea8539da6661 upstream.

In ungraceful teardowns isert close flows seem racy such that
isert_wait_conn hangs as RDMA_CM_EVENT_DISCONNECTED never
gets invoked (no one called rdma_disconnect).

Both graceful and ungraceful teardowns will have rx flush errors
(isert posts a batch once connection is established). Once all
flush errors are consumed we invoke isert_wait_conn and it will
be responsible for calling rdma_disconnect. This way it can be
sure that rdma_disconnect was called and it won't wait forever.

This patch also removes the logout_posted indicator. either the
logout completion was consumed and no problem decrementing the
post_send_buf_count, or it was consumed as a flush error. no point
of keeping it for isert_wait_conn as there is no danger that
isert_conn will be accidentally removed while it is running.

(Drop unnecessary sleep_on_conn_wait_comp check in
 isert_cq_rx_comp_err - nab)

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/isert/ib_isert.c | 31 ++++++++++---------------------
 drivers/infiniband/ulp/isert/ib_isert.h |  1 -
 2 files changed, 10 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 9b5381c..cbd87ff 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -684,14 +684,10 @@ isert_disconnect_work(struct work_struct *work)
 		isert_put_conn(isert_conn);
 		return;
 	}
-	if (!isert_conn->logout_posted) {
-		pr_debug("Calling rdma_disconnect for !logout_posted from"
-			 " isert_disconnect_work\n");
-		rdma_disconnect(isert_conn->conn_cm_id);
-		mutex_unlock(&isert_conn->conn_mutex);
-		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
-		goto wake_up;
-	}
+
+	/* Send DREQ/DREP towards our initiator */
+	rdma_disconnect(isert_conn->conn_cm_id);
+
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
@@ -1587,11 +1583,8 @@ isert_do_control_comp(struct work_struct *work)
 		break;
 	case ISTATE_SEND_LOGOUTRSP:
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
-		/*
-		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_wait_conn()
-		 */
-		isert_conn->logout_posted = true;
+
+		atomic_dec(&isert_conn->post_send_buf_count);
 		iscsit_logout_post_handler(cmd, cmd->conn);
 		break;
 	case ISTATE_SEND_TEXTRSP:
@@ -1763,6 +1756,8 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn)
 	isert_conn->state = ISER_CONN_DOWN;
 	mutex_unlock(&isert_conn->conn_mutex);
 
+	iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+
 	complete(&isert_conn->conn_wait_comp_err);
 }
 
@@ -2758,15 +2753,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	struct isert_conn *isert_conn = conn->context;
 
 	pr_debug("isert_wait_conn: Starting \n");
-	/*
-	 * Decrement post_send_buf_count for special case when called
-	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
-	 */
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->logout_posted)
-		atomic_dec(&isert_conn->post_send_buf_count);
 
-	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->conn_cm_id) {
 		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 68d9f35..abbc331 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -93,7 +93,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	bool			logout_posted;
 	int			post_recv_buf_count;
 	atomic_t		post_send_buf_count;
 	u32			responder_resources;
-- 
1.9.1

[PATCH 3.13 039/198] HID: core: fix validation of report id 0

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Kees Cook <keescook@chromium.org>

commit 1b15d2e5b8077670b1e6a33250a0d9577efff4a5 upstream.

Some drivers use the first HID report in the list instead of using an
index. In these cases, validation uses ID 0, which was supposed to mean
"first known report". This fixes the problem, which was causing at least
the lgff family of devices to stop working since hid_validate_values
was being called with ID 0, but the devices used single numbered IDs
for their reports:

0x05, 0x01,         /*  Usage Page (Desktop),                   */
0x09, 0x05,         /*  Usage (Gamepad),                        */
0xA1, 0x01,         /*  Collection (Application),               */
0xA1, 0x02,         /*      Collection (Logical),               */
0x85, 0x01,         /*          Report ID (1),                  */
...

Reported-by: Simon Wood <simon@mungewell.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/hid/hid-core.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 12f1a45..5b9e996 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -842,7 +842,17 @@ struct hid_report *hid_validate_values(struct hid_device *hid,
 	 * ->numbered being checked, which may not always be the case when
 	 * drivers go to access report values.
 	 */
-	report = hid->report_enum[type].report_id_hash[id];
+	if (id == 0) {
+		/*
+		 * Validating on id 0 means we should examine the first
+		 * report in the list.
+		 */
+		report = list_entry(
+				hid->report_enum[type].report_list.next,
+				struct hid_report, list);
+	} else {
+		report = hid->report_enum[type].report_id_hash[id];
+	}
 	if (!report) {
 		hid_err(hid, "missing %s %u\n", hid_report_names[type], id);
 		return NULL;
-- 
1.9.1

[PATCH 3.13 040/198] IB/srp: Fix a sporadic crash triggered by cable pulling

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Bart Van Assche <bvanassche@acm.org>

commit 024ca90151f5e4296d30f72c13ff9a075e23c9ec upstream.

Avoid that the loops that iterate over the request ring can encounter
a pointer to a SCSI command in req->scmnd that is no longer associated
with that request. If the function srp_unmap_data() is invoked twice
for a SCSI command that is not in flight then that would cause
ib_fmr_pool_unmap() to be invoked with an invalid pointer as argument,
resulting in a kernel oops.

Reported-by: Sagi Grimberg <sagig@mellanox.com>
Reference: http://thread.gmane.org/gmane.linux.drivers.rdma/19068/focus=19069
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index a886319..c74d8b6 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1575,6 +1575,12 @@ err_unmap:
 err_iu:
 	srp_put_tx_iu(target, iu, SRP_IU_CMD);
 
+	/*
+	 * Avoid that the loops that iterate over the request ring can
+	 * encounter a dangling SCSI command pointer.
+	 */
+	req->scmnd = NULL;
+
 	spin_lock_irqsave(&target->lock, flags);
 	list_add(&req->list, &target->free_reqs);
 
-- 
1.9.1

[PATCH 3.13 041/198] Target/iser: Improve cm events handling

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg <sagig@mellanox.com>

commit 88c4015fda6d014392f76d3b1688347950d7a12d upstream.

There are 4 RDMA_CM events that all basically mean that
the user should teardown the IB connection:
- DISCONNECTED
- ADDR_CHANGE
- DEVICE_REMOVAL
- TIMEWAIT_EXIT

Only in DISCONNECTED/ADDR_CHANGE it makes sense to
call rdma_disconnect (send DREQ/DREP to our initiator).
So we keep the same teardown handler for all of them
but only indicate calling rdma_disconnect for the relevant
events.

This patch also removes redundant debug prints for each single
event.

v2 changes:
 - Call isert_disconnected_handler() for DEVICE_REMOVAL (Or + Sag)

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/isert/ib_isert.c | 26 ++++++++++++++------------
 drivers/infiniband/ulp/isert/ib_isert.h |  1 +
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index cbd87ff..a281a7f 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -685,8 +685,10 @@ isert_disconnect_work(struct work_struct *work)
 		return;
 	}
 
-	/* Send DREQ/DREP towards our initiator */
-	rdma_disconnect(isert_conn->conn_cm_id);
+	if (isert_conn->disconnect) {
+		/* Send DREQ/DREP towards our initiator */
+		rdma_disconnect(isert_conn->conn_cm_id);
+	}
 
 	mutex_unlock(&isert_conn->conn_mutex);
 
@@ -696,10 +698,11 @@ wake_up:
 }
 
 static void
-isert_disconnected_handler(struct rdma_cm_id *cma_id)
+isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
 {
 	struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context;
 
+	isert_conn->disconnect = disconnect;
 	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
 	schedule_work(&isert_conn->conn_logout_work);
 }
@@ -708,29 +711,28 @@ static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
+	bool disconnect = false;
 
 	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
 		 event->event, event->status, cma_id->context, cma_id);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
-		pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n");
 		ret = isert_connect_request(cma_id, event);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
-		pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n");
 		isert_connected_handler(cma_id);
 		break;
-	case RDMA_CM_EVENT_DISCONNECTED:
-		pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n");
-		isert_disconnected_handler(cma_id);
-		break;
-	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
+	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
+	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
+		disconnect = true;
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
+		isert_disconnected_handler(cma_id, disconnect);
 		break;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	default:
-		pr_err("Unknown RDMA CMA event: %d\n", event->event);
+		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
 	}
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index abbc331..2b126e0 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -127,6 +127,7 @@ struct isert_conn {
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
+	bool                    disconnect;
 };
 
 #define ISERT_MAX_CQ 64
-- 
1.9.1

[PATCH 3.13 042/198] Target/iser: Wait for proper cleanup before unloading

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg <sagig@mellanox.com>

commit f5ebec9629cf78eeeea4b8258882a9f439ab2404 upstream.

disconnected_handler works are scheduled on system_wq.
When attempting to unload, first make sure all works
have cleaned up.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/isert/ib_isert.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index a281a7f..bde56da 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2832,6 +2832,7 @@ destroy_rx_wq:
 
 static void __exit isert_exit(void)
 {
+	flush_scheduled_work();
 	destroy_workqueue(isert_comp_wq);
 	destroy_workqueue(isert_rx_wq);
 	iscsit_unregister_transport(&iser_target_transport);
-- 
1.9.1

[PATCH 3.13 043/198] mtd: nand: omap: fix BCHx ecc.correct to return detected bit-flips in erased-page

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: pekon gupta <pekon@ti.com>

commit f306e8c3b667632952f1a4a74ffb910bbc06255f upstream.

fixes: commit 62116e5171e00f85a8d53f76e45b84423c89ff34
       mtd: nand: omap2: Support for hardware BCH error correction.

In omap_elm_correct_data(), if bitflip_count in an erased-page is within the
correctable limit (< ecc.strength), then it is not indicated back to the caller
ecc->read_page().

This mis-guides upper layers like MTD and UBIFS layer to assume erased-page as
perfectly clean and use it for writing even if actual bitflip_count was
dangerously high (bitflip_count > mtd->bitflip_threshold).

This patch fixes this above issue, by returning 'stats' to caller
ecc->read_page() under all scenarios.

Reported-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Pekon Gupta <pekon@ti.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/mtd/nand/omap2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 2365b5a..b594e61 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1451,7 +1451,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 
 	/* Check if any error reported */
 	if (!is_error_reported)
-		return 0;
+		return stat;
 
 	/* Decode BCH error using ELM module */
 	elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec);
-- 
1.9.1

[PATCH 3.13 044/198] mtd: eLBC NAND: fix subpage write support

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Pekon Gupta <pekon@ti.com>

commit f034d87def51f026b735d1e2877e9387011b2ba3 upstream.

As subpage write is enabled by default for all drivers, nand_write_subpage_hwecc
causes a crash if the driver did not register ecc->hwctl or ecc->calculate.
This behavior was introduced in
   commit 837a6ba4f3b6d23026674e6af6b6849a4634fff9
   "mtd: nand: subpage write support for hardware based ECC schemes".

This fixes a crash by emulating subpage write support by padding sub-page data
with 0xff on either sides to make it full page compatible.

Reported-by: Helmut Schaa <helmut.schaa@googlemail.com>
Tested-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: Pekon Gupta <pekon@ti.com>
Reviewed-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/mtd/nand/fsl_elbc_nand.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index c966fc7..6ce1fd2 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -724,6 +724,19 @@ static int fsl_elbc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return 0;
 }
 
+/* ECC will be calculated automatically, and errors will be detected in
+ * waitfunc.
+ */
+static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				uint32_t offset, uint32_t data_len,
+				const uint8_t *buf, int oob_required)
+{
+	fsl_elbc_write_buf(mtd, buf, mtd->writesize);
+	fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+	return 0;
+}
+
 static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 {
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
@@ -762,6 +775,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 
 	chip->ecc.read_page = fsl_elbc_read_page;
 	chip->ecc.write_page = fsl_elbc_write_page;
+	chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
 	/* If CS Base Register selects full hardware ECC then use it */
 	if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
-- 
1.9.1

[PATCH 3.13 045/198] reiserfs: call truncate_setsize under tailpack mutex

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jeff Mahoney <jeffm@suse.com>

commit 22e7478ddbcb670e33fab72d0bbe7c394c3a2c84 upstream.

Prior to commit 0e4f6a791b1e (Fix reiserfs_file_release()), reiserfs
truncates serialized on i_mutex. They mostly still do, with the exception
of reiserfs_file_release. That blocks out other writers via the tailpack
mutex and the inode openers counter adjusted in reiserfs_file_open.

However, NFS will call reiserfs_setattr without having called ->open, so
we end up with a race when nfs is calling ->setattr while another
process is releasing the file. Ultimately, it triggers the
BUG_ON(inode->i_size != new_file_size) check in maybe_indirect_to_direct.

The solution is to pull the lock into reiserfs_setattr to encompass the
truncate_setsize call as well.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/reiserfs/inode.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ad62bdb..1e4cf9d 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3220,8 +3220,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		error = inode_newsize_ok(inode, attr->ia_size);
 		if (!error) {
+			/*
+			 * Could race against reiserfs_file_release
+			 * if called from NFS, so take tailpack mutex.
+			 */
+			mutex_lock(&REISERFS_I(inode)->tailpack);
 			truncate_setsize(inode, attr->ia_size);
-			reiserfs_vfs_truncate_file(inode);
+			reiserfs_truncate_file(inode, 1);
+			mutex_unlock(&REISERFS_I(inode)->tailpack);
 		}
 	}
 
-- 
1.9.1

[PATCH 3.13 046/198] ARM: stacktrace: avoid listing stacktrace functions in stacktrace

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Russell King <rmk+kernel@arm.linux.org.uk>

commit 3683f44c42e991d313dc301504ee0fca1aeb8580 upstream.

While debugging the FEC ethernet driver using stacktrace, it was noticed
that the stacktraces always begin as follows:

 [<c00117b4>] save_stack_trace_tsk+0x0/0x98
 [<c0011870>] save_stack_trace+0x24/0x28
 ...

This is because the stack trace code includes the stack frames for itself.
This is incorrect behaviour, and also leads to "skip" doing the wrong
thing (which is the number of stack frames to avoid recording.)

Perversely, it does the right thing when passed a non-current thread.  Fix
this by ensuring that we have a known constant number of frames above the
main stack trace function, and always skip these.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm/kernel/stacktrace.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index af4e8c8..6582c4a 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d)
 	return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+	struct stack_trace *trace, unsigned int nosched)
 {
 	struct stack_trace_data data;
 	struct stackframe frame;
 
 	data.trace = trace;
 	data.skip = trace->skip;
+	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
 #ifdef CONFIG_SMP
@@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
-		data.no_sched_functions = 1;
 		frame.fp = thread_saved_fp(tsk);
 		frame.sp = thread_saved_sp(tsk);
 		frame.lr = 0;		/* recovered from the stack */
@@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	} else {
 		register unsigned long current_sp asm ("sp");
 
-		data.no_sched_functions = 0;
+		/* We don't want this function nor the caller */
+		data.skip += 2;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_sp;
 		frame.lr = (unsigned long)__builtin_return_address(0);
-		frame.pc = (unsigned long)save_stack_trace_tsk;
+		frame.pc = (unsigned long)__save_stack_trace;
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace, 1);
+}
+
 void save_stack_trace(struct stack_trace *trace)
 {
-	save_stack_trace_tsk(current, trace);
+	__save_stack_trace(current, trace, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
-- 
1.9.1

[PATCH 3.13 047/198] SUNRPC: Fix a module reference leak in svc_handle_xprt

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <trond.myklebust@primarydata.com>

commit c789102c20bbbdda6831a273e046715be9d6af79 upstream.

If the accept() call fails, we need to put the module reference.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/sunrpc/svc_xprt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640..b9aad47 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -730,6 +730,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt)
 			svc_add_new_temp_xprt(serv, newxpt);
+		else
+			module_put(xprt->xpt_class->xcl_owner);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
-- 
1.9.1

[PATCH 3.13 048/198] [media] uvcvideo: Fix clock param realtime setting

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Olivier Langlois <olivier@trillion01.com>

commit 3b35fc81e7ec552147a4fd843d0da0bbbe4ef253 upstream.

timestamps in v4l2 buffers returned to userspace are updated in
uvc_video_clock_update() which uses timestamps fetched from
uvc_video_clock_decode() by calling unconditionally ktime_get_ts().

Hence setting the module clock param to realtime has no effect before
this patch.

This has been tested with ffmpeg:

ffmpeg -y -f v4l2 -input_format yuyv422 -video_size 640x480 -framerate 30 -i /dev/video0 \
 -f alsa -acodec pcm_s16le -ar 16000 -ac 1 -i default \
 -c:v libx264 -preset ultrafast \
 -c:a libfdk_aac \
 out.mkv

and inspecting the v4l2 input starting timestamp.

Signed-off-by: Olivier Langlois <olivier@trillion01.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/usb/uvc/uvc_video.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index e32d6a5..2ef5b0f8 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -361,6 +361,14 @@ static int uvc_commit_video(struct uvc_streaming *stream,
  * Clocks and timestamps
  */
 
+static inline void uvc_video_get_ts(struct timespec *ts)
+{
+	if (uvc_clock_param == CLOCK_MONOTONIC)
+		ktime_get_ts(ts);
+	else
+		ktime_get_real_ts(ts);
+}
+
 static void
 uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 		       const __u8 *data, int len)
@@ -420,7 +428,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 	stream->clock.last_sof = dev_sof;
 
 	host_sof = usb_get_current_frame_number(stream->dev->udev);
-	ktime_get_ts(&ts);
+	uvc_video_get_ts(&ts);
 
 	/* The UVC specification allows device implementations that can't obtain
 	 * the USB frame number to keep their own frame counters as long as they
@@ -1011,10 +1019,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 			return -ENODATA;
 		}
 
-		if (uvc_clock_param == CLOCK_MONOTONIC)
-			ktime_get_ts(&ts);
-		else
-			ktime_get_real_ts(&ts);
+		uvc_video_get_ts(&ts);
 
 		buf->buf.v4l2_buf.sequence = stream->sequence;
 		buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
-- 
1.9.1

[PATCH 3.13 049/198] [media] ivtv: Fix Oops when no firmware is loaded

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <tiwai@suse.de>

commit deb29e90221a6d4417aa67be971613c353180331 upstream.

When ivtv PCM device is accessed at the state where no firmware is
loaded, it oopses like:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000050
  IP: [<ffffffffa049a881>] try_mailbox.isra.0+0x11/0x50 [ivtv]
  Call Trace:
    [<ffffffffa049aa20>] ivtv_api_call+0x160/0x6b0 [ivtv]
    [<ffffffffa049af86>] ivtv_api+0x16/0x40 [ivtv]
    [<ffffffffa049b10c>] ivtv_vapi+0xac/0xc0 [ivtv]
    [<ffffffffa049d40d>] ivtv_start_v4l2_encode_stream+0x19d/0x630 [ivtv]
    [<ffffffffa0530653>] snd_ivtv_pcm_capture_open+0x173/0x1c0 [ivtv_alsa]
    [<ffffffffa04526f1>] snd_pcm_open_substream+0x51/0x100 [snd_pcm]
    [<ffffffffa0452853>] snd_pcm_open+0xb3/0x260 [snd_pcm]
    [<ffffffffa0452a37>] snd_pcm_capture_open+0x37/0x50 [snd_pcm]
    [<ffffffffa033f557>] snd_open+0xa7/0x1e0 [snd]
    [<ffffffff8118a628>] chrdev_open+0x88/0x1d0
    [<ffffffff811840be>] do_dentry_open+0x1de/0x270
    [<ffffffff81193a73>] do_last+0x1c3/0xec0
    [<ffffffff81194826>] path_openat+0xb6/0x670
    [<ffffffff81195b65>] do_filp_open+0x35/0x80
    [<ffffffff81185449>] do_sys_open+0x129/0x210
    [<ffffffff815b782d>] system_call_fastpath+0x1a/0x1f

This patch adds the check of firmware at PCM open callback like other
open callbacks of this driver.

Bugzilla: https://apibugzilla.novell.com/show_bug.cgi?id=875440

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/media/pci/ivtv/ivtv-alsa-pcm.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index e1863db..7a9b98b 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -159,6 +159,12 @@ static int snd_ivtv_pcm_capture_open(struct snd_pcm_substream *substream)
 
 	/* Instruct the CX2341[56] to start sending packets */
 	snd_ivtv_lock(itvsc);
+
+	if (ivtv_init_on_first_open(itv)) {
+		snd_ivtv_unlock(itvsc);
+		return -ENXIO;
+	}
+
 	s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM];
 
 	v4l2_fh_init(&item.fh, s->vdev);
-- 
1.9.1

[PATCH 3.13 050/198] CIFS: Fix memory leaks in SMB2_open

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Pavel Shilovsky <pshilovsky@samba.org>

commit 663a962151593c69374776e8651238d0da072459 upstream.

Signed-off-by: Pavel Shilovsky <pshilovsky@samba.org>
Reviewed-by: Shirish Pargaonkar <spargaonkar@suse.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/cifs/smb2pdu.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 787e171..63339c5 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1089,6 +1089,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	int rc = 0;
 	unsigned int num_iovecs = 2;
 	__u32 file_attributes = 0;
+	char *dhc_buf = NULL, *lc_buf = NULL;
 
 	cifs_dbg(FYI, "create/open\n");
 
@@ -1155,6 +1156,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			kfree(copy_path);
 			return rc;
 		}
+		lc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -1169,9 +1171,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
-			kfree(iov[num_iovecs-1].iov_base);
+			kfree(lc_buf);
 			return rc;
 		}
+		dhc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
@@ -1203,6 +1206,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		*oplock = rsp->OplockLevel;
 creat_exit:
 	kfree(copy_path);
+	kfree(lc_buf);
+	kfree(dhc_buf);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
-- 
1.9.1

[PATCH 3.13 051/198] iio:adc:max1363 incorrect resolutions for max11604, max11605, max11610 and max11611.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jonathan Cameron <jic23@kernel.org>

commit a91a73c8b39a6b8bcc53fafa5372c65387c81233 upstream.

Reported-by: Erik Habbinga <Erik.Habbinga@schneider-electric.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Acked-by: Hartmut Knaack <knaack.h@gmx.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/iio/adc/max1363.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index 5edb991..603b731 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1258,8 +1258,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11605] = {
 		.bits = 8,
@@ -1268,8 +1268,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11606] = {
 		.bits = 10,
@@ -1318,8 +1318,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11611] = {
 		.bits = 10,
@@ -1328,8 +1328,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11612] = {
 		.bits = 12,
-- 
1.9.1

[PATCH 3.13 052/198] staging/mt29f_spinand: Terminate of match table

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Stephen Boyd <sboyd@codeaurora.org>

commit ffd07de65ef5315053ea16356cd533b7f47c17e9 upstream.

Failure to terminate this match table can lead to boot failures
depending on where the compiler places the match table.

Cc: Kamlakant Patel <kamlakant.patel@broadcom.com>
Cc: Mona Anonuevo <manonuevo@micron.com>
Cc: linux-mtd@lists.infradead.org
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/staging/mt29f_spinand/mt29f_spinand.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c
index 51dbc13..5a40925 100644
--- a/drivers/staging/mt29f_spinand/mt29f_spinand.c
+++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c
@@ -924,6 +924,7 @@ static int spinand_remove(struct spi_device *spi)
 
 static const struct of_device_id spinand_dt[] = {
 	{ .compatible = "spinand,mt29f", },
+	{}
 };
 
 /*
-- 
1.9.1

[PATCH 3.13 053/198] mac80211: fix IBSS join by initializing last_scan_completed

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= <khalasa@piap.pl>

commit c7d37a66e345df2fdf1aa7b2c9a6d3d53846ca5b upstream.

Without this fix, freshly rebooted Linux creates a new IBSS
instead of joining an existing one. Only when jiffies counter
overflows after 5 minutes the IBSS can be successfully joined.

Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
[edit commit message slightly]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/mac80211/ibss.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index d40e0e1..3727941 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1676,6 +1676,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	sdata->u.ibss.control_port = params->control_port;
 	sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs;
 	sdata->u.ibss.basic_rates = params->basic_rates;
+	sdata->u.ibss.last_scan_completed = jiffies;
 
 	/* fix basic_rates if channel does not support these rates */
 	rate_flags = ieee80211_chandef_rate_flags(&params->chandef);
-- 
1.9.1

[PATCH 3.13 054/198] KVM: lapic: sync highest ISR to hardware apic on EOI

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini <pbonzini@redhat.com>

commit fc57ac2c9ca8109ea97fcc594f4be436944230cc upstream.

When Hyper-V enlightenments are in effect, Windows prefers to issue an
Hyper-V MSR write to issue an EOI rather than an x2apic MSR write.
The Hyper-V MSR write is not handled by the processor, and besides
being slower, this also causes bugs with APIC virtualization.  The
reason is that on EOI the processor will modify the highest in-service
interrupt (SVI) field of the VMCS, as explained in section 29.1.4 of
the SDM; every other step in EOI virtualization is already done by
apic_send_eoi or on VM entry, but this one is missing.

We need to do the same, and be careful not to muck with the isr_count
and highest_isr_cache fields that are unused when virtual interrupt
delivery is enabled.

Reviewed-by: Yang Zhang <yang.z.zhang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/x86/kvm/lapic.c | 62 ++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 43 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d86ff15..92bbb39 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
 		++apic->isr_count;
 	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 	apic->highest_isr_cache = vec;
 }
 
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
+	/*
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
+	 */
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
+}
+
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
-}
-
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (vector == -1)
 		return -1;
 
-- 
1.9.1

[PATCH 3.13 055/198] s390/time: cast tv_nsec to u64 prior to shift in update_vsyscall

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Martin Schwidefsky <schwidefsky@de.ibm.com>

commit b6f4296279ab3ada554d993d12844272fd86b36a upstream.

Analog to git commit 28b92e09e25bdc0ae864b22eacf195a74f861389
first cast tk->wall_to_monotonic.tv_nsec to u64 before doing
the shift with tk->shift to avoid loosing relevant bits on a
32-bit kernel.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/s390/kernel/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index dd95f163..a80190b 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -226,7 +226,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtom_clock_sec =
 		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = tk->xtime_nsec +
-		+ (tk->wall_to_monotonic.tv_nsec << tk->shift);
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift);
 	nsecps = (u64) NSEC_PER_SEC << tk->shift;
 	while (vdso_data->wtom_clock_nsec >= nsecps) {
 		vdso_data->wtom_clock_nsec -= nsecps;
-- 
1.9.1

[PATCH 3.13 056/198] ahci: add PCI ID for Marvell 88SE91A0 SATA Controller

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?Andreas=20Schr=C3=A4gle?= <ajs124.ajs124@gmail.com>

commit 754a292fe6b08196cb135c03b404444e17de520a upstream.

Add support for Marvell Technology Group Ltd. 88SE91A0 SATA 6Gb/s
Controller by adding its PCI ID.

Signed-off-by: Andreas Schrägle <ajs124.ajs124@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/ata/ahci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index bc5579e..7460492 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -444,6 +444,8 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 on some Gigabyte */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0),
+	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
-- 
1.9.1

[PATCH 3.13 057/198] ext4: fix zeroing of page during writeback

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jan Kara <jack@suse.cz>

commit eeece469dedadf3918bad50ad80f4616a0064e90 upstream.

Tail of a page straddling inode size must be zeroed when being written
out due to POSIX requirement that modifications of mmaped page beyond
inode size must not be written to the file. ext4_bio_write_page() did
this only for blocks fully beyond inode size but didn't properly zero
blocks partially beyond inode size. Fix this.

The problem has been uncovered by mmap_11-4 test in openposix test suite
(part of LTP).

Reported-by: Xiaoguang Wang <wangxg.fnst@cn.fujitsu.com>
Fixes: 5a0dc7365c240
Fixes: bd2d0210cf22f
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/ext4/page-io.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index d84cc95..598c4c6 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -422,6 +422,17 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	ClearPageError(page);
 
 	/*
+	 * Comments copied from block_write_full_page_endio:
+	 *
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	if (len < PAGE_CACHE_SIZE)
+		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
 	 * mark all buffers in the page before submitting so that
 	 * end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -432,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
-			/*
-			 * Comments copied from block_write_full_page_endio:
-			 *
-			 * The page straddles i_size.  It must be zeroed out on
-			 * each and every writepage invocation because it may
-			 * be mmapped.  "A file is mapped in multiples of the
-			 * page size.  For a file that is not a multiple of
-			 * the  page size, the remaining memory is zeroed when
-			 * mapped, and writes to that region are not written
-			 * out to the file."
-			 */
-			zero_user_segment(page, block_start,
-					  block_start + blocksize);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
-- 
1.9.1

[PATCH 3.13 058/198] ext4: fix wrong assert in ext4_mb_normalize_request()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Maurizio Lombardi <mlombard@redhat.com>

commit b5b60778558cafad17bbcbf63e0310bd3c68eb17 upstream.

The variable "size" is expressed as number of blocks and not as
number of clusters, this could trigger a kernel panic when using
ext4 with the size of a cluster different from the size of a block.

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/ext4/mballoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 04a5c75..08ddfda 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3135,7 +3135,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
-- 
1.9.1

[PATCH 3.13 059/198] IB/mlx5: add missing padding at end of struct mlx5_ib_create_cq

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <ydroneaud@opteya.com>

commit a8237b32a3faab155a5dc8f886452147ce73da3e upstream.

The i386 ABI disagrees with most other ABIs regarding alignment of
data type larger than 4 bytes: on most ABIs a padding must be added at
end of the structures, while it is not required on i386.

So for most ABI struct mlx5_ib_create_cq get padded to be aligned on a
8 bytes multiple, while for i386, such padding is not added.

The tool pahole can be used to find such implicit padding:

  $ pahole --anon_include \
  	 --nested_anon_include \
  	 --recursive \
  	 --class_name mlx5_ib_create_cq \
  	 drivers/infiniband/hw/mlx5/mlx5_ib.o

Then, structure layout can be compared between i386 and x86_64:

  +++ obj-i386/drivers/infiniband/hw/mlx5/mlx5_ib.o.pahole.txt    2014-03-28 11:43:07.386413682 +0100
  --- obj-x86_64/drivers/infiniband/hw/mlx5/mlx5_ib.o.pahole.txt  2014-03-27 13:06:17.788472721 +0100
  @@ -34,9 +34,8 @@ struct mlx5_ib_create_cq {
          __u64                      db_addr;              /*     8     8 */
          __u32                      cqe_size;             /*    16     4 */

  -       /* size: 20, cachelines: 1, members: 3 */
  -       /* last cacheline: 20 bytes */
  +       /* size: 24, cachelines: 1, members: 3 */
  +       /* padding: 4 */
  +       /* last cacheline: 24 bytes */
   };

This ABI disagreement will make an x86_64 kernel try to read past the
buffer provided by an i386 binary.

When boundary check will be implemented, a x86_64 kernel will refuse
to read past the i386 userspace provided buffer and the uverb will
fail.

Anyway, if the structure lies in memory on a page boundary and next
page is not mapped, ib_copy_from_udata() will fail when trying to read
the 4 bytes of padding and the uverb will fail.

This patch makes create_cq_user() takes care of the input data size to
handle the case where no padding is provided.

This way, x86_64 kernel will be able to handle struct
mlx5_ib_create_cq as sent by unpatched and patched i386 libmlx5.

Link: http://marc.info/?i=cover.1399309513.git.ydroneaud@opteya.com
Fixes: e126ba97dba9e ("mlx5: Add driver for Mellanox Connect-IB adapter")
Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/hw/mlx5/cq.c   | 13 ++++++++++++-
 drivers/infiniband/hw/mlx5/user.h |  1 +
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b726274..65cfbd2 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -32,6 +32,7 @@
 
 #include <linux/kref.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 #include "mlx5_ib.h"
 #include "user.h"
 
@@ -518,14 +519,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int *cqe_size, int *index, int *inlen)
 {
 	struct mlx5_ib_create_cq ucmd;
+	size_t ucmdlen;
 	int page_shift;
 	int npages;
 	int ncont;
 	int err;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
 
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
 		return -EINVAL;
 
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index a886de3..e7da977 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -84,6 +84,7 @@ struct mlx5_ib_create_cq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	cqe_size;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_cq_resp {
-- 
1.9.1

[PATCH 3.13 060/198] IB/mlx5: add missing padding at end of struct mlx5_ib_create_srq

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <ydroneaud@opteya.com>

commit 43bc889380c2ad9aa230eccc03a15cc52cf710d4 upstream.

The i386 ABI disagrees with most other ABIs regarding alignment of
data type larger than 4 bytes: on most ABIs a padding must be added at
end of the structures, while it is not required on i386.

So for most ABIs struct mlx5_ib_create_srq gets implicitly padded to be
aligned on a 8 bytes multiple, while for i386, such padding is not
added.

Tool pahole could be used to find such implicit padding:

  $ pahole --anon_include \
           --nested_anon_include \
           --recursive \
           --class_name mlx5_ib_create_srq \
           drivers/infiniband/hw/mlx5/mlx5_ib.o

Then, structure layout can be compared between i386 and x86_64:

  +++ obj-i386/drivers/infiniband/hw/mlx5/mlx5_ib.o.pahole.txt    2014-03-28 11:43:07.386413682 +0100
  --- obj-x86_64/drivers/infiniband/hw/mlx5/mlx5_ib.o.pahole.txt  2014-03-27 13:06:17.788472721 +0100
  @@ -69,7 +68,6 @@ struct mlx5_ib_create_srq {
          __u64                      db_addr;              /*     8     8 */
          __u32                      flags;                /*    16     4 */

  -       /* size: 20, cachelines: 1, members: 3 */
  -       /* last cacheline: 20 bytes */
  +       /* size: 24, cachelines: 1, members: 3 */
  +       /* padding: 4 */
  +       /* last cacheline: 24 bytes */
   };

ABI disagreement will make an x86_64 kernel try to read past
the buffer provided by an i386 binary.

When boundary check will be implemented, the x86_64 kernel will
refuse to read past the i386 userspace provided buffer and the
uverb will fail.

Anyway, if the structure lay in memory on a page boundary and
next page is not mapped, ib_copy_from_udata() will fail and the
uverb will fail.

This patch makes create_srq_user() takes care of the input
data size to handle the case where no padding was provided.

This way, x86_64 kernel will be able to handle struct mlx5_ib_create_srq
as sent by unpatched and patched i386 libmlx5.

Link: http://marc.info/?i=cover.1399309513.git.ydroneaud@opteya.com
Fixes: e126ba97dba9e ("mlx5: Add driver for Mellanox Connect-IB adapter")
Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/hw/mlx5/srq.c  | 14 +++++++++++++-
 drivers/infiniband/hw/mlx5/user.h |  1 +
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 210b3ea..384af6d 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/srq.h>
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 
 #include "mlx5_ib.h"
 #include "user.h"
@@ -78,16 +79,27 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_create_srq ucmd;
+	size_t ucmdlen;
 	int err;
 	int npages;
 	int page_shift;
 	int ncont;
 	u32 offset;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) {
 		mlx5_ib_dbg(dev, "failed copy udata\n");
 		return -EFAULT;
 	}
+
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
 
 	srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size,
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index e7da977..84fea5d 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -100,6 +100,7 @@ struct mlx5_ib_create_srq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	flags;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_srq_resp {
-- 
1.9.1

[PATCH 3.13 061/198] IB/qib: Fix port in pkey change event

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mike Marciniszyn <mike.marciniszyn@intel.com>

commit 911eccd284d13d78c92ec4f1f1092c03457d732a upstream.

The code used a literal 1 in dispatching an IB_EVENT_PKEY_CHANGE.

As of the dual port qib QDR card, this is not necessarily correct.

Change to use the port as specified in the call.

Reported-by: Alex Estrin <alex.estrin@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/hw/qib/qib_mad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index ccb1191..1dd9fcb 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys)
 
 		event.event = IB_EVENT_PKEY_CHANGE;
 		event.device = &dd->verbs_dev.ibdev;
-		event.element.port_num = 1;
+		event.element.port_num = port;
 		ib_dispatch_event(&event);
 	}
 	return 0;
-- 
1.9.1

[PATCH 3.13 062/198] IB/ipath: Translate legacy diagpkt into newer extended diagpkt

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dennis Dalessandro <dennis.dalessandro@intel.com>

commit 7e6d3e5c70f13874fb06e6b67696ed90ce79bd48 upstream.

This patch addresses an issue where the legacy diagpacket is sent in
from the user, but the driver operates on only the extended
diagpkt. This patch specifically initializes the extended diagpkt
based on the legacy packet.

Reported-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/hw/ipath/ipath_diag.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index e2f9a51..45802e9 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -346,6 +346,10 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 			ret = -EFAULT;
 			goto bail;
 		}
+		dp.len = odp.len;
+		dp.unit = odp.unit;
+		dp.data = odp.data;
+		dp.pbc_wd = 0;
 	} else {
 		ret = -EINVAL;
 		goto bail;
-- 
1.9.1

[PATCH 3.13 063/198] mei: me: fix hw ready reset flow

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tomas Winkler <tomas.winkler@intel.com>

commit b04ada92ffaabb868497a1fce8e4f6bf74e5488f upstream.

We cleared H_RST for H_CSR on spurious interrupt generated when ME_RDY
while cleared and not while  ME_RDY is set. The spurious interrupt
is not delivered on all platforms in this case the
driver may fail to initialize.

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/misc/mei/hw-me.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 3412adc..f285dc1 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -164,6 +164,9 @@ static void mei_me_hw_reset_release(struct mei_device *dev)
 	hcsr |= H_IG;
 	hcsr &= ~H_RST;
 	mei_hcsr_set(hw, hcsr);
+
+	/* complete this write before we set host ready on another CPU */
+	mmiowb();
 }
 /**
  * mei_me_hw_reset - resets fw via mei csr register.
@@ -201,6 +204,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 static void mei_me_host_set_ready(struct mei_device *dev)
 {
 	struct mei_me_hw *hw = to_me_hw(dev);
+	hw->host_hw_state = mei_hcsr_read(hw);
 	hw->host_hw_state |= H_IE | H_IG | H_RDY;
 	mei_hcsr_set(hw, hw->host_hw_state);
 }
@@ -496,6 +500,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/*  check if we need to start the dev */
 	if (!mei_host_is_ready(dev)) {
 		if (mei_hw_is_ready(dev)) {
+			mei_me_hw_reset_release(dev);
 			dev_dbg(&dev->pdev->dev, "we need to start the dev.\n");
 
 			dev->recvd_hw_ready = true;
@@ -504,8 +509,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 			mutex_unlock(&dev->device_lock);
 			return IRQ_HANDLED;
 		} else {
-			dev_dbg(&dev->pdev->dev, "Reset Completed.\n");
-			mei_me_hw_reset_release(dev);
+			dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n");
 			mutex_unlock(&dev->device_lock);
 			return IRQ_HANDLED;
 		}
-- 
1.9.1

[PATCH 3.13 064/198] mei: me: drop harmful wait optimization

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tomas Winkler <tomas.winkler@intel.com>

commit 07cd7be3d92eeeae1f92a017f2cfe4fdd9256526 upstream.

It my take time till ME_RDY will be cleared after the reset,
so we cannot check the bit before we got the interrupt

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/misc/mei/hw-me.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index f285dc1..4835edc 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -186,6 +186,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 	else
 		hcsr &= ~H_IE;
 
+	dev->recvd_hw_ready = false;
 	mei_me_reg_write(hw, H_CSR, hcsr);
 
 	if (dev->dev_state == MEI_DEV_POWER_DOWN)
@@ -237,10 +238,7 @@ static bool mei_me_hw_is_ready(struct mei_device *dev)
 static int mei_me_hw_ready_wait(struct mei_device *dev)
 {
 	int err;
-	if (mei_me_hw_is_ready(dev))
-		return 0;
 
-	dev->recvd_hw_ready = false;
 	mutex_unlock(&dev->device_lock);
 	err = wait_event_interruptible_timeout(dev->wait_hw_ready,
 			dev->recvd_hw_ready,
-- 
1.9.1

[PATCH 3.13 065/198] mei: me: read H_CSR after asserting reset

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tomas Winkler <tomas.winkler@intel.com>

commit c40765d919d25d2d44d99c4ce39e48808f137e1e upstream.

According the spec the host should read H_CSR again
after asserting reset H_RST to ensure that reset was
read by the firmware

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ kamal: backport to 3.13-stable: also includes mei_me_hw_reset() change from
    33ec082 mei: revamp mei reset state machine ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/misc/mei/hw-me.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 4835edc..cbc9187 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -189,7 +189,19 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 	dev->recvd_hw_ready = false;
 	mei_me_reg_write(hw, H_CSR, hcsr);
 
-	if (dev->dev_state == MEI_DEV_POWER_DOWN)
+	/*
+	 * Host reads the H_CSR once to ensure that the
+	 * posted write to H_CSR completes.
+	 */
+	hcsr = mei_hcsr_read(hw);
+
+	if ((hcsr & H_RST) == 0)
+		dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr);
+
+	if ((hcsr & H_RDY) == H_RDY)
+		dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr);
+
+	if (intr_enable == false)
 		mei_me_hw_reset_release(dev);
 
 	return 0;
-- 
1.9.1

[PATCH 3.13 066/198] usb: usbtest: fix unlink write error with pattern 1

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Huang Rui <ray.huang@amd.com>

commit e4d58f5dcb7d7be45df8def31881ebfae99c75da upstream.

TEST 12 and TEST 24 unlinks the URB write request for N times. When
host and gadget both initialize pattern 1 (mod 63) data series to
transfer, the gadget side will complain the wrong data which is not
expected.  Because in host side, usbtest doesn't fill the data buffer
as mod 63 and this patch fixed it.

[20285.488974] dwc3 dwc3.0.auto: ep1out-bulk: Transfer Not Ready
[20285.489181] dwc3 dwc3.0.auto: ep1out-bulk: reason Transfer Not Active
[20285.489423] dwc3 dwc3.0.auto: ep1out-bulk: req ffff8800aa6cb480 dma aeb50800 length 512 last
[20285.489727] dwc3 dwc3.0.auto: ep1out-bulk: cmd 'Start Transfer' params 00000000 a9eaf000 00000000
[20285.490055] dwc3 dwc3.0.auto: Command Complete --> 0
[20285.490281] dwc3 dwc3.0.auto: ep1out-bulk: Transfer Not Ready
[20285.490492] dwc3 dwc3.0.auto: ep1out-bulk: reason Transfer Active
[20285.490713] dwc3 dwc3.0.auto: ep1out-bulk: endpoint busy
[20285.490909] dwc3 dwc3.0.auto: ep1out-bulk: Transfer Complete
[20285.491117] dwc3 dwc3.0.auto: request ffff8800aa6cb480 from ep1out-bulk completed 512/512 ===> 0
[20285.491431] zero gadget: bad OUT byte, buf[1] = 0
[20285.491605] dwc3 dwc3.0.auto: ep1out-bulk: cmd 'Set Stall' params 00000000 00000000 00000000
[20285.491915] dwc3 dwc3.0.auto: Command Complete --> 0
[20285.492099] dwc3 dwc3.0.auto: queing request ffff8800aa6cb480 to ep1out-bulk length 512
[20285.492387] dwc3 dwc3.0.auto: ep1out-bulk: Transfer Not Ready
[20285.492595] dwc3 dwc3.0.auto: ep1out-bulk: reason Transfer Not Active
[20285.492830] dwc3 dwc3.0.auto: ep1out-bulk: req ffff8800aa6cb480 dma aeb51000 length 512 last
[20285.493135] dwc3 dwc3.0.auto: ep1out-bulk: cmd 'Start Transfer' params 00000000 a9eaf000 00000000
[20285.493465] dwc3 dwc3.0.auto: Command Complete --> 0

Signed-off-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/usb/misc/usbtest.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index b415282..9cb3d13 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -1303,6 +1303,11 @@ static int unlink1(struct usbtest_dev *dev, int pipe, int size, int async)
 	urb->context = &completion;
 	urb->complete = unlink1_callback;
 
+	if (usb_pipeout(urb->pipe)) {
+		simple_fill_buf(urb);
+		urb->transfer_flags |= URB_ZERO_PACKET;
+	}
+
 	/* keep the endpoint busy.  there are lots of hc/hcd-internal
 	 * states, and testing should get to all of them over time.
 	 *
@@ -1433,6 +1438,11 @@ static int unlink_queued(struct usbtest_dev *dev, int pipe, unsigned num,
 				unlink_queued_callback, &ctx);
 		ctx.urbs[i]->transfer_dma = buf_dma;
 		ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
+
+		if (usb_pipeout(ctx.urbs[i]->pipe)) {
+			simple_fill_buf(ctx.urbs[i]);
+			ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET;
+		}
 	}
 
 	/* Submit all the URBs and then unlink URBs num - 4 and num - 2. */
-- 
1.9.1

[PATCH 3.13 067/198] s390/lowcore: reserve 96 bytes for IRB in lowcore

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christian Borntraeger <borntraeger@de.ibm.com>

commit 993072ee67aa179c48c85eb19869804e68887d86 upstream.

The IRB might be 96 bytes if the extended-I/O-measurement facility is
used. This feature is currently not used by Linux, but struct irb
already has the emw defined. So let's make the irb in lowcore match the
size of the internal data structure to be future proof.
We also have to add a pad, to correctly align the paste.

The bigger irb field also circumvents a bug in some QEMU versions that
always write the emw field on test subchannel and therefore destroy the
paste definitions of this CPU. Running under these QEMU version broke
some timing functions in the VDSO and all users of these functions,
e.g. some JREs.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/s390/include/asm/lowcore.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141..2bed4f0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -142,9 +142,9 @@ struct _lowcore {
 	__u8	pad_0x02fc[0x0300-0x02fc];	/* 0x02fc */
 
 	/* Interrupt response block */
-	__u8	irb[64];			/* 0x0300 */
+	__u8	irb[96];			/* 0x0300 */
 
-	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
+	__u8	pad_0x0360[0x0e00-0x0360];	/* 0x0360 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -288,12 +288,13 @@ struct _lowcore {
 	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
 
 	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0400 */
+	__u8	irb[96];			/* 0x0400 */
+	__u8	pad_0x0460[0x0480-0x0460];	/* 0x0460 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0440 */
+	__u32	paste[16];			/* 0x0480 */
 
-	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
+	__u8	pad_0x04c0[0x0e00-0x04c0];	/* 0x04c0 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
-- 
1.9.1

[PATCH 3.13 068/198] mac80211: fix a memory leak on sta rate selection table

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Felix Fietkau <nbd@openwrt.org>

commit 53d045258ee2e38b1e882617cb0799a04d05f5fa upstream.

If the rate control algorithm uses a selection table, it
is leaked when the station is destroyed - fix that.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Reported-by: Christophe Prévotaux <cprevotaux@nltinc.com>
Fixes: 0d528d85c519 ("mac80211: improve the rate control API")
[add commit log entry, remove pointless NULL check]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/mac80211/sta_info.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f92e221..ae0c132 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -271,6 +271,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
 
-- 
1.9.1

[PATCH 3.13 069/198] mac80211: don't check netdev state for debugfs read/write

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Arik Nemtsov <arik@wizery.com>

commit 923eaf367206e01f22c97aee22300e332d071916 upstream.

Doing so will lead to an oops for a p2p-dev interface, since it has
no netdev.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/mac80211/debugfs_netdev.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 04b5a14..cae3d14 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read(
 	ssize_t ret = -EINVAL;
 
 	read_lock(&dev_base_lock);
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*format)(sdata, buf, sizeof(buf));
+	ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
 	if (ret >= 0)
@@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write(
 
 	ret = -ENODEV;
 	rtnl_lock();
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*write)(sdata, buf, count);
+	ret = (*write)(sdata, buf, count);
 	rtnl_unlock();
 
 	return ret;
-- 
1.9.1

[PATCH 3.13 070/198] mtd: pxa3xx_nand: make the driver work on big-endian systems

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>

commit b7e460624f0f3c31150f3b09e75b0d009e22ba5f upstream.

The pxa3xx_nand driver currently uses __raw_writel() and __raw_readl()
to access I/O registers. However, those functions do not do any
endianness swapping, which means that they won't work when the CPU
runs in big-endian but the I/O registers are little endian, which is
the common situation for ARM systems running big endian.

Since __raw_writel() and __raw_readl() do not include any memory
barriers and the pxa3xx_nand driver can only be compiled for ARM
platforms, the closest I/o accessors functions that do endianess
swapping are writel_relaxed() and readl_relaxed().

This patch has been verified to work on Armada XP GP: without the
patch, the NAND is not detected when the kernel runs big endian while
it is properly detected when the kernel runs little endian. With the
patch applied, the NAND is properly detected in both situations
(little and big endian).

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/mtd/nand/pxa3xx_nand.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 4b3aaa8..0527537 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -110,10 +110,10 @@
 
 /* macros for registers read/write */
 #define nand_writel(info, off, val)	\
-	__raw_writel((val), (info)->mmio_base + (off))
+	writel_relaxed((val), (info)->mmio_base + (off))
 
 #define nand_readl(info, off)		\
-	__raw_readl((info)->mmio_base + (off))
+	readl_relaxed((info)->mmio_base + (off))
 
 /* error code and state */
 enum {
-- 
1.9.1

[PATCH 3.13 071/198] hv: use correct order when freeing monitor_pages

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@redhat.com>

commit a100d88df1e924e5c9678fabf054d1bae7ab74fb upstream.

We try to free two pages when only one has been allocated.
Cleanup path is unlikely, so I haven't found any trace that would fit,
but I hope that free_pages_prepare() does catch it.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Amos Kong <akong@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/hv/connection.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 2e7801a..05827ec 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -224,8 +224,8 @@ cleanup:
 		vmbus_connection.int_page = NULL;
 	}
 
-	free_pages((unsigned long)vmbus_connection.monitor_pages[0], 1);
-	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 1);
+	free_pages((unsigned long)vmbus_connection.monitor_pages[0], 0);
+	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0);
 	vmbus_connection.monitor_pages[0] = NULL;
 	vmbus_connection.monitor_pages[1] = NULL;
 
-- 
1.9.1

[PATCH 3.13 072/198] usb: qcserial: add Netgear AirCard 341U

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Aleksander Morgado <aleksander@aleksander.es>

commit ff1fcd50bc2459744e6f948310bc18eb7d6e8c72 upstream.

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Aleksander: backport to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/usb/serial/qcserial.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 6c0a542..781e4db 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -151,6 +151,9 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)},	/* Netgear AirCard 341U Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)},	/* Netgear AirCard 341U NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)},	/* Netgear AirCard 341U Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
-- 
1.9.1

[PATCH 3.13 073/198] usb: qcserial: add additional Sierra Wireless QMI devices

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Aleksander Morgado <aleksander@aleksander.es>

commit 0ce5fb58564fd85aa8fd2d24209900e2e845317b upstream.

A set of new VID/PIDs retrieved from the out-of-tree GobiNet/GobiSerial
Sierra Wireless drivers.

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Link: http://marc.info/?l=linux-usb&m=140136310027293&w=2
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Aleksander: backport to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/usb/serial/qcserial.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 781e4db..43d93db 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -145,15 +145,33 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)},	/* Sierra Wireless EM7355 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)},	/* Sierra Wireless EM7355 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)},	/* Sierra Wireless EM7355 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 3)},	/* Sierra Wireless Modem Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)},	/* Sierra Wireless MC7305/MC7355 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)},	/* Sierra Wireless MC7305/MC7355 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)},	/* Sierra Wireless MC7305/MC7355 Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 3)},	/* Sierra Wireless Modem Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)},	/* Netgear AirCard 341U Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)},	/* Netgear AirCard 341U NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)},	/* Netgear AirCard 341U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 3)},	/* Sierra Wireless Modem Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
-- 
1.9.1

[PATCH 3.13 074/198] IB/umad: Fix error handling

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Bart Van Assche <bvanassche@acm.org>

commit 8ec0a0e6b58218bdc1db91dd70ebfcd6ad8dd6cd upstream.

Avoid leaking a kref count in ib_umad_open() if port->ib_dev == NULL
or if nonseekable_open() fails.

Avoid leaking a kref count, that sm_sem is kept down and also that the
IB_PORT_SM capability mask is not cleared in ib_umad_sm_open() if
nonseekable_open() fails.

Since container_of() never returns NULL, remove the code that tests
whether container_of() returns NULL.

Moving the kref_get() call from the start of ib_umad_*open() to the
end is safe since it is the responsibility of the caller of these
functions to ensure that the cdev pointer remains valid until at least
when these functions return.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>

[ydroneaud@opteya.com: rework a bit to reduce the amount of code changed]

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>

[ nonseekable_open() can't actually fail, but....  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/core/user_mad.c | 49 +++++++++++++++++++++-----------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index f0d588f..9bdf576 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -780,27 +780,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 {
 	struct ib_umad_port *port;
 	struct ib_umad_file *file;
-	int ret;
+	int ret = -ENXIO;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	mutex_lock(&port->file_mutex);
 
-	if (!port->ib_dev) {
-		ret = -ENXIO;
+	if (!port->ib_dev)
 		goto out;
-	}
 
+	ret = -ENOMEM;
 	file = kzalloc(sizeof *file, GFP_KERNEL);
-	if (!file) {
-		kref_put(&port->umad_dev->ref, ib_umad_release_dev);
-		ret = -ENOMEM;
+	if (!file)
 		goto out;
-	}
 
 	mutex_init(&file->mutex);
 	spin_lock_init(&file->send_lock);
@@ -814,6 +806,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 	list_add_tail(&file->port_list, &port->file_list);
 
 	ret = nonseekable_open(inode, filp);
+	if (ret) {
+		list_del(&file->port_list);
+		kfree(file);
+		goto out;
+	}
+
+	kref_get(&port->umad_dev->ref);
 
 out:
 	mutex_unlock(&port->file_mutex);
@@ -880,10 +879,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	int ret;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	if (filp->f_flags & O_NONBLOCK) {
 		if (down_trylock(&port->sm_sem)) {
@@ -898,17 +893,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	}
 
 	ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
-	if (ret) {
-		up(&port->sm_sem);
-		goto fail;
-	}
+	if (ret)
+		goto err_up_sem;
 
 	filp->private_data = port;
 
-	return nonseekable_open(inode, filp);
+	ret = nonseekable_open(inode, filp);
+	if (ret)
+		goto err_clr_sm_cap;
+
+	kref_get(&port->umad_dev->ref);
+
+	return 0;
+
+err_clr_sm_cap:
+	swap(props.set_port_cap_mask, props.clr_port_cap_mask);
+	ib_modify_port(port->ib_dev, port->port_num, 0, &props);
+
+err_up_sem:
+	up(&port->sm_sem);
 
 fail:
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
 	return ret;
 }
 
-- 
1.9.1

[PATCH 3.13 075/198] RDMA/cxgb4: Add missing padding at end of struct c4iw_create_cq_resp

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Yann Droneaud <ydroneaud@opteya.com>

commit b6f04d3d21458818073a2f5af5339f958864bf71 upstream.

The i386 ABI disagrees with most other ABIs regarding alignment of
data types larger than 4 bytes: on most ABIs a padding must be added
at end of the structures, while it is not required on i386.

So for most ABI struct c4iw_create_cq_resp gets implicitly padded
to be aligned on a 8 bytes multiple, while for i386, such padding
is not added.

The tool pahole can be used to find such implicit padding:

  $ pahole --anon_include \
           --nested_anon_include \
           --recursive \
           --class_name c4iw_create_cq_resp \
           drivers/infiniband/hw/cxgb4/iw_cxgb4.o

Then, structure layout can be compared between i386 and x86_64:

  +++ obj-i386/drivers/infiniband/hw/cxgb4/iw_cxgb4.o.pahole.txt   2014-03-28 11:43:05.547432195 +0100
  --- obj-x86_64/drivers/infiniband/hw/cxgb4/iw_cxgb4.o.pahole.txt 2014-03-28 10:55:10.990133017 +0100
  @@ -14,9 +13,8 @@ struct c4iw_create_cq_resp {
          __u32                      size;                 /*    28     4 */
          __u32                      qid_mask;             /*    32     4 */

  -       /* size: 36, cachelines: 1, members: 6 */
  -       /* last cacheline: 36 bytes */
  +       /* size: 40, cachelines: 1, members: 6 */
  +       /* padding: 4 */
  +       /* last cacheline: 40 bytes */
   };

This ABI disagreement will make an x86_64 kernel try to write past the
buffer provided by an i386 binary.

When boundary check will be implemented, the x86_64 kernel will refuse
to write past the i386 userspace provided buffer and the uverbs will
fail.

If the structure is on a page boundary and the next page is not
mapped, ib_copy_to_udata() will fail and the uverb will fail.

This patch adds an explicit padding at end of structure
c4iw_create_cq_resp, and, like 92b0ca7cb149 ("IB/mlx5: Fix stack info
leak in mlx5_ib_alloc_ucontext()"), makes function c4iw_create_cq()
not writting this padding field to userspace. This way, x86_64 kernel
will be able to write struct c4iw_create_cq_resp as expected by
unpatched and patched i386 libcxgb4.

Link: http://marc.info/?i=cover.1399309513.git.ydroneaud@opteya.com
Fixes: cfdda9d764362 ("RDMA/cxgb4: Add driver for Chelsio T4 RNIC")
Fixes: e24a72a3302a6 ("RDMA/cxgb4: Fix four byte info leak in c4iw_create_cq()")
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/hw/cxgb4/cq.c   | 3 ++-
 drivers/infiniband/hw/cxgb4/user.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 88de3aa..deadaa3 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -940,7 +940,8 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 		uresp.gts_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
 		spin_unlock(&ucontext->mmap_lock);
-		ret = ib_copy_to_udata(udata, &uresp, sizeof uresp);
+		ret = ib_copy_to_udata(udata, &uresp,
+				       sizeof(uresp) - sizeof(uresp.reserved));
 		if (ret)
 			goto err5;
 
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index 32b754c..4893599 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -48,6 +48,7 @@ struct c4iw_create_cq_resp {
 	__u32 cqid;
 	__u32 size;
 	__u32 qid_mask;
+	__u32 reserved; /* explicit padding (optional for i386) */
 };
 
 
-- 
1.9.1

[PATCH 3.13 076/198] MIPS: KVM: Allocate at least 16KB for exception handlers

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: James Hogan <james.hogan@imgtec.com>

commit 7006e2dfda9adfa40251093604db76d7e44263b3 upstream.

Each MIPS KVM guest has its own copy of the KVM exception vector. This
contains the TLB refill exception handler at offset 0x000, the general
exception handler at offset 0x180, and interrupt exception handlers at
offset 0x200 in case Cause_IV=1. A common handler is copied to offset
0x2000 and offset 0x3000 is used for temporarily storing k1 during entry
from guest.

However the amount of memory allocated for this purpose is calculated as
0x200 rounded up to the next page boundary, which is insufficient if 4KB
pages are in use. This can lead to the common handler at offset 0x2000
being overwritten and infinitely recursive exceptions on the next exit
from the guest.

Increase the minimum size from 0x200 to 0x4000 to cover the full use of
the page.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: kvm@vger.kernel.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: Sanjay Lal <sanjayl@kymasys.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/mips/kvm/kvm_mips.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index 73b3482..3dfbe82 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -304,7 +304,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (cpu_has_veic || cpu_has_vint) {
 		size = 0x200 + VECTORSPACING * 64;
 	} else {
-		size = 0x200;
+		size = 0x4000;
 	}
 
 	/* Save Linux EBASE */
-- 
1.9.1

[PATCH 3.13 077/198] block: virtio_blk: don't hold spin lock during world switch

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ming Lei <ming.lei@canonical.com>

commit e8edca6f7f92234202d6dd163c118ef495244d7c upstream.

Firstly, it isn't necessary to hold lock of vblk->vq_lock
when notifying hypervisor about queued I/O.

Secondly, virtqueue_notify() will cause world switch and
it may take long time on some hypervisors(such as, qemu-arm),
so it isn't good to hold the lock and block other vCPUs.

On arm64 quad core VM(qemu-kvm), the patch can increase I/O
performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
	- without the patch: 14K IOPS
	- with the patch: 34K IOPS

fio script:
	[global]
	direct=1
	bsrange=4k-4k
	timeout=10
	numjobs=4
	ioengine=libaio
	iodepth=64

	filename=/dev/vdc
	group_reporting=1

	[f1]
	rw=randread

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/virtio_blk.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 9b734f2..53e3db6 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -159,6 +159,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	unsigned int num;
 	const bool last = (req->cmd_flags & REQ_END) != 0;
 	int err;
+	bool notify = false;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
@@ -211,10 +212,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
-	if (last)
-		virtqueue_kick(vblk->vq);
-
+	if (last && virtqueue_kick_prepare(vblk->vq))
+		notify = true;
 	spin_unlock_irqrestore(&vblk->vq_lock, flags);
+
+	if (notify)
+		virtqueue_notify(vblk->vq);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
-- 
1.9.1

[PATCH 3.13 078/198] nfsd: getattr for FATTR4_WORD0_FILES_AVAIL needs the statfs buffer

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <hch@lst.de>

commit 12337901d654415d9f764b5f5ba50052e9700f37 upstream.

Note nobody's ever noticed because the typical client probably never
requests FILES_AVAIL without also requesting something else on the list.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/nfsd/nfs4xdr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8d679dc..78310f0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2128,8 +2128,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	err = vfs_getattr(&path, &stat);
 	if (err)
 		goto out_nfserr;
-	if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
-			FATTR4_WORD0_MAXNAME)) ||
+	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+			FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
 	    (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
 		       FATTR4_WORD1_SPACE_TOTAL))) {
 		err = vfs_statfs(&path, &statfs);
-- 
1.9.1

[PATCH 3.13 079/198] ASoC: tlv320aci3x: Fix custom snd_soc_dapm_put_volsw_aic3x() function

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Ujfalusi <peter.ujfalusi@ti.com>

commit e6c111fac4464e3f4bf7b3802b517dafc80f8e0f upstream.

For some unknown reason the parameters for snd_soc_test_bits() were in wrong
order:
It was:
snd_soc_test_bits(codec, val, mask, reg); /* WRONG!!! */
while it should be:
snd_soc_test_bits(codec, reg, mask, val);

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/soc/codecs/tlv320aic3x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index 546d16b..da7e7cb 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -169,7 +169,7 @@ static int snd_soc_dapm_put_volsw_aic3x(struct snd_kcontrol *kcontrol,
 	mask <<= shift;
 	val <<= shift;
 
-	change = snd_soc_test_bits(codec, val, mask, reg);
+	change = snd_soc_test_bits(codec, reg, mask, val);
 	if (change) {
 		update.kcontrol = kcontrol;
 		update.reg = reg;
-- 
1.9.1

[PATCH 3.13 080/198] UBIFS: Remove incorrect assertion in shrink_tnc()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: hujianyang <hujianyang@huawei.com>

commit 72abc8f4b4e8574318189886de627a2bfe6cd0da upstream.

I hit the same assert failed as Dolev Raviv reported in Kernel v3.10
shows like this:

[ 9641.164028] UBIFS assert failed in shrink_tnc at 131 (pid 13297)
[ 9641.234078] CPU: 1 PID: 13297 Comm: mmap.test Tainted: G           O 3.10.40 #1
[ 9641.234116] [<c0011a6c>] (unwind_backtrace+0x0/0x12c) from [<c000d0b0>] (show_stack+0x20/0x24)
[ 9641.234137] [<c000d0b0>] (show_stack+0x20/0x24) from [<c0311134>] (dump_stack+0x20/0x28)
[ 9641.234188] [<c0311134>] (dump_stack+0x20/0x28) from [<bf22425c>] (shrink_tnc_trees+0x25c/0x350 [ubifs])
[ 9641.234265] [<bf22425c>] (shrink_tnc_trees+0x25c/0x350 [ubifs]) from [<bf2245ac>] (ubifs_shrinker+0x25c/0x310 [ubifs])
[ 9641.234307] [<bf2245ac>] (ubifs_shrinker+0x25c/0x310 [ubifs]) from [<c00cdad8>] (shrink_slab+0x1d4/0x2f8)
[ 9641.234327] [<c00cdad8>] (shrink_slab+0x1d4/0x2f8) from [<c00d03d0>] (do_try_to_free_pages+0x300/0x544)
[ 9641.234344] [<c00d03d0>] (do_try_to_free_pages+0x300/0x544) from [<c00d0a44>] (try_to_free_pages+0x2d0/0x398)
[ 9641.234363] [<c00d0a44>] (try_to_free_pages+0x2d0/0x398) from [<c00c6a60>] (__alloc_pages_nodemask+0x494/0x7e8)
[ 9641.234382] [<c00c6a60>] (__alloc_pages_nodemask+0x494/0x7e8) from [<c00f62d8>] (new_slab+0x78/0x238)
[ 9641.234400] [<c00f62d8>] (new_slab+0x78/0x238) from [<c031081c>] (__slab_alloc.constprop.42+0x1a4/0x50c)
[ 9641.234419] [<c031081c>] (__slab_alloc.constprop.42+0x1a4/0x50c) from [<c00f80e8>] (kmem_cache_alloc_trace+0x54/0x188)
[ 9641.234459] [<c00f80e8>] (kmem_cache_alloc_trace+0x54/0x188) from [<bf227908>] (do_readpage+0x168/0x468 [ubifs])
[ 9641.234553] [<bf227908>] (do_readpage+0x168/0x468 [ubifs]) from [<bf2296a0>] (ubifs_readpage+0x424/0x464 [ubifs])
[ 9641.234606] [<bf2296a0>] (ubifs_readpage+0x424/0x464 [ubifs]) from [<c00c17c0>] (filemap_fault+0x304/0x418)
[ 9641.234638] [<c00c17c0>] (filemap_fault+0x304/0x418) from [<c00de694>] (__do_fault+0xd4/0x530)
[ 9641.234665] [<c00de694>] (__do_fault+0xd4/0x530) from [<c00e10c0>] (handle_pte_fault+0x480/0xf54)
[ 9641.234690] [<c00e10c0>] (handle_pte_fault+0x480/0xf54) from [<c00e2bf8>] (handle_mm_fault+0x140/0x184)
[ 9641.234716] [<c00e2bf8>] (handle_mm_fault+0x140/0x184) from [<c0316688>] (do_page_fault+0x150/0x3ac)
[ 9641.234737] [<c0316688>] (do_page_fault+0x150/0x3ac) from [<c000842c>] (do_DataAbort+0x3c/0xa0)
[ 9641.234759] [<c000842c>] (do_DataAbort+0x3c/0xa0) from [<c0314e38>] (__dabt_usr+0x38/0x40)

After analyzing the code, I found a condition that may cause this failed
in correct operations. Thus, I think this assertion is wrong and should be
removed.

Suppose there are two clean znodes and one dirty znode in TNC. So the
per-filesystem atomic_t @clean_zn_cnt is (2). If commit start, dirty_znode
is set to COW_ZNODE in get_znodes_to_commit() in case of potentially ops
on this znode. We clear COW bit and DIRTY bit in write_index() without
@tnc_mutex locked. We don't increase @clean_zn_cnt in this place. As the
comments in write_index() shows, if another process hold @tnc_mutex and
dirty this znode after we clean it, @clean_zn_cnt would be decreased to (1).
We will increase @clean_zn_cnt to (2) with @tnc_mutex locked in
free_obsolete_znodes() to keep it right.

If shrink_tnc() performs between decrease and increase, it will release
other 2 clean znodes it holds and found @clean_zn_cnt is less than zero
(1 - 2 = -1), then hit the assertion. Because free_obsolete_znodes() will
soon correct @clean_zn_cnt and no harm to fs in this case, I think this
assertion could be removed.

2 clean zondes and 1 dirty znode, @clean_zn_cnt == 2

Thread A (commit)         Thread B (write or others)       Thread C (shrinker)
->write_index
   ->clear_bit(DIRTY_NODE)
   ->clear_bit(COW_ZNODE)

            @clean_zn_cnt == 2
                          ->mutex_locked(&tnc_mutex)
                          ->dirty_cow_znode
                              ->!ubifs_zn_cow(znode)
                              ->!test_and_set_bit(DIRTY_NODE)
                              ->atomic_dec(&clean_zn_cnt)
                          ->mutex_unlocked(&tnc_mutex)

            @clean_zn_cnt == 1
                                                           ->mutex_locked(&tnc_mutex)
                                                           ->shrink_tnc
                                                             ->destroy_tnc_subtree
                                                             ->atomic_sub(&clean_zn_cnt, 2)
                                                             ->ubifs_assert  <- hit
                                                           ->mutex_unlocked(&tnc_mutex)

            @clean_zn_cnt == -1
->mutex_lock(&tnc_mutex)
->free_obsolete_znodes
   ->atomic_inc(&clean_zn_cnt)
->mutux_unlock(&tnc_mutex)

            @clean_zn_cnt == 0 (correct after shrink)

Signed-off-by: hujianyang <hujianyang@huawei.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/ubifs/shrinker.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index f35135e..9a9fb94 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention)
 			freed = ubifs_destroy_tnc_subtree(znode);
 			atomic_long_sub(freed, &ubifs_clean_zn_cnt);
 			atomic_long_sub(freed, &c->clean_zn_cnt);
-			ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
 			total_freed += freed;
 			znode = zprev;
 		}
-- 
1.9.1

[PATCH 3.13 081/198] Bluetooth: Fix L2CAP deadlock

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jukka Taimisto <jtt@codenomicon.com>

commit 8a96f3cd22878fc0bb564a8478a6e17c0b8dca73 upstream.

-[0x01 Introduction

We have found a programming error causing a deadlock in Bluetooth subsystem
of Linux kernel. The problem is caused by missing release_sock() call when
L2CAP connection creation fails due full accept queue.

The issue can be reproduced with 3.15-rc5 kernel and is also present in
earlier kernels.

-[0x02 Details

The problem occurs when multiple L2CAP connections are created to a PSM which
contains listening socket (like SDP) and left pending, for example,
configuration (the underlying ACL link is not disconnected between
connections).

When L2CAP connection request is received and listening socket is found the
l2cap_sock_new_connection_cb() function (net/bluetooth/l2cap_sock.c) is called.
This function locks the 'parent' socket and then checks if the accept queue
is full.

1178         lock_sock(parent);
1179
1180         /* Check for backlog size */
1181         if (sk_acceptq_is_full(parent)) {
1182                 BT_DBG("backlog full %d", parent->sk_ack_backlog);
1183                 return NULL;
1184         }

If case the accept queue is full NULL is returned, but the 'parent' socket
is not released. Thus when next L2CAP connection request is received the code
blocks on lock_sock() since the parent is still locked.

Also note that for connections already established and waiting for
configuration to complete a timeout will occur and l2cap_chan_timeout()
(net/bluetooth/l2cap_core.c) will be called. All threads calling this
function will also be blocked waiting for the channel mutex since the thread
which is waiting on lock_sock() alread holds the channel mutex.

We were able to reproduce this by sending continuously L2CAP connection
request followed by disconnection request containing invalid CID. This left
the created connections pending configuration.

After the deadlock occurs it is impossible to kill bluetoothd, btmon will not
get any more data etc. requiring reboot to recover.

-[0x03 Fix

Releasing the 'parent' socket when l2cap_sock_new_connection_cb() returns NULL
seems to fix the issue.

Signed-off-by: Jukka Taimisto <jtt@codenomicon.com>
Reported-by: Tommi Mäkilä <tmakila@codenomicon.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/l2cap_sock.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 7cc24d2..9c27684 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1047,13 +1047,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		release_sock(parent);
 		return NULL;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
 			      GFP_ATOMIC);
-	if (!sk)
+	if (!sk) {
+		release_sock(parent);
 		return NULL;
+        }
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
-- 
1.9.1

[PATCH 3.13 082/198] vgaswitcheroo: switch the mux to the igp on power down when runpm is enabled

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Deucher <alexander.deucher@amd.com>

commit f2bc561610962693be61425cf913778586d8f9c1 upstream.

Avoids blank screens on muxed systems when runpm is active.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=75917

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/vga/vga_switcheroo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index ec0ae2d..6866448 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -623,7 +623,8 @@ static int vga_switcheroo_runtime_suspend(struct device *dev)
 	ret = dev->bus->pm->runtime_suspend(dev);
 	if (ret)
 		return ret;
-
+	if (vgasr_priv.handler->switchto)
+		vgasr_priv.handler->switchto(VGA_SWITCHEROO_IGD);
 	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_OFF);
 	return 0;
 }
-- 
1.9.1

[PATCH 3.13 083/198] drm/radeon: fix typo in radeon_connector_is_dp12_capable()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Deucher <alexander.deucher@amd.com>

commit af5d36539dfe043f1cf0f8b7334d6bb12cd14e75 upstream.

We were checking the ext clock rather than the display clock.

Noticed by ArtForz on IRC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_connectors.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 20a768a..719cd0e 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1411,7 +1411,7 @@ bool radeon_connector_is_dp12_capable(struct drm_connector *connector)
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (ASIC_IS_DCE5(rdev) &&
-	    (rdev->clock.dp_extclk >= 53900) &&
+	    (rdev->clock.default_dispclk >= 53900) &&
 	    radeon_connector_encoder_is_hbr2(connector)) {
 		return true;
 	}
-- 
1.9.1

[PATCH 3.13 084/198] drm/radeon/dp: fix lane/clock setup for dp 1.2 capable devices

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Deucher <alexander.deucher@amd.com>

commit 3b6d9fd23e015b5397c438fd3cd74147d2c805b6 upstream.

Only DCE5+ asics support DP 1.2.

Noticed by ArtForz on IRC.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/radeon/atombios_dp.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index fb3ae07..a1a0350 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -384,6 +384,19 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 
 /***** radeon specific DP functions *****/
 
+static int radeon_dp_get_max_link_rate(struct drm_connector *connector,
+				       u8 dpcd[DP_DPCD_SIZE])
+{
+	int max_link_rate;
+
+	if (radeon_connector_is_dp12_capable(connector))
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
+	else
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
+
+	return max_link_rate;
+}
+
 /* First get the min lane# when low rate is used according to pixel clock
  * (prefer low rate), second check max lane# supported by DP panel,
  * if the max lane# < low rate lane# then use max lane# instead.
@@ -393,7 +406,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 					int pix_clock)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
+	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
 	int max_lane_num = drm_dp_max_lane_count(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
@@ -431,7 +444,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
 			return 540000;
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return radeon_dp_get_max_link_rate(connector, dpcd);
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
-- 
1.9.1

[PATCH 3.13 085/198] drm/radeon/atom: fix dithering on certain panels

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Deucher <alexander.deucher@amd.com>

commit 642528355c694f5ed68f6bff9ff520326a249f99 upstream.

We need to specify the encoder mode as LVDS for eDP
when using the Crtc_Source atom table in order to properly
set up the FMT hardware.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=73911

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/radeon/atombios_encoders.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index cf90161..95ac45e 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1897,8 +1897,11 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
 					args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT;
 				else
 					args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
-			} else
+			} else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+				args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS;
+			} else {
 				args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
+			}
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
-- 
1.9.1

[PATCH 3.13 086/198] drm/radeon: only apply hdmi bpc pll flags when encoder mode is hdmi

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Deucher <alexander.deucher@amd.com>

commit 7d5ab3009a8ca777174f6f469277b3922d56fd4b upstream.

May fix display issues with non-HDMI displays.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/radeon/atombios_crtc.c | 48 ++++++++++++++++++----------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index c9ee271..aedfc27 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -857,14 +857,16 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+					break;
+				}
 			}
 			args.v5.ucTransmitterID = encoder_id;
 			args.v5.ucEncoderMode = encoder_mode;
@@ -879,20 +881,22 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
-				break;
-			case 12:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
-				break;
-			case 16:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
+					break;
+				case 12:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
+					break;
+				case 16:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+					break;
+				}
 			}
 			args.v6.ucTransmitterID = encoder_id;
 			args.v6.ucEncoderMode = encoder_mode;
-- 
1.9.1

[PATCH 3.13 087/198] ahci: Add Device ID for HighPoint RocketRaid 642L

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Carretero?= <cJ-ko@zougloub.eu>

commit d251836508fb26cd1a22b41381739835ee23728d upstream.

This device normally comes with a proprietary driver, using a web GUI
to configure RAID:
 http://www.highpoint-tech.com/USA_new/series_rr600-download.htm
But thankfully it also works out of the box with the AHCI driver,
being just a Marvell 88SE9235.

Devices 640L, 644L, 644LS should also be supported but not tested here.

Signed-off-by: Jérôme Carretero <cJ-ko@zougloub.eu>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/ata/ahci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 7460492..2d9f619 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -450,6 +450,8 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
 	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642),
+	  .driver_data = board_ahci_yes_fbs },
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
-- 
1.9.1

[PATCH 3.13 088/198] mm: fix sleeping function warning from __put_anon_vma

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd@google.com>

commit 7f39dda9d86fb4f4f17af0de170decf125726f8c upstream.

Trinity reports BUG:

  sleeping function called from invalid context at kernel/locking/rwsem.c:47
  in_atomic(): 0, irqs_disabled(): 0, pid: 5787, name: trinity-c27

__might_sleep < down_write < __put_anon_vma < page_get_anon_vma <
migrate_pages < compact_zone < compact_zone_order < try_to_compact_pages ..

Right, since conversion to mutex then rwsem, we should not put_anon_vma()
from inside an rcu_read_lock()ed section: fix the two places that did so.
And add might_sleep() to anon_vma_free(), as suggested by Peter Zijlstra.

Fixes: 88c22088bf23 ("mm: optimize page_lock_anon_vma() fast-path")
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/rmap.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 22478fb..cd6b576 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
+	might_sleep();
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock_write(anon_vma);
@@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	 * above cannot corrupt).
 	 */
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
+		return NULL;
 	}
 out:
 	rcu_read_unlock();
@@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	}
 
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
-		goto out;
+		return NULL;
 	}
 
 	/* we pinned the anon_vma, its safe to sleep */
-- 
1.9.1

[PATCH 3.13 089/198] hugetlb: restrict hugepage_migration_support() to x86_64

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit c177c81e09e517bbf75b67762cdab1b83aba6976 upstream.

Currently hugepage migration is available for all archs which support
pmd-level hugepage, but testing is done only for x86_64 and there're
bugs for other archs.  So to avoid breaking such archs, this patch
limits the availability strictly to x86_64 until developers of other
archs get interested in enabling this feature.

Simply disabling hugepage migration on non-x86_64 archs is not enough to
fix the reported problem where sys_move_pages() hits the BUG_ON() in
follow_page(FOLL_GET), so let's fix this by checking if hugepage
migration is supported in vma_migratable().

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm/mm/hugetlbpage.c     |  5 -----
 arch/arm64/mm/hugetlbpage.c   |  5 -----
 arch/ia64/mm/hugetlbpage.c    |  5 -----
 arch/metag/mm/hugetlbpage.c   |  5 -----
 arch/mips/mm/hugetlbpage.c    |  5 -----
 arch/powerpc/mm/hugetlbpage.c | 10 ----------
 arch/s390/mm/hugetlbpage.c    |  5 -----
 arch/sh/mm/hugetlbpage.c      |  5 -----
 arch/sparc/mm/hugetlbpage.c   |  5 -----
 arch/tile/mm/hugetlbpage.c    |  5 -----
 arch/x86/Kconfig              |  4 ++++
 arch/x86/mm/hugetlbpage.c     | 10 ----------
 include/linux/hugetlb.h       | 13 +++++--------
 include/linux/mempolicy.h     |  6 ++++++
 mm/Kconfig                    |  3 +++
 15 files changed, 18 insertions(+), 73 deletions(-)

diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 54ee616..66781bf 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 31eb959..023747b 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ int pud_huge(pud_t pud)
 #endif
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 68232db..76069c1 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,11 +114,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 0424315..3c52fa6 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -110,11 +110,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 01fda44..a7fee0d 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -85,11 +85,6 @@ int pud_huge(pud_t pud)
 	return (pud_val(pud) & _PAGE_HUGE) != 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 90bb6d9..b673b77 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd)
 	 */
 	return ((pgd_val(pgd) & 0x3) != 0x0);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
 #else
 int pmd_huge(pmd_t pmd)
 {
@@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd)
 {
 	return 0;
 }
-
-int pmd_huge_support(void)
-{
-	return 0;
-}
 #endif
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d261c62..248445f 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -223,11 +223,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmdp, int write)
 {
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 0d676a4..d776234 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -83,11 +83,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 3096317..8545f62 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -232,11 +232,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 0cb3bba..e514899 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -166,11 +166,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0952ecd..9e31880 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1890,6 +1890,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 	depends on X86_64 || X86_PAE
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 9d980d8..fa029fb 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	return NULL;
 }
-
-int pmd_huge_support(void)
-{
-	return 0;
-}
 #else
 
 struct page *
@@ -80,11 +75,6 @@ int pud_huge(pud_t pud)
 {
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
 #endif
 
 /* x86_64 also uses this file */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bd7e987..5572709 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -386,15 +386,13 @@ static inline pgoff_t basepage_index(struct page *page)
 
 extern void dissolve_free_huge_pages(unsigned long start_pfn,
 				     unsigned long end_pfn);
-int pmd_huge_support(void);
-/*
- * Currently hugepage migration is enabled only for pmd-based hugepage.
- * This function will be updated when hugepage migration is more widely
- * supported.
- */
 static inline int hugepage_migration_support(struct hstate *h)
 {
-	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+	return huge_page_shift(h) == PMD_SHIFT;
+#else
+	return 0;
+#endif
 }
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
@@ -434,7 +432,6 @@ static inline pgoff_t basepage_index(struct page *page)
 	return page->index;
 }
 #define dissolve_free_huge_pages(s, e)	do {} while (0)
-#define pmd_huge_support()	0
 #define hugepage_migration_support(h)	0
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 9fe426b..2eb88a1 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -176,6 +176,12 @@ static inline int vma_migratable(struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 		return 0;
+
+#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+	if (vma->vm_flags & VM_HUGETLB)
+		return 0;
+#endif
+
 	/*
 	 * Migration allocates pages in the highest zone. If we cannot
 	 * do so then migration (at least from node to node) is not
diff --git a/mm/Kconfig b/mm/Kconfig
index 723bbe0..bfc2cb5 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -263,6 +263,9 @@ config MIGRATION
 	  pages as migration can relocate pages to satisfy a huge page
 	  allocation instead of reclaiming.
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	boolean
+
 config PHYS_ADDR_T_64BIT
 	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
 
-- 
1.9.1

[PATCH 3.13 090/198] kthread: fix return value of kthread_create() upon SIGKILL.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>

commit 8fe6929cfd43c44834858a53e129ffdc7c166298 upstream.

Commit 786235eeba0e ("kthread: make kthread_create() killable") meant
for allowing kthread_create() to abort as soon as killed by the
OOM-killer.  But returning -ENOMEM is wrong if killed by SIGKILL from
userspace.  Change kthread_create() to return -EINTR upon SIGKILL.

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/kthread.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee..f6249f9 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -262,7 +262,7 @@ static void create_kthread(struct kthread_create_info *create)
  * kthread_stop() has been called).  The return value should be zero
  * or a negative error number; it will be passed to kthread_stop().
  *
- * Returns a task_struct or ERR_PTR(-ENOMEM).
+ * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR).
  */
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 					   void *data, int node,
@@ -298,7 +298,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 		 * that thread.
 		 */
 		if (xchg(&create->done, NULL))
-			return ERR_PTR(-ENOMEM);
+			return ERR_PTR(-EINTR);
 		/*
 		 * kthreadd (or new kernel thread) will call complete()
 		 * shortly.
-- 
1.9.1

[PATCH 3.13 091/198] mm: vmscan: do not throttle based on pfmemalloc reserves if node has no ZONE_NORMAL

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mel Gorman <mgorman@suse.de>

commit 675becce15f320337499bc1a9356260409a5ba29 upstream.

throttle_direct_reclaim() is meant to trigger during swap-over-network
during which the min watermark is treated as a pfmemalloc reserve.  It
throttes on the first node in the zonelist but this is flawed.

The user-visible impact is that a process running on CPU whose local
memory node has no ZONE_NORMAL will stall for prolonged periods of time,
possibly indefintely.  This is due to throttle_direct_reclaim thinking the
pfmemalloc reserves are depleted when in fact they don't exist on that
node.

On a NUMA machine running a 32-bit kernel (I know) allocation requests
from CPUs on node 1 would detect no pfmemalloc reserves and the process
gets throttled.  This patch adjusts throttling of direct reclaim to
throttle based on the first node in the zonelist that has a usable
ZONE_NORMAL or lower zone.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/vmscan.c | 43 +++++++++++++++++++++++++++++++++++++------
 1 file changed, 37 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 05e6095..d873137 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2484,10 +2484,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2512,9 +2519,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2533,10 +2540,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
-- 
1.9.1

[PATCH 3.13 092/198] memcg: do not hang on OOM when killed by userspace OOM access to memory reserves

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Michal Hocko <mhocko@suse.cz>

commit d8dc595ce3909fbc131bdf5ab8c9808fe624b18d upstream.

Eric has reported that he can see task(s) stuck in memcg OOM handler
regularly.  The only way out is to

	echo 0 > $GROUP/memory.oom_control

His usecase is:

- Setup a hierarchy with memory and the freezer (disable kernel oom and
  have a process watch for oom).

- In that memory cgroup add a process with one thread per cpu.

- In one thread slowly allocate once per second I think it is 16M of ram
  and mlock and dirty it (just to force the pages into ram and stay
  there).

- When oom is achieved loop:
  * attempt to freeze all of the tasks.
  * if frozen send every task SIGKILL, unfreeze, remove the directory in
    cgroupfs.

Eric has then pinpointed the issue to be memcg specific.

All tasks are sitting on the memcg_oom_waitq when memcg oom is disabled.
Those that have received fatal signal will bypass the charge and should
continue on their way out.  The tricky part is that the exit path might
trigger a page fault (e.g.  exit_robust_list), thus the memcg charge,
while its memcg is still under OOM because nobody has released any charges
yet.

Unlike with the in-kernel OOM handler the exiting task doesn't get
TIF_MEMDIE set so it doesn't shortcut further charges of the killed task
and falls to the memcg OOM again without any way out of it as there are no
fatal signals pending anymore.

This patch fixes the issue by checking PF_EXITING early in
mem_cgroup_try_charge and bypass the charge same as if it had fatal
signal pending or TIF_MEMDIE set.

Normally exiting tasks (aka not killed) will bypass the charge now but
this should be OK as the task is leaving and will release memory and
increasing the memory pressure just to release it in a moment seems
dubious wasting of cycles.  Besides that charges after exit_signals should
be rare.

I am bringing this patch again (rebased on the current mmotm tree). I
hope we can move forward finally. If there is still an opposition then
I would really appreciate a concurrent approach so that we can discuss
alternatives.

http://comments.gmane.org/gmane.linux.kernel.stable/77650 is a reference
to the followup discussion when the patch has been dropped from the mmotm
last time.

Reported-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ kamal: backport to 3.13: whitespace ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/memcontrol.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f506001..44b0eec 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2706,8 +2706,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	 * in system level. So, allow to go ahead dying process in addition to
 	 * MEMDIE process.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)
-		     || fatal_signal_pending(current)))
+	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
+		     fatal_signal_pending(current) ||
+		     current->flags & PF_EXITING))
 		goto bypass;
 
 	if (unlikely(task_in_memcg_oom(current)))
-- 
1.9.1

[PATCH 3.13 093/198] mm: page_alloc: use word-based accesses for get/set pageblock bitmaps

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mel Gorman <mgorman@suse.de>

commit e58469bafd0524e848c3733bc3918d854595e20f upstream.

The test_bit operations in get/set pageblock flags are expensive.  This
patch reads the bitmap on a word basis and use shifts and masks to isolate
the bits of interest.  Similarly masks are used to set a local copy of the
bitmap and then use cmpxchg to update the bitmap if there have been no
other changes made in parallel.

In a test running dd onto tmpfs the overhead of the pageblock-related
functions went from 1.27% in profiles to 0.5%.

In addition to the performance benefits, this patch closes races that are
possible between:

a) get_ and set_pageblock_migratetype(), where get_pageblock_migratetype()
   reads part of the bits before and other part of the bits after
   set_pageblock_migratetype() has updated them.

b) set_pageblock_migratetype() and set_pageblock_skip(), where the non-atomic
   read-modify-update set bit operation in set_pageblock_skip() will cause
   lost updates to some bits changed in the set_pageblock_migratetype().

Joonsoo Kim first reported the case a) via code inspection.  Vlastimil
Babka's testing with a debug patch showed that either a) or b) occurs
roughly once per mmtests' stress-highalloc benchmark (although not
necessarily in the same pageblock).  Furthermore during development of
unrelated compaction patches, it was observed that frequent calls to
{start,undo}_isolate_page_range() the race occurs several thousands of
times and has resulted in NULL pointer dereferences in move_freepages()
and free_one_page() in places where free_list[migratetype] is
manipulated by e.g.  list_move().  Further debugging confirmed that
migratetype had invalid value of 6, causing out of bounds access to the
free_list array.

That confirmed that the race exist, although it may be extremely rare,
and currently only fatal where page isolation is performed due to
memory hot remove.  Races on pageblocks being updated by
set_pageblock_migratetype(), where both old and new migratetype are
lower MIGRATE_RESERVE, currently cannot result in an invalid value
being observed, although theoretically they may still lead to
unexpected creation or destruction of MIGRATE_RESERVE pageblocks.
Furthermore, things could get suddenly worse when memory isolation is
used more, or when new migratetypes are added.

After this patch, the race has no longer been observed in testing.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reported-and-tested-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/linux/mmzone.h          |  6 ++++-
 include/linux/pageblock-flags.h | 37 ++++++++++++++++++++++++-----
 mm/page_alloc.c                 | 52 +++++++++++++++++++++++++----------------
 3 files changed, 68 insertions(+), 27 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bd791e4..5648290 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -75,9 +75,13 @@ enum {
 
 extern int page_group_by_mobility_disabled;
 
+#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
+#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
+
 static inline int get_pageblock_migratetype(struct page *page)
 {
-	return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
+	BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2);
+	return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK);
 }
 
 struct free_area {
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2ee8cd2..c08730c 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -30,9 +30,12 @@ enum pageblock_bits {
 	PB_migrate,
 	PB_migrate_end = PB_migrate + 3 - 1,
 			/* 3 bits required for migrate types */
-#ifdef CONFIG_COMPACTION
 	PB_migrate_skip,/* If set the block is skipped by compaction */
-#endif /* CONFIG_COMPACTION */
+
+	/*
+	 * Assume the bits will always align on a word. If this assumption
+	 * changes then get/set pageblock needs updating.
+	 */
 	NR_PAGEBLOCK_BITS
 };
 
@@ -62,11 +65,33 @@ extern int pageblock_order;
 /* Forward declaration */
 struct page;
 
+unsigned long get_pageblock_flags_mask(struct page *page,
+				unsigned long end_bitidx,
+				unsigned long mask);
+void set_pageblock_flags_mask(struct page *page,
+				unsigned long flags,
+				unsigned long end_bitidx,
+				unsigned long mask);
+
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
-unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx);
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
-					int start_bitidx, int end_bitidx);
+static inline unsigned long get_pageblock_flags_group(struct page *page,
+					int start_bitidx, int end_bitidx)
+{
+	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+	unsigned long mask = (1 << nr_flag_bits) - 1;
+
+	return get_pageblock_flags_mask(page, end_bitidx, mask);
+}
+
+static inline void set_pageblock_flags_group(struct page *page,
+					unsigned long flags,
+					int start_bitidx, int end_bitidx)
+{
+	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+	unsigned long mask = (1 << nr_flag_bits) - 1;
+
+	set_pageblock_flags_mask(page, flags, end_bitidx, mask);
+}
 
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7376863..6e864d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5940,53 +5940,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
  * @end_bitidx: The last bit of interest
  * returns pageblock_bits flags
  */
-unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx)
+unsigned long get_pageblock_flags_mask(struct page *page,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long flags = 0;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long word;
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (test_bit(bitidx + start_bitidx, bitmap))
-			flags |= value;
-
-	return flags;
+	word = bitmap[word_bitidx];
+	bitidx += end_bitidx;
+	return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
 }
 
 /**
- * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @start_bitidx: The first bit of interest
  * @end_bitidx: The last bit of interest
  * @flags: The flags to set
  */
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
-					int start_bitidx, int end_bitidx)
+void set_pageblock_flags_mask(struct page *page, unsigned long flags,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long old_word, word;
+
+	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
+
 	VM_BUG_ON(!zone_spans_pfn(zone, pfn));
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (flags & value)
-			__set_bit(bitidx + start_bitidx, bitmap);
-		else
-			__clear_bit(bitidx + start_bitidx, bitmap);
+	bitidx += end_bitidx;
+	mask <<= (BITS_PER_LONG - bitidx - 1);
+	flags <<= (BITS_PER_LONG - bitidx - 1);
+
+	word = ACCESS_ONCE(bitmap[word_bitidx]);
+	for (;;) {
+		old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
+		if (word == old_word)
+			break;
+		word = old_word;
+	}
 }
 
 /*
-- 
1.9.1

[PATCH 3.13 094/198] mm/memory-failure.c-failure: send right signal code to correct thread

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tony Luck <tony.luck@intel.com>

commit a70ffcac741d31a406c1d2b832ae43d658e7e1cf upstream.

When a thread in a multi-threaded application hits a machine check because
of an uncorrectable error in memory - we want to send the SIGBUS with
si.si_code = BUS_MCEERR_AR to that thread.  Currently we fail to do that
if the active thread is not the primary thread in the process.
collect_procs() just finds primary threads and this test:

	if ((flags & MF_ACTION_REQUIRED) && t == current) {

will see that the thread we found isn't the current thread and so send a
si.si_code = BUS_MCEERR_AO to the primary (and nothing to the active
thread at this time).

We can fix this by checking whether "current" shares the same mm with the
process that collect_procs() said owned the page.  If so, we send the
SIGBUS to current (with code BUS_MCEERR_AR).

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Otto Bruggeman <otto.g.bruggeman@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Chen Gong <gong.chen@linux.jf.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/memory-failure.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3b0855b..2b5da71 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #endif
 	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 
-	if ((flags & MF_ACTION_REQUIRED) && t == current) {
+	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
 		si.si_code = BUS_MCEERR_AR;
-		ret = force_sig_info(SIGBUS, &si, t);
+		ret = force_sig_info(SIGBUS, &si, current);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
-- 
1.9.1

[PATCH 3.13 095/198] mm/memory-failure.c: don't let collect_procs() skip over processes for MF_ACTION_REQUIRED

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tony Luck <tony.luck@intel.com>

commit 74614de17db6fb472370c426d4f934d8d616edf2 upstream.

When Linux sees an "action optional" machine check (where h/w has reported
an error that is not in the current execution path) we generally do not
want to signal a process, since most processes do not have a SIGBUS
handler - we'd just prematurely terminate the process for a problem that
they might never actually see.

task_early_kill() decides whether to consider a process - and it checks
whether this specific process has been marked for early signals with
"prctl", or if the system administrator has requested early signals for
all processes using /proc/sys/vm/memory_failure_early_kill.

But for MF_ACTION_REQUIRED case we must not defer.  The error is in the
execution path of the current thread so we must send the SIGBUS
immediatley.

Fix by passing a flag argument through collect_procs*() to
task_early_kill() so it knows whether we can defer or must take action.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Chen Gong <gong.chen@linux.jf.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/memory-failure.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2b5da71..e5f7031 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -384,10 +384,12 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk)
+static int task_early_kill(struct task_struct *tsk, int force_early)
 {
 	if (!tsk->mm)
 		return 0;
+	if (force_early)
+		return 1;
 	if (tsk->flags & PF_MCE_PROCESS)
 		return !!(tsk->flags & PF_MCE_EARLY);
 	return sysctl_memory_failure_early_kill;
@@ -397,7 +399,7 @@ static int task_early_kill(struct task_struct *tsk)
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -413,7 +415,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
@@ -432,7 +434,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -443,7 +445,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
@@ -469,7 +471,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;
 
@@ -480,9 +483,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }
 
@@ -967,7 +970,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
-- 
1.9.1

[PATCH 3.13 096/198] mm/memory-failure.c: support use of a dedicated thread to handle SIGBUS(BUS_MCEERR_AO)

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit 3ba08129e38437561df44c36b7ea9081185d5333 upstream.

Currently memory error handler handles action optional errors in the
deferred manner by default.  And if a recovery aware application wants
to handle it immediately, it can do it by setting PF_MCE_EARLY flag.
However, such signal can be sent only to the main thread, so it's
problematic if the application wants to have a dedicated thread to
handler such signals.

So this patch adds dedicated thread support to memory error handler.  We
have PF_MCE_EARLY flags for each thread separately, so with this patch
AO signal is sent to the thread with PF_MCE_EARLY flag set, not the main
thread.  If you want to implement a dedicated thread, you call prctl()
to set PF_MCE_EARLY on the thread.

Memory error handler collects processes to be killed, so this patch lets
it check PF_MCE_EARLY flag on each thread in the collecting routines.

No behavioral change for all non-early kill cases.

Tony said:

: The old behavior was crazy - someone with a multithreaded process might
: well expect that if they call prctl(PF_MCE_EARLY) in just one thread, then
: that thread would see the SIGBUS with si_code = BUS_MCEERR_A0 - even if
: that thread wasn't the main thread for the process.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: Kamil Iskra <iskra@mcs.anl.gov>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Chen Gong <gong.chen@linux.jf.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 Documentation/vm/hwpoison.txt |  5 ++++
 mm/memory-failure.c           | 56 +++++++++++++++++++++++++++++++++----------
 2 files changed, 48 insertions(+), 13 deletions(-)

diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 5500684..6ae89a9 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -84,6 +84,11 @@ PR_MCE_KILL
 		PR_MCE_KILL_EARLY: Early kill
 		PR_MCE_KILL_LATE:  Late kill
 		PR_MCE_KILL_DEFAULT: Use system global default
+	Note that if you want to have a dedicated thread which handles
+	the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
+	call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
+	the SIGBUS is sent to the main thread.
+
 PR_MCE_KILL_GET
 	return current mode
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e5f7031..ba1ab14 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -384,15 +384,44 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk, int force_early)
+/*
+ * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
+ * on behalf of the thread group. Return task_struct of the (first found)
+ * dedicated thread if found, and return NULL otherwise.
+ *
+ * We already hold read_lock(&tasklist_lock) in the caller, so we don't
+ * have to call rcu_read_lock/unlock() in this function.
+ */
+static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
+{
+	struct task_struct *t;
+
+	for_each_thread(tsk, t)
+		if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
+			return t;
+	return NULL;
+}
+
+/*
+ * Determine whether a given process is "early kill" process which expects
+ * to be signaled when some page under the process is hwpoisoned.
+ * Return task_struct of the dedicated thread (main thread unless explicitly
+ * specified) if the process is "early kill," and otherwise returns NULL.
+ */
+static struct task_struct *task_early_kill(struct task_struct *tsk,
+					   int force_early)
 {
+	struct task_struct *t;
 	if (!tsk->mm)
-		return 0;
+		return NULL;
 	if (force_early)
-		return 1;
-	if (tsk->flags & PF_MCE_PROCESS)
-		return !!(tsk->flags & PF_MCE_EARLY);
-	return sysctl_memory_failure_early_kill;
+		return tsk;
+	t = find_early_kill_thread(tsk);
+	if (t)
+		return t;
+	if (sysctl_memory_failure_early_kill)
+		return tsk;
+	return NULL;
 }
 
 /*
@@ -414,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk, force_early))
+		if (!t)
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
 			vma = vmac->vma;
 			if (!page_mapped_in_vma(page, vma))
 				continue;
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -444,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk, force_early))
+		if (!t)
 			continue;
-
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
 				      pgoff) {
 			/*
@@ -457,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * Assume applications who requested early kill want
 			 * to be informed of all such data corruptions.
 			 */
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
-- 
1.9.1

[PATCH 3.13 097/198] powerpc/serial: Use saner flags when creating legacy ports

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

commit c4cad90f9e9dcb85afc5e75a02ae3522ed077296 upstream.

We had a mix & match of flags used when creating legacy ports
depending on where we found them in the device-tree. Among others
we were missing UPF_SKIP_TEST for some kind of ISA ports which is
a problem as quite a few UARTs out there don't support the loopback
test (such as a lot of BMCs).

Let's pick the set of flags used by the SoC code and generalize it
which means autoconf, no loopback test, irq maybe shared and fixed
port.

Sending to stable as the lack of UPF_SKIP_TEST is breaking
serial on some machines so I want this back into distros

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/kernel/legacy_serial.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 40bd7bd..8a8b722 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = {
 static unsigned int legacy_serial_count;
 static int legacy_serial_console = -1;
 
+static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
+	UPF_SHARE_IRQ | UPF_FIXED_PORT;
+
 static unsigned int tsi_serial_in(struct uart_port *p, int offset)
 {
 	unsigned int tmp;
@@ -153,8 +156,6 @@ static int __init add_legacy_soc_port(struct device_node *np,
 {
 	u64 addr;
 	const __be32 *addrp;
-	upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
-		| UPF_FIXED_PORT;
 	struct device_node *tsi = of_get_parent(np);
 
 	/* We only support ports that have a clock frequency properly
@@ -185,9 +186,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	if (tsi && !strcmp(tsi->type, "tsi-bridge"))
-		return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 	else
-		return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_MEM, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 }
 
 static int __init add_legacy_isa_port(struct device_node *np,
@@ -233,7 +236,7 @@ static int __init add_legacy_isa_port(struct device_node *np,
 
 	/* Add port, irq will be dealt with later */
 	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
-			       taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+			       taddr, NO_IRQ, legacy_port_flags, 0);
 
 }
 
@@ -306,7 +309,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	return add_legacy_port(np, index, iotype, base, addr, NO_IRQ,
-			       UPF_BOOT_AUTOCONF, np != pci_dev);
+			       legacy_port_flags, np != pci_dev);
 }
 #endif
 
-- 
1.9.1

[PATCH 3.13 098/198] powerpc: 64bit sendfile is capped at 2GB

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Anton Blanchard <anton@samba.org>

commit 5d73320a96fcce80286f1447864c481b5f0b96fa upstream.

commit 8f9c0119d7ba (compat: fs: Generic compat_sys_sendfile
implementation) changed the PowerPC 64bit sendfile call from
sys_sendile64 to sys_sendfile.

Unfortunately this broke sendfile of lengths greater than 2G because
sys_sendfile caps at MAX_NON_LFS. Restore what we had previously which
fixes the bug.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/include/asm/systbl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 43523fe..05fcdd8 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd)
 SYSCALL_SPU(capget)
 SYSCALL_SPU(capset)
 COMPAT_SYS(sigaltstack)
-COMPAT_SYS_SPU(sendfile)
+SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 PPC_SYS(vfork)
-- 
1.9.1

[PATCH 3.13 099/198] ALSA: hda/realtek - Add support of ALC891 codec

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Kailang Yang <kailang@realtek.com>

commit b6c5fbad16aa5026f508093a8d651c25e1cb6179 upstream.

New codec support for ALC891.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c8a66e0..d370e43 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5482,6 +5482,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
 	{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
 	{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+	{ .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
 	{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
 	{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
 	{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
-- 
1.9.1

[PATCH 3.13 100/198] rbd: use reference counts for image requests

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Elder <elder@linaro.org>

commit 0f2d5be792b0466b06797f637cfbb0f64dbb408c upstream.

Each image request contains a reference count, but to date it has
not actually been used.  (I think this was just an oversight.) A
recent report involving rbd failing an assertion shed light on why
and where we need to use these reference counts.

Every OSD request associated with an object request uses
rbd_osd_req_callback() as its callback function.  That function will
call a helper function (dependent on the type of OSD request) that
will set the object request's "done" flag if the object request if
appropriate.  If that "done" flag is set, the object request is
passed to rbd_obj_request_complete().

In rbd_obj_request_complete(), requests are processed in sequential
order.  So if an object request completes before one of its
predecessors in the image request, the completion is deferred.
Otherwise, if it's a completing object's "turn" to be completed, it
is passed to rbd_img_obj_end_request(), which records the result of
the operation, accumulates transferred bytes, and so on.  Next, the
successor to this request is checked and if it is marked "done",
(deferred) completion processing is performed on that request, and
so on.  If the last object request in an image request is completed,
rbd_img_request_complete() is called, which (typically) destroys
the image request.

There is a race here, however.  The instant an object request is
marked "done" it can be provided (by a thread handling completion of
one of its predecessor operations) to rbd_img_obj_end_request(),
which (for the last request) can then lead to the image request
getting torn down.  And this can happen *before* that object has
itself entered rbd_img_obj_end_request().  As a result, once it
*does* enter that function, the image request (and even the object
request itself) may have been freed and become invalid.

All that's necessary to avoid this is to properly count references
to the image requests.  We tear down an image request's object
requests all at once--only when the entire image request has
completed.  So there's no need for an image request to count
references for its object requests.  However, we don't want an
image request to go away until the last of its object requests
has passed through rbd_img_obj_callback().  In other words,
we don't want rbd_img_request_complete() to necessarily
result in the image request being destroyed, because it may
get called before we've finished processing on all of its
object requests.

So the fix is to add a reference to an image request for
each of its object requests.  The reference can be viewed
as representing an object request that has not yet finished
its call to rbd_img_obj_callback().  That is emphasized by
getting the reference right after assigning that as the image
object's callback function.  The corresponding release of that
reference is done at the end of rbd_img_obj_callback(), which
every image object request passes through exactly once.

Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/rbd.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index cb1db29..7e37f90 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1395,6 +1395,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+	dout("%s: img %p (was %d)\n", __func__, img_request,
+	     atomic_read(&img_request->kref.refcount));
+	kref_get(&img_request->kref);
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request);
 static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
@@ -2148,6 +2155,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request)
 	img_request->next_completion = which;
 out:
 	spin_unlock_irq(&img_request->completion_lock);
+	rbd_img_request_put(img_request);
 
 	if (!more)
 		rbd_img_request_complete(img_request);
@@ -2244,6 +2252,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 			goto out_partial;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
+		rbd_img_request_get(img_request);
 
 		osd_req_op_extent_init(osd_req, 0, opcode, offset, length,
 						0, 0);
-- 
1.9.1

[PATCH 3.13 101/198] iscsi-target: Reject mutual authentication with reflected CHAP_C

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 1d2b60a5545942b1376cb48c1d55843d71e3a08f upstream.

This patch adds an explicit check in chap_server_compute_md5() to ensure
the CHAP_C value received from the initiator during mutual authentication
does not match the original CHAP_C provided by the target.

This is in line with RFC-3720, section 8.2.1:

   Originators MUST NOT reuse the CHAP challenge sent by the Responder
   for the other direction of a bidirectional authentication.
   Responders MUST check for this condition and close the iSCSI TCP
   connection if it occurs.

Reported-by: Tejas Vaykole <tejas.vaykole@calsoftinc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/iscsi/iscsi_target_auth.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index de77d9a..6689de6 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -314,6 +314,16 @@ static int chap_server_compute_md5(
 		goto out;
 	}
 	/*
+	 * During mutual authentication, the CHAP_C generated by the
+	 * initiator must not match the original CHAP_C generated by
+	 * the target.
+	 */
+	if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+		pr_err("initiator CHAP_C matches target CHAP_C, failing"
+		       " login attempt\n");
+		goto out;
+	}
+	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
 	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-- 
1.9.1

[PATCH 3.13 102/198] powerpc/mm: Check paca psize is up to date for huge mappings

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Michael Ellerman <mpe@ellerman.id.au>

commit 09567e7fd44291bfc08accfdd67ad8f467842332 upstream.

We have a bug in our hugepage handling which exhibits as an infinite
loop of hash faults. If the fault is being taken in the kernel it will
typically trigger the softlockup detector, or the RCU stall detector.

The bug is as follows:

 1. mmap(0xa0000000, ..., MAP_FIXED | MAP_HUGE_TLB | MAP_ANONYMOUS ..)
 2. Slice code converts the slice psize to 16M.
 3. The code on lines 539-540 of slice.c in slice_get_unmapped_area()
    synchronises the mm->context with the paca->context. So the paca slice
    mask is updated to include the 16M slice.
 3. Either:
    * mmap() fails because there are no huge pages available.
    * mmap() succeeds and the mapping is then munmapped.
    In both cases the slice psize remains at 16M in both the paca & mm.
 4. mmap(0xa0000000, ..., MAP_FIXED | MAP_ANONYMOUS ..)
 5. The slice psize is converted back to 64K. Because of the check on line 539
    of slice.c we DO NOT update the paca->context. The paca slice mask is now
    out of sync with the mm slice mask.
 6. User/kernel accesses 0xa0000000.
 7. The SLB miss handler slb_allocate_realmode() **uses the paca slice mask**
    to create an SLB entry and inserts it in the SLB.
18. With the 16M SLB entry in place the hardware does a hash lookup, no entry
    is found so a data access exception is generated.
19. The data access handler calls do_page_fault() -> handle_mm_fault().
10. __handle_mm_fault() creates a THP mapping with do_huge_pmd_anonymous_page().
11. The hardware retries the access, there is still nothing in the hash table
    so once again a data access exception is generated.
12. hash_page() calls into __hash_page_thp() and inserts a mapping in the
    hash. Although the THP mapping maps 16M the hashing is done using 64K
    as the segment page size.
13. hash_page() returns immediately after calling __hash_page_thp(), skipping
    over the code at line 1125. Resulting in the mismatch between the
    paca->context and mm->context not being detected.
14. The hardware retries the access, the hash it generates using the 16M
    SLB entry does NOT match the hash we inserted.
15. We take another data access and go into __hash_page_thp().
16. We see a valid entry in the hpte_slot_array and so we call updatepp()
    which succeeds.
17. Goto 14.

We could fix this in two ways. The first would be to remove or modify
the check on line 539 of slice.c.

The second option is to cause the check of paca psize in hash_page() on
line 1125 to also be done for THP pages.

We prefer the latter, because the check & update of the paca psize is
not done until we know it's necessary. It's also done only on the
current cpu, so we don't need to IPI all other cpus.

Without further rearranging the code, the simplest fix is to pull out
the code that checks paca psize and call it in two places. Firstly for
THP/hugetlb, and secondly for other mappings as before.

Thanks to Dave Jones for trinity, which originally found this bug.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/mm/hash_utils_64.c | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 6176b3c..3b7a3d1 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -945,6 +945,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
 		trap, vsid, ssize, psize, lpsize, pte);
 }
 
+static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+			     int psize, bool user_region)
+{
+	if (user_region) {
+		if (psize != get_paca_psize(ea)) {
+			get_paca()->context = mm->context;
+			slb_flush_and_rebolt();
+		}
+	} else if (get_paca()->vmalloc_sllp !=
+		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
+		get_paca()->vmalloc_sllp =
+			mmu_psize_defs[mmu_vmalloc_psize].sllp;
+		slb_vmalloc_update();
+	}
+}
+
 /* Result code is:
  *  0 - handled
  *  1 - normal page fault
@@ -1066,6 +1082,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
+		check_paca_psize(ea, mm, psize, user_region);
+
 		goto bail;
 	}
 
@@ -1106,17 +1124,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #endif
 		}
 	}
-	if (user_region) {
-		if (psize != get_paca_psize(ea)) {
-			get_paca()->context = mm->context;
-			slb_flush_and_rebolt();
-		}
-	} else if (get_paca()->vmalloc_sllp !=
-		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
-		get_paca()->vmalloc_sllp =
-			mmu_psize_defs[mmu_vmalloc_psize].sllp;
-		slb_vmalloc_update();
-	}
+
+	check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
-- 
1.9.1

[PATCH 3.13 103/198] xfs: block allocation work needs to be kswapd aware

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dave Chinner <dchinner@redhat.com>

commit 1f6d64829db78a7e1d63e15c9f48f0a5d2b5a679 upstream.

Upon memory pressure, kswapd calls xfs_vm_writepage() from
shrink_page_list(). This can result in delayed allocation occurring
and that gets deferred to the the allocation workqueue.

The allocation then runs outside kswapd context, which means if it
needs memory (and it does to demand page metadata from disk) it can
block in shrink_inactive_list() waiting for IO congestion. These
blocking waits are normally avoiding in kswapd context, so under
memory pressure writeback from kswapd can be arbitrarily delayed by
memory reclaim.

To avoid this, pass the kswapd context to the allocation being done
by the workqueue, so that memory reclaim understands correctly that
the work is being done for kswapd and therefore it is not blocked
and does not delay memory reclaim.

To avoid issues with int->char conversion of flag fields (as noticed
in v1 of this patch) convert the flag fields in the struct
xfs_bmalloca to bool types. pahole indicates these variables are
still single byte variables, so no extra space is consumed by this
change.

Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/xfs/xfs_bmap_util.c | 16 +++++++++++++---
 fs/xfs/xfs_bmap_util.h | 13 +++++++------
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 82e0dab..035d06a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -258,14 +258,23 @@ xfs_bmapi_allocate_worker(
 	struct xfs_bmalloca	*args = container_of(work,
 						struct xfs_bmalloca, work);
 	unsigned long		pflags;
+	unsigned long		new_pflags = PF_FSTRANS;
 
-	/* we are in a transaction context here */
-	current_set_flags_nested(&pflags, PF_FSTRANS);
+	/*
+	 * we are in a transaction context here, but may also be doing work
+	 * in kswapd context, and hence we may need to inherit that state
+	 * temporarily to ensure that we don't block waiting for memory reclaim
+	 * in any way.
+	 */
+	if (args->kswapd)
+		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+	current_set_flags_nested(&pflags, new_pflags);
 
 	args->result = __xfs_bmapi_allocate(args);
 	complete(args->done);
 
-	current_restore_flags_nested(&pflags, PF_FSTRANS);
+	current_restore_flags_nested(&pflags, new_pflags);
 }
 
 /*
@@ -284,6 +293,7 @@ xfs_bmapi_allocate(
 
 
 	args->done = &done;
+	args->kswapd = current_is_kswapd();
 	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
 	queue_work(xfs_alloc_wq, &args->work);
 	wait_for_completion(&done);
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 900747b..f33711d 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -50,12 +50,13 @@ struct xfs_bmalloca {
 	xfs_extlen_t		total;	/* total blocks needed for xaction */
 	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
-	char			eof;	/* set if allocating past last extent */
-	char			wasdel;	/* replacing a delayed allocation */
-	char			userdata;/* set if is user data */
-	char			aeof;	/* allocated space at eof */
-	char			conv;	/* overwriting unwritten extents */
-	char			stack_switch;
+	bool			eof;	/* set if allocating past last extent */
+	bool			wasdel;	/* replacing a delayed allocation */
+	bool			userdata;/* set if is user data */
+	bool			aeof;	/* allocated space at eof */
+	bool			conv;	/* overwriting unwritten extents */
+	bool			stack_switch;
+	bool			kswapd;	/* allocation in kswapd context */
 	int			flags;
 	struct completion	*done;
 	struct work_struct	work;
-- 
1.9.1

[PATCH 3.13 104/198] IB/umad: Fix use-after-free on close

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Bart Van Assche <bvanassche@acm.org>

commit 60e1751cb52cc6d1ae04b6bd3c2b96e770b5823f upstream.

Avoid that closing /dev/infiniband/umad<n> or /dev/infiniband/issm<n>
triggers a use-after-free.  __fput() invokes f_op->release() before it
invokes cdev_put().  Make sure that the ib_umad_device structure is
freed by the cdev_put() call instead of f_op->release().  This avoids
that changing the port mode from IB into Ethernet and back to IB
followed by restarting opensmd triggers the following kernel oops:

    general protection fault: 0000 [#1] PREEMPT SMP
    RIP: 0010:[<ffffffff810cc65c>]  [<ffffffff810cc65c>] module_put+0x2c/0x170
    Call Trace:
     [<ffffffff81190f20>] cdev_put+0x20/0x30
     [<ffffffff8118e2ce>] __fput+0x1ae/0x1f0
     [<ffffffff8118e35e>] ____fput+0xe/0x10
     [<ffffffff810723bc>] task_work_run+0xac/0xe0
     [<ffffffff81002a9f>] do_notify_resume+0x9f/0xc0
     [<ffffffff814b8398>] int_signal+0x12/0x17

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=75051
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Yann Droneaud <ydroneaud@opteya.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/core/user_mad.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 9bdf576..1acb991 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -98,7 +98,7 @@ struct ib_umad_port {
 
 struct ib_umad_device {
 	int                  start_port, end_port;
-	struct kref          ref;
+	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
 
@@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS);
 static void ib_umad_add_one(struct ib_device *device);
 static void ib_umad_remove_one(struct ib_device *device);
 
-static void ib_umad_release_dev(struct kref *ref)
+static void ib_umad_release_dev(struct kobject *kobj)
 {
 	struct ib_umad_device *dev =
-		container_of(ref, struct ib_umad_device, ref);
+		container_of(kobj, struct ib_umad_device, kobj);
 
 	kfree(dev);
 }
 
+static struct kobj_type ib_umad_dev_ktype = {
+	.release = ib_umad_release_dev,
+};
+
 static int hdr_size(struct ib_umad_file *file)
 {
 	return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
@@ -812,7 +816,7 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 		goto out;
 	}
 
-	kref_get(&port->umad_dev->ref);
+	kobject_get(&port->umad_dev->kobj);
 
 out:
 	mutex_unlock(&port->file_mutex);
@@ -851,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp)
 	mutex_unlock(&file->port->file_mutex);
 
 	kfree(file);
-	kref_put(&dev->ref, ib_umad_release_dev);
+	kobject_put(&dev->kobj);
 
 	return 0;
 }
@@ -902,7 +906,7 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	if (ret)
 		goto err_clr_sm_cap;
 
-	kref_get(&port->umad_dev->ref);
+	kobject_get(&port->umad_dev->kobj);
 
 	return 0;
 
@@ -932,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp)
 
 	up(&port->sm_sem);
 
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&port->umad_dev->kobj);
 
 	return ret;
 }
@@ -1000,6 +1004,7 @@ static int find_overflow_devnum(void)
 }
 
 static int ib_umad_init_port(struct ib_device *device, int port_num,
+			     struct ib_umad_device *umad_dev,
 			     struct ib_umad_port *port)
 {
 	int devnum;
@@ -1032,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 
 	cdev_init(&port->cdev, &umad_fops);
 	port->cdev.owner = THIS_MODULE;
+	port->cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num);
 	if (cdev_add(&port->cdev, base, 1))
 		goto err_cdev;
@@ -1050,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	base += IB_UMAD_MAX_PORTS;
 	cdev_init(&port->sm_cdev, &umad_sm_fops);
 	port->sm_cdev.owner = THIS_MODULE;
+	port->sm_cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num);
 	if (cdev_add(&port->sm_cdev, base, 1))
 		goto err_sm_cdev;
@@ -1143,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	kref_init(&umad_dev->ref);
+	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
 	umad_dev->start_port = s;
 	umad_dev->end_port   = e;
@@ -1151,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device)
 	for (i = s; i <= e; ++i) {
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
-		if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
+		if (ib_umad_init_port(device, i, umad_dev,
+				      &umad_dev->port[i - s]))
 			goto err;
 	}
 
@@ -1163,7 +1171,7 @@ err:
 	while (--i >= s)
 		ib_umad_kill_port(&umad_dev->port[i - s]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static void ib_umad_remove_one(struct ib_device *device)
@@ -1177,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device)
 	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
 		ib_umad_kill_port(&umad_dev->port[i]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static char *umad_devnode(struct device *dev, umode_t *mode)
-- 
1.9.1

[PATCH 3.13 105/198] mm: vmscan: clear kswapd's special reclaim powers before exiting

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johannes Weiner <hannes@cmpxchg.org>

commit 71abdc15adf8c702a1dd535f8e30df50758848d2 upstream.

When kswapd exits, it can end up taking locks that were previously held
by allocating tasks while they waited for reclaim.  Lockdep currently
warns about this:

On Wed, May 28, 2014 at 06:06:34PM +0800, Gu Zheng wrote:
>  inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-R} usage.
>  kswapd2/1151 [HC0[0]:SC0[0]:HE1:SE1] takes:
>   (&sig->group_rwsem){+++++?}, at: exit_signals+0x24/0x130
>  {RECLAIM_FS-ON-W} state was registered at:
>     mark_held_locks+0xb9/0x140
>     lockdep_trace_alloc+0x7a/0xe0
>     kmem_cache_alloc_trace+0x37/0x240
>     flex_array_alloc+0x99/0x1a0
>     cgroup_attach_task+0x63/0x430
>     attach_task_by_pid+0x210/0x280
>     cgroup_procs_write+0x16/0x20
>     cgroup_file_write+0x120/0x2c0
>     vfs_write+0xc0/0x1f0
>     SyS_write+0x4c/0xa0
>     tracesys+0xdd/0xe2
>  irq event stamp: 49
>  hardirqs last  enabled at (49):  _raw_spin_unlock_irqrestore+0x36/0x70
>  hardirqs last disabled at (48):  _raw_spin_lock_irqsave+0x2b/0xa0
>  softirqs last  enabled at (0):  copy_process.part.24+0x627/0x15f0
>  softirqs last disabled at (0):            (null)
>
>  other info that might help us debug this:
>   Possible unsafe locking scenario:
>
>         CPU0
>         ----
>    lock(&sig->group_rwsem);
>    <Interrupt>
>      lock(&sig->group_rwsem);
>
>   *** DEADLOCK ***
>
>  no locks held by kswapd2/1151.
>
>  stack backtrace:
>  CPU: 30 PID: 1151 Comm: kswapd2 Not tainted 3.10.39+ #4
>  Call Trace:
>    dump_stack+0x19/0x1b
>    print_usage_bug+0x1f7/0x208
>    mark_lock+0x21d/0x2a0
>    __lock_acquire+0x52a/0xb60
>    lock_acquire+0xa2/0x140
>    down_read+0x51/0xa0
>    exit_signals+0x24/0x130
>    do_exit+0xb5/0xa50
>    kthread+0xdb/0x100
>    ret_from_fork+0x7c/0xb0

This is because the kswapd thread is still marked as a reclaimer at the
time of exit.  But because it is exiting, nobody is actually waiting on
it to make reclaim progress anymore, and it's nothing but a regular
thread at this point.  Be tidy and strip it of all its powers
(PF_MEMALLOC, PF_SWAPWRITE, PF_KSWAPD, and the lockdep reclaim state)
before returning from the thread function.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/vmscan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d873137..1d891f4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3298,7 +3298,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }
 
-- 
1.9.1

[PATCH 3.13 106/198] rtc: rtc-at91rm9200: fix infinite wait for ACKUPD irq

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Boris BREZILLON <boris.brezillon@free-electrons.com>

commit 2fe121e1f5aa3bf31b418a9790db6c400e922291 upstream.

The rtc user must wait at least 1 sec between each time/calandar update
(see atmel's datasheet chapter "Updating Time/Calendar").

Use the 1Hz interrupt to update the at91_rtc_upd_rdy flag and wait for
the at91_rtc_wait_upd_rdy event if the rtc is not ready.

This patch fixes a deadlock in an uninterruptible wait when the RTC is
updated more than once every second.  AFAICT the bug is here from the
beginning, but I think we should at least backport this fix to 3.10 and
the following longterm and stable releases.

Signed-off-by: Boris BREZILLON <boris.brezillon@free-electrons.com>
Reported-by: Bryan Evenson <bevenson@melinkcorp.com>
Tested-by: Bryan Evenson <bevenson@melinkcorp.com>
Cc: Andrew Victor <linux@maxim.org.za>
Cc: Nicolas Ferre <nicolas.ferre@atmel.com>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/rtc/rtc-at91rm9200.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 3281c90..44fe83e 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -48,6 +48,7 @@ struct at91_rtc_config {
 
 static const struct at91_rtc_config *at91_rtc_config;
 static DECLARE_COMPLETION(at91_rtc_updated);
+static DECLARE_COMPLETION(at91_rtc_upd_rdy);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;
@@ -161,6 +162,8 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
+	wait_for_completion(&at91_rtc_upd_rdy);
+
 	/* Stop Time/Calendar from counting */
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
@@ -183,7 +186,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 
 	/* Restart Time/Calendar */
 	cr = at91_rtc_read(AT91_RTC_CR);
+	at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
 	at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM));
+	at91_rtc_write_ier(AT91_RTC_SECEV);
 
 	return 0;
 }
@@ -290,8 +295,10 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
-		if (rtsr & AT91_RTC_SECEV)
-			events |= (RTC_UF | RTC_IRQF);
+		if (rtsr & AT91_RTC_SECEV) {
+			complete(&at91_rtc_upd_rdy);
+			at91_rtc_write_idr(AT91_RTC_SECEV);
+		}
 		if (rtsr & AT91_RTC_ACKUPD)
 			complete(&at91_rtc_updated);
 
@@ -413,6 +420,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 	platform_set_drvdata(pdev, rtc);
 
+	/* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy
+	 * completion.
+	 */
+	at91_rtc_write_ier(AT91_RTC_SECEV);
+
 	dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n");
 	return 0;
 }
-- 
1.9.1

[PATCH 3.13 107/198] ptrace: fix fork event messages across pid namespaces

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Matthew Dempsky <mdempsky@chromium.org>

commit 4e52365f279564cef0ddd41db5237f0471381093 upstream.

When tracing a process in another pid namespace, it's important for fork
event messages to contain the child's pid as seen from the tracer's pid
namespace, not the parent's.  Otherwise, the tracer won't be able to
correlate the fork event with later SIGTRAP signals it receives from the
child.

We still risk a race condition if a ptracer from a different pid
namespace attaches after we compute the pid_t value.  However, sending a
bogus fork event message in this unlikely scenario is still a vast
improvement over the status quo where we always send bogus fork event
messages to debuggers in a different pid namespace than the forking
process.

Signed-off-by: Matthew Dempsky <mdempsky@chromium.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Julien Tinnes <jln@chromium.org>
Cc: Roland McGrath <mcgrathr@chromium.org>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/linux/ptrace.h | 32 ++++++++++++++++++++++++++++++++
 kernel/fork.c          | 10 +++++++---
 2 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 07d0df6..077904c 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>		/* For struct task_struct.  */
 #include <linux/err.h>			/* for IS_ERR_VALUE */
 #include <linux/bug.h>			/* For BUG_ON.  */
+#include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
 #include <uapi/linux/ptrace.h>
 
 /*
@@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message)
 }
 
 /**
+ * ptrace_event_pid - possibly stop for a ptrace event notification
+ * @event:	%PTRACE_EVENT_* value to report
+ * @pid:	process identifier for %PTRACE_GETEVENTMSG to return
+ *
+ * Check whether @event is enabled and, if so, report @event and @pid
+ * to the ptrace parent.  @pid is reported as the pid_t seen from the
+ * the ptrace parent's pid namespace.
+ *
+ * Called without locks.
+ */
+static inline void ptrace_event_pid(int event, struct pid *pid)
+{
+	/*
+	 * FIXME: There's a potential race if a ptracer in a different pid
+	 * namespace than parent attaches between computing message below and
+	 * when we acquire tasklist_lock in ptrace_stop().  If this happens,
+	 * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG.
+	 */
+	unsigned long message = 0;
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = task_active_pid_ns(rcu_dereference(current->parent));
+	if (ns)
+		message = pid_nr_ns(pid, ns);
+	rcu_read_unlock();
+
+	ptrace_event(event, message);
+}
+
+/**
  * ptrace_init_task - initialize ptrace state for a new child
  * @child:		new child task
  * @ptrace:		true if child should be ptrace'd by parent's tracer
diff --git a/kernel/fork.c b/kernel/fork.c
index f330664..d0ca776 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1606,10 +1606,12 @@ long do_fork(unsigned long clone_flags,
 	 */
 	if (!IS_ERR(p)) {
 		struct completion vfork;
+		struct pid *pid;
 
 		trace_sched_process_fork(current, p);
 
-		nr = task_pid_vnr(p);
+		pid = get_task_pid(p, PIDTYPE_PID);
+		nr = pid_vnr(pid);
 
 		if (clone_flags & CLONE_PARENT_SETTID)
 			put_user(nr, parent_tidptr);
@@ -1624,12 +1626,14 @@ long do_fork(unsigned long clone_flags,
 
 		/* forking complete and child started to run, tell ptracer */
 		if (unlikely(trace))
-			ptrace_event(trace, nr);
+			ptrace_event_pid(trace, pid);
 
 		if (clone_flags & CLONE_VFORK) {
 			if (!wait_for_vfork_done(p, &vfork))
-				ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+				ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
 		}
+
+		put_pid(pid);
 	} else {
 		nr = PTR_ERR(p);
 	}
-- 
1.9.1

[PATCH 3.13 108/198] idr: fix overflow bug during maximum ID calculation at maximum height

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lai Jiangshan <laijs@cn.fujitsu.com>

commit 3afb69cb5572b3c8c898c00880803cf1a49852c4 upstream.

idr_replace() open-codes the logic to calculate the maximum valid ID
given the height of the idr tree; unfortunately, the open-coded logic
doesn't account for the fact that the top layer may have unused slots
and over-shifts the limit to zero when the tree is at its maximum
height.

The following test code shows it fails to replace the value for
id=((1<<27)+42):

  static void test5(void)
  {
        int id;
        DEFINE_IDR(test_idr);
  #define TEST5_START ((1<<27)+42) /* use the highest layer */

        printk(KERN_INFO "Start test5\n");
        id = idr_alloc(&test_idr, (void *)1, TEST5_START, 0, GFP_KERNEL);
        BUG_ON(id != TEST5_START);
        TEST_BUG_ON(idr_replace(&test_idr, (void *)2, TEST5_START) != (void *)1);
        idr_destroy(&test_idr);
        printk(KERN_INFO "End of test5\n");
  }

Fix the bug by using idr_max() which correctly takes into account the
maximum allowed shift.

sub_alloc() shares the same problem and may incorrectly fail with
-EAGAIN; however, this bug doesn't affect correct operation because
idr_get_empty_slot(), which already uses idr_max(), retries with the
increased @id in such cases.

[tj@kernel.org: Updated patch description.]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 lib/idr.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/lib/idr.c b/lib/idr.c
index bfe4db4..674c30b 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -250,7 +250,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
 			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
 
 			/* if already at the top layer, we need to grow */
-			if (id >= 1 << (idp->layers * IDR_BITS)) {
+			if (id > idr_max(idp->layers)) {
 				*starting_id = id;
 				return -EAGAIN;
 			}
@@ -827,12 +827,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 	if (!p)
 		return ERR_PTR(-EINVAL);
 
-	n = (p->layer+1) * IDR_BITS;
-
-	if (id >= (1 << n))
+	if (id > idr_max(p->layer + 1))
 		return ERR_PTR(-EINVAL);
 
-	n -= IDR_BITS;
+	n = p->layer * IDR_BITS;
 	while ((n > 0) && p) {
 		p = p->ary[(id >> n) & IDR_MASK];
 		n -= IDR_BITS;
-- 
1.9.1

[PATCH 3.13 109/198] Input: elantech - deal with clickpads reporting right button events

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hans de Goede <hdegoede@redhat.com>

commit cd9e83e2754465856097f31c7ab933ce74c473f8 upstream.

At least the Dell Vostro 5470 elantech *clickpad* reports right button
clicks when clicked in the right bottom area:

https://bugzilla.redhat.com/show_bug.cgi?id=1103528

This is different from how (elantech) clickpads normally operate, normally
no matter where the user clicks on the pad the pad always reports a left
button event, since there is only 1 hardware button beneath the path.

It looks like Dell has put 2 buttons under the pad, one under each bottom
corner, causing this.

Since this however still clearly is a real clickpad hardware-wise, we still
want to report it as such to userspace, so that things like finger movement
in the bottom area can be properly ignored as it should be on clickpads.

So deal with this weirdness by simply mapping a right click to a left click
on elantech clickpads. As an added advantage this is something which we can
simply do on all elantech clickpads, so no need to add special quirks for
this weird model.

Reported-and-tested-by: Elder Marco <eldermarco@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/input/mouse/elantech.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 230cdcf..360e46b 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -473,8 +473,15 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 	input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
 	input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2);
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_report_abs(dev, ABS_PRESSURE, pres);
 	input_report_abs(dev, ABS_TOOL_WIDTH, width);
 
@@ -484,10 +491,17 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 static void elantech_input_sync_v4(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
+	struct elantech_data *etd = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_mt_report_pointer_emulation(dev, true);
 	input_sync(dev);
 }
-- 
1.9.1

[PATCH 3.13 110/198] Input: elantech - don't set bit 1 of reg_10 when the no_hw_res quirk is set

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hans de Goede <hdegoede@redhat.com>

commit fb4f8f568a9def02240ef9bf7aabd246dc63a081 upstream.

The touchpad on the GIGABYTE U2442 not only stops communicating when we try
to set bit 3 (enable real hardware resolution) of reg_10, but on some BIOS
versions also when we set bit 1 (enable two finger mode auto correct).

I've asked the original reporter of:
https://bugzilla.kernel.org/show_bug.cgi?id=61151

To check that not setting bit 1 does not lead to any adverse effects on his
model / BIOS revision, and it does not, so this commit fixes the touchpad
not working on these versions by simply never setting bit 1 for laptop
models with the no_hw_res quirk.

Reported-and-tested-by: James Lademann <jwlademann@gmail.com>
Tested-by: Philipp Wolfer <ph.wolfer@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/input/mouse/elantech.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 360e46b..233516a 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -849,7 +849,7 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		if (etd->set_hw_resolution)
 			etd->reg_10 = 0x0b;
 		else
-			etd->reg_10 = 0x03;
+			etd->reg_10 = 0x01;
 
 		if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
 			rc = -1;
@@ -1350,7 +1350,8 @@ static int elantech_reconnect(struct psmouse *psmouse)
 }
 
 /*
- * Some hw_version 3 models go into error state when we try to set bit 3 of r10
+ * Some hw_version 3 models go into error state when we try to set
+ * bit 3 and/or bit 1 of r10.
  */
 static const struct dmi_system_id no_hw_res_dmi_table[] = {
 #if defined(CONFIG_DMI) && defined(CONFIG_X86)
-- 
1.9.1

[PATCH 3.13 111/198] nfsd4: fix FREE_STATEID lockowner leak

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "J. Bruce Fields" <bfields@redhat.com>

commit 48385408b45523d9a432c66292d47ef43efcbb94 upstream.

27b11428b7de ("nfsd4: remove lockowner when removing lock stateid")
introduced a memory leak.

Reported-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/nfsd/nfs4state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 63b6cdc..025cd8e8d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3713,7 +3713,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
 	 * correspondance, and we have to delete the lockowner when we
 	 * delete the lock stateid:
 	 */
-	unhash_lockowner(lo);
+	release_lockowner(lo);
 	return nfs_ok;
 }
 
-- 
1.9.1

[PATCH 3.13 112/198] Btrfs: fix double free in find_lock_delalloc_range

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chris Mason <clm@fb.com>

commit 7d78874273463a784759916fc3e0b4e2eb141c70 upstream.

We need to NULL the cached_state after freeing it, otherwise
we might free it again if find_delalloc_range doesn't find anything.

Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/btrfs/extent_io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ff43802..809bbe1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1644,6 +1644,7 @@ again:
 		 * shortening the size of the delalloc range we're searching
 		 */
 		free_extent_state(cached_state);
+		cached_state = NULL;
 		if (!loops) {
 			max_bytes = PAGE_CACHE_SIZE;
 			loops = 1;
-- 
1.9.1

[PATCH 3.13 113/198] target: Set CMD_T_ACTIVE bit for Task Management Requests

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit f15e9cd910c4d9da7de43f2181f362082fc45f0f upstream.

This patch fixes a bug where se_cmd descriptors associated with a
Task Management Request (TMR) where not setting CMD_T_ACTIVE before
being dispatched into target_tmr_work() process context.

This is required in order for transport_generic_free_cmd() ->
transport_wait_for_tasks() to wait on se_cmd->t_transport_stop_comp
if a session reset event occurs while an ABORT_TASK is outstanding
waiting for another I/O to complete.

Cc: Thomas Glanzmann <thomas@glanzmann.de>
Cc: Charalampos Pournaris <charpour@gmail.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/target_core_transport.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9095aef..453690f 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2784,6 +2784,12 @@ static void target_tmr_work(struct work_struct *work)
 int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd->transport_state |= CMD_T_ACTIVE;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
-- 
1.9.1

[PATCH 3.13 114/198] target: Use complete_all for se_cmd->t_transport_stop_comp

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit a95d6511303b848da45ee27b35018bb58087bdc6 upstream.

This patch fixes a bug where multiple waiters on ->t_transport_stop_comp
occurs due to a concurrent ABORT_TASK and session reset both invoking
transport_wait_for_tasks(), while waiting for the associated se_cmd
descriptor backend processing to complete.

For this case, complete_all() should be invoked in order to wake up
both waiters in core_tmr_abort_task() + transport_generic_free_cmd()
process contexts.

Cc: Thomas Glanzmann <thomas@glanzmann.de>
Cc: Charalampos Pournaris <charpour@gmail.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/target_core_transport.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 453690f..31adaac 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -534,7 +534,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return 1;
 	}
 
@@ -653,7 +653,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	if (cmd->transport_state & CMD_T_ABORTED &&
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	} else if (cmd->transport_state & CMD_T_FAILED) {
 		INIT_WORK(&cmd->work, target_complete_failure_work);
@@ -1710,7 +1710,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 			cmd->se_tfo->get_task_tag(cmd));
 
 		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	}
 
-- 
1.9.1

[PATCH 3.13 115/198] iscsi-target: Fix ABORT_TASK + connection reset iscsi_queue_req memory leak

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit bbc050488525e1ab1194c27355f63c66814385b8 upstream.

This patch fixes a iscsi_queue_req memory leak when ABORT_TASK response
has been queued by TFO->queue_tm_rsp() -> lio_queue_tm_rsp() after a
long standing I/O completes, but the connection has already reset and
waiting for cleanup to complete in iscsit_release_commands_from_conn()
-> transport_generic_free_cmd() -> transport_wait_for_tasks() code.

It moves iscsit_free_queue_reqs_for_conn() after the per-connection command
list has been released, so that the associated se_cmd tag can be completed +
released by target-core before freeing any remaining iscsi_queue_req memory
for the connection generated by lio_queue_tm_rsp().

Cc: Thomas Glanzmann <thomas@glanzmann.de>
Cc: Charalampos Pournaris <charpour@gmail.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/iscsi/iscsi_target.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 9ab2b91..fe63a02 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4204,8 +4204,6 @@ int iscsit_close_connection(
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);
 
-	iscsit_free_queue_reqs_for_conn(conn);
-
 	/*
 	 * During Connection recovery drop unacknowledged out of order
 	 * commands for this connection, and prepare the other commands
@@ -4222,6 +4220,7 @@ int iscsit_close_connection(
 		iscsit_clear_ooo_cmdsns_for_conn(conn);
 		iscsit_release_commands_from_conn(conn);
 	}
+	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
 	 * Handle decrementing session or connection usage count if
-- 
1.9.1

[PATCH 3.13 116/198] drm/nv50-/mc: fix kms pageflip events by reordering irq handling order.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mario Kleiner <mario.kleiner.de@gmail.com>

commit dcfb1009df3b4ad8d2e0779dd45b438629d6858a upstream.

Whenever a single nouveau_mc_intr() main gpu irq-handler invocation was
responsible for calling both, the vblank-irq handler (display engine irq)
and kms-pageflip completion handler (from fifo irq), the order of
invocation was wrong. nouveau_finish_flip() was called before
drm_handle_vblank() for the vblank of pageflip completion, so the
emitted pageflip event contained stale vblank count and timestamp
from previous vblank. This caused failure in userspace to timestamp
properly.

Reorder order of invocation of engine irq handlers: Put
NVDEV_ENGINE_DISP always on top, and thereby before NVDEV_ENGINE_FIFO,
so that drm_handle_vblank() gets called to update vblank timestamps
and count before potential pageflip events make use of that
information.

This works on nv-50 and later, where kms-pageflip completion triggers
an irq either after a separate vblank irq, or both pageflip and vblank
trigger one common irq invocation, but never before vblank irqs.

v2 (Ben):
- removed mods for nv04-nv40, it doesn't help there anyway
- this is considered a hack, and a better solution should be found

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c | 2 +-
 drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c | 2 +-
 drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
index e8822a9..90d8bf8 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nv50_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP before FIFO, so pageflip-timestamping works! */
 	{ 0x00000001, NVDEV_ENGINE_MPEG },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -34,7 +35,6 @@ nv50_mc_intr[] = {
 	{ 0x00020000, NVDEV_ENGINE_VP },	/* NV84- */
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0002d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index f8a6f18..95b3d35 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -26,6 +26,7 @@
 
 static const struct nouveau_mc_intr
 nv98_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -37,7 +38,6 @@ nv98_mc_intr[] = {
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
 	{ 0x00400000, NVDEV_ENGINE_COPY0 },	/* NVA3-     */
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0042d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
index c02b476..c809743 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nvc0_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work. */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000020, NVDEV_ENGINE_COPY0 },
 	{ 0x00000040, NVDEV_ENGINE_COPY1 },
@@ -39,7 +40,6 @@ nvc0_mc_intr[] = {
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
 	{ 0x01000000, NVDEV_SUBDEV_PWR },
 	{ 0x02000000, NVDEV_SUBDEV_LTCG },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x40000000, NVDEV_SUBDEV_IBUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
-- 
1.9.1

[PATCH 3.13 117/198] drm/nouveau/kms/nv04-nv40: fix pageflip events via special case.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mario Kleiner <mario.kleiner.de@gmail.com>

commit af4870e406126b7ac0ae7c7ce5751f25ebe60f28 upstream.

Cards with nv04 display engine can't reliably use vblank
counts and timestamps computed via drm_handle_vblank(), as
the function gets invoked after sending the pageflip events.

Fix this by defaulting to the old crtcid = -1 fallback path
on <= NV-50 cards, and only using the precise path on NV-50
and later.

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/nouveau/nouveau_display.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index a0b2b87..cdaee13 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -692,6 +692,7 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	struct drm_device *dev = drm->dev;
 	struct nouveau_page_flip_state *s;
 	unsigned long flags;
+	int crtcid = -1;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 
@@ -702,8 +703,13 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	}
 
 	s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
-	if (s->event)
-		drm_send_vblank_event(dev, s->crtc, s->event);
+	if (s->event) {
+		/* Vblank timestamps/counts are only correct on >= NV-50 */
+		if (nv_device(drm->device)->card_type >= NV_50)
+			crtcid = s->crtc;
+
+		drm_send_vblank_event(dev, crtcid, s->event);
+	}
 
 	list_del(&s->head);
 	if (ps)
-- 
1.9.1

[PATCH 3.13 118/198] NFS: populate ->net in mount data when remounting

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mateusz Guzik <mguzik@redhat.com>

commit a914722f333b3359d2f4f12919380a334176bb89 upstream.

Otherwise the kernel oopses when remounting with IPv6 server because
net is dereferenced in dev_get_by_name.

Use net ns of current thread so that dev_get_by_name does not operate on
foreign ns. Changing the address is prohibited anyway so this should not
affect anything.

Signed-off-by: Mateusz Guzik <mguzik@redhat.com>
Cc: linux-nfs@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/nfs/super.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 910ed90..05c3a6e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2246,6 +2246,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
 	data->version = nfsvers;
 	data->minorversion = nfss->nfs_client->cl_minorversion;
+	data->net = current->nsproxy->net_ns;
 	memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
 		data->nfs_server.addrlen);
 
-- 
1.9.1

[PATCH 3.13 119/198] auditsc: audit_krule mask accesses need bounds checking

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@amacapital.net>

commit a3c54931199565930d6d84f4c3456f6440aefd41 upstream.

Fixes an easy DoS and possible information disclosure.

This does nothing about the broken state of x32 auditing.

eparis: If the admin has enabled auditd and has specifically loaded
audit rules.  This bug has been around since before git.  Wow...

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/auditsc.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b590eae..d36a620 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -720,6 +720,22 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
 	return AUDIT_BUILD_CONTEXT;
 }
 
+static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
+{
+	int word, bit;
+
+	if (val > 0xffffffff)
+		return false;
+
+	word = AUDIT_WORD(val);
+	if (word >= AUDIT_BITMASK_SIZE)
+		return false;
+
+	bit = AUDIT_BIT(val);
+
+	return rule->mask[word] & bit;
+}
+
 /* At syscall entry and exit time, this filter is called if the
  * audit_state is not low enough that auditing cannot take place, but is
  * also not high enough that we already know we have to write an audit
@@ -737,11 +753,8 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 
 	rcu_read_lock();
 	if (!list_empty(list)) {
-		int word = AUDIT_WORD(ctx->major);
-		int bit  = AUDIT_BIT(ctx->major);
-
 		list_for_each_entry_rcu(e, list, list) {
-			if ((e->rule.mask[word] & bit) == bit &&
+			if (audit_in_mask(&e->rule, ctx->major) &&
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state, false)) {
 				rcu_read_unlock();
@@ -761,20 +774,16 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 static int audit_filter_inode_name(struct task_struct *tsk,
 				   struct audit_names *n,
 				   struct audit_context *ctx) {
-	int word, bit;
 	int h = audit_hash_ino((u32)n->ino);
 	struct list_head *list = &audit_inode_hash[h];
 	struct audit_entry *e;
 	enum audit_state state;
 
-	word = AUDIT_WORD(ctx->major);
-	bit  = AUDIT_BIT(ctx->major);
-
 	if (list_empty(list))
 		return 0;
 
 	list_for_each_entry_rcu(e, list, list) {
-		if ((e->rule.mask[word] & bit) == bit &&
+		if (audit_in_mask(&e->rule, ctx->major) &&
 		    audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
 			ctx->current_state = state;
 			return 1;
-- 
1.9.1

[PATCH 3.13 120/198] watchdog: kempld-wdt: Use the correct value when configuring the prescaler with the watchdog

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: gundberg <per.gundberg@icomera.com>

commit a9e0436b303e94ba57d3bd4b1fcbeaa744b7ebeb upstream.

Use the prescaler index, rather than its value, to configure the watchdog.
This will prevent a mismatch with the prescaler used to calculate the cycles.

Signed-off-by: Per Gundberg <per.gundberg@icomera.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Michael Brunner <michael.brunner@kontron.com>
Tested-by: Michael Brunner <michael.brunner@kontron.com>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/watchdog/kempld_wdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c
index 20dc738..d9c1a16 100644
--- a/drivers/watchdog/kempld_wdt.c
+++ b/drivers/watchdog/kempld_wdt.c
@@ -162,7 +162,7 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data,
 	kempld_get_mutex(pld);
 	stage_cfg = kempld_read8(pld, KEMPLD_WDT_STAGE_CFG(stage->id));
 	stage_cfg &= ~STAGE_CFG_PRESCALER_MASK;
-	stage_cfg |= STAGE_CFG_SET_PRESCALER(prescaler);
+	stage_cfg |= STAGE_CFG_SET_PRESCALER(PRESCALER_21);
 	kempld_write8(pld, KEMPLD_WDT_STAGE_CFG(stage->id), stage_cfg);
 	kempld_write32(pld, KEMPLD_WDT_STAGE_TIMEOUT(stage->id),
 			stage_timeout);
-- 
1.9.1

[PATCH 3.13 121/198] watchdog: ath79_wdt: avoid spurious restarts on AR934x

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Gabor Juhos <juhosg@openwrt.org>

commit 23afeb613ec0e10aecfae7838a14d485db62ac52 upstream.

On some AR934x based systems, where the frequency of
the AHB bus is relatively high, the built-in watchdog
causes a spurious restart when it gets enabled.

The possible cause of these restarts is that the timeout
value written into the TIMER register does not reaches
the hardware in time.

Add an explicit delay into the ath79_wdt_enable function
to avoid the spurious restarts.

Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/watchdog/ath79_wdt.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 9fa1f69..61098cd 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -20,6 +20,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -91,6 +92,15 @@ static inline void ath79_wdt_keepalive(void)
 static inline void ath79_wdt_enable(void)
 {
 	ath79_wdt_keepalive();
+
+	/*
+	 * Updating the TIMER register requires a few microseconds
+	 * on the AR934x SoCs at least. Use a small delay to ensure
+	 * that the TIMER register is updated within the hardware
+	 * before enabling the watchdog.
+	 */
+	udelay(2);
+
 	ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR);
 	/* flush write */
 	ath79_wdt_rr(WDOG_REG_CTRL);
-- 
1.9.1

[PATCH 3.13 122/198] watchdog: sp805: Set watchdog_device->timeout from ->set_timeout()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Viresh Kumar <viresh.kumar@linaro.org>

commit 938626d96a3ffb9eb54552bb0d3a4f2b30ffdeb0 upstream.

Implementation of ->set_timeout() is supposed to set 'timeout' field of 'struct
watchdog_device' passed to it. sp805 was rather setting this in a local
variable. Fix it.

Reported-by: Arun Ramamurthy <arun.ramamurthy@broadcom.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/watchdog/sp805_wdt.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 3f786ce..88bcdfb 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -60,7 +60,6 @@
  * @adev: amba device structure of wdt
  * @status: current status of wdt
  * @load_val: load value to be set for current timeout
- * @timeout: current programmed timeout
  */
 struct sp805_wdt {
 	struct watchdog_device		wdd;
@@ -69,7 +68,6 @@ struct sp805_wdt {
 	struct clk			*clk;
 	struct amba_device		*adev;
 	unsigned int			load_val;
-	unsigned int			timeout;
 };
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -99,7 +97,7 @@ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout)
 	spin_lock(&wdt->lock);
 	wdt->load_val = load;
 	/* roundup timeout to closest positive integer value */
-	wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
+	wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
 	spin_unlock(&wdt->lock);
 
 	return 0;
-- 
1.9.1

[PATCH 3.13 123/198] fs,userns: Change inode_capable to capable_wrt_inode_uidgid

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@amacapital.net>

commit 23adbe12ef7d3d4195e80800ab36b37bee28cd03 upstream.

The kernel has no concept of capabilities with respect to inodes; inodes
exist independently of namespaces.  For example, inode_capable(inode,
CAP_LINUX_IMMUTABLE) would be nonsense.

This patch changes inode_capable to check for uid and gid mappings and
renames it to capable_wrt_inode_uidgid, which should make it more
obvious what it does.

Fixes CVE-2014-4014.

Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Serge Hallyn <serge.hallyn@ubuntu.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/attr.c                  |  8 ++++----
 fs/inode.c                 | 10 +++++++---
 fs/namei.c                 | 11 ++++++-----
 fs/xfs/xfs_ioctl.c         |  2 +-
 include/linux/capability.h |  2 +-
 kernel/capability.c        | 20 ++++++++------------
 6 files changed, 27 insertions(+), 26 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c
index 5d4e59d..6530ced 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 	if ((ia_valid & ATTR_UID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	     !uid_eq(attr->ia_uid, inode->i_uid)) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 		/* Also check the setgid bit! */
 		if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
 				inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
@@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		umode_t mode = attr->ia_mode;
 
 		if (!in_group_p(inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
diff --git a/fs/inode.c b/fs/inode.c
index 4bcdad3..e846a32 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1840,14 +1840,18 @@ EXPORT_SYMBOL(inode_init_owner);
  * inode_owner_or_capable - check current task permissions to inode
  * @inode: inode being checked
  *
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
  */
 bool inode_owner_or_capable(const struct inode *inode)
 {
+	struct user_namespace *ns;
+
 	if (uid_eq(current_fsuid(), inode->i_uid))
 		return true;
-	if (inode_capable(inode, CAP_FOWNER))
+
+	ns = current_user_ns();
+	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
 		return true;
 	return false;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 3a1ea70a..01aca74 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -321,10 +321,11 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 		if (!(mask & MAY_WRITE))
-			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+			if (capable_wrt_inode_uidgid(inode,
+						     CAP_DAC_READ_SEARCH))
 				return 0;
 		return -EACCES;
 	}
@@ -334,7 +335,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 
 	/*
@@ -342,7 +343,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
 			return 0;
 
 	return -EACCES;
@@ -2359,7 +2360,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-	return !inode_capable(inode, CAP_FOWNER);
+	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
 }
 
 /*
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 33ad9a7..c7c2da8 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1245,7 +1245,7 @@ xfs_ioctl_setattr(
 		 * cleared upon successful return from chown()
 		 */
 		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
-		    !inode_capable(VFS_I(ip), CAP_FSETID))
+		    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
 			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
 
 		/*
diff --git a/include/linux/capability.h b/include/linux/capability.h
index a6ee1f9..84b13ad 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -210,7 +210,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 				      struct user_namespace *ns, int cap);
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
-extern bool inode_capable(const struct inode *inode, int cap);
+extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 
 /* audit system wants to get cap info from files as well */
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e66bf9..788653b 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -433,23 +433,19 @@ bool capable(int cap)
 EXPORT_SYMBOL(capable);
 
 /**
- * inode_capable - Check superior capability over inode
+ * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
  *
- * Return true if the current task has the given superior capability
- * targeted at it's own user namespace and that the given inode is owned
- * by the current user namespace or a child namespace.
- *
- * Currently we check to see if an inode is owned by the current
- * user namespace by seeing if the inode's owner maps into the
- * current user namespace.
- *
+ * Return true if the current task has the given capability targeted at
+ * its own user namespace and that the given inode's uid and gid are
+ * mapped into the current user namespace.
  */
-bool inode_capable(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
 {
 	struct user_namespace *ns = current_user_ns();
 
-	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
+		kgid_has_mapping(ns, inode->i_gid);
 }
-EXPORT_SYMBOL(inode_capable);
+EXPORT_SYMBOL(capable_wrt_inode_uidgid);
-- 
1.9.1

[PATCH 3.13 124/198] powerpc: Add AT_HWCAP2 to indicate V.CRYPTO category support

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

commit dd58a092c4202f2bd490adab7285b3ff77f8e467 upstream.

The Vector Crypto category instructions are supported by current POWER8
chips, advertise them to userspace using a specific bit to properly
differentiate with chips of the same architecture level that might not
have them.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/include/uapi/asm/cputable.h | 1 +
 arch/powerpc/kernel/cputable.c           | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 5b76579..de2c0e4 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -41,5 +41,6 @@
 #define PPC_FEATURE2_EBB		0x10000000
 #define PPC_FEATURE2_ISEL		0x08000000
 #define PPC_FEATURE2_TAR		0x04000000
+#define PPC_FEATURE2_VEC_CRYPTO		0x02000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 597d954..c5d3d02 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -105,7 +105,8 @@ extern void __restore_cpu_e6500(void);
 				 PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8	(PPC_FEATURE2_ARCH_2_07 | \
 				 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
-				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR)
+				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+				 PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T	(COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
 				 PPC_FEATURE_TRUE_LE | \
 				 PPC_FEATURE_HAS_ALTIVEC_COMP)
-- 
1.9.1

[PATCH 3.13 125/198] powerpc: Correct DSCR during TM context switch

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sam bobroff <sam.bobroff@au1.ibm.com>

commit 96d016108640bc2b7fb0ee800737f80923847294 upstream.

Correct the DSCR SPR becoming temporarily corrupted if a task is
context switched during a transaction.

The problem occurs while suspending the task and is caused by saving
the DSCR to thread.dscr after it has already been set to the CPU's
default value:

__switch_to() calls __switch_to_tm()
	which calls tm_reclaim_task()
	which calls tm_reclaim_thread()
	which calls tm_reclaim()
		where the DSCR is set to the CPU's default
__switch_to() calls _switch()
		where thread.dscr is set to the DSCR

When the task is resumed, it's transaction will be doomed (as usual)
and the DSCR SPR will be corrupted, although the checkpointed value
will be correct. Therefore the DSCR will be immediately corrected by
the transaction aborting, unless it has been suspended. In that case
the incorrect value can be seen by the task until it resumes the
transaction.

The fix is to treat the DSCR similarly to the TAR and save it early
in __switch_to().

A program exposing the problem is added to the kernel self tests as:
tools/testing/selftests/powerpc/tm/tm-resched-dscr.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/include/asm/switch_to.h               |  6 +-
 arch/powerpc/kernel/entry_64.S                     |  6 --
 arch/powerpc/kernel/process.c                      |  8 +-
 tools/testing/selftests/powerpc/Makefile           |  2 +-
 tools/testing/selftests/powerpc/tm/Makefile        | 15 ++++
 .../testing/selftests/powerpc/tm/tm-resched-dscr.c | 90 ++++++++++++++++++++++
 6 files changed, 114 insertions(+), 13 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/tm/Makefile
 create mode 100644 tools/testing/selftests/powerpc/tm/tm-resched-dscr.c

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index aace905..3b8d941 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -16,13 +16,15 @@ struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
 #ifdef CONFIG_PPC_BOOK3S_64
-static inline void save_tar(struct thread_struct *prev)
+static inline void save_early_sprs(struct thread_struct *prev)
 {
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		prev->tar = mfspr(SPRN_TAR);
+	if (cpu_has_feature(CPU_FTR_DSCR))
+		prev->dscr = mfspr(SPRN_DSCR);
 }
 #else
-static inline void save_tar(struct thread_struct *prev) {}
+static inline void save_early_sprs(struct thread_struct *prev) {}
 #endif
 
 extern void load_up_fpu(void);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index bbfb029..fb5ba6d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -432,12 +432,6 @@ BEGIN_FTR_SECTION
 	std	r24,THREAD_VRSAVE(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_PPC64
-BEGIN_FTR_SECTION
-	mfspr	r25,SPRN_DSCR
-	std	r25,THREAD_DSCR(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
-#endif
 	and.	r0,r0,r22
 	beq+	1f
 	andc	r22,r22,r0
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c274355..79e063b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -626,15 +626,15 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	WARN_ON(!irqs_disabled());
 
-	/* Back up the TAR across context switches.
+	/* Back up the TAR and DSCR across context switches.
 	 * Note that the TAR is not available for use in the kernel.  (To
 	 * provide this, the TAR should be backed up/restored on exception
 	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
 	 * pt_regs anyway (for debug).)
-	 * Save the TAR here before we do treclaim/trecheckpoint as these
-	 * will change the TAR.
+	 * Save the TAR and DSCR here before we do treclaim/trecheckpoint as
+	 * these will change them.
 	 */
-	save_tar(&prev->thread);
+	save_early_sprs(&prev->thread);
 
 	__switch_to_tm(prev);
 
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index bd24ae5..b99b500 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -13,7 +13,7 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CC CFLAGS
 
-TARGETS = pmu
+TARGETS = pmu tm
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
new file mode 100644
index 0000000..51267f4
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -0,0 +1,15 @@
+PROGS := tm-resched-dscr
+
+all: $(PROGS)
+
+$(PROGS):
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS) *.o
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
new file mode 100644
index 0000000..ee98e38
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -0,0 +1,90 @@
+/* Test context switching to see if the DSCR SPR is correctly preserved
+ * when within a transaction.
+ *
+ * Note: We assume that the DSCR has been left at the default value (0)
+ * for all CPUs.
+ *
+ * Method:
+ *
+ * Set a value into the DSCR.
+ *
+ * Start a transaction, and suspend it (*).
+ *
+ * Hard loop checking to see if the transaction has become doomed.
+ *
+ * Now that we *may* have been preempted, record the DSCR and TEXASR SPRS.
+ *
+ * If the abort was because of a context switch, check the DSCR value.
+ * Otherwise, try again.
+ *
+ * (*) If the transaction is not suspended we can't see the problem because
+ * the transaction abort handler will restore the DSCR to it's checkpointed
+ * value before we regain control.
+ */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <asm/tm.h>
+
+#define TBEGIN          ".long 0x7C00051D ;"
+#define TEND            ".long 0x7C00055D ;"
+#define TCHECK          ".long 0x7C00059C ;"
+#define TSUSPEND        ".long 0x7C0005DD ;"
+#define TRESUME         ".long 0x7C2005DD ;"
+#define SPRN_TEXASR     0x82
+#define SPRN_DSCR       0x03
+
+int main(void) {
+	uint64_t rv, dscr1 = 1, dscr2, texasr;
+
+	printf("Check DSCR TM context switch: ");
+	fflush(stdout);
+	for (;;) {
+		rv = 1;
+		asm __volatile__ (
+			/* set a known value into the DSCR */
+			"ld      3, %[dscr1];"
+			"mtspr   %[sprn_dscr], 3;"
+
+			/* start and suspend a transaction */
+			TBEGIN
+			"beq     1f;"
+			TSUSPEND
+
+			/* hard loop until the transaction becomes doomed */
+			"2: ;"
+			TCHECK
+			"bc      4, 0, 2b;"
+
+			/* record DSCR and TEXASR */
+			"mfspr   3, %[sprn_dscr];"
+			"std     3, %[dscr2];"
+			"mfspr   3, %[sprn_texasr];"
+			"std     3, %[texasr];"
+
+			TRESUME
+			TEND
+			"li      %[rv], 0;"
+			"1: ;"
+			: [rv]"=r"(rv), [dscr2]"=m"(dscr2), [texasr]"=m"(texasr)
+			: [dscr1]"m"(dscr1)
+			, [sprn_dscr]"i"(SPRN_DSCR), [sprn_texasr]"i"(SPRN_TEXASR)
+			: "memory", "r3"
+		);
+		assert(rv); /* make sure the transaction aborted */
+		if ((texasr >> 56) != TM_CAUSE_RESCHED) {
+			putchar('.');
+			fflush(stdout);
+			continue;
+		}
+		if (dscr2 != dscr1) {
+			printf(" FAIL\n");
+			exit(EXIT_FAILURE);
+		} else {
+			printf(" OK\n");
+			exit(EXIT_SUCCESS);
+		}
+	}
+}
-- 
1.9.1

[PATCH 3.13 126/198] powerpc: Don't setup CPUs with bad status

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Michael Neuling <mikey@neuling.org>

commit 59a53afe70fd530040bdc69581f03d880157f15a upstream.

OPAL will mark a CPU that is guarded as "bad" in the status property of the CPU
node.

Unfortunatley Linux doesn't check this property and will put the bad CPU in the
present map.  This has caused hangs on booting when we try to unsplit the core.

This patch checks the CPU is avaliable via this status property before putting
it in the present map.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Tested-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/kernel/setup-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index bc76cc6..486cc04 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -458,7 +458,7 @@ void __init smp_setup_cpu_maps(void)
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
 			    j, cpu, be32_to_cpu(intserv[j]));
-			set_cpu_present(cpu, true);
+			set_cpu_present(cpu, of_device_is_available(dn));
 			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
-- 
1.9.1

[PATCH 3.13 127/198] powerpc/perf: Ensure all EBB register state is cleared on fork()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Michael Ellerman <mpe@ellerman.id.au>

commit 3df48c981d5a9610e02e9270b1bc4274fb536710 upstream.

In commit 330a1eb "Core EBB support for 64-bit book3s" I messed up
clear_task_ebb(). It clears some but not all of the task's Event Based
Branch (EBB) registers when we duplicate a task struct.

That allows a child task to observe the EBBHR & EBBRR of its parent,
which it should not be able to do.

Fix it by clearing EBBHR & EBBRR.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/include/asm/switch_to.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 3b8d941..369f298 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -88,6 +88,8 @@ static inline void clear_task_ebb(struct task_struct *t)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
     /* EBB perf events are not inherited, so clear all EBB state. */
+    t->thread.ebbrr = 0;
+    t->thread.ebbhr = 0;
     t->thread.bescr = 0;
     t->thread.mmcr2 = 0;
     t->thread.mmcr0 = 0;
-- 
1.9.1

[PATCH 3.13 128/198] Target/iscsi: Fix sendtargets response pdu for iser transport

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg <sagig@mellanox.com>

commit 22c7aaa57e80853b4904a46c18f97db0036a3b97 upstream.

In case the transport is iser we should not include the
iscsi target info in the sendtargets text response pdu.
This causes sendtargets response to include the target
info twice.

Modify iscsit_build_sendtargets_response to filter
transport types that don't match.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Reported-by: Slava Shwartsman <valyushash@gmail.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/infiniband/ulp/isert/ib_isert.c |  2 +-
 drivers/target/iscsi/iscsi_target.c     | 14 ++++++++++----
 include/target/iscsi/iscsi_transport.h  |  3 ++-
 3 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index bde56da..5199f4e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2016,7 +2016,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	int rc;
 
 	isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc);
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND);
 	if (rc < 0)
 		return rc;
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index fe63a02..711dff4 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -3360,7 +3360,9 @@ static bool iscsit_check_inaddr_any(struct iscsi_np *np)
 
 #define SENDTARGETS_BUF_LIMIT 32768U
 
-static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
+static int
+iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
+				  enum iscsit_transport_type network_transport)
 {
 	char *payload = NULL;
 	struct iscsi_conn *conn = cmd->conn;
@@ -3437,6 +3439,9 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
 				struct iscsi_np *np = tpg_np->tpg_np;
 				bool inaddr_any = iscsit_check_inaddr_any(np);
 
+				if (np->np_network_transport != network_transport)
+					continue;
+
 				if (!target_name_printed) {
 					len = sprintf(buf, "TargetName=%s",
 						      tiqn->tiqn);
@@ -3490,11 +3495,12 @@ eob:
 
 int
 iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
-		      struct iscsi_text_rsp *hdr)
+		      struct iscsi_text_rsp *hdr,
+		      enum iscsit_transport_type network_transport)
 {
 	int text_length, padding;
 
-	text_length = iscsit_build_sendtargets_response(cmd);
+	text_length = iscsit_build_sendtargets_response(cmd, network_transport);
 	if (text_length < 0)
 		return text_length;
 
@@ -3532,7 +3538,7 @@ static int iscsit_send_text_rsp(
 	u32 tx_size = 0;
 	int text_length, iov_count = 0, rc;
 
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP);
 	if (rc < 0)
 		return rc;
 
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 361bd0f..78edd78 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -68,7 +68,8 @@ extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_tm_rsp *);
 extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *,
-				struct iscsi_text_rsp *);
+				struct iscsi_text_rsp *,
+				enum iscsit_transport_type);
 extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_reject *);
 extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *,
-- 
1.9.1

[PATCH 3.13 129/198] target: Report correct response length for some commands

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Roland Dreier <roland@purestorage.com>

commit 2426bd456a61407388b6e61fc5f98dbcbebc50e2 upstream.

When an initiator sends an allocation length bigger than what its
command consumes, the target should only return the actual response data
and set the residual length to the unused part of the allocation length.

Add a helper function that command handlers (INQUIRY, READ CAPACITY,
etc) can use to do this correctly, and use this code to get the correct
residual for commands that don't use the full initiator allocation in the
handlers for READ CAPACITY, READ CAPACITY(16), INQUIRY, MODE SENSE and
REPORT LUNS.

This addresses a handful of failures as reported by Christophe with
the Windows Certification Kit:

  http://permalink.gmane.org/gmane.linux.scsi.target.devel/6515

Signed-off-by: Roland Dreier <roland@purestorage.com>
Tested-by: Christophe Vu-Brugier <cvubrugier@yahoo.fr>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/target_core_sbc.c       |  4 ++--
 drivers/target/target_core_spc.c       |  9 ++++++---
 drivers/target/target_core_transport.c | 17 +++++++++++++++++
 include/target/target_core_backend.h   |  1 +
 4 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index baa8bf4..45d0bc6 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -80,7 +80,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8);
 	return 0;
 }
 
@@ -128,7 +128,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 32);
 	return 0;
 }
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 021c3f4..143e75b 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -646,6 +646,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 	unsigned char buf[SE_INQUIRY_BUF];
 	sense_reason_t ret;
 	int p;
+	int len = 0;
 
 	memset(buf, 0, SE_INQUIRY_BUF);
 
@@ -663,6 +664,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		}
 
 		ret = spc_emulate_inquiry_std(cmd, buf);
+		len = buf[4] + 5;
 		goto out;
 	}
 
@@ -670,6 +672,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		if (cdb[2] == evpd_handlers[p].page) {
 			buf[1] = cdb[2];
 			ret = evpd_handlers[p].emulate(cmd, buf);
+			len = get_unaligned_be16(&buf[2]) + 4;
 			goto out;
 		}
 	}
@@ -685,7 +688,7 @@ out:
 	}
 
 	if (!ret)
-		target_complete_cmd(cmd, GOOD);
+		target_complete_cmd_with_length(cmd, GOOD, len);
 	return ret;
 }
 
@@ -1003,7 +1006,7 @@ set_length:
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, length);
 	return 0;
 }
 
@@ -1180,7 +1183,7 @@ done:
 	buf[3] = (lun_count & 0xff);
 	transport_kunmap_data_sg(cmd);
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
 	return 0;
 }
 EXPORT_SYMBOL(spc_emulate_report_luns);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 31adaac..ea545f4 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -669,6 +669,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
+void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
+{
+	if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
+		if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+			cmd->residual_count += cmd->data_length - length;
+		} else {
+			cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
+			cmd->residual_count = cmd->data_length - length;
+		}
+
+		cmd->data_length = length;
+	}
+
+	target_complete_cmd(cmd, scsi_status);
+}
+EXPORT_SYMBOL(target_complete_cmd_with_length);
+
 static void target_add_to_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 39e0114..feacd9b 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -56,6 +56,7 @@ int	transport_subsystem_register(struct se_subsystem_api *);
 void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
+void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
 
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
-- 
1.9.1

[PATCH 3.13 130/198] dm thin: update discard_granularity to reflect the thin-pool blocksize

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lukas Czerner <lczerner@redhat.com>

commit 09869de57ed2728ae3c619803932a86cb0e2c4f8 upstream.

DM thinp already checks whether the discard_granularity of the data
device is a factor of the thin-pool block size.  But when using the
dm-thin-pool's discard passdown support, DM thinp was not selecting the
max of the underlying data device's discard_granularity and the
thin-pool's block size.

Update set_discard_limits() to set discard_granularity to the max of
these values.  This enables blkdev_issue_discard() to properly align the
discards that are sent to the DM thin device on a full block boundary.
As such each discard will now cover an entire DM thin-pool block and the
block will be reclaimed.

Reported-by: Zdenek Kabelac <zkabelac@redhat.com>
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/md/dm-thin.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e4cc196..f8c36d3 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2695,7 +2695,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
 	 */
 	if (pt->adjusted_pf.discard_passdown) {
 		data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
-		limits->discard_granularity = data_limits->discard_granularity;
+		limits->discard_granularity = max(data_limits->discard_granularity,
+						  pool->sectors_per_block << SECTOR_SHIFT);
 	} else
 		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 }
-- 
1.9.1

[PATCH 3.13 131/198] ALSA: compress: Cancel the optimization of compiler and fix the size of struct for all platform.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Wang, Xiaoming" <xiaoming.wang@intel.com>

commit 2bd0ae464a6cf7363bbf72c8545e0aa43caa57f0 upstream.

Cancel the optimization of compiler for struct snd_compr_avail
which size will be 0x1c in 32bit kernel while 0x20 in 64bit
kernel under the optimizer. That will make compaction between
32bit and 64bit. So add packed to fix the size of struct
snd_compr_avail to 0x1c for all platform.

Signed-off-by: Zhang Dongxing <dongxing.zhang@intel.com>
Signed-off-by: xiaoming wang <xiaoming.wang@intel.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/uapi/sound/compress_offload.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 5759810..21eed48 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -80,7 +80,7 @@ struct snd_compr_tstamp {
 struct snd_compr_avail {
 	__u64 avail;
 	struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed));
 
 enum snd_compr_direction {
 	SND_COMPRESS_PLAYBACK = 0,
-- 
1.9.1

[PATCH 3.13 132/198] hwmon: (ina2xx) Cast to s16 on shunt and current regs

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Fabio Baltieri <fabio.baltieri@gmail.com>

commit c0214f98943b1fe43f7be61b7782b0c8f0836f28 upstream.

All devices supported by ina2xx are bidirectional and report the
measured shunt voltage and power values as a signed 16 bit, but the
current driver implementation caches all registers as u16, leading
to an incorrect sign extension when reporting to userspace in
ina2xx_get_value().

This patch fixes the problem by casting the signed registers to s16.
Tested on an INA219.

Signed-off-by: Fabio Baltieri <fabio.baltieri@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/hwmon/ina2xx.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 93d26e8..bfd3f3e 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -148,7 +148,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 
 	switch (reg) {
 	case INA2XX_SHUNT_VOLTAGE:
-		val = DIV_ROUND_CLOSEST(data->regs[reg],
+		/* signed register */
+		val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
 					data->config->shunt_div);
 		break;
 	case INA2XX_BUS_VOLTAGE:
@@ -160,8 +161,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 		val = data->regs[reg] * data->config->power_lsb;
 		break;
 	case INA2XX_CURRENT:
-		/* LSB=1mA (selected). Is in mA */
-		val = data->regs[reg];
+		/* signed register, LSB=1mA (selected), in mA */
+		val = (s16)data->regs[reg];
 		break;
 	default:
 		/* programmer goofed */
-- 
1.9.1

[PATCH 3.13 133/198] evm: prohibit userspace writing 'security.evm' HMAC value

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mimi Zohar <zohar@linux.vnet.ibm.com>

commit 2fb1c9a4f2dbc2f0bd2431c7fa64d0b5483864e4 upstream.

Calculating the 'security.evm' HMAC value requires access to the
EVM encrypted key.  Only the kernel should have access to it.  This
patch prevents userspace tools(eg. setfattr, cp --preserve=xattr)
from setting/modifying the 'security.evm' HMAC value directly.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 security/integrity/evm/evm_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 336b3dd..3c5cbb9 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -285,12 +285,20 @@ out:
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0)
+	    && (xattr_data->type == EVM_XATTR_HMAC))
+		return -EPERM;
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }
-- 
1.9.1

[PATCH 3.13 134/198] ALSA: hda - Add quirk for external mic on Lifebook U904

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Henningsson <david.henningsson@canonical.com>

commit 2041d56464a067461d7cc21734a0f024587ed2ff upstream.

According to the bug reporter (Данило Шеган), the external mic
starts to work and has proper jack detection if only pin 0x19
is marked properly as an external headset mic.

AlsaInfo at https://bugs.launchpad.net/ubuntu/+source/pulseaudio/+bug/1328587/+attachment/4128991/+files/AlsaInfo.txt

BugLink: https://bugs.launchpad.net/bugs/1328587
Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d370e43..d44229b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3958,6 +3958,7 @@ enum {
 	ALC269_FIXUP_HEADSET_MIC,
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
+	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -4081,6 +4082,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_QUANTA_MUTE
 	},
+	[ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4442,6 +4450,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
-- 
1.9.1

[PATCH 3.13 135/198] ALSA: hda/realtek - Add more entry for enable HP mute led

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Kailang Yang <kailang@realtek.com>

commit c60666bd2224a32606364fdbc620e4cb9446a1d1 upstream.

More HP machine need mute led support.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 47 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d44229b..5724c7e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4428,6 +4428,53 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
+	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	/* ALC290 */
+	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
-- 
1.9.1

[PATCH 3.13 136/198] ALSA: hda/realtek - Add more entry for enable HP mute led

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Kailang Yang <kailang@realtek.com>

commit 8a02b164d4bfac108bfe37e98108bff1e062bd3d upstream.

More HP machine need mute led support.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5724c7e..6cbbd98 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4429,14 +4429,24 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -4475,6 +4485,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
-- 
1.9.1

[PATCH 3.13 137/198] ACPI / video: Add Dell Inspiron 5737 to the blacklist

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Edward Lin <yidi.lin@canonical.com>

commit 08a56226d84706d402372d891550e130ef5df9f0 upstream.

With win8 capabiltiy, the ACPI backlight control is broken.
The system also loses backlight setting when resuming from S3.

Add this model to the the ACPI video detect blacklist to make backlight
functionality work.

Although backlight functionality works via video.use_native_backlight=1,
this approach may be safer.

Signed-off-by: Edward Lin <yidi.lin@canonical.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Tim Gardner <tim.gardner@canonical.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/acpi/video_detect.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 84875fd..7245a5d 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -176,6 +176,14 @@ static struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Dell Inspiron 5737",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"),
+		},
+	},
 	{ },
 };
 
-- 
1.9.1

[PATCH 3.13 138/198] staging: iio: tsl2x7x_core: fix proximity treshold

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mario Schuknecht <mario.schuknecht@dresearch-fe.de>

commit c404618cd06dad771495fe1cf9d5a63b5664f65f upstream.

Consider high byte of proximity min and max treshold in function
'tsl2x7x_chip_on'. So far, the high byte was not set.

Signed-off-by: Mario Schuknecht <mario.schuknecht@dresearch-fe.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/staging/iio/light/tsl2x7x_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index 1880502..5b1f237 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -667,9 +667,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev)
 	chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
 			chip->tsl2x7x_settings.prox_pulse_count;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
-	chip->tsl2x7x_settings.prox_thres_low;
+			(chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
-			chip->tsl2x7x_settings.prox_thres_high;
+			(chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
 
 	/* and make sure we're not already on */
 	if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
-- 
1.9.1

[PATCH 3.13 139/198] iio: Fix endianness issue in ak8975_read_axis()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Meerwald <pmeerw@pmeerw.net>

commit 8ba42fb7b17649c9ab5b5e79d4e90370a0b4645e upstream.

i2c_smbus_read_word_data() does host endian conversion already,
no need for le16_to_cpu()

Signed-off-by: Peter Meerwald <pmeerw@pmeerw.net>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/iio/magnetometer/ak8975.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 0542354..053117c 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -352,8 +352,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 {
 	struct ak8975_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	u16 meas_reg;
-	s16 raw;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -401,16 +399,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 		dev_err(&client->dev, "Read axis data fails\n");
 		goto exit;
 	}
-	meas_reg = ret;
 
 	mutex_unlock(&data->lock);
 
-	/* Endian conversion of the measured values. */
-	raw = (s16) (le16_to_cpu(meas_reg));
-
 	/* Clamp to valid range. */
-	raw = clamp_t(s16, raw, -4096, 4095);
-	*val = raw;
+	*val = clamp_t(s16, ret, -4096, 4095);
 	return IIO_VAL_INT;
 
 exit:
-- 
1.9.1

[PATCH 3.13 140/198] rtmutex: Handle deadlock detection smarter

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <tglx@linutronix.de>

commit 3d5c9340d1949733eb37616abd15db36aef9a57c upstream.

Even in the case when deadlock detection is not requested by the
caller, we can detect deadlocks. Right now the code stops the lock
chain walk and keeps the waiter enqueued, even on itself. Silly not to
yell when such a scenario is detected and to keep the waiter enqueued.

Return -EDEADLK unconditionally and handle it at the call sites.

The futex calls return -EDEADLK. The non futex ones dequeue the
waiter, throw a warning and put the task into a schedule loop.

Tagged for stable as it makes the code more robust.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brad Mouring <bmouring@ni.com>
Link: http://lkml.kernel.org/r/20140605152801.836501969@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/locking/rtmutex-debug.h |  5 +++++
 kernel/locking/rtmutex.c       | 33 ++++++++++++++++++++++++++++-----
 kernel/locking/rtmutex.h       |  5 +++++
 3 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d5..ab29b6a 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 16d5356c..1029a85 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -196,7 +196,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
  retry:
 	/*
@@ -259,7 +259,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
@@ -433,7 +433,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 * which is wrong, as the other waiter is not in a deadlock
 	 * situation.
 	 */
-	if (detect_deadlock && owner == task)
+	if (owner == task)
 		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -650,6 +650,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
@@ -687,8 +707,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -996,7 +1018,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd0..f6a1f3c 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -24,3 +24,8 @@
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
 #define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
-- 
1.9.1

[PATCH 3.13 141/198] rtmutex: Detect changes in the pi lock chain

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <tglx@linutronix.de>

commit 82084984383babe728e6e3c9a8e5c46278091315 upstream.

When we walk the lock chain, we drop all locks after each step. So the
lock chain can change under us before we reacquire the locks. That's
harmless in principle as we just follow the wrong lock path. But it
can lead to a false positive in the dead lock detection logic:

T0 holds L0
T0 blocks on L1 held by T1
T1 blocks on L2 held by T2
T2 blocks on L3 held by T3
T4 blocks on L4 held by T4

Now we walk the chain

lock T1 -> lock L2 -> adjust L2 -> unlock T1 ->
     lock T2 ->  adjust T2 ->  drop locks

T2 times out and blocks on L0

Now we continue:

lock T2 -> lock L0 -> deadlock detected, but it's not a deadlock at all.

Brad tried to work around that in the deadlock detection logic itself,
but the more I looked at it the less I liked it, because it's crystal
ball magic after the fact.

We actually can detect a chain change very simple:

lock T1 -> lock L2 -> adjust L2 -> unlock T1 -> lock T2 -> adjust T2 ->

     next_lock = T2->pi_blocked_on->lock;

drop locks

T2 times out and blocks on L0

Now we continue:

lock T2 ->

     if (next_lock != T2->pi_blocked_on->lock)
     	   return;

So if we detect that T2 is now blocked on a different lock we stop the
chain walk. That's also correct in the following scenario:

lock T1 -> lock L2 -> adjust L2 -> unlock T1 -> lock T2 -> adjust T2 ->

     next_lock = T2->pi_blocked_on->lock;

drop locks

T3 times out and drops L3
T2 acquires L3 and blocks on L4 now

Now we continue:

lock T2 ->

     if (next_lock != T2->pi_blocked_on->lock)
     	   return;

We don't have to follow up the chain at that point, because T2
propagated our priority up to T4 already.

[ Folded a cleanup patch from peterz ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Brad Mouring <bmouring@ni.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140605152801.930031935@linutronix.de
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/locking/rtmutex.c | 95 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 71 insertions(+), 24 deletions(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 1029a85..ff24a43 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -142,27 +142,36 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
  *
- * @task: the task owning the mutex (owner) for which a chain walk is probably
- *	  needed
+ * @task:	the task owning the mutex (owner) for which a chain walk is
+ *		probably needed
  * @deadlock_detect: do we have to carry out deadlock detection?
- * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck
- * 	       things for a task that has just got its priority adjusted, and
- *	       is waiting on a mutex)
+ * @orig_lock:	the mutex (can be NULL if we are walking the chain to recheck
+ *		things for a task that has just got its priority adjusted, and
+ *		is waiting on a mutex)
+ * @next_lock:	the mutex on which the owner of @orig_lock was blocked before
+ *		we dropped its pi_lock. Is never dereferenced, only used for
+ *		comparison to detect lock chain changes.
  * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
- *		 its priority to the mutex owner (can be NULL in the case
- *		 depicted above or if the top waiter is gone away and we are
- *		 actually deboosting the owner)
- * @top_task: the current top waiter
+ *		its priority to the mutex owner (can be NULL in the case
+ *		depicted above or if the top waiter is gone away and we are
+ *		actually deboosting the owner)
+ * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
@@ -221,6 +230,18 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
@@ -306,11 +327,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
+	/*
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -421,8 +457,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
 
 	/*
 	 * Early deadlock detection. We really don't want the task to
@@ -455,20 +492,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
 		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
 		chain_walk = 1;
+	}
 
-	if (!chain_walk)
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
+
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -480,8 +525,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -530,8 +575,8 @@ static void remove_waiter(struct rt_mutex *lock,
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
@@ -555,15 +600,15 @@ static void remove_waiter(struct rt_mutex *lock,
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+		/* Store the lock on which owner is blocked or NULL */
+		next_lock = task_blocked_on_lock(owner);
 
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
-	if (!chain_walk)
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -571,7 +616,7 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -584,6 +629,7 @@ static void remove_waiter(struct rt_mutex *lock,
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -593,12 +639,13 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
 }
 
 /**
-- 
1.9.1

[PATCH 3.13 142/198] drm/i915: Disable FBC by default also on Haswell and later

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chris Wilson <chris@chris-wilson.co.uk>

commit 0368920e51ae0cded0eb518c340a4dd17764d461 upstream.

It causes black screen on bootup and is approximately 100x slower than
running with FBC disabled, so the GPU runs at a high frequency for much
longer - completely contrary to the power saving claims. It also still
has mutex deadlocks in multi-head scenarios, which can lead to a
system/X lockup. These bugs were known before FBC was enabled by default
on Haswell and still have not been fixed.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=79716
Reported-and-tested-by: Jon Kristensen <info@jonkri.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[Jani: update subject to reflect the actual change]
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
[ kamal: backport to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4128d0e..1218c44 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -498,8 +498,7 @@ void intel_update_fbc(struct drm_device *dev)
 	obj = intel_fb->obj;
 	adjusted_mode = &intel_crtc->config.adjusted_mode;
 
-	if (i915_enable_fbc < 0 &&
-	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
+	if (i915_enable_fbc < 0) {
 		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
 			DRM_DEBUG_KMS("disabled per chip default\n");
 		goto out_disable;
-- 
1.9.1

[PATCH 3.13 143/198] drm/i915: Avoid div-by-zero when pixel_multiplier is zero

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>

commit 2b85886a5457f5c5dbcd32edbd4e6bba0f4e8678 upstream.

On certain platforms pixel_multiplier is read out in
.get_pipe_config(), but it also gets used to calculate the
pixel clock in intel_sdvo_get_config(). If the pipe is disable
but some SDVO outputs are active, we may end up dividing by zero
in intel_sdvo_get_config().

To avoid the problem simply check for zero pixel_multiplier and skip
the division. Another attempt at fixing this involved populating
pixel_multiplier to 1 even for disabled pipes, but that triggered a
WARN because SDVO_CMD_GET_CLOCK_RATE_MULT command failed and thus
encoder_pixel_multiplier was left at zero and didn't match
pipe_config->pixel_multiplier.

The "divide by pixel_multiplier" operation got introduced here:
 commit 18442d08786472c63a0a80c27f92b033dffc26de
 Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
 Date:   Fri Sep 13 16:00:08 2013 +0300

    drm/i915: Fix port_clock and adjusted_mode.clock readout all over

and it has caused a regression on certain machines since they would
hit the div-by-zero during resume.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=76520
Tested-by: Tim Richardson <tim@tim-richardson.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/i915/intel_sdvo.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index a583e8f..9528239 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1364,7 +1364,9 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 			 >> SDVO_PORT_MULTIPLY_SHIFT) + 1;
 	}
 
-	dotclock = pipe_config->port_clock / pipe_config->pixel_multiplier;
+	dotclock = pipe_config->port_clock;
+	if (pipe_config->pixel_multiplier)
+		dotclock /= pipe_config->pixel_multiplier;
 
 	if (HAS_PCH_SPLIT(dev))
 		ironlake_check_encoder_dotclock(pipe_config, dotclock);
-- 
1.9.1

[PATCH 3.13 144/198] drm/i915: Reorder semaphore deadlock check

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chris Wilson <chris@chris-wilson.co.uk>

commit 4be173813e57c7298103a83155c2391b5b167b4c upstream.

If a semaphore is waiting on another ring, which in turn happens to be
waiting on the first ring, but that second semaphore has been signalled,
we will be able to kick the second ring and so can treat the first ring
as a valid WAIT and not as HUNG.

v2: Be paranoid and cap the potential recursion depth whilst visiting
the semaphore signallers. (Mika)

References: https://bugs.freedesktop.org/show_bug.cgi?id=54226
References: https://bugs.freedesktop.org/show_bug.cgi?id=75502
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/i915/i915_irq.c         | 18 ++++++++++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4ad5cc5..2093c72 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2394,10 +2394,14 @@ static int semaphore_passed(struct intel_ring_buffer *ring)
 	struct intel_ring_buffer *signaller;
 	u32 seqno, ctl;
 
-	ring->hangcheck.deadlock = true;
+	ring->hangcheck.deadlock++;
 
 	signaller = semaphore_waits_for(ring, &seqno);
-	if (signaller == NULL || signaller->hangcheck.deadlock)
+	if (signaller == NULL)
+		return -1;
+
+	/* Prevent pathological recursion due to driver bugs */
+	if (signaller->hangcheck.deadlock >= I915_NUM_RINGS)
 		return -1;
 
 	/* cursory check for an unkickable deadlock */
@@ -2405,7 +2409,13 @@ static int semaphore_passed(struct intel_ring_buffer *ring)
 	if (ctl & RING_WAIT_SEMAPHORE && semaphore_passed(signaller) < 0)
 		return -1;
 
-	return i915_seqno_passed(signaller->get_seqno(signaller, false), seqno);
+	if (i915_seqno_passed(signaller->get_seqno(signaller, false), seqno))
+		return 1;
+
+	if (signaller->hangcheck.deadlock)
+		return -1;
+
+	return 0;
 }
 
 static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
@@ -2414,7 +2424,7 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
-		ring->hangcheck.deadlock = false;
+		ring->hangcheck.deadlock = 0;
 }
 
 static enum intel_ring_hangcheck_action
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0b243ce..78b875a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -42,11 +42,11 @@ enum intel_ring_hangcheck_action {
 };
 
 struct intel_ring_hangcheck {
-	bool deadlock;
 	u32 seqno;
 	u32 acthd;
 	int score;
 	enum intel_ring_hangcheck_action action;
+	int deadlock;
 };
 
 struct  intel_ring_buffer {
-- 
1.9.1

[PATCH 3.13 145/198] iio: adc: at91: signedness bug in at91_adc_get_trigger_value_by_name()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Carpenter <dan.carpenter@oracle.com>

commit 4f3bcd878f1d3c730fe00f619b7260c6125d49eb upstream.

at91_adc_get_trigger_value_by_name() was returning -ENOMEM truncated to
a positive u8 and that doesn't work.  I've changed it to int and
refactored it to preserve the error code.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Tested-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/iio/adc/at91_adc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index bbba014..e6bf77d 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -322,12 +322,11 @@ static int at91_adc_channel_init(struct iio_dev *idev)
 	return idev->num_channels;
 }
 
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 					     struct at91_adc_trigger *triggers,
 					     const char *trigger_name)
 {
 	struct at91_adc_state *st = iio_priv(idev);
-	u8 value = 0;
 	int i;
 
 	for (i = 0; i < st->trigger_number; i++) {
@@ -340,15 +339,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 			return -ENOMEM;
 
 		if (strcmp(trigger_name, name) == 0) {
-			value = triggers[i].value;
 			kfree(name);
-			break;
+			if (triggers[i].value == 0)
+				return -EINVAL;
+			return triggers[i].value;
 		}
 
 		kfree(name);
 	}
 
-	return value;
+	return -EINVAL;
 }
 
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -358,14 +358,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	struct iio_buffer *buffer = idev->buffer;
 	struct at91_adc_reg_desc *reg = st->registers;
 	u32 status = at91_adc_readl(st, reg->trigger_register);
-	u8 value;
+	int value;
 	u8 bit;
 
 	value = at91_adc_get_trigger_value_by_name(idev,
 						   st->trigger_list,
 						   idev->trig->name);
-	if (value == 0)
-		return -EINVAL;
+	if (value < 0)
+		return value;
 
 	if (state) {
 		st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
-- 
1.9.1

[PATCH 3.13 146/198] rtmutex: Plug slow unlock race

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <tglx@linutronix.de>

commit 27e35715df54cbc4f2d044f681802ae30479e7fb upstream.

When the rtmutex fast path is enabled the slow unlock function can
create the following situation:

spin_lock(foo->m->wait_lock);
foo->m->owner = NULL;
	    			rt_mutex_lock(foo->m); <-- fast path
				free = atomic_dec_and_test(foo->refcnt);
				rt_mutex_unlock(foo->m); <-- fast path
				if (free)
				   kfree(foo);

spin_unlock(foo->m->wait_lock); <--- Use after free.

Plug the race by changing the slow unlock to the following scheme:

     while (!rt_mutex_has_waiters(m)) {
     	    /* Clear the waiters bit in m->owner */
	    clear_rt_mutex_waiters(m);
      	    owner = rt_mutex_owner(m);
      	    spin_unlock(m->wait_lock);
      	    if (cmpxchg(m->owner, owner, 0) == owner)
      	       return;
      	    spin_lock(m->wait_lock);
     }

So in case of a new waiter incoming while the owner tries the slow
path unlock we have two situations:

 unlock(wait_lock);
					lock(wait_lock);
 cmpxchg(p, owner, 0) == owner
 	    	   			mark_rt_mutex_waiters(lock);
	 				acquire(lock);

Or:

 unlock(wait_lock);
					lock(wait_lock);
	 				mark_rt_mutex_waiters(lock);
 cmpxchg(p, owner, 0) != owner
					enqueue_waiter();
					unlock(wait_lock);
 lock(wait_lock);
 wakeup_next waiter();
 unlock(wait_lock);
					lock(wait_lock);
					acquire(lock);

If the fast path is disabled, then the simple

   m->owner = NULL;
   unlock(m->wait_lock);

is sufficient as all access to m->owner is serialized via
m->wait_lock;

Also document and clarify the wakeup_next_waiter function as suggested
by Oleg Nesterov.

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140611183852.937945560@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/locking/rtmutex.c | 115 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 109 insertions(+), 6 deletions(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index ff24a43..51a8334 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -82,6 +82,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -89,6 +130,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 /*
@@ -536,7 +588,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -557,10 +610,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 */
 	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -813,12 +879,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
-- 
1.9.1

[PATCH 3.13 147/198] Revert "offb: Add palette hack for little endian"

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

commit 68986c9f0f4552c34c248501eb0c690553866d6e upstream.

This reverts commit e1edf18b20076da83dd231dbd2146cbbc31c0b14.

This patch was a misguided attempt at fixing offb for LE ppc64
kernels on BE qemu but is just wrong ... it breaks real LE/LE
setups, LE with real HW, and existing mixed endian systems
that did the fight thing with the appropriate device-tree
property. Bad reviewing on my part, sorry.

The right fix is to either make qemu change its endian when
the guest changes endian (working on that) or to use the
existing foreign endian support.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/video/offb.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/video/offb.c b/drivers/video/offb.c
index 7d44d66..43a0a52 100644
--- a/drivers/video/offb.c
+++ b/drivers/video/offb.c
@@ -91,15 +91,6 @@ extern boot_infos_t *boot_infos;
 #define AVIVO_DC_LUTB_WHITE_OFFSET_GREEN        0x6cd4
 #define AVIVO_DC_LUTB_WHITE_OFFSET_RED          0x6cd8
 
-#define FB_RIGHT_POS(p, bpp)         (fb_be_math(p) ? 0 : (32 - (bpp)))
-
-static inline u32 offb_cmap_byteswap(struct fb_info *info, u32 value)
-{
-	u32 bpp = info->var.bits_per_pixel;
-
-	return cpu_to_be32(value) >> FB_RIGHT_POS(info, bpp);
-}
-
     /*
      *  Set a single color register. The values supplied are already
      *  rounded down to the hardware's capabilities (according to the
@@ -129,7 +120,7 @@ static int offb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 			mask <<= info->var.transp.offset;
 			value |= mask;
 		}
-		pal[regno] = offb_cmap_byteswap(info, value);
+		pal[regno] = value;
 		return 0;
 	}
 
-- 
1.9.1

[PATCH 3.13 148/198] ACPI / ia64 / sba_iommu: Restore the working initialization ordering

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>

commit 12e27b115472ad0f3b142ddf59d3998305984408 upstream.

Commit 66345d5f79fc (ACPI / ia64 / sba_iommu: Use ACPI scan handler
for device discovery) changed the ordering of SBA (System Bus Adapter)
IOMMU initialization with respect to the PCI host bridge initialization
which broke things inadvertently, because the SBA IOMMU initialization
code has to run after the PCI host bridge has been initialized.

Fix that by reworking the SBA IOMMU ACPI scan handler so that it
claims the discovered matching ACPI device objects without attempting
to initialize anything and move the entire SBA IOMMU initialization
to sba_init() that runs after the PCI bus has been enumerated.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=76691
Fixes: 66345d5f79fc (ACPI / ia64 / sba_iommu: Use ACPI scan handler for device discovery)
Reported-and-tested-by: Émeric Maschino <emeric.maschino@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/ia64/hp/common/sba_iommu.c | 64 ++++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 27 deletions(-)

diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 4c530a8..676c8a0 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -242,7 +242,7 @@ struct ioc {
 	struct pci_dev	*sac_only_dev;
 };
 
-static struct ioc *ioc_list;
+static struct ioc *ioc_list, *ioc_found;
 static int reserve_sba_gart = 1;
 
 static SBA_INLINE void sba_mark_invalid(struct ioc *, dma_addr_t, size_t);
@@ -1807,20 +1807,13 @@ static struct ioc_iommu ioc_iommu_info[] __initdata = {
 	{ SX2000_IOC_ID, "sx2000", NULL },
 };
 
-static struct ioc * __init
-ioc_init(unsigned long hpa, void *handle)
+static void ioc_init(unsigned long hpa, struct ioc *ioc)
 {
-	struct ioc *ioc;
 	struct ioc_iommu *info;
 
-	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
-	if (!ioc)
-		return NULL;
-
 	ioc->next = ioc_list;
 	ioc_list = ioc;
 
-	ioc->handle = handle;
 	ioc->ioc_hpa = ioremap(hpa, 0x1000);
 
 	ioc->func_id = READ_REG(ioc->ioc_hpa + IOC_FUNC_ID);
@@ -1861,8 +1854,6 @@ ioc_init(unsigned long hpa, void *handle)
 		"%s %d.%d HPA 0x%lx IOVA space %dMb at 0x%lx\n",
 		ioc->name, (ioc->rev >> 4) & 0xF, ioc->rev & 0xF,
 		hpa, ioc->iov_size >> 20, ioc->ibase);
-
-	return ioc;
 }
 
 
@@ -2041,22 +2032,21 @@ sba_map_ioc_to_node(struct ioc *ioc, acpi_handle handle)
 #define sba_map_ioc_to_node(ioc, handle)
 #endif
 
-static int __init
-acpi_sba_ioc_add(struct acpi_device *device,
-		 const struct acpi_device_id *not_used)
+static void acpi_sba_ioc_add(struct ioc *ioc)
 {
-	struct ioc *ioc;
+	acpi_handle handle = ioc->handle;
 	acpi_status status;
 	u64 hpa, length;
 	struct acpi_device_info *adi;
 
-	status = hp_acpi_csr_space(device->handle, &hpa, &length);
+	ioc_found = ioc->next;
+	status = hp_acpi_csr_space(handle, &hpa, &length);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
-	status = acpi_get_object_info(device->handle, &adi);
+	status = acpi_get_object_info(handle, &adi);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
 	/*
 	 * For HWP0001, only SBA appears in ACPI namespace.  It encloses the PCI
@@ -2077,13 +2067,13 @@ acpi_sba_ioc_add(struct acpi_device *device,
 	if (!iovp_shift)
 		iovp_shift = 12;
 
-	ioc = ioc_init(hpa, device->handle);
-	if (!ioc)
-		return 1;
-
+	ioc_init(hpa, ioc);
 	/* setup NUMA node association */
-	sba_map_ioc_to_node(ioc, device->handle);
-	return 0;
+	sba_map_ioc_to_node(ioc, handle);
+	return;
+
+ err:
+	kfree(ioc);
 }
 
 static const struct acpi_device_id hp_ioc_iommu_device_ids[] = {
@@ -2091,9 +2081,26 @@ static const struct acpi_device_id hp_ioc_iommu_device_ids[] = {
 	{"HWP0004", 0},
 	{"", 0},
 };
+
+static int acpi_sba_ioc_attach(struct acpi_device *device,
+			       const struct acpi_device_id *not_used)
+{
+	struct ioc *ioc;
+
+	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
+	if (!ioc)
+		return -ENOMEM;
+
+	ioc->next = ioc_found;
+	ioc_found = ioc;
+	ioc->handle = device->handle;
+	return 1;
+}
+
+
 static struct acpi_scan_handler acpi_sba_ioc_handler = {
 	.ids	= hp_ioc_iommu_device_ids,
-	.attach	= acpi_sba_ioc_add,
+	.attach	= acpi_sba_ioc_attach,
 };
 
 static int __init acpi_sba_ioc_init_acpi(void)
@@ -2128,9 +2135,12 @@ sba_init(void)
 #endif
 
 	/*
-	 * ioc_list should be populated by the acpi_sba_ioc_handler's .attach()
+	 * ioc_found should be populated by the acpi_sba_ioc_handler's .attach()
 	 * routine, but that only happens if acpi_scan_init() has already run.
 	 */
+	while (ioc_found)
+		acpi_sba_ioc_add(ioc_found);
+
 	if (!ioc_list) {
 #ifdef CONFIG_IA64_GENERIC
 		/*
-- 
1.9.1

[PATCH 3.13 149/198] epoll: fix use-after-free in eventpoll_release_file

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Konstantin Khlebnikov <koct9i@gmail.com>

commit ebe06187bf2aec10d537ce4595e416035367d703 upstream.

This fixes use-after-free of epi->fllink.next inside list loop macro.
This loop actually releases elements in the body.  The list is
rcu-protected but here we cannot hold rcu_read_lock because we need to
lock mutex inside.

The obvious solution is to use list_for_each_entry_safe().  RCU-ness
isn't essential because nobody can change this list under us, it's final
fput for this file.

The bug was introduced by ae10b2b4eb01 ("epoll: optimize EPOLL_CTL_DEL
using rcu")

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Reported-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Jason Baron <jbaron@akamai.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/eventpoll.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index af90312..ead0046 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = {
 void eventpoll_release_file(struct file *file)
 {
 	struct eventpoll *ep;
-	struct epitem *epi;
+	struct epitem *epi, *next;
 
 	/*
 	 * We don't want to get "file->f_lock" because it is not
@@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file)
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
-- 
1.9.1

[PATCH 3.13 150/198] drm/nouveau/kms: reference vblank for crtc during pageflip.

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mario Kleiner <mario.kleiner.de@gmail.com>

commit ba124a41058b300a5464206d2d33803cc3dc82ec upstream.

Need to drm_vblank_get/put() the crtc involved in a
pending pageflip, or we might not get vblank irqs and
updates of vblank counts and timestamps for pageflip
events and flip completion.

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/nouveau/nouveau_display.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index cdaee13..91999bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -630,6 +630,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		  fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y,
 		  new_bo->bo.offset };
 
+	/* Keep vblanks on during flip, for the target crtc of this flip */
+	drm_vblank_get(dev, nouveau_crtc(crtc)->index);
+
 	/* Emit a page flip */
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nv50_display_flip_next(crtc, fb, chan, swap_interval);
@@ -673,6 +676,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return 0;
 
 fail_unreserve:
+	drm_vblank_put(dev, nouveau_crtc(crtc)->index);
 	ttm_bo_unreserve(&old_bo->bo);
 fail_unpin:
 	mutex_unlock(&chan->cli->mutex);
@@ -711,6 +715,9 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 		drm_send_vblank_event(dev, crtcid, s->event);
 	}
 
+	/* Give up ownership of vblank for page-flipped crtc */
+	drm_vblank_put(dev, s->crtc);
+
 	list_del(&s->head);
 	if (ps)
 		*ps = *s;
-- 
1.9.1

[PATCH 3.13 151/198] ARM: mvebu: DT: fix OpenBlocks AX3-4 RAM size

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jason Cooper <jason@lakedaemon.net>

commit e47043aea3853a74a9aa5726a1faa916d7462ab7 upstream.

The OpenBlocks AX3-4 has a non-DT bootloader.  It also comes with 1GB of
soldered on RAM, and a DIMM slot for expansion.

Unfortunately, atags_to_fdt() doesn't work in big-endian mode, so we see
the following failure when attempting to boot a big-endian kernel:

  686 slab pages
  17 pages shared
  0 pages swap cached
  [ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name
  Kernel panic - not syncing: Out of memory and no killable processes...

  CPU: 1 PID: 351 Comm: kworker/u4:0 Not tainted 3.15.0-rc8-next-20140603 #1
  [<c0215a54>] (unwind_backtrace) from [<c021160c>] (show_stack+0x10/0x14)
  [<c021160c>] (show_stack) from [<c0802500>] (dump_stack+0x78/0x94)
  [<c0802500>] (dump_stack) from [<c0800068>] (panic+0x90/0x21c)
  [<c0800068>] (panic) from [<c02b5704>] (out_of_memory+0x320/0x340)
  [<c02b5704>] (out_of_memory) from [<c02b93a0>] (__alloc_pages_nodemask+0x874/0x930)
  [<c02b93a0>] (__alloc_pages_nodemask) from [<c02d446c>] (handle_mm_fault+0x744/0x96c)
  [<c02d446c>] (handle_mm_fault) from [<c02cf250>] (__get_user_pages+0xd0/0x4c0)
  [<c02cf250>] (__get_user_pages) from [<c02f3598>] (get_arg_page+0x54/0xbc)
  [<c02f3598>] (get_arg_page) from [<c02f3878>] (copy_strings+0x278/0x29c)
  [<c02f3878>] (copy_strings) from [<c02f38bc>] (copy_strings_kernel+0x20/0x28)
  [<c02f38bc>] (copy_strings_kernel) from [<c02f4f1c>] (do_execve+0x3a8/0x4c8)
  [<c02f4f1c>] (do_execve) from [<c025ac10>] (____call_usermodehelper+0x15c/0x194)
  [<c025ac10>] (____call_usermodehelper) from [<c020e9b8>] (ret_from_fork+0x14/0x3c)
  CPU0: stopping
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.15.0-rc8-next-20140603 #1
  [<c0215a54>] (unwind_backtrace) from [<c021160c>] (show_stack+0x10/0x14)
  [<c021160c>] (show_stack) from [<c0802500>] (dump_stack+0x78/0x94)
  [<c0802500>] (dump_stack) from [<c021429c>] (handle_IPI+0x138/0x174)
  [<c021429c>] (handle_IPI) from [<c02087f0>] (armada_370_xp_handle_irq+0xb0/0xcc)
  [<c02087f0>] (armada_370_xp_handle_irq) from [<c0212100>] (__irq_svc+0x40/0x50)
  Exception stack(0xc0b6bf68 to 0xc0b6bfb0)
  bf60:                   e9fad598 00000000 00f509a3 00000000 c0b6a000 c0b724c4
  bf80: c0b72458 c0b6a000 00000000 00000000 c0b66da0 c0b6a000 00000000 c0b6bfb0
  bfa0: c027bb94 c027bb24 60000313 ffffffff
  [<c0212100>] (__irq_svc) from [<c027bb24>] (cpu_startup_entry+0x54/0x214)
  [<c027bb24>] (cpu_startup_entry) from [<c0ac5b30>] (start_kernel+0x318/0x37c)
  [<c0ac5b30>] (start_kernel) from [<00208078>] (0x208078)
  ---[ end Kernel panic - not syncing: Out of memory and no killable processes...

A similar failure will also occur if ARM_ATAG_DTB_COMPAT isn't selected.

Fix this by setting a sane default (1 GB) in the dts file.

Signed-off-by: Jason Cooper <jason@lakedaemon.net>
Tested-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index d6cce8a..d11b1b5 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -23,7 +23,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0 0x00000000 0 0xC0000000>; /* 3 GB */
+		reg = <0 0x00000000 0 0x40000000>; /* 1 GB soldered on */
 	};
 
 	soc {
-- 
1.9.1

[PATCH 3.13 152/198] USB: EHCI: avoid BIOS handover on the HASEE E200

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alan Stern <stern@rowland.harvard.edu>

commit b0a50e92bda3c4aeb8017d4e6c6e92146ebd5c9b upstream.

Leandro Liptak reports that his HASEE E200 computer hangs when we ask
the BIOS to hand over control of the EHCI host controller.  This
definitely sounds like a bug in the BIOS, but at the moment there is
no way to fix it.

This patch works around the problem by avoiding the handoff whenever
the motherboard and BIOS version match those of Leandro's computer.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Leandro Liptak <leandroliptak@gmail.com>
Tested-by: Leandro Liptak <leandroliptak@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/usb/host/pci-quirks.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index dfbdd3a..af93c8c 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -657,6 +657,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
 		},
 	},
+	{
+		/* HASEE E200 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+			DMI_MATCH(DMI_BOARD_NAME, "E210"),
+			DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+		},
+	},
 	{ }
 };
 
@@ -666,9 +674,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev,
 {
 	int try_handoff = 1, tried_handoff = 0;
 
-	/* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
-	 * the handoff on its unused controller.  Skip it. */
-	if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+	/*
+	 * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+	 * the handoff on its unused controller.  Skip it.
+	 *
+	 * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+	 */
+	if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+			pdev->device == 0x27cc)) {
 		if (dmi_check_system(ehci_dmi_nohandoff_table))
 			try_handoff = 0;
 	}
-- 
1.9.1

[PATCH 3.13 153/198] arm64: Bug fix in stack alignment exception

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: ChiaHao <andy.jhshiu@gmail.com>

commit 3906c2b53cd23c2ae03e6ce41432c8e7f0a3cbbb upstream.

The value of ESR has been stored into x1, and should be directly pass to
do_sp_pc_abort function, "MOV x1, x25" is an extra operation and do_sp_pc_abort
will get the wrong value of ESR.

Signed-off-by: ChiaHao <andy.jhshiu@gmail.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm64/kernel/entry.S | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 4d2c6f3..013baa0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -275,7 +275,6 @@ el1_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:
-- 
1.9.1

[PATCH 3.13 154/198] arm64: ptrace: change fs when passing kernel pointer to regset code

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Will Deacon <will.deacon@arm.com>

commit c168870704bcde6bb63d05f7882b620dd3985a46 upstream.

Our compat PTRACE_POKEUSR implementation simply passes the user data to
regset_copy_from_user after some simple range checking. Unfortunately,
the data in question has already been copied to the kernel stack by this
point, so the subsequent access_ok check fails and the ptrace request
returns -EFAULT. This causes problems tracing fork() with older versions
of strace.

This patch briefly changes the fs to KERNEL_DS, so that the access_ok
check passes even with a kernel address.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm64/kernel/ptrace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6a8928b..bf288e4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -821,6 +821,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 				    compat_ulong_t val)
 {
 	int ret;
+	mm_segment_t old_fs = get_fs();
 
 	if (off & 3 || off >= COMPAT_USER_SZ)
 		return -EIO;
@@ -828,10 +829,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 	if (off >= sizeof(compat_elf_gregset_t))
 		return 0;
 
+	set_fs(KERNEL_DS);
 	ret = copy_regset_from_user(tsk, &user_aarch32_view,
 				    REGSET_COMPAT_GPR, off,
 				    sizeof(compat_ulong_t),
 				    &val);
+	set_fs(old_fs);
+
 	return ret;
 }
 
-- 
1.9.1

[PATCH 3.13 155/198] arm64: uid16: fix __kernel_old_{gid,uid}_t definitions

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Will Deacon <will.deacon@arm.com>

commit 34c65c43f1518bf85f93526ad373adc6a683b4c5 upstream.

Whilst native arm64 applications don't have the 16-bit UID/GID syscalls
wired up, compat tasks can still access them. The 16-bit wrappers for
these syscalls use __kernel_old_uid_t and __kernel_old_gid_t, which must
be 16-bit data types to maintain compatibility with the 16-bit UIDs used
by compat applications.

This patch defines 16-bit __kernel_old_{gid,uid}_t types for arm64
instead of using the 32-bit types provided by asm-generic.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm64/include/asm/Kbuild             |  1 -
 arch/arm64/include/uapi/asm/posix_types.h | 10 ++++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)
 create mode 100644 arch/arm64/include/uapi/asm/posix_types.h

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 519f89f..0d41221 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -28,7 +28,6 @@ generic-y += mutex.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += poll.h
-generic-y += posix_types.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
diff --git a/arch/arm64/include/uapi/asm/posix_types.h b/arch/arm64/include/uapi/asm/posix_types.h
new file mode 100644
index 0000000..7985ff6
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/posix_types.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_POSIX_TYPES_H
+#define __ASM_POSIX_TYPES_H
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
+#include <asm-generic/posix_types.h>
+
+#endif /*  __ASM_POSIX_TYPES_H */
-- 
1.9.1

[PATCH 3.13 156/198] arm64: ptrace: fix empty registers set in prstatus of aarch32 process core

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Victor Kamensky <victor.kamensky@linaro.org>

commit 2227901a0230d8fde81ba9c602d649839390f56b upstream.

Currently core file of aarch32 process prstatus note has empty
registers set. As result aarch32 core files create by V8 kernel are
not very useful.

It happens because compat_gpr_get and compat_gpr_set functions can
copy registers values to/from either kbuf or ubuf. ELF core file
collection function fill_thread_core_info calls compat_gpr_get
with kbuf set and ubuf set to 0. But current compat_gpr_get and
compat_gpr_set function handle copy to/from only ubuf case.

Fix is to handle kbuf and ubuf as two separate cases in similar
way as other functions like user_regset_copyout, user_regset_copyin do.

Signed-off-by: Victor Kamensky <victor.kamensky@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm64/kernel/ptrace.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index bf288e4..7a50b86 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -650,11 +650,16 @@ static int compat_gpr_get(struct task_struct *target,
 			reg = task_pt_regs(target)->regs[idx];
 		}
 
-		ret = copy_to_user(ubuf, &reg, sizeof(reg));
-		if (ret)
-			break;
-
-		ubuf += sizeof(reg);
+		if (kbuf) {
+			memcpy(kbuf, &reg, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_to_user(ubuf, &reg, sizeof(reg));
+			if (ret)
+				break;
+
+			ubuf += sizeof(reg);
+		}
 	}
 
 	return ret;
@@ -684,11 +689,16 @@ static int compat_gpr_set(struct task_struct *target,
 		unsigned int idx = start + i;
 		compat_ulong_t reg;
 
-		ret = copy_from_user(&reg, ubuf, sizeof(reg));
-		if (ret)
-			return ret;
+		if (kbuf) {
+			memcpy(&reg, kbuf, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_from_user(&reg, ubuf, sizeof(reg));
+			if (ret)
+				return ret;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 
 		switch (idx) {
 		case 15:
-- 
1.9.1

[PATCH 3.13 157/198] arm64/dma: Removing ARCH_HAS_DMA_GET_REQUIRED_MASK macro

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>

commit f3a183cb422574014538017b5b291a416396f97e upstream.

Arm64 does not define dma_get_required_mask() function.
Therefore, it should not define the ARCH_HAS_DMA_GET_REQUIRED_MASK.
This causes build errors in some device drivers (e.g. mpt2sas)

Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/arm64/include/asm/dma-mapping.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index fd0c0c0..064d352 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -26,8 +26,6 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
 
-- 
1.9.1

[PATCH 3.13 158/198] ALSA: control: Protect user controls against concurrent access

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lars-Peter Clausen <lars@metafoo.de>

commit 07f4d9d74a04aa7c72c5dae0ef97565f28f17b92 upstream.

The user-control put and get handlers as well as the tlv do not protect against
concurrent access from multiple threads. Since the state of the control is not
updated atomically it is possible that either two write operations or a write
and a read operation race against each other. Both can lead to arbitrary memory
disclosure. This patch introduces a new lock that protects user-controls from
concurrent access. Since applications typically access controls sequentially
than in parallel a single lock per card should be fine.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 include/sound/core.h |  2 ++
 sound/core/control.c | 31 +++++++++++++++++++++++++------
 sound/core/init.c    |  1 +
 3 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/include/sound/core.h b/include/sound/core.h
index 2a14f1f..d6bc961 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -121,6 +121,8 @@ struct snd_card {
 	int user_ctl_count;		/* count of all user controls */
 	struct list_head controls;	/* all controls for this card */
 	struct list_head ctl_files;	/* active control files */
+	struct mutex user_ctl_lock;	/* protects user controls against
+					   concurrent access */
 
 	struct snd_info_entry *proc_root;	/* root for soundcard specific files */
 	struct snd_info_entry *proc_id;	/* the card id */
diff --git a/sound/core/control.c b/sound/core/control.c
index d8aa206..183fab2 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -992,6 +992,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file,
 
 struct user_element {
 	struct snd_ctl_elem_info info;
+	struct snd_card *card;
 	void *elem_data;		/* element data */
 	unsigned long elem_data_size;	/* size of element data in bytes */
 	void *tlv_data;			/* TLV data */
@@ -1035,7 +1036,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol,
 {
 	struct user_element *ue = kcontrol->private_data;
 
+	mutex_lock(&ue->card->user_ctl_lock);
 	memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return 0;
 }
 
@@ -1044,10 +1047,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol,
 {
 	int change;
 	struct user_element *ue = kcontrol->private_data;
-	
+
+	mutex_lock(&ue->card->user_ctl_lock);
 	change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
 	if (change)
 		memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return change;
 }
 
@@ -1067,19 +1072,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol,
 		new_data = memdup_user(tlv, size);
 		if (IS_ERR(new_data))
 			return PTR_ERR(new_data);
+		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
 			change = memcmp(ue->tlv_data, new_data, size);
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
+		mutex_unlock(&ue->card->user_ctl_lock);
 	} else {
-		if (! ue->tlv_data_size || ! ue->tlv_data)
-			return -ENXIO;
-		if (size < ue->tlv_data_size)
-			return -ENOSPC;
+		int ret = 0;
+
+		mutex_lock(&ue->card->user_ctl_lock);
+		if (!ue->tlv_data_size || !ue->tlv_data) {
+			ret = -ENXIO;
+			goto err_unlock;
+		}
+		if (size < ue->tlv_data_size) {
+			ret = -ENOSPC;
+			goto err_unlock;
+		}
 		if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
-			return -EFAULT;
+			ret = -EFAULT;
+err_unlock:
+		mutex_unlock(&ue->card->user_ctl_lock);
+		if (ret)
+			return ret;
 	}
 	return change;
 }
@@ -1211,6 +1229,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
 	if (ue == NULL)
 		return -ENOMEM;
+	ue->card = card;
 	ue->info = *info;
 	ue->info.access = 0;
 	ue->elem_data = (char *)ue + sizeof(*ue);
diff --git a/sound/core/init.c b/sound/core/init.c
index e3c93cd..1ac7ea0 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -215,6 +215,7 @@ int snd_card_create(int idx, const char *xid,
 	INIT_LIST_HEAD(&card->devices);
 	init_rwsem(&card->controls_rwsem);
 	rwlock_init(&card->ctl_files_rwlock);
+	mutex_init(&card->user_ctl_lock);
 	INIT_LIST_HEAD(&card->controls);
 	INIT_LIST_HEAD(&card->ctl_files);
 	spin_lock_init(&card->files_lock);
-- 
1.9.1

[PATCH 3.13 159/198] ALSA: control: Fix replacing user controls

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lars-Peter Clausen <lars@metafoo.de>

commit 82262a46627bebb0febcc26664746c25cef08563 upstream.

There are two issues with the current implementation for replacing user
controls. The first is that the code does not check if the control is actually a
user control and neither does it check if the control is owned by the process
that tries to remove it. That allows userspace applications to remove arbitrary
controls, which can cause a user after free if a for example a driver does not
expect a control to be removed from under its feed.

The second issue is that on one hand when a control is replaced the
user_ctl_count limit is not checked and on the other hand the user_ctl_count is
increased (even though the number of user controls does not change). This allows
userspace, once the user_ctl_count limit as been reached, to repeatedly replace
a control until user_ctl_count overflows. Once that happens new controls can be
added effectively bypassing the user_ctl_count limit.

Both issues can be fixed by instead of open-coding the removal of the control
that is to be replaced to use snd_ctl_remove_user_ctl(). This function does
proper permission checks as well as decrements user_ctl_count after the control
has been removed.

Note that by using snd_ctl_remove_user_ctl() the check which returns -EBUSY at
beginning of the function if the control already exists is removed. This is not
a problem though since the check is quite useless, because the lock that is
protecting the control list is released between the check and before adding the
new control to the list, which means that it is possible that a different
control with the same settings is added to the list after the check. Luckily
there is another check that is done while holding the lock in snd_ctl_add(), so
we'll rely on that to make sure that the same control is not added twice.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/core/control.c | 25 +++++++++----------------
 1 file changed, 9 insertions(+), 16 deletions(-)

diff --git a/sound/core/control.c b/sound/core/control.c
index 183fab2..15bc844 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1155,8 +1155,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	struct user_element *ue;
 	int idx, err;
 
-	if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
-		return -ENOMEM;
 	if (info->count < 1)
 		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
@@ -1165,21 +1163,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 				 SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
 	info->id.numid = 0;
 	memset(&kctl, 0, sizeof(kctl));
-	down_write(&card->controls_rwsem);
-	_kctl = snd_ctl_find_id(card, &info->id);
-	err = 0;
-	if (_kctl) {
-		if (replace)
-			err = snd_ctl_remove(card, _kctl);
-		else
-			err = -EBUSY;
-	} else {
-		if (replace)
-			err = -ENOENT;
+
+	if (replace) {
+		err = snd_ctl_remove_user_ctl(file, &info->id);
+		if (err)
+			return err;
 	}
-	up_write(&card->controls_rwsem);
-	if (err < 0)
-		return err;
+
+	if (card->user_ctl_count >= MAX_USER_CONTROLS)
+		return -ENOMEM;
+
 	memcpy(&kctl.id, &info->id, sizeof(info->id));
 	kctl.count = info->owner ? info->owner : 1;
 	access |= SNDRV_CTL_ELEM_ACCESS_USER;
-- 
1.9.1

[PATCH 3.13 160/198] ALSA: control: Don't access controls outside of protected regions

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lars-Peter Clausen <lars@metafoo.de>

commit fd9f26e4eca5d08a27d12c0933fceef76ed9663d upstream.

A control that is visible on the card->controls list can be freed at any time.
This means we must not access any of its memory while not holding the
controls_rw_lock. Otherwise we risk a use after free access.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/core/control.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/sound/core/control.c b/sound/core/control.c
index 15bc844..d4a597f 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -331,6 +331,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 {
 	struct snd_ctl_elem_id id;
 	unsigned int idx;
+	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
@@ -359,8 +360,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -389,6 +391,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol,
 		    bool add_on_replace)
 {
 	struct snd_ctl_elem_id id;
+	unsigned int count;
 	unsigned int idx;
 	struct snd_kcontrol *old;
 	int ret;
@@ -424,8 +427,9 @@ add:
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -898,9 +902,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file,
 			result = kctl->put(kctl, control);
 		}
 		if (result > 0) {
+			struct snd_ctl_elem_id id = control->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
-				       &control->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
 			return 0;
 		}
 	}
@@ -1334,8 +1338,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
 		}
 		err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
 		if (err > 0) {
+			struct snd_ctl_elem_id id = kctl->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
 			return 0;
 		}
 	} else {
-- 
1.9.1

[PATCH 3.13 161/198] ALSA: control: Handle numid overflow

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lars-Peter Clausen <lars@metafoo.de>

commit ac902c112d90a89e59916f751c2745f4dbdbb4bd upstream.

Each control gets automatically assigned its numids when the control is created.
The allocation is done by incrementing the numid by the amount of allocated
numids per allocation. This means that excessive creation and destruction of
controls (e.g. via SNDRV_CTL_IOCTL_ELEM_ADD/REMOVE) can cause the id to
eventually overflow. Currently when this happens for the control that caused the
overflow kctl->id.numid + kctl->count will also over flow causing it to be
smaller than kctl->id.numid. Most of the code assumes that this is something
that can not happen, so we need to make sure that it won't happen

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/core/control.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/core/control.c b/sound/core/control.c
index d4a597f..93215b4 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card,
 {
 	struct snd_kcontrol *kctl;
 
+	/* Make sure that the ids assigned to the control do not wrap around */
+	if (card->last_numid >= UINT_MAX - count)
+		card->last_numid = 0;
+
 	list_for_each_entry(kctl, &card->controls, list) {
 		if (kctl->id.numid < card->last_numid + 1 + count &&
 		    kctl->id.numid + kctl->count > card->last_numid + 1) {
-- 
1.9.1

[PATCH 3.13 162/198] ALSA: control: Make sure that id->index does not overflow

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Lars-Peter Clausen <lars@metafoo.de>

commit 883a1d49f0d77d30012f114b2e19fc141beb3e8e upstream.

The ALSA control code expects that the range of assigned indices to a control is
continuous and does not overflow. Currently there are no checks to enforce this.
If a control with a overflowing index range is created that control becomes
effectively inaccessible and unremovable since snd_ctl_find_id() will not be
able to find it. This patch adds a check that makes sure that controls with a
overflowing index range can not be created.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/core/control.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/core/control.c b/sound/core/control.c
index 93215b4..98a29b2 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -343,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
 	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		goto error;
+
 	down_write(&card->controls_rwsem);
 	if (snd_ctl_find_id(card, &id)) {
 		up_write(&card->controls_rwsem);
-- 
1.9.1

[PATCH 3.13 163/198] Bluetooth: Fix SSP acceptor just-works confirmation without MITM

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit ba15a58b179ed76a7e887177f2b06de12c58ec8f upstream.

>From the Bluetooth Core Specification 4.1 page 1958:

"if both devices have set the Authentication_Requirements parameter to
one of the MITM Protection Not Required options, authentication stage 1
shall function as if both devices set their IO capabilities to
DisplayOnly (e.g., Numeric comparison with automatic confirmation on
both devices)"

So far our implementation has done user confirmation for all just-works
cases regardless of the MITM requirements, however following the
specification to the word means that we should not be doing confirmation
when neither side has the MITM flag set.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Tested-by: Szymon Janc <szymon.janc@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/hci_event.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e70a426..aeda116 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3183,8 +3183,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		/* If we're not the initiators request authorization to
 		 * proceed from user space (mgmt_user_confirm with
-		 * confirm_hint set to 1). */
-		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+		 * confirm_hint set to 1). The exception is if neither
+		 * side had MITM in which case we do auto-accept.
+		 */
+		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+		    (loc_mitm || rem_mitm)) {
 			BT_DBG("Confirming auto-accept as acceptor");
 			confirm_hint = 1;
 			goto confirm;
-- 
1.9.1

[PATCH 3.13 164/198] Bluetooth: Fix setting correct authentication information for SMP STK

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit fff3490f47810e2d34b91fb9e31103e923b11c2f upstream.

When we store the STK in slave role we should set the correct
authentication information for it. If the pairing is producing a HIGH
security level the STK is considered authenticated, and otherwise it's
considered unauthenticated. This patch fixes the value passed to the
hci_add_ltk() function when adding the STK on the slave side.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Tested-by: Marcin Kraglak <marcin.kraglak@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/smp.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 4b07acb..7e355bb 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -467,7 +467,7 @@ static void random_work(struct work_struct *work)
 		hci_le_start_enc(hcon, ediv, rand, stk);
 		hcon->enc_key_size = smp->enc_key_size;
 	} else {
-		u8 stk[16], r[16], rand[8];
+		u8 stk[16], r[16], rand[8], auth;
 		__le16 ediv;
 
 		memset(rand, 0, sizeof(rand));
@@ -482,8 +482,13 @@ static void random_work(struct work_struct *work)
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
 
+		if (hcon->pending_sec_level == BT_SECURITY_HIGH)
+			auth = 1;
+		else
+			auth = 0;
+
 		hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type,
-			    HCI_SMP_STK_SLAVE, 0, 0, stk, smp->enc_key_size,
+			    HCI_SMP_STK_SLAVE, 0, auth, stk, smp->enc_key_size,
 			    ediv, rand);
 	}
 
-- 
1.9.1

[PATCH 3.13 165/198] Bluetooth: Fix indicating discovery state when canceling inquiry

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit 50143a433b70e3145bcf8a4a4e54f0c11bdee32b upstream.

When inquiry is canceled through the HCI_Cancel_Inquiry command there is
no Inquiry Complete event generated. Instead, all we get is the command
complete for the HCI_Inquiry_Cancel command. This means that we must
call the hci_discovery_set_state() function from the respective command
complete handler in order to ensure that user space knows the correct
discovery state.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/hci_event.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index aeda116..fa88469 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -48,6 +48,10 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
 	smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
 	wake_up_bit(&hdev->flags, HCI_INQUIRY);
 
+	hci_dev_lock(hdev);
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	hci_dev_unlock(hdev);
+
 	hci_conn_check_pending(hdev);
 }
 
-- 
1.9.1

[PATCH 3.13 166/198] Bluetooth: Fix locking of hdev when calling into SMP code

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Johan Hedberg <johan.hedberg@intel.com>

commit c73f94b8c093a615ce80eabbde0ac6eb9abfe31a upstream.

The SMP code expects hdev to be unlocked since e.g. crypto functions
will try to (re)lock it. Therefore, we need to release the lock before
calling into smp.c from mgmt.c. Without this we risk a deadlock whenever
the smp_user_confirm_reply() function is called.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Tested-by: Lukasz Rymanowski <lukasz.rymanowski@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/mgmt.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 074d836..75c2ecb 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2826,8 +2826,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
-		/* Continue with pairing via SMP */
+		/* Continue with pairing via SMP. The hdev lock must be
+		 * released as SMP may try to recquire it for crypto
+		 * purposes.
+		 */
+		hci_dev_unlock(hdev);
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+		hci_dev_lock(hdev);
 
 		if (!err)
 			err = cmd_complete(sk, hdev->id, mgmt_op,
-- 
1.9.1

[PATCH 3.13 167/198] Bluetooth: Allow change security level on ATT_CID in slave role

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Marcin Kraglak <marcin.kraglak@tieto.com>

commit 92d1372e1a9fec00e146b74e8b9ad7a385b9b37f upstream.

Kernel supports SMP Security Request so don't block increasing security
when we are slave.

Signed-off-by: Marcin Kraglak <marcin.kraglak@tieto.com>
Acked-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 net/bluetooth/l2cap_sock.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 9c27684..c9e0915 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -691,11 +691,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 
 		/*change security for LE channels */
 		if (chan->scid == L2CAP_CID_ATT) {
-			if (!conn->hcon->out) {
-				err = -EINVAL;
-				break;
-			}
-
 			if (smp_conn_security(conn->hcon, sec.level))
 				break;
 			sk->sk_state = BT_CONFIG;
-- 
1.9.1

[PATCH 3.13 168/198] rt2x00: disable TKIP on USB

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Stanislaw Gruszka <sgruszka@redhat.com>

commit 8edcb0ba0d56f5914eef11eda6db8bfe74eb9ca8 upstream.

On USB we can not get atomically TKIP key. We have to disable support
for TKIP acceleration on USB hardware to avoid bug as showed bellow.

[  860.827243] BUG: scheduling while atomic: hostapd/3397/0x00000002
<snip>
[  860.827280] Call Trace:
[  860.827282]  [<ffffffff81682ea6>] dump_stack+0x4d/0x66
[  860.827284]  [<ffffffff8167eb9b>] __schedule_bug+0x47/0x55
[  860.827285]  [<ffffffff81685bb3>] __schedule+0x733/0x7b0
[  860.827287]  [<ffffffff81685c59>] schedule+0x29/0x70
[  860.827289]  [<ffffffff81684f8a>] schedule_timeout+0x15a/0x2b0
[  860.827291]  [<ffffffff8105ac50>] ? ftrace_raw_event_tick_stop+0xc0/0xc0
[  860.827294]  [<ffffffff810c13c2>] ? __module_text_address+0x12/0x70
[  860.827296]  [<ffffffff81686823>] wait_for_completion_timeout+0xb3/0x140
[  860.827298]  [<ffffffff81080fc0>] ? wake_up_state+0x20/0x20
[  860.827301]  [<ffffffff814d5b3d>] usb_start_wait_urb+0x7d/0x150
[  860.827303]  [<ffffffff814d5cd5>] usb_control_msg+0xc5/0x110
[  860.827305]  [<ffffffffa02fb0c6>] rt2x00usb_vendor_request+0xc6/0x160  [rt2x00usb]
[  860.827307]  [<ffffffffa02fb215>] rt2x00usb_vendor_req_buff_lock+0x75/0x150 [rt2x00usb]
[  860.827309]  [<ffffffffa02fb393>] rt2x00usb_vendor_request_buff+0xa3/0xe0 [rt2x00usb]
[  860.827311]  [<ffffffffa023d1a3>] rt2x00usb_register_multiread+0x33/0x40 [rt2800usb]
[  860.827314]  [<ffffffffa05805f9>] rt2800_get_tkip_seq+0x39/0x50  [rt2800lib]
[  860.827321]  [<ffffffffa0480f88>] ieee80211_get_key+0x218/0x2a0  [mac80211]
[  860.827322]  [<ffffffff815cc68c>] ? __nlmsg_put+0x6c/0x80
[  860.827329]  [<ffffffffa051b02e>] nl80211_get_key+0x22e/0x360 [cfg80211]

Reported-and-tested-by: Peter Wu <lekensteyn@gmail.com>
Reported-and-tested-by: Pontus Fuchs <pontus.fuchs@gmail.com>
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/wireless/rt2x00/rt2x00mac.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index b4e94ae..bc21fae 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -489,6 +489,8 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	crypto.cipher = rt2x00crypto_key_to_cipher(key);
 	if (crypto.cipher == CIPHER_NONE)
 		return -EOPNOTSUPP;
+	if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev))
+		return -EOPNOTSUPP;
 
 	crypto.cmd = cmd;
 
-- 
1.9.1

[PATCH 3.13 169/198] b43: fix frequency reported on G-PHY with /new/ firmware

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <zajec5@gmail.com>

commit 2fc68eb122c7ea6cd5be1fe7d6650c0beb2f4f40 upstream.

Support for firmware rev 508+ was added years ago, but we never noticed
it reports channel in a different way for G-PHY devices. Instead of
offset from 2400 MHz it simply passes channel id (AKA hw_value).

So far it was (most probably) affecting monitor mode users only, but
the following recent commit made it noticeable for quite everybody:

commit 3afc2167f60a327a2c1e1e2600ef209a3c2b75b7
Author: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date:   Tue Mar 4 16:50:13 2014 +0200

    cfg80211/mac80211: ignore signal if the frame was heard on wrong channel

Reported-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Tested-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/wireless/b43/xmit.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 50e5ddb..628ff62 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -810,9 +810,13 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		break;
 	case B43_PHYTYPE_G:
 		status.band = IEEE80211_BAND_2GHZ;
-		/* chanid is the radio channel cookie value as used
-		 * to tune the radio. */
-		status.freq = chanid + 2400;
+		/* Somewhere between 478.104 and 508.1084 firmware for G-PHY
+		 * has been modified to be compatible with N-PHY and others.
+		 */
+		if (dev->fw.rev >= 508)
+			status.freq = ieee80211_channel_to_frequency(chanid, status.band);
+		else
+			status.freq = chanid + 2400;
 		break;
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
-- 
1.9.1

[PATCH 3.13 170/198] rt2x00: fix rfkill regression on rt2500pci

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Stanislaw Gruszka <stf_xl@wp.pl>

commit 616a8394b5df8c88f4dd416f4527439a4e365034 upstream.

As reported by Niels, starting rfkill polling during device probe
(commit e2bc7c5, generally sane change) broke rfkill on rt2500pci
device. I considered that bug as some initalization issue, which
should be fixed on rt2500pci specific code. But after several
attempts (see bug report for details) we fail to find working solution.
Hence I decided to revert to old behaviour on rt2500pci to fix
regression.

Additionally patch also unregister rfkill on device remove instead
of ifconfig down, what was another issue introduced by bad commit.

Bug report:
https://bugzilla.kernel.org/show_bug.cgi?id=73821

Fixes: e2bc7c5f3cb8 ("rt2x00: Fix rfkill_polling register function.")
Bisected-by: Niels <nille0386@googlemail.com>
Reported-and-tested-by: Niels <nille0386@googlemail.com>
Signed-off-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/wireless/rt2x00/rt2500pci.c |  7 ++++++-
 drivers/net/wireless/rt2x00/rt2x00.h    |  1 +
 drivers/net/wireless/rt2x00/rt2x00dev.c | 24 +++++++++++++++++++++---
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index 0ac5c58..13f557a 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1684,8 +1684,13 @@ static int rt2500pci_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Detect if this device has an hardware controlled radio.
 	 */
-	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO))
+	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) {
 		__set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags);
+		/*
+		 * On this device RFKILL initialized during probe does not work.
+		 */
+		__set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags);
+	}
 
 	/*
 	 * Check if the BBP tuning should be enabled.
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index e4ba2ce..c06ffb7 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -695,6 +695,7 @@ enum rt2x00_capability_flags {
 	REQUIRE_SW_SEQNO,
 	REQUIRE_HT_TX_DESC,
 	REQUIRE_PS_AUTOWAKE,
+	REQUIRE_DELAYED_RFKILL,
 
 	/*
 	 * Capabilities
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 9dd92a7..78d0056 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -1128,9 +1128,10 @@ static void rt2x00lib_uninitialize(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/*
-	 * Unregister extra components.
+	 * Stop rfkill polling.
 	 */
-	rt2x00rfkill_unregister(rt2x00dev);
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
 
 	/*
 	 * Allow the HW to uninitialize.
@@ -1168,6 +1169,12 @@ static int rt2x00lib_initialize(struct rt2x00_dev *rt2x00dev)
 
 	set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags);
 
+	/*
+	 * Start rfkill polling.
+	 */
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
+
 	return 0;
 }
 
@@ -1377,7 +1384,12 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 	rt2x00link_register(rt2x00dev);
 	rt2x00leds_register(rt2x00dev);
 	rt2x00debug_register(rt2x00dev);
-	rt2x00rfkill_register(rt2x00dev);
+
+	/*
+	 * Start rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
 
 	return 0;
 
@@ -1393,6 +1405,12 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
 
 	/*
+	 * Stop rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
+
+	/*
 	 * Disable radio.
 	 */
 	rt2x00lib_disable_radio(rt2x00dev);
-- 
1.9.1

[PATCH 3.13 171/198] blkcg: fix use-after-free in __blkg_release_rcu() by making blkcg_gq refcnt an atomic_t

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Tejun Heo <tj@kernel.org>

commit a5049a8ae34950249a7ae94c385d7c5c98914412 upstream.

Hello,

So, this patch should do.  Joe, Vivek, can one of you guys please
verify that the oops goes away with this patch?

Jens, the original thread can be read at

  http://thread.gmane.org/gmane.linux.kernel/1720729

The fix converts blkg->refcnt from int to atomic_t.  It does some
overhead but it should be minute compared to everything else which is
going on and the involved cacheline bouncing, so I think it's highly
unlikely to cause any noticeable difference.  Also, the refcnt in
question should be converted to a perpcu_ref for blk-mq anyway, so the
atomic_t is likely to go away pretty soon anyway.

Thanks.

------- 8< -------
__blkg_release_rcu() may be invoked after the associated request_queue
is released with a RCU grace period inbetween.  As such, the function
and callbacks invoked from it must not dereference the associated
request_queue.  This is clearly indicated in the comment above the
function.

Unfortunately, while trying to fix a different issue, 2a4fd070ee85
("blkcg: move bulk of blkcg_gq release operations to the RCU
callback") ignored this and added [un]locking of @blkg->q->queue_lock
to __blkg_release_rcu().  This of course can cause oops as the
request_queue may be long gone by the time this code gets executed.

  general protection fault: 0000 [#1] SMP
  CPU: 21 PID: 30 Comm: rcuos/21 Not tainted 3.15.0 #1
  Hardware name: Stratus ftServer 6400/G7LAZ, BIOS BIOS Version 6.3:57 12/25/2013
  task: ffff880854021de0 ti: ffff88085403c000 task.ti: ffff88085403c000
  RIP: 0010:[<ffffffff8162e9e5>]  [<ffffffff8162e9e5>] _raw_spin_lock_irq+0x15/0x60
  RSP: 0018:ffff88085403fdf0  EFLAGS: 00010086
  RAX: 0000000000020000 RBX: 0000000000000010 RCX: 0000000000000000
  RDX: 000060ef80008248 RSI: 0000000000000286 RDI: 6b6b6b6b6b6b6b6b
  RBP: ffff88085403fdf0 R08: 0000000000000286 R09: 0000000000009f39
  R10: 0000000000020001 R11: 0000000000020001 R12: ffff88103c17a130
  R13: ffff88103c17a080 R14: 0000000000000000 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff88107fca0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000006e5ab8 CR3: 000000000193d000 CR4: 00000000000407e0
  Stack:
   ffff88085403fe18 ffffffff812cbfc2 ffff88103c17a130 0000000000000000
   ffff88103c17a130 ffff88085403fec0 ffffffff810d1d28 ffff880854021de0
   ffff880854021de0 ffff88107fcaec58 ffff88085403fe80 ffff88107fcaec30
  Call Trace:
   [<ffffffff812cbfc2>] __blkg_release_rcu+0x72/0x150
   [<ffffffff810d1d28>] rcu_nocb_kthread+0x1e8/0x300
   [<ffffffff81091d81>] kthread+0xe1/0x100
   [<ffffffff8163813c>] ret_from_fork+0x7c/0xb0
  Code: ff 47 04 48 8b 7d 08 be 00 02 00 00 e8 55 48 a4 ff 5d c3 0f 1f 00 66 66 66 66 90 55 48 89 e5
  +fa 66 66 90 66 66 90 b8 00 00 02 00 <f0> 0f c1 07 89 c2 c1 ea 10 66 39 c2 75 02 5d c3 83 e2 fe 0f
  +b7
  RIP  [<ffffffff8162e9e5>] _raw_spin_lock_irq+0x15/0x60
   RSP <ffff88085403fdf0>

The request_queue locking was added because blkcg_gq->refcnt is an int
protected with the queue lock and __blkg_release_rcu() needs to put
the parent.  Let's fix it by making blkcg_gq->refcnt an atomic_t and
dropping queue locking in the function.

Given the general heavy weight of the current request_queue and blkcg
operations, this is unlikely to cause any noticeable overhead.
Moreover, blkcg_gq->refcnt is likely to be converted to percpu_ref in
the near future, so whatever (most likely negligible) overhead it may
add is temporary.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Joe Lawrence <joe.lawrence@stratus.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/g/alpine.DEB.2.02.1406081816540.17948@jlaw-desktop.mno.stratus.com
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 block/blk-cgroup.c |  7 ++-----
 block/blk-cgroup.h | 17 +++++++----------
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4e491d9..dd0dd2d 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,7 +80,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
-	blkg->refcnt = 1;
+	atomic_set(&blkg->refcnt, 1);
 
 	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
 	if (blkcg != &blkcg_root) {
@@ -399,11 +399,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head)
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
-	if (blkg->parent) {
-		spin_lock_irq(blkg->q->queue_lock);
+	if (blkg->parent)
 		blkg_put(blkg->parent);
-		spin_unlock_irq(blkg->q->queue_lock);
-	}
 
 	blkg_free(blkg);
 }
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154ea..c135f56 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
+#include <linux/atomic.h>
 
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
@@ -104,7 +105,7 @@ struct blkcg_gq {
 	struct request_list		rl;
 
 	/* reference count */
-	int				refcnt;
+	atomic_t			refcnt;
 
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
@@ -253,13 +254,12 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
  * blkg_get - get a blkg reference
  * @blkg: blkg to get
  *
- * The caller should be holding queue_lock and an existing reference.
+ * The caller should be holding an existing reference.
  */
 static inline void blkg_get(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(!blkg->refcnt);
-	blkg->refcnt++;
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	atomic_inc(&blkg->refcnt);
 }
 
 void __blkg_release_rcu(struct rcu_head *rcu);
@@ -267,14 +267,11 @@ void __blkg_release_rcu(struct rcu_head *rcu);
 /**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
- *
- * The caller should be holding queue_lock.
  */
 static inline void blkg_put(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(blkg->refcnt <= 0);
-	if (!--blkg->refcnt)
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	if (atomic_dec_and_test(&blkg->refcnt))
 		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
 }
 
-- 
1.9.1

[PATCH 3.13 172/198] rbd: handle parent_overlap on writes correctly

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ilya Dryomov <ilya.dryomov@inktank.com>

commit 9638556a276125553549fdfe349c464481ec2f39 upstream.

The following check in rbd_img_obj_request_submit()

    rbd_dev->parent_overlap <= obj_request->img_offset

allows the fall through to the non-layered write case even if both
parent_overlap and obj_request->img_offset belong to the same RADOS
object.  This leads to data corruption, because the area to the left of
parent_overlap ends up unconditionally zero-filled instead of being
populated with parent data.  Suppose we want to write 1M to offset 6M
of image bar, which is a clone of foo@snap; object_size is 4M,
parent_overlap is 5M:

    rbd_data.<id>.0000000000000001
     ---------------------|----------------------|------------
    | should be copyup'ed | should be zeroed out | write ...
     ---------------------|----------------------|------------
   4M                    5M                     6M
                    parent_overlap    obj_request->img_offset

4..5M should be copyup'ed from foo, yet it is zero-filled, just like
5..6M is.

Given that the only striping mode kernel client currently supports is
chunking (i.e. stripe_unit == object_size, stripe_count == 1), round
parent_overlap up to the next object boundary for the purposes of the
overlap check.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/block/rbd.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 7e37f90..a1455cc 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1379,6 +1379,14 @@ static bool obj_request_exists_test(struct rbd_obj_request *obj_request)
 	return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
 }
 
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+	return obj_request->img_offset <
+	    round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
@@ -2675,7 +2683,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	 */
 	if (!img_request_write_test(img_request) ||
 		!img_request_layered_test(img_request) ||
-		rbd_dev->parent_overlap <= obj_request->img_offset ||
+		!obj_request_overlaps_parent(obj_request) ||
 		((known = obj_request_known_test(obj_request)) &&
 			obj_request_exists_test(obj_request))) {
 
-- 
1.9.1

[PATCH 3.13 173/198] ALSA: hda - hdmi: call overridden init on resume

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Pierre Ossman <pierre@ossman.eu>

commit a283368382c50345dff61525f493ea307f21ec9b upstream.

We need to call the proper init function in case it has been
overridden, as it might restore things that the generic routing
doesn't know anything about. E.g. AMD cards have special verbs
that need resetting.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=77901
Fixes: 5a61358433b1 ('ALSA: hda - hdmi: Add ATI/AMD multi-channel audio support')
Signed-off-by: Pierre Ossman <pierre@ossman.eu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/patch_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index a21a325..2f66de6 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2177,7 +2177,7 @@ static int generic_hdmi_resume(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 	int pin_idx;
 
-	generic_hdmi_init(codec);
+	codec->patch_ops.init(codec);
 	snd_hda_codec_resume_amp(codec);
 	snd_hda_codec_resume_cache(codec);
 
-- 
1.9.1

[PATCH 3.13 174/198] lzo: properly check for overruns

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 206a81c18401c0cde6e579164f752c4b147324ce upstream.

The lzo decompressor can, if given some really crazy data, possibly
overrun some variable types.  Modify the checking logic to properly
detect overruns before they happen.

Reported-by: "Don A. Bailey" <donb@securitymouse.com>
Tested-by: "Don A. Bailey" <donb@securitymouse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 lib/lzo/lzo1x_decompress_safe.c | 62 +++++++++++++++++++++++++++--------------
 1 file changed, 41 insertions(+), 21 deletions(-)

diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d..8563081 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -19,11 +19,31 @@
 #include <linux/lzo.h>
 #include "lzodefs.h"
 
-#define HAVE_IP(x)      ((size_t)(ip_end - ip) >= (size_t)(x))
-#define HAVE_OP(x)      ((size_t)(op_end - op) >= (size_t)(x))
-#define NEED_IP(x)      if (!HAVE_IP(x)) goto input_overrun
-#define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
-#define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
+#define HAVE_IP(t, x)					\
+	(((size_t)(ip_end - ip) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define HAVE_OP(t, x)					\
+	(((size_t)(op_end - op) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define NEED_IP(t, x)					\
+	do {						\
+		if (!HAVE_IP(t, x))			\
+			goto input_overrun;		\
+	} while (0)
+
+#define NEED_OP(t, x)					\
+	do {						\
+		if (!HAVE_OP(t, x))			\
+			goto output_overrun;		\
+	} while (0)
+
+#define TEST_LB(m_pos)					\
+	do {						\
+		if ((m_pos) < out)			\
+			goto lookbehind_overrun;	\
+	} while (0)
 
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
@@ -58,14 +78,14 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 					while (unlikely(*ip == 0)) {
 						t += 255;
 						ip++;
-						NEED_IP(1);
+						NEED_IP(1, 0);
 					}
 					t += 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-				if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
+				if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) {
 					const unsigned char *ie = ip + t;
 					unsigned char *oe = op + t;
 					do {
@@ -81,8 +101,8 @@ copy_literal_run:
 				} else
 #endif
 				{
-					NEED_OP(t);
-					NEED_IP(t + 3);
+					NEED_OP(t, 0);
+					NEED_IP(t, 3);
 					do {
 						*op++ = *ip++;
 					} while (--t > 0);
@@ -95,7 +115,7 @@ copy_literal_run:
 				m_pos -= t >> 2;
 				m_pos -= *ip++ << 2;
 				TEST_LB(m_pos);
-				NEED_OP(2);
+				NEED_OP(2, 0);
 				op[0] = m_pos[0];
 				op[1] = m_pos[1];
 				op += 2;
@@ -119,10 +139,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 31 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			m_pos = op - 1;
 			next = get_unaligned_le16(ip);
@@ -137,10 +157,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 7 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			next = get_unaligned_le16(ip);
 			ip += 2;
@@ -154,7 +174,7 @@ copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 		if (op - m_pos >= 8) {
 			unsigned char *oe = op + t;
-			if (likely(HAVE_OP(t + 15))) {
+			if (likely(HAVE_OP(t, 15))) {
 				do {
 					COPY8(op, m_pos);
 					op += 8;
@@ -164,7 +184,7 @@ copy_literal_run:
 					m_pos += 8;
 				} while (op < oe);
 				op = oe;
-				if (HAVE_IP(6)) {
+				if (HAVE_IP(6, 0)) {
 					state = next;
 					COPY4(op, ip);
 					op += next;
@@ -172,7 +192,7 @@ copy_literal_run:
 					continue;
 				}
 			} else {
-				NEED_OP(t);
+				NEED_OP(t, 0);
 				do {
 					*op++ = *m_pos++;
 				} while (op < oe);
@@ -181,7 +201,7 @@ copy_literal_run:
 #endif
 		{
 			unsigned char *oe = op + t;
-			NEED_OP(t);
+			NEED_OP(t, 0);
 			op[0] = m_pos[0];
 			op[1] = m_pos[1];
 			op += 2;
@@ -194,15 +214,15 @@ match_next:
 		state = next;
 		t = next;
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-		if (likely(HAVE_IP(6) && HAVE_OP(4))) {
+		if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) {
 			COPY4(op, ip);
 			op += t;
 			ip += t;
 		} else
 #endif
 		{
-			NEED_IP(t + 3);
-			NEED_OP(t);
+			NEED_IP(t, 3);
+			NEED_OP(t, 0);
 			while (t > 0) {
 				*op++ = *ip++;
 				t--;
-- 
1.9.1

[PATCH 3.13 175/198] lz4: ensure length does not wrap

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 206204a1162b995e2185275167b22468c00d6b36 upstream.

Given some pathologically compressed data, lz4 could possibly decide to
wrap a few internal variables, causing unknown things to happen.  Catch
this before the wrapping happens and abort the decompression.

Reported-by: "Don A. Bailey" <donb@securitymouse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 lib/lz4/lz4_decompress.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index df6839e..99a03ac 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			len = *ip++;
 			for (; len == 255; length += 255)
 				len = *ip++;
+			if (unlikely(length > (size_t)(length + len)))
+				goto _output_error;
 			length += len;
 		}
 
-- 
1.9.1

[PATCH 3.13 176/198] x86_32, entry: Do syscall exit work on badsys (CVE-2014-4508)

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@amacapital.net>

commit 554086d85e71f30abe46fc014fea31929a7c6a8a upstream.

The bad syscall nr paths are their own incomprehensible route
through the entry control flow.  Rearrange them to work just like
syscalls that return -ENOSYS.

This fixes an OOPS in the audit code when fast-path auditing is
enabled and sysenter gets a bad syscall nr (CVE-2014-4508).

This has probably been broken since Linux 2.6.27:
af0575bba0 i386 syscall audit fast-path

Cc: Roland McGrath <roland@redhat.com>
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/e09c499eade6fc321266dd6b54da7beb28d6991c.1403558229.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/x86/kernel/entry_32.S | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2780b8f..6491353 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -431,9 +431,10 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
 	movl %eax,PT_EAX(%esp)
+sysenter_after_call:
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
@@ -683,7 +684,12 @@ END(syscall_fault)
 
 syscall_badsys:
 	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	jmp syscall_exit
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,PT_EAX(%esp)
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
 /*
-- 
1.9.1

[PATCH 3.13 177/198] hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned entry

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit 4a705fef986231a3e7a6b1a6d3c37025f021f49f upstream.

There's a race between fork() and hugepage migration, as a result we try
to "dereference" a swap entry as a normal pte, causing kernel panic.
The cause of the problem is that copy_hugetlb_page_range() can't handle
"swap entry" family (migration entry and hwpoisoned entry) so let's fix
it.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/hugetlb.c | 71 ++++++++++++++++++++++++++++++++++++------------------------
 1 file changed, 43 insertions(+), 28 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c8c4a03..1984a3d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2347,6 +2347,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 		update_mmu_cache(vma, address, ptep);
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_migration_entry(swp))
+		return 1;
+	else
+		return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
+		return 1;
+	else
+		return 0;
+}
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
@@ -2376,10 +2401,26 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
-		if (!huge_pte_none(huge_ptep_get(src_pte))) {
+		entry = huge_ptep_get(src_pte);
+		if (huge_pte_none(entry)) { /* skip none entry */
+			;
+		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
+				    is_hugetlb_entry_hwpoisoned(entry))) {
+			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+			if (is_write_migration_entry(swp_entry) && cow) {
+				/*
+				 * COW mappings require pages in both
+				 * parent and child to be set to read.
+				 */
+				make_migration_entry_read(&swp_entry);
+				entry = swp_entry_to_pte(swp_entry);
+				set_huge_pte_at(src, addr, src_pte, entry);
+			}
+			set_huge_pte_at(dst, addr, dst_pte, entry);
+		} else {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
-			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
 			page_dup_rmap(ptepage);
@@ -2394,32 +2435,6 @@ nomem:
 	return -ENOMEM;
 }
 
-static int is_hugetlb_entry_migration(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
 void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			    unsigned long start, unsigned long end,
 			    struct page *ref_page)
-- 
1.9.1

[PATCH 3.13 178/198] kernel/watchdog.c: remove preemption restrictions when restarting lockup detector

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Don Zickus <dzickus@redhat.com>

commit bde92cf455a03a91badb7046855592d8c008e929 upstream.

Peter Wu noticed the following splat on his machine when updating
/proc/sys/kernel/watchdog_thresh:

  BUG: sleeping function called from invalid context at mm/slub.c:965
  in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: init
  3 locks held by init/1:
   #0:  (sb_writers#3){.+.+.+}, at: [<ffffffff8117b663>] vfs_write+0x143/0x180
   #1:  (watchdog_proc_mutex){+.+.+.}, at: [<ffffffff810e02d3>] proc_dowatchdog+0x33/0x110
   #2:  (cpu_hotplug.lock){.+.+.+}, at: [<ffffffff810589c2>] get_online_cpus+0x32/0x80
  Preemption disabled at:[<ffffffff810e0384>] proc_dowatchdog+0xe4/0x110

  CPU: 0 PID: 1 Comm: init Not tainted 3.16.0-rc1-testing #34
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  Call Trace:
    dump_stack+0x4e/0x7a
    __might_sleep+0x11d/0x190
    kmem_cache_alloc_trace+0x4e/0x1e0
    perf_event_alloc+0x55/0x440
    perf_event_create_kernel_counter+0x26/0xe0
    watchdog_nmi_enable+0x75/0x140
    update_timers_all_cpus+0x53/0xa0
    proc_dowatchdog+0xe4/0x110
    proc_sys_call_handler+0xb3/0xc0
    proc_sys_write+0x14/0x20
    vfs_write+0xad/0x180
    SyS_write+0x49/0xb0
    system_call_fastpath+0x16/0x1b
  NMI watchdog: disabled (cpu0): hardware events not enabled

What happened is after updating the watchdog_thresh, the lockup detector
is restarted to utilize the new value.  Part of this process involved
disabling preemption.  Once preemption was disabled, perf tried to
allocate a new event (as part of the restart).  This caused the above
BUG_ON as you can't sleep with preemption disabled.

The preemption restriction seemed agressive as we are not doing anything
on that particular cpu, but with all the online cpus (which are
protected by the get_online_cpus lock).  Remove the restriction and the
BUG_ON goes away.

Signed-off-by: Don Zickus <dzickus@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reported-by: Peter Wu <peter@lekensteyn.nl>
Tested-by: Peter Wu <peter@lekensteyn.nl>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 kernel/watchdog.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610..c9b6f01 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -524,10 +524,8 @@ static void update_timers_all_cpus(void)
 	int cpu;
 
 	get_online_cpus();
-	preempt_disable();
 	for_each_online_cpu(cpu)
 		update_timers(cpu);
-	preempt_enable();
 	put_online_cpus();
 }
 
-- 
1.9.1

[PATCH 3.13 179/198] mm, pcp: allow restoring percpu_pagelist_fraction default

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Rientjes <rientjes@google.com>

commit 7cd2b0a34ab8e4db971920eef8982f985441adfb upstream.

Oleg reports a division by zero error on zero-length write() to the
percpu_pagelist_fraction sysctl:

    divide error: 0000 [#1] SMP DEBUG_PAGEALLOC
    CPU: 1 PID: 9142 Comm: badarea_io Not tainted 3.15.0-rc2-vm-nfs+ #19
    Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
    task: ffff8800d5aeb6e0 ti: ffff8800d87a2000 task.ti: ffff8800d87a2000
    RIP: 0010: percpu_pagelist_fraction_sysctl_handler+0x84/0x120
    RSP: 0018:ffff8800d87a3e78  EFLAGS: 00010246
    RAX: 0000000000000f89 RBX: ffff88011f7fd000 RCX: 0000000000000000
    RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000010
    RBP: ffff8800d87a3e98 R08: ffffffff81d002c8 R09: ffff8800d87a3f50
    R10: 000000000000000b R11: 0000000000000246 R12: 0000000000000060
    R13: ffffffff81c3c3e0 R14: ffffffff81cfddf8 R15: ffff8801193b0800
    FS:  00007f614f1e9740(0000) GS:ffff88011f440000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
    CR2: 00007f614f1fa000 CR3: 00000000d9291000 CR4: 00000000000006e0
    Call Trace:
      proc_sys_call_handler+0xb3/0xc0
      proc_sys_write+0x14/0x20
      vfs_write+0xba/0x1e0
      SyS_write+0x46/0xb0
      tracesys+0xe1/0xe6

However, if the percpu_pagelist_fraction sysctl is set by the user, it
is also impossible to restore it to the kernel default since the user
cannot write 0 to the sysctl.

This patch allows the user to write 0 to restore the default behavior.
It still requires a fraction equal to or larger than 8, however, as
stated by the documentation for sanity.  If a value in the range [1, 7]
is written, the sysctl will return EINVAL.

This successfully solves the divide by zero issue at the same time.

Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 Documentation/sysctl/vm.txt |  3 ++-
 kernel/sysctl.c             |  3 +--
 mm/page_alloc.c             | 40 ++++++++++++++++++++++++++++------------
 3 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 1fbd4eb..afb8f2e 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -669,7 +669,8 @@ The batch value of each per cpu pagelist is also updated as a result.  It is
 set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
 
 The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+the high water marks for each per cpu page list.  If the user writes '0' to this
+sysctl, it will revert to this default behavior.
 
 ==============================================================
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index fcdced1..bbf0a95 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -138,7 +138,6 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
-static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
@@ -1310,7 +1309,7 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(percpu_pagelist_fraction),
 		.mode		= 0644,
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
-		.extra1		= &min_percpu_pagelist_fract,
+		.extra1		= &zero,
 	},
 #ifdef CONFIG_MMU
 	{
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e864d6..856d95c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION	(8)
 
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
@@ -4071,7 +4072,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
 #endif
 
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
 	int batch;
@@ -4187,8 +4188,8 @@ static void pageset_set_high(struct per_cpu_pageset *p,
 	pageset_update(&p->pcp, high, batch);
 }
 
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
-		struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+				       struct per_cpu_pageset *pcp)
 {
 	if (percpu_pagelist_fraction)
 		pageset_set_high(pcp,
@@ -5781,23 +5782,38 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
-	unsigned int cpu;
+	int old_percpu_pagelist_fraction;
 	int ret;
 
+	mutex_lock(&pcp_batch_high_lock);
+	old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
-	if (!write || (ret < 0))
-		return ret;
+	if (!write || ret < 0)
+		goto out;
+
+	/* Sanity checking to avoid pcp imbalance */
+	if (percpu_pagelist_fraction &&
+	    percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+		percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* No change? */
+	if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+		goto out;
 
-	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		unsigned long  high;
-		high = zone->managed_pages / percpu_pagelist_fraction;
+		unsigned int cpu;
+
 		for_each_possible_cpu(cpu)
-			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
-					 high);
+			pageset_set_high_and_batch(zone,
+					per_cpu_ptr(zone->pageset, cpu));
 	}
+out:
 	mutex_unlock(&pcp_batch_high_lock);
-	return 0;
+	return ret;
 }
 
 int hashdist = HASHDIST_DEFAULT;
-- 
1.9.1

[PATCH 3.13 180/198] DMA, CMA: fix possible memory leak

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit fe8eea4f4a3f299ef83ed090d5354698ebe4fda8 upstream.

We should free memory for bitmap when we find zone mismatch, otherwise
this memory will leak.

Additionally, I copy code comment from PPC KVM's CMA code to inform why
we need to check zone mis-match.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Reviewed-by: Michal Nazarewicz <mina86@mina86.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Alexander Graf <agraf@suse.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/base/dma-contiguous.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 165c2c2..d3bffa4 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -155,13 +155,23 @@ static int __init cma_activate_area(struct cma *cma)
 		base_pfn = pfn;
 		for (j = pageblock_nr_pages; j; --j, pfn++) {
 			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
 			if (page_zone(pfn_to_page(pfn)) != zone)
-				return -EINVAL;
+				goto err;
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
 
 	return 0;
+
+err:
+	kfree(cma->bitmap);
+	return -EINVAL;
 }
 
 static struct cma cma_areas[MAX_CMA_AREAS];
-- 
1.9.1

[PATCH 3.13 181/198] mm: fix crashes from mbind() merging vmas

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd@google.com>

commit d05f0cdcbe6388723f1900c549b4850360545201 upstream.

In v2.6.34 commit 9d8cebd4bcd7 ("mm: fix mbind vma merge problem")
introduced vma merging to mbind(), but it should have also changed the
convention of passing start vma from queue_pages_range() (formerly
check_range()) to new_vma_page(): vma merging may have already freed
that structure, resulting in BUG at mm/mempolicy.c:1738 and probably
worse crashes.

Fixes: 9d8cebd4bcd7 ("mm: fix mbind vma merge problem")
Reported-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Tested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 mm/mempolicy.c | 46 ++++++++++++++++++++--------------------------
 1 file changed, 20 insertions(+), 26 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e980746..65c7674 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -654,19 +654,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  * @nodes and @flags,) it's isolated and queued to the pagelist which is
  * passed via @private.)
  */
-static struct vm_area_struct *
+static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		const nodemask_t *nodes, unsigned long flags, void *private)
 {
-	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
+	int err = 0;
+	struct vm_area_struct *vma, *prev;
 
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
+	vma = find_vma(mm, start);
+	if (!vma)
+		return -EFAULT;
 	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
 		unsigned long endvma = vma->vm_end;
 
 		if (endvma > end)
@@ -676,9 +675,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 		}
 
 		if (flags & MPOL_MF_LAZY) {
@@ -692,15 +691,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 			err = queue_pages_pgd_range(vma, start, endvma, nodes,
 						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
+			if (err)
 				break;
-			}
 		}
 next:
 		prev = vma;
 	}
-	return first;
+	return err;
 }
 
 /*
@@ -1185,16 +1182,17 @@ out:
 
 /*
  * Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
  * Search forward from there, if not.  N.B., this assumes that the
  * list of pages handed to migrate_pages()--which is how we get here--
  * is in virtual address order.
  */
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
-	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
 
+	vma = find_vma(current->mm, start);
 	while (vma) {
 		address = page_address_in_vma(page, vma);
 		if (address != -EFAULT)
@@ -1226,7 +1224,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
 	return NULL;
 }
@@ -1236,7 +1234,6 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     unsigned short mode, unsigned short mode_flags,
 		     nodemask_t *nmask, unsigned long flags)
 {
-	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	struct mempolicy *new;
 	unsigned long end;
@@ -1302,11 +1299,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (err)
 		goto mpol_out;
 
-	vma = queue_pages_range(mm, start, end, nmask,
+	err = queue_pages_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
-
-	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma))
+	if (!err)
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -1314,9 +1309,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_vma_page,
-					(unsigned long)vma,
-					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+			nr_failed = migrate_pages(&pagelist, new_page,
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
 		}
-- 
1.9.1

[PATCH 3.13 182/198] drm/i915: Hold the table lock whilst walking the file's idr and counting the objects in debugfs

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chris Wilson <chris@chris-wilson.co.uk>

commit 5b5ffff0d25060ab0e21fa0f6cd16428e87bf1ea upstream.

Fixes an issue whereby we may race with the table updates (before the
core takes the struct_mutex) and so risk dereferencing a stale pointer in
the iterator for /debugfs/.../i915_gem_objects. For example,

[ 1524.757545] BUG: unable to handle kernel paging request at f53af748
[ 1524.757572] IP: [<c1406982>] per_file_stats+0x12/0x100
[ 1524.757599] *pdpt = 0000000001b13001 *pde = 00000000379fb067 *pte = 80000000353af060
[ 1524.757621] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC
[ 1524.757637] Modules linked in: ctr ccm arc4 ath9k ath9k_common ath9k_hw ath snd_hda_codec_conexant mac80211 snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec bnep snd_hwdep rfcomm snd_pcm gpio_ich dell_wmi sparse_keymap snd_seq_midi hid_multitouch uvcvideo snd_seq_midi_event dell_laptop snd_rawmidi dcdbas snd_seq videobuf2_vmalloc videobuf2_memops videobuf2_core usbhid videodev snd_seq_device coretemp snd_timer hid joydev kvm_intel cfg80211 ath3k kvm btusb bluetooth serio_raw snd microcode soundcore lpc_ich wmi mac_hid parport_pc ppdev lp parport psmouse ahci libahci
[ 1524.757825] CPU: 3 PID: 1911 Comm: intel-gpu-overl Tainted: G        W  OE 3.15.0-rc3+ #96
[ 1524.757840] Hardware name: Dell Inc. Inspiron 1090/Inspiron 1090, BIOS A06 08/23/2011
[ 1524.757855] task: f52f36c0 ti: f4cbc000 task.ti: f4cbc000
[ 1524.757869] EIP: 0060:[<c1406982>] EFLAGS: 00210202 CPU: 3
[ 1524.757884] EIP is at per_file_stats+0x12/0x100
[ 1524.757896] EAX: 0000002d EBX: 00000000 ECX: f4cbdefc EDX: f53af700
[ 1524.757909] ESI: c1406970 EDI: f53af700 EBP: f4cbde6c ESP: f4cbde5c
[ 1524.757922]  DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
[ 1524.757934] CR0: 80050033 CR2: f53af748 CR3: 356af000 CR4: 000007f0
[ 1524.757945] Stack:
[ 1524.757957]  f4cbdefc 00000000 c1406970 f53af700 f4cbdea8 c12e5f15 f4cbdefc c1406970
[ 1524.757993]  0000ffff f4cbde90 0000002d f5dc5cd0 e4e80438 c1181d59 f4cbded8 f4d89900
[ 1524.758027]  f5631b40 e5131074 c1903f37 f4cbdf28 c14068e6 f52648a0 c1927748 c1903f37
[ 1524.758062] Call Trace:
[ 1524.758084]  [<c1406970>] ? i915_gem_object_info+0x510/0x510
[ 1524.758106]  [<c12e5f15>] idr_for_each+0xa5/0x100
[ 1524.758126]  [<c1406970>] ? i915_gem_object_info+0x510/0x510
[ 1524.758148]  [<c1181d59>] ? seq_vprintf+0x29/0x50
[ 1524.758168]  [<c14068e6>] i915_gem_object_info+0x486/0x510
[ 1524.758189]  [<c11823a6>] seq_read+0xd6/0x380
[ 1524.758208]  [<c116d11d>] ? final_putname+0x1d/0x40
[ 1524.758227]  [<c11822d0>] ? seq_hlist_next_percpu+0x90/0x90
[ 1524.758246]  [<c1163e52>] vfs_read+0x82/0x150
[ 1524.758265]  [<c11645d6>] SyS_read+0x46/0x90
[ 1524.758285]  [<c16b8d8c>] sysenter_do_call+0x12/0x22
[ 1524.758298] Code: f5 8f 2a 00 83 c4 6c 31 c0 5b 5e 5f 5d c3 8d 74 26 00 8d bc 27 00 00 00 00 55 89 e5 57 56 53 83 ec 04 3e 8d 74 26 00 83 41 04 01 <8b> 42 48 01 41 08 8b 42 4c 89 d7 85 c0 75 07 8b 42 60 85 c0 74
[ 1524.758461] EIP: [<c1406982>] per_file_stats+0x12/0x100 SS:ESP 0068:f4cbde5c
[ 1524.758485] CR2: 00000000f53af748

Reported-by: Sam Jansen <sam.jansen@starleaf.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sam Jansen <sam.jansen@starleaf.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6ed45a9..6410324 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -408,7 +408,9 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		struct file_stats stats;
 
 		memset(&stats, 0, sizeof(stats));
+		spin_lock(&file->table_lock);
 		idr_for_each(&file->object_idr, per_file_stats, &stats);
+		spin_unlock(&file->table_lock);
 		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu unbound)\n",
 			   get_pid_task(file->pid, PIDTYPE_PID)->comm,
 			   stats.count,
-- 
1.9.1

[PATCH 3.13 183/198] [CIFS] fix mount failure with broken pathnames when smb3 mount with mapchars option

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Steve French <smfrench@gmail.com>

commit ce36d9ab3bab06b7b5522f5c8b68fac231b76ffb upstream.

When we SMB3 mounted with mapchars (to allow reserved characters : \ / > < * ?
via the Unicode Windows to POSIX remap range) empty paths
(eg when we open "" to query the root of the SMB3 directory on mount) were not
null terminated so we sent garbarge as a path name on empty paths which caused
SMB2/SMB2.1/SMB3 mounts to fail when mapchars was specified.  mapchars is
particularly important since Unix Extensions for SMB3 are not supported (yet)

Signed-off-by: Steve French <smfrench@gmail.com>
Reviewed-by: David Disseldorp <ddiss@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/cifs/cifs_unicode.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45..15e9505 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@ int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		 const struct nls_table *cp, int mapChars)
 {
-	int i, j, charlen;
+	int i, charlen;
+	int j = 0;
 	char src_char;
 	__le16 dst_char;
 	wchar_t tmp;
@@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	if (!mapChars)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
-	for (i = 0, j = 0; i < srclen; j++) {
+	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
 		switch (src_char) {
 		case 0:
-			put_unaligned(0, &target[j]);
 			goto ctoUTF16_out;
 		case ':':
 			dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	}
 
 ctoUTF16_out:
+	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
 	return j;
 }
 
-- 
1.9.1

[PATCH 3.13 184/198] aio: fix aio request leak when events are reaped by userspace

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin LaHaise <bcrl@kvack.org>

commit f8567a3845ac05bb28f3c1b478ef752762bd39ef upstream.

The aio cleanups and optimizations by kmo that were merged into the 3.10
tree added a regression for userspace event reaping.  Specifically, the
reference counts are not decremented if the event is reaped in userspace,
leading to the application being unable to submit further aio requests.
This patch applies to 3.12+.  A separate backport is required for 3.10/3.11.
This issue was uncovered as part of CVE-2014-0206.

Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Petr Matousek <pmatouse@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/aio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 04cd768..e9566f2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1007,6 +1007,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 
 	/* everything turned out well, dispose of the aiocb. */
 	kiocb_free(iocb);
+	put_reqs_available(ctx, 1);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1086,8 +1087,6 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	flush_dcache_page(ctx->ring_pages[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, tail);
-
-	put_reqs_available(ctx, ret);
 out:
 	mutex_unlock(&ctx->ring_lock);
 
-- 
1.9.1

[PATCH 3.13 185/198] aio: fix kernel memory disclosure in io_getevents() introduced in v3.10

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin LaHaise <bcrl@kvack.org>

commit edfbbf388f293d70bf4b7c0bc38774d05e6f711a upstream.

A kernel memory disclosure was introduced in aio_read_events_ring() in v3.10
by commit a31ad380bed817aa25f8830ad23e1a0480fef797.  The changes made to
aio_read_events_ring() failed to correctly limit the index into
ctx->ring_pages[], allowing an attacked to cause the subsequent kmap() of
an arbitrary page with a copy_to_user() to copy the contents into userspace.
This vulnerability has been assigned CVE-2014-0206.  Thanks to Mateusz and
Petr for disclosing this issue.

This patch applies to v3.12+.  A separate backport is needed for 3.10/3.11.

Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Petr Matousek <pmatouse@redhat.com>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/aio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/aio.c b/fs/aio.c
index e9566f2..19e7d95 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1049,6 +1049,9 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	if (head == tail)
 		goto out;
 
+	head %= ctx->nr_events;
+	tail %= ctx->nr_events;
+
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
-- 
1.9.1

[PATCH 3.13 186/198] nfs: Fix cache_validity check in nfs_write_pageuptodate()

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Scott Mayhew <smayhew@redhat.com>

commit 18dd78c427513fb0f89365138be66e6ee8700d1b upstream.

NFS_INO_INVALID_DATA cannot be ignored, even if we have a delegation.

We're still having some problems with data corruption when multiple
clients are appending to a file and those clients are being granted
write delegations on open.

To reproduce:

Client A:
vi /mnt/`hostname -s`
while :; do echo "XXXXXXXXXXXXXXX" >>/mnt/file; sleep $(( $RANDOM % 5 )); done

Client B:
vi /mnt/`hostname -s`
while :; do echo "YYYYYYYYYYYYYYY" >>/mnt/file; sleep $(( $RANDOM % 5 )); done

What's happening is that in nfs_update_inode() we're recognizing that
the file size has changed and we're setting NFS_INO_INVALID_DATA
accordingly, but then we ignore the cache_validity flags in
nfs_write_pageuptodate() because we have a delegation.  As a result,
in nfs_updatepage() we're extending the write to cover the full page
even though we've not read in the data to begin with.

Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
[ kamal: backport to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 fs/nfs/write.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 6a85038..af7c958 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -911,9 +911,11 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 {
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+	if (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
 		return false;
 out:
+	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA)
+		return false;
 	return PageUptodate(page) != 0;
 }
 
-- 
1.9.1

[PATCH 3.13 187/198] powerpc: Don't skip ePAPR spin-table CPUs

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Scott Wood <scottwood@freescale.com>

commit 6663a4fa6711050036562ddfd2086edf735fae21 upstream.

Commit 59a53afe70fd530040bdc69581f03d880157f15a "powerpc: Don't setup
CPUs with bad status" broke ePAPR SMP booting.  ePAPR says that CPUs
that aren't presently running shall have status of disabled, with
enable-method being used to determine whether the CPU can be enabled.

Fix by checking for spin-table, which is currently the only supported
enable-method.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/powerpc/kernel/setup-common.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 486cc04..04aa4d3 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -456,9 +456,17 @@ void __init smp_setup_cpu_maps(void)
 		}
 
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
+			bool avail;
+
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
 			    j, cpu, be32_to_cpu(intserv[j]));
-			set_cpu_present(cpu, of_device_is_available(dn));
+
+			avail = of_device_is_available(dn);
+			if (!avail)
+				avail = !of_property_match_string(dn,
+						"enable-method", "spin-table");
+
+			set_cpu_present(cpu, avail);
 			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
-- 
1.9.1

[PATCH 3.13 188/198] net: allwinner: emac: Add missing free_irq

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Maxime Ripard <maxime.ripard@free-electrons.com>

commit b91113282bf44df46aba374a0b8f88a75bfd4b3f upstream.

If the mdio probe function fails in emac_open, the interrupt we just requested
isn't freed. If emac_open is called again, for example because we try to set up
the interface again, the kernel will oops because the interrupt wasn't properly
released.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/ethernet/allwinner/sun4i-emac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 46dfb13..81576c6 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -726,6 +726,7 @@ static int emac_open(struct net_device *dev)
 
 	ret = emac_mdio_probe(dev);
 	if (ret < 0) {
+		free_irq(dev->irq, dev);
 		netdev_err(dev, "cannot probe MDIO bus\n");
 		return ret;
 	}
-- 
1.9.1

[PATCH 3.13 189/198] ALSA: usb-audio: Fix races at disconnection and PCM closing

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <tiwai@suse.de>

commit 92a586bdc06de6629dae1b357dac221253f55ff8 upstream.

When a USB-audio device is disconnected while PCM is still running, we
still see some race: the disconnect callback calls
snd_usb_endpoint_free() that calls release_urbs() and then kfree()
while a PCM stream would be closed at the same time and calls
stop_endpoints() that leads to wait_clear_urbs().  That is, the EP
object might be deallocated while a PCM stream is syncing with
wait_clear_urbs() with the same EP.

Basically calling multiple wait_clear_urbs() would work fine, also
calling wait_clear_urbs() and release_urbs() would work, too, as
wait_clear_urbs() just reads some fields in ep.  The problem is the
succeeding kfree() in snd_pcm_endpoint_free().

This patch moves out the EP deallocation into the later point, the
destructor callback.  At this stage, all PCMs must have been already
closed, so it's safe to free the objects.

Reported-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/usb/card.c     | 13 ++++++++++---
 sound/usb/endpoint.c | 17 ++++++++++++++---
 sound/usb/endpoint.h |  1 +
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/sound/usb/card.c b/sound/usb/card.c
index d979050..af19560 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -304,6 +304,11 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 
 static int snd_usb_audio_free(struct snd_usb_audio *chip)
 {
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &chip->ep_list)
+		snd_usb_endpoint_free(p);
+
 	mutex_destroy(&chip->mutex);
 	kfree(chip);
 	return 0;
@@ -580,7 +585,7 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 				     struct snd_usb_audio *chip)
 {
 	struct snd_card *card;
-	struct list_head *p, *n;
+	struct list_head *p;
 
 	if (chip == (void *)-1L)
 		return;
@@ -593,14 +598,16 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 	mutex_lock(&register_mutex);
 	chip->num_interfaces--;
 	if (chip->num_interfaces <= 0) {
+		struct snd_usb_endpoint *ep;
+
 		snd_card_disconnect(card);
 		/* release the pcm resources */
 		list_for_each(p, &chip->pcm_list) {
 			snd_usb_stream_disconnect(p);
 		}
 		/* release the endpoint resources */
-		list_for_each_safe(p, n, &chip->ep_list) {
-			snd_usb_endpoint_free(p);
+		list_for_each_entry(ep, &chip->ep_list, list) {
+			snd_usb_endpoint_release(ep);
 		}
 		/* release the midi resources */
 		list_for_each(p, &chip->midi_list) {
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 814430f..105ece3 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -981,19 +981,30 @@ void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep)
 }
 
 /**
+ * snd_usb_endpoint_release: Tear down an snd_usb_endpoint
+ *
+ * @ep: the endpoint to release
+ *
+ * This function does not care for the endpoint's use count but will tear
+ * down all the streaming URBs immediately.
+ */
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep)
+{
+	release_urbs(ep, 1);
+}
+
+/**
  * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint
  *
  * @ep: the list header of the endpoint to free
  *
- * This function does not care for the endpoint's use count but will tear
- * down all the streaming URBs immediately and free all resources.
+ * This free all resources of the given ep.
  */
 void snd_usb_endpoint_free(struct list_head *head)
 {
 	struct snd_usb_endpoint *ep;
 
 	ep = list_entry(head, struct snd_usb_endpoint, list);
-	release_urbs(ep, 1);
 	kfree(ep);
 }
 
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 1c7e8ee..e61ee5c 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -23,6 +23,7 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_free(struct list_head *head);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
-- 
1.9.1

[PATCH 3.13 190/198] recordmcount/MIPS: Fix possible incorrect mcount_loc table entries in modules

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Smith <alex.smith@imgtec.com>

commit 91ad11d7cc6f4472ebf177a6252fbf0fd100d798 upstream.

On MIPS calls to _mcount in modules generate 2 instructions to load
the _mcount address (and therefore 2 relocations). The mcount_loc
table should only reference the first of these, so the second is
filtered out by checking the relocation offset and ignoring ones that
immediately follow the previous one seen.

However if a module has an _mcount call at offset 0, the second
relocation would not be filtered out due to old_r_offset == 0
being taken to mean that the current relocation is the first one
seen, and both would end up in the mcount_loc table.

This results in ftrace_make_nop() patching both (adjacent)
instructions to branches over the _mcount call sequence like so:

  0xffffffffc08a8000:  04 00 00 10     b       0xffffffffc08a8014
  0xffffffffc08a8004:  04 00 00 10     b       0xffffffffc08a8018
  0xffffffffc08a8008:  2d 08 e0 03     move    at,ra
  ...

The second branch is in the delay slot of the first, which is
defined to be unpredictable - on the platform on which this bug was
encountered, it triggers a reserved instruction exception.

Fix by initializing old_r_offset to ~0 and using that instead of 0
to determine whether the current relocation is the first seen.

Signed-off-by: Alex Smith <alex.smith@imgtec.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/7098/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 scripts/recordmcount.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 9d1421e..49b582a 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -163,11 +163,11 @@ static int mcount_adjust = 0;
 
 static int MIPS_is_fake_mcount(Elf_Rel const *rp)
 {
-	static Elf_Addr old_r_offset;
+	static Elf_Addr old_r_offset = ~(Elf_Addr)0;
 	Elf_Addr current_r_offset = _w(rp->r_offset);
 	int is_fake;
 
-	is_fake = old_r_offset &&
+	is_fake = (old_r_offset != ~(Elf_Addr)0) &&
 		(current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET);
 	old_r_offset = current_r_offset;
 
-- 
1.9.1

[PATCH 3.13 191/198] MIPS: MSC: Prevent out-of-bounds writes to MIPS SC ioremap'd region

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Markos Chandras <markos.chandras@imgtec.com>

commit ab6c15bc6620ebe220970cc040b29bcb2757f373 upstream.

Previously, the lower limit for the MIPS SC initialization loop was
set incorrectly allowing one extra loop leading to writes
beyond the MSC ioremap'd space. More precisely, the value of the 'imp'
in the last loop increased beyond the msc_irqmap_t boundaries and
as a result of which, the 'n' variable was loaded with an incorrect
value. This value was used later on to calculate the offset in the
MSC01_IC_SUP which led to random crashes like the following one:

CPU 0 Unable to handle kernel paging request at virtual address e75c0200,
epc == 8058dba4, ra == 8058db90
[...]
Call Trace:
[<8058dba4>] init_msc_irqs+0x104/0x154
[<8058b5bc>] arch_init_irq+0xd8/0x154
[<805897b0>] start_kernel+0x220/0x36c

Kernel panic - not syncing: Attempted to kill the idle task!

This patch fixes the problem

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Reviewed-by: James Hogan <james.hogan@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/7118/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 arch/mips/kernel/irq-msc01.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index fab40f7..ac9facc 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -131,7 +131,7 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma
 
 	board_bind_eic_interrupt = &msc_bind_eic_interrupt;
 
-	for (; nirq >= 0; nirq--, imp++) {
+	for (; nirq > 0; nirq--, imp++) {
 		int n = imp->im_irq;
 
 		switch (imp->im_type) {
-- 
1.9.1

[PATCH 3.13 192/198] ALSA: hda - restore BCLK M/N values when resuming HSW/BDW display controller

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mengdong Lin <mengdong.lin@intel.com>

commit a07187c992be945ab561b370cbb49cfd72064c3c upstream.

For Intel Haswell/Broadwell display HD-A controller, the 24MHz HD-A link BCLK
is converted from Core Display Clock (CDCLK): BCLK = CDCLK * M / N
And there are two registers EM4 and EM5 to program M, N value respectively.
The EM4/EM5 values will be lost and when the display power well is disabled.

BIOS programs CDCLK selected by OEM and EM4/EM5, but BIOS has no idea about
display power well on/off at runtime. So the M/N can be wrong if non-default
CDCLK is used when the audio controller resumes, which results in an invalid
BCLK and abnormal audio playback rate. So this patch saves and restores valid
M/N values on controller suspend/resume.

And 'struct hda_intel' is defined to contain standard HD-A 'struct azx' and
Intel specific fields, as Takashi suggested.

Signed-off-by: Mengdong Lin <mengdong.lin@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 sound/pci/hda/hda_intel.c | 63 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 56 insertions(+), 7 deletions(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 619d9a3..eab13e2 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -663,6 +663,22 @@ static char *driver_short_names[] = {
 	[AZX_DRIVER_GENERIC] = "HD-Audio Generic",
 };
 
+/* Intel HSW/BDW display HDA controller Extended Mode registers.
+ * EM4 (M value) and EM5 (N Value) are used to convert CDClk (Core Display
+ * Clock) to 24MHz BCLK: BCLK = CDCLK * M / N
+ * The values will be lost when the display power well is disabled.
+ */
+#define ICH6_REG_EM4			0x100c
+#define ICH6_REG_EM5			0x1010
+
+struct hda_intel {
+	struct azx chip;
+
+	/* HSW/BDW display HDA controller to restore BCLK from CDCLK */
+	unsigned int bclk_m;
+	unsigned int bclk_n;
+};
+
 /*
  * macros for easy use
  */
@@ -2906,6 +2922,22 @@ static int param_set_xint(const char *val, const struct kernel_param *kp)
 #define azx_del_card_list(chip) /* NOP */
 #endif /* CONFIG_PM */
 
+static void haswell_save_bclk(struct azx *chip)
+{
+	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+
+	hda->bclk_m = azx_readw(chip, EM4);
+	hda->bclk_n = azx_readw(chip, EM5);
+}
+
+static void haswell_restore_bclk(struct azx *chip)
+{
+	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+
+	azx_writew(chip, EM4, hda->bclk_m);
+	azx_writew(chip, EM5, hda->bclk_n);
+}
+
 #if defined(CONFIG_PM_SLEEP) || defined(SUPPORT_VGA_SWITCHEROO)
 /*
  * power management
@@ -2932,6 +2964,13 @@ static int azx_suspend(struct device *dev)
 		free_irq(chip->irq, chip);
 		chip->irq = -1;
 	}
+
+	/* Save BCLK M/N values before they become invalid in D3.
+	 * Will test if display power well can be released now.
+	 */
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		haswell_save_bclk(chip);
+
 	if (chip->msi)
 		pci_disable_msi(chip->pci);
 	pci_disable_device(pci);
@@ -2951,8 +2990,10 @@ static int azx_resume(struct device *dev)
 	if (chip->disabled)
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
 		hda_display_power(true);
+		haswell_restore_bclk(chip);
+	}
 	pci_set_power_state(pci, PCI_D0);
 	pci_restore_state(pci);
 	if (pci_enable_device(pci) < 0) {
@@ -2996,8 +3037,10 @@ static int azx_runtime_suspend(struct device *dev)
 	azx_stop_chip(chip);
 	azx_enter_link_reset(chip);
 	azx_clear_irq_pending(chip);
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+		haswell_save_bclk(chip);
 		hda_display_power(false);
+	}
 	return 0;
 }
 
@@ -3015,8 +3058,10 @@ static int azx_runtime_resume(struct device *dev)
 	if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME))
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
 		hda_display_power(true);
+		haswell_restore_bclk(chip);
+	}
 
 	/* Read STATESTS before controller reset */
 	status = azx_readw(chip, STATESTS);
@@ -3213,6 +3258,8 @@ static int register_vga_switcheroo(struct azx *chip)
 static int azx_free(struct azx *chip)
 {
 	struct pci_dev *pci = chip->pci;
+	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+
 	int i;
 
 	if ((chip->driver_caps & AZX_DCAPS_PM_RUNTIME)
@@ -3274,7 +3321,7 @@ static int azx_free(struct azx *chip)
 		hda_display_power(false);
 		hda_i915_exit();
 	}
-	kfree(chip);
+	kfree(hda);
 
 	return 0;
 }
@@ -3521,6 +3568,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	static struct snd_device_ops ops = {
 		.dev_free = azx_dev_free,
 	};
+	struct hda_intel *hda;
 	struct azx *chip;
 	int err;
 
@@ -3530,13 +3578,14 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
-	if (!chip) {
-		snd_printk(KERN_ERR SFX "%s: Cannot allocate chip\n", pci_name(pci));
+	hda = kzalloc(sizeof(*hda), GFP_KERNEL);
+	if (!hda) {
+		snd_printk(KERN_ERR SFX "%s: Cannot allocate hda\n", pci_name(pci));
 		pci_disable_device(pci);
 		return -ENOMEM;
 	}
 
+	chip = &hda->chip;
 	spin_lock_init(&chip->reg_lock);
 	mutex_init(&chip->open_mutex);
 	chip->card = card;
-- 
1.9.1

[PATCH 3.13 193/198] target: Fix left-over se_lun->lun_sep pointer OOPs

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 83ff42fcce070801a3aa1cd6a3269d7426271a8d upstream.

This patch fixes a left-over se_lun->lun_sep pointer OOPs when one
of the /sys/kernel/config/target/$FABRIC/$WWPN/$TPGT/lun/$LUN/alua*
attributes is accessed after the $DEVICE symlink has been removed.

To address this bug, go ahead and clear se_lun->lun_sep memory in
core_dev_unexport(), so that the existing checks for show/store
ALUA attributes in target_core_fabric_configfs.c work as expected.

Reported-by: Sebastian Herbszt <herbszt@gmx.de>
Tested-by: Sebastian Herbszt <herbszt@gmx.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/target_core_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 8d27ba6..04e9288 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -616,6 +616,7 @@ void core_dev_unexport(
 	dev->export_count--;
 	spin_unlock(&hba->device_lock);
 
+	lun->lun_sep = NULL;
 	lun->lun_se_dev = NULL;
 }
 
-- 
1.9.1

[PATCH 3.13 194/198] iscsi-target: Explicily clear login response PDU in exception path

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 683497566d48f86e04d026de1ee658dd74fc1077 upstream.

This patch adds a explicit memset to the login response PDU
exception path in iscsit_tx_login_rsp().

This addresses a regression bug introduced in commit baa4d64b
where the initiator would end up not receiving the login
response and associated status class + detail, before closing
the login connection.

Reported-by: Christophe Vu-Brugier <cvubrugier@yahoo.fr>
Tested-by: Christophe Vu-Brugier <cvubrugier@yahoo.fr>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/iscsi/iscsi_target_util.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 5477eca..ffa0eba 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1296,6 +1296,8 @@ int iscsit_tx_login_rsp(struct iscsi_conn *conn, u8 status_class, u8 status_deta
 	login->login_failed = 1;
 	iscsit_collect_login_stats(conn, status_class, status_detail);
 
+	memset(&login->rsp[0], 0, ISCSI_HDR_LEN);
+
 	hdr	= (struct iscsi_login_rsp *)&login->rsp[0];
 	hdr->opcode		= ISCSI_OP_LOGIN_RSP;
 	hdr->status_class	= status_class;
-- 
1.9.1

[PATCH 3.13 195/198] efi-pstore: Fix an overflow on 32-bit builds

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andrzej Zaborowski <andrew.zaborowski@intel.com>

commit 783ee43118dc773bc8b0342c5b230e017d5a04d0 upstream.

In generic_id the long int timestamp is multiplied by 100000 and needs
an explicit cast to u64.

Without that the id in the resulting pstore filename is wrong and
userspace may have problems parsing it, but more importantly files in
pstore can never be deleted and may fill the EFI flash (brick device?).
This happens because when generic pstore code wants to delete a file,
it passes the id to the EFI backend which reinterpretes it and a wrong
variable name is attempted to be deleted.  There's no error message but
after remounting pstore, deleted files would reappear.

Signed-off-by: Andrew Zaborowski <andrew.zaborowski@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/firmware/efi/efi-pstore.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 4b9dc83..e992abc 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -40,7 +40,7 @@ struct pstore_read_data {
 static inline u64 generic_id(unsigned long timestamp,
 			     unsigned int part, int count)
 {
-	return (timestamp * 100 + part) * 1000 + count;
+	return ((u64) timestamp * 100 + part) * 1000 + count;
 }
 
 static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
-- 
1.9.1

[PATCH 3.13 196/198] lz4: fix another possible overrun

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 4148c1f67abf823099b2d7db6851e4aea407f5ee upstream.

There is one other possible overrun in the lz4 code as implemented by
Linux at this point in time (which differs from the upstream lz4
codebase, but will get synced at in a future kernel release.)  As
pointed out by Don, we also need to check the overflow in the data
itself.

While we are at it, replace the odd error return value with just a
"simple" -1 value as the return value is never used for anything other
than a basic "did this work or not" check.

Reported-by: "Don A. Bailey" <donb@securitymouse.com>
Reported-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 lib/lz4/lz4_decompress.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 99a03ac..b74da44 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -108,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 		if (length == ML_MASK) {
 			for (; *ip == 255; length += 255)
 				ip++;
+			if (unlikely(length > (size_t)(length + *ip)))
+				goto _output_error;
 			length += *ip++;
 		}
 
@@ -157,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *)ip) - source));
+	return -1;
 }
 
 static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
-- 
1.9.1

[PATCH 3.13 197/198] iscsi-target: Avoid rejecting incorrect ITT for Data-Out

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 97c99b47ac58bacb7c09e1f47d5d184434f6b06a upstream.

This patch changes iscsit_check_dataout_hdr() to dump the incoming
Data-Out payload when the received ITT is not associated with a
WRITE, instead of calling iscsit_reject_cmd() for the non WRITE
ITT descriptor.

This addresses a bug where an initiator sending an Data-Out for
an ITT associated with a READ would end up generating a reject
for the READ, eventually resulting in list corruption.

Reported-by: Santosh Kulkarni <santosh.kulkarni@calsoftinc.com>
Reported-by: Arshad Hussain <arshad.hussain@calsoftinc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/iscsi/iscsi_target.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 711dff4..6c727b9 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1289,7 +1289,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 	if (cmd->data_direction != DMA_TO_DEVICE) {
 		pr_err("Command ITT: 0x%08x received DataOUT for a"
 			" NON-WRITE command.\n", cmd->init_task_tag);
-		return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf);
+		return iscsit_dump_data_payload(conn, payload_length, 1);
 	}
 	se_cmd = &cmd->se_cmd;
 	iscsit_mod_dataout_timer(cmd);
-- 
1.9.1

[PATCH 3.13 198/198] iscsi-target: fix iscsit_del_np deadlock on unload

[Kamal Mostafa]

3.13.11.5 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <mpatocka@redhat.com>

commit 81a9c5e72bdf7109a65102ca61d8cbd722cf4021 upstream.

On uniprocessor preemptible kernel, target core deadlocks on unload. The
following events happen:
* iscsit_del_np is called
* it calls send_sig(SIGINT, np->np_thread, 1);
* the scheduler switches to the np_thread
* the np_thread is woken up, it sees that kthread_should_stop() returns
  false, so it doesn't terminate
* the np_thread clears signals with flush_signals(current); and goes back
  to sleep in iscsit_accept_np
* the scheduler switches back to iscsit_del_np
* iscsit_del_np calls kthread_stop(np->np_thread);
* the np_thread is waiting in iscsit_accept_np and it doesn't respond to
  kthread_stop

The deadlock could be resolved if the administrator sends SIGINT signal to
the np_thread with killall -INT iscsi_np

The reproducible deadlock was introduced in commit
db6077fd0b7dd41dc6ff18329cec979379071f87, but the thread-stopping code was
racy even before.

This patch fixes the problem. Using kthread_should_stop to stop the
np_thread is unreliable, so we test np_thread_state instead. If
np_thread_state equals ISCSI_NP_THREAD_SHUTDOWN, the thread exits.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/target/iscsi/iscsi_target_login.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 369ef10..1b2db7a 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1195,7 +1195,7 @@ old_sess_out:
 static int __iscsi_target_login_thread(struct iscsi_np *np)
 {
 	u8 *buffer, zero_tsih = 0;
-	int ret = 0, rc, stop;
+	int ret = 0, rc;
 	struct iscsi_conn *conn = NULL;
 	struct iscsi_login *login;
 	struct iscsi_portal_group *tpg = NULL;
@@ -1209,6 +1209,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 		complete(&np->np_restart_comp);
+	} else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) {
+		spin_unlock_bh(&np->np_thread_lock);
+		goto exit;
 	} else {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 	}
@@ -1401,10 +1404,8 @@ old_sess_out:
 	}
 
 out:
-	stop = kthread_should_stop();
-	/* Wait for another socket.. */
-	if (!stop)
-		return 1;
+	return 1;
+
 exit:
 	iscsi_stop_login_thread_timer(np);
 	spin_lock_bh(&np->np_thread_lock);
@@ -1421,7 +1422,7 @@ int iscsi_target_login_thread(void *arg)
 
 	allow_signal(SIGINT);
 
-	while (!kthread_should_stop()) {
+	while (1) {
 		ret = __iscsi_target_login_thread(np);
 		/*
 		 * We break and exit here unless another sock_accept() call
-- 
1.9.1