[3.16.y-ckt stable] Linux 3.16.7-ckt26 stable review

[3.16.y-ckt stable] Linux 3.16.7-ckt26 stable review

[Luis Henriques]

This is the start of the review cycle for the Linux 3.16.7-ckt26 stable
kernel.

This version contains 142 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/ubuntu/linux.git/log/?h=linux-3.16.y-review

git://kernel.ubuntu.com/ubuntu/linux.git  linux-3.16.y-review

The review period for version 3.16.7-ckt26 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 3.16.y-ckt extended stable kernel
series, see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable .

 -Luis

--
 Documentation/filesystems/efivarfs.txt         |   7 +
 Documentation/networking/ip-sysctl.txt         |   8 +
 arch/arm/boot/dts/kirkwood-ds112.dts           |   2 +-
 arch/arm/kvm/guest.c                           |   2 +-
 arch/mips/kernel/traps.c                       |  13 +-
 arch/powerpc/kernel/module_64.c                |   2 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S        |  14 ++
 arch/x86/ia32/ia32entry.S                      |   1 +
 arch/x86/kernel/acpi/sleep.c                   |   7 +
 arch/x86/kvm/paging_tmpl.h                     |   2 +-
 arch/x86/kvm/vmx.c                             |   7 +
 arch/x86/kvm/x86.c                             |   9 +-
 block/bio.c                                    |   9 +-
 crypto/ablkcipher.c                            |   1 +
 crypto/blkcipher.c                             |   1 +
 drivers/ata/libata-scsi.c                      |  11 +-
 drivers/dma/dw/core.c                          |  15 +-
 drivers/firmware/dmi_scan.c                    |   5 +-
 drivers/firmware/efi/efivars.c                 |  33 ++-
 drivers/firmware/efi/vars.c                    | 144 +++++++++----
 drivers/gpio/gpio-rcar.c                       |  42 ++++
 drivers/gpu/drm/ast/ast_main.c                 |   2 +-
 drivers/gpu/drm/i915/intel_dsi_panel_vbt.c     |   8 +-
 drivers/gpu/drm/i915/intel_i2c.c               |   2 +-
 drivers/gpu/drm/qxl/qxl_ioctl.c                |   3 +-
 drivers/gpu/drm/radeon/radeon_device.c         |   1 -
 drivers/gpu/drm/radeon/radeon_pm.c             |   8 +-
 drivers/gpu/drm/radeon/radeon_sa.c             |   5 -
 drivers/gpu/drm/radeon/radeon_ttm.c            |   2 +-
 drivers/hwmon/ads1015.c                        |   2 +-
 drivers/infiniband/core/sa_query.c             |   2 +-
 drivers/input/tablet/aiptek.c                  |   9 +
 drivers/iommu/amd_iommu_init.c                 |  34 ++--
 drivers/iommu/dmar.c                           |   2 +-
 drivers/iommu/intel_irq_remapping.c            |   2 +-
 drivers/md/bcache/super.c                      |   2 +
 drivers/media/i2c/adv7604.c                    |   3 +-
 drivers/mtd/ubi/upd.c                          |   2 +-
 drivers/net/bonding/bond_main.c                |  40 ++--
 drivers/net/can/usb/ems_usb.c                  |  14 +-
 drivers/net/can/usb/gs_usb.c                   |  24 +--
 drivers/net/ethernet/broadcom/tg3.c            |  25 ++-
 drivers/net/ethernet/mellanox/mlx4/en_clock.c  |  25 ++-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  11 +-
 drivers/net/ethernet/mellanox/mlx4/en_port.c   |   4 +-
 drivers/net/ethernet/moxa/moxart_ether.c       |   4 +-
 drivers/net/phy/bcm7xxx.c                      |   2 +-
 drivers/net/phy/dp83640.c                      |  17 ++
 drivers/net/ppp/pppoe.c                        |   2 +
 drivers/net/usb/cdc_ncm.c                      |  21 +-
 drivers/net/usb/qmi_wwan.c                     |   1 +
 drivers/pci/xen-pcifront.c                     |  10 +-
 drivers/s390/block/dasd_alias.c                |  23 ++-
 drivers/scsi/scsi_sysfs.c                      |   6 +-
 drivers/staging/android/binder.c               |   2 +-
 drivers/target/target_core_tmr.c               | 137 ++++++++++---
 drivers/target/target_core_transport.c         | 272 +++++++++++++++++--------
 drivers/usb/chipidea/otg.c                     |   2 +-
 drivers/usb/dwc3/core.h                        |   1 -
 drivers/usb/dwc3/ep0.c                         |   5 -
 drivers/usb/dwc3/gadget.c                      |  70 +++++--
 drivers/usb/serial/cp210x.c                    |   3 +
 drivers/usb/serial/option.c                    |  14 ++
 drivers/usb/serial/qcserial.c                  |   7 +-
 drivers/vfio/pci/vfio_pci.c                    |   9 +-
 drivers/vfio/vfio_iommu_type1.c                |   6 +-
 drivers/xen/xen-pciback/pciback_ops.c          |   9 +-
 fs/aio.c                                       |   9 +-
 fs/cifs/cifsencrypt.c                          |   2 +-
 fs/cifs/cifsfs.h                               |  12 +-
 fs/cifs/cifssmb.c                              |  21 +-
 fs/cifs/smb2pdu.c                              |  24 ++-
 fs/efivarfs/file.c                             |  70 +++++++
 fs/efivarfs/inode.c                            |  30 ++-
 fs/efivarfs/internal.h                         |   3 +-
 fs/efivarfs/super.c                            |  16 +-
 fs/ext4/inode.c                                |  72 +++++--
 fs/ext4/move_extent.c                          |  16 +-
 fs/ext4/resize.c                               |   2 +-
 fs/hpfs/namei.c                                |  31 +--
 fs/jffs2/README.Locking                        |   5 +-
 fs/jffs2/build.c                               |  75 +++++--
 fs/jffs2/file.c                                |  39 ++--
 fs/jffs2/gc.c                                  |  17 +-
 fs/jffs2/nodelist.h                            |   6 +-
 fs/namei.c                                     |   4 +
 fs/nfs/nfs4proc.c                              |   4 +-
 include/linux/ata.h                            |   4 +-
 include/linux/compiler.h                       |   2 +-
 include/linux/efi.h                            |   5 +-
 include/linux/ipv6.h                           |   1 +
 include/linux/libata.h                         |   2 +-
 include/linux/nfs_fs.h                         |   4 +-
 include/linux/skbuff.h                         |  25 +++
 include/linux/tracepoint.h                     |  17 +-
 include/linux/ucs2_string.h                    |   4 +
 include/net/ip_fib.h                           |   1 +
 include/net/iw_handler.h                       |   6 +
 include/target/target_core_base.h              |   2 +
 include/uapi/linux/ipv6.h                      |   1 +
 kernel/resource.c                              |   5 +-
 kernel/trace/trace_events.c                    |   3 +-
 lib/ucs2_string.c                              |  62 ++++++
 net/ceph/messenger.c                           |   4 +-
 net/core/skbuff.c                              |   2 +
 net/core/sysctl_net_core.c                     |  10 +
 net/ipv4/devinet.c                             |   2 +-
 net/ipv4/igmp.c                                |   3 +-
 net/ipv4/ip_sockglue.c                         |   2 +
 net/ipv4/ping.c                                |   4 +-
 net/ipv4/raw.c                                 |   4 +-
 net/ipv4/route.c                               |  77 +++++--
 net/ipv4/tcp.c                                 |   4 +-
 net/ipv4/tcp_ipv4.c                            |  13 +-
 net/ipv4/tcp_metrics.c                         |   2 +-
 net/ipv4/udp.c                                 |   4 +-
 net/ipv6/addrconf.c                            |  12 +-
 net/ipv6/datagram.c                            |   3 +
 net/ipv6/exthdrs_core.c                        |   6 +-
 net/ipv6/mcast.c                               |   3 +-
 net/ipv6/ndisc.c                               |  16 +-
 net/iucv/af_iucv.c                             |   3 +
 net/mac80211/agg-rx.c                          |   2 +-
 net/mac80211/rc80211_minstrel_ht.c             |   2 +-
 net/sctp/protocol.c                            |  47 ++++-
 net/sunrpc/cache.c                             |   2 +-
 net/unix/af_unix.c                             |  23 ++-
 net/unix/diag.c                                |   2 +-
 net/wireless/core.c                            |   2 +
 net/wireless/wext-core.c                       |  52 ++++-
 sound/core/control_compat.c                    |  90 ++++++--
 sound/core/rawmidi_compat.c                    |  53 +++++
 sound/core/seq/oss/seq_oss.c                   |   2 -
 sound/core/seq/oss/seq_oss_device.h            |   1 -
 sound/core/seq/oss/seq_oss_init.c              |  16 --
 sound/core/seq/seq_fifo.c                      |   4 +-
 sound/core/seq/seq_memory.c                    |  19 +-
 sound/core/seq/seq_ports.c                     |  17 +-
 sound/core/seq/seq_prioq.c                     |   4 +-
 sound/core/seq/seq_queue.c                     |   4 +-
 sound/core/seq/seq_timer.c                     |   4 +-
 sound/core/timer_compat.c                      |  18 +-
 sound/pci/hda/patch_realtek.c                  |  17 ++
 sound/pci/rme9652/hdsp.c                       |   4 +-
 sound/pci/rme9652/hdspm.c                      |  16 +-
 sound/soc/codecs/wm8958-dsp2.c                 |   8 +-
 sound/soc/codecs/wm8994.c                      |   4 +-
 sound/soc/codecs/wm_adsp.c                     |   8 +-
 tools/testing/selftests/efivarfs/efivarfs.sh   |  19 +-
 tools/testing/selftests/efivarfs/open-unlink.c |  72 ++++++-
 virt/kvm/async_pf.c                            |   2 +-
 151 files changed, 1800 insertions(+), 680 deletions(-)

Al Viro (1):
      do_last(): don't let a bogus return value from ->open() et.al. to confuse us

Alex Deucher (3):
      drm/radeon/pm: adjust display configuration after powerstate
      drm/radeon/pm: update current crtc info after setting the powerstate
      Revert "drm/radeon/pm: adjust display configuration after powerstate"

Amir Vadai (1):
      net/mlx4_en: Count HW buffer overrun only once

Andreas Schwab (1):
      powerpc: Fix dedotify for binutils >= 2.26

Andrey Skvortsov (1):
      USB: option: add support for SIM7100E

Andy Lutomirski (1):
      x86/entry/compat: Add missing CLAC to entry_INT80_32

Andy Shevchenko (1):
      dmaengine: dw: disable BLOCK IRQs for non-cyclic xfer

Anton Protopopov (2):
      cifs: fix erroneous return value
      rtnl: RTM_GETNETCONF: fix wrong return value

Arnd Bergmann (2):
      tracing: Fix freak link error caused by branch tracer
      libata: fix HDIO_GET_32BIT ioctl

Ben Hutchings (1):
      crypto: {blk,giv}cipher: Set has_setkey

Benjamin Coddington (1):
      NFSv4: Fix a dentry leak on alias use

Benjamin Poirier (1):
      mld, igmp: Fix reserved tailroom calculation

Bjørn Mork (4):
      USB: option: add "4G LTE usb-modem U901"
      qmi_wwan: add "4G LTE usb-modem U901"
      USB: qcserial: add Sierra Wireless EM74xx device ID
      cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind

CQ Tang (1):
      iommu/vt-d: Fix 64-bit accesses to 32-bit DMAR_GSTS_REG

Chris Bainbridge (1):
      mac80211: fix use of uninitialised values in RX aggregation

Christian Borntraeger (1):
      KVM: async_pf: do not warn on page allocation failures

Christoph Hellwig (1):
      nfs: fix nfs_size_to_loff_t

Dan Carpenter (1):
      net: moxa: fix an error code

Daniele Palmas (1):
      USB: serial: option: add support for Telit LE922 PID 0x1045

David Woodhouse (2):
      jffs2: Fix page lock / f->sem deadlock
      Fix directory hardlinks from deleted directories

Dmitry V. Levin (1):
      unix_diag: fix incorrect sign extension in unix_lookup_by_ino

Eric Dumazet (2):
      tcp: fix NULL deref in tcp_v4_send_ack()
      ipv4: fix memory leaks in ip_cmsg_send() callers

Eryu Guan (2):
      ext4: don't read blocks from disk after extents being swapped
      ext4: iterate over buffer heads correctly in move_extent_per_page()

Eugenia Emantayev (2):
      net/mlx4_en: Choose time-stamping shift value according to HW frequency
      net/mlx4_en: Avoid changing dev->features directly in run-time

Felix Fietkau (1):
      mac80211: minstrel_ht: set default tx aggregation timeout to 0

Florian Fainelli (1):
      net: phy: bcm7xxx: Fix shadow mode 2 disabling

Florian Westphal (1):
      ipv6: re-enable fragment header matching in ipv6_find_hdr

Geert Uytterhoeven (1):
      gpio: rcar: Add Runtime PM handling for interrupts

Gerd Hoffmann (1):
      drm/qxl: use kmalloc_array to alloc reloc_info in qxl_process_single_command

Gerhard Uttenthaler (1):
      can: ems_usb: Fix possible tx overflow

Greg Kroah-Hartman (1):
      AIO: properly check iovec sizes

Guillaume Nault (1):
      pppoe: fix reference counting in PPPoE proxy

Hangbin Liu (1):
      net/ipv6: add sysctl option accept_ra_min_hop_limit

Hannes Reinecke (1):
      bio: return EINTR if copying to user space got interrupted

Hans Verkuil (1):
      [media] adv7604: fix tx 5v detect regression

Hans Westgaard Ry (1):
      net:Add sysctl_max_skb_frags

Harvey Hunt (1):
      libata: Align ata_device's id on a cacheline

Heinrich Schuchardt (1):
      ARM: dts: kirkwood: use unique machine name for ds112

Ilya Dryomov (1):
      libceph: don't bail early from try_read() when skipping a message

Insu Yun (1):
      ext4: fix potential integer overflow

Jack Morgenstein (1):
      net/mlx4_core: Allow resetting VF admin mac to zero

James Bottomley (1):
      scsi: fix soft lockup in scsi_remove_target() on module removal

Jan Kara (2):
      ext4: fix bh->b_state corruption
      ext4: fix crashes in dioread_nolock mode

Jani Nikula (2):
      drm/i915/dsi: defend gpio table against out of bounds access
      drm/i915/dsi: don't pass arbitrary data to sideband

Jason Andryuk (1):
      lib/ucs2_string: Correct ucs2 -> utf8 conversion

Jay Vosburgh (1):
      bonding: Fix ARP monitor validation

Jianjian Huo (1):
      bcache: add mutex lock for bch_is_open

Johannes Berg (2):
      wext: fix message delay/ordering
      cfg80211/wext: fix message ordering

John Youn (1):
      usb: dwc3: Fix assignment of EP transfer resources

Justin Maggard (1):
      cifs: fix out-of-bounds access in lease parsing

Kai-Heng Feng (1):
      ALSA: hda - Fixing background noise on Dell Inspiron 3162

Ken Lin (1):
      USB: cp210x: add IDs for GE B650V3 and B850V3 boards

Konrad Rzeszutek Wilk (3):
      xen/pciback: Check PF instead of VF for PCI_COMMAND_MEMORY
      xen/pciback: Save the number of MSI-X entries to be copied later.
      xen/pcifront: Fix mysterious crashes when NUMA locality information was extracted.

Konstantin Khlebnikov (1):
      tcp: convert cached rtt from usec to jiffies when feeding initial rto

Linus Torvalds (1):
      Revert "drm/radeon: call hpd_irq_event on resume"

Lisa Du (1):
      drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE

Luis Henriques (2):
      Revert "firmware: dmi_scan: Fix UUID endianness for SMBIOS >= 2.6"
      Revert "drm/radeon: hold reference to fences in radeon_sa_bo_new"

Maciej W. Rozycki (1):
      MIPS: traps: Fix SIGFPE information leak from `do_ov' and `do_trap_or_bp'

Manfred Rudigier (1):
      net: dp83640: Fix tx timestamp overflow handling.

Marcelo Tosatti (1):
      KVM: x86: move steal time initialization to vcpu entry time

Matt Fleming (1):
      efi: Add pstore variables to the deletion whitelist

Maximilain Schneider (1):
      can: gs_usb: fixed disconnect bug by removing erroneous use of kfree()

Michael S. Tsirkin (2):
      vfio: fix ioctl error handling
      arm/arm64: KVM: Fix ioctl error handling

Mike Krinkin (1):
      KVM: x86: MMU: fix ubsan index-out-of-range warning

Mikulas Patocka (1):
      hpfs: don't truncate the file when delete fails

Neil Horman (1):
      sctp: Fix port hash table size computation

Nicholas Bellinger (6):
      target: Fix LUN_RESET active TMR descriptor handling
      target: Fix LUN_RESET active I/O handling for ACK_KREF
      target: Fix TAS handling for multi-session se_node_acls
      target: Fix remote-port TMR ABORT + se_cmd fabric stop
      target: Fix race with SCF_SEND_DELAYED_TAS handling
      target: Drop incorrect ABORT_TASK put for completed commands

Or Gerlitz (1):
      IB/core: Use GRH when the path hop-limit > 0

Paolo Abeni (1):
      ipv6/udp: use sticky pktinfo egress ifindex on connect()

Patrik Halfar (1):
      USB: qcserial: add Dell Wireless 5809e Gobi 4G HSPA+ (rev3)

Paul Mackerras (1):
      KVM: PPC: Book3S HV: Sanitize special-purpose register values on guest exit

Pavel Shilovsky (1):
      CIFS: Fix SMB2+ interim response processing for read requests

Peter Chen (1):
      usb: chipidea: otg: change workqueue ci_otg as freezable

Peter Jones (5):
      lib/ucs2_string: Add ucs2 -> utf8 helper functions
      efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version
      efi: Do variable name validation tests in utf8
      efi: Make our variable validation list include the guid
      efi: Make efivarfs entries immutable by default

Peter Rosin (1):
      hwmon: (ads1015) Handle negative conversion values correctly

Radim Krčmář (1):
      KVM: VMX: disable PEBS before a guest entry

Rainer Weikusat (2):
      af_unix: Don't set err in unix_stream_read_generic unless there was an error
      af_unix: Guard against other == sk in unix_dgram_sendmsg

Rasmus Villemoes (2):
      drm/i915: fix error path in intel_setup_gmbus()
      drm/radeon: use post-decrement in error handling

Richard Weinberger (1):
      ubi: Fix out of bounds write in volume update code

Simon Guinot (1):
      kernel/resource.c: fix muxed resource handling in __request_region()

Simon South (1):
      ALSA: hda - Fix mic issues on Acer Aspire E1-472

Siva Reddy Kallam (1):
      tg3: Fix for tg3 transmit queue 0 timed out when too many gso_segs

Stefan Haberland (2):
      s390/dasd: prevent incorrect length error under z/VM after PAV changes
      s390/dasd: fix refcount for PAV reassignment

Stefan Hajnoczi (1):
      sunrpc/cache: fix off-by-one in qword_get()

Steven Rostedt (Red Hat) (3):
      tracepoints: Do not trace when cpu is offline
      tracing: Fix showing function event in available_events
      tracing: Fix check for cpu online when event is disabled

Suravee Suthikulpanit (1):
      iommu/amd: Fix boot warning when device 00:00.0 is not iommu covered

Takashi Iwai (15):
      ALSA: seq: Drop superfluous error/debug messages after malloc failures
      ALSA: seq: Fix leak of pool buffer at concurrent writes
      ALSA: seq: Fix double port list deletion
      ALSA: hda - Fix headset support and noise on HP EliteBook 755 G2
      ALSA: ctl: Fix ioctls for X32 ABI
      ALSA: rawmidi: Fix ioctls X32 ABI
      ALSA: timer: Fix broken compat timer user status ioctl
      ALSA: timer: Fix ioctls for X32 ABI
      ALSA: hdspm: Fix wrong boolean ctl value accesses
      ALSA: hdspm: Fix zero-division
      ALSA: hdsp: Fix wrong boolean ctl value accesses
      ALSA: seq: oss: Don't drain at closing a client
      ASoC: wm8958: Fix enum ctl accesses in a wrong type
      ASoC: wm8994: Fix enum ctl accesses in a wrong type
      ASoC: wm_adsp: Fix enum ctl accesses in a wrong type

Thomas Betker (1):
      Revert "jffs2: Fix lock acquisition order bug in jffs2_write_begin"

Timothy Pearson (1):
      drm/ast: Fix incorrect register check for DRAM width

Todd E Brandt (1):
      PM / sleep / x86: Fix crash on graph trace through x86 suspend

Ursula Braun (1):
      af_iucv: Validate socket address length in iucv_sock_bind()

Vittorio Alfieri (1):
      USB: cp210x: Add ID for Parrot NMEA GPS Flight Recorder

Vladis Dronov (1):
      Input: aiptek - fix crash on detecting device without endpoints

Xin Long (1):
      route: check and remove route cache when we get route

Yadan Fan (1):
      Fix cifs_uniqueid_to_ino_t() function for s390x

Yegor Yefremov (1):
      USB: serial: option: add support for Quectel UC20

[PATCH 3.16.y-ckt 001/142] Revert "firmware: dmi_scan: Fix UUID endianness for SMBIOS >= 2.6"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Luis Henriques <luis.henriques@canonical.com>

This reverts commit 0f7b4f7914e450b1bcffdbd26bbf35ee304cbfea, which was
commit ff4319dc7cd58c92b389960e375038335d157a60 upstream.

This commit introduced a regression in this kernel.  Commit 95be58df74a5
("firmware: dmi_scan: Use full dmi version for SMBIOS3") added support for
SMBIOS3.  However, this was not backport to this kernel version, and thus
commit ff4319dc7cd5 should have not been applied.

BugLink: https://bugs.launchpad.net/bugs/1551419
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/firmware/dmi_scan.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 48142b88e672..35286fe52823 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -493,7 +493,6 @@ static int __init dmi_present(const u8 *buf)
 			dmi_ver = smbios_ver;
 		else
 			dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F);
-		dmi_ver <<= 8;
 		dmi_num = (buf[13] << 8) | buf[12];
 		dmi_len = (buf[7] << 8) | buf[6];
 		dmi_base = (buf[11] << 24) | (buf[10] << 16) |
@@ -502,10 +501,10 @@ static int __init dmi_present(const u8 *buf)
 		if (dmi_walk_early(dmi_decode) == 0) {
 			if (smbios_ver) {
 				pr_info("SMBIOS %d.%d present.\n",
-					dmi_ver >> 16, (dmi_ver >> 8) & 0xFF);
+				       dmi_ver >> 8, dmi_ver & 0xFF);
 			} else {
 				pr_info("Legacy DMI %d.%d present.\n",
-					dmi_ver >> 16, (dmi_ver >> 8) & 0xFF);
+				       dmi_ver >> 8, dmi_ver & 0xFF);
 			}
 			dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string));
 			printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string);

[PATCH 3.16.y-ckt 002/142] iommu/vt-d: Fix 64-bit accesses to 32-bit DMAR_GSTS_REG

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: CQ Tang <cq.tang@intel.com>

commit fda3bec12d0979aae3f02ee645913d66fbc8a26e upstream.

This is a 32-bit register. Apparently harmless on real hardware, but
causing justified warnings in simulation.

Signed-off-by: CQ Tang <cq.tang@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/iommu/dmar.c                | 2 +-
 drivers/iommu/intel_irq_remapping.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 55f1515d54c9..04a5e5366ac0 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1246,7 +1246,7 @@ void dmar_disable_qi(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts =  readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_QIES))
 		goto end;
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 9b174893f0f5..c21e80461d2d 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -504,7 +504,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_IRES))
 		goto end;
 

[PATCH 3.16.y-ckt 003/142] drm/i915/dsi: defend gpio table against out of bounds access

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jani Nikula <jani.nikula@intel.com>

commit 4db3a2448ec8902310acb78de39b6227a9a56ac8 upstream.

Do not blindly trust the VBT data used for indexing.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/cc32d40c2b47f2d2151811855ac2c3dabab1d57d.1454582914.git.jani.nikula@intel.com
(cherry picked from commit 5d2d0a12d3d08bf50434f0b5947bb73bac04b941)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/i915/intel_dsi_panel_vbt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index 21a0d348cedc..9db5dc8f4521 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -173,6 +173,11 @@ static u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, u8 *data)
 	/* pull up/down */
 	action = *data++;
 
+	if (gpio >= ARRAY_SIZE(gtable)) {
+		DRM_DEBUG_KMS("unknown gpio %u\n", gpio);
+		goto out;
+	}
+
 	function = gtable[gpio].function_reg;
 	pad = gtable[gpio].pad_reg;
 
@@ -190,6 +195,7 @@ static u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, u8 *data)
 	vlv_gpio_nc_write(dev_priv, pad, val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
+out:
 	return data;
 }
 

[PATCH 3.16.y-ckt 004/142] drm/i915/dsi: don't pass arbitrary data to sideband

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jani Nikula <jani.nikula@intel.com>

commit 26f6f2d301c1fb46acb1138ee155125815239b0d upstream.

Since sequence block v2 the second byte contains flags other than just
pull up/down. Don't pass arbitrary data to the sideband interface.

The rest may or may not work for sequence block v2, but there should be
no harm done.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/ebe3c2eee623afc4b3a134533b01f8d591d13f32.1454582914.git.jani.nikula@intel.com
(cherry picked from commit 4e1c63e3761b84ec7d87c75b58bbc8bcf18e98ee)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/i915/intel_dsi_panel_vbt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index 9db5dc8f4521..53dbd2e85f06 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -171,7 +171,7 @@ static u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, u8 *data)
 	gpio = *data++;
 
 	/* pull up/down */
-	action = *data++;
+	action = *data++ & 1;
 
 	if (gpio >= ARRAY_SIZE(gtable)) {
 		DRM_DEBUG_KMS("unknown gpio %u\n", gpio);

[PATCH 3.16.y-ckt 005/142] powerpc: Fix dedotify for binutils >= 2.26

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Andreas Schwab <schwab@linux-m68k.org>

commit f15838e9cac8f78f0cc506529bb9d3b9fa589c1f upstream.

Since binutils 2.26 BFD is doing suffix merging on STRTAB sections.  But
dedotify modifies the symbol names in place, which can also modify
unrelated symbols with a name that matches a suffix of a dotted name.  To
remove the leading dot of a symbol name we can just increment the pointer
into the STRTAB section instead.

Backport to all stables to avoid breakage when people update their
binutils - mpe.

Signed-off-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/powerpc/kernel/module_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ec4106224d89..1a24e1c47588 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -337,7 +337,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 		if (syms[i].st_shndx == SHN_UNDEF) {
 			char *name = strtab + syms[i].st_name;
 			if (name[0] == '.')
-				memmove(name, name+1, strlen(name));
+				syms[i].st_name++;
 		}
 	}
 }

[PATCH 3.16.y-ckt 006/142] drm/i915: fix error path in intel_setup_gmbus()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Rasmus Villemoes <linux@rasmusvillemoes.dk>

commit ed3f9fd1e865975ceefdb2a43b453e090b1fd787 upstream.

This fails to undo the setup for pin==0; moreover, something
interesting happens if the setup failed already at pin==0.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Fixes: f899fc64cda8 ("drm/i915: use GMBUS to manage i2c links")
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1455048677-19882-3-git-send-email-linux@rasmusvillemoes.dk
(cherry picked from commit 2417c8c03f508841b85bf61acc91836b7b0e2560)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
[ luis: backported to 3.16:
  - use 'i' instead of 'pin'
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/i915/intel_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 81f8ec85a48a..a9cbe5e146fb 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -680,7 +680,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 	return 0;
 
 err:
-	while (--i) {
+	while (i--) {
 		struct intel_gmbus *bus = &dev_priv->gmbus[i];
 		i2c_del_adapter(&bus->adapter);
 	}

[PATCH 3.16.y-ckt 007/142] cifs: fix erroneous return value

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Anton Protopopov <a.s.protopopov@gmail.com>

commit 4b550af519854421dfec9f7732cdddeb057134b2 upstream.

The setup_ntlmv2_rsp() function may return positive value ENOMEM instead
of -ENOMEM in case of kmalloc failure.

Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/cifs/cifsencrypt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 3299778391fd..0bd335a393f8 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -710,7 +710,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}

[PATCH 3.16.y-ckt 008/142] s390/dasd: prevent incorrect length error under z/VM after PAV changes

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Stefan Haberland <stefan.haberland@de.ibm.com>

commit 020bf042e5b397479c1174081b935d0ff15d1a64 upstream.

The channel checks the specified length and the provided amount of
data for CCWs and provides an incorrect length error if the size does
not match. Under z/VM with simulation activated the length may get
changed. Having the suppress length indication bit set is stated as
good CCW coding practice and avoids errors under z/VM.

Signed-off-by: Stefan Haberland <stefan.haberland@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/s390/block/dasd_alias.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index a2597e683e79..d52d7a23b2e7 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -722,7 +722,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
-	ccw->flags = 0 ;
+	ccw->flags = CCW_FLAG_SLI;
 	ccw->count = 16;
 	ccw->cda = (__u32)(addr_t) cqr->data;
 	((char *)cqr->data)[0] = reason;

[PATCH 3.16.y-ckt 009/142] s390/dasd: fix refcount for PAV reassignment

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Stefan Haberland <stefan.haberland@de.ibm.com>

commit 9d862ababb609439c5d6987f6d3ddd09e703aa0b upstream.

Add refcount to the DASD device when a summary unit check worker is
scheduled. This prevents that the device is set offline with worker
in place.

Signed-off-by: Stefan Haberland <stefan.haberland@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/s390/block/dasd_alias.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index d52d7a23b2e7..6a64e86e8ccd 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -264,8 +264,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		spin_unlock_irqrestore(&lcu->lock, flags);
 		cancel_work_sync(&lcu->suc_data.worker);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->suc_data.device)
+		if (device == lcu->suc_data.device) {
+			dasd_put_device(device);
 			lcu->suc_data.device = NULL;
+		}
 	}
 	was_pending = 0;
 	if (device == lcu->ruac_data.device) {
@@ -273,8 +275,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		was_pending = 1;
 		cancel_delayed_work_sync(&lcu->ruac_data.dwork);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->ruac_data.device)
+		if (device == lcu->ruac_data.device) {
+			dasd_put_device(device);
 			lcu->ruac_data.device = NULL;
+		}
 	}
 	private->lcu = NULL;
 	spin_unlock_irqrestore(&lcu->lock, flags);
@@ -549,8 +553,10 @@ static void lcu_update_work(struct work_struct *work)
 	if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) {
 		DBF_DEV_EVENT(DBF_WARNING, device, "could not update"
 			    " alias data in lcu (rc = %d), retry later", rc);
-		schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ);
+		if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ))
+			dasd_put_device(device);
 	} else {
+		dasd_put_device(device);
 		lcu->ruac_data.device = NULL;
 		lcu->flags &= ~UPDATE_PENDING;
 	}
@@ -593,8 +599,10 @@ static int _schedule_lcu_update(struct alias_lcu *lcu,
 	 */
 	if (!usedev)
 		return -EINVAL;
+	dasd_get_device(usedev);
 	lcu->ruac_data.device = usedev;
-	schedule_delayed_work(&lcu->ruac_data.dwork, 0);
+	if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0))
+		dasd_put_device(usedev);
 	return 0;
 }
 
@@ -926,6 +934,7 @@ static void summary_unit_check_handling_work(struct work_struct *work)
 	/* 3. read new alias configuration */
 	_schedule_lcu_update(lcu, device);
 	lcu->suc_data.device = NULL;
+	dasd_put_device(device);
 	spin_unlock_irqrestore(&lcu->lock, flags);
 }
 
@@ -985,6 +994,8 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 	}
 	lcu->suc_data.reason = reason;
 	lcu->suc_data.device = device;
+	dasd_get_device(device);
 	spin_unlock(&lcu->lock);
-	schedule_work(&lcu->suc_data.worker);
+	if (!schedule_work(&lcu->suc_data.worker))
+		dasd_put_device(device);
 };

[PATCH 3.16.y-ckt 010/142] scsi: fix soft lockup in scsi_remove_target() on module removal

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: James Bottomley <James.Bottomley@HansenPartnership.com>

commit 90a88d6ef88edcfc4f644dddc7eef4ea41bccf8b upstream.

This softlockup is currently happening:

[  444.088002] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:1:29]
[  444.088002] Modules linked in: lpfc(-) qla2x00tgt(O) qla2xxx_scst(O) scst_vdisk(O) scsi_transport_fc libcrc32c scst(O) dlm configfs nfsd lockd grace nfs_acl auth_rpcgss sunrpc ed
d snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device dm_mod iTCO_wdt snd_hda_codec_realtek snd_hda_codec_generic gpio_ich iTCO_vendor_support ppdev snd_hda_intel snd_hda_codec snd_hda
_core snd_hwdep tg3 snd_pcm snd_timer libphy lpc_ich parport_pc ptp acpi_cpufreq snd pps_core fjes parport i2c_i801 ehci_pci tpm_tis tpm sr_mod cdrom soundcore floppy hwmon sg 8250_
fintek pcspkr i915 drm_kms_helper uhci_hcd ehci_hcd drm fb_sys_fops sysimgblt sysfillrect syscopyarea i2c_algo_bit usbcore button video usb_common fan ata_generic ata_piix libata th
ermal
[  444.088002] CPU: 1 PID: 29 Comm: kworker/1:1 Tainted: G           O    4.4.0-rc5-2.g1e923a3-default #1
[  444.088002] Hardware name: FUJITSU SIEMENS ESPRIMO E           /D2164-A1, BIOS 5.00 R1.10.2164.A1               05/08/2006
[  444.088002] Workqueue: fc_wq_4 fc_rport_final_delete [scsi_transport_fc]
[  444.088002] task: f6266ec0 ti: f6268000 task.ti: f6268000
[  444.088002] EIP: 0060:[<c07e7044>] EFLAGS: 00000286 CPU: 1
[  444.088002] EIP is at _raw_spin_unlock_irqrestore+0x14/0x20
[  444.088002] EAX: 00000286 EBX: f20d3800 ECX: 00000002 EDX: 00000286
[  444.088002] ESI: f50ba800 EDI: f2146848 EBP: f6269ec8 ESP: f6269ec8
[  444.088002]  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
[  444.088002] CR0: 8005003b CR2: 08f96600 CR3: 363ae000 CR4: 000006d0
[  444.088002] Stack:
[  444.088002]  f6269eec c066b0f7 00000286 f2146848 f50ba808 f50ba800 f50ba800 f2146a90
[  444.088002]  f2146848 f6269f08 f8f0a4ed f3141000 f2146800 f2146a90 f619fa00 00000040
[  444.088002]  f6269f40 c026cb25 00000001 166c6392 00000061 f6757140 f6136340 00000004
[  444.088002] Call Trace:
[  444.088002]  [<c066b0f7>] scsi_remove_target+0x167/0x1c0
[  444.088002]  [<f8f0a4ed>] fc_rport_final_delete+0x9d/0x1e0 [scsi_transport_fc]
[  444.088002]  [<c026cb25>] process_one_work+0x155/0x3e0
[  444.088002]  [<c026cde7>] worker_thread+0x37/0x490
[  444.088002]  [<c027214b>] kthread+0x9b/0xb0
[  444.088002]  [<c07e72c1>] ret_from_kernel_thread+0x21/0x40

What appears to be happening is that something has pinned the target
so it can't go into STARGET_DEL via final release and the loop in
scsi_remove_target spins endlessly until that happens.

The fix for this soft lockup is to not keep looping over a device that
we've called remove on but which hasn't gone into DEL state.  This
patch will retain a simplistic memory of the last target and not keep
looping over it.

Reported-by: Sebastian Herbszt <herbszt@gmx.de>
Tested-by: Sebastian Herbszt <herbszt@gmx.de>
Fixes: 40998193560dab6c3ce8d25f4fa58a23e252ef38
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/scsi/scsi_sysfs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 7e78015d6ab7..6c26b9743c52 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1148,16 +1148,18 @@ static void __scsi_remove_target(struct scsi_target *starget)
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget;
+	struct scsi_target *starget, *last_target = NULL;
 	unsigned long flags;
 
 restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
-		if (starget->state == STARGET_DEL)
+		if (starget->state == STARGET_DEL ||
+		    starget == last_target)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			kref_get(&starget->reap_ref);
+			last_target = starget;
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			__scsi_remove_target(starget);
 			scsi_target_reap(starget);

[PATCH 3.16.y-ckt 011/142] ext4: fix potential integer overflow

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Insu Yun <wuninsu@gmail.com>

commit 46901760b46064964b41015d00c140c83aa05bcf upstream.

Since sizeof(ext_new_group_data) > sizeof(ext_new_flex_group_data),
integer overflow could be happened.
Therefore, need to fix integer overflow sanitization.

Signed-off-by: Insu Yun <wuninsu@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/resize.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index dd4f37e2f18f..d534e589949b 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -186,7 +186,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 

[PATCH 3.16.y-ckt 012/142] ext4: don't read blocks from disk after extents being swapped

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eryu Guan <guaneryu@gmail.com>

commit bcff24887d00bce102e0857d7b0a8c44a40f53d1 upstream.

I notice ext4/307 fails occasionally on ppc64 host, reporting md5
checksum mismatch after moving data from original file to donor file.

The reason is that move_extent_per_page() calls __block_write_begin()
and block_commit_write() to write saved data from original inode blocks
to donor inode blocks, but __block_write_begin() not only maps buffer
heads but also reads block content from disk if the size is not block
size aligned.  At this time the physical block number in mapped buffer
head is pointing to the donor file not the original file, and that
results in reading wrong data to page, which get written to disk in
following block_commit_write call.

This also can be reproduced by the following script on 1k block size ext4
on x86_64 host:

    mnt=/mnt/ext4
    donorfile=$mnt/donor
    testfile=$mnt/testfile
    e4compact=~/xfstests/src/e4compact

    rm -f $donorfile $testfile

    # reserve space for donor file, written by 0xaa and sync to disk to
    # avoid EBUSY on EXT4_IOC_MOVE_EXT
    xfs_io -fc "pwrite -S 0xaa 0 1m" -c "fsync" $donorfile

    # create test file written by 0xbb
    xfs_io -fc "pwrite -S 0xbb 0 1023" -c "fsync" $testfile

    # compute initial md5sum
    md5sum $testfile | tee md5sum.txt
    # drop cache, force e4compact to read data from disk
    echo 3 > /proc/sys/vm/drop_caches

    # test defrag
    echo "$testfile" | $e4compact -i -v -f $donorfile
    # check md5sum
    md5sum -c md5sum.txt

Fix it by creating & mapping buffer heads only but not reading blocks
from disk, because all the data in page is guaranteed to be up-to-date
in mext_page_mkuptodate().

Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/move_extent.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 2484c7ec6a72..146f8cd627b2 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -915,10 +915,11 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int w_flags = 0;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -1027,8 +1028,16 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
-				   ext4_get_block);
+	if (!page_has_buffers(pagep[0]))
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 

[PATCH 3.16.y-ckt 013/142] bio: return EINTR if copying to user space got interrupted

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Hannes Reinecke <hare@suse.de>

commit 2d99b55d378c996b9692a0c93dd25f4ed5d58934 upstream.

Commit 35dc248383bbab0a7203fca4d722875bc81ef091 introduced a check for
current->mm to see if we have a user space context and only copies data
if we do. Now if an IO gets interrupted by a signal data isn't copied
into user space any more (as we don't have a user space context) but
user space isn't notified about it.

This patch modifies the behaviour to return -EINTR from bio_uncopy_user()
to notify userland that a signal has interrupted the syscall, otherwise
it could lead to a situation where the caller may get a buffer with
no data returned.

This can be reproduced by issuing SG_IO ioctl()s in one thread while
constantly sending signals to it.

Fixes: 35dc248 [SCSI] sg: Fix user memory corruption when SG_IO is interrupted by a signal
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
[ luis: backported to 3.16: based on Johannes' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 block/bio.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 6467e6afdcd9..529e4195724e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1110,9 +1110,12 @@ int bio_uncopy_user(struct bio *bio)
 			ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
 					     bio_data_dir(bio) == READ,
 					     0, bmd->is_our_pages);
-		else if (bmd->is_our_pages)
-			bio_for_each_segment_all(bvec, bio, i)
-				__free_page(bvec->bv_page);
+		else {
+			ret = -EINTR;
+			if (bmd->is_our_pages)
+				bio_for_each_segment_all(bvec, bio, i)
+					__free_page(bvec->bv_page);
+		}
 	}
 	kfree(bmd);
 	bio_put(bio);

[PATCH 3.16.y-ckt 014/142] ALSA: seq: Drop superfluous error/debug messages after malloc failures

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 24db8bbaa3fcfaf0c2faccbff5864b58088ac1f6 upstream.

The kernel memory allocators already report the errors when the
requested allocation fails, thus we don't need to warn it again in
each caller side.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/seq/seq_fifo.c   | 4 +---
 sound/core/seq/seq_memory.c | 8 ++------
 sound/core/seq/seq_ports.c  | 4 +---
 sound/core/seq/seq_prioq.c  | 4 +---
 sound/core/seq/seq_queue.c  | 4 +---
 sound/core/seq/seq_timer.c  | 4 +---
 6 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 53a403e17c5b..1d5acbe0c08b 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -33,10 +33,8 @@ struct snd_seq_fifo *snd_seq_fifo_new(int poolsize)
 	struct snd_seq_fifo *f;
 
 	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (f == NULL) {
-		pr_debug("ALSA: seq: malloc failed for snd_seq_fifo_new() \n");
+	if (!f)
 		return NULL;
-	}
 
 	f->pool = snd_seq_pool_new(poolsize);
 	if (f->pool == NULL) {
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 1e206de0c2dd..07002abdd9c7 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -387,10 +387,8 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 		return 0;
 
 	pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
-	if (pool->ptr == NULL) {
-		pr_debug("ALSA: seq: malloc for sequencer events failed\n");
+	if (!pool->ptr)
 		return -ENOMEM;
-	}
 
 	/* add new cells to the free cell list */
 	spin_lock_irqsave(&pool->lock, flags);
@@ -463,10 +461,8 @@ struct snd_seq_pool *snd_seq_pool_new(int poolsize)
 
 	/* create pool block */
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
-	if (pool == NULL) {
-		pr_debug("ALSA: seq: malloc failed for pool\n");
+	if (!pool)
 		return NULL;
-	}
 	spin_lock_init(&pool->lock);
 	pool->ptr = NULL;
 	pool->free = NULL;
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 2dcdf81e0abb..3c8630ff36af 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -141,10 +141,8 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client,
 
 	/* create a new port */
 	new_port = kzalloc(sizeof(*new_port), GFP_KERNEL);
-	if (! new_port) {
-		pr_debug("ALSA: seq: malloc failed for registering client port\n");
+	if (!new_port)
 		return NULL;	/* failure, out of memory */
-	}
 	/* init port data */
 	new_port->addr.client = client->number;
 	new_port->addr.port = -1;
diff --git a/sound/core/seq/seq_prioq.c b/sound/core/seq/seq_prioq.c
index 021b02bc9330..bc1c8488fc2a 100644
--- a/sound/core/seq/seq_prioq.c
+++ b/sound/core/seq/seq_prioq.c
@@ -59,10 +59,8 @@ struct snd_seq_prioq *snd_seq_prioq_new(void)
 	struct snd_seq_prioq *f;
 
 	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (f == NULL) {
-		pr_debug("ALSA: seq: malloc failed for snd_seq_prioq_new()\n");
+	if (!f)
 		return NULL;
-	}
 	
 	spin_lock_init(&f->lock);
 	f->head = NULL;
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index 52defd86d8b4..77ec21420355 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -111,10 +111,8 @@ static struct snd_seq_queue *queue_new(int owner, int locked)
 	struct snd_seq_queue *q;
 
 	q = kzalloc(sizeof(*q), GFP_KERNEL);
-	if (q == NULL) {
-		pr_debug("ALSA: seq: malloc failed for snd_seq_queue_new()\n");
+	if (!q)
 		return NULL;
-	}
 
 	spin_lock_init(&q->owner_lock);
 	spin_lock_init(&q->check_lock);
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index c943dc41c6fe..a2468f1101d1 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -56,10 +56,8 @@ struct snd_seq_timer *snd_seq_timer_new(void)
 	struct snd_seq_timer *tmr;
 	
 	tmr = kzalloc(sizeof(*tmr), GFP_KERNEL);
-	if (tmr == NULL) {
-		pr_debug("ALSA: seq: malloc failed for snd_seq_timer_new() \n");
+	if (!tmr)
 		return NULL;
-	}
 	spin_lock_init(&tmr->lock);
 
 	/* reset setup to defaults */

[PATCH 3.16.y-ckt 015/142] ALSA: seq: Fix leak of pool buffer at concurrent writes

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit d99a36f4728fcbcc501b78447f625bdcce15b842 upstream.

When multiple concurrent writes happen on the ALSA sequencer device
right after the open, it may try to allocate vmalloc buffer for each
write and leak some of them.  It's because the presence check and the
assignment of the buffer is done outside the spinlock for the pool.

The fix is to move the check and the assignment into the spinlock.

(The current implementation is suboptimal, as there can be multiple
 unnecessary vmallocs because the allocation is done before the check
 in the spinlock.  But the pool size is already checked beforehand, so
 this isn't a big problem; that is, the only possible path is the
 multiple writes before any pool assignment, and practically seen, the
 current coverage should be "good enough".)

The issue was triggered by syzkaller fuzzer.

BugLink: http://lkml.kernel.org/r/CACT4Y+bSzazpXNvtAr=WXaL8hptqjHwqEyFA+VN2AWEx=aurkg@mail.gmail.com
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/seq/seq_memory.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 07002abdd9c7..04ef9b5351f9 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
-	if (pool->ptr)			/* should be atomic? */
-		return 0;
 
-	pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
-	if (!pool->ptr)
+	cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
+	if (!cellptr)
 		return -ENOMEM;
 
 	/* add new cells to the free cell list */
 	spin_lock_irqsave(&pool->lock, flags);
+	if (pool->ptr) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		vfree(cellptr);
+		return 0;
+	}
+
+	pool->ptr = cellptr;
 	pool->free = NULL;
 
 	for (cell = 0; cell < pool->size; cell++) {

[PATCH 3.16.y-ckt 016/142] dmaengine: dw: disable BLOCK IRQs for non-cyclic xfer

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>

commit ee1cdcdae59563535485a5f56ee72c894ab7d7ad upstream.

The commit 2895b2cad6e7 ("dmaengine: dw: fix cyclic transfer callbacks")
re-enabled BLOCK interrupts with regard to make cyclic transfers work. However,
this change becomes a regression for non-cyclic transfers as interrupt counters
under stress test had been grown enormously (approximately per 4-5 bytes in the
UART loop back test).

Taking into consideration above enable BLOCK interrupts if and only if channel
is programmed to perform cyclic transfer.

Fixes: 2895b2cad6e7 ("dmaengine: dw: fix cyclic transfer callbacks")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mans Rullgard <mans@mansr.com>
Tested-by: Mans Rullgard <mans@mansr.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/dma/dw/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index e968366e6cdd..43c8de0f00f4 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -169,7 +169,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
-	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
 	dwc->initialized = true;
@@ -596,6 +595,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
 		spin_unlock_irqrestore(&dwc->lock, flags);
 	}
+
+	/* Re-enable interrupts */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 }
 
 /* ------------------------------------------------------------------------- */
@@ -626,11 +628,8 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_scan_descriptors(dw, dwc);
 	}
 
-	/*
-	 * Re-enable interrupts.
-	 */
+	/* Re-enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
 
@@ -1216,6 +1215,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 int dw_dma_cyclic_start(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
 	unsigned long		flags;
 
 	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
@@ -1224,7 +1224,12 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 	}
 
 	spin_lock_irqsave(&dwc->lock, flags);
+
+	/* Enable interrupts to perform cyclic transfer */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
+
 	dwc_dostart(dwc, dwc->cdesc->desc[0]);
+
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;

[PATCH 3.16.y-ckt 017/142] tracepoints: Do not trace when cpu is offline

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

commit f37755490fe9bf76f6ba1d8c6591745d3574a6a6 upstream.

The tracepoint infrastructure uses RCU sched protection to enable and
disable tracepoints safely. There are some instances where tracepoints are
used in infrastructure code (like kfree()) that get called after a CPU is
going offline, and perhaps when it is coming back online but hasn't been
registered yet.

This can probuce the following warning:

 [ INFO: suspicious RCU usage. ]
 4.4.0-00006-g0fe53e8-dirty #34 Tainted: G S
 -------------------------------
 include/trace/events/kmem.h:141 suspicious rcu_dereference_check() usage!

 other info that might help us debug this:

 RCU used illegally from offline CPU!  rcu_scheduler_active = 1, debug_locks = 1
 no locks held by swapper/8/0.

 stack backtrace:
  CPU: 8 PID: 0 Comm: swapper/8 Tainted: G S              4.4.0-00006-g0fe53e8-dirty #34
  Call Trace:
  [c0000005b76c78d0] [c0000000008b9540] .dump_stack+0x98/0xd4 (unreliable)
  [c0000005b76c7950] [c00000000010c898] .lockdep_rcu_suspicious+0x108/0x170
  [c0000005b76c79e0] [c00000000029adc0] .kfree+0x390/0x440
  [c0000005b76c7a80] [c000000000055f74] .destroy_context+0x44/0x100
  [c0000005b76c7b00] [c0000000000934a0] .__mmdrop+0x60/0x150
  [c0000005b76c7b90] [c0000000000e3ff0] .idle_task_exit+0x130/0x140
  [c0000005b76c7c20] [c000000000075804] .pseries_mach_cpu_die+0x64/0x310
  [c0000005b76c7cd0] [c000000000043e7c] .cpu_die+0x3c/0x60
  [c0000005b76c7d40] [c0000000000188d8] .arch_cpu_idle_dead+0x28/0x40
  [c0000005b76c7db0] [c000000000101e6c] .cpu_startup_entry+0x50c/0x560
  [c0000005b76c7ed0] [c000000000043bd8] .start_secondary+0x328/0x360
  [c0000005b76c7f90] [c000000000008a6c] start_secondary_prolog+0x10/0x14

This warning is not a false positive either. RCU is not protecting code that
is being executed while the CPU is offline.

Instead of playing "whack-a-mole(TM)" and adding conditional statements to
the tracepoints we find that are used in this instance, simply add a
cpu_online() test to the tracepoint code where the tracepoint will be
ignored if the CPU is offline.

Use of raw_smp_processor_id() is fine, as there should never be a case where
the tracepoint code goes from running on a CPU that is online and suddenly
gets migrated to a CPU that is offline.

Link: http://lkml.kernel.org/r/1455387773-4245-1-git-send-email-kda@linux-powerpc.org

Reported-by: Denis Kirjanov <kda@linux-powerpc.org>
Fixes: 97e1c18e8d17b ("tracing: Kernel Tracepoints")
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
[ luis: backported to 3.16:
  - included linux/percpu.h as suggested by Steven for other stable kernels ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/tracepoint.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 2e2a5f7717e5..30e788953524 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -14,8 +14,11 @@
  * See the file COPYING for more details.
  */
 
+#include <linux/smp.h>
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/static_key.h>
 
@@ -121,6 +124,9 @@ extern void syscall_unregfunc(void);
 		void *it_func;						\
 		void *__data;						\
 									\
+		if (!cpu_online(raw_smp_processor_id()))		\
+			return;						\
+									\
 		if (!(cond))						\
 			return;						\
 		prercu;							\

[PATCH 3.16.y-ckt 018/142] tracing: Fix freak link error caused by branch tracer

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Arnd Bergmann <arnd@arndb.de>

commit b33c8ff4431a343561e2319f17c14286f2aa52e2 upstream.

In my randconfig tests, I came across a bug that involves several
components:

* gcc-4.9 through at least 5.3
* CONFIG_GCOV_PROFILE_ALL enabling -fprofile-arcs for all files
* CONFIG_PROFILE_ALL_BRANCHES overriding every if()
* The optimized implementation of do_div() that tries to
  replace a library call with an division by multiplication
* code in drivers/media/dvb-frontends/zl10353.c doing

        u32 adc_clock = 450560; /* 45.056 MHz */
        if (state->config.adc_clock)
                adc_clock = state->config.adc_clock;
        do_div(value, adc_clock);

In this case, gcc fails to determine whether the divisor
in do_div() is __builtin_constant_p(). In particular, it
concludes that __builtin_constant_p(adc_clock) is false, while
__builtin_constant_p(!!adc_clock) is true.

That in turn throws off the logic in do_div() that also uses
__builtin_constant_p(), and instead of picking either the
constant- optimized division, and the code in ilog2() that uses
__builtin_constant_p() to figure out whether it knows the answer at
compile time. The result is a link error from failing to find
multiple symbols that should never have been called based on
the __builtin_constant_p():

dvb-frontends/zl10353.c:138: undefined reference to `____ilog2_NaN'
dvb-frontends/zl10353.c:138: undefined reference to `__aeabi_uldivmod'
ERROR: "____ilog2_NaN" [drivers/media/dvb-frontends/zl10353.ko] undefined!
ERROR: "__aeabi_uldivmod" [drivers/media/dvb-frontends/zl10353.ko] undefined!

This patch avoids the problem by changing __trace_if() to check
whether the condition is known at compile-time to be nonzero, rather
than checking whether it is actually a constant.

I see this one link error in roughly one out of 1600 randconfig builds
on ARM, and the patch fixes all known instances.

Link: http://lkml.kernel.org/r/1455312410-1058841-1-git-send-email-arnd@arndb.de

Acked-by: Nicolas Pitre <nico@linaro.org>
Fixes: ab3c9c686e22 ("branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER=y")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index da293bf86575..8f6e7b2d667f 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -138,7 +138,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
 #define __trace_if(cond) \
-	if (__builtin_constant_p((cond)) ? !!(cond) :			\
+	if (__builtin_constant_p(!!(cond)) ? !!(cond) :			\
 	({								\
 		int ______r;						\
 		static struct ftrace_branch_data			\

[PATCH 3.16.y-ckt 019/142] ALSA: seq: Fix double port list deletion

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 13d5e5d4725c64ec06040d636832e78453f477b7 upstream.

The commit [7f0973e973cd: ALSA: seq: Fix lockdep warnings due to
double mutex locks] split the management of two linked lists (source
and destination) into two individual calls for avoiding the AB/BA
deadlock.  However, this may leave the possible double deletion of one
of two lists when the counterpart is being deleted concurrently.
It ends up with a list corruption, as revealed by syzkaller fuzzer.

This patch fixes it by checking the list emptiness and skipping the
deletion and the following process.

BugLink: http://lkml.kernel.org/r/CACT4Y+bay9qsrz6dQu31EcGaH9XwfW7o3oBzSQUG9fMszoh=Sg@mail.gmail.com
Fixes: 7f0973e973cd ('ALSA: seq: Fix lockdep warnings due to 'double mutex locks)
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/seq/seq_ports.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 3c8630ff36af..9c1c8d50f593 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -538,19 +538,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client,
 					bool is_src, bool ack)
 {
 	struct snd_seq_port_subs_info *grp;
+	struct list_head *list;
+	bool empty;
 
 	grp = is_src ? &port->c_src : &port->c_dest;
+	list = is_src ? &subs->src_list : &subs->dest_list;
 	down_write(&grp->list_mutex);
 	write_lock_irq(&grp->list_lock);
-	if (is_src)
-		list_del(&subs->src_list);
-	else
-		list_del(&subs->dest_list);
+	empty = list_empty(list);
+	if (!empty)
+		list_del_init(list);
 	grp->exclusive = 0;
 	write_unlock_irq(&grp->list_lock);
 	up_write(&grp->list_mutex);
 
-	unsubscribe_port(client, port, grp, &subs->info, ack);
+	if (!empty)
+		unsubscribe_port(client, port, grp, &subs->info, ack);
 }
 
 /* connect two ports */

[PATCH 3.16.y-ckt 020/142] drm/radeon: use post-decrement in error handling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Rasmus Villemoes <linux@rasmusvillemoes.dk>

commit bc3f5d8c4ca01555820617eb3b6c0857e4df710d upstream.

We need to use post-decrement to get the pci_map_page undone also for
i==0, and to avoid some very unpleasant behaviour if pci_map_page
failed already at i==0.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_ttm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 7555349e30da..c4675b9729c9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -629,7 +629,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 						       0, PAGE_SIZE,
 						       PCI_DMA_BIDIRECTIONAL);
 		if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) {
-			while (--i) {
+			while (i--) {
 				pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i],
 					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 				gtt->ttm.dma_address[i] = 0;

[PATCH 3.16.y-ckt 021/142] drm/qxl: use kmalloc_array to alloc reloc_info in qxl_process_single_command

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Gerd Hoffmann <kraxel@redhat.com>

commit 34855706c30d52b0a744da44348b5d1cc39fbe51 upstream.

This avoids integer overflows on 32bit machines when calculating
reloc_info size, as reported by Alan Cox.

Cc: gnomes@lxorguk.ukuu.org.uk
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/qxl/qxl_ioctl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 7354a4cda59d..3aefaa058f0c 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 		       cmd->command_size))
 		return -EFAULT;
 
-	reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL);
+	reloc_info = kmalloc_array(cmd->relocs_num,
+				   sizeof(struct qxl_reloc_info), GFP_KERNEL);
 	if (!reloc_info)
 		return -ENOMEM;
 

[PATCH 3.16.y-ckt 022/142] ext4: fix bh->b_state corruption

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jan Kara <jack@suse.com>

commit ed8ad83808f009ade97ebbf6519bc3a97fefbc0c upstream.

ext4 can update bh->b_state non-atomically in _ext4_get_block() and
ext4_da_get_block_prep(). Usually this is fine since bh is just a
temporary storage for mapping information on stack but in some cases it
can be fully living bh attached to a page. In such case non-atomic
update of bh->b_state can race with an atomic update which then gets
lost. Usually when we are mapping bh and thus updating bh->b_state
non-atomically, nobody else touches the bh and so things work out fine
but there is one case to especially worry about: ext4_finish_bio() uses
BH_Uptodate_Lock on the first bh in the page to synchronize handling of
PageWriteback state. So when blocksize < pagesize, we can be atomically
modifying bh->b_state of a buffer that actually isn't under IO and thus
can race e.g. with delalloc trying to map that buffer. The result is
that we can mistakenly set / clear BH_Uptodate_Lock bit resulting in the
corruption of PageWriteback state or missed unlock of BH_Uptodate_Lock.

Fix the problem by always updating bh->b_state bits atomically.

Reported-by: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
[ luis: backported to 3.16:
  - replaced READ_ONCE() by ACCESS_ONCE() ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f7a77141a77c..2d7e9a181be0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -712,6 +712,34 @@ has_zeroout:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = ACCESS_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -748,7 +776,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -1694,7 +1722,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked

[PATCH 3.16.y-ckt 023/142] ext4: fix crashes in dioread_nolock mode

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jan Kara <jack@suse.cz>

commit 74dae4278546b897eb81784fdfcce872ddd8b2b8 upstream.

Competing overwrite DIO in dioread_nolock mode will just overwrite
pointer to io_end in the inode. This may result in data corruption or
extent conversion happening from IO completion interrupt because we
don't properly set buffer_defer_completion() when unlocked DIO races
with locked DIO to unwritten extent.

Since unlocked DIO doesn't need io_end for anything, just avoid
allocating it and corrupting pointer from inode for locked DIO.
A cleaner fix would be to avoid these games with io_end pointer from the
inode but that requires more intrusive changes so we leave that for
later.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/inode.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2d7e9a181be0..9af7ee7d0193 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3201,29 +3201,29 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
 	if (overwrite) {
 		get_block_func = ext4_get_block_write_nolock;
 	} else {
+		ext4_inode_aio_set(inode, NULL);
+		if (!is_sync_kiocb(iocb)) {
+			io_end = ext4_init_io_end(inode, GFP_NOFS);
+			if (!io_end) {
+				ret = -ENOMEM;
+				goto retake_lock;
+			}
+			/*
+			 * Grab reference for DIO. Will be dropped in
+			 * ext4_end_io_dio()
+			 */
+			iocb->private = ext4_get_io_end(io_end);
+			/*
+			 * we save the io structure for current async direct
+			 * IO, so that later ext4_map_blocks() could flag the
+			 * io structure whether there is a unwritten extents
+			 * needs to be converted when IO is completed.
+			 */
+			ext4_inode_aio_set(inode, io_end);
+		}
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}

[PATCH 3.16.y-ckt 024/142] kernel/resource.c: fix muxed resource handling in __request_region()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Simon Guinot <simon.guinot@sequanux.org>

commit 59ceeaaf355fa0fb16558ef7c24413c804932ada upstream.

In __request_region, if a conflict with a BUSY and MUXED resource is
detected, then the caller goes to sleep and waits for the resource to be
released.  A pointer on the conflicting resource is kept.  At wake-up
this pointer is used as a parent to retry to request the region.

A first problem is that this pointer might well be invalid (if for
example the conflicting resource have already been freed).  Another
problem is that the next call to __request_region() fails to detect a
remaining conflict.  The previously conflicting resource is passed as a
parameter and __request_region() will look for a conflict among the
children of this resource and not at the resource itself.  It is likely
to succeed anyway, even if there is still a conflict.

Instead, the parent of the conflicting resource should be passed to
__request_region().

As a fix, this patch doesn't update the parent resource pointer in the
case we have to wait for a muxed region right after.

Reported-and-tested-by: Vincent Pelletier <plr.vincent@gmail.com>
Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Tested-by: Vincent Donnefort <vdonnefort@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/resource.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/resource.c b/kernel/resource.c
index 3c2237ac32db..db48bab5ea18 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -957,9 +957,10 @@ struct resource * __request_region(struct resource *parent,
 		if (!conflict)
 			break;
 		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
+			if (!(conflict->flags & IORESOURCE_BUSY)) {
+				parent = conflict;
 				continue;
+			}
 		}
 		if (conflict->flags & flags & IORESOURCE_MUXED) {
 			add_wait_queue(&muxed_resource_wait, &wait);

[PATCH 3.16.y-ckt 025/142] x86/entry/compat: Add missing CLAC to entry_INT80_32

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Andy Lutomirski <luto@kernel.org>

commit 3d44d51bd339766f0178f0cf2e8d048b4a4872aa upstream.

This doesn't seem to fix a regression -- I don't think the CLAC was
ever there.

I double-checked in a debugger: entries through the int80 gate do
not automatically clear AC.

Stable maintainers: I can provide a backport to 4.3 and earlier if
needed.  This needs to be backported all the way to 3.10.

Reported-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 63bcff2a307b ("x86, smap: Add STAC and CLAC instructions to control user space access")
Link: http://lkml.kernel.org/r/b02b7e71ae54074be01fc171cbd4b72517055c0e.1456345086.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[ kamal: backport to 3.10 through 3.19-stable: file rename; context ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/ia32/ia32entry.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 92a2e9333620..b74ac9c5710b 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -422,6 +422,7 @@ ENTRY(ia32_syscall)
 	/*CFI_REL_OFFSET	cs,CS-RIP*/
 	CFI_REL_OFFSET	rip,RIP-RIP
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	ASM_CLAC			/* Do this early to minimize exposure */
 	SWAPGS
 	/*
 	 * No need to follow this irqs on/off section: the syscall

[PATCH 3.16.y-ckt 026/142] crypto: {blk,giv}cipher: Set has_setkey

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Ben Hutchings <ben@decadent.org.uk>

Commit a1383cd86a06 ("crypto: skcipher - Add crypto_skcipher_has_setkey")
was incorrectly backported to the 3.2.y and 3.16.y stable branches.
We need to set ablkcipher_tfm::has_setkey in the
crypto_init_blkcipher_ops_async() and crypto_init_givcipher_ops()
functions as well as crypto_init_ablkcipher_ops().

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 crypto/ablkcipher.c | 1 +
 crypto/blkcipher.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index 5da16526c890..970b48e70624 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -457,6 +457,7 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
+	crt->has_setkey = alg->max_keysize;
 
 	return 0;
 }
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 7180cb2fe026..3c551d46aa3b 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -471,6 +471,7 @@ static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm)
 	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
+	crt->has_setkey = alg->max_keysize;
 
 	return 0;
 }

[PATCH 3.16.y-ckt 027/142] nfs: fix nfs_size_to_loff_t

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Christoph Hellwig <hch@lst.de>

commit 50ab8ec74a153eb30db26529088bc57dd700b24c upstream.

See http: //www.infradead.org/rpr.html
X-Evolution-Source: 1451162204.2173.11@leira.trondhjem.org
Content-Transfer-Encoding: 8bit
Mime-Version: 1.0

We support OFFSET_MAX just fine, so don't round down below it.  Also
switch to using min_t to make the helper more readable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Fixes: 433c92379d9c ("NFS: Clean up nfs_size_to_loff_t()")
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/nfs_fs.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index e30f6059ecd6..7faf70d9e869 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -577,9 +577,7 @@ static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
 static inline loff_t nfs_size_to_loff_t(__u64 size)
 {
-	if (size > (__u64) OFFSET_MAX - 1)
-		return OFFSET_MAX - 1;
-	return (loff_t) size;
+	return min_t(u64, size, OFFSET_MAX);
 }
 
 static inline ino_t

[PATCH 3.16.y-ckt 028/142] xen/pciback: Check PF instead of VF for PCI_COMMAND_MEMORY

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 8d47065f7d1980dde52abb874b301054f3013602 upstream.

Commit 408fb0e5aa7fda0059db282ff58c3b2a4278baa0 (xen/pciback: Don't
allow MSI-X ops if PCI_COMMAND_MEMORY is not set) prevented enabling
MSI-X on passed-through virtual functions, because it checked the VF
for PCI_COMMAND_MEMORY but this is not a valid bit for VFs.

Instead, check the physical function for PCI_COMMAND_MEMORY.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/xen/xen-pciback/pciback_ops.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 73dafdc494aa..1078e8d631c9 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
 	/*
 	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
 	 * to access the BARs where the MSI-X entries reside.
+	 * But VF devices are unique in which the PF needs to be checked.
 	 */
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd);
 	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
 		return -ENXIO;
 

[PATCH 3.16.y-ckt 029/142] xen/pciback: Save the number of MSI-X entries to be copied later.

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit d159457b84395927b5a52adb72f748dd089ad5e5 upstream.

Commit 8135cf8b092723dbfcc611fe6fdcb3a36c9951c5 (xen/pciback: Save
xen_pci_op commands before processing it) broke enabling MSI-X because
it would never copy the resulting vectors into the response.  The
number of vectors requested was being overwritten by the return value
(typically zero for success).

Save the number of vectors before processing the op, so the correct
number of vectors are copied afterwards.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/xen/xen-pciback/pciback_ops.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 1078e8d631c9..fb0221434f81 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -333,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data)
 	struct xen_pcibk_dev_data *dev_data = NULL;
 	struct xen_pci_op *op = &pdev->op;
 	int test_intx = 0;
+#ifdef CONFIG_PCI_MSI
+	unsigned int nr = 0;
+#endif
 
 	*op = pdev->sh_info->op;
 	barrier();
@@ -361,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 			op->err = xen_pcibk_disable_msi(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_enable_msix:
+			nr = op->value;
 			op->err = xen_pcibk_enable_msix(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_disable_msix:
@@ -383,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
 		unsigned int i;
 
-		for (i = 0; i < op->value; i++)
+		for (i = 0; i < nr; i++)
 			pdev->sh_info->op.msix_entries[i].vector =
 				op->msix_entries[i].vector;
 	}

[PATCH 3.16.y-ckt 030/142] xen/pcifront: Fix mysterious crashes when NUMA locality information was extracted.

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

commit 4d8c8bd6f2062c9988817183a91fe2e623c8aa5e upstream.

Occasionaly PV guests would crash with:

pciback 0000:00:00.1: Xen PCI mapped GSI0 to IRQ16
BUG: unable to handle kernel paging request at 0000000d1a8c0be0
.. snip..
  <ffffffff8139ce1b>] find_next_bit+0xb/0x10
  [<ffffffff81387f22>] cpumask_next_and+0x22/0x40
  [<ffffffff813c1ef8>] pci_device_probe+0xb8/0x120
  [<ffffffff81529097>] ? driver_sysfs_add+0x77/0xa0
  [<ffffffff815293e4>] driver_probe_device+0x1a4/0x2d0
  [<ffffffff813c1ddd>] ? pci_match_device+0xdd/0x110
  [<ffffffff81529657>] __device_attach_driver+0xa7/0xb0
  [<ffffffff815295b0>] ? __driver_attach+0xa0/0xa0
  [<ffffffff81527622>] bus_for_each_drv+0x62/0x90
  [<ffffffff8152978d>] __device_attach+0xbd/0x110
  [<ffffffff815297fb>] device_attach+0xb/0x10
  [<ffffffff813b75ac>] pci_bus_add_device+0x3c/0x70
  [<ffffffff813b7618>] pci_bus_add_devices+0x38/0x80
  [<ffffffff813dc34e>] pcifront_scan_root+0x13e/0x1a0
  [<ffffffff817a0692>] pcifront_backend_changed+0x262/0x60b
  [<ffffffff814644c6>] ? xenbus_gather+0xd6/0x160
  [<ffffffff8120900f>] ? put_object+0x2f/0x50
  [<ffffffff81465c1d>] xenbus_otherend_changed+0x9d/0xa0
  [<ffffffff814678ee>] backend_changed+0xe/0x10
  [<ffffffff81463a28>] xenwatch_thread+0xc8/0x190
  [<ffffffff810f22f0>] ? woken_wake_function+0x10/0x10

which was the result of two things:

When we call pci_scan_root_bus we would pass in 'sd' (sysdata)
pointer which was an 'pcifront_sd' structure. However in the
pci_device_add it expects that the 'sd' is 'struct sysdata' and
sets the dev->node to what is in sd->node (offset 4):

set_dev_node(&dev->dev, pcibus_to_node(bus));

 __pcibus_to_node(const struct pci_bus *bus)
{
        const struct pci_sysdata *sd = bus->sysdata;

        return sd->node;
}

However our structure was pcifront_sd which had nothing at that
offset:

struct pcifront_sd {
        int                        domain;    /*     0     4 */
        /* XXX 4 bytes hole, try to pack */
        struct pcifront_device *   pdev;      /*     8     8 */
}

That is an hole - filled with garbage as we used kmalloc instead of
kzalloc (the second problem).

This patch fixes the issue by:
 1) Use kzalloc to initialize to a well known state.
 2) Put 'struct pci_sysdata' at the start of 'pcifront_sd'. That
    way access to the 'node' will access the right offset.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/pci/xen-pcifront.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 53df39a22c8a..626360b07701 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -52,7 +52,7 @@ struct pcifront_device {
 };
 
 struct pcifront_sd {
-	int domain;
+	struct pci_sysdata sd;
 	struct pcifront_device *pdev;
 };
 
@@ -66,7 +66,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd,
 				    unsigned int domain, unsigned int bus,
 				    struct pcifront_device *pdev)
 {
-	sd->domain = domain;
+	/* Because we do not expose that information via XenBus. */
+	sd->sd.node = first_online_node;
+	sd->sd.domain = domain;
 	sd->pdev = pdev;
 }
 
@@ -464,8 +466,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
 		 domain, bus);
 
-	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
-	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kzalloc(sizeof(*sd), GFP_KERNEL);
 	if (!bus_entry || !sd) {
 		err = -ENOMEM;
 		goto err_out;

[PATCH 3.16.y-ckt 031/142] usb: dwc3: Fix assignment of EP transfer resources

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: John Youn <John.Youn@synopsys.com>

commit c450960187f45d4260db87c7dd4fc0bceb5565d8 upstream.

The assignement of EP transfer resources was not handled properly in the
dwc3 driver. Commit aebda6187181 ("usb: dwc3: Reset the transfer
resource index on SET_INTERFACE") previously fixed one aspect of this
where resources may be exhausted with multiple calls to SET_INTERFACE.
However, it introduced an issue where composite devices with multiple
interfaces can be assigned the same transfer resources for different
endpoints. This patch solves both issues.

The assignment of transfer resources cannot perfectly follow the data
book due to the fact that the controller driver does not have all
knowledge of the configuration in advance. It is given this information
piecemeal by the composite gadget framework after every
SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook
programming model in this scenario can cause errors. For two reasons:

1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION and
SET_INTERFACE (8.1.5). This is incorrect in the scenario of multiple
interfaces.

2) The databook does not mention doing more DEPXFERCFG for new endpoint
on alt setting (8.1.6).

The following simplified method is used instead:

All hardware endpoints can be assigned a transfer resource and this
setting will stay persistent until either a core reset or hibernation.
So whenever we do a DEPSTARTCFG(0) we can go ahead and do DEPXFERCFG for
every hardware endpoint as well. We are guaranteed that there are as
many transfer resources as endpoints.

This patch triggers off of the calling dwc3_gadget_start_config() for
EP0-out, which always happens first, and which should only happen in one
of the above conditions.

Fixes: aebda6187181 ("usb: dwc3: Reset the transfer resource index on SET_INTERFACE")
Reported-by: Ravi Babu <ravibabu@ti.com>
Signed-off-by: John Youn <johnyoun@synopsys.com>
Signed-off-by: Felipe Balbi <balbi@kernel.org>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/dwc3/core.h   |  1 -
 drivers/usb/dwc3/ep0.c    |  5 ----
 drivers/usb/dwc3/gadget.c | 70 +++++++++++++++++++++++++++++++++++------------
 3 files changed, 52 insertions(+), 24 deletions(-)

diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 1ba964de9c3b..fd91c10a21a9 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -754,7 +754,6 @@ struct dwc3 {
 	unsigned		pullups_connected:1;
 	unsigned		resize_fifos:1;
 	unsigned		setup_packet_pending:1;
-	unsigned		start_config_issued:1;
 	unsigned		three_stage_setup:1;
 };
 
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 312bc0542562..ba35201e19fe 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -524,7 +524,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 	int ret;
 	u32 reg;
 
-	dwc->start_config_issued = false;
 	cfg = le16_to_cpu(ctrl->wValue);
 
 	switch (state) {
@@ -707,10 +706,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 		dev_vdbg(dwc->dev, "USB_REQ_SET_ISOCH_DELAY\n");
 		ret = dwc3_ep0_set_isoch_delay(dwc, ctrl);
 		break;
-	case USB_REQ_SET_INTERFACE:
-		dev_vdbg(dwc->dev, "USB_REQ_SET_INTERFACE");
-		dwc->start_config_issued = false;
-		/* Fall through */
 	default:
 		dev_vdbg(dwc->dev, "Forwarding to gadget driver\n");
 		ret = dwc3_ep0_delegate_req(dwc, ctrl);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 186a79d43250..4a279bb9092a 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -472,24 +472,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep)
 	dep->trb_pool_dma = 0;
 }
 
+static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep);
+
+/**
+ * dwc3_gadget_start_config - Configure EP resources
+ * @dwc: pointer to our controller context structure
+ * @dep: endpoint that is being enabled
+ *
+ * The assignment of transfer resources cannot perfectly follow the
+ * data book due to the fact that the controller driver does not have
+ * all knowledge of the configuration in advance. It is given this
+ * information piecemeal by the composite gadget framework after every
+ * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook
+ * programming model in this scenario can cause errors. For two
+ * reasons:
+ *
+ * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION
+ * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of
+ * multiple interfaces.
+ *
+ * 2) The databook does not mention doing more DEPXFERCFG for new
+ * endpoint on alt setting (8.1.6).
+ *
+ * The following simplified method is used instead:
+ *
+ * All hardware endpoints can be assigned a transfer resource and this
+ * setting will stay persistent until either a core reset or
+ * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and
+ * do DEPXFERCFG for every hardware endpoint as well. We are
+ * guaranteed that there are as many transfer resources as endpoints.
+ *
+ * This function is called for each endpoint when it is being enabled
+ * but is triggered only when called for EP0-out, which always happens
+ * first, and which should only happen in one of the above conditions.
+ */
 static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 {
 	struct dwc3_gadget_ep_cmd_params params;
 	u32			cmd;
+	int			i;
+	int			ret;
+
+	if (dep->number)
+		return 0;
 
 	memset(&params, 0x00, sizeof(params));
+	cmd = DWC3_DEPCMD_DEPSTARTCFG;
 
-	if (dep->number != 1) {
-		cmd = DWC3_DEPCMD_DEPSTARTCFG;
-		/* XferRscIdx == 0 for ep0 and 2 for the remaining */
-		if (dep->number > 1) {
-			if (dwc->start_config_issued)
-				return 0;
-			dwc->start_config_issued = true;
-			cmd |= DWC3_DEPCMD_PARAM(2);
-		}
+	ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	if (ret)
+		return ret;
 
-		return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) {
+		struct dwc3_ep *dep = dwc->eps[i];
+
+		if (!dep)
+			continue;
+
+		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -603,10 +645,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		struct dwc3_trb	*trb_st_hw;
 		struct dwc3_trb	*trb_link;
 
-		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
-		if (ret)
-			return ret;
-
 		dep->endpoint.desc = desc;
 		dep->comp_desc = comp_desc;
 		dep->type = usb_endpoint_type(desc);
@@ -1666,8 +1704,6 @@ static int dwc3_gadget_start(struct usb_gadget *g,
 	}
 	dwc3_writel(dwc->regs, DWC3_DCFG, reg);
 
-	dwc->start_config_issued = false;
-
 	/* Start with SuperSpeed Default */
 	dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512);
 
@@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc)
 	dwc3_writel(dwc->regs, DWC3_DCTL, reg);
 
 	dwc3_disconnect_gadget(dwc);
-	dwc->start_config_issued = false;
 
 	dwc->gadget.speed = USB_SPEED_UNKNOWN;
 	dwc->setup_packet_pending = false;
@@ -2293,7 +2328,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
 
 	dwc3_stop_active_transfers(dwc);
 	dwc3_clear_stall_all_ep(dwc);
-	dwc->start_config_issued = false;
 
 	/* Reset device address to zero */
 	reg = dwc3_readl(dwc->regs, DWC3_DCFG);

[PATCH 3.16.y-ckt 032/142] NFSv4: Fix a dentry leak on alias use

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Benjamin Coddington <bcodding@redhat.com>

commit d9dfd8d741683347ee159d25f5b50c346a0df557 upstream.

In the case where d_add_unique() finds an appropriate alias to use it will
have already incremented the reference count.  An additional dget() to swap
the open context's dentry is unnecessary and will leak a reference.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Fixes: 275bb307865a3 ("NFSv4: Move dentry instantiation into the NFSv4-...")
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/nfs/nfs4proc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cdbc0599664d..864b3214cc89 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2243,9 +2243,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 		dentry = d_add_unique(dentry, igrab(state->inode));
 		if (dentry == NULL) {
 			dentry = opendata->dentry;
-		} else if (dentry != ctx->dentry) {
+		} else {
 			dput(ctx->dentry);
-			ctx->dentry = dget(dentry);
+			ctx->dentry = dentry;
 		}
 		nfs_set_verifier(dentry,
 				nfs_save_change_attribute(opendata->dir->d_inode));

[PATCH 3.16.y-ckt 033/142] USB: option: add support for SIM7100E

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Andrey Skvortsov <andrej.skvortzov@gmail.com>

commit 3158a8d416f4e1b79dcc867d67cb50013140772c upstream.

$ lsusb:
Bus 001 Device 101: ID 1e0e:9001 Qualcomm / Option

$ usb-devices:
T:  Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=101 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  2
P:  Vendor=1e0e ProdID=9001 Rev= 2.32
S:  Manufacturer=SimTech, Incorporated
S:  Product=SimTech, Incorporated
S:  SerialNumber=0123456789ABCDEF
C:* #Ifs= 7 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)

The last interface (6) is used for Android Composite ADB interface.

Serial port layout:
0: QCDM/DIAG
1: NMEA
2: AT
3: AT/PPP
4: audio

Signed-off-by: Andrey Skvortsov <andrej.skvortzov@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/option.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 57d38623929d..be60c6758dc0 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -317,6 +317,7 @@ static void option_instat_callback(struct urb *urb);
 #define TOSHIBA_PRODUCT_G450			0x0d45
 
 #define ALINK_VENDOR_ID				0x1e0e
+#define SIMCOM_PRODUCT_SIM7100E			0x9001 /* Yes, ALINK_VENDOR_ID */
 #define ALINK_PRODUCT_PH300			0x9100
 #define ALINK_PRODUCT_3GU			0x9200
 
@@ -617,6 +618,10 @@ static const struct option_blacklist_info zte_1255_blacklist = {
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info simcom_sim7100e_blacklist = {
+	.reserved = BIT(5) | BIT(6),
+};
+
 static const struct option_blacklist_info telit_le910_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(2),
@@ -1656,6 +1661,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(ALINK_VENDOR_ID, 0x9000) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E),
+	  .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist
 	},

[PATCH 3.16.y-ckt 034/142] USB: cp210x: add IDs for GE B650V3 and B850V3 boards

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Ken Lin <ken.lin@advantech.com.tw>

commit 6627ae19385283b89356a199d7f03c75ba35fb29 upstream.

Add USB ID for cp2104/5 devices on GE B650v3 and B850v3 boards.

Signed-off-by: Ken Lin <ken.lin@advantech.com.tw>
Signed-off-by: Akshay Bhat <akshay.bhat@timesys.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/cp210x.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 02e6fe228a63..21bf168981f9 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -162,6 +162,8 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */
+	{ USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
+	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
 	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */

[PATCH 3.16.y-ckt 035/142] USB: option: add "4G LTE usb-modem U901"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>

commit d061c1caa31d4d9792cfe48a2c6b309a0e01ef46 upstream.

Thomas reports:

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=05c6 ProdID=6001 Rev=00.00
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=1234567890ABCDEF
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/option.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index be60c6758dc0..46305ca6158e 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1142,6 +1142,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */

[PATCH 3.16.y-ckt 036/142] hwmon: (ads1015) Handle negative conversion values correctly

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Rosin <peda@axentia.se>

commit acc146943957d7418a6846f06e029b2c5e87e0d5 upstream.

Make the divisor signed as DIV_ROUND_CLOSEST is undefined for negative
dividends when the divisor is unsigned.

Signed-off-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/hwmon/ads1015.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 126516414c11..44223f5d92d8 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -126,7 +126,7 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel,
 	struct ads1015_data *data = i2c_get_clientdata(client);
 	unsigned int pga = data->channel_data[channel].pga;
 	int fullscale = fullscale_table[pga];
-	const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
+	const int mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
 
 	return DIV_ROUND_CLOSEST(reg * fullscale, mask);
 }

[PATCH 3.16.y-ckt 037/142] drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Lisa Du <cldu@marvell.com>

commit 7a64cd887fdb97f074c3fda03bee0bfb9faceac3 upstream.

There's one point was missed in the patch commit da49889deb34 ("staging:
binder: Support concurrent 32 bit and 64 bit processes."). When configure
BINDER_IPC_32BIT, the size of binder_uintptr_t was 32bits, but size of
void * is 64bit on 64bit system. Correct it here.

Signed-off-by: Lisa Du <cldu@marvell.com>
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Fixes: da49889deb34 ("staging: binder: Support concurrent 32 bit and 64 bit processes.")
Acked-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ luis: backported to 3.16:
  - binder is still in staging in the 3.16 kernel]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/staging/android/binder.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index a741da77828a..3b79624703a7 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -2049,7 +2049,7 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
 				return -EFAULT;
 
-			ptr += sizeof(void *);
+			ptr += sizeof(cookie);
 			list_for_each_entry(w, &proc->delivered_death, entry) {
 				struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
 

[PATCH 3.16.y-ckt 038/142] can: ems_usb: Fix possible tx overflow

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>

commit 90cfde46586d2286488d8ed636929e936c0c9ab2 upstream.

This patch fixes the problem that more CAN messages could be sent to the
interface as could be send on the CAN bus. This was more likely for slow baud
rates. The sleeping _start_xmit was woken up in the _write_bulk_callback. Under
heavy TX load this produced another bulk transfer without checking the
free_slots variable and hence caused the overflow in the interface.

Signed-off-by: Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/can/usb/ems_usb.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 00f2534dde73..91a4312e5c34 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -117,6 +117,9 @@ MODULE_LICENSE("GPL v2");
  */
 #define EMS_USB_ARM7_CLOCK 8000000
 
+#define CPC_TX_QUEUE_TRIGGER_LOW	25
+#define CPC_TX_QUEUE_TRIGGER_HIGH	35
+
 /*
  * CAN-Message representation in a CPC_MSG. Message object type is
  * CPC_MSG_TYPE_CAN_FRAME or CPC_MSG_TYPE_RTR_FRAME or
@@ -278,6 +281,11 @@ static void ems_usb_read_interrupt_callback(struct urb *urb)
 	switch (urb->status) {
 	case 0:
 		dev->free_slots = dev->intr_in_buffer[1];
+		if(dev->free_slots > CPC_TX_QUEUE_TRIGGER_HIGH){
+			if (netif_queue_stopped(netdev)){
+				netif_wake_queue(netdev);
+			}
+		}
 		break;
 
 	case -ECONNRESET: /* unlink */
@@ -529,8 +537,6 @@ static void ems_usb_write_bulk_callback(struct urb *urb)
 	/* Release context */
 	context->echo_index = MAX_TX_URBS;
 
-	if (netif_queue_stopped(netdev))
-		netif_wake_queue(netdev);
 }
 
 /*
@@ -590,7 +596,7 @@ static int ems_usb_start(struct ems_usb *dev)
 	int err, i;
 
 	dev->intr_in_buffer[0] = 0;
-	dev->free_slots = 15; /* initial size */
+	dev->free_slots = 50; /* initial size */
 
 	for (i = 0; i < MAX_RX_URBS; i++) {
 		struct urb *urb = NULL;
@@ -841,7 +847,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 
 		/* Slow down tx path */
 		if (atomic_read(&dev->active_tx_urbs) >= MAX_TX_URBS ||
-		    dev->free_slots < 5) {
+		    dev->free_slots < CPC_TX_QUEUE_TRIGGER_LOW) {
 			netif_stop_queue(netdev);
 		}
 	}

[PATCH 3.16.y-ckt 039/142] drm/radeon/pm: adjust display configuration after powerstate

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit 39d4275058baf53e89203407bf3841ff2c74fa32 upstream.

set_power_state defaults to no displays, so we need to update
the display configuration after setting up the powerstate on the
first call. In most cases this is not an issue since ends up
getting called multiple times at any given modeset and the proper
order is achieved in the display changed handling at the top of
the function.

Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Jordan Lazare <Jordan.Lazare@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_pm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 98dcccacd678..97e1a70df5a9 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -936,8 +936,6 @@ force:
 
 	/* update display watermarks based on new power state */
 	radeon_bandwidth_update(rdev);
-	/* update displays */
-	radeon_dpm_display_configuration_changed(rdev);
 
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
@@ -958,6 +956,9 @@ force:
 
 	radeon_dpm_post_set_power_state(rdev);
 
+	/* update displays */
+	radeon_dpm_display_configuration_changed(rdev);
+
 	if (rdev->asic->dpm.force_performance_level) {
 		if (rdev->pm.dpm.thermal_active) {
 			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;

[PATCH 3.16.y-ckt 040/142] sunrpc/cache: fix off-by-one in qword_get()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Stefan Hajnoczi <stefanha@redhat.com>

commit b7052cd7bcf3c1478796e93e3dff2b44c9e82943 upstream.

The qword_get() function NUL-terminates its output buffer.  If the input
string is in hex format \xXXXX... and the same length as the output
buffer, there is an off-by-one:

  int qword_get(char **bpp, char *dest, int bufsize)
  {
      ...
      while (len < bufsize) {
          ...
          *dest++ = (h << 4) | l;
          len++;
      }
      ...
      *dest = '\0';
      return len;
  }

This patch ensures the NUL terminator doesn't fall outside the output
buffer.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/sunrpc/cache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 48f14003af10..14d38ec5e53d 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1230,7 +1230,7 @@ int qword_get(char **bpp, char *dest, int bufsize)
 	if (bp[0] == '\\' && bp[1] == 'x') {
 		/* HEX STRING */
 		bp += 2;
-		while (len < bufsize) {
+		while (len < bufsize - 1) {
 			int h, l;
 
 			h = hex_to_bin(bp[0]);

[PATCH 3.16.y-ckt 041/142] KVM: async_pf: do not warn on page allocation failures

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit d7444794a02ff655eda87e3cc54e86b940e7736f upstream.

In async_pf we try to allocate with NOWAIT to get an element quickly
or fail. This code also handle failures gracefully. Lets silence
potential page allocation failures under load.

qemu-system-s39: page allocation failure: order:0,mode:0x2200000
[...]
Call Trace:
([<00000000001146b8>] show_trace+0xf8/0x148)
[<000000000011476a>] show_stack+0x62/0xe8
[<00000000004a36b8>] dump_stack+0x70/0x98
[<0000000000272c3a>] warn_alloc_failed+0xd2/0x148
[<000000000027709e>] __alloc_pages_nodemask+0x94e/0xb38
[<00000000002cd36a>] new_slab+0x382/0x400
[<00000000002cf7ac>] ___slab_alloc.constprop.30+0x2dc/0x378
[<00000000002d03d0>] kmem_cache_alloc+0x160/0x1d0
[<0000000000133db4>] kvm_setup_async_pf+0x6c/0x198
[<000000000013dee8>] kvm_arch_vcpu_ioctl_run+0xd48/0xd58
[<000000000012fcaa>] kvm_vcpu_ioctl+0x372/0x690
[<00000000002f66f6>] do_vfs_ioctl+0x3be/0x510
[<00000000002f68ec>] SyS_ioctl+0xa4/0xb8
[<0000000000781c5e>] system_call+0xd6/0x264
[<000003ffa24fa06a>] 0x3ffa24fa06a

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 virt/kvm/async_pf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d6a3d0993d88..965a818dea75 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -171,7 +171,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 	 * do alloc nowait since if we are going to sleep anyway we
 	 * may as well sleep faulting in page
 	 */
-	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
+	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
 	if (!work)
 		return 0;
 

[PATCH 3.16.y-ckt 042/142] tracing: Fix showing function event in available_events

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

commit d045437a169f899dfb0f6f7ede24cc042543ced9 upstream.

The ftrace:function event is only displayed for parsing the function tracer
data. It is not used to enable function tracing, and does not include an
"enable" file in its event directory.

Originally, this event was kept separate from other events because it did
not have a ->reg parameter. But perf added a "reg" parameter for its use
which caused issues, because it made the event available to functions where
it was not compatible for.

Commit 9b63776fa3ca9 "tracing: Do not enable function event with enable"
added a TRACE_EVENT_FL_IGNORE_ENABLE flag that prevented the function event
from being enabled by normal trace events. But this commit missed keeping
the function event from being displayed by the "available_events" directory,
which is used to show what events can be enabled by set_event.

One documented way to enable all events is to:

 cat available_events > set_event

But because the function event is displayed in the available_events, this
now causes an INVALID error:

 cat: write error: Invalid argument

Reported-by: Chunyu Hu <chuhu@redhat.com>
Fixes: 9b63776fa3ca9 "tracing: Do not enable function event with enable"
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace_events.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 41c56b7e882c..ecf3e9fb8ee4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -642,7 +642,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && call->class->reg)
+		if (call->class && call->class->reg &&
+		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 			return file;
 	}
 

[PATCH 3.16.y-ckt 043/142] libceph: don't bail early from try_read() when skipping a message

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Ilya Dryomov <idryomov@gmail.com>

commit e7a88e82fe380459b864e05b372638aeacb0f52d upstream.

The contract between try_read() and try_write() is that when called
each processes as much data as possible.  When instructed by osd_client
to skip a message, try_read() is violating this contract by returning
after receiving and discarding a single message instead of checking for
more.  try_write() then gets a chance to write out more requests,
generating more replies/skips for try_read() to handle, forcing the
messenger into a starvation loop.

Reported-by: Varada Kari <Varada.Kari@sandisk.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Tested-by: Varada Kari <Varada.Kari@sandisk.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ceph/messenger.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 6b15183a68c8..f2ea1a093800 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2285,7 +2285,7 @@ static int read_partial_message(struct ceph_connection *con)
 		con->in_base_pos = -front_len - middle_len - data_len -
 			sizeof(m->footer);
 		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 0;
+		return 1;
 	} else if ((s64)seq - (s64)con->in_seq > 1) {
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
 		       seq, con->in_seq + 1);
@@ -2318,7 +2318,7 @@ static int read_partial_message(struct ceph_connection *con)
 				sizeof(m->footer);
 			con->in_tag = CEPH_MSGR_TAG_READY;
 			con->in_seq++;
-			return 0;
+			return 1;
 		}
 
 		BUG_ON(!con->in_msg);

[PATCH 3.16.y-ckt 044/142] ALSA: hda - Fixing background noise on Dell Inspiron 3162

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Kai-Heng Feng <kaihengfeng@gmail.com>

commit 3b43b71f05d3ecd01c4116254666d9492301697d upstream.

After login to the desktop on Dell Inspiron 3162,
there's a very loud background noise comes from the builtin speaker.
The noise does not go away even if the speaker is muted.

The noise disappears after using the aamix fixup.

Codec: Realtek ALC3234
Address: 0
AFG Function Id: 0x1 (unsol 1)
    Vendor Id: 0x10ec0255
    Subsystem Id: 0x10280725
    Revision Id: 0x100002
    No Modem Function Group found

BugLink: http://bugs.launchpad.net/bugs/1549620
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index af6448309a00..64282220edbd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4341,6 +4341,7 @@ enum {
 	ALC275_FIXUP_DELL_XPS,
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
+	ALC255_FIXUP_DELL_SPK_NOISE,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -4827,6 +4828,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_THINKPAD_ACPI
 	},
+	[ALC255_FIXUP_DELL_SPK_NOISE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -4892,6 +4899,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),

[PATCH 3.16.y-ckt 045/142] KVM: x86: MMU: fix ubsan index-out-of-range warning

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Mike Krinkin <krinkin.m.u@gmail.com>

commit 17e4bce0ae63c7e03f3c7fa8d80890e7af3d4971 upstream.

Ubsan reports the following warning due to a typo in
update_accessed_dirty_bits template, the patch fixes
the typo:

[  168.791851] ================================================================================
[  168.791862] UBSAN: Undefined behaviour in arch/x86/kvm/paging_tmpl.h:252:15
[  168.791866] index 4 is out of range for type 'u64 [4]'
[  168.791871] CPU: 0 PID: 2950 Comm: qemu-system-x86 Tainted: G           O L  4.5.0-rc5-next-20160222 #7
[  168.791873] Hardware name: LENOVO 23205NG/23205NG, BIOS G2ET95WW (2.55 ) 07/09/2013
[  168.791876]  0000000000000000 ffff8801cfcaf208 ffffffff81c9f780 0000000041b58ab3
[  168.791882]  ffffffff82eb2cc1 ffffffff81c9f6b4 ffff8801cfcaf230 ffff8801cfcaf1e0
[  168.791886]  0000000000000004 0000000000000001 0000000000000000 ffffffffa1981600
[  168.791891] Call Trace:
[  168.791899]  [<ffffffff81c9f780>] dump_stack+0xcc/0x12c
[  168.791904]  [<ffffffff81c9f6b4>] ? _atomic_dec_and_lock+0xc4/0xc4
[  168.791910]  [<ffffffff81da9e81>] ubsan_epilogue+0xd/0x8a
[  168.791914]  [<ffffffff81daafa2>] __ubsan_handle_out_of_bounds+0x15c/0x1a3
[  168.791918]  [<ffffffff81daae46>] ? __ubsan_handle_shift_out_of_bounds+0x2bd/0x2bd
[  168.791922]  [<ffffffff811287ef>] ? get_user_pages_fast+0x2bf/0x360
[  168.791954]  [<ffffffffa1794050>] ? kvm_largepages_enabled+0x30/0x30 [kvm]
[  168.791958]  [<ffffffff81128530>] ? __get_user_pages_fast+0x360/0x360
[  168.791987]  [<ffffffffa181b818>] paging64_walk_addr_generic+0x1b28/0x2600 [kvm]
[  168.792014]  [<ffffffffa1819cf0>] ? init_kvm_mmu+0x1100/0x1100 [kvm]
[  168.792019]  [<ffffffff8129e350>] ? debug_check_no_locks_freed+0x350/0x350
[  168.792044]  [<ffffffffa1819cf0>] ? init_kvm_mmu+0x1100/0x1100 [kvm]
[  168.792076]  [<ffffffffa181c36d>] paging64_gva_to_gpa+0x7d/0x110 [kvm]
[  168.792121]  [<ffffffffa181c2f0>] ? paging64_walk_addr_generic+0x2600/0x2600 [kvm]
[  168.792130]  [<ffffffff812e848b>] ? debug_lockdep_rcu_enabled+0x7b/0x90
[  168.792178]  [<ffffffffa17d9a4a>] emulator_read_write_onepage+0x27a/0x1150 [kvm]
[  168.792208]  [<ffffffffa1794d44>] ? __kvm_read_guest_page+0x54/0x70 [kvm]
[  168.792234]  [<ffffffffa17d97d0>] ? kvm_task_switch+0x160/0x160 [kvm]
[  168.792238]  [<ffffffff812e848b>] ? debug_lockdep_rcu_enabled+0x7b/0x90
[  168.792263]  [<ffffffffa17daa07>] emulator_read_write+0xe7/0x6d0 [kvm]
[  168.792290]  [<ffffffffa183b620>] ? em_cr_write+0x230/0x230 [kvm]
[  168.792314]  [<ffffffffa17db005>] emulator_write_emulated+0x15/0x20 [kvm]
[  168.792340]  [<ffffffffa18465f8>] segmented_write+0xf8/0x130 [kvm]
[  168.792367]  [<ffffffffa1846500>] ? em_lgdt+0x20/0x20 [kvm]
[  168.792374]  [<ffffffffa14db512>] ? vmx_read_guest_seg_ar+0x42/0x1e0 [kvm_intel]
[  168.792400]  [<ffffffffa1846d82>] writeback+0x3f2/0x700 [kvm]
[  168.792424]  [<ffffffffa1846990>] ? em_sidt+0xa0/0xa0 [kvm]
[  168.792449]  [<ffffffffa185554d>] ? x86_decode_insn+0x1b3d/0x4f70 [kvm]
[  168.792474]  [<ffffffffa1859032>] x86_emulate_insn+0x572/0x3010 [kvm]
[  168.792499]  [<ffffffffa17e71dd>] x86_emulate_instruction+0x3bd/0x2110 [kvm]
[  168.792524]  [<ffffffffa17e6e20>] ? reexecute_instruction.part.110+0x2e0/0x2e0 [kvm]
[  168.792532]  [<ffffffffa14e9a81>] handle_ept_misconfig+0x61/0x460 [kvm_intel]
[  168.792539]  [<ffffffffa14e9a20>] ? handle_pause+0x450/0x450 [kvm_intel]
[  168.792546]  [<ffffffffa15130ea>] vmx_handle_exit+0xd6a/0x1ad0 [kvm_intel]
[  168.792572]  [<ffffffffa17f6a6c>] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm]
[  168.792597]  [<ffffffffa17f6bcd>] kvm_arch_vcpu_ioctl_run+0xd3d/0x6090 [kvm]
[  168.792621]  [<ffffffffa17f6a6c>] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm]
[  168.792627]  [<ffffffff8293b530>] ? __ww_mutex_lock_interruptible+0x1630/0x1630
[  168.792651]  [<ffffffffa17f5e90>] ? kvm_arch_vcpu_runnable+0x4f0/0x4f0 [kvm]
[  168.792656]  [<ffffffff811eeb30>] ? preempt_notifier_unregister+0x190/0x190
[  168.792681]  [<ffffffffa17e0447>] ? kvm_arch_vcpu_load+0x127/0x650 [kvm]
[  168.792704]  [<ffffffffa178e9a3>] kvm_vcpu_ioctl+0x553/0xda0 [kvm]
[  168.792727]  [<ffffffffa178e450>] ? vcpu_put+0x40/0x40 [kvm]
[  168.792732]  [<ffffffff8129e350>] ? debug_check_no_locks_freed+0x350/0x350
[  168.792735]  [<ffffffff82946087>] ? _raw_spin_unlock+0x27/0x40
[  168.792740]  [<ffffffff8163a943>] ? handle_mm_fault+0x1673/0x2e40
[  168.792744]  [<ffffffff8129daa8>] ? trace_hardirqs_on_caller+0x478/0x6c0
[  168.792747]  [<ffffffff8129dcfd>] ? trace_hardirqs_on+0xd/0x10
[  168.792751]  [<ffffffff812e848b>] ? debug_lockdep_rcu_enabled+0x7b/0x90
[  168.792756]  [<ffffffff81725a80>] do_vfs_ioctl+0x1b0/0x12b0
[  168.792759]  [<ffffffff817258d0>] ? ioctl_preallocate+0x210/0x210
[  168.792763]  [<ffffffff8174aef3>] ? __fget+0x273/0x4a0
[  168.792766]  [<ffffffff8174acd0>] ? __fget+0x50/0x4a0
[  168.792770]  [<ffffffff8174b1f6>] ? __fget_light+0x96/0x2b0
[  168.792773]  [<ffffffff81726bf9>] SyS_ioctl+0x79/0x90
[  168.792777]  [<ffffffff82946880>] entry_SYSCALL_64_fastpath+0x23/0xc1
[  168.792780] ================================================================================

Signed-off-by: Mike Krinkin <krinkin.m.u@gmail.com>
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/kvm/paging_tmpl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 484711d2c71f..ed6eb79d3f6b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -257,7 +257,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 			return ret;
 
 		mark_page_dirty(vcpu->kvm, table_gfn);
-		walker->ptes[level] = pte;
+		walker->ptes[level - 1] = pte;
 	}
 	return 0;
 }

[PATCH 3.16.y-ckt 046/142] ALSA: hda - Fix headset support and noise on HP EliteBook 755 G2

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit f883982dc1b117f04579f0896821cd9f2e397f94 upstream.

HP EliteBook 755 G2 with ALC3228 (ALC280) codec [103c:221c] requires
the known fixup (ALC269_FIXUP_HEADSET_MIC) for making the headset mic
working.  Also, it suffers from the loopback noise problem, so we
should disable aamix path as well.

Reported-by: Derick Eddington <derick.eddington@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 64282220edbd..437688036c2a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4342,6 +4342,7 @@ enum {
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC255_FIXUP_DELL_SPK_NOISE,
+	ALC280_FIXUP_HP_HEADSET_MIC,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -4834,6 +4835,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC280_FIXUP_HP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -4951,6 +4958,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	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(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),

[PATCH 3.16.y-ckt 047/142] hpfs: don't truncate the file when delete fails

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Mikulas Patocka <mikulas@twibright.com>

commit b6853f78e763d42c7a158d8de3549c9827c604ab upstream.

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

If there is not enough available space, the HPFS driver attempted to
truncate the file, but this results in a deadlock since the commit
7dd29d8d865efdb00c0542a5d2c87af8c52ea6c7 ("HPFS: Introduce a global mutex
and lock it on every callback from VFS").

This patch removes the code that tries to truncate the file and -ENOSPC is
returned instead. If the user hits -ENOSPC on delete, he should try to
delete other files (that are stored in a leaf btree node), so that the
delete operation will make some space for deleting the file stored in
non-leaf btree node.

Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/hpfs/namei.c | 31 +++----------------------------
 1 file changed, 3 insertions(+), 28 deletions(-)

diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 0642cafaab34..12da295759f7 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -377,12 +377,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	dnode_secno dno;
 	int r;
-	int rep = 0;
 	int err;
 
 	hpfs_lock(dir->i_sb);
 	hpfs_adjust_length(name, &len);
-again:
+
 	err = -ENOENT;
 	de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
 	if (!de)
@@ -402,33 +401,9 @@ again:
 		hpfs_error(dir->i_sb, "there was error when removing dirent");
 		err = -EFSERROR;
 		break;
-	case 2:		/* no space for deleting, try to truncate file */
-
+	case 2:		/* no space for deleting */
 		err = -ENOSPC;
-		if (rep++)
-			break;
-
-		dentry_unhash(dentry);
-		if (!d_unhashed(dentry)) {
-			hpfs_unlock(dir->i_sb);
-			return -ENOSPC;
-		}
-		if (generic_permission(inode, MAY_WRITE) ||
-		    !S_ISREG(inode->i_mode) ||
-		    get_write_access(inode)) {
-			d_rehash(dentry);
-		} else {
-			struct iattr newattrs;
-			/*pr_info("truncating file before delete.\n");*/
-			newattrs.ia_size = 0;
-			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs, NULL);
-			put_write_access(inode);
-			if (!err)
-				goto again;
-		}
-		hpfs_unlock(dir->i_sb);
-		return -ENOSPC;
+		break;
 	default:
 		drop_nlink(inode);
 		err = 0;

[PATCH 3.16.y-ckt 048/142] do_last(): don't let a bogus return value from ->open() et.al. to confuse us

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Al Viro <viro@zeniv.linux.org.uk>

commit c80567c82ae4814a41287618e315a60ecf513be6 upstream.

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

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/namei.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/namei.c b/fs/namei.c
index 8a0c3d9d8298..34f8224be4ed 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3108,6 +3108,10 @@ opened:
 			goto exit_fput;
 	}
 out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);

[PATCH 3.16.y-ckt 049/142] ARM: dts: kirkwood: use unique machine name for ds112

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Heinrich Schuchardt <xypron.glpk@gmx.de>

commit 9d021c9d1b4b774a35d8a03d58dbf029544debda upstream.

Downstream packages like Debian flash-kernel use
/proc/device-tree/model
to determine which dtb file to install.

Hence each dts in the Linux kernel should provide a unique model
identifier.

Commit 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS
devices") created the new files kirkwood-ds111.dts and kirkwood-ds112.dts
using the same model identifier.

This patch provides a unique model identifier for the
Synology DiskStation DS112.

Fixes: 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS devices")
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/boot/dts/kirkwood-ds112.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts
index bf4143c6cb8f..b84af3da8c84 100644
--- a/arch/arm/boot/dts/kirkwood-ds112.dts
+++ b/arch/arm/boot/dts/kirkwood-ds112.dts
@@ -14,7 +14,7 @@
 #include "kirkwood-synology.dtsi"
 
 / {
-	model = "Synology DS111";
+	model = "Synology DS112";
 	compatible = "synology,ds111", "marvell,kirkwood";
 
 	memory {

[PATCH 3.16.y-ckt 050/142] bonding: Fix ARP monitor validation

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jay Vosburgh <jay.vosburgh@canonical.com>

commit 21a75f0915dde8674708b39abfcda113911c49b1 upstream.

The current logic in bond_arp_rcv will accept an incoming ARP for
validation if (a) the receiving slave is either "active" (which includes
the currently active slave, or the current ARP slave) or, (b) there is a
currently active slave, and it has received an ARP since it became active.
For case (b), the receiving slave isn't the currently active slave, and is
receiving the original broadcast ARP request, not an ARP reply from the
target.

	This logic can fail if there is no currently active slave.  In
this situation, the ARP probe logic cycles through all slaves, assigning
each in turn as the "current_arp_slave" for one arp_interval, then setting
that one as "active," and sending an ARP probe from that slave.  The
current logic expects the ARP reply to arrive on the sending
current_arp_slave, however, due to switch FDB updating delays, the reply
may be directed to another slave.

	This can arise if the bonding slaves and switch are working, but
the ARP target is not responding.  When the ARP target recovers, a
condition may result wherein the ARP target host replies faster than the
switch can update its forwarding table, causing each ARP reply to be sent
to the previous current_arp_slave.  This will never pass the logic in
bond_arp_rcv, as neither of the above conditions (a) or (b) are met.

	Some experimentation on a LAN shows ARP reply round trips in the
200 usec range, but my available switches never update their FDB in less
than 4000 usec.

	This patch changes the logic in bond_arp_rcv to additionally
accept an ARP reply for validation on any slave if there is a current ARP
slave and it sent an ARP probe during the previous arp_interval.

Fixes: aeea64ac717a ("bonding: don't trust arp requests unless active slave really works")
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/bonding/bond_main.c | 40 ++++++++++++++++++++++++++++------------
 1 file changed, 28 insertions(+), 12 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8b555aca45eb..41503ce1e3b7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -210,6 +210,8 @@ static int lacp_fast;
 
 static int bond_init(struct net_device *bond_dev);
 static void bond_uninit(struct net_device *bond_dev);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -2352,7 +2354,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2399,27 +2401,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/*
-	 * Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
+	 *
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
+	 *
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)

[PATCH 3.16.y-ckt 051/142] af_unix: Don't set err in unix_stream_read_generic unless there was an error

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Rainer Weikusat <rweikusat@mobileactivedefense.com>

commit 1b92ee3d03af6643df395300ba7748f19ecdb0c5 upstream.

The present unix_stream_read_generic contains various code sequences of
the form

err = -EDISASTER;
if (<test>)
	goto out;

This has the unfortunate side effect of possibly causing the error code
to bleed through to the final

out:
	return copied ? : err;

and then to be wrongly returned if no data was copied because the caller
didn't supply a data buffer, as demonstrated by the program available at

http://pad.lv/1540731

Change it such that err is only set if an error condition was detected.

Fixes: 3822b5c2fc62 ("af_unix: Revert 'lock_interruptible' in stream receive code")
Reported-by: Joseph Salisbury <joseph.salisbury@canonical.com>
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16:
  - modify unix_stream_recvmsg() instead of unix_stream_read_generic()
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/unix/af_unix.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index bfc5f03889a9..5a5721a7f9e0 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2092,13 +2092,15 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	long timeo;
 	int skip;
 
-	err = -EINVAL;
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+		err = -EINVAL;
 		goto out;
+	}
 
-	err = -EOPNOTSUPP;
-	if (flags&MSG_OOB)
+	if (unlikely(flags & MSG_OOB)) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
@@ -2146,9 +2148,11 @@ again:
 				goto unlock;
 
 			unix_state_unlock(sk);
-			err = -EAGAIN;
-			if (!timeo)
+			if (!timeo) {
+				err = -EAGAIN;
 				break;
+			}
+
 			mutex_unlock(&u->readlock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last);

[PATCH 3.16.y-ckt 052/142] af_unix: Guard against other == sk in unix_dgram_sendmsg

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Rainer Weikusat <rweikusat@mobileactivedefense.com>

commit a5527dda344fff0514b7989ef7a755729769daa1 upstream.

The unix_dgram_sendmsg routine use the following test

if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {

to determine if sk and other are in an n:1 association (either
established via connect or by using sendto to send messages to an
unrelated socket identified by address). This isn't correct as the
specified address could have been bound to the sending socket itself or
because this socket could have been connected to itself by the time of
the unix_peer_get but disconnected before the unix_state_lock(other). In
both cases, the if-block would be entered despite other == sk which
might either block the sender unintentionally or lead to trying to unlock
the same spin lock twice for a non-blocking send. Add a other != sk
check to guard against this.

Fixes: 7d267278a9ec ("unix: avoid use-after-free in ep_remove_wait_queue")
Reported-By: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Tested-by: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5a5721a7f9e0..3e6f0eba8216 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1722,7 +1722,12 @@ restart_locked:
 			goto out_unlock;
 	}
 
-	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	/* other == sk && unix_peer(other) != sk if
+	 * - unix_peer(sk) == NULL, destination address bound to sk
+	 * - unix_peer(sk) == sk by time of get but disconnected before lock
+	 */
+	if (other != sk &&
+	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 

[PATCH 3.16.y-ckt 053/142] net: phy: bcm7xxx: Fix shadow mode 2 disabling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Florian Fainelli <f.fainelli@gmail.com>

commit 50d899808d33a5b0aa82be23e824119944042689 upstream.

The clear and set masks in the call to phy_set_clr_bits() called from
bcm7xxx_config_init() are inverted. We need to fix this by swapping the two
arguments, that is, set 0 bits, but clear the shade mode 2 enable bit.

Fixes: b560a58c45c66 ("net: phy: add Broadcom BCM7xxx internal PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/phy/bcm7xxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 526b94cea569..51678e393793 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -204,7 +204,7 @@ static int bcm7xxx_config_init(struct phy_device *phydev)
 	phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555);
 
 	/* reset shadow mode 2 */
-	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0);
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, MII_BCM7XXX_SHD_MODE_2);
 	if (ret < 0)
 		return ret;
 

[PATCH 3.16.y-ckt 054/142] net/mlx4_en: Count HW buffer overrun only once

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Amir Vadai <amir@vadai.me>

commit 281e8b2fdf8e4ef366b899453cae50e09b577ada upstream.

RdropOvflw counts overrun of HW buffer, therefore should
be used for rx_fifo_errors only.

Currently RdropOvflw counter is mistakenly also set into
rx_missed_errors and rx_over_errors too, which makes the
device total dropped packets accounting to show wrong results.

Fix that. Use it for rx_fifo_errors only.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC')
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index c2cfb05e7290..40d6c3c6b3a0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -177,11 +177,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 			   be64_to_cpu(mlx4_en_stats->MCAST_novlan);
 	stats->collisions = 0;
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
-	stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_over_errors = 0;
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_frame_errors = 0;
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_missed_errors = 0;
 	stats->tx_aborted_errors = 0;
 	stats->tx_carrier_errors = 0;
 	stats->tx_fifo_errors = 0;

[PATCH 3.16.y-ckt 055/142] net/mlx4_en: Choose time-stamping shift value according to HW frequency

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eugenia Emantayev <eugenia@mellanox.com>

commit 31c128b66e5b28f468076e4f3ca3025c35342041 upstream.

Previously, the shift value used for time-stamping was constant and didn't
depend on the HW chip frequency. Change that to take the frequency into account
and calculate the maximal value in cycles per wraparound of ten seconds. This
time slot was chosen since it gives a good accuracy in time synchronization.

Algorithm for shift value calculation:
 * Round up the maximal value in cycles to nearest power of two

 * Calculate maximal multiplier by division of all 64 bits set
   to above result

 * Then, invert the function clocksource_khz2mult() to get the shift from
   maximal mult value

Fixes: ec693d47010e ('net/mlx4_en: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_clock.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 74ed9f8fd267..74e783ba68ea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -285,6 +285,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
+#define MLX4_EN_WRAP_AROUND_SEC	10ULL
+
+/* This function calculates the max shift that enables the user range
+ * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
+ */
+static u32 freq_to_shift(u16 freq)
+{
+	u32 freq_khz = freq * 1000;
+	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
+		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+	/* calculate max possible multiplier in order to fit in 64bit */
+	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+
+	/* This comes from the reverse of clocksource_khz2mult */
+	return ilog2(div_u64(max_mul * freq_khz, 1000000));
+}
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
@@ -303,12 +321,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
-	/* Using shift to make calculation more accurate. Since current HW
-	 * clock frequency is 427 MHz, and cycles are given using a 48 bits
-	 * register, the biggest shift when calculating using u64, is 14
-	 * (max_cycles * multiplier < 2^64)
-	 */
-	mdev->cycles.shift = 14;
+	mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock);
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
 	mdev->nominal_c_mult = mdev->cycles.mult;

[PATCH 3.16.y-ckt 056/142] net/mlx4_en: Avoid changing dev->features directly in run-time

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eugenia Emantayev <eugenia@mellanox.com>

commit 925ab1aa9394bbaeac47ee5b65d3fdf0fb8135cf upstream.

It's forbidden to manually change dev->features in run-time. Currently, this is
done in the driver to make sure that GSO_UDP_TUNNEL is advertized only when
VXLAN tunnel is set. However, since the stack actually does features intersection
with hw_enc_features, we can safely revert to advertizing features early when
registering the netdevice.

Fixes: f4a1edd56120 ('net/mlx4_en: Advertize encapsulation offloads [...]')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bf3878823c96..1f588195fe9f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2324,8 +2324,6 @@ out:
 	/* set offloads */
 	priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
 }
 
 static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
@@ -2336,8 +2334,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 	/* unset offloads */
 	priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL);
-	priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    &= ~NETIF_F_GSO_UDP_TUNNEL;
 
 	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
 				  VXLAN_STEER_BY_OUTER_MAC, 0);
@@ -2618,6 +2614,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
 		dev->priv_flags |= IFF_UNICAST_FLT;
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 
 	netif_carrier_off(dev);

[PATCH 3.16.y-ckt 057/142] unix_diag: fix incorrect sign extension in unix_lookup_by_ino

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Dmitry V. Levin" <ldv@altlinux.org>

commit b5f0549231ffb025337be5a625b0ff9f52b016f0 upstream.

The value passed by unix_diag_get_exact to unix_lookup_by_ino has type
__u32, but unix_lookup_by_ino's argument ino has type int, which is not
a problem yet.
However, when ino is compared with sock_i_ino return value of type
unsigned long, ino is sign extended to signed long, and this results
to incorrect comparison on 64-bit architectures for inode numbers
greater than INT_MAX.

This bug was found by strace test suite.

Fixes: 5d3cae8bc39d ("unix_diag: Dumping exact socket core")
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/unix/diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 86fa0f3b2caf..27dd3dcb7739 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -219,7 +219,7 @@ done:
 	return skb->len;
 }
 
-static struct sock *unix_lookup_by_ino(int ino)
+static struct sock *unix_lookup_by_ino(unsigned int ino)
 {
 	int i;
 	struct sock *sk;

[PATCH 3.16.y-ckt 058/142] af_iucv: Validate socket address length in iucv_sock_bind()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Ursula Braun <ursula.braun@de.ibm.com>

commit 52a82e23b9f2a9e1d429c5207f8575784290d008 upstream.

Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Evgeny Cherkashin <Eugene.Crosser@ru.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/iucv/af_iucv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 7a95fa4a3de1..f521848e26c7 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -709,6 +709,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 	if (!addr || addr->sa_family != AF_IUCV)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_iucv))
+		return -EINVAL;
+
 	lock_sock(sk);
 	if (sk->sk_state != IUCV_OPEN) {
 		err = -EBADFD;

[PATCH 3.16.y-ckt 059/142] net: dp83640: Fix tx timestamp overflow handling.

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Manfred Rudigier <Manfred.Rudigier@omicron.at>

commit 81e8f2e930fe76b9814c71b9d87c30760b5eb705 upstream.

PHY status frames are not reliable, the PHY may not be able to send them
during heavy receive traffic. This overflow condition is signaled by the
PHY in the next status frame, but the driver did not make use of it.
Instead it always reported wrong tx timestamps to user space after an
overflow happened because it assigned newly received tx timestamps to old
packets in the queue.

This commit fixes this issue by clearing the tx timestamp queue every time
an overflow happens, so that no timestamps are delivered for overflow
packets. This way time stamping will continue correctly after an overflow.

Signed-off-by: Manfred Rudigier <manfred.rudigier@omicron.at>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/phy/dp83640.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index a6fd0d8f4128..4c8eb5721d4d 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -759,6 +759,11 @@ static void decode_rxts(struct dp83640_private *dp83640,
 {
 	struct rxts *rxts;
 	unsigned long flags;
+	u8 overflow;
+
+	overflow = (phy_rxts->ns_hi >> 14) & 0x3;
+	if (overflow)
+		pr_debug("rx timestamp queue overflow, count %d\n", overflow);
 
 	spin_lock_irqsave(&dp83640->rx_lock, flags);
 
@@ -782,6 +787,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct sk_buff *skb;
 	u64 ns;
+	u8 overflow;
 
 	/* We must already have the skb that triggered this. */
 
@@ -791,6 +797,17 @@ static void decode_txts(struct dp83640_private *dp83640,
 		pr_debug("have timestamp but tx_queue empty\n");
 		return;
 	}
+
+	overflow = (phy_txts->ns_hi >> 14) & 0x3;
+	if (overflow) {
+		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
+		while (skb) {
+			skb_complete_tx_timestamp(skb, NULL);
+			skb = skb_dequeue(&dp83640->tx_queue);
+		}
+		return;
+	}
+
 	ns = phy2txts(phy_txts);
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 	shhwtstamps.hwtstamp = ns_to_ktime(ns);

[PATCH 3.16.y-ckt 060/142] tcp: fix NULL deref in tcp_v4_send_ack()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eric Dumazet <edumazet@google.com>

commit e62a123b8ef7c5dc4db2c16383d506860ad21b47 upstream.

Neal reported crashes with this stack trace :

 RIP: 0010:[<ffffffff8c57231b>] tcp_v4_send_ack+0x41/0x20f
...
 CR2: 0000000000000018 CR3: 000000044005c000 CR4: 00000000001427e0
...
  [<ffffffff8c57258e>] tcp_v4_reqsk_send_ack+0xa5/0xb4
  [<ffffffff8c1a7caa>] tcp_check_req+0x2ea/0x3e0
  [<ffffffff8c19e420>] tcp_rcv_state_process+0x850/0x2500
  [<ffffffff8c1a6d21>] tcp_v4_do_rcv+0x141/0x330
  [<ffffffff8c56cdb2>] sk_backlog_rcv+0x21/0x30
  [<ffffffff8c098bbd>] tcp_recvmsg+0x75d/0xf90
  [<ffffffff8c0a8700>] inet_recvmsg+0x80/0xa0
  [<ffffffff8c17623e>] sock_aio_read+0xee/0x110
  [<ffffffff8c066fcf>] do_sync_read+0x6f/0xa0
  [<ffffffff8c0673a1>] SyS_read+0x1e1/0x290
  [<ffffffff8c5ca262>] system_call_fastpath+0x16/0x1b

The problem here is the skb we provide to tcp_v4_send_ack() had to
be parked in the backlog of a new TCP fastopen child because this child
was owned by the user at the time an out of window packet arrived.

Before queuing a packet, TCP has to set skb->dev to NULL as the device
could disappear before packet is removed from the queue.

Fix this issue by using the net pointer provided by the socket (being a
timewait or a request socket).

IPv6 is immune to the bug : tcp_v6_send_response() already gets the net
pointer from the socket if provided.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/tcp_ipv4.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0fd3c84ffaf8..6b4c3e3639bf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -704,7 +704,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -719,7 +720,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -780,7 +780,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sock_net(sk), skb,
+			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
@@ -799,8 +800,10 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
-			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+					     tcp_sk(sk)->snd_nxt;
+
+	tcp_v4_send_ack(sock_net(sk), skb, seq,
 			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
 			tcp_time_stamp,
 			req->ts_recent,

[PATCH 3.16.y-ckt 061/142] ipv6/udp: use sticky pktinfo egress ifindex on connect()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Paolo Abeni <pabeni@redhat.com>

commit 1cdda91871470f15e79375991bd2eddc6e86ddb1 upstream.

Currently, the egress interface index specified via IPV6_PKTINFO
is ignored by __ip6_datagram_connect(), so that RFC 3542 section 6.7
can be subverted when the user space application calls connect()
before sendmsg().
Fix it by initializing properly flowi6_oif in connect() before
performing the route lookup.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv6/datagram.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index ec4c8be39488..21ef73a35831 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,6 +162,9 @@ ipv4_connected:
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
 
+	if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;
 

[PATCH 3.16.y-ckt 062/142] net/ipv6: add sysctl option accept_ra_min_hop_limit

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Hangbin Liu <liuhangbin@gmail.com>

commit 8013d1d7eafb0589ca766db6b74026f76b7f5cb4 upstream.

Commit 6fd99094de2b ("ipv6: Don't reduce hop limit for an interface")
disabled accept hop limit from RA if it is smaller than the current hop
limit for security stuff. But this behavior kind of break the RFC definition.

RFC 4861, 6.3.4.  Processing Received Router Advertisements
   A Router Advertisement field (e.g., Cur Hop Limit, Reachable Time,
   and Retrans Timer) may contain a value denoting that it is
   unspecified.  In such cases, the parameter should be ignored and the
   host should continue using whatever value it is already using.

   If the received Cur Hop Limit value is non-zero, the host SHOULD set
   its CurHopLimit variable to the received value.

So add sysctl option accept_ra_min_hop_limit to let user choose the minimum
hop limit value they can accept from RA. And set default to 1 to meet RFC
standards.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: YOSHIFUJI Hideaki <hideaki.yoshifuji@miraclelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 Documentation/networking/ip-sysctl.txt |  8 ++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  1 +
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       | 16 +++++++---------
 5 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ab42c95f9985..36aa39eee48f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1210,6 +1210,14 @@ accept_ra_defrtr - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_min_hop_limit - INTEGER
+	Minimum hop limit Information in Router Advertisement.
+
+	Hop limit Information in Router Advertisement less than this
+	variable shall be ignored.
+
+	Default: 1
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f3d5d11b8871..9cc2240d7e52 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,6 +29,7 @@ struct ipv6_devconf {
 	__s32		max_desync_factor;
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
+	__s32		accept_ra_min_hop_limit;
 	__s32		accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	__s32		accept_ra_rtr_pref;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 593b0e32d956..f1d321427905 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -163,6 +163,7 @@ enum {
 	DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_SUPPRESS_FRAG_NDISC,
+	DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 75630e173adf..405575f9ae77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -186,6 +186,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -222,6 +223,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -4294,6 +4296,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
 	array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
 	array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+	array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit;
 	array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -5079,6 +5082,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_min_hop_limit",
+			.data		= &ipv6_devconf.accept_ra_min_hop_limit,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "accept_ra_pinfo",
 			.data		= &ipv6_devconf.accept_ra_pinfo,
 			.maxlen		= sizeof(int),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e2eb53c719dc..577338204863 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1189,18 +1189,16 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
-	if (ra_msg->icmph.icmp6_hop_limit) {
-		/* Only set hop_limit on the interface if it is higher than
-		 * the current hop_limit.
-		 */
-		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+	if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+	    ra_msg->icmph.icmp6_hop_limit) {
+		if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
 			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+			if (rt)
+				dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
+					       ra_msg->icmph.icmp6_hop_limit);
 		} else {
-			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
 		}
-		if (rt)
-			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
-				       ra_msg->icmph.icmp6_hop_limit);
 	}
 
 skip_defrtr:

[PATCH 3.16.y-ckt 063/142] net:Add sysctl_max_skb_frags

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>

commit 5f74f82ea34c0da80ea0b49192bb5ea06e063593 upstream.

Devices may have limits on the number of fragments in an skb they support.
Current codebase uses a constant as maximum for number of fragments one
skb can hold and use.
When enabling scatter/gather and running traffic with many small messages
the codebase uses the maximum number of fragments and may thereby violate
the max for certain devices.
The patch introduces a global variable as max number of fragments.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/skbuff.h     |  1 +
 net/core/skbuff.c          |  2 ++
 net/core/sysctl_net_core.c | 10 ++++++++++
 net/ipv4/tcp.c             |  4 ++--
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 010bc80be91c..c046cb92172e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -169,6 +169,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7e31a99e0ed9..8c5409067930 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -77,6 +77,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index e731c96eac4b..cd386d2fd039 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -27,6 +27,7 @@ static int one = 1;
 static int ushort_max = USHRT_MAX;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
@@ -363,6 +364,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9c4f0d2f2892..9ee5a4bbb289 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -929,7 +929,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1213,7 +1213,7 @@ new_segment:
 
 				if (!skb_can_coalesce(skb, i, pfrag->page,
 						      pfrag->offset)) {
-					if (i == MAX_SKB_FRAGS || !sg) {
+					if (i == sysctl_max_skb_frags || !sg) {
 						tcp_mark_push(tp, skb);
 						goto new_segment;
 					}

[PATCH 3.16.y-ckt 064/142] tg3: Fix for tg3 transmit queue 0 timed out when too many gso_segs

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Siva Reddy Kallam <siva.kallam@broadcom.com>

commit b7d987295c74500b733a0ba07f9a9bcc4074fa83 upstream.

tg3_tso_bug() can hit a condition where the entire tx ring is not big
enough to segment the GSO packet. For example, if MSS is very small,
gso_segs can exceed the tx ring size. When we hit the condition, it
will cause tx timeout.

tg3_tso_bug() is called to handle TSO and DMA hardware bugs.
For TSO bugs, if tg3_tso_bug() cannot succeed, we have to drop the packet.
For DMA bugs, we can still fall back to linearize the SKB and let the
hardware transmit the TSO packet.

This patch adds a function tg3_tso_bug_gso_check() to check if there
are enough tx descriptors for GSO before calling tg3_tso_bug().
The caller will then handle the error appropriately - drop or
lineraize the SKB.

v2: Corrected patch description to avoid confusion.

Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Acked-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/broadcom/tg3.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 24d42c6d0c66..c13932e671fb 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7829,6 +7829,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7932,14 +7940,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8071,7 +8084,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */

[PATCH 3.16.y-ckt 065/142] ipv4: fix memory leaks in ip_cmsg_send() callers

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eric Dumazet <edumazet@google.com>

commit 919483096bfe75dda338e98d56da91a263746a0a upstream.

Dmitry reported memory leaks of IP options allocated in
ip_cmsg_send() when/if this function returns an error.

Callers are responsible for the freeing.

Many thanks to Dmitry for the report and diagnostic.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/ip_sockglue.c | 2 ++
 net/ipv4/ping.c        | 4 +++-
 net/ipv4/raw.c         | 4 +++-
 net/ipv4/udp.c         | 4 +++-
 4 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7aa584c36c15..c7ec866adac9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -216,6 +216,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 30d0a64be413..9c68e94cd66d 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -748,8 +748,10 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2c65160565e1..29ad1c63e2ea 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -525,8 +525,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2478b20692e8..716475fc884b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -972,8 +972,10 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;

[PATCH 3.16.y-ckt 066/142] qmi_wwan: add "4G LTE usb-modem U901"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>

commit aac8d3c282e024c344c5b86dc1eab7af88bb9716 upstream.

Thomas reports:

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=05c6 ProdID=6001 Rev=00.00
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=1234567890ABCDEF
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index c745fd79eb9e..ab0a4f32a46c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -542,6 +542,7 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x6001, 3)},	/* 4G LTE usb-modem U901 */
 	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
 	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},

[PATCH 3.16.y-ckt 067/142] pppoe: fix reference counting in PPPoE proxy

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Guillaume Nault <g.nault@alphalink.fr>

commit 29e73269aa4d36f92b35610c25f8b01c789b0dc8 upstream.

Drop reference on the relay_po socket when __pppoe_xmit() succeeds.
This is already handled correctly in the error path.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ppp/pppoe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa563136373..afac3cdac44b 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -392,6 +392,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
 
 		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
 			goto abort_put;
+
+		sock_put(sk_pppox(relay_po));
 	} else {
 		if (sock_queue_rcv_skb(sk, skb))
 			goto abort_kfree;

[PATCH 3.16.y-ckt 068/142] route: check and remove route cache when we get route

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Xin Long <lucien.xin@gmail.com>

commit deed49df7390d5239024199e249190328f1651e7 upstream.

Since the gc of ipv4 route was removed, the route cached would has
no chance to be removed, and even it has been timeout, it still could
be used, cause no code to check it's expires.

Fix this issue by checking  and removing route cache when we get route.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/net/ip_fib.h |  1 +
 net/ipv4/route.c     | 77 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 64 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 699c4046a8cb..fac652dc6852 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -59,6 +59,7 @@ struct fib_nh_exception {
 	struct rtable __rcu		*fnhe_rth_input;
 	struct rtable __rcu		*fnhe_rth_output;
 	unsigned long			fnhe_stamp;
+	struct rcu_head			rcu;
 };
 
 struct fnhe_hash_bucket {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d53aee9cbfe2..5df7ed8c62d9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -125,6 +125,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -754,7 +755,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1526,6 +1527,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1580,11 +1611,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe != NULL)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -1935,19 +1975,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2494,7 +2544,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;

[PATCH 3.16.y-ckt 069/142] rtnl: RTM_GETNETCONF: fix wrong return value

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Anton Protopopov <a.s.protopopov@gmail.com>

commit a97eb33ff225f34a8124774b3373fd244f0e83ce upstream.

An error response from a RTM_GETNETCONF request can return the positive
error value EINVAL in the struct nlmsgerr that can mislead userspace.

Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/devinet.c  | 2 +-
 net/ipv6/addrconf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e9449376b58e..aa4b9990dd7a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1798,7 +1798,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 405575f9ae77..c844b31c767e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -535,7 +535,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 

[PATCH 3.16.y-ckt 070/142] sctp: Fix port hash table size computation

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Neil Horman <nhorman@tuxdriver.com>

commit d9749fb5942f51555dc9ce1ac0dbb1806960a975 upstream.

Dmitry Vyukov noted recently that the sctp_port_hashtable had an error in
its size computation, observing that the current method never guaranteed
that the hashsize (measured in number of entries) would be a power of two,
which the input hash function for that table requires.  The root cause of
the problem is that two values need to be computed (one, the allocation
order of the storage requries, as passed to __get_free_pages, and two the
number of entries for the hash table).  Both need to be ^2, but for
different reasons, and the existing code is simply computing one order
value, and using it as the basis for both, which is wrong (i.e. it assumes
that ((1<<order)*PAGE_SIZE)/sizeof(bucket) is still ^2 when its not).

To fix this, we change the logic slightly.  We start by computing a goal
allocation order (which is limited by the maximum size hash table we want
to support.  Then we attempt to allocate that size table, decreasing the
order until a successful allocation is made.  Then, with the resultant
successful order we compute the number of buckets that hash table supports,
which we then round down to the nearest power of two, giving us the number
of entries the table actually supports.

I've tested this locally here, using non-debug and spinlock-debug kernels,
and the number of entries in the hashtable consistently work out to be
powers of two in all cases.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
CC: Dmitry Vyukov <dvyukov@google.com>
CC: Vladislav Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/sctp/protocol.c | 47 ++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 38 insertions(+), 9 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e30c2091a4e1..c143f74a25b9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -60,6 +60,8 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 
+#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
+
 /* Global data structures. */
 struct sctp_globals sctp_globals __read_mostly;
 
@@ -1332,6 +1334,8 @@ static __init int sctp_init(void)
 	unsigned long limit;
 	int max_share;
 	int order;
+	int num_entries;
+	int max_entry_order;
 
 	BUILD_BUG_ON(sizeof(struct sctp_ulpevent) >
 		     sizeof(((struct sk_buff *) 0)->cb));
@@ -1385,14 +1389,24 @@ static __init int sctp_init(void)
 
 	/* Size and allocate the association hash table.
 	 * The methodology is similar to that of the tcp hash tables.
+	 * Though not identical.  Start by getting a goal size
 	 */
 	if (totalram_pages >= (128 * 1024))
 		goal = totalram_pages >> (22 - PAGE_SHIFT);
 	else
 		goal = totalram_pages >> (24 - PAGE_SHIFT);
 
-	for (order = 0; (1UL << order) < goal; order++)
-		;
+	/* Then compute the page order for said goal */
+	order = get_order(goal);
+
+	/* Now compute the required page order for the maximum sized table we
+	 * want to create
+	 */
+	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
+				    sizeof(struct sctp_bind_hashbucket));
+
+	/* Limit the page order by that maximum hash table size */
+	order = min(order, max_entry_order);
 
 	do {
 		sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE /
@@ -1426,27 +1440,42 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
 	}
 
-	/* Allocate and initialize the SCTP port hash table.  */
+	/* Allocate and initialize the SCTP port hash table.
+	 * Note that order is initalized to start at the max sized
+	 * table we want to support.  If we can't get that many pages
+	 * reduce the order and try again
+	 */
 	do {
-		sctp_port_hashsize = (1UL << order) * PAGE_SIZE /
-					sizeof(struct sctp_bind_hashbucket);
-		if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
-			continue;
 		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
 			__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order);
 	} while (!sctp_port_hashtable && --order > 0);
+
 	if (!sctp_port_hashtable) {
 		pr_err("Failed bind hash alloc\n");
 		status = -ENOMEM;
 		goto err_bhash_alloc;
 	}
+
+	/* Now compute the number of entries that will fit in the
+	 * port hash space we allocated
+	 */
+	num_entries = (1UL << order) * PAGE_SIZE /
+		      sizeof(struct sctp_bind_hashbucket);
+
+	/* And finish by rounding it down to the nearest power of two
+	 * this wastes some memory of course, but its needed because
+	 * the hash function operates based on the assumption that
+	 * that the number of entries is a power of two
+	 */
+	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
+
 	for (i = 0; i < sctp_port_hashsize; i++) {
 		spin_lock_init(&sctp_port_hashtable[i].lock);
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
 	}
 
-	pr_info("Hash tables configured (established %d bind %d)\n",
-		sctp_assoc_hashsize, sctp_port_hashsize);
+	pr_info("Hash tables configured (established %d bind %d/%d)\n",
+		sctp_assoc_hashsize, sctp_port_hashsize, num_entries);
 
 	sctp_sysctl_register();
 

[PATCH 3.16.y-ckt 071/142] target: Fix LUN_RESET active TMR descriptor handling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit a6d9bb1c9605cd4f44e2d8290dc4d0e88f20292d upstream.

This patch fixes a NULL pointer se_cmd->cmd_kref < 0
refcount bug during TMR LUN_RESET with active TMRs,
triggered during se_cmd + se_tmr_req descriptor
shutdown + release via core_tmr_drain_tmr_list().

To address this bug, go ahead and obtain a local
kref_get_unless_zero(&se_cmd->cmd_kref) for active I/O
to set CMD_T_ABORTED, and transport_wait_for_tasks()
followed by the final target_put_sess_cmd() to drop
the local ->cmd_kref.

Also add two new checks within target_tmr_work() to
avoid CMD_T_ABORTED -> TFO->queue_tm_rsp() callbacks
ahead of invoking the backend -> fabric put in
transport_cmd_check_stop_to_fabric().

For good measure, also change core_tmr_release_req()
to use list_del_init() ahead of se_tmr_req memory
free.

Reviewed-by: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
[ luis: backported to 3.16: used Nicholas' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_tmr.c       | 22 +++++++++++++++++++++-
 drivers/target/target_core_transport.c | 17 +++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index f7cd95e8111a..1b74be036149 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -76,7 +76,7 @@ void core_tmr_release_req(
 	}
 
 	spin_lock_irqsave(&dev->se_tmr_lock, flags);
-	list_del(&tmr->tmr_list);
+	list_del_init(&tmr->tmr_list);
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
 
 	kfree(tmr);
@@ -181,9 +181,11 @@ static void core_tmr_drain_tmr_list(
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_tmr_list);
+	struct se_session *sess;
 	struct se_tmr_req *tmr_p, *tmr_pp;
 	struct se_cmd *cmd;
 	unsigned long flags;
+	bool rc;
 	/*
 	 * Release all pending and outgoing TMRs aside from the received
 	 * LUN_RESET tmr..
@@ -209,17 +211,31 @@ static void core_tmr_drain_tmr_list(
 		if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd))
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
 		spin_lock(&cmd->t_state_lock);
 		if (!(cmd->transport_state & CMD_T_ACTIVE)) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
 		if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&cmd->t_state_lock);
 
+		rc = kref_get_unless_zero(&cmd->cmd_kref);
+		spin_unlock(&sess->sess_cmd_lock);
+		if (!rc) {
+			printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n");
+			continue;
+		}
 		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
 	}
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
@@ -233,7 +249,11 @@ static void core_tmr_drain_tmr_list(
 			(preempt_and_abort_list) ? "Preempt" : "", tmr_p,
 			tmr_p->function, tmr_p->response, cmd->t_state);
 
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
+
 		transport_cmd_finish_abort(cmd, 1);
+		target_put_sess_cmd(cmd->se_sess, cmd);
 	}
 }
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9eeeb78bf604..4e0b86685369 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2951,8 +2951,17 @@ static void target_tmr_work(struct work_struct *work)
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
 	struct se_device *dev = cmd->se_dev;
 	struct se_tmr_req *tmr = cmd->se_tmr_req;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		tmr->response = TMR_FUNCTION_REJECTED;
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	switch (tmr->function) {
 	case TMR_ABORT_TASK:
 		core_tmr_abort_task(dev, tmr, cmd->se_sess);
@@ -2980,9 +2989,17 @@ static void target_tmr_work(struct work_struct *work)
 		break;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
 	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+check_stop:
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 

[PATCH 3.16.y-ckt 072/142] target: Fix LUN_RESET active I/O handling for ACK_KREF

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit febe562c20dfa8f33bee7d419c6b517986a5aa33 upstream.

This patch fixes a NULL pointer se_cmd->cmd_kref < 0
refcount bug during TMR LUN_RESET with active se_cmd
I/O, that can be triggered during se_cmd descriptor
shutdown + release via core_tmr_drain_state_list() code.

To address this bug, add common __target_check_io_state()
helper for ABORT_TASK + LUN_RESET w/ CMD_T_COMPLETE
checking, and set CMD_T_ABORTED + obtain ->cmd_kref for
both cases ahead of last target_put_sess_cmd() after
TFO->aborted_task() -> transport_cmd_finish_abort()
callback has completed.

It also introduces SCF_ACK_KREF to determine when
transport_cmd_finish_abort() needs to drop the second
extra reference, ahead of calling target_put_sess_cmd()
for the final kref_put(&se_cmd->cmd_kref).

It also updates transport_cmd_check_stop() to avoid
holding se_cmd->t_state_lock while dropping se_cmd
device state via target_remove_from_state_list(), now
that core_tmr_drain_state_list() is holding the
se_device lock while checking se_cmd state from
within TMR logic.

Finally, move transport_put_cmd() release of SGL +
TMR + extended CDB memory into target_free_cmd_mem()
in order to avoid potential resource leaks in TMR
ABORT_TASK + LUN_RESET code-paths.  Also update
target_release_cmd_kref() accordingly.

Reviewed-by: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
[ luis: backported to 3.16: used Nicholas' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_tmr.c       | 64 +++++++++++++++++++++++---------
 drivers/target/target_core_transport.c | 67 +++++++++++++++-------------------
 2 files changed, 76 insertions(+), 55 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 1b74be036149..224b1942aabe 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -115,6 +115,34 @@ static int target_check_cdb_and_preempt(struct list_head *list,
 	return 1;
 }
 
+static bool __target_check_io_state(struct se_cmd *se_cmd)
+{
+	struct se_session *sess = se_cmd->se_sess;
+
+	assert_spin_locked(&sess->sess_cmd_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+	/*
+	 * If command already reached CMD_T_COMPLETE state within
+	 * target_complete_cmd(), this se_cmd has been passed to
+	 * fabric driver and will not be aborted.
+	 *
+	 * Otherwise, obtain a local se_cmd->cmd_kref now for TMR
+	 * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as
+	 * long as se_cmd->cmd_kref is still active unless zero.
+	 */
+	spin_lock(&se_cmd->t_state_lock);
+	if (se_cmd->transport_state & CMD_T_COMPLETE) {
+		pr_debug("Attempted to abort io tag: %u already complete,"
+			" skipping\n", se_cmd->se_tfo->get_task_tag(se_cmd));
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	se_cmd->transport_state |= CMD_T_ABORTED;
+	spin_unlock(&se_cmd->t_state_lock);
+
+	return kref_get_unless_zero(&se_cmd->cmd_kref);
+}
+
 void core_tmr_abort_task(
 	struct se_device *dev,
 	struct se_tmr_req *tmr,
@@ -142,25 +170,20 @@ void core_tmr_abort_task(
 		printk("ABORT_TASK: Found referenced %s task_tag: %u\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		spin_lock(&se_cmd->t_state_lock);
-		if (se_cmd->transport_state & CMD_T_COMPLETE) {
-			printk("ABORT_TASK: ref_tag: %u already complete, skipping\n", ref_tag);
-			spin_unlock(&se_cmd->t_state_lock);
+		if (!__target_check_io_state(se_cmd)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+			target_put_sess_cmd(se_sess, se_cmd);
 			goto out;
 		}
-		se_cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock(&se_cmd->t_state_lock);
 
 		list_del_init(&se_cmd->se_cmd_list);
-		kref_get(&se_cmd->cmd_kref);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		target_put_sess_cmd(se_sess, se_cmd);
 		transport_cmd_finish_abort(se_cmd, true);
+		target_put_sess_cmd(se_sess, se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %d\n", ref_tag);
@@ -265,8 +288,10 @@ static void core_tmr_drain_state_list(
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_task_list);
+	struct se_session *sess;
 	struct se_cmd *cmd, *next;
 	unsigned long flags;
+	int rc;
 
 	/*
 	 * Complete outstanding commands with TASK_ABORTED SAM status.
@@ -305,6 +330,16 @@ static void core_tmr_drain_state_list(
 		if (prout_cmd == cmd)
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
+		rc = __target_check_io_state(cmd);
+		spin_unlock(&sess->sess_cmd_lock);
+		if (!rc)
+			continue;
+
 		list_move_tail(&cmd->state_list, &drain_task_list);
 		cmd->state_active = false;
 	}
@@ -312,7 +347,7 @@ static void core_tmr_drain_state_list(
 
 	while (!list_empty(&drain_task_list)) {
 		cmd = list_entry(drain_task_list.next, struct se_cmd, state_list);
-		list_del(&cmd->state_list);
+		list_del_init(&cmd->state_list);
 
 		pr_debug("LUN_RESET: %s cmd: %p"
 			" ITT/CmdSN: 0x%08x/0x%08x, i_state: %d, t_state: %d"
@@ -336,16 +371,11 @@ static void core_tmr_drain_state_list(
 		 * loop above, but we do it down here given that
 		 * cancel_work_sync may block.
 		 */
-		if (cmd->t_state == TRANSPORT_COMPLETE)
-			cancel_work_sync(&cmd->work);
-
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
-		target_stop_cmd(cmd, &flags);
-
-		cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
 
 		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas);
+		target_put_sess_cmd(cmd->se_sess, cmd);
 	}
 }
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 4e0b86685369..600171f50d28 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -511,9 +511,6 @@ void transport_deregister_session(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
-/*
- * Called with cmd->t_state_lock held.
- */
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -538,10 +535,6 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (write_pending)
-		cmd->t_state = TRANSPORT_WRITE_PENDING;
-
 	if (remove_from_lists) {
 		target_remove_from_state_list(cmd);
 
@@ -551,6 +544,10 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 		cmd->se_lun = NULL;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (write_pending)
+		cmd->t_state = TRANSPORT_WRITE_PENDING;
+
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
@@ -605,6 +602,8 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
+	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
@@ -616,7 +615,7 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return;
-	if (remove)
+	if (remove && ack_kref)
 		transport_put_cmd(cmd);
 }
 
@@ -684,7 +683,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
 	 */
-	if (cmd->transport_state & CMD_T_ABORTED &&
+	if (cmd->transport_state & CMD_T_ABORTED ||
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		complete_all(&cmd->t_transport_stop_comp);
@@ -2133,20 +2132,14 @@ static inline void transport_free_pages(struct se_cmd *cmd)
 }
 
 /**
- * transport_release_cmd - free a command
- * @cmd:       command to free
+ * transport_put_cmd - release a reference to a command
+ * @cmd:       command to release
  *
- * This routine unconditionally frees a command, and reference counting
- * or list removal must be done in the caller.
+ * This routine releases our reference to the command and frees it if possible.
  */
-static int transport_release_cmd(struct se_cmd *cmd)
+static int transport_put_cmd(struct se_cmd *cmd)
 {
 	BUG_ON(!cmd->se_tfo);
-
-	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
-		core_tmr_release_req(cmd->se_tmr_req);
-	if (cmd->t_task_cdb != cmd->__t_task_cdb)
-		kfree(cmd->t_task_cdb);
 	/*
 	 * If this cmd has been setup with target_get_sess_cmd(), drop
 	 * the kref and call ->release_cmd() in kref callback.
@@ -2154,18 +2147,6 @@ static int transport_release_cmd(struct se_cmd *cmd)
 	return target_put_sess_cmd(cmd->se_sess, cmd);
 }
 
-/**
- * transport_put_cmd - release a reference to a command
- * @cmd:       command to release
- *
- * This routine releases our reference to the command and frees it if possible.
- */
-static int transport_put_cmd(struct se_cmd *cmd)
-{
-	transport_free_pages(cmd);
-	return transport_release_cmd(cmd);
-}
-
 void *transport_kmap_data_sg(struct se_cmd *cmd)
 {
 	struct scatterlist *sg = cmd->t_data_sg;
@@ -2363,14 +2344,13 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
 
 int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 {
-	unsigned long flags;
 	int ret = 0;
 
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			 transport_wait_for_tasks(cmd);
+			transport_wait_for_tasks(cmd);
 
-		ret = transport_release_cmd(cmd);
+		ret = transport_put_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
 			transport_wait_for_tasks(cmd);
@@ -2379,11 +2359,8 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 		 * has already added se_cmd to state_list, but fabric has
 		 * failed command before I/O submission.
 		 */
-		if (cmd->state_active) {
-			spin_lock_irqsave(&cmd->t_state_lock, flags);
+		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		}
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
@@ -2431,6 +2408,16 @@ out:
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
 
+static void target_free_cmd_mem(struct se_cmd *cmd)
+{
+	transport_free_pages(cmd);
+
+	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		core_tmr_release_req(cmd->se_tmr_req);
+	if (cmd->t_task_cdb != cmd->__t_task_cdb)
+		kfree(cmd->t_task_cdb);
+}
+
 static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
@@ -2438,17 +2425,20 @@ static void target_release_cmd_kref(struct kref *kref)
 
 	if (list_empty(&se_cmd->se_cmd_list)) {
 		spin_unlock(&se_sess->sess_cmd_lock);
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
 	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
 		spin_unlock(&se_sess->sess_cmd_lock);
+		target_free_cmd_mem(se_cmd);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
 	list_del(&se_cmd->se_cmd_list);
 	spin_unlock(&se_sess->sess_cmd_lock);
 
+	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
 
@@ -2459,6 +2449,7 @@ static void target_release_cmd_kref(struct kref *kref)
 int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd)
 {
 	if (!se_sess) {
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
 	}

[PATCH 3.16.y-ckt 073/142] target: Fix TAS handling for multi-session se_node_acls

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit ebde1ca5a908b10312db4ecd7553e3ba039319ab upstream.

This patch fixes a bug in TMR task aborted status (TAS)
handling when multiple sessions are connected to the
same target WWPN endpoint and se_node_acl descriptor,
resulting in TASK_ABORTED status to not be generated
for aborted se_cmds on the remote port.

This is due to core_tmr_handle_tas_abort() incorrectly
comparing se_node_acl instead of se_session, for which
the multi-session case is expected to be sharing the
same se_node_acl.

Instead, go ahead and update core_tmr_handle_tas_abort()
to compare tmr_sess + cmd->se_sess in order to determine
if the LUN_RESET was received on a different I_T nexus,
and TASK_ABORTED status response needs to be generated.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
[ luis: backported to 3.16: used Nicholas' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_tmr.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 224b1942aabe..f6f0a898ecfb 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -83,7 +83,7 @@ void core_tmr_release_req(
 }
 
 static void core_tmr_handle_tas_abort(
-	struct se_node_acl *tmr_nacl,
+	struct se_session *tmr_sess,
 	struct se_cmd *cmd,
 	int tas)
 {
@@ -91,8 +91,7 @@ static void core_tmr_handle_tas_abort(
 	/*
 	 * TASK ABORTED status (TAS) bit support
 	*/
-	if ((tmr_nacl &&
-	     (tmr_nacl != cmd->se_sess->se_node_acl)) && tas) {
+	if (tmr_sess && tmr_sess != cmd->se_sess && tas) {
 		remove = false;
 		transport_send_task_abort(cmd);
 	}
@@ -283,7 +282,7 @@ static void core_tmr_drain_tmr_list(
 static void core_tmr_drain_state_list(
 	struct se_device *dev,
 	struct se_cmd *prout_cmd,
-	struct se_node_acl *tmr_nacl,
+	struct se_session *tmr_sess,
 	int tas,
 	struct list_head *preempt_and_abort_list)
 {
@@ -374,7 +373,7 @@ static void core_tmr_drain_state_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas);
+		core_tmr_handle_tas_abort(tmr_sess, cmd, tas);
 		target_put_sess_cmd(cmd->se_sess, cmd);
 	}
 }
@@ -387,6 +386,7 @@ int core_tmr_lun_reset(
 {
 	struct se_node_acl *tmr_nacl = NULL;
 	struct se_portal_group *tmr_tpg = NULL;
+	struct se_session *tmr_sess = NULL;
 	int tas;
         /*
 	 * TASK_ABORTED status bit, this is configurable via ConfigFS
@@ -405,8 +405,9 @@ int core_tmr_lun_reset(
 	 * or struct se_device passthrough..
 	 */
 	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
-		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
-		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
+		tmr_sess = tmr->task_cmd->se_sess;
+		tmr_nacl = tmr_sess->se_node_acl;
+		tmr_tpg = tmr_sess->se_tpg;
 		if (tmr_nacl && tmr_tpg) {
 			pr_debug("LUN_RESET: TMR caller fabric: %s"
 				" initiator port %s\n",
@@ -419,7 +420,7 @@ int core_tmr_lun_reset(
 		dev->transport->name, tas);
 
 	core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list);
-	core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas,
+	core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas,
 				preempt_and_abort_list);
 
 	/*

[PATCH 3.16.y-ckt 074/142] target: Fix remote-port TMR ABORT + se_cmd fabric stop

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 0f4a943168f31d29a1701908931acaba518b131a upstream.

To address the bug where fabric driver level shutdown
of se_cmd occurs at the same time when TMR CMD_T_ABORTED
is happening resulting in a -1 ->cmd_kref, this patch
adds a CMD_T_FABRIC_STOP bit that is used to determine
when TMR + driver I_T nexus shutdown is happening
concurrently.

It changes target_sess_cmd_list_set_waiting() to obtain
se_cmd->cmd_kref + set CMD_T_FABRIC_STOP, and drop local
reference in target_wait_for_sess_cmds() and invoke extra
target_put_sess_cmd() during Task Aborted Status (TAS)
when necessary.

Also, it adds a new target_wait_free_cmd() wrapper around
transport_wait_for_tasks() for the special case within
transport_generic_free_cmd() to set CMD_T_FABRIC_STOP,
and is now aware of CMD_T_ABORTED + CMD_T_TAS status
bits to know when an extra transport_put_cmd() during
TAS is required.

Note transport_generic_free_cmd() is expected to block on
cmd->cmd_wait_comp in order to follow what iscsi-target
expects during iscsi_conn context se_cmd shutdown.

Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@daterainc.com>
[ luis: backported to 3.16: used Nicholas' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_tmr.c       |  57 ++++++++++----
 drivers/target/target_core_transport.c | 137 +++++++++++++++++++++++++--------
 include/target/target_core_base.h      |   2 +
 3 files changed, 148 insertions(+), 48 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index f6f0a898ecfb..ebdbaaf6111d 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -82,16 +82,18 @@ void core_tmr_release_req(
 	kfree(tmr);
 }
 
-static void core_tmr_handle_tas_abort(
-	struct se_session *tmr_sess,
-	struct se_cmd *cmd,
-	int tas)
+static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
-	bool remove = true;
+	unsigned long flags;
+	bool remove = true, send_tas;
 	/*
 	 * TASK ABORTED status (TAS) bit support
-	*/
-	if (tmr_sess && tmr_sess != cmd->se_sess && tas) {
+	 */
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	send_tas = (cmd->transport_state & CMD_T_TAS);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
+	if (send_tas) {
 		remove = false;
 		transport_send_task_abort(cmd);
 	}
@@ -114,7 +116,8 @@ static int target_check_cdb_and_preempt(struct list_head *list,
 	return 1;
 }
 
-static bool __target_check_io_state(struct se_cmd *se_cmd)
+static bool __target_check_io_state(struct se_cmd *se_cmd,
+				    struct se_session *tmr_sess, int tas)
 {
 	struct se_session *sess = se_cmd->se_sess;
 
@@ -122,21 +125,33 @@ static bool __target_check_io_state(struct se_cmd *se_cmd)
 	WARN_ON_ONCE(!irqs_disabled());
 	/*
 	 * If command already reached CMD_T_COMPLETE state within
-	 * target_complete_cmd(), this se_cmd has been passed to
-	 * fabric driver and will not be aborted.
+	 * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
+	 * this se_cmd has been passed to fabric driver and will
+	 * not be aborted.
 	 *
 	 * Otherwise, obtain a local se_cmd->cmd_kref now for TMR
 	 * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as
 	 * long as se_cmd->cmd_kref is still active unless zero.
 	 */
 	spin_lock(&se_cmd->t_state_lock);
-	if (se_cmd->transport_state & CMD_T_COMPLETE) {
-		pr_debug("Attempted to abort io tag: %u already complete,"
+	if (se_cmd->transport_state & (CMD_T_COMPLETE | CMD_T_FABRIC_STOP)) {
+		pr_debug("Attempted to abort io tag: %u already complete or"
+			" fabric stop, skipping\n",
+			se_cmd->se_tfo->get_task_tag(se_cmd));
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+		pr_debug("Attempted to abort io tag: %u already shutdown,"
 			" skipping\n", se_cmd->se_tfo->get_task_tag(se_cmd));
 		spin_unlock(&se_cmd->t_state_lock);
 		return false;
 	}
 	se_cmd->transport_state |= CMD_T_ABORTED;
+
+	if ((tmr_sess != se_cmd->se_sess) && tas)
+		se_cmd->transport_state |= CMD_T_TAS;
+
 	spin_unlock(&se_cmd->t_state_lock);
 
 	return kref_get_unless_zero(&se_cmd->cmd_kref);
@@ -169,7 +184,7 @@ void core_tmr_abort_task(
 		printk("ABORT_TASK: Found referenced %s task_tag: %u\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		if (!__target_check_io_state(se_cmd)) {
+		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 			target_put_sess_cmd(se_sess, se_cmd);
 			goto out;
@@ -239,7 +254,8 @@ static void core_tmr_drain_tmr_list(
 
 		spin_lock(&sess->sess_cmd_lock);
 		spin_lock(&cmd->t_state_lock);
-		if (!(cmd->transport_state & CMD_T_ACTIVE)) {
+		if (!(cmd->transport_state & CMD_T_ACTIVE) ||
+		     (cmd->transport_state & CMD_T_FABRIC_STOP)) {
 			spin_unlock(&cmd->t_state_lock);
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
@@ -249,15 +265,22 @@ static void core_tmr_drain_tmr_list(
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
 		cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&cmd->t_state_lock);
 
 		rc = kref_get_unless_zero(&cmd->cmd_kref);
-		spin_unlock(&sess->sess_cmd_lock);
 		if (!rc) {
 			printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n");
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		spin_unlock(&sess->sess_cmd_lock);
+
 		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
 	}
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
@@ -334,7 +357,7 @@ static void core_tmr_drain_state_list(
 			continue;
 
 		spin_lock(&sess->sess_cmd_lock);
-		rc = __target_check_io_state(cmd);
+		rc = __target_check_io_state(cmd, tmr_sess, tas);
 		spin_unlock(&sess->sess_cmd_lock);
 		if (!rc)
 			continue;
@@ -373,7 +396,7 @@ static void core_tmr_drain_state_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		core_tmr_handle_tas_abort(tmr_sess, cmd, tas);
+		core_tmr_handle_tas_abort(cmd, tas);
 		target_put_sess_cmd(cmd->se_sess, cmd);
 	}
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 600171f50d28..3128b718ff73 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2342,18 +2342,33 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
 	}
 }
 
+static bool
+__transport_wait_for_tasks(struct se_cmd *, bool, bool *, bool *,
+			   unsigned long *flags);
+
+static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	__transport_wait_for_tasks(cmd, true, aborted, tas, &flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+}
+
 int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 {
 	int ret = 0;
+	bool aborted = false, tas = false;
 
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 
-		ret = transport_put_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
-			transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
@@ -2365,7 +2380,21 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
 
-		ret = transport_put_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
+	}
+	/*
+	 * If the task has been internally aborted due to TMR ABORT_TASK
+	 * or LUN_RESET, target_core_tmr.c is responsible for performing
+	 * the remaining calls to target_put_sess_cmd(), and not the
+	 * callers of this function.
+	 */
+	if (aborted) {
+		pr_debug("Detected CMD_T_ABORTED for ITT: %u\n",
+			cmd->se_tfo->get_task_tag(cmd));
+		wait_for_completion(&cmd->cmd_wait_comp);
+		cmd->se_tfo->release_cmd(cmd);
+		ret = 1;
 	}
 	return ret;
 }
@@ -2422,6 +2451,7 @@ static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
+	bool fabric_stop;
 
 	if (list_empty(&se_cmd->se_cmd_list)) {
 		spin_unlock(&se_sess->sess_cmd_lock);
@@ -2429,13 +2459,19 @@ static void target_release_cmd_kref(struct kref *kref)
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
-	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
+
+	spin_lock(&se_cmd->t_state_lock);
+	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP);
+	spin_unlock(&se_cmd->t_state_lock);
+
+	if (se_cmd->cmd_wait_set || fabric_stop) {
+		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock(&se_sess->sess_cmd_lock);
 		target_free_cmd_mem(se_cmd);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
-	list_del(&se_cmd->se_cmd_list);
+	list_del_init(&se_cmd->se_cmd_list);
 	spin_unlock(&se_sess->sess_cmd_lock);
 
 	target_free_cmd_mem(se_cmd);
@@ -2467,6 +2503,7 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd;
 	unsigned long flags;
+	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (se_sess->sess_tearing_down) {
@@ -2476,8 +2513,15 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 	se_sess->sess_tearing_down = 1;
 	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
 
-	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list)
-		se_cmd->cmd_wait_set = 1;
+	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
+		if (rc) {
+			se_cmd->cmd_wait_set = 1;
+			spin_lock(&se_cmd->t_state_lock);
+			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+			spin_unlock(&se_cmd->t_state_lock);
+		}
+	}
 
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
@@ -2490,15 +2534,25 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
+	bool tas;
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del(&se_cmd->se_cmd_list);
+		list_del_init(&se_cmd->se_cmd_list);
 
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));
 
+		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
+		tas = (se_cmd->transport_state & CMD_T_TAS);
+		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
+
+		if (!target_put_sess_cmd(se_sess, se_cmd)) {
+			if (tas)
+				target_put_sess_cmd(se_sess, se_cmd);
+		}
+
 		wait_for_completion(&se_cmd->cmd_wait_comp);
 		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
 			" fabric state: %d\n", se_cmd, se_cmd->t_state,
@@ -2541,34 +2595,38 @@ int transport_clear_lun_ref(struct se_lun *lun)
 	return 0;
 }
 
-/**
- * transport_wait_for_tasks - wait for completion to occur
- * @cmd:	command to wait
- *
- * Called from frontend fabric context to wait for storage engine
- * to pause and/or release frontend generated struct se_cmd.
- */
-bool transport_wait_for_tasks(struct se_cmd *cmd)
+static bool
+__transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
+			   bool *aborted, bool *tas, unsigned long *flags)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
-	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (fabric_stop)
+		cmd->transport_state |= CMD_T_FABRIC_STOP;
+
+	if (cmd->transport_state & CMD_T_ABORTED)
+		*aborted = true;
+
+	if (cmd->transport_state & CMD_T_TAS)
+		*tas = true;
+
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
 	if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
-	if (!(cmd->transport_state & CMD_T_ACTIVE)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	if (!(cmd->transport_state & CMD_T_ACTIVE))
+		return false;
+
+	if (fabric_stop && *aborted)
 		return false;
-	}
 
 	cmd->transport_state |= CMD_T_STOP;
 
@@ -2577,20 +2635,37 @@ bool transport_wait_for_tasks(struct se_cmd *cmd)
 		cmd, cmd->se_tfo->get_task_tag(cmd),
 		cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
 
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
 
 	wait_for_completion(&cmd->t_transport_stop_comp);
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	spin_lock_irqsave(&cmd->t_state_lock, *flags);
 	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
 
 	pr_debug("wait_for_tasks: Stopped wait_for_completion("
 		"&cmd->t_transport_stop_comp) for ITT: 0x%08x\n",
 		cmd->se_tfo->get_task_tag(cmd));
 
+	return true;
+}
+
+/**
+ * transport_wait_for_tasks - wait for completion to occur
+ * @cmd:	command to wait
+ *
+ * Called from frontend fabric context to wait for storage engine
+ * to pause and/or release frontend generated struct se_cmd.
+ */
+bool transport_wait_for_tasks(struct se_cmd *cmd)
+{
+	unsigned long flags;
+	bool ret, aborted = false, tas = false;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	ret = __transport_wait_for_tasks(cmd, false, &aborted, &tas, &flags);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	return true;
+	return ret;
 }
 EXPORT_SYMBOL(transport_wait_for_tasks);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 0c37d70a4f57..e193e5d5ae58 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -533,6 +533,8 @@ struct se_cmd {
 #define CMD_T_DEV_ACTIVE	(1 << 7)
 #define CMD_T_REQUEST_STOP	(1 << 8)
 #define CMD_T_BUSY		(1 << 9)
+#define CMD_T_TAS		(1 << 10)
+#define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
 	struct completion	t_transport_stop_comp;
 

[PATCH 3.16.y-ckt 075/142] target: Fix race with SCF_SEND_DELAYED_TAS handling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 310d3d314be7f0a84011ebdc4bdccbcae9755a87 upstream.

This patch fixes a race between setting of SCF_SEND_DELAYED_TAS
in transport_send_task_abort(), and check of the same bit in
transport_check_aborted_status().

It adds a __transport_check_aborted_status() version that is
used by target_execute_cmd() when se_cmd->t_state_lock is
held, and a transport_check_aborted_status() wrapper for
all other existing callers.

Also, it handles the case where the check happens before
transport_send_task_abort() gets called.  For this, go
ahead and set SCF_SEND_DELAYED_TAS early when necessary,
and have transport_send_task_abort() send the abort.

Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
[ luis: backported to 3.16: based on Nicholas' backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_transport.c | 55 ++++++++++++++++++++++++++--------
 1 file changed, 42 insertions(+), 13 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 3128b718ff73..f787e53e12e8 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1758,19 +1758,21 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 	return true;
 }
 
+static int __transport_check_aborted_status(struct se_cmd *, int);
+
 void target_execute_cmd(struct se_cmd *cmd)
 {
 	/*
-	 * If the received CDB has aleady been aborted stop processing it here.
-	 */
-	if (transport_check_aborted_status(cmd, 1))
-		return;
-
-	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
+	 *
+	 * If the received CDB has aleady been aborted stop processing it here.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
+	if (__transport_check_aborted_status(cmd, 1)) {
+		spin_unlock_irq(&cmd->t_state_lock);
+		return;
+	}
 	if (cmd->transport_state & CMD_T_STOP) {
 		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
 			__func__, __LINE__,
@@ -2951,28 +2953,50 @@ after_reason:
 }
 EXPORT_SYMBOL(transport_send_check_condition_and_sense);
 
-int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
 	if (!(cmd->transport_state & CMD_T_ABORTED))
 		return 0;
-
 	/*
 	 * If cmd has been aborted but either no status is to be sent or it has
 	 * already been sent, just return
 	 */
-	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS))
+	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) {
+		if (send_status)
+			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
 		return 1;
+	}
 
-	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08x\n",
-		 cmd->t_task_cdb[0], cmd->se_tfo->get_task_tag(cmd));
+	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB:"
+		 " 0x%02x ITT: 0x%08x\n", cmd->t_task_cdb[0],
+		 cmd->se_tfo->get_task_tag(cmd));
 
 	cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS;
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 	trace_target_cmd_complete(cmd);
+
+	spin_unlock_irq(&cmd->t_state_lock);
 	cmd->se_tfo->queue_status(cmd);
+	spin_lock_irq(&cmd->t_state_lock);
 
 	return 1;
 }
+
+int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+{
+	int ret;
+
+	spin_lock_irq(&cmd->t_state_lock);
+	ret = __transport_check_aborted_status(cmd, send_status);
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(transport_check_aborted_status);
 
 void transport_send_task_abort(struct se_cmd *cmd)
@@ -2994,12 +3018,17 @@ void transport_send_task_abort(struct se_cmd *cmd)
 	 */
 	if (cmd->data_direction == DMA_TO_DEVICE) {
 		if (cmd->se_tfo->write_pending_status(cmd) != 0) {
-			cmd->transport_state |= CMD_T_ABORTED;
+			spin_lock_irqsave(&cmd->t_state_lock, flags);
+			if (cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS) {
+				spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+				goto send_abort;
+			}
 			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
-			smp_mb__after_atomic();
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 			return;
 		}
 	}
+send_abort:
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 
 	transport_lun_remove_cmd(cmd);

[PATCH 3.16.y-ckt 076/142] Revert "drm/radeon: hold reference to fences in radeon_sa_bo_new"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Luis Henriques <luis.henriques@canonical.com>

This reverts commit 73187980dfefe5198aadcfdf0a377e461eed2bfa, which was
commit f6ff4f67cdf8455d0a4226eeeaf5af17c37d05eb upstream.

This patch was triggering a Oops in stable kernel 3.10.99.  Christian
agrees that the patch is correct but "assumes that radeon_fence_unref()
can safely take NULL as the fence which is not the case for older
kernels."

Reported-by: Erik Andersen <andersen@codepoet.org>
Acked-by: Christian König <christian.koenig@amd.com>
Cc: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_sa.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 15fd57296081..adcf3e2f07da 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -349,13 +349,8 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
-		for (i = 0; i < RADEON_NUM_RINGS; ++i)
-			radeon_fence_ref(fences[i]);
-
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
-		for (i = 0; i < RADEON_NUM_RINGS; ++i)
-			radeon_fence_unref(&fences[i]);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
 		if (r == -ENOENT) {

[PATCH 3.16.y-ckt 077/142] libata: fix HDIO_GET_32BIT ioctl

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Arnd Bergmann <arnd@arndb.de>

commit 287e6611ab1eac76c2c5ebf6e345e04c80ca9c61 upstream.

As reported by Soohoon Lee, the HDIO_GET_32BIT ioctl does not
work correctly in compat mode with libata.

I have investigated the issue further and found multiple problems
that all appeared with the same commit that originally introduced
HDIO_GET_32BIT handling in libata back in linux-2.6.8 and presumably
also linux-2.4, as the code uses "copy_to_user(arg, &val, 1)" to copy
a 'long' variable containing either 0 or 1 to user space.

The problems with this are:

* On big-endian machines, this will always write a zero because it
  stores the wrong byte into user space.

* In compat mode, the upper three bytes of the variable are updated
  by the compat_hdio_ioctl() function, but they now contain
  uninitialized stack data.

* The hdparm tool calling this ioctl uses a 'static long' variable
  to store the result. This means at least the upper bytes are
  initialized to zero, but calling another ioctl like HDIO_GET_MULTCOUNT
  would fill them with data that remains stale when the low byte
  is overwritten. Fortunately libata doesn't implement any of the
  affected ioctl commands, so this would only happen when we query
  both an IDE and an ATA device in the same command such as
  "hdparm -N -c /dev/hda /dev/sda"

* The libata code for unknown reasons started using ATA_IOC_GET_IO32
  and ATA_IOC_SET_IO32 as aliases for HDIO_GET_32BIT and HDIO_SET_32BIT,
  while the ioctl commands that were added later use the normal
  HDIO_* names. This is harmless but rather confusing.

This addresses all four issues by changing the code to use put_user()
on an 'unsigned long' variable in HDIO_GET_32BIT, like the IDE subsystem
does, and by clarifying the names of the ioctl commands.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: Soohoon Lee <Soohoon.Lee@f5.com>
Tested-by: Soohoon Lee <Soohoon.Lee@f5.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/ata/libata-scsi.c | 11 +++++------
 include/linux/ata.h       |  4 ++--
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 30af1877fcea..b87512ff6292 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -674,19 +674,18 @@ static int ata_ioc32(struct ata_port *ap)
 int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev,
 		     int cmd, void __user *arg)
 {
-	int val = -EINVAL, rc = -EINVAL;
+	unsigned long val;
+	int rc = -EINVAL;
 	unsigned long flags;
 
 	switch (cmd) {
-	case ATA_IOC_GET_IO32:
+	case HDIO_GET_32BIT:
 		spin_lock_irqsave(ap->lock, flags);
 		val = ata_ioc32(ap);
 		spin_unlock_irqrestore(ap->lock, flags);
-		if (copy_to_user(arg, &val, 1))
-			return -EFAULT;
-		return 0;
+		return put_user(val, (unsigned long __user *)arg);
 
-	case ATA_IOC_SET_IO32:
+	case HDIO_SET_32BIT:
 		val = (unsigned long) arg;
 		rc = 0;
 		spin_lock_irqsave(ap->lock, flags);
diff --git a/include/linux/ata.h b/include/linux/ata.h
index f2f4d8da97c0..f7ff6554a354 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -484,8 +484,8 @@ enum ata_tf_protocols {
 };
 
 enum ata_ioctls {
-	ATA_IOC_GET_IO32	= 0x309,
-	ATA_IOC_SET_IO32	= 0x324,
+	ATA_IOC_GET_IO32	= 0x309, /* HDIO_GET_32BIT */
+	ATA_IOC_SET_IO32	= 0x324, /* HDIO_SET_32BIT */
 };
 
 /* core structures */

[PATCH 3.16.y-ckt 078/142] [media] adv7604: fix tx 5v detect regression

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Hans Verkuil <hansverk@cisco.com>

commit 0ba4581c84cfb39fd527f6b3457f1c97f6356c04 upstream.

The 5 volt detect functionality broke in 3.14: the code reads IO register 0x70
again after it has already been cleared. Instead it should use the cached
irq_reg_0x70 value and the io_write to 0x71 to clear 0x70 can be dropped since
this has already been done.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/media/i2c/adv7604.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 67403b94f0a2..f70cdea2fcc1 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -1981,10 +1981,9 @@ static int adv7604_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 	}
 
 	/* tx 5v detect */
-	tx_5v = io_read(sd, 0x70) & info->cable_det_mask;
+	tx_5v = irq_reg_0x70 & info->cable_det_mask;
 	if (tx_5v) {
 		v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v);
-		io_write(sd, 0x71, tx_5v);
 		adv7604_s_detect_tx_5v_ctrl(sd);
 		if (handled)
 			*handled = true;

[PATCH 3.16.y-ckt 079/142] usb: chipidea: otg: change workqueue ci_otg as freezable

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Chen <peter.chen@nxp.com>

commit d144dfea8af7108f613139623e63952ed7e69c0c upstream.

If we use USB ID pin as wakeup source, and there is a USB block
device on this USB OTG (ID) cable, the system will be deadlock
after system resume.

The root cause for this problem is: the workqueue ci_otg may try
to remove hcd before the driver resume has finished, and hcd will
disconnect the device on it, then, it will call device_release_driver,
and holds the device lock "dev->mutex", but it is never unlocked since
it waits workqueue writeback to run to flush the block information, but
the workqueue writeback is freezable, it is not thawed before driver
resume has finished.

When the driver (device: sd 0:0:0:0:) resume goes to dpm_complete, it
tries to get its device lock "dev->mutex", but it can't get it forever,
then the deadlock occurs. Below call stacks show the situation.

So, in order to fix this problem, we need to change workqueue ci_otg
as freezable, then the work item in this workqueue will be run after
driver's resume, this workqueue will not be blocked forever like above
case since the workqueue writeback has been thawed too.

Tested at: i.mx6qdl-sabresd and i.mx6sx-sdb.

[  555.178869] kworker/u2:13   D c07de74c     0   826      2 0x00000000
[  555.185310] Workqueue: ci_otg ci_otg_work
[  555.189353] Backtrace:
[  555.191849] [<c07de4fc>] (__schedule) from [<c07dec6c>] (schedule+0x48/0xa0)
[  555.198912]  r10:ee471ba0 r9:00000000 r8:00000000 r7:00000002 r6:ee470000 r5:ee471ba4
[  555.206867]  r4:ee470000
[  555.209453] [<c07dec24>] (schedule) from [<c07e2fc4>] (schedule_timeout+0x15c/0x1e0)
[  555.217212]  r4:7fffffff r3:edc2b000
[  555.220862] [<c07e2e68>] (schedule_timeout) from [<c07df6c8>] (wait_for_common+0x94/0x144)
[  555.229140]  r8:00000000 r7:00000002 r6:ee470000 r5:ee471ba4 r4:7fffffff
[  555.235980] [<c07df634>] (wait_for_common) from [<c07df790>] (wait_for_completion+0x18/0x1c)
[  555.244430]  r10:00000001 r9:c0b5563c r8:c0042e48 r7:ef086000 r6:eea4372c r5:ef131b00
[  555.252383]  r4:00000000
[  555.254970] [<c07df778>] (wait_for_completion) from [<c0043cb8>] (flush_work+0x19c/0x234)
[  555.263177] [<c0043b1c>] (flush_work) from [<c0043fac>] (flush_delayed_work+0x48/0x4c)
[  555.271106]  r8:ed5b5000 r7:c0b38a3c r6:eea439cc r5:eea4372c r4:eea4372c
[  555.277958] [<c0043f64>] (flush_delayed_work) from [<c00eae18>] (bdi_unregister+0x84/0xec)
[  555.286236]  r4:eea43520 r3:20000153
[  555.289885] [<c00ead94>] (bdi_unregister) from [<c02c2154>] (blk_cleanup_queue+0x180/0x29c)
[  555.298250]  r5:eea43808 r4:eea43400
[  555.301909] [<c02c1fd4>] (blk_cleanup_queue) from [<c0417914>] (__scsi_remove_device+0x48/0xb8)
[  555.310623]  r7:00000000 r6:20000153 r5:ededa950 r4:ededa800
[  555.316403] [<c04178cc>] (__scsi_remove_device) from [<c0415e90>] (scsi_forget_host+0x64/0x68)
[  555.325028]  r5:ededa800 r4:ed5b5000
[  555.328689] [<c0415e2c>] (scsi_forget_host) from [<c0409828>] (scsi_remove_host+0x78/0x104)
[  555.337054]  r5:ed5b5068 r4:ed5b5000
[  555.340709] [<c04097b0>] (scsi_remove_host) from [<c04cdfcc>] (usb_stor_disconnect+0x50/0xb4)
[  555.349247]  r6:ed5b56e4 r5:ed5b5818 r4:ed5b5690 r3:00000008
[  555.355025] [<c04cdf7c>] (usb_stor_disconnect) from [<c04b3bc8>] (usb_unbind_interface+0x78/0x25c)
[  555.363997]  r8:c13919b4 r7:edd3c000 r6:edd3c020 r5:ee551c68 r4:ee551c00 r3:c04cdf7c
[  555.371892] [<c04b3b50>] (usb_unbind_interface) from [<c03dc248>] (__device_release_driver+0x8c/0x118)
[  555.381213]  r10:00000001 r9:edd90c00 r8:c13919b4 r7:ee551c68 r6:c0b546e0 r5:c0b5563c
[  555.389167]  r4:edd3c020
[  555.391752] [<c03dc1bc>] (__device_release_driver) from [<c03dc2fc>] (device_release_driver+0x28/0x34)
[  555.401071]  r5:edd3c020 r4:edd3c054
[  555.404721] [<c03dc2d4>] (device_release_driver) from [<c03db304>] (bus_remove_device+0xe0/0x110)
[  555.413607]  r5:edd3c020 r4:ef17f04c
[  555.417253] [<c03db224>] (bus_remove_device) from [<c03d8128>] (device_del+0x114/0x21c)
[  555.425270]  r6:edd3c028 r5:edd3c020 r4:ee551c00 r3:00000000
[  555.431045] [<c03d8014>] (device_del) from [<c04b1560>] (usb_disable_device+0xa4/0x1e8)
[  555.439061]  r8:edd3c000 r7:eded8000 r6:00000000 r5:00000001 r4:ee551c00
[  555.445906] [<c04b14bc>] (usb_disable_device) from [<c04a8e54>] (usb_disconnect+0x74/0x224)
[  555.454271]  r9:edd90c00 r8:ee551000 r7:ee551c68 r6:ee551c9c r5:ee551c00 r4:00000001
[  555.462156] [<c04a8de0>] (usb_disconnect) from [<c04a8fb8>] (usb_disconnect+0x1d8/0x224)
[  555.470259]  r10:00000001 r9:edd90000 r8:ee471e2c r7:ee551468 r6:ee55149c r5:ee551400
[  555.478213]  r4:00000001
[  555.480797] [<c04a8de0>] (usb_disconnect) from [<c04ae5ec>] (usb_remove_hcd+0xa0/0x1ac)
[  555.488813]  r10:00000001 r9:ee471eb0 r8:00000000 r7:ef3d9500 r6:eded810c r5:eded80b0
[  555.496765]  r4:eded8000
[  555.499351] [<c04ae54c>] (usb_remove_hcd) from [<c04d4158>] (host_stop+0x28/0x64)
[  555.506847]  r6:eeb50010 r5:eded8000 r4:eeb51010
[  555.511563] [<c04d4130>] (host_stop) from [<c04d09b8>] (ci_otg_work+0xc4/0x124)
[  555.518885]  r6:00000001 r5:eeb50010 r4:eeb502a0 r3:c04d4130
[  555.524665] [<c04d08f4>] (ci_otg_work) from [<c00454f0>] (process_one_work+0x194/0x420)
[  555.532682]  r6:ef086000 r5:eeb502a0 r4:edc44480
[  555.537393] [<c004535c>] (process_one_work) from [<c00457b0>] (worker_thread+0x34/0x514)
[  555.545496]  r10:edc44480 r9:ef086000 r8:c0b1a100 r7:ef086034 r6:00000088 r5:edc44498
[  555.553450]  r4:ef086000
[  555.556032] [<c004577c>] (worker_thread) from [<c004bab4>] (kthread+0xdc/0xf8)
[  555.563268]  r10:00000000 r9:00000000 r8:00000000 r7:c004577c r6:edc44480 r5:eddc15c0
[  555.571221]  r4:00000000
[  555.573804] [<c004b9d8>] (kthread) from [<c000fef0>] (ret_from_fork+0x14/0x24)
[  555.581040]  r7:00000000 r6:00000000 r5:c004b9d8 r4:eddc15c0

[  553.429383] sh              D c07de74c     0   694    691 0x00000000
[  553.435801] Backtrace:
[  553.438295] [<c07de4fc>] (__schedule) from [<c07dec6c>] (schedule+0x48/0xa0)
[  553.445358]  r10:edd3c054 r9:edd3c078 r8:edddbd50 r7:edcbbc00 r6:c1377c34 r5:60000153
[  553.453313]  r4:eddda000
[  553.455896] [<c07dec24>] (schedule) from [<c07deff8>] (schedule_preempt_disabled+0x10/0x14)
[  553.464261]  r4:edd3c058 r3:0000000a
[  553.467910] [<c07defe8>] (schedule_preempt_disabled) from [<c07e0bbc>] (mutex_lock_nested+0x1a0/0x3e8)
[  553.477254] [<c07e0a1c>] (mutex_lock_nested) from [<c03e927c>] (dpm_complete+0xc0/0x1b0)
[  553.485358]  r10:00561408 r9:edd3c054 r8:c0b4863c r7:edddbd90 r6:c0b485d8 r5:edd3c020
[  553.493313]  r4:edd3c0d0
[  553.495896] [<c03e91bc>] (dpm_complete) from [<c03e9388>] (dpm_resume_end+0x1c/0x20)
[  553.503652]  r9:00000000 r8:c0b1a9d0 r7:c1334ec0 r6:c1334edc r5:00000003 r4:00000010
[  553.511544] [<c03e936c>] (dpm_resume_end) from [<c0079894>] (suspend_devices_and_enter+0x158/0x504)
[  553.520604]  r4:00000000 r3:c1334efc
[  553.524250] [<c007973c>] (suspend_devices_and_enter) from [<c0079e74>] (pm_suspend+0x234/0x2cc)
[  553.532961]  r10:00561408 r9:ed6b7300 r8:00000004 r7:c1334eec r6:00000000 r5:c1334ee8
[  553.540914]  r4:00000003
[  553.543493] [<c0079c40>] (pm_suspend) from [<c0078a6c>] (state_store+0x6c/0xc0)

[  555.703684] 7 locks held by kworker/u2:13/826:
[  555.708140]  #0:  ("%s""ci_otg"){++++.+}, at: [<c0045484>] process_one_work+0x128/0x420
[  555.716277]  #1:  ((&ci->work)){+.+.+.}, at: [<c0045484>] process_one_work+0x128/0x420
[  555.724317]  #2:  (usb_bus_list_lock){+.+.+.}, at: [<c04ae5e4>] usb_remove_hcd+0x98/0x1ac
[  555.732626]  #3:  (&dev->mutex){......}, at: [<c04a8e28>] usb_disconnect+0x48/0x224
[  555.740403]  #4:  (&dev->mutex){......}, at: [<c04a8e28>] usb_disconnect+0x48/0x224
[  555.748179]  #5:  (&dev->mutex){......}, at: [<c03dc2f4>] device_release_driver+0x20/0x34
[  555.756487]  #6:  (&shost->scan_mutex){+.+.+.}, at: [<c04097d0>] scsi_remove_host+0x20/0x104

Cc: Jun Li <jun.li@nxp.com>
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/chipidea/otg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c
index a048b08b9d4d..92f169ca520e 100644
--- a/drivers/usb/chipidea/otg.c
+++ b/drivers/usb/chipidea/otg.c
@@ -116,7 +116,7 @@ static void ci_otg_work(struct work_struct *work)
 int ci_hdrc_otg_init(struct ci_hdrc *ci)
 {
 	INIT_WORK(&ci->work, ci_otg_work);
-	ci->wq = create_singlethread_workqueue("ci_otg");
+	ci->wq = create_freezable_workqueue("ci_otg");
 	if (!ci->wq) {
 		dev_err(ci->dev, "can't create workqueue\n");
 		return -ENODEV;

[PATCH 3.16.y-ckt 080/142] Revert "jffs2: Fix lock acquisition order bug in jffs2_write_begin"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Thomas Betker <thomas.betker@rohde-schwarz.com>

commit 157078f64b8a9cd7011b6b900b2f2498df850748 upstream.

This reverts commit 5ffd3412ae55
("jffs2: Fix lock acquisition order bug in jffs2_write_begin").

The commit modified jffs2_write_begin() to remove a deadlock with
jffs2_garbage_collect_live(), but this introduced new deadlocks found
by multiple users. page_lock() actually has to be called before
mutex_lock(&c->alloc_sem) or mutex_lock(&f->sem) because
jffs2_write_end() and jffs2_readpage() are called with the page locked,
and they acquire c->alloc_sem and f->sem, resp.

In other words, the lock order in jffs2_write_begin() was correct, and
it is the jffs2_garbage_collect_live() path that has to be changed.

Revert the commit to get rid of the new deadlocks, and to clear the way
for a better fix of the original deadlock.

Reported-by: Deng Chao <deng.chao1@zte.com.cn>
Reported-by: Ming Liu <liu.ming50@gmail.com>
Reported-by: wangzaiwei <wangzaiwei@top-vision.cn>
Signed-off-by: Thomas Betker <thomas.betker@rohde-schwarz.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/jffs2/file.c | 39 ++++++++++++++++++---------------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 64989ca9ba90..129eccb4c5a8 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -139,39 +139,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	struct page *pg;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
-	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-	struct jffs2_raw_inode ri;
-	uint32_t alloc_len = 0;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
 	int ret = 0;
 
-	jffs2_dbg(1, "%s()\n", __func__);
-
-	if (pageofs > inode->i_size) {
-		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-		if (ret)
-			return ret;
-	}
-
-	mutex_lock(&f->sem);
 	pg = grab_cache_page_write_begin(mapping, index, flags);
-	if (!pg) {
-		if (alloc_len)
-			jffs2_complete_reservation(c);
-		mutex_unlock(&f->sem);
+	if (!pg)
 		return -ENOMEM;
-	}
 	*pagep = pg;
 
-	if (alloc_len) {
+	jffs2_dbg(1, "%s()\n", __func__);
+
+	if (pageofs > inode->i_size) {
 		/* Make new hole frag from old EOF to new page */
+		struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+		struct jffs2_raw_inode ri;
 		struct jffs2_full_dnode *fn;
+		uint32_t alloc_len;
 
 		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
 			  (unsigned int)inode->i_size, pageofs);
 
+		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+		if (ret)
+			goto out_page;
+
+		mutex_lock(&f->sem);
 		memset(&ri, 0, sizeof(ri));
 
 		ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -198,6 +192,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (IS_ERR(fn)) {
 			ret = PTR_ERR(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -212,10 +207,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		jffs2_complete_reservation(c);
 		inode->i_size = pageofs;
+		mutex_unlock(&f->sem);
 	}
 
 	/*
@@ -224,18 +221,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * case of a short-copy.
 	 */
 	if (!PageUptodate(pg)) {
+		mutex_lock(&f->sem);
 		ret = jffs2_do_readpage_nolock(inode, pg);
+		mutex_unlock(&f->sem);
 		if (ret)
 			goto out_page;
 	}
-	mutex_unlock(&f->sem);
 	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
 	unlock_page(pg);
 	page_cache_release(pg);
-	mutex_unlock(&f->sem);
 	return ret;
 }
 

[PATCH 3.16.y-ckt 081/142] jffs2: Fix page lock / f->sem deadlock

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: David Woodhouse <David.Woodhouse@intel.com>

commit 49e91e7079febe59a20ca885a87dd1c54240d0f1 upstream.

With this fix, all code paths should now be obtaining the page lock before
f->sem.

Reported-by: Szabó Tamás <sztomi89@gmail.com>
Tested-by: Thomas Betker <thomas.betker@rohde-schwarz.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/jffs2/README.Locking |  5 +----
 fs/jffs2/gc.c           | 17 ++++++++++-------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
 	JFFS2 LOCKING DOCUMENTATION
 	---------------------------
 
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
 This document attempts to describe the existing locking rules for
 JFFS2. It is not expected to remain perfectly up to date, but ought to
 be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
 	   any f->sem held.
 	2. Never attempt to lock two file mutexes in one thread.
 	   No ordering rules have been made for doing so.
+	3. Never lock a page cache page with f->sem held.
 
 
 	erase_completion_lock spinlock
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..95d5880a63ee 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		BUG_ON(start > orig_start);
 	}
 
-	/* First, use readpage() to read the appropriate page into the page cache */
-	/* Q: What happens if we actually try to GC the _same_ page for which commit_write()
-	 *    triggered garbage collection in the first place?
-	 * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
-	 *    page OK. We'll actually write it out again in commit_write, which is a little
-	 *    suboptimal, but at least we're correct.
-	 */
+	/* The rules state that we must obtain the page lock *before* f->sem, so
+	 * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+	 * actually going to *change* so we're safe; we only allow reading.
+	 *
+	 * It is important to note that jffs2_write_begin() will ensure that its
+	 * page is marked Uptodate before allocating space. That means that if we
+	 * end up here trying to GC the *same* page that jffs2_write_begin() is
+	 * trying to write out, read_cache_page() will not deadlock. */
+	mutex_unlock(&f->sem);
 	pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+	mutex_lock(&f->sem);
 
 	if (IS_ERR(pg_ptr)) {
 		pr_warn("read_cache_page() returned error: %ld\n",

[PATCH 3.16.y-ckt 082/142] Fix directory hardlinks from deleted directories

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: David Woodhouse <David.Woodhouse@intel.com>

commit be629c62a603e5935f8177fd8a19e014100a259e upstream.

When a directory is deleted, we don't take too much care about killing off
all the dirents that belong to it — on the basis that on remount, the scan
will conclude that the directory is dead anyway.

This doesn't work though, when the deleted directory contained a child
directory which was moved *out*. In the early stages of the fs build
we can then end up with an apparent hard link, with the child directory
appearing both in its true location, and as a child of the original
directory which are this stage of the mount process we don't *yet* know
is defunct.

To resolve this, take out the early special-casing of the "directories
shall not have hard links" rule in jffs2_build_inode_pass1(), and let the
normal nlink processing happen for directories as well as other inodes.

Then later in the build process we can set ic->pino_nlink to the parent
inode#, as is required for directories during normal operaton, instead
of the nlink. And complain only *then* about hard links which are still
in evidence even after killing off all the unreachable paths.

Reported-by: Liu Song <liu.song11@zte.com.cn>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/jffs2/build.c    | 75 ++++++++++++++++++++++++++++++++++++++++-------------
 fs/jffs2/nodelist.h |  6 ++++-
 2 files changed, 62 insertions(+), 19 deletions(-)

diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index a3750f902adc..c1f04947d7dc 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -49,7 +49,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
 
 
 static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
-				    struct jffs2_inode_cache *ic)
+				    struct jffs2_inode_cache *ic,
+				    int *dir_hardlinks)
 {
 	struct jffs2_full_dirent *fd;
 
@@ -68,19 +69,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 			dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
 				  fd->name, fd->ino, ic->ino);
 			jffs2_mark_node_obsolete(c, fd->raw);
+			/* Clear the ic/raw union so it doesn't cause problems later. */
+			fd->ic = NULL;
 			continue;
 		}
 
+		/* From this point, fd->raw is no longer used so we can set fd->ic */
+		fd->ic = child_ic;
+		child_ic->pino_nlink++;
+		/* If we appear (at this stage) to have hard-linked directories,
+		 * set a flag to trigger a scan later */
 		if (fd->type == DT_DIR) {
-			if (child_ic->pino_nlink) {
-				JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
-					    fd->name, fd->ino, ic->ino);
-				/* TODO: What do we do about it? */
-			} else {
-				child_ic->pino_nlink = ic->ino;
-			}
-		} else
-			child_ic->pino_nlink++;
+			child_ic->flags |= INO_FLAGS_IS_DIR;
+			if (child_ic->pino_nlink > 1)
+				*dir_hardlinks = 1;
+		}
 
 		dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
 		/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -94,8 +97,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 */
 static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 {
-	int ret;
-	int i;
+	int ret, i, dir_hardlinks = 0;
 	struct jffs2_inode_cache *ic;
 	struct jffs2_full_dirent *fd;
 	struct jffs2_full_dirent *dead_fds = NULL;
@@ -119,7 +121,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	/* Now scan the directory tree, increasing nlink according to every dirent found. */
 	for_each_inode(i, c, ic) {
 		if (ic->scan_dents) {
-			jffs2_build_inode_pass1(c, ic);
+			jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
 			cond_resched();
 		}
 	}
@@ -155,6 +157,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	}
 
 	dbg_fsbuild("pass 2a complete\n");
+
+	if (dir_hardlinks) {
+		/* If we detected directory hardlinks earlier, *hopefully*
+		 * they are gone now because some of the links were from
+		 * dead directories which still had some old dirents lying
+		 * around and not yet garbage-collected, but which have
+		 * been discarded above. So clear the pino_nlink field
+		 * in each directory, so that the final scan below can
+		 * print appropriate warnings. */
+		for_each_inode(i, c, ic) {
+			if (ic->flags & INO_FLAGS_IS_DIR)
+				ic->pino_nlink = 0;
+		}
+	}
 	dbg_fsbuild("freeing temporary data structures\n");
 
 	/* Finally, we can scan again and free the dirent structs */
@@ -162,6 +178,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 		while(ic->scan_dents) {
 			fd = ic->scan_dents;
 			ic->scan_dents = fd->next;
+			/* We do use the pino_nlink field to count nlink of
+			 * directories during fs build, so set it to the
+			 * parent ino# now. Now that there's hopefully only
+			 * one. */
+			if (fd->type == DT_DIR) {
+				if (!fd->ic) {
+					/* We'll have complained about it and marked the coresponding
+					   raw node obsolete already. Just skip it. */
+					continue;
+				}
+
+				/* We *have* to have set this in jffs2_build_inode_pass1() */
+				BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+				/* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+				 * is set. Otherwise, we know this should never trigger anyway, so
+				 * we don't do the check. And ic->pino_nlink still contains the nlink
+				 * value (which is 1). */
+				if (dir_hardlinks && fd->ic->pino_nlink) {
+					JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+						    fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+					/* Should we unlink it from its previous parent? */
+				}
+
+				/* For directories, ic->pino_nlink holds that parent inode # */
+				fd->ic->pino_nlink = ic->ino;
+			}
 			jffs2_free_full_dirent(fd);
 		}
 		ic->scan_dents = NULL;
@@ -240,11 +283,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
 
 			/* Reduce nlink of the child. If it's now zero, stick it on the
 			   dead_fds list to be cleaned up later. Else just free the fd */
-
-			if (fd->type == DT_DIR)
-				child_ic->pino_nlink = 0;
-			else
-				child_ic->pino_nlink--;
+			child_ic->pino_nlink--;
 
 			if (!child_ic->pino_nlink) {
 				dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
 #define INO_STATE_CLEARING	6	/* In clear_inode() */
 
 #define INO_FLAGS_XATTR_CHECKED	0x01	/* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR	0x02	/* is a directory */
 
 #define RAWNODE_CLASS_INODE_CACHE	0
 #define RAWNODE_CLASS_XATTR_DATUM	1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
 
 struct jffs2_full_dirent
 {
-	struct jffs2_raw_node_ref *raw;
+	union {
+		struct jffs2_raw_node_ref *raw;
+		struct jffs2_inode_cache *ic; /* Just during part of build */
+	};
 	struct jffs2_full_dirent *next;
 	uint32_t version;
 	uint32_t ino; /* == zero for unlink */

[PATCH 3.16.y-ckt 083/142] iommu/amd: Fix boot warning when device 00:00.0 is not iommu covered

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>

commit 38e45d02ea9f194b89d6bf41e52ccafc8e2c2b47 upstream.

The setup code for the performance counters in the AMD IOMMU driver
tests whether the counters can be written. It tests to setup a counter
for device 00:00.0, which fails on systems where this particular device
is not covered by the IOMMU.

Fix this by not relying on device 00:00.0 but only on the IOMMU being
present.

Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/iommu/amd_iommu_init.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 0e08545d7298..69f1b6adb904 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -226,6 +226,10 @@ static enum iommu_init_state init_state = IOMMU_START_STATE;
 static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
 
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+				    u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write);
+
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -1182,8 +1186,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 	amd_iommu_pc_present = true;
 
 	/* Check if the performance counters can be written to */
-	if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) ||
-	    (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) ||
+	if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
+	    (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
 	    (val != val2)) {
 		pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
 		amd_iommu_pc_present = false;
@@ -2316,22 +2320,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid)
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
 
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+				    u8 bank, u8 cntr, u8 fxn,
 				    u64 *value, bool is_write)
 {
-	struct amd_iommu *iommu;
 	u32 offset;
 	u32 max_offset_lim;
 
-	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_present)
-		return -ENODEV;
-
-	/* Locate the iommu associated with the device ID */
-	iommu = amd_iommu_rlookup_table[devid];
-
 	/* Check for valid iommu and pc register indexing */
-	if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7)))
+	if (WARN_ON((fxn > 0x28) || (fxn & 7)))
 		return -ENODEV;
 
 	offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
@@ -2355,3 +2352,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
 	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
+
+int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write)
+{
+	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present || iommu == NULL)
+		return -ENODEV;
+
+	return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
+					value, is_write);
+}

[PATCH 3.16.y-ckt 084/142] libata: Align ata_device's id on a cacheline

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Harvey Hunt <harvey.hunt@imgtec.com>

commit 4ee34ea3a12396f35b26d90a094c75db95080baa upstream.

The id buffer in ata_device is a DMA target, but it isn't explicitly
cacheline aligned. Due to this, adjacent fields can be overwritten with
stale data from memory on non coherent architectures. As a result, the
kernel is sometimes unable to communicate with an ATA device.

Fix this by ensuring that the id buffer is cacheline aligned.

This issue is similar to that fixed by Commit 84bda12af31f
("libata: align ap->sector_buf").

Signed-off-by: Harvey Hunt <harvey.hunt@imgtec.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/libata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/libata.h b/include/linux/libata.h
index 714274450c07..bd83b8e83cfe 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -714,7 +714,7 @@ struct ata_device {
 	union {
 		u16		id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */
 		u32		gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
-	};
+	} ____cacheline_aligned;
 
 	/* DEVSLP Timing Variables from Identify Device Data Log */
 	u8			devslp_timing[ATA_LOG_DEVSLP_SIZE];

[PATCH 3.16.y-ckt 085/142] vfio: fix ioctl error handling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Michael S. Tsirkin" <mst@redhat.com>

commit 8160c4e455820d5008a1116d2dca35f0363bb062 upstream.

Calling return copy_to_user(...) in an ioctl will not
do the right thing if there's a pagefault:
copy_to_user returns the number of bytes not copied
in this case.

Fix up vfio to do
	return copy_to_user(...)) ?
		-EFAULT : 0;

everywhere.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
[ luis: backported to 3.16:
  - dropped changes to vfio_platform_common.c ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/vfio/pci/vfio_pci.c     | 9 ++++++---
 drivers/vfio/vfio_iommu_type1.c | 6 ++++--
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 652ab678160e..a1e77f570b19 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -346,7 +346,8 @@ static long vfio_pci_ioctl(void *device_data,
 		info.num_regions = VFIO_PCI_NUM_REGIONS;
 		info.num_irqs = VFIO_PCI_NUM_IRQS;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
 		struct pci_dev *pdev = vdev->pdev;
@@ -419,7 +420,8 @@ static long vfio_pci_ioctl(void *device_data,
 			return -EINVAL;
 		}
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
 		struct vfio_irq_info info;
@@ -453,7 +455,8 @@ static long vfio_pci_ioctl(void *device_data,
 		else
 			info.flags |= VFIO_IRQ_INFO_NORESIZE;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
 		struct vfio_irq_set hdr;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0734fbe5b651..0e153f23c47f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -908,7 +908,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
 		struct vfio_iommu_type1_dma_map map;
@@ -941,7 +942,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		if (ret)
 			return ret;
 
-		return copy_to_user((void __user *)arg, &unmap, minsz);
+		return copy_to_user((void __user *)arg, &unmap, minsz) ?
+			-EFAULT : 0;
 	}
 
 	return -ENOTTY;

[PATCH 3.16.y-ckt 086/142] ALSA: ctl: Fix ioctls for X32 ABI

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 6236d8bb2afcfe71b88ecea554e0dc638090a45f upstream.

The X32 ABI takes the same alignment like x86-64, and this may result
in the incompatible struct size from ia32.  Unfortunately, we hit this
in some control ABI: struct snd_ctl_elem_value differs between them
due to the position of 64bit variable array.  This ends up with the
unknown ioctl (ENOTTY) error.

The fix is to add the compat entries for the new aligned struct.

Reported-and-tested-by: Steven Newbury <steve@snewbury.org.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/control_compat.c | 90 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 74 insertions(+), 16 deletions(-)

diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c
index b9c0910fb8c4..0608f216f359 100644
--- a/sound/core/control_compat.c
+++ b/sound/core/control_compat.c
@@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 {
         unsigned char reserved[128];
 };
 
+#ifdef CONFIG_X86_X32
+/* x32 has a different alignment for 64bit values from ia32 */
+struct snd_ctl_elem_value_x32 {
+	struct snd_ctl_elem_id id;
+	unsigned int indirect;	/* bit-field causes misalignment */
+	union {
+		s32 integer[128];
+		unsigned char data[512];
+		s64 integer64[64];
+	} value;
+	unsigned char reserved[128];
+};
+#endif /* CONFIG_X86_X32 */
 
 /* get the value type and count of the control */
 static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id,
@@ -219,9 +232,11 @@ static int get_elem_size(int type, int count)
 
 static int copy_ctl_value_from_user(struct snd_card *card,
 				    struct snd_ctl_elem_value *data,
-				    struct snd_ctl_elem_value32 __user *data32,
+				    void __user *userdata,
+				    void __user *valuep,
 				    int *typep, int *countp)
 {
+	struct snd_ctl_elem_value32 __user *data32 = userdata;
 	int i, type, size;
 	int uninitialized_var(count);
 	unsigned int indirect;
@@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 	if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
 	    type == SNDRV_CTL_ELEM_TYPE_INTEGER) {
 		for (i = 0; i < count; i++) {
+			s32 __user *intp = valuep;
 			int val;
-			if (get_user(val, &data32->value.integer[i]))
+			if (get_user(val, &intp[i]))
 				return -EFAULT;
 			data->value.integer.value[i] = val;
 		}
@@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 			dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type);
 			return -EINVAL;
 		}
-		if (copy_from_user(data->value.bytes.data,
-				   data32->value.data, size))
+		if (copy_from_user(data->value.bytes.data, valuep, size))
 			return -EFAULT;
 	}
 
@@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 }
 
 /* restore the value to 32bit */
-static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32,
+static int copy_ctl_value_to_user(void __user *userdata,
+				  void __user *valuep,
 				  struct snd_ctl_elem_value *data,
 				  int type, int count)
 {
@@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32,
 	if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
 	    type == SNDRV_CTL_ELEM_TYPE_INTEGER) {
 		for (i = 0; i < count; i++) {
+			s32 __user *intp = valuep;
 			int val;
 			val = data->value.integer.value[i];
-			if (put_user(val, &data32->value.integer[i]))
+			if (put_user(val, &intp[i]))
 				return -EFAULT;
 		}
 	} else {
 		size = get_elem_size(type, count);
-		if (copy_to_user(data32->value.data,
-				 data->value.bytes.data, size))
+		if (copy_to_user(valuep, data->value.bytes.data, size))
 			return -EFAULT;
 	}
 	return 0;
 }
 
-static int snd_ctl_elem_read_user_compat(struct snd_card *card, 
-					 struct snd_ctl_elem_value32 __user *data32)
+static int ctl_elem_read_user(struct snd_card *card,
+			      void __user *userdata, void __user *valuep)
 {
 	struct snd_ctl_elem_value *data;
 	int err, type, count;
@@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card,
 	if (data == NULL)
 		return -ENOMEM;
 
-	if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0)
+	err = copy_ctl_value_from_user(card, data, userdata, valuep,
+				       &type, &count);
+	if (err < 0)
 		goto error;
 
 	snd_power_lock(card);
@@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card,
 		err = snd_ctl_elem_read(card, data);
 	snd_power_unlock(card);
 	if (err >= 0)
-		err = copy_ctl_value_to_user(data32, data, type, count);
+		err = copy_ctl_value_to_user(userdata, valuep, data,
+					     type, count);
  error:
 	kfree(data);
 	return err;
 }
 
-static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
-					  struct snd_ctl_elem_value32 __user *data32)
+static int ctl_elem_write_user(struct snd_ctl_file *file,
+			       void __user *userdata, void __user *valuep)
 {
 	struct snd_ctl_elem_value *data;
 	struct snd_card *card = file->card;
@@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
 	if (data == NULL)
 		return -ENOMEM;
 
-	if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0)
+	err = copy_ctl_value_from_user(card, data, userdata, valuep,
+				       &type, &count);
+	if (err < 0)
 		goto error;
 
 	snd_power_lock(card);
@@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
 		err = snd_ctl_elem_write(card, file, data);
 	snd_power_unlock(card);
 	if (err >= 0)
-		err = copy_ctl_value_to_user(data32, data, type, count);
+		err = copy_ctl_value_to_user(userdata, valuep, data,
+					     type, count);
  error:
 	kfree(data);
 	return err;
 }
 
+static int snd_ctl_elem_read_user_compat(struct snd_card *card,
+					 struct snd_ctl_elem_value32 __user *data32)
+{
+	return ctl_elem_read_user(card, data32, &data32->value);
+}
+
+static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
+					  struct snd_ctl_elem_value32 __user *data32)
+{
+	return ctl_elem_write_user(file, data32, &data32->value);
+}
+
+#ifdef CONFIG_X86_X32
+static int snd_ctl_elem_read_user_x32(struct snd_card *card,
+				      struct snd_ctl_elem_value_x32 __user *data32)
+{
+	return ctl_elem_read_user(card, data32, &data32->value);
+}
+
+static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file,
+				       struct snd_ctl_elem_value_x32 __user *data32)
+{
+	return ctl_elem_write_user(file, data32, &data32->value);
+}
+#endif /* CONFIG_X86_X32 */
+
 /* add or replace a user control */
 static int snd_ctl_elem_add_compat(struct snd_ctl_file *file,
 				   struct snd_ctl_elem_info32 __user *data32,
@@ -393,6 +441,10 @@ enum {
 	SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32),
 	SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32),
 	SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32),
+#ifdef CONFIG_X86_X32
+	SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32),
+	SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32),
+#endif /* CONFIG_X86_X32 */
 };
 
 static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns
 		return snd_ctl_elem_add_compat(ctl, argp, 0);
 	case SNDRV_CTL_IOCTL_ELEM_REPLACE32:
 		return snd_ctl_elem_add_compat(ctl, argp, 1);
+#ifdef CONFIG_X86_X32
+	case SNDRV_CTL_IOCTL_ELEM_READ_X32:
+		return snd_ctl_elem_read_user_x32(ctl->card, argp);
+	case SNDRV_CTL_IOCTL_ELEM_WRITE_X32:
+		return snd_ctl_elem_write_user_x32(ctl, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 
 	down_read(&snd_ioctl_rwsem);

[PATCH 3.16.y-ckt 087/142] ALSA: rawmidi: Fix ioctls X32 ABI

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 2251fbbc1539f05b0b206b37a602d5776be37252 upstream.

Like the previous fixes for ctl and PCM, we need a fix for
incompatible X32 ABI regarding the rawmidi: namely, struct
snd_rawmidi_status has the timespec, and the size and the alignment on
X32 differ from IA32.

This patch fixes the incompatible ioctl for X32.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/rawmidi_compat.c | 53 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c
index 5268c1f58c25..09a89094dcf7 100644
--- a/sound/core/rawmidi_compat.c
+++ b/sound/core/rawmidi_compat.c
@@ -94,9 +94,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile,
 	return 0;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has 64bit timespec and 64bit alignment */
+struct snd_rawmidi_status_x32 {
+	s32 stream;
+	u32 rsvd; /* alignment */
+	struct timespec tstamp;
+	u32 avail;
+	u32 xruns;
+	unsigned char reserved[16];
+} __attribute__((packed));
+
+#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst))
+
+static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile,
+					struct snd_rawmidi_status_x32 __user *src)
+{
+	int err;
+	struct snd_rawmidi_status status;
+
+	if (rfile->output == NULL)
+		return -EINVAL;
+	if (get_user(status.stream, &src->stream))
+		return -EFAULT;
+
+	switch (status.stream) {
+	case SNDRV_RAWMIDI_STREAM_OUTPUT:
+		err = snd_rawmidi_output_status(rfile->output, &status);
+		break;
+	case SNDRV_RAWMIDI_STREAM_INPUT:
+		err = snd_rawmidi_input_status(rfile->input, &status);
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (err < 0)
+		return err;
+
+	if (put_timespec(&status.tstamp, &src->tstamp) ||
+	    put_user(status.avail, &src->avail) ||
+	    put_user(status.xruns, &src->xruns))
+		return -EFAULT;
+
+	return 0;
+}
+#endif /* CONFIG_X86_X32 */
+
 enum {
 	SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32),
 	SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32),
+#ifdef CONFIG_X86_X32
+	SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32),
+#endif /* CONFIG_X86_X32 */
 };
 
 static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -115,6 +164,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign
 		return snd_rawmidi_ioctl_params_compat(rfile, argp);
 	case SNDRV_RAWMIDI_IOCTL_STATUS32:
 		return snd_rawmidi_ioctl_status_compat(rfile, argp);
+#ifdef CONFIG_X86_X32
+	case SNDRV_RAWMIDI_IOCTL_STATUS_X32:
+		return snd_rawmidi_ioctl_status_x32(rfile, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 	return -ENOIOCTLCMD;
 }

[PATCH 3.16.y-ckt 088/142] ALSA: timer: Fix broken compat timer user status ioctl

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 3a72494ac2a3bd229db941d51e7efe2f6ccd947b upstream.

The timer user status compat ioctl returned the bogus struct used for
64bit architectures instead of the 32bit one.  This patch addresses
it to return the proper struct.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/timer_compat.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c
index e05802ae6e1b..8e7eddf35c6a 100644
--- a/sound/core/timer_compat.c
+++ b/sound/core/timer_compat.c
@@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file,
 					struct snd_timer_status32 __user *_status)
 {
 	struct snd_timer_user *tu;
-	struct snd_timer_status status;
+	struct snd_timer_status32 status;
 	
 	tu = file->private_data;
 	if (snd_BUG_ON(!tu->timeri))
 		return -ENXIO;
 	memset(&status, 0, sizeof(status));
-	status.tstamp = tu->tstamp;
+	status.tstamp.tv_sec = tu->tstamp.tv_sec;
+	status.tstamp.tv_nsec = tu->tstamp.tv_nsec;
 	status.resolution = snd_timer_resolution(tu->timeri);
 	status.lost = tu->timeri->lost;
 	status.overrun = tu->overrun;

[PATCH 3.16.y-ckt 089/142] ALSA: timer: Fix ioctls for X32 ABI

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit b24e7ad1fdc22177eb3e51584e1cfcb45d818488 upstream.

X32 ABI takes the 64bit timespec, thus the timer user status ioctl becomes
incompatible with IA32.  This results in NOTTY error when the ioctl is
issued.

Meanwhile, this struct in X32 is essentially identical with the one in
X86-64, so we can just bypassing to the existing code for this
specific compat ioctl.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/timer_compat.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c
index 8e7eddf35c6a..2e908225d754 100644
--- a/sound/core/timer_compat.c
+++ b/sound/core/timer_compat.c
@@ -89,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file,
 	return 0;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has the same struct as x86-64 */
+#define snd_timer_user_status_x32(file, s) \
+	snd_timer_user_status(file, s)
+#endif /* CONFIG_X86_X32 */
+
 /*
  */
 
 enum {
 	SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32),
 	SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32),
+#ifdef CONFIG_X86_X32
+	SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status),
+#endif /* CONFIG_X86_X32 */
 };
 
 static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -123,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns
 		return snd_timer_user_info_compat(file, argp);
 	case SNDRV_TIMER_IOCTL_STATUS32:
 		return snd_timer_user_status_compat(file, argp);
+#ifdef CONFIG_X86_X32
+	case SNDRV_TIMER_IOCTL_STATUS_X32:
+		return snd_timer_user_status_x32(file, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 	return -ENOIOCTLCMD;
 }

[PATCH 3.16.y-ckt 090/142] cifs: fix out-of-bounds access in lease parsing

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Justin Maggard <jmaggard10@gmail.com>

commit deb7deff2f00bdbbcb3d560dad2a89ef37df837d upstream.

When opening a file, SMB2_open() attempts to parse the lease state from the
SMB2 CREATE Response.  However, the parsing code was not careful to ensure
that the create contexts are not empty or invalid, which can lead to out-
of-bounds memory access.  This can be seen easily by trying
to read a file from a OSX 10.11 SMB3 server.  Here is sample crash output:

BUG: unable to handle kernel paging request at ffff8800a1a77cc6
IP: [<ffffffff8828a734>] SMB2_open+0x804/0x960
PGD 8f77067 PUD 0
Oops: 0000 [#1] SMP
Modules linked in:
CPU: 3 PID: 2876 Comm: cp Not tainted 4.5.0-rc3.x86_64.1+ #14
Hardware name: NETGEAR ReadyNAS 314          /ReadyNAS 314          , BIOS 4.6.5 10/11/2012
task: ffff880073cdc080 ti: ffff88005b31c000 task.ti: ffff88005b31c000
RIP: 0010:[<ffffffff8828a734>]  [<ffffffff8828a734>] SMB2_open+0x804/0x960
RSP: 0018:ffff88005b31fa08  EFLAGS: 00010282
RAX: 0000000000000015 RBX: 0000000000000000 RCX: 0000000000000006
RDX: 0000000000000000 RSI: 0000000000000246 RDI: ffff88007eb8c8b0
RBP: ffff88005b31fad8 R08: 666666203d206363 R09: 6131613030383866
R10: 3030383866666666 R11: 00000000000002b0 R12: ffff8800660fd800
R13: ffff8800a1a77cc2 R14: 00000000424d53fe R15: ffff88005f5a28c0
FS:  00007f7c8a2897c0(0000) GS:ffff88007eb80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: ffff8800a1a77cc6 CR3: 000000005b281000 CR4: 00000000000006e0
Stack:
 ffff88005b31fa70 ffffffff88278789 00000000000001d3 ffff88005f5a2a80
 ffffffff00000003 ffff88005d029d00 ffff88006fde05a0 0000000000000000
 ffff88005b31fc78 ffff88006fde0780 ffff88005b31fb2f 0000000100000fe0
Call Trace:
 [<ffffffff88278789>] ? cifsConvertToUTF16+0x159/0x2d0
 [<ffffffff8828cf68>] smb2_open_file+0x98/0x210
 [<ffffffff8811e80c>] ? __kmalloc+0x1c/0xe0
 [<ffffffff882685f4>] cifs_open+0x2a4/0x720
 [<ffffffff88122cef>] do_dentry_open+0x1ff/0x310
 [<ffffffff88268350>] ? cifsFileInfo_get+0x30/0x30
 [<ffffffff88123d92>] vfs_open+0x52/0x60
 [<ffffffff88131dd0>] path_openat+0x170/0xf70
 [<ffffffff88097d48>] ? remove_wait_queue+0x48/0x50
 [<ffffffff88133a29>] do_filp_open+0x79/0xd0
 [<ffffffff8813f2ca>] ? __alloc_fd+0x3a/0x170
 [<ffffffff881240c4>] do_sys_open+0x114/0x1e0
 [<ffffffff881241a9>] SyS_open+0x19/0x20
 [<ffffffff8896e257>] entry_SYSCALL_64_fastpath+0x12/0x6a
Code: 4d 8d 6c 07 04 31 c0 4c 89 ee e8 47 6f e5 ff 31 c9 41 89 ce 44 89 f1 48 c7 c7 28 b1 bd 88 31 c0 49 01 cd 4c 89 ee e8 2b 6f e5 ff <45> 0f b7 75 04 48 c7 c7 31 b1 bd 88 31 c0 4d 01 ee 4c 89 f6 e8
RIP  [<ffffffff8828a734>] SMB2_open+0x804/0x960
 RSP <ffff88005b31fa08>
CR2: ffff8800a1a77cc6
---[ end trace d9f69ba64feee469 ]---

Signed-off-by: Justin Maggard <jmaggard@netgear.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/cifs/smb2pdu.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 87077559a0ab..c83a5a2fac70 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1012,21 +1012,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 {
 	char *data_offset;
 	struct create_context *cc;
-	unsigned int next = 0;
+	unsigned int next;
+	unsigned int remaining;
 	char *name;
 
 	data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset);
+	remaining = le32_to_cpu(rsp->CreateContextsLength);
 	cc = (struct create_context *)data_offset;
-	do {
-		cc = (struct create_context *)((char *)cc + next);
+	while (remaining >= sizeof(struct create_context)) {
 		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) != 4 ||
-		    strncmp(name, "RqLs", 4)) {
-			next = le32_to_cpu(cc->Next);
-			continue;
-		}
-		return server->ops->parse_lease_buf(cc, epoch);
-	} while (next != 0);
+		if (le16_to_cpu(cc->NameLength) == 4 &&
+		    strncmp(name, "RqLs", 4) == 0)
+			return server->ops->parse_lease_buf(cc, epoch);
+
+		next = le32_to_cpu(cc->Next);
+		if (!next)
+			break;
+		remaining -= next;
+		cc = (struct create_context *)((char *)cc + next);
+	}
 
 	return 0;
 }

[PATCH 3.16.y-ckt 091/142] CIFS: Fix SMB2+ interim response processing for read requests

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Pavel Shilovsky <pshilovsky@samba.org>

commit 6cc3b24235929b54acd5ecc987ef11a425bd209e upstream.

For interim responses we only need to parse a header and update
a number credits. Now it is done for all SMB2+ command except
SMB2_READ which is wrong. Fix this by adding such processing.

Signed-off-by: Pavel Shilovsky <pshilovsky@samba.org>
Tested-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/cifs/cifssmb.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 6ce4e0954b98..2df1390e5d66 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1399,11 +1399,10 @@ openRetry:
  * current bigbuf.
  */
 static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
-	struct cifs_readdata *rdata = mid->callback_data;
 
 	while (remaining > 0) {
 		int length;
@@ -1417,10 +1416,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		remaining -= length;
 	}
 
-	dequeue_mid(mid, rdata->result);
 	return 0;
 }
 
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	int length;
+	struct cifs_readdata *rdata = mid->callback_data;
+
+	length = discard_remaining_data(server);
+	dequeue_mid(mid, rdata->result);
+	return length;
+}
+
 int
 cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
@@ -1449,6 +1458,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return length;
 	server->total_read += length;
 
+	if (server->ops->is_status_pending &&
+	    server->ops->is_status_pending(buf, server, 0)) {
+		discard_remaining_data(server);
+		return -1;
+	}
+
 	/* Was the SMB read successful? */
 	rdata->result = server->ops->map_error(buf, false);
 	if (rdata->result != 0) {

[PATCH 3.16.y-ckt 092/142] Fix cifs_uniqueid_to_ino_t() function for s390x

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Yadan Fan <ydfan@novell.com>

commit 1ee9f4bd1a97026a7b2d7ae9f1f74b45680d0003 upstream.

This issue is caused by commit 02323db17e3a7 ("cifs: fix
cifs_uniqueid_to_ino_t not to ever return 0"), when BITS_PER_LONG
is 64 on s390x, the corresponding cifs_uniqueid_to_ino_t()
function will cast 64-bit fileid to 32-bit by using (ino_t)fileid,
because ino_t (typdefed __kernel_ino_t) is int type.

It's defined in arch/s390/include/uapi/asm/posix_types.h

    #ifndef __s390x__

    typedef unsigned long   __kernel_ino_t;
    ...
    #else /* __s390x__ */

    typedef unsigned int    __kernel_ino_t;

So the #ifdef condition is wrong for s390x, we can just still use
one cifs_uniqueid_to_ino_t() function with comparing sizeof(ino_t)
and sizeof(u64) to choose the correct execution accordingly.

Signed-off-by: Yadan Fan <ydfan@suse.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/cifs/cifsfs.h | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 70f178a7c759..e48d496c43c7 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -31,19 +31,15 @@
  * so that it will fit. We use hash_64 to convert the value to 31 bits, and
  * then add 1, to ensure that we don't end up with a 0 as the value.
  */
-#if BITS_PER_LONG == 64
 static inline ino_t
 cifs_uniqueid_to_ino_t(u64 fileid)
 {
+	if ((sizeof(ino_t)) < (sizeof(u64)))
+		return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+
 	return (ino_t)fileid;
+
 }
-#else
-static inline ino_t
-cifs_uniqueid_to_ino_t(u64 fileid)
-{
-	return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
-}
-#endif
 
 extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;

[PATCH 3.16.y-ckt 093/142] arm/arm64: KVM: Fix ioctl error handling

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Michael S. Tsirkin" <mst@redhat.com>

commit 4cad67fca3fc952d6f2ed9e799621f07666a560f upstream.

Calling return copy_to_user(...) in an ioctl will not
do the right thing if there's a pagefault:
copy_to_user returns the number of bytes not copied
in this case.

Fix up kvm to do
	return copy_to_user(...)) ?  -EFAULT : 0;

everywhere.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
[ luis: backported to 3.16:
  - dropped changes to arch/arm64/kvm/guest.c ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/kvm/guest.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 2786eae10c0d..f3f6415b7828 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -183,7 +183,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	u64 val;
 
 	val = kvm_arm_timer_get_reg(vcpu, reg->id);
-	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
 }
 
 static unsigned long num_core_regs(void)

[PATCH 3.16.y-ckt 094/142] ALSA: hdspm: Fix wrong boolean ctl value accesses

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 537e48136295c5860a92138c5ea3959b9542868b upstream.

snd-hdspm driver accesses enum item values (int) instead of boolean
values (long) wrongly for some ctl elements.  This patch fixes them.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/pci/rme9652/hdspm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index f292bed4424d..004fd3260048 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -2266,7 +2266,7 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol,
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
 
-	hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]);
+	hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]);
 	return 0;
 }
 
@@ -4465,7 +4465,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol,
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.enumerated.item[0] = hdspm->tco->term;
+	ucontrol->value.integer.value[0] = hdspm->tco->term;
 
 	return 0;
 }
@@ -4476,8 +4476,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol,
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
 
-	if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) {
-		hdspm->tco->term = ucontrol->value.enumerated.item[0];
+	if (hdspm->tco->term != ucontrol->value.integer.value[0]) {
+		hdspm->tco->term = ucontrol->value.integer.value[0];
 
 		hdspm_tco_write(hdspm);
 

[PATCH 3.16.y-ckt 095/142] ALSA: hdspm: Fix zero-division

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit c1099c3294c2344110085a38c50e478a5992b368 upstream.

HDSPM driver contains a code issuing zero-division potentially in
system sample rate ctl code.  This patch fixes it by not processing
a zero or invalid rate value as a divisor, as well as excluding the
invalid value to be passed via the given ctl element.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/pci/rme9652/hdspm.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 004fd3260048..811d3c1eb338 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -1602,6 +1602,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate)
 {
 	u64 n;
 
+	if (snd_BUG_ON(rate <= 0))
+		return;
+
 	if (rate >= 112000)
 		rate /= 4;
 	else if (rate >= 56000)
@@ -2220,6 +2223,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm)
 		} else {
 			/* slave mode, return external sample rate */
 			rate = hdspm_external_sample_rate(hdspm);
+			if (!rate)
+				rate = hdspm->system_sample_rate;
 		}
 	}
 
@@ -2265,7 +2270,10 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol,
 					    ucontrol)
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
+	int rate = ucontrol->value.integer.value[0];
 
+	if (rate < 27000 || rate > 207000)
+		return -EINVAL;
 	hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]);
 	return 0;
 }

[PATCH 3.16.y-ckt 096/142] ALSA: hdsp: Fix wrong boolean ctl value accesses

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit eab3c4db193f5fcccf70e884de9a922ca2c63d80 upstream.

snd-hdsp driver accesses enum item values (int) instead of boolean
values (long) wrongly for some ctl elements.  This patch fixes them.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/pci/rme9652/hdsp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 4c6f5d1c9882..a2fbc99aad87 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -2927,7 +2927,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl
 {
 	struct hdsp *hdsp = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp);
+	ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp);
 	return 0;
 }
 
@@ -2939,7 +2939,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl
 
 	if (!snd_hdsp_use_is_exclusive(hdsp))
 		return -EBUSY;
-	val = ucontrol->value.enumerated.item[0];
+	val = ucontrol->value.integer.value[0];
 	spin_lock_irq(&hdsp->lock);
 	if (val != hdsp_dds_offset(hdsp))
 		change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0;

[PATCH 3.16.y-ckt 097/142] USB: qcserial: add Dell Wireless 5809e Gobi 4G HSPA+ (rev3)

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Patrik Halfar <patrik_halfar@halfarit.cz>

commit 013dd239d6220a4e0dfdf0d45a82c34f1fd73deb upstream.

New revision of Dell Wireless 5809e Gobi 4G HSPA+ Mobile Broadband Card
has new idProduct.

Bus 002 Device 006: ID 413c:81b3 Dell Computer Corp.
Device Descriptor:
  bLength                18
  bDescriptorType         1
  bcdUSB               2.00
  bDeviceClass            0
  bDeviceSubClass         0
  bDeviceProtocol         0
  bMaxPacketSize0        64
  idVendor           0x413c Dell Computer Corp.
  idProduct          0x81b3
  bcdDevice            0.06
  iManufacturer           1 Sierra Wireless, Incorporated
  iProduct                2 Dell Wireless 5809e Gobi™ 4G HSPA+ Mobile Broadband Card
  iSerial                 3
  bNumConfigurations      2

Signed-off-by: Patrik Halfar <patrik_halfar@halfarit.cz>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/qcserial.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 514fa91cf74e..f1eb03eed5cf 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -163,6 +163,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81a8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b1)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */

[PATCH 3.16.y-ckt 098/142] USB: cp210x: Add ID for Parrot NMEA GPS Flight Recorder

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Vittorio Alfieri <vittorio88@gmail.com>

commit 3c4c615d70c8cbdc8ba8c79ed702640930652a79 upstream.

The Parrot NMEA GPS Flight Recorder is a USB composite device
consisting of hub, flash storage, and cp210x usb to serial chip.
It is an accessory to the mass-produced Parrot AR Drone 2.
The device emits standard NMEA messages which make the it compatible
with NMEA compatible software. It was tested using gpsd version 3.11-3
as an NMEA interpreter and using the official Parrot Flight Recorder.

Signed-off-by: Vittorio Alfieri <vittorio88@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/cp210x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 21bf168981f9..922723edd6b0 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -164,6 +164,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */
 	{ USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
 	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
+	{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
 	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */

[PATCH 3.16.y-ckt 099/142] USB: serial: option: add support for Telit LE922 PID 0x1045

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Daniele Palmas <dnlplm@gmail.com>

commit 5deef5551c77e488922cc4bf4bc76df63be650d0 upstream.

This patch adds support for 0x1045 PID of Telit LE922.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/option.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 46305ca6158e..b5839df3e4a1 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -273,6 +273,7 @@ static void option_instat_callback(struct urb *urb);
 #define TELIT_PRODUCT_UE910_V2			0x1012
 #define TELIT_PRODUCT_LE922_USBCFG0		0x1042
 #define TELIT_PRODUCT_LE922_USBCFG3		0x1043
+#define TELIT_PRODUCT_LE922_USBCFG5		0x1045
 #define TELIT_PRODUCT_LE920			0x1200
 #define TELIT_PRODUCT_LE910			0x1201
 
@@ -1202,6 +1203,8 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3),
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
 		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),

[PATCH 3.16.y-ckt 100/142] USB: serial: option: add support for Quectel UC20

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Yegor Yefremov <yegorslists@googlemail.com>

commit c0992d0f54847d0d1d85c60fcaa054f175ab1ccd upstream.

Add support for Quectel UC20 and blacklist the QMI interface.

Signed-off-by: Yegor Yefremov <yegorslists@googlemail.com>
[johan: amend commit message ]
Signed-off-by: Johan Hovold <johan@kernel.org>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/option.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index b5839df3e4a1..5396e8bfeb6b 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1152,6 +1152,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC73xx */
 	{ USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x9041, 0xff),
 	  .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC7305/MC7355 */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),

[PATCH 3.16.y-ckt 101/142] ALSA: seq: oss: Don't drain at closing a client

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 197b958c1e76a575d77038cc98b4bebc2134279f upstream.

The OSS sequencer client tries to drain the pending events at
releasing.  Unfortunately, as spotted by syzkaller fuzzer, this may
lead to an unkillable process state when the event has been queued at
the far future.  Since the process being released can't be signaled
any longer, it remains and waits for the echo-back event in that far
future.

Back to history, the draining feature was implemented at the time we
misinterpreted POSIX definition for blocking file operation.
Actually, such a behavior is superfluous at release, and we should
just release the device as is instead of keeping it up forever.

This patch just removes the draining call that may block the release
for too long time unexpectedly.

BugLink: http://lkml.kernel.org/r/CACT4Y+Y4kD-aBGj37rf-xBw9bH3GMU6P+MYg4W1e-s-paVD2pg@mail.gmail.com
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/seq/oss/seq_oss.c        |  2 --
 sound/core/seq/oss/seq_oss_device.h |  1 -
 sound/core/seq/oss/seq_oss_init.c   | 16 ----------------
 3 files changed, 19 deletions(-)

diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 16d42679e43f..bb032d7593e3 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -144,8 +144,6 @@ odev_release(struct inode *inode, struct file *file)
 	if ((dp = file->private_data) == NULL)
 		return 0;
 
-	snd_seq_oss_drain_write(dp);
-
 	mutex_lock(&register_mutex);
 	snd_seq_oss_release(dp);
 	mutex_unlock(&register_mutex);
diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h
index b43924325249..d7b4d016b547 100644
--- a/sound/core/seq/oss/seq_oss_device.h
+++ b/sound/core/seq/oss/seq_oss_device.h
@@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co
 unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait);
 
 void snd_seq_oss_reset(struct seq_oss_devinfo *dp);
-void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp);
 
 /* */
 void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time);
diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c
index beea8c861f49..acefecb1a47a 100644
--- a/sound/core/seq/oss/seq_oss_init.c
+++ b/sound/core/seq/oss/seq_oss_init.c
@@ -441,22 +441,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp)
 
 
 /*
- * Wait until the queue is empty (if we don't have nonblock)
- */
-void
-snd_seq_oss_drain_write(struct seq_oss_devinfo *dp)
-{
-	if (! dp->timer->running)
-		return;
-	if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) &&
-	    dp->writeq) {
-		while (snd_seq_oss_writeq_sync(dp->writeq))
-			;
-	}
-}
-
-
-/*
  * reset sequencer devices
  */
 void

[PATCH 3.16.y-ckt 102/142] drm/ast: Fix incorrect register check for DRAM width

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Timothy Pearson <tpearson@raptorengineeringinc.com>

commit 2d02b8bdba322b527c5f5168ce1ca10c2d982a78 upstream.

During DRAM initialization on certain ASpeed devices, an incorrect
bit (bit 10) was checked in the "SDRAM Bus Width Status" register
to determine DRAM width.

Query bit 6 instead in accordance with the Aspeed AST2050 datasheet v1.05.

Signed-off-by: Timothy Pearson <tpearson@raptorengineeringinc.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/ast/ast_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 0dfefbf929a3..cb6d626dad02 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -182,7 +182,7 @@ static int ast_get_dram_info(struct drm_device *dev)
 	} while (ast_read32(ast, 0x10000) != 0x01);
 	data = ast_read32(ast, 0x10004);
 
-	if (data & 0x400)
+	if (data & 0x40)
 		ast->dram_bus_width = 16;
 	else
 		ast->dram_bus_width = 32;

[PATCH 3.16.y-ckt 103/142] USB: qcserial: add Sierra Wireless EM74xx device ID

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>

commit 04fdbc825ffc02fb098964b92de802fff44e73fd upstream.

The MC74xx and EM74xx modules use different IDs by default, according
to the Lenovo EM7455 driver for Windows.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/qcserial.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index f1eb03eed5cf..f0a2ad15a992 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -155,8 +155,10 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
-	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx/EM74xx */
-	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx/EM74xx */
+	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
+	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
+	{DEVICE_SWI(0x1199, 0x9078)},	/* Sierra Wireless EM74xx */
+	{DEVICE_SWI(0x1199, 0x9079)},	/* Sierra Wireless EM74xx */
 	{DEVICE_SWI(0x413c, 0x81a2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a4)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */

[PATCH 3.16.y-ckt 104/142] drm/radeon/pm: update current crtc info after setting the powerstate

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit 5e031d9fe8b0741f11d49667dfc3ebf5454121fd upstream.

On CI, we need to see if the number of crtcs changes to determine
whether or not we need to upload the mclk table again.  In practice
we don't currently upload the mclk table again after the initial load.
The only reason you would would be to add new states, e.g., for
arbitrary mclk setting which is not currently supported.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_pm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 97e1a70df5a9..a05d569fa038 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -937,10 +937,6 @@ force:
 	/* update display watermarks based on new power state */
 	radeon_bandwidth_update(rdev);
 
-	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
-	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
-	rdev->pm.dpm.single_display = single_display;
-
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
 		struct radeon_ring *ring = &rdev->ring[i];
@@ -959,6 +955,10 @@ force:
 	/* update displays */
 	radeon_dpm_display_configuration_changed(rdev);
 
+	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
+	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
+	rdev->pm.dpm.single_display = single_display;
+
 	if (rdev->asic->dpm.force_performance_level) {
 		if (rdev->pm.dpm.thermal_active) {
 			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;

[PATCH 3.16.y-ckt 105/142] PM / sleep / x86: Fix crash on graph trace through x86 suspend

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Todd E Brandt <todd.e.brandt@linux.intel.com>

commit 92f9e179a702a6adbc11e2fedc76ecd6ffc9e3f7 upstream.

Pause/unpause graph tracing around do_suspend_lowlevel as it has
inconsistent call/return info after it jumps to the wakeup vector.
The graph trace buffer will otherwise become misaligned and
may eventually crash and hang on suspend.

To reproduce the issue and test the fix:
Run a function_graph trace over suspend/resume and set the graph
function to suspend_devices_and_enter. This consistently hangs the
system without this fix.

Signed-off-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/kernel/acpi/sleep.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 31368207837c..8255d2fe8cfa 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
 
+#include <linux/ftrace.h>
 #include "../../realmode/rm/wakeup.h"
 #include "sleep.h"
 
@@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void)
        saved_magic = 0x123456789abcdef0L;
 #endif /* CONFIG_64BIT */
 
+	/*
+	 * Pause/unpause graph tracing around do_suspend_lowlevel as it has
+	 * inconsistent call/return info after it jumps to the wakeup vector.
+	 */
+	pause_graph_tracing();
 	do_suspend_lowlevel();
+	unpause_graph_tracing();
 	return 0;
 }
 

[PATCH 3.16.y-ckt 106/142] ALSA: hda - Fix mic issues on Acer Aspire E1-472

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Simon South <simon@simonsouth.com>

commit 02322ac9dee9aff8d8862e8d6660ebe102f492ea upstream.

This patch applies the microphone-related fix created for the Acer
Aspire E1-572 to the E1-472 as well, as it uses the same Realtek ALC282
CODEC and demonstrates the same issues.

This patch allows an external, headset microphone to be used and limits
the gain on the (quite noisy) internal microphone.

Signed-off-by: Simon South <simon@simonsouth.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@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 437688036c2a..d7e12d704196 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4853,6 +4853,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC),
+	SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),

[PATCH 3.16.y-ckt 107/142] MIPS: traps: Fix SIGFPE information leak from `do_ov' and `do_trap_or_bp'

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Maciej W. Rozycki" <macro@imgtec.com>

commit e723e3f7f9591b79e8c56b3d7c5a204a9c571b55 upstream.

Avoid sending a partially initialised `siginfo_t' structure along SIGFPE
signals issued from `do_ov' and `do_trap_or_bp', leading to information
leaking from the kernel stack.

Signed-off-by: Maciej W. Rozycki <macro@imgtec.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/mips/kernel/traps.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 027fefba8b96..bdf9139fd92b 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -691,15 +691,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
 asmlinkage void do_ov(struct pt_regs *regs)
 {
 	enum ctx_state prev_state;
-	siginfo_t info;
+	siginfo_t info = {
+		.si_signo = SIGFPE,
+		.si_code = FPE_INTOVF,
+		.si_addr = (void __user *)regs->cp0_epc,
+	};
 
 	prev_state = exception_enter();
 	die_if_kernel("Integer overflow", regs);
 
-	info.si_code = FPE_INTOVF;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *) regs->cp0_epc;
 	force_sig_info(SIGFPE, &info, current);
 	exception_exit(prev_state);
 }
@@ -802,7 +802,7 @@ out:
 static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	const char *str)
 {
-	siginfo_t info;
+	siginfo_t info = { 0 };
 	char b[40];
 
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -830,7 +830,6 @@ static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 		else
 			info.si_code = FPE_INTOVF;
 		info.si_signo = SIGFPE;
-		info.si_errno = 0;
 		info.si_addr = (void __user *) regs->cp0_epc;
 		force_sig_info(SIGFPE, &info, current);
 		break;

[PATCH 3.16.y-ckt 108/142] ubi: Fix out of bounds write in volume update code

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Richard Weinberger <richard@nod.at>

commit e4f6daac20332448529b11f09388f1d55ef2084c upstream.

ubi_start_leb_change() allocates too few bytes.
ubi_more_leb_change_data() will write up to req->upd_bytes +
ubi->min_io_size bytes.

Signed-off-by: Richard Weinberger <richard@nod.at>
Reviewed-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/mtd/ubi/upd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index 2a1b6e037e1a..0134ba32a057 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 	vol->changing_leb = 1;
 	vol->ch_lnum = req->lnum;
 
-	vol->upd_buf = vmalloc(req->bytes);
+	vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size));
 	if (!vol->upd_buf)
 		return -ENOMEM;
 

[PATCH 3.16.y-ckt 109/142] gpio: rcar: Add Runtime PM handling for interrupts

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Geert Uytterhoeven <geert+renesas@glider.be>

commit b26a719bdba9aa926ceaadecc66e07623d2b8a53 upstream.

The R-Car GPIO driver handles Runtime PM for requested GPIOs only.

When using a GPIO purely as an interrupt source, no Runtime PM handling
is done, and the GPIO module's clock may not be enabled.

To fix this:
  - Add .irq_request_resources() and .irq_release_resources() callbacks
    to handle Runtime PM when an interrupt is requested,
  - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM
    when e.g. disabling/enabling an interrupt, or configuring the
    interrupt type.

Fixes: d5c3d84657db57bd "net: phy: Avoid polling PHY with PHY_IGNORE_INTERRUPTS"
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
[ luis: backported to 3.16:
  - use gpio_to_priv() instead of gpiochip_get_data()
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpio/gpio-rcar.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index c3ea3e9e3d14..b97094ce448f 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -186,6 +186,44 @@ static inline struct gpio_rcar_priv *gpio_to_priv(struct gpio_chip *chip)
 	return container_of(chip, struct gpio_rcar_priv, gpio_chip);
 }
 
+static void gpio_rcar_irq_bus_lock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpio_to_priv(gc);
+
+	pm_runtime_get_sync(&p->pdev->dev);
+}
+
+static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpio_to_priv(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
+
+static int gpio_rcar_irq_request_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpio_to_priv(gc);
+	int error;
+
+	error = pm_runtime_get_sync(&p->pdev->dev);
+	if (error < 0)
+		return error;
+
+	return 0;
+}
+
+static void gpio_rcar_irq_release_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpio_to_priv(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
 static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 						       unsigned int gpio,
 						       bool output)
@@ -414,6 +452,10 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	irq_chip->irq_mask = gpio_rcar_irq_disable;
 	irq_chip->irq_unmask = gpio_rcar_irq_enable;
 	irq_chip->irq_set_type = gpio_rcar_irq_set_type;
+	irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock;
+	irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock;
+	irq_chip->irq_request_resources = gpio_rcar_irq_request_resources;
+	irq_chip->irq_release_resources = gpio_rcar_irq_release_resources;
 	irq_chip->flags	= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_SET_TYPE_MASKED
 			 | IRQCHIP_MASK_ON_SUSPEND;
 

[PATCH 3.16.y-ckt 110/142] IB/core: Use GRH when the path hop-limit > 0

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Or Gerlitz <ogerlitz@mellanox.com>

commit 11d8d645343efba0c975aefe7c2cf3b33c836c75 upstream.

According to IBTA spec v1.3 section 12.7.19, QPs should use GRH when
the path returned by the SA has hop-limit > 0. Currently, we do that
only for the > 1 case, fix that.

Fixes: 6d969a471ba1 ('IB/sa: Add ib_init_ah_from_path()')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/infiniband/core/sa_query.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 233eaf541f55..3ca38f9ad26a 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -542,7 +542,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 
 	force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET;
 
-	if (rec->hop_limit > 1 || force_grh) {
+	if (rec->hop_limit > 0 || force_grh) {
 		ah_attr->ah_flags = IB_AH_GRH;
 		ah_attr->grh.dgid = rec->dgid;
 

[PATCH 3.16.y-ckt 111/142] wext: fix message delay/ordering

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Johannes Berg <johannes.berg@intel.com>

commit 8bf862739a7786ae72409220914df960a0aa80d8 upstream.

Beniamino reported that he was getting an RTM_NEWLINK message for a
given interface, after the RTM_DELLINK for it. It turns out that the
message is a wireless extensions message, which was sent because the
interface had been connected and disconnection while it was deleted
caused a wext message.

For its netlink messages, wext uses RTM_NEWLINK, but the message is
without all the regular rtnetlink attributes, so "ip monitor link"
prints just rudimentary information:

5: wlan1: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default
    link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff
Deleted 5: wlan1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default
    link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff
5: wlan1: <BROADCAST,MULTICAST,UP>
    link/ether
(from my hwsim reproduction)

This can cause userspace to get confused since it doesn't expect an
RTM_NEWLINK message after RTM_DELLINK.

The reason for this is that wext schedules a worker to send out the
messages, and the scheduling delay can cause the messages to get out
to userspace in different order.

To fix this, have wext register a netdevice notifier and flush out
any pending messages when netdevice state changes. This fixes any
ordering whenever the original message wasn't sent by a notifier
itself.

Reported-by: Beniamino Galvani <bgalvani@redhat.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/wireless/wext-core.c | 51 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index c8717c1d082e..87dd619fb2e9 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -342,6 +342,39 @@ static const int compat_event_type_size[] = {
 
 /* IW event code */
 
+static void wireless_nlevent_flush(void)
+{
+	struct sk_buff *skb;
+	struct net *net;
+
+	ASSERT_RTNL();
+
+	for_each_net(net) {
+		while ((skb = skb_dequeue(&net->wext_nlevents)))
+			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
+				    GFP_KERNEL);
+	}
+}
+
+static int wext_netdev_notifier_call(struct notifier_block *nb,
+				     unsigned long state, void *ptr)
+{
+	/*
+	 * When a netdev changes state in any way, flush all pending messages
+	 * to avoid them going out in a strange order, e.g. RTM_NEWLINK after
+	 * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close()
+	 * or similar - all of which could otherwise happen due to delays from
+	 * schedule_work().
+	 */
+	wireless_nlevent_flush();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block wext_netdev_notifier = {
+	.notifier_call = wext_netdev_notifier_call,
+};
+
 static int __net_init wext_pernet_init(struct net *net)
 {
 	skb_queue_head_init(&net->wext_nlevents);
@@ -360,7 +393,12 @@ static struct pernet_operations wext_pernet_ops = {
 
 static int __init wireless_nlevent_init(void)
 {
-	return register_pernet_subsys(&wext_pernet_ops);
+	int err = register_pernet_subsys(&wext_pernet_ops);
+
+	if (err)
+		return err;
+
+	return register_netdevice_notifier(&wext_netdev_notifier);
 }
 
 subsys_initcall(wireless_nlevent_init);
@@ -368,17 +406,8 @@ subsys_initcall(wireless_nlevent_init);
 /* Process events generated by the wireless layer or the driver. */
 static void wireless_nlevent_process(struct work_struct *work)
 {
-	struct sk_buff *skb;
-	struct net *net;
-
 	rtnl_lock();
-
-	for_each_net(net) {
-		while ((skb = skb_dequeue(&net->wext_nlevents)))
-			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
-				    GFP_KERNEL);
-	}
-
+	wireless_nlevent_flush();
 	rtnl_unlock();
 }
 

[PATCH 3.16.y-ckt 112/142] cfg80211/wext: fix message ordering

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Johannes Berg <johannes.berg@intel.com>

commit cb150b9d23be6ee7f3a0fff29784f1c5b5ac514d upstream.

Since cfg80211 frequently takes actions from its netdev notifier
call, wireless extensions messages could still be ordered badly
since the wext netdev notifier, since wext is built into the
kernel, runs before the cfg80211 netdev notifier. For example,
the following can happen:

5: wlan1: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN group default
    link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff
5: wlan1: <BROADCAST,MULTICAST,UP>
    link/ether

when setting the interface down causes the wext message.

To also fix this, export the wireless_nlevent_flush() function
and also call it from the cfg80211 notifier.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/net/iw_handler.h | 6 ++++++
 net/wireless/core.c      | 2 ++
 net/wireless/wext-core.c | 3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index a830b01baba4..e8aa72eaded5 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length);
 /* Send a single event to user space */
 void wireless_send_event(struct net_device *dev, unsigned int cmd,
 			 union iwreq_data *wrqu, const char *extra);
+#ifdef CONFIG_WEXT_CORE
+/* flush all previous wext events - if work is done from netdev notifiers */
+void wireless_nlevent_flush(void);
+#else
+static inline void wireless_nlevent_flush(void) {}
+#endif
 
 /* We may need a function to send a stream of events to user space.
  * More on that later... */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index a1c40654dd9b..59bc2ff8cfc5 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1048,6 +1048,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		return NOTIFY_DONE;
 	}
 
+	wireless_nlevent_flush();
+
 	return NOTIFY_OK;
 }
 
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 87dd619fb2e9..b50ee5d622e1 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -342,7 +342,7 @@ static const int compat_event_type_size[] = {
 
 /* IW event code */
 
-static void wireless_nlevent_flush(void)
+void wireless_nlevent_flush(void)
 {
 	struct sk_buff *skb;
 	struct net *net;
@@ -355,6 +355,7 @@ static void wireless_nlevent_flush(void)
 				    GFP_KERNEL);
 	}
 }
+EXPORT_SYMBOL_GPL(wireless_nlevent_flush);
 
 static int wext_netdev_notifier_call(struct notifier_block *nb,
 				     unsigned long state, void *ptr)

[PATCH 3.16.y-ckt 113/142] mac80211: fix use of uninitialised values in RX aggregation

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Chris Bainbridge <chris.bainbridge@gmail.com>

commit f39ea2690bd61efec97622c48323f40ed6e16317 upstream.

Use kzalloc instead of kmalloc for struct tid_ampdu_rx to
initialize the "removed" field (all others are initialized
manually). That fixes:

UBSAN: Undefined behaviour in net/mac80211/rx.c:932:29
load of value 2 is not a valid value for type '_Bool'
CPU: 3 PID: 1134 Comm: kworker/u16:7 Not tainted 4.5.0-rc1+ #265
Workqueue: phy0 rt2x00usb_work_rxdone
 0000000000000004 ffff880254a7ba50 ffffffff8181d866 0000000000000007
 ffff880254a7ba78 ffff880254a7ba68 ffffffff8188422d ffffffff8379b500
 ffff880254a7bab8 ffffffff81884747 0000000000000202 0000000348620032
Call Trace:
 [<ffffffff8181d866>] dump_stack+0x45/0x5f
 [<ffffffff8188422d>] ubsan_epilogue+0xd/0x40
 [<ffffffff81884747>] __ubsan_handle_load_invalid_value+0x67/0x70
 [<ffffffff82227b4d>] ieee80211_sta_reorder_release.isra.16+0x5ed/0x730
 [<ffffffff8222ca14>] ieee80211_prepare_and_rx_handle+0xd04/0x1c00
 [<ffffffff8222db03>] __ieee80211_rx_handle_packet+0x1f3/0x750
 [<ffffffff8222e4a7>] ieee80211_rx_napi+0x447/0x990

While at it, convert to use sizeof(*tid_agg_rx) instead.

Fixes: 788211d81bfdf ("mac80211: fix RX A-MPDU session reorder timer deletion")
Signed-off-by: Chris Bainbridge <chris.bainbridge@gmail.com>
[reword commit message, use sizeof(*tid_agg_rx)]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/mac80211/agg-rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 9608c6e65887..07706bec2e3a 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -294,7 +294,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local,
 	}
 
 	/* prepare A-MPDU MLME for Rx aggregation */
-	tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL);
+	tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL);
 	if (!tid_agg_rx)
 		goto end;
 

[PATCH 3.16.y-ckt 114/142] mac80211: minstrel_ht: set default tx aggregation timeout to 0

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Felix Fietkau <nbd@openwrt.org>

commit 7a36b930e6ed4702c866dc74a5ad07318a57c688 upstream.

The value 5000 was put here with the addition of the timeout field to
ieee80211_start_tx_ba_session. It was originally added in mac80211 to
save resources for drivers like iwlwifi, which only supports a limited
number of concurrent aggregation sessions.

Since iwlwifi does not use minstrel_ht and other drivers don't need
this, 0 is a better default - especially since there have been
recent reports of aggregation setup related issues reproduced with
ath9k. This should improve stability without causing any adverse
effects.

Acked-by: Avery Pennarun <apenwarr@gmail.com>
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/mac80211/rc80211_minstrel_ht.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 85c1e74b7714..d4144f8630ef 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -464,7 +464,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 	if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO)
 		return;
 
-	ieee80211_start_tx_ba_session(pubsta, tid, 5000);
+	ieee80211_start_tx_ba_session(pubsta, tid, 0);
 }
 
 static void

[PATCH 3.16.y-ckt 115/142] can: gs_usb: fixed disconnect bug by removing erroneous use of kfree()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Maximilain Schneider <max@schneidersoft.net>

commit e9a2d81b1761093386a0bb8a4f51642ac785ef63 upstream.

gs_destroy_candev() erroneously calls kfree() on a struct gs_can *, which is
allocated through alloc_candev() and should instead be freed using
free_candev() alone.

The inappropriate use of kfree() causes the kernel to hang when
gs_destroy_candev() is called.

Only the struct gs_usb * which is allocated through kzalloc() should be freed
using kfree() when the device is disconnected.

Signed-off-by: Maximilian Schneider <max@schneidersoft.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/can/usb/gs_usb.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 04b0f84612f0..047b63caa3b7 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -825,9 +825,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface
 static void gs_destroy_candev(struct gs_can *dev)
 {
 	unregister_candev(dev->netdev);
-	free_candev(dev->netdev);
 	usb_kill_anchored_urbs(&dev->tx_submitted);
-	kfree(dev);
+	free_candev(dev->netdev);
 }
 
 static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
@@ -910,12 +909,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 	for (i = 0; i < icount; i++) {
 		dev->canch[i] = gs_make_candev(i, intf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
+			/* save error code to return later */
+			rc = PTR_ERR(dev->canch[i]);
+
 			/* on failure destroy previously created candevs */
 			icount = i;
-			for (i = 0; i < icount; i++) {
+			for (i = 0; i < icount; i++)
 				gs_destroy_candev(dev->canch[i]);
-				dev->canch[i] = NULL;
-			}
+
+			usb_kill_anchored_urbs(&dev->rx_submitted);
 			kfree(dev);
 			return rc;
 		}
@@ -936,16 +938,12 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		return;
 	}
 
-	for (i = 0; i < GS_MAX_INTF; i++) {
-		struct gs_can *can = dev->canch[i];
-
-		if (!can)
-			continue;
-
-		gs_destroy_candev(can);
-	}
+	for (i = 0; i < GS_MAX_INTF; i++)
+		if (dev->canch[i])
+			gs_destroy_candev(dev->canch[i]);
 
 	usb_kill_anchored_urbs(&dev->rx_submitted);
+	kfree(dev);
 }
 
 static const struct usb_device_id gs_usb_table[] = {

[PATCH 3.16.y-ckt 116/142] ASoC: wm8958: Fix enum ctl accesses in a wrong type

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit d0784829ae3b0beeb69b476f017d5c8a2eb95198 upstream.

"MBC Mode", "VSS Mode", "VSS HPF Mode" and "Enhanced EQ Mode" ctls in
wm8958 codec driver are enum, while the current driver accesses
wrongly via value.integer.value[].  They have to be via
value.enumerated.item[] instead.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/soc/codecs/wm8958-dsp2.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b2ebb104d879..418a768e670c 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */

[PATCH 3.16.y-ckt 117/142] ASoC: wm8994: Fix enum ctl accesses in a wrong type

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 8019c0b37cd5a87107808300a496388b777225bf upstream.

The DRC Mode like "AIF1DRC1 Mode" and EQ Mode like "AIF1.1 EQ Mode" in
wm8994 codec driver are enum ctls, while the current driver accesses
wrongly via value.integer.value[].  They have to be via
value.enumerated.item[] instead.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/soc/codecs/wm8994.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index d54c10e4fa90..e1bb8b036909 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -360,7 +360,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int drc = wm8994_get_drc(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (drc < 0)
 		return drc;
@@ -467,7 +467,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int block = wm8994_get_retune_mobile_block(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (block < 0)
 		return block;

[PATCH 3.16.y-ckt 118/142] ASoC: wm_adsp: Fix enum ctl accesses in a wrong type

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Takashi Iwai <tiwai@suse.de>

commit 15c665700bf6f4543f003ac0fbb1e9ec692e93f2 upstream.

The firmware ctls like "DSP1 Firmware" in wm_adsp codec driver are
enum, while the current driver accesses wrongly via
value.integer.value[].  They have to be via value.enumerated.item[]
instead.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/soc/codecs/wm_adsp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 051350052d62..51bdb4765b41 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -246,7 +246,7 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	struct wm_adsp *adsp = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = adsp[e->shift_l].fw;
+	ucontrol->value.enumerated.item[0] = adsp[e->shift_l].fw;
 
 	return 0;
 }
@@ -258,16 +258,16 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	struct wm_adsp *adsp = snd_soc_codec_get_drvdata(codec);
 
-	if (ucontrol->value.integer.value[0] == adsp[e->shift_l].fw)
+	if (ucontrol->value.enumerated.item[0] == adsp[e->shift_l].fw)
 		return 0;
 
-	if (ucontrol->value.integer.value[0] >= WM_ADSP_NUM_FW)
+	if (ucontrol->value.enumerated.item[0] >= WM_ADSP_NUM_FW)
 		return -EINVAL;
 
 	if (adsp[e->shift_l].running)
 		return -EBUSY;
 
-	adsp[e->shift_l].fw = ucontrol->value.integer.value[0];
+	adsp[e->shift_l].fw = ucontrol->value.enumerated.item[0];
 
 	return 0;
 }

[PATCH 3.16.y-ckt 119/142] target: Drop incorrect ABORT_TASK put for completed commands

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Nicholas Bellinger <nab@linux-iscsi.org>

commit 7f54ab5ff52fb0b91569bc69c4a6bc5cac1b768d upstream.

This patch fixes a recent ABORT_TASK regression associated
with commit febe562c, where a left-over target_put_sess_cmd()
would still be called when __target_check_io_state() detected
a command has already been completed, and explicit ABORT must
be avoided.

Note commit febe562c dropped the local kref_get_unless_zero()
check in core_tmr_abort_task(), but did not drop this extra
corresponding target_put_sess_cmd() in the failure path.

So go ahead and drop this now bogus target_put_sess_cmd(),
and avoid this potential use-after-free.

Reported-by: Dan Lane <dracodan@gmail.com>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/target/target_core_tmr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index ebdbaaf6111d..033a59cd6c70 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -186,7 +186,6 @@ void core_tmr_abort_task(
 
 		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-			target_put_sess_cmd(se_sess, se_cmd);
 			goto out;
 		}
 

[PATCH 3.16.y-ckt 120/142] Revert "drm/radeon: call hpd_irq_event on resume"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 256faedcfd646161477d47a1a78c32a562d2e845 upstream.

This reverts commit dbb17a21c131eca94eb31136eee9a7fe5aff00d9.

It turns out that commit can cause problems for systems with multiple
GPUs, and causes X to hang on at least a HP Pavilion dv7 with hybrid
graphics.

This got noticed originally in 4.4.4, where this patch had already
gotten back-ported, but 4.5-rc7 was verified to have the same problem.

Alexander Deucher says:
 "It looks like you have a muxed system so I suspect what's happening is
  that one of the display is being reported as connected for both the
  IGP and the dGPU and then the desktop environment gets confused or
  there some sort problem in the detect functions since the mux is not
  switched to the dGPU.  I don't see an easy fix unless Dave has any
  ideas.  I'd say just revert for now"

Reported-by: Jörg-Volker Peetz <jvpeetz@web.de>
Acked-by: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: Dave Airlie <airlied@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_device.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index f7296ca6510c..ca470fb17aa4 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1649,7 +1649,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	drm_kms_helper_poll_enable(dev);
-	drm_helper_hpd_irq_event(dev);
 
 	/* set the power state here in case we are a PX system or headless */
 	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)

[PATCH 3.16.y-ckt 121/142] KVM: PPC: Book3S HV: Sanitize special-purpose register values on guest exit

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Paul Mackerras <paulus@samba.org>

commit ccec44563b18a0ce90e2d4f332784b3cb25c8e9c upstream.

Thomas Huth discovered that a guest could cause a hard hang of a
host CPU by setting the Instruction Authority Mask Register (IAMR)
to a suitable value.  It turns out that this is because when the
code was added to context-switch the new special-purpose registers
(SPRs) that were added in POWER8, we forgot to add code to ensure
that they were restored to a sane value on guest exit.

This adds code to set those registers where a bad value could
compromise the execution of the host kernel to a suitable neutral
value on guest exit.

Fixes: b005255e12a3
Reported-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6fafff75f24a..f3197994b733 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1280,6 +1280,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6, VCPU_ACOP(r9)
 	stw	r7, VCPU_GUEST_PID(r9)
 	std	r8, VCPU_WORT(r9)
+	/*
+	 * Restore various registers to 0, where non-zero values
+	 * set by the guest could disrupt the host.
+	 */
+	li	r0, 0
+	mtspr	SPRN_IAMR, r0
+	mtspr	SPRN_CIABR, r0
+	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_TCSCR, r0
+	mtspr	SPRN_WORT, r0
+	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
+	li	r0, 1
+	sldi	r0, r0, 31
+	mtspr	SPRN_MMCRS, r0
 8:
 
 	/* Save and reset AMR and UAMOR before turning on the MMU */

[PATCH 3.16.y-ckt 122/142] KVM: VMX: disable PEBS before a guest entry

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit 7099e2e1f4d9051f31bbfa5803adf954bb5d76ef upstream.

Linux guests on Haswell (and also SandyBridge and Broadwell, at least)
would crash if you decided to run a host command that uses PEBS, like
  perf record -e 'cpu/mem-stores/pp' -a

This happens because KVM is using VMX MSR switching to disable PEBS, but
SDM [2015-12] 18.4.4.4 Re-configuring PEBS Facilities explains why it
isn't safe:
  When software needs to reconfigure PEBS facilities, it should allow a
  quiescent period between stopping the prior event counting and setting
  up a new PEBS event. The quiescent period is to allow any latent
  residual PEBS records to complete its capture at their previously
  specified buffer address (provided by IA32_DS_AREA).

There might not be a quiescent period after the MSR switch, so a CPU
ends up using host's MSR_IA32_DS_AREA to access an area in guest's
memory.  (Or MSR switching is just buggy on some models.)

The guest can learn something about the host this way:
If the guest doesn't map address pointed by MSR_IA32_DS_AREA, it results
in #PF where we leak host's MSR_IA32_DS_AREA through CR2.

After that, a malicious guest can map and configure memory where
MSR_IA32_DS_AREA is pointing and can therefore get an output from
host's tracing.

This is not a critical leak as the host must initiate with PEBS tracing
and I have not been able to get a record from more than one instruction
before vmentry in vmx_vcpu_run() (that place has most registers already
overwritten with guest's).

We could disable PEBS just few instructions before vmentry, but
disabling it earlier shouldn't affect host tracing too much.
We also don't need to switch MSR_IA32_PEBS_ENABLE on VMENTRY, but that
optimization isn't worth its code, IMO.

(If you are implementing PEBS for guests, be sure to handle the case
 where both host and guest enable PEBS, because this patch doesn't.)

Fixes: 26a4f3c08de4 ("perf/x86: disable PEBS on a guest entry.")
Reported-by: Jiří Olša <jolsa@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/kvm/vmx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d1d7086f0e9b..e7cd4c833c40 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1574,6 +1574,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			return;
 		}
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		/* PEBS needs a quiescent period after being disabled (to write
+		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
+		 * provide that period, so a CPU could write host's record into
+		 * guest's memory.
+		 */
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
 	for (i = 0; i < m->nr; ++i)

[PATCH 3.16.y-ckt 123/142] Revert "drm/radeon/pm: adjust display configuration after powerstate"

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit d74e766e1916d0e09b86e4b5b9d0f819628fd546 upstream.

This reverts commit 39d4275058baf53e89203407bf3841ff2c74fa32.

This caused a regression on some older hardware.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=113891

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/radeon/radeon_pm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index a05d569fa038..afd4adaf9f2d 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -936,6 +936,8 @@ force:
 
 	/* update display watermarks based on new power state */
 	radeon_bandwidth_update(rdev);
+	/* update displays */
+	radeon_dpm_display_configuration_changed(rdev);
 
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
@@ -952,9 +954,6 @@ force:
 
 	radeon_dpm_post_set_power_state(rdev);
 
-	/* update displays */
-	radeon_dpm_display_configuration_changed(rdev);
-
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
 	rdev->pm.dpm.single_display = single_display;

[PATCH 3.16.y-ckt 124/142] tcp: convert cached rtt from usec to jiffies when feeding initial rto

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>

commit 9bdfb3b79e61c60e1a3e2dc05ad164528afa6b8a upstream.

Currently it's converted into msecs, thus HZ=1000 intact.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/tcp_metrics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4fe041805989..600add256464 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -550,7 +550,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from

[PATCH 3.16.y-ckt 125/142] net/mlx4_core: Allow resetting VF admin mac to zero

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jack Morgenstein <jackm@dev.mellanox.co.il>

commit 6e5224224faa50ec4c8949dcefadf895e565f0d1 upstream.

The VF administrative mac addresses (stored in the PF driver) are
initialized to zero when the PF driver starts up.

These addresses may be modified in the PF driver through ndo calls
initiated by iproute2 or libvirt.

While we allow the PF/host to change the VF admin mac address from zero
to a valid unicast mac, we do not allow restoring the VF admin mac to
zero. We currently only allow changing this mac to a different unicast mac.

This leads to problems when libvirt scripts are used to deal with
VF mac addresses, and libvirt attempts to revoke the mac so this
host will not use it anymore.

Fix this by allowing resetting a VF administrative MAC back to zero.

Fixes: 8f7ba3ca12f6 ('net/mlx4: Add set VF mac address support')
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reported-by: Moshe Levi <moshele@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 1f588195fe9f..50b1f909ce0d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2244,7 +2244,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 	struct mlx4_en_dev *mdev = en_priv->mdev;
 	u64 mac_u64 = mlx4_mac_to_u64(mac);
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);

[PATCH 3.16.y-ckt 126/142] mld, igmp: Fix reserved tailroom calculation

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Benjamin Poirier <bpoirier@suse.com>

commit 1837b2e2bcd23137766555a63867e649c0b637f0 upstream.

The current reserved_tailroom calculation fails to take hlen and tlen into
account.

skb:
[__hlen__|__data____________|__tlen___|__extra__]
^                                               ^
head                                            skb_end_offset

In this representation, hlen + data + tlen is the size passed to alloc_skb.
"extra" is the extra space made available in __alloc_skb because of
rounding up by kmalloc. We can reorder the representation like so:

[__hlen__|__data____________|__extra__|__tlen___]
^                                               ^
head                                            skb_end_offset

The maximum space available for ip headers and payload without
fragmentation is min(mtu, data + extra). Therefore,
reserved_tailroom
= data + extra + tlen - min(mtu, data + extra)
= skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen)
= skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen)

Compare the second line to the current expression:
reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset)
and we can see that hlen and tlen are not taken into account.

The min() in the third line can be expanded into:
if mtu < skb_tailroom - tlen:
	reserved_tailroom = skb_tailroom - mtu
else:
	reserved_tailroom = tlen

Depending on hlen, tlen, mtu and the number of multicast address records,
the current code may output skbs that have less tailroom than
dev->needed_tailroom or it may output more skbs than needed because not all
space available is used.

Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/skbuff.h | 24 ++++++++++++++++++++++++
 net/ipv4/igmp.c        |  3 +--
 net/ipv6/mcast.c       |  3 +--
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c046cb92172e..629f519224ee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1671,6 +1671,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 static inline void skb_reset_inner_headers(struct sk_buff *skb)
 {
 	skb->inner_mac_header = skb->mac_header;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 719c3d707327..727447c17954 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -352,9 +352,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index e33349701050..ad84e7dec433 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1571,9 +1571,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:

[PATCH 3.16.y-ckt 127/142] ipv6: re-enable fragment header matching in ipv6_find_hdr

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Florian Westphal <fw@strlen.de>

commit 5d150a985520bbe3cb2aa1ceef24a7e32f20c15f upstream.

When ipv6_find_hdr is used to find a fragment header
(caller specifies target NEXTHDR_FRAGMENT) we erronously return
-ENOENT for all fragments with nonzero offset.

Before commit 9195bb8e381d, when target was specified, we did not
enter the exthdr walk loop as nexthdr == target so this used to work.

Now we do (so we can skip empty route headers). When we then stumble upon
a frag with nonzero frag_off we must return -ENOENT ("header not found")
only if the caller did not specifically request NEXTHDR_FRAGMENT.

This allows nfables exthdr expression to match ipv6 fragments, e.g. via

nft add rule ip6 filter input frag frag-off gt 0

Fixes: 9195bb8e381d ("ipv6: improve ipv6_find_hdr() to skip empty routing headers")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv6/exthdrs_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 8af3eb57f438..c7c8f71d0d48 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {

[PATCH 3.16.y-ckt 128/142] net: moxa: fix an error code

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Dan Carpenter <dan.carpenter@oracle.com>

commit 1d3cd1773fddfdc9ffb0c2dec9a954c7a54bc207 upstream.

We accidentally return IS_ERR(priv->base) which is 1 instead of
PTR_ERR(priv->base) which is the error code.

Fixes: 6c821bd9edc9 ('net: Add MOXA ART SoCs ethernet driver')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/moxa/moxart_ether.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 5020fd47825d..d627a78912e3 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -456,9 +456,9 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ndev->base_addr = res->start;
 	priv->base = devm_ioremap_resource(p_dev, res);
-	ret = IS_ERR(priv->base);
-	if (ret) {
+	if (IS_ERR(priv->base)) {
 		dev_err(p_dev, "devm_ioremap_resource failed\n");
+		ret = PTR_ERR(priv->base);
 		goto init_fail;
 	}
 

[PATCH 3.16.y-ckt 129/142] cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>

commit 4d06dd537f95683aba3651098ae288b7cbff8274 upstream.

usbnet_link_change will call schedule_work and should be
avoided if bind is failing. Otherwise we will end up with
scheduled work referring to a netdev which has gone away.

Instead of making the call conditional, we can just defer
it to usbnet_probe, using the driver_info flag made for
this purpose.

Fixes: 8a34b0ae8778 ("usbnet: cdc_ncm: apply usbnet_link_change")
Reported-by: Andrey Konovalov <andreyknvl@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16:
  - cdc_ncm_bind_common() takes only 3 args in 3.16
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/usb/cdc_ncm.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 8067b8fbb0ee..b7b3ed5f666c 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -948,23 +948,11 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
 
 static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
-
 	/* MBIM backwards compatible function? */
 	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
 
-	/* The NCM data altsetting is fixed */
-	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM);
-
-	/*
-	 * We should get an event when network connection is "connected" or
-	 * "disconnected". Set network connection in "disconnected" state
-	 * (carrier is OFF) during attach, so the IP network stack does not
-	 * start IPv6 negotiation and more.
-	 */
-	usbnet_link_change(dev, 0, 0);
-	return ret;
+	return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM);
 }
 
 static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max)
@@ -1506,7 +1494,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
-	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
+	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+			| FLAG_LINK_INTR,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1519,7 +1508,7 @@ static const struct driver_info cdc_ncm_info = {
 static const struct driver_info wwan_info = {
 	.description = "Mobile Broadband Network Device",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN,
+			| FLAG_LINK_INTR | FLAG_WWAN,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1532,7 +1521,7 @@ static const struct driver_info wwan_info = {
 static const struct driver_info wwan_noarp_info = {
 	.description = "Mobile Broadband Network Device (NO ARP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN | FLAG_NOARP,
+			| FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,

[PATCH 3.16.y-ckt 130/142] ext4: iterate over buffer heads correctly in move_extent_per_page()

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Eryu Guan <guaneryu@gmail.com>

commit 6ffe77bad545f4a7c8edd2a4ee797ccfcd894ab4 upstream.

In commit bcff24887d00 ("ext4: don't read blocks from disk after extents
being swapped") bh is not updated correctly in the for loop and wrong
data has been written to disk. generic/324 catches this on sub-page
block size ext4.

Fixes: bcff24887d00 ("ext4: don't read blocks from disk after extentsbeing swapped")
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/move_extent.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 146f8cd627b2..2423b0068183 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -1037,6 +1037,7 @@ data_copy:
 		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
 		if (*err < 0)
 			break;
+		bh = bh->b_this_page;
 	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);

[PATCH 3.16.y-ckt 131/142] Input: aiptek - fix crash on detecting device without endpoints

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Vladis Dronov <vdronov@redhat.com>

commit 8e20cf2bce122ce9262d6034ee5d5b76fbb92f96 upstream.

The aiptek driver crashes in aiptek_probe() when a specially crafted USB
device without endpoints is detected. This fix adds a check that the device
has proper configuration expected by the driver. Also an error return value
is changed to more matching one in one of the error paths.

Reported-by: Ralf Spenneberg <ralf@spenneberg.net>
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Moritz Muehlenhoff <jmm@inutil.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/input/tablet/aiptek.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c
index e7f966da6efa..78ca44840d60 100644
--- a/drivers/input/tablet/aiptek.c
+++ b/drivers/input/tablet/aiptek.c
@@ -1819,6 +1819,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	input_set_abs_params(inputdev, ABS_TILT_Y, AIPTEK_TILT_MIN, AIPTEK_TILT_MAX, 0, 0);
 	input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0);
 
+	/* Verify that a device really has an endpoint */
+	if (intf->altsetting[0].desc.bNumEndpoints < 1) {
+		dev_err(&intf->dev,
+			"interface has %d endpoints, but must have minimum 1\n",
+			intf->altsetting[0].desc.bNumEndpoints);
+		err = -EINVAL;
+		goto fail3;
+	}
 	endpoint = &intf->altsetting[0].endpoint[0].desc;
 
 	/* Go set up our URB, which is called when the tablet receives
@@ -1861,6 +1869,7 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	if (i == ARRAY_SIZE(speeds)) {
 		dev_info(&intf->dev,
 			 "Aiptek tried all speeds, no sane response\n");
+		err = -EINVAL;
 		goto fail3;
 	}
 

[PATCH 3.16.y-ckt 132/142] AIO: properly check iovec sizes

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

In Linus's tree, the iovec code has been reworked massively, but in
older kernels the AIO layer should be checking this before passing the
request on to other layers.

Many thanks to Ben Hawkes of Google Project Zero for pointing out the
issue.

Reported-by: Ben Hawkes <hawkes@google.com>
Acked-by: Benjamin LaHaise <bcrl@kvack.org>
Tested-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Moritz Muehlenhoff <jmm@inutil.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/aio.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index a6f86dae34be..7aaa4164bba5 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1378,11 +1378,16 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
 				       unsigned long *nr_segs,
 				       struct iovec *iovec)
 {
-	if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
+	size_t len = kiocb->ki_nbytes;
+
+	if (len > MAX_RW_COUNT)
+		len = MAX_RW_COUNT;
+
+	if (unlikely(!access_ok(!rw, buf, len)))
 		return -EFAULT;
 
 	iovec->iov_base = buf;
-	iovec->iov_len = kiocb->ki_nbytes;
+	iovec->iov_len = len;
 	*nr_segs = 1;
 	return 0;
 }

[PATCH 3.16.y-ckt 133/142] bcache: add mutex lock for bch_is_open

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jianjian Huo <samuel.huo@gmail.com>

commit 789d21dbd9d8889e62c79ec19585fcc97e42ef07 upstream.

Since bch_is_open will iterate linked list bch_cache_sets and
uncached_devices, it needs bch_register_lock.

Signed-off-by: Jianjian Huo <samuel.huo@gmail.com>
Cc: Kamal Mostafa <kamal@canonical.com>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/md/bcache/super.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 72e660cafadd..70db24e41947 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1950,10 +1950,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (IS_ERR(bdev)) {
 		if (bdev == ERR_PTR(-EBUSY)) {
 			bdev = lookup_bdev(strim(path));
+			mutex_lock(&bch_register_lock);
 			if (!IS_ERR(bdev) && bch_is_open(bdev))
 				err = "device already registered";
 			else
 				err = "device busy";
+			mutex_unlock(&bch_register_lock);
 			if (attr == &ksysfs_register_quiet)
 				goto out;
 		}

[PATCH 3.16.y-ckt 134/142] KVM: x86: move steal time initialization to vcpu entry time

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Marcelo Tosatti <mtosatti@redhat.com>

commit 7cae2bedcbd4680b155999655e49c27b9cf020fa upstream.

As reported at https://bugs.launchpad.net/qemu/+bug/1494350,
it is possible to have vcpu->arch.st.last_steal initialized
from a thread other than vcpu thread, say the iothread, via
KVM_SET_MSRS.

Which can cause an overflow later (when subtracting from vcpu threads
sched_info.run_delay).

To avoid that, move steal time accumulation to vcpu entry time,
before copying steal time data to guest.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: David Matlack <dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Liang Chen <liangchen.linux@gmail.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/kvm/x86.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e9b9fc00da15..89e06ec39dd7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2025,6 +2025,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu)
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	accumulate_steal_time(vcpu);
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -2157,12 +2159,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & KVM_MSR_ENABLED))
 			break;
 
-		vcpu->arch.st.last_steal = current->sched_info.run_delay;
-
-		preempt_disable();
-		accumulate_steal_time(vcpu);
-		preempt_enable();
-
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 		break;
@@ -2859,7 +2855,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->cpu = cpu;
 	}
 
-	accumulate_steal_time(vcpu);
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 }
 

[PATCH 3.16.y-ckt 135/142] lib/ucs2_string: Add ucs2 -> utf8 helper functions

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Jones <pjones@redhat.com>

commit 73500267c930baadadb0d02284909731baf151f7 upstream.

This adds ucs2_utf8size(), which tells us how big our ucs2 string is in
bytes, and ucs2_as_utf8, which translates from ucs2 to utf8..

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/ucs2_string.h |  4 +++
 lib/ucs2_string.c           | 62 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+			   unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 6f500ef2301d..17dd74e21ef9 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+	unsigned long i;
+	unsigned long j = 0;
+
+	for (i = 0; i < ucs2_strlen(src); i++) {
+		u16 c = src[i];
+
+		if (c > 0x800)
+			j += 3;
+		else if (c > 0x80)
+			j += 2;
+		else
+			j += 1;
+	}
+
+	return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+	unsigned int i;
+	unsigned long j = 0;
+	unsigned long limit = ucs2_strnlen(src, maxlength);
+
+	for (i = 0; maxlength && i < limit; i++) {
+		u16 c = src[i];
+
+		if (c > 0x800) {
+			if (maxlength < 3)
+				break;
+			maxlength -= 3;
+			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+			dest[j++] = 0x80 | (c & 0x003f);
+		} else if (c > 0x80) {
+			if (maxlength < 2)
+				break;
+			maxlength -= 2;
+			dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
+			dest[j++] = 0x80 | (c & 0x01f);
+		} else {
+			maxlength -= 1;
+			dest[j++] = c & 0x7f;
+		}
+	}
+	if (maxlength)
+		dest[j] = '\0';
+	return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);

[PATCH 3.16.y-ckt 136/142] efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Jones <pjones@redhat.com>

commit e0d64e6a880e64545ad7d55786aa84ab76bac475 upstream.

Translate EFI's UCS-2 variable names to UTF-8 instead of just assuming
all variable names fit in ASCII.

Signed-off-by: Peter Jones <pjones@redhat.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
[ luis: backported to 3.16: adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/firmware/efi/efivars.c | 28 ++++++++++------------------
 fs/efivarfs/super.c            |  7 +++----
 2 files changed, 13 insertions(+), 22 deletions(-)

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 463c56545ae8..f8ad5d6c7e69 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -541,35 +541,27 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 {
 	int i, short_name_size;
 	char *short_name;
-	unsigned long variable_name_size;
-	efi_char16_t *variable_name;
-
-	variable_name = new_var->var.VariableName;
-	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
+	unsigned long utf8_name_size;
+	efi_char16_t *variable_name = new_var->var.VariableName;
 
 	/*
-	 * Length of the variable bytes in ASCII, plus the '-' separator,
+	 * Length of the variable bytes in UTF8, plus the '-' separator,
 	 * plus the GUID, plus trailing NUL
 	 */
-	short_name_size = variable_name_size / sizeof(efi_char16_t)
-				+ 1 + EFI_VARIABLE_GUID_LEN + 1;
-
-	short_name = kzalloc(short_name_size, GFP_KERNEL);
+	utf8_name_size = ucs2_utf8size(variable_name);
+	short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1;
 
+	short_name = kmalloc(short_name_size, GFP_KERNEL);
 	if (!short_name)
 		return 1;
 
-	/* Convert Unicode to normal chars (assume top bits are 0),
-	   ala UTF-8 */
-	for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) {
-		short_name[i] = variable_name[i] & 0xFF;
-	}
+	ucs2_as_utf8(short_name, variable_name, short_name_size);
+
 	/* This is ugly, but necessary to separate one vendor's
 	   private variables from another's.         */
-
-	*(short_name + strlen(short_name)) = '-';
+	short_name[utf8_name_size] = '-';
 	efi_guid_unparse(&new_var->var.VendorGuid,
-			 short_name + strlen(short_name));
+			 short_name + utf8_name_size + 1);
 
 	new_var->kobj.kset = efivars_kset;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index c2f421c30ccd..3a7778d1bddc 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,7 +118,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
@@ -128,15 +128,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
 
 	name[len] = '-';
 

[PATCH 3.16.y-ckt 137/142] efi: Do variable name validation tests in utf8

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Jones <pjones@redhat.com>

commit 3dcb1f55dfc7631695e69df4a0d589ce5274bd07 upstream.

Actually translate from ucs2 to utf8 before doing the test, and then
test against our other utf8 data, instead of fudging it.

Signed-off-by: Peter Jones <pjones@redhat.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/firmware/efi/vars.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 5abe943e3404..aad48b99553f 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -189,10 +189,19 @@ static const struct variable_validate variable_validate[] = {
 };
 
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
+efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
 {
 	int i;
-	u16 *unicode_name = var_name;
+	unsigned long utf8_size;
+	u8 *utf8_name;
+
+	utf8_size = ucs2_utf8size(var_name);
+	utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL);
+	if (!utf8_name)
+		return false;
+
+	ucs2_as_utf8(utf8_name, var_name, utf8_size);
+	utf8_name[utf8_size] = '\0';
 
 	for (i = 0; variable_validate[i].validate != NULL; i++) {
 		const char *name = variable_validate[i].name;
@@ -200,28 +209,29 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
 
 		for (match = 0; ; match++) {
 			char c = name[match];
-			u16 u = unicode_name[match];
-
-			/* All special variables are plain ascii */
-			if (u > 127)
-				return true;
+			char u = utf8_name[match];
 
 			/* Wildcard in the matching name means we've matched */
-			if (c == '*')
+			if (c == '*') {
+				kfree(utf8_name);
 				return variable_validate[i].validate(var_name,
-							     match, data, len);
+							match, data, data_size);
+			}
 
 			/* Case sensitive match */
 			if (c != u)
 				break;
 
 			/* Reached the end of the string while matching */
-			if (!c)
+			if (!c) {
+				kfree(utf8_name);
 				return variable_validate[i].validate(var_name,
-							     match, data, len);
+							match, data, data_size);
+			}
 		}
 	}
 
+	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);

[PATCH 3.16.y-ckt 138/142] efi: Make our variable validation list include the guid

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Jones <pjones@redhat.com>

commit 8282f5d9c17fe15a9e658c06e3f343efae1a2a2f upstream.

All the variables in this list so far are defined to be in the global
namespace in the UEFI spec, so this just further ensures we're
validating the variables we think we are.

Including the guid for entries will become more important in future
patches when we decide whether or not to allow deletion of variables
based on presence in this list.

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/firmware/efi/efivars.c |  5 ++--
 drivers/firmware/efi/vars.c    | 52 +++++++++++++++++++++++++++---------------
 include/linux/efi.h            |  3 ++-
 3 files changed, 38 insertions(+), 22 deletions(-)

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index f8ad5d6c7e69..c807409630cc 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -220,7 +220,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(vendor, name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -446,7 +446,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(new_var->VendorGuid, name, data,
+			    size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index aad48b99553f..ce0ead43f7e1 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -165,31 +165,42 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
 }
 
 struct variable_validate {
+	efi_guid_t vendor;
 	char *name;
 	bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
 			 unsigned long len);
 };
 
+/*
+ * This is the list of variables we need to validate.
+ *
+ * If it has a validate() method that's not NULL, it'll go into the
+ * validation routine.  If not, it is assumed valid.
+ *
+ * Note that it's sorted by {vendor,name}, but globbed names must come after
+ * any other name with the same prefix.
+ */
 static const struct variable_validate variable_validate[] = {
-	{ "BootNext", validate_uint16 },
-	{ "BootOrder", validate_boot_order },
-	{ "DriverOrder", validate_boot_order },
-	{ "Boot*", validate_load_option },
-	{ "Driver*", validate_load_option },
-	{ "ConIn", validate_device_path },
-	{ "ConInDev", validate_device_path },
-	{ "ConOut", validate_device_path },
-	{ "ConOutDev", validate_device_path },
-	{ "ErrOut", validate_device_path },
-	{ "ErrOutDev", validate_device_path },
-	{ "Timeout", validate_uint16 },
-	{ "Lang", validate_ascii_string },
-	{ "PlatformLang", validate_ascii_string },
-	{ "", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ NULL_GUID, "", NULL },
 };
 
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
+efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		unsigned long data_size)
 {
 	int i;
 	unsigned long utf8_size;
@@ -203,9 +214,12 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
 	ucs2_as_utf8(utf8_name, var_name, utf8_size);
 	utf8_name[utf8_size] = '\0';
 
-	for (i = 0; variable_validate[i].validate != NULL; i++) {
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
 		const char *name = variable_validate[i].name;
-		int match;
+		int match = 0;
+
+		if (efi_guidcmp(vendor, variable_validate[i].vendor))
+			continue;
 
 		for (match = 0; ; match++) {
 			char c = name[match];
@@ -815,7 +829,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 
 	*set = false;
 
-	if (efivar_validate(name, data, *size) == false)
+	if (efivar_validate(*vendor, name, data, *size) == false)
 		return -EINVAL;
 
 	/*
diff --git a/include/linux/efi.h b/include/linux/efi.h
index b3fac7c1656c..971a69d3641d 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1143,7 +1143,8 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 				       struct list_head *head, bool remove);
 
-bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		     unsigned long data_size);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);

[PATCH 3.16.y-ckt 139/142] efi: Make efivarfs entries immutable by default

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Peter Jones <pjones@redhat.com>

commit ed8b0de5a33d2a2557dce7f9429dca8cb5bc5879 upstream.

"rm -rf" is bricking some peoples' laptops because of variables being
used to store non-reinitializable firmware driver data that's required
to POST the hardware.

These are 100% bugs, and they need to be fixed, but in the mean time it
shouldn't be easy to *accidentally* brick machines.

We have to have delete working, and picking which variables do and don't
work for deletion is quite intractable, so instead make everything
immutable by default (except for a whitelist), and make tools that
aren't quite so broad-spectrum unset the immutable flag.

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
[ luis: backported to 3.16:
  - use mutex_lock/unlock() instead of inode_lock/unlock()
  - use root->d_inode instead of d_inode()  ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 Documentation/filesystems/efivarfs.txt         |  7 +++
 drivers/firmware/efi/vars.c                    | 87 +++++++++++++++++++-------
 fs/efivarfs/file.c                             | 70 +++++++++++++++++++++
 fs/efivarfs/inode.c                            | 30 +++++----
 fs/efivarfs/internal.h                         |  3 +-
 fs/efivarfs/super.c                            |  9 ++-
 include/linux/efi.h                            |  2 +
 tools/testing/selftests/efivarfs/efivarfs.sh   | 19 +++++-
 tools/testing/selftests/efivarfs/open-unlink.c | 72 ++++++++++++++++++++-
 9 files changed, 258 insertions(+), 41 deletions(-)

diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
index c477af086e65..686a64bba775 100644
--- a/Documentation/filesystems/efivarfs.txt
+++ b/Documentation/filesystems/efivarfs.txt
@@ -14,3 +14,10 @@ filesystem.
 efivarfs is typically mounted like this,
 
 	mount -t efivarfs none /sys/firmware/efi/efivars
+
+Due to the presence of numerous firmware bugs where removing non-standard
+UEFI variables causes the system firmware to fail to POST, efivarfs
+files that are not well-known standardized variables are created
+as immutable files.  This doesn't prevent removal - "chattr -i" will work -
+but it does prevent this kind of failure from being accomplished
+accidentally.
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index ce0ead43f7e1..ab68e57172aa 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -172,10 +172,12 @@ struct variable_validate {
 };
 
 /*
- * This is the list of variables we need to validate.
+ * This is the list of variables we need to validate, as well as the
+ * whitelist for what we think is safe not to default to immutable.
  *
  * If it has a validate() method that's not NULL, it'll go into the
- * validation routine.  If not, it is assumed valid.
+ * validation routine.  If not, it is assumed valid, but still used for
+ * whitelisting.
  *
  * Note that it's sorted by {vendor,name}, but globbed names must come after
  * any other name with the same prefix.
@@ -193,11 +195,37 @@ static const struct variable_validate variable_validate[] = {
 	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
 	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
 	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
 	{ NULL_GUID, "", NULL },
 };
 
+static bool
+variable_matches(const char *var_name, size_t len, const char *match_name,
+		 int *match)
+{
+	for (*match = 0; ; (*match)++) {
+		char c = match_name[*match];
+		char u = var_name[*match];
+
+		/* Wildcard in the matching name means we've matched */
+		if (c == '*')
+			return true;
+
+		/* Case sensitive match */
+		if (!c && *match == len)
+			return true;
+
+		if (c != u)
+			return false;
+
+		if (!c)
+			return true;
+	}
+	return true;
+}
+
 bool
 efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		unsigned long data_size)
@@ -221,35 +249,48 @@ efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		if (efi_guidcmp(vendor, variable_validate[i].vendor))
 			continue;
 
-		for (match = 0; ; match++) {
-			char c = name[match];
-			char u = utf8_name[match];
-
-			/* Wildcard in the matching name means we've matched */
-			if (c == '*') {
-				kfree(utf8_name);
-				return variable_validate[i].validate(var_name,
-							match, data, data_size);
-			}
-
-			/* Case sensitive match */
-			if (c != u)
+		if (variable_matches(utf8_name, utf8_size+1, name, &match)) {
+			if (variable_validate[i].validate == NULL)
 				break;
-
-			/* Reached the end of the string while matching */
-			if (!c) {
-				kfree(utf8_name);
-				return variable_validate[i].validate(var_name,
-							match, data, data_size);
-			}
+			kfree(utf8_name);
+			return variable_validate[i].validate(var_name, match,
+							     data, data_size);
 		}
 	}
-
 	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);
 
+bool
+efivar_variable_is_removable(efi_guid_t vendor, const char *var_name,
+			     size_t len)
+{
+	int i;
+	bool found = false;
+	int match = 0;
+
+	/*
+	 * Check if our variable is in the validated variables list
+	 */
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		if (efi_guidcmp(variable_validate[i].vendor, vendor))
+			continue;
+
+		if (variable_matches(var_name, len,
+				     variable_validate[i].name, &match)) {
+			found = true;
+			break;
+		}
+	}
+
+	/*
+	 * If it's in our list, it is removable.
+	 */
+	return found;
+}
+EXPORT_SYMBOL_GPL(efivar_variable_is_removable);
+
 static efi_status_t
 check_var_size(u32 attributes, unsigned long size)
 {
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cdb2971192a5..2a36e916d239 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	mutex_lock(&inode->i_mutex);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	mutex_unlock(&inode->i_mutex);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 07ab49745e31..7e7318f10575 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 3a7778d1bddc..b57db0c6c2af 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -120,6 +120,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	char *name;
 	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -137,13 +138,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	ucs2_as_utf8(name, entry->var.VariableName, len);
 
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
+
 	name[len] = '-';
 
 	efi_guid_unparse(&entry->var.VendorGuid, name + len + 1);
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -199,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 971a69d3641d..8cb09c9d81ef 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1145,6 +1145,8 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 
 bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+				  size_t len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index 77edcdcc016b..057278448515 100644
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -88,7 +88,11 @@ test_delete()
 		exit 1
 	fi
 
-	rm $file
+	rm $file 2>/dev/null
+	if [ $? -ne 0 ]; then
+		chattr -i $file
+		rm $file
+	fi
 
 	if [ -e $file ]; then
 		echo "$file couldn't be deleted" >&2
@@ -111,6 +115,7 @@ test_zero_size_delete()
 		exit 1
 	fi
 
+	chattr -i $file
 	printf "$attrs" > $file
 
 	if [ -e $file ]; then
@@ -141,7 +146,11 @@ test_valid_filenames()
 			echo "$file could not be created" >&2
 			ret=1
 		else
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 		fi
 	done
 
@@ -174,7 +183,11 @@ test_invalid_filenames()
 
 		if [ -e $file ]; then
 			echo "Creating $file should have failed" >&2
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 			ret=1
 		fi
 	done
diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c
index 8c0764407b3c..4af74f733036 100644
--- a/tools/testing/selftests/efivarfs/open-unlink.c
+++ b/tools/testing/selftests/efivarfs/open-unlink.c
@@ -1,10 +1,68 @@
+#include <errno.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <linux/fs.h>
+
+static int set_immutable(const char *path, int immutable)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+
+	if (immutable)
+		flags |= FS_IMMUTABLE_FL;
+	else
+		flags &= ~FS_IMMUTABLE_FL;
+
+	rc = ioctl(fd, FS_IOC_SETFLAGS, &flags);
+	error = errno;
+	close(fd);
+	errno = error;
+	return rc;
+}
+
+static int get_immutable(const char *path)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+	close(fd);
+	if (flags & FS_IMMUTABLE_FL)
+		return 1;
+	return 0;
+}
 
 int main(int argc, char **argv)
 {
@@ -27,7 +85,7 @@ int main(int argc, char **argv)
 	buf[4] = 0;
 
 	/* create a test variable */
-	fd = open(path, O_WRONLY | O_CREAT);
+	fd = open(path, O_WRONLY | O_CREAT, 0600);
 	if (fd < 0) {
 		perror("open(O_WRONLY)");
 		return EXIT_FAILURE;
@@ -41,6 +99,18 @@ int main(int argc, char **argv)
 
 	close(fd);
 
+	rc = get_immutable(path);
+	if (rc < 0) {
+		perror("ioctl(FS_IOC_GETFLAGS)");
+		return EXIT_FAILURE;
+	} else if (rc) {
+		rc = set_immutable(path, 0);
+		if (rc < 0) {
+			perror("ioctl(FS_IOC_SETFLAGS)");
+			return EXIT_FAILURE;
+		}
+	}
+
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
 		perror("open");

[PATCH 3.16.y-ckt 140/142] efi: Add pstore variables to the deletion whitelist

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Matt Fleming <matt@codeblueprint.co.uk>

commit e246eb568bc4cbbdd8a30a3c11151ff9b7ca7312 upstream.

Laszlo explains why this is a good idea,

 'This is because the pstore filesystem can be backed by UEFI variables,
  and (for example) a crash might dump the last kilobytes of the dmesg
  into a number of pstore entries, each entry backed by a separate UEFI
  variable in the above GUID namespace, and with a variable name
  according to the above pattern.

  Please see "drivers/firmware/efi/efi-pstore.c".

  While this patch series will not prevent the user from deleting those
  UEFI variables via the pstore filesystem (i.e., deleting a pstore fs
  entry will continue to delete the backing UEFI variable), I think it
  would be nice to preserve the possibility for the sysadmin to delete
  Linux-created UEFI variables that carry portions of the crash log,
  *without* having to mount the pstore filesystem.'

There's also no chance of causing machines to become bricked by
deleting these variables, which is the whole purpose of excluding
things from the whitelist.

Use the LINUX_EFI_CRASH_GUID guid and a wildcard '*' for the match so
that we don't have to update the string in the future if new variable
name formats are created for crash dump variables.

Reported-by: Laszlo Ersek <lersek@redhat.com>
Acked-by: Peter Jones <pjones@redhat.com>
Tested-by: Peter Jones <pjones@redhat.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/firmware/efi/vars.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index ab68e57172aa..4e2f46938bf0 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -198,6 +198,7 @@ static const struct variable_validate variable_validate[] = {
 	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
 	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ LINUX_EFI_CRASH_GUID, "*", NULL },
 	{ NULL_GUID, "", NULL },
 };
 

[PATCH 3.16.y-ckt 141/142] lib/ucs2_string: Correct ucs2 -> utf8 conversion

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Jason Andryuk <jandryuk@gmail.com>

commit a68075908a37850918ad96b056acc9ac4ce1bd90 upstream.

The comparisons should be >= since 0x800 and 0x80 require an additional bit
to store.

For the 3 byte case, the existing shift would drop off 2 more bits than
intended.

For the 2 byte case, there should be 5 bits bits in byte 1, and 6 bits in
byte 2.

Signed-off-by: Jason Andryuk <jandryuk@gmail.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Matthew Garrett <mjg59@coreos.com>
Cc: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 lib/ucs2_string.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 17dd74e21ef9..f0b323abb4c6 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -59,9 +59,9 @@ ucs2_utf8size(const ucs2_char_t *src)
 	for (i = 0; i < ucs2_strlen(src); i++) {
 		u16 c = src[i];
 
-		if (c > 0x800)
+		if (c >= 0x800)
 			j += 3;
-		else if (c > 0x80)
+		else if (c >= 0x80)
 			j += 2;
 		else
 			j += 1;
@@ -88,19 +88,19 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
 	for (i = 0; maxlength && i < limit; i++) {
 		u16 c = src[i];
 
-		if (c > 0x800) {
+		if (c >= 0x800) {
 			if (maxlength < 3)
 				break;
 			maxlength -= 3;
 			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
-			dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
 			dest[j++] = 0x80 | (c & 0x003f);
-		} else if (c > 0x80) {
+		} else if (c >= 0x80) {
 			if (maxlength < 2)
 				break;
 			maxlength -= 2;
-			dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
-			dest[j++] = 0x80 | (c & 0x01f);
+			dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
+			dest[j++] = 0x80 | (c & 0x03f);
 		} else {
 			maxlength -= 1;
 			dest[j++] = c & 0x7f;

[PATCH 3.16.y-ckt 142/142] tracing: Fix check for cpu online when event is disabled

[Luis Henriques]

3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

commit dc17147de328a74bbdee67c1bf37d2f1992de756 upstream.

Commit f37755490fe9b ("tracepoints: Do not trace when cpu is offline") added
a check to make sure that tracepoints only get called when the cpu is
online, as it uses rcu_read_lock_sched() for protection.

Commit 3a630178fd5f3 ("tracing: generate RCU warnings even when tracepoints
are disabled") added lockdep checks (including rcu checks) for events that
are not enabled to catch possible RCU issues that would only be triggered if
a trace event was enabled. Commit f37755490fe9b only stopped the warnings
when the trace event was enabled but did not prevent warnings if the trace
event was called when disabled.

To fix this, the cpu online check is moved to where the condition is added
to the trace event. This will place the cpu online check in all places that
it may be used now and in the future.

Fixes: f37755490fe9b ("tracepoints: Do not trace when cpu is offline")
Fixes: 3a630178fd5f3 ("tracing: generate RCU warnings even when tracepoints are disabled")
Reported-by: Sudeep Holla <sudeep.holla@arm.com>
Tested-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/tracepoint.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 30e788953524..acc120a637ac 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -124,9 +124,6 @@ extern void syscall_unregfunc(void);
 		void *it_func;						\
 		void *__data;						\
 									\
-		if (!cpu_online(raw_smp_processor_id()))		\
-			return;						\
-									\
 		if (!(cond))						\
 			return;						\
 		prercu;							\
@@ -270,15 +267,19 @@ extern void syscall_unregfunc(void);
  * "void *__data, proto" as the callback prototype.
  */
 #define DECLARE_TRACE_NOARGS(name)					\
-		__DECLARE_TRACE(name, void, , 1, void *__data, __data)
+	__DECLARE_TRACE(name, void, ,					\
+			cpu_online(raw_smp_processor_id()),		\
+			void *__data, __data)
 
 #define DECLARE_TRACE(name, proto, args)				\
-		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1,	\
-				PARAMS(void *__data, proto),		\
-				PARAMS(__data, args))
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()),		\
+			PARAMS(void *__data, proto),			\
+			PARAMS(__data, args))
 
 #define DECLARE_TRACE_CONDITION(name, proto, args, cond)		\
-	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \
 			PARAMS(void *__data, proto),			\
 			PARAMS(__data, args))
 

Re: [PATCH 3.16.y-ckt 062/142] net/ipv6: add sysctl option accept_ra_min_hop_limit

[Luis Henriques]

On Tue, Mar 22, 2016 at 10:39:51AM +0000, Luis Henriques wrote:
> 3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.
>

I am replacing this patch by a slightly modified version as suggested by
Yoshifuji (see bellow).  It basically adds a few missing definitions to
the enum in include/uapi/linux/ipv6.h so that it's compatible with
mainline kernel.

Cheers,
--
Luís

>From efd019f933a538e4147aee811e6b2dd7a1aafdef Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 30 Jul 2015 14:28:42 +0800
Subject: net/ipv6: add sysctl option accept_ra_min_hop_limit

commit 8013d1d7eafb0589ca766db6b74026f76b7f5cb4 upstream.

Commit 6fd99094de2b ("ipv6: Don't reduce hop limit for an interface")
disabled accept hop limit from RA if it is smaller than the current hop
limit for security stuff. But this behavior kind of break the RFC definition.

RFC 4861, 6.3.4.  Processing Received Router Advertisements
   A Router Advertisement field (e.g., Cur Hop Limit, Reachable Time,
   and Retrans Timer) may contain a value denoting that it is
   unspecified.  In such cases, the parameter should be ignored and the
   host should continue using whatever value it is already using.

   If the received Cur Hop Limit value is non-zero, the host SHOULD set
   its CurHopLimit variable to the received value.

So add sysctl option accept_ra_min_hop_limit to let user choose the minimum
hop limit value they can accept from RA. And set default to 1 to meet RFC
standards.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: YOSHIFUJI Hideaki <hideaki.yoshifuji@miraclelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16:
  - added missing DEVCONF_* as suggested by Yoshfuji so that uapi contains
    the same values as mainline
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 Documentation/networking/ip-sysctl.txt |  8 ++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  6 ++++++
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       | 16 +++++++---------
 5 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ab42c95f9985..36aa39eee48f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1210,6 +1210,14 @@ accept_ra_defrtr - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_min_hop_limit - INTEGER
+	Minimum hop limit Information in Router Advertisement.
+
+	Hop limit Information in Router Advertisement less than this
+	variable shall be ignored.
+
+	Default: 1
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f3d5d11b8871..9cc2240d7e52 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,6 +29,7 @@ struct ipv6_devconf {
 	__s32		max_desync_factor;
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
+	__s32		accept_ra_min_hop_limit;
 	__s32		accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	__s32		accept_ra_rtr_pref;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 593b0e32d956..5985f28e98b3 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -163,6 +163,12 @@ enum {
 	DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_SUPPRESS_FRAG_NDISC,
+	DEVCONF_ACCEPT_RA_FROM_LOCAL,
+	DEVCONF_USE_OPTIMISTIC,
+	DEVCONF_ACCEPT_RA_MTU,
+	DEVCONF_STABLE_SECRET,
+	DEVCONF_USE_OIF_ADDRS_ONLY,
+	DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 75630e173adf..405575f9ae77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -186,6 +186,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -222,6 +223,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -4294,6 +4296,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
 	array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
 	array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+	array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit;
 	array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -5079,6 +5082,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_min_hop_limit",
+			.data		= &ipv6_devconf.accept_ra_min_hop_limit,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "accept_ra_pinfo",
 			.data		= &ipv6_devconf.accept_ra_pinfo,
 			.maxlen		= sizeof(int),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e2eb53c719dc..577338204863 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1189,18 +1189,16 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
-	if (ra_msg->icmph.icmp6_hop_limit) {
-		/* Only set hop_limit on the interface if it is higher than
-		 * the current hop_limit.
-		 */
-		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+	if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+	    ra_msg->icmph.icmp6_hop_limit) {
+		if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
 			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+			if (rt)
+				dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
+					       ra_msg->icmph.icmp6_hop_limit);
 		} else {
-			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
 		}
-		if (rt)
-			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
-				       ra_msg->icmph.icmp6_hop_limit);
 	}
 
 skip_defrtr:

Re: [PATCH 3.16.y-ckt 062/142] net/ipv6: add sysctl option accept_ra_min_hop_limit

[Luis Henriques]

On Tue, Mar 22, 2016 at 10:39:51AM +0000, Luis Henriques wrote:
> 3.16.7-ckt26 -stable review patch.  If anyone has any objections, please let me know.
>

I am replacing this patch by a slightly modified version as suggested by
Yoshifuji (see bellow).  It basically adds a few missing definitions to
the enum in include/uapi/linux/ipv6.h so that it's compatible with
mainline kernel.

Cheers,
--
Lu�s

>From efd019f933a538e4147aee811e6b2dd7a1aafdef Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 30 Jul 2015 14:28:42 +0800
Subject: net/ipv6: add sysctl option accept_ra_min_hop_limit

commit 8013d1d7eafb0589ca766db6b74026f76b7f5cb4 upstream.

Commit 6fd99094de2b ("ipv6: Don't reduce hop limit for an interface")
disabled accept hop limit from RA if it is smaller than the current hop
limit for security stuff. But this behavior kind of break the RFC definition.

RFC 4861, 6.3.4.  Processing Received Router Advertisements
   A Router Advertisement field (e.g., Cur Hop Limit, Reachable Time,
   and Retrans Timer) may contain a value denoting that it is
   unspecified.  In such cases, the parameter should be ignored and the
   host should continue using whatever value it is already using.

   If the received Cur Hop Limit value is non-zero, the host SHOULD set
   its CurHopLimit variable to the received value.

So add sysctl option accept_ra_min_hop_limit to let user choose the minimum
hop limit value they can accept from RA. And set default to 1 to meet RFC
standards.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: YOSHIFUJI Hideaki <hideaki.yoshifuji@miraclelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backported to 3.16:
  - added missing DEVCONF_* as suggested by Yoshfuji so that uapi contains
    the same values as mainline
  - adjusted context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 Documentation/networking/ip-sysctl.txt |  8 ++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  6 ++++++
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       | 16 +++++++---------
 5 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ab42c95f9985..36aa39eee48f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1210,6 +1210,14 @@ accept_ra_defrtr - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_min_hop_limit - INTEGER
+	Minimum hop limit Information in Router Advertisement.
+
+	Hop limit Information in Router Advertisement less than this
+	variable shall be ignored.
+
+	Default: 1
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f3d5d11b8871..9cc2240d7e52 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,6 +29,7 @@ struct ipv6_devconf {
 	__s32		max_desync_factor;
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
+	__s32		accept_ra_min_hop_limit;
 	__s32		accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	__s32		accept_ra_rtr_pref;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 593b0e32d956..5985f28e98b3 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -163,6 +163,12 @@ enum {
 	DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_SUPPRESS_FRAG_NDISC,
+	DEVCONF_ACCEPT_RA_FROM_LOCAL,
+	DEVCONF_USE_OPTIMISTIC,
+	DEVCONF_ACCEPT_RA_MTU,
+	DEVCONF_STABLE_SECRET,
+	DEVCONF_USE_OIF_ADDRS_ONLY,
+	DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 75630e173adf..405575f9ae77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -186,6 +186,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -222,6 +223,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -4294,6 +4296,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
 	array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
 	array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+	array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit;
 	array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -5079,6 +5082,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_min_hop_limit",
+			.data		= &ipv6_devconf.accept_ra_min_hop_limit,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "accept_ra_pinfo",
 			.data		= &ipv6_devconf.accept_ra_pinfo,
 			.maxlen		= sizeof(int),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e2eb53c719dc..577338204863 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1189,18 +1189,16 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
-	if (ra_msg->icmph.icmp6_hop_limit) {
-		/* Only set hop_limit on the interface if it is higher than
-		 * the current hop_limit.
-		 */
-		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+	if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+	    ra_msg->icmph.icmp6_hop_limit) {
+		if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
 			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+			if (rt)
+				dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
+					       ra_msg->icmph.icmp6_hop_limit);
 		} else {
-			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
 		}
-		if (rt)
-			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
-				       ra_msg->icmph.icmp6_hop_limit);
 	}
 
 skip_defrtr: