[ 3.5.y.z extended stable ] Linux 3.5.7.12 stable review

[ 3.5.y.z extended stable ] Linux 3.5.7.12 stable review

[Luis Henriques]

I am announcing the review cycle for the 3.5.7.12 stable release. This new
release contains 118 patches, which are posted as a response to this
message. They are also available at the following repository:

git://kernel.ubuntu.com/ubuntu/linux.git linux-3.5.y-review

If there are any problems, or if anything is missing, please answer to
this or to any of the followup patches. Note that any answer should be
made at maximum in 3 days, after that the final release of 3.5.7.12 will be
made.

For more information about the 3.5.y.z extended stable tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Included below are the diffstat and shortlog for this release.

-Luis

-- 
 arch/arm/include/asm/pgtable.h                     |   9 ++
 arch/arm/kernel/perf_event.c                       |   5 +-
 arch/arm/kernel/sched_clock.c                      |   4 +-
 arch/arm/mach-omap2/cpuidle34xx.c                  |   5 +-
 arch/arm/mm/cache-feroceon-l2.c                    |   1 +
 arch/ia64/include/asm/futex.h                      |   5 +-
 arch/ia64/include/asm/mca.h                        |   1 +
 arch/ia64/kernel/irq.c                             |   8 ++
 arch/ia64/kernel/mca.c                             |  37 ++++---
 arch/ia64/kvm/vtlb.c                               |   2 +-
 arch/sparc/include/asm/pgtable_64.h                |   1 +
 arch/sparc/include/asm/switch_to_64.h              |   3 +-
 arch/sparc/include/asm/tlbflush_64.h               |  37 +++++--
 arch/sparc/kernel/smp_64.c                         |  41 ++++++-
 arch/sparc/mm/tlb.c                                |  39 ++++++-
 arch/sparc/mm/tsb.c                                |  57 +++++++---
 arch/sparc/mm/ultra.S                              | 119 ++++++++++++++++-----
 arch/x86/kernel/cpu/perf_event_intel.c             |  15 ++-
 arch/x86/xen/enlighten.c                           |   5 +-
 arch/x86/xen/smp.c                                 |   2 +
 arch/x86/xen/time.c                                |   6 +-
 crypto/algif_hash.c                                |   2 +
 crypto/algif_skcipher.c                            |   1 +
 drivers/acpi/pci_root.c                            |   4 +-
 drivers/char/hpet.c                                |  14 +--
 drivers/gpu/drm/i915/intel_ringbuffer.c            |   5 -
 drivers/md/md.c                                    |   9 +-
 drivers/mtd/mtdchar.c                              |  23 +---
 drivers/net/bonding/bond_main.c                    |  10 ++
 drivers/net/can/mcp251x.c                          |  10 +-
 drivers/net/can/sja1000/sja1000_of_platform.c      |  31 +++---
 drivers/net/ethernet/atheros/atl1e/atl1e.h         |   2 +-
 drivers/net/ethernet/atheros/atl1e/atl1e_main.c    |   1 +
 drivers/net/ethernet/freescale/gianfar_ptp.c       |   3 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  10 ++
 .../net/wireless/ath/ath9k/ar9580_1p0_initvals.h   |   2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_init.c      |   2 +-
 drivers/net/wireless/b43/phy_n.c                   |   3 +-
 drivers/net/wireless/iwlwifi/iwl-agn-sta.c         |   5 +-
 drivers/net/wireless/iwlwifi/iwl-debugfs.c         |  16 +--
 drivers/net/wireless/mwifiex/pcie.c                |   4 +-
 drivers/net/wireless/rt2x00/rt2800lib.c            |  10 +-
 drivers/pci/pci.c                                  |  12 +--
 drivers/regulator/core.c                           |  10 +-
 drivers/rtc/rtc-at91rm9200.c                       |  14 ++-
 drivers/rtc/rtc-cmos.c                             |   4 +-
 drivers/s390/char/sclp_cmd.c                       |   4 +-
 drivers/ssb/driver_chipcommon_pmu.c                |  29 +++++
 drivers/tty/pty.c                                  |   3 +
 drivers/tty/serial/serial_core.c                   |   4 +
 drivers/tty/tty_io.c                               |  14 ++-
 drivers/usb/chipidea/udc.c                         |   8 ++
 drivers/usb/chipidea/udc.h                         |   4 +-
 drivers/usb/core/devio.c                           |   2 +
 drivers/usb/misc/appledisplay.c                    |   1 +
 drivers/usb/serial/ftdi_sio.c                      |  23 ++--
 drivers/usb/serial/ftdi_sio_ids.h                  |   4 +-
 drivers/usb/serial/option.c                        |   8 ++
 drivers/usb/storage/cypress_atacb.c                |  16 ++-
 drivers/video/fbmem.c                              |  40 +++----
 fs/aio.c                                           |   2 +-
 fs/dcache.c                                        |   4 +-
 fs/exec.c                                          |   7 +-
 fs/ext4/Kconfig                                    |   3 +-
 fs/ext4/ext4_jbd2.h                                |   6 +-
 fs/ext4/fsync.c                                    |   3 +-
 fs/ext4/inode.c                                    |  11 +-
 fs/ext4/mballoc.c                                  |   8 +-
 fs/ext4/mmp.c                                      |   2 +-
 fs/ext4/resize.c                                   |   2 +
 fs/ext4/super.c                                    |   7 +-
 fs/fscache/stats.c                                 |   2 +-
 fs/hfsplus/extents.c                               |   2 +-
 fs/jbd2/commit.c                                   |  50 +++++----
 fs/jbd2/journal.c                                  |  31 ++++++
 fs/lockd/clntlock.c                                |   3 +
 fs/lockd/clntproc.c                                |   3 -
 fs/nfs/nfs4proc.c                                  |   6 ++
 fs/notify/inotify/inotify_user.c                   |   6 +-
 fs/sysfs/dir.c                                     |  15 ++-
 include/asm-generic/pgtable.h                      |  10 ++
 include/linux/ipc_namespace.h                      |   2 +-
 include/linux/jbd2.h                               |   2 +
 include/linux/mm.h                                 |   2 +
 include/linux/netdevice.h                          |   2 +-
 include/linux/sched.h                              |  18 +---
 include/linux/skbuff.h                             |   7 ++
 include/linux/socket.h                             |   3 +-
 include/linux/ssb/ssb_driver_chipcommon.h          |   2 +
 include/net/scm.h                                  |   2 +-
 ipc/shm.c                                          |   2 +-
 kernel/cgroup.c                                    |   2 +-
 kernel/events/core.c                               |   3 +-
 kernel/hrtimer.c                                   |   6 ++
 kernel/sched/core.c                                |   6 +-
 kernel/signal.c                                    |   2 +-
 kernel/time/tick-broadcast.c                       |   4 +
 kernel/time/tick-common.c                          |   1 +
 kernel/trace/ftrace.c                              |   5 +-
 kernel/trace/trace.c                               |  64 +++++------
 kernel/trace/trace_selftest.c                      |   9 +-
 kernel/trace/trace_stack.c                         |  76 +++++++++++--
 kernel/trace/trace_stat.c                          |   2 +
 mm/hugetlb.c                                       |  12 ++-
 mm/memory.c                                        |  47 ++++++++
 mm/mmap.c                                          |   4 +-
 net/atm/common.c                                   |   2 +
 net/ax25/af_ax25.c                                 |   1 +
 net/bluetooth/af_bluetooth.c                       |   4 +-
 net/bluetooth/rfcomm/sock.c                        |   1 +
 net/caif/caif_socket.c                             |   2 +
 net/core/dev.c                                     |   4 +
 net/core/dev_addr_lists.c                          |   6 +-
 net/core/rtnetlink.c                               |   4 +-
 net/core/sock.c                                    |  14 ++-
 net/ipv4/esp4.c                                    |   6 +-
 net/ipv4/ip_fragment.c                             |  15 ++-
 net/ipv4/syncookies.c                              |   4 +-
 net/ipv4/tcp_input.c                               |  64 ++++++-----
 net/ipv4/tcp_output.c                              |   8 +-
 net/ipv6/addrconf.c                                |  27 +++++
 net/ipv6/reassembly.c                              |  13 ++-
 net/irda/af_irda.c                                 |   2 +
 net/iucv/af_iucv.c                                 |   2 +
 net/l2tp/l2tp_ip6.c                                |   1 +
 net/llc/af_llc.c                                   |   2 +
 net/netrom/af_netrom.c                             |   1 +
 net/nfc/llcp/sock.c                                |   2 +
 net/rose/af_rose.c                                 |   1 +
 net/sched/sch_cbq.c                                |   5 +-
 net/sctp/auth.c                                    |   2 +-
 net/tipc/socket.c                                  |   7 ++
 net/unix/af_unix.c                                 |   2 +-
 net/wireless/reg.c                                 |   2 +-
 sound/core/pcm_native.c                            |  12 +--
 135 files changed, 1027 insertions(+), 426 deletions(-)

Adrian Thomasset (2):
      USB: ftdi_sio: correct ST Micro Connect Lite PIDs
      USB: ftdi_sio: enable two UART ports on ST Microconnect Lite

Alex A. Mihaylov (1):
      rt2x00: Fix transmit power troubles on some Ralink RT30xx cards

Andrzej Hajda (1):
      regulator: fixed regulator_bulk_enable unwinding code

Anurup m (1):
      fs/fscache/stats.c: fix memory leak

Balakumaran Kannan (1):
      net IPv6 : Fix broken IPv6 routing table after loopback down-up

Ben Greear (1):
      net: rate-limit warn-bad-offload splats.

Ben Jencks (1):
      usb/misc/appledisplay: Add 24" LED Cinema display

Bjørn Mork (1):
      USB: option: add a D-Link DWM-156 variant

Catalin Marinas (1):
      arm: set the page table freeing ceiling to TASK_SIZE

Christoph Fritz (1):
      can: sja1000: fix handling on dt properties on little endian systems

Daniel Borkmann (1):
      net: sctp: sctp_auth_key_put: use kzfree instead of kfree

Daniel Lezcano (1):
      ARM: omap3: cpuidle: enable time keeping

David Engraf (1):
      hrtimer: Fix ktime_add_ns() overflow on 32bit architectures

David S. Miller (1):
      sparc64: Fix race in TLB batch processing.

Derek Basehore (1):
      drivers/rtc/rtc-cmos.c: don't disable hpet emulation on suspend

Dmitry Monakhov (3):
      jbd2: fix race between jbd2_journal_remove_checkpoint and ->j_commit_callback
      ext4: fix journal callback list traversal
      ext4: fix big-endian bug in metadata checksum calculations

Dmitry Popov (1):
      tcp: incoming connections might use wrong route under synflood

Emese Revfy (1):
      kernel/signal.c: stop info leak via the tkill and the tgkill syscalls

Emmanuel Grumbach (1):
      iwlwifi: dvm: don't send zeroed LQ cmd

Eric Dumazet (2):
      tcp: call tcp_replace_ts_recent() from tcp_ack()
      net: drop dst before queueing fragments

Eric W. Biederman (1):
      af_unix: If we don't care about credentials coallesce all messages

Federico Vaga (1):
      serial_core.c: add put_device() after device_find_child()

Felix Fietkau (2):
      ath9k_htc: accept 1.x firmware newer than 1.3
      ath9k_hw: change AR9580 initvals to fix a stability issue

Filippo Turato (1):
      USB: serial: option: Added support Olivetti Olicard 145

Greg Thelen (1):
      fs/dcache.c: add cond_resched() to shrink_dcache_parent()

Hannes Frederic Sowa (1):
      atl1e: limit gso segment size to prevent generation of wrong ip length fields

Hans de Goede (1):
      usbfs: Always allow ctrl requests with USB_RECIP_ENDPOINT on the ctrl ep

Heiko Carstens (1):
      s390/memory hotplug: prevent offline of active memory increments

Hugh Dickins (1):
      mm: allow arch code to control the user page table ceiling

Illia Ragozin (1):
      ARM: 7696/1: Fix kexec by setting outer_cache.inv_all for Feroceon

Jacob Keller (1):
      ixgbe: fix EICR write in ixgbe_msix_other

Jiri Slaby (2):
      TTY: do not update atime/mtime on read/write
      TTY: fix atime/mtime regression

Johan Hovold (1):
      drivers/rtc/rtc-at91rm9200.c: fix missing iounmap

Johannes Berg (1):
      wireless: regulatory: fix channel disabling race condition

Konrad Rzeszutek Wilk (3):
      xen/smp: Fix leakage of timer interrupt line for every CPU online/offline.
      xen/smp/spinlock: Fix leakage of the spinlock interrupt line for every CPU online/offline
      xen/time: Fix kasprintf splat when allocating timer%d IRQ line.

Li Zefan (1):
      cgroup: fix an off-by-one bug which may trigger BUG_ON()

Linus Torvalds (7):
      vm: add vm_iomap_memory() helper function
      vm: convert HPET mmap to vm_iomap_memory() helper
      vm: convert fb_mmap to vm_iomap_memory() helper
      vm: convert snd_pcm_lib_mmap_iomem() to vm_iomap_memory() helper
      vm: convert mtdchar mmap to vm_iomap_memory() helper
      net: fix incorrect credentials passing
      tty: fix up atime/mtime mess, take three

Luis Henriques (1):
      Revert "drm/i915: GFX_MODE Flush TLB Invalidate Mode must be '1' for scanline waits"

Marc Kleine-Budde (1):
      can: mcp251x: add missing IRQF_ONESHOT to request_threaded_irq

Mathias Krause (14):
      crypto: algif - suppress sending source address information in recvmsg
      atm: update msg_namelen in vcc_recvmsg()
      ax25: fix info leak via msg_name in ax25_recvmsg()
      Bluetooth: fix possible info leak in bt_sock_recvmsg()
      Bluetooth: RFCOMM - Fix missing msg_namelen update in rfcomm_sock_recvmsg()
      caif: Fix missing msg_namelen update in caif_seqpkt_recvmsg()
      irda: Fix missing msg_namelen update in irda_recvmsg_dgram()
      iucv: Fix missing msg_namelen update in iucv_sock_recvmsg()
      llc: Fix missing msg_namelen update in llc_ui_recvmsg()
      netrom: fix info leak via msg_name in nr_recvmsg()
      NFC: llcp: fix info leaks via msg_name in llcp_sock_recvmsg()
      rose: fix info leak via msg_name in rose_recvmsg()
      tipc: fix info leaks via msg_name in recv_msg/recv_stream
      l2tp: fix info leak in l2tp_ip6_recvmsg()

Michael Grzeschik (2):
      usb: chipidea: udc: fix memory access of shared memory on armv5 machines
      usb: chipidea: udc: fix memory leak in _ep_nuke

Michael Riesch (1):
      rtnetlink: Call nlmsg_parse() with correct header length

Ming Lei (1):
      sysfs: fix use after free in case of concurrent read/write and readdir

Namhyung Kim (3):
      tracing: Fix off-by-one on allocating stat->pages
      tracing: Reset ftrace_graph_filter_enabled if count is zero
      tracing: Check return value of tracing_init_dentry()

Naoya Horiguchi (1):
      hugetlbfs: add swap entry check in follow_hugetlb_page()

NeilBrown (1):
      md: bad block list should default to disabled.

Oleg Nesterov (1):
      exec: do not abuse ->cred_guard_mutex in threadgroup_lock()

Patrick McHardy (1):
      netfilter: don't reset nf_trace in nf_reset()

Prarit Bhargava (1):
      hrtimer: Add expiry time overflow check in hrtimer_interrupt

Rafael J. Wysocki (1):
      PCI/PM: Fix fallback to PCI_D0 in pci_platform_power_transition()

Rafał Miłecki (1):
      ssb: implement spurious tone avoidance

Richard Cochran (1):
      gianfar: do not advertise any alarm capability.

Robin Holt (1):
      ipc: sysv shared memory limited to 8TiB

Stanislaw Gruszka (1):
      iwlwifi: fix freeing uninitialized pointer

Stefani Seibold (1):
      USB: add ftdi_sio USB ID for GDM Boost V1.x

Stephan Schreiber (2):
      Wrong asm register contraints in the futex implementation
      Wrong asm register contraints in the kvm implementation

Stephane Eranian (1):
      perf/x86: Fix offcore_rsp valid mask for SNB/IVB

Stephen Boyd (1):
      ARM: 7699/1: sched_clock: Add more notrace to prevent recursion

Steven Rostedt (Red Hat) (4):
      tracing: Use stack of calling function for stack tracer
      tracing: Fix stack tracer with fentry use
      tracing: Remove most or all of stack tracer stack size from stack_max_size
      tracing: Fix ftrace_dump()

Tejun Heo (1):
      sched: Convert BUG_ON()s in try_to_wake_up_local() to WARN_ON_ONCE()s

Theodore Ts'o (3):
      ext4/jbd2: don't wait (forever) for stale tid caused by wraparound
      ext4: fix online resizing for ext3-compat file systems
      ext4: fix Kconfig documentation for CONFIG_EXT4_DEBUG

Thomas Gleixner (1):
      clockevents: Set dummy handler on CPU_DEAD shutdown

Thomas Graf (1):
      tcp: Reallocate headroom if it would overflow csum_start

Tommi Rantala (1):
      perf: Treat attr.config as u64 in perf_swevent_init()

Tony Luck (1):
      Fix initialization of CMCI/CMCP interrupts

Tormod Volden (1):
      usb-storage: CY7C68300A chips do not support Cypress ATACB

Trond Myklebust (2):
      NFSv4: Handle NFS4ERR_DELAY and NFS4ERR_GRACE in nfs4_open_delegation_recall
      LOCKD: Ensure that nlmclnt_block resets block->b_status after a server reboot

Vasily Averin (1):
      cbq: incorrect processing of high limits

Vlad Yasevich (1):
      net: count hw_addr syncs so that unsync works properly.

Vyacheslav Dubeyko (1):
      hfsplus: fix potential overflow in hfsplus_file_truncate()

Wei Yongjun (3):
      perf: Fix error return code
      netrom: fix invalid use of sizeof in nr_recvmsg()
      esp4: fix error return code in esp_output()

Will Deacon (1):
      ARM: 7698/1: perf: fix group validation when using enable_on_exec

Yinghai Lu (1):
      PCI / ACPI: Don't query OSC support with all possible controls

Yogesh Ashok Powar (2):
      mwifiex: Use pci_release_region() instead of a pci_release_regions()
      mwifiex: Call pci_release_region after calling pci_disable_device

Zhao Hongjiang (2):
      aio: fix possible invalid memory access when DEBUG is enabled
      inotify: invalid mask should return a error number but not set it

nikolay@redhat.com (2):
      bonding: fix bonding_masters race condition in bond unloading
      bonding: IFF_BONDING is not stripped on enslave failure

[PATCH 001/118] ath9k_htc: accept 1.x firmware newer than 1.3

[Luis Henriques]

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

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

From: Felix Fietkau <nbd@openwrt.org>

commit 319e7bd96aca64a478f3aad40711c928405b8b77 upstream.

Since the firmware has been open sourced, the minor version has been
bumped to 1.4 and the API/ABI will stay compatible across further 1.x
releases.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index 25213d5..21c280b 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -774,7 +774,7 @@ static int ath9k_init_firmware_version(struct ath9k_htc_priv *priv)
 	 * required version.
 	 */
 	if (priv->fw_version_major != MAJOR_VERSION_REQ ||
-	    priv->fw_version_minor != MINOR_VERSION_REQ) {
+	    priv->fw_version_minor < MINOR_VERSION_REQ) {
 		dev_err(priv->dev, "ath9k_htc: Please upgrade to FW version %d.%d\n",
 			MAJOR_VERSION_REQ, MINOR_VERSION_REQ);
 		return -EINVAL;
-- 
1.8.1.2

[PATCH 002/118] ssb: implement spurious tone avoidance

[Luis Henriques]

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

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

From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <zajec5@gmail.com>

commit 46fc4c909339f5a84d1679045297d9d2fb596987 upstream.

And make use of it in b43. This fixes a regression introduced with
49d55cef5b1925a5c1efb6aaddaa40fc7c693335
b43: N-PHY: implement spurious tone avoidance
This commit made BCM4322 use only MCS 0 on channel 13, which of course
resulted in performance drop (down to 0.7Mb/s).

Reported-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/b43/phy_n.c          |  3 ++-
 drivers/ssb/driver_chipcommon_pmu.c       | 29 +++++++++++++++++++++++++++++
 include/linux/ssb/ssb_driver_chipcommon.h |  2 ++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 6be2f73..4ce3e1f 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -4582,7 +4582,8 @@ static void b43_nphy_pmu_spur_avoid(struct b43_wldev *dev, bool avoid)
 #endif
 #ifdef CONFIG_B43_SSB
 	case B43_BUS_SSB:
-		/* FIXME */
+		ssb_pmu_spuravoid_pllupdate(&dev->dev->sdev->bus->chipco,
+					    avoid);
 		break;
 #endif
 	}
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index b58fef7..1fb9b22 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -645,3 +645,32 @@ u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc)
 		return 0;
 	}
 }
+
+void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid)
+{
+	u32 pmu_ctl = 0;
+
+	switch (cc->dev->bus->chip_id) {
+	case 0x4322:
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL0, 0x11100070);
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL1, 0x1014140a);
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL5, 0x88888854);
+		if (spuravoid == 1)
+			ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05201828);
+		else
+			ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05001828);
+		pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD;
+		break;
+	case 43222:
+		/* TODO: BCM43222 requires updating PLLs too */
+		return;
+	default:
+		ssb_printk(KERN_ERR PFX
+			   "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
+			   cc->dev->bus->chip_id);
+		return;
+	}
+
+	chipco_set32(cc, SSB_CHIPCO_PMU_CTL, pmu_ctl);
+}
+EXPORT_SYMBOL_GPL(ssb_pmu_spuravoid_pllupdate);
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index 1a6b004..29ce7e4 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -219,6 +219,7 @@
 #define SSB_CHIPCO_PMU_CTL			0x0600 /* PMU control */
 #define  SSB_CHIPCO_PMU_CTL_ILP_DIV		0xFFFF0000 /* ILP div mask */
 #define  SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT	16
+#define  SSB_CHIPCO_PMU_CTL_PLL_UPD		0x00000400
 #define  SSB_CHIPCO_PMU_CTL_NOILPONW		0x00000200 /* No ILP on wait */
 #define  SSB_CHIPCO_PMU_CTL_HTREQEN		0x00000100 /* HT req enable */
 #define  SSB_CHIPCO_PMU_CTL_ALPREQEN		0x00000080 /* ALP req enable */
@@ -661,5 +662,6 @@ enum ssb_pmu_ldo_volt_id {
 void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc,
 			     enum ssb_pmu_ldo_volt_id id, u32 voltage);
 void ssb_pmu_set_ldo_paref(struct ssb_chipcommon *cc, bool on);
+void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid);
 
 #endif /* LINUX_SSB_CHIPCO_H_ */
-- 
1.8.1.2

[PATCH 003/118] can: mcp251x: add missing IRQF_ONESHOT to request_threaded_irq

[Luis Henriques]

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

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

From: Marc Kleine-Budde <mkl@pengutronix.de>

commit db388d6460ffa53b3b38429da6f70a913f89b048 upstream.

Since commit:

    1c6c695 genirq: Reject bogus threaded irq requests

threaded irqs must provide a primary handler or set the IRQF_ONESHOT flag.
Since the mcp251x driver doesn't make use of a primary handler set the
IRQF_ONESHOT flag.

Reported-by: Mylene Josserand <Mylene.Josserand@navocap.com>
Tested-by: Mylene Josserand <Mylene.Josserand@navocap.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/can/mcp251x.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c
index 9d60742..a17c048 100644
--- a/drivers/net/can/mcp251x.c
+++ b/drivers/net/can/mcp251x.c
@@ -922,6 +922,7 @@ static int mcp251x_open(struct net_device *net)
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
 	struct mcp251x_platform_data *pdata = spi->dev.platform_data;
+	unsigned long flags;
 	int ret;
 
 	ret = open_candev(net);
@@ -938,9 +939,14 @@ static int mcp251x_open(struct net_device *net)
 	priv->tx_skb = NULL;
 	priv->tx_len = 0;
 
+	flags = IRQF_ONESHOT;
+	if (pdata->irq_flags)
+		flags |= pdata->irq_flags;
+	else
+		flags |= IRQF_TRIGGER_FALLING;
+
 	ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist,
-		  pdata->irq_flags ? pdata->irq_flags : IRQF_TRIGGER_FALLING,
-		  DEVICE_NAME, priv);
+				   flags, DEVICE_NAME, priv);
 	if (ret) {
 		dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
 		if (pdata->transceiver_enable)
-- 
1.8.1.2

[PATCH 004/118] can: sja1000: fix handling on dt properties on little endian systems

[Luis Henriques]

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

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

From: Christoph Fritz <chf.fritz@googlemail.com>

commit 0443de5fbf224abf41f688d8487b0c307dc5a4b4 upstream.

To get correct endianes on little endian cpus (like arm) while reading device
tree properties, this patch replaces of_get_property() with
of_property_read_u32(). While there use of_property_read_bool() for the
handling of the boolean "nxp,no-comparator-bypass" property.

Signed-off-by: Christoph Fritz <chf.fritz@googlemail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/can/sja1000/sja1000_of_platform.c | 31 +++++++++++++--------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c
index f2683eb..c505b55 100644
--- a/drivers/net/can/sja1000/sja1000_of_platform.c
+++ b/drivers/net/can/sja1000/sja1000_of_platform.c
@@ -94,8 +94,8 @@ static int __devinit sja1000_ofp_probe(struct platform_device *ofdev)
 	struct net_device *dev;
 	struct sja1000_priv *priv;
 	struct resource res;
-	const u32 *prop;
-	int err, irq, res_size, prop_size;
+	u32 prop;
+	int err, irq, res_size;
 	void __iomem *base;
 
 	err = of_address_to_resource(np, 0, &res);
@@ -136,27 +136,27 @@ static int __devinit sja1000_ofp_probe(struct platform_device *ofdev)
 	priv->read_reg = sja1000_ofp_read_reg;
 	priv->write_reg = sja1000_ofp_write_reg;
 
-	prop = of_get_property(np, "nxp,external-clock-frequency", &prop_size);
-	if (prop && (prop_size ==  sizeof(u32)))
-		priv->can.clock.freq = *prop / 2;
+	err = of_property_read_u32(np, "nxp,external-clock-frequency", &prop);
+	if (!err)
+		priv->can.clock.freq = prop / 2;
 	else
 		priv->can.clock.freq = SJA1000_OFP_CAN_CLOCK; /* default */
 
-	prop = of_get_property(np, "nxp,tx-output-mode", &prop_size);
-	if (prop && (prop_size == sizeof(u32)))
-		priv->ocr |= *prop & OCR_MODE_MASK;
+	err = of_property_read_u32(np, "nxp,tx-output-mode", &prop);
+	if (!err)
+		priv->ocr |= prop & OCR_MODE_MASK;
 	else
 		priv->ocr |= OCR_MODE_NORMAL; /* default */
 
-	prop = of_get_property(np, "nxp,tx-output-config", &prop_size);
-	if (prop && (prop_size == sizeof(u32)))
-		priv->ocr |= (*prop << OCR_TX_SHIFT) & OCR_TX_MASK;
+	err = of_property_read_u32(np, "nxp,tx-output-config", &prop);
+	if (!err)
+		priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK;
 	else
 		priv->ocr |= OCR_TX0_PULLDOWN; /* default */
 
-	prop = of_get_property(np, "nxp,clock-out-frequency", &prop_size);
-	if (prop && (prop_size == sizeof(u32)) && *prop) {
-		u32 divider = priv->can.clock.freq * 2 / *prop;
+	err = of_property_read_u32(np, "nxp,clock-out-frequency", &prop);
+	if (!err && prop) {
+		u32 divider = priv->can.clock.freq * 2 / prop;
 
 		if (divider > 1)
 			priv->cdr |= divider / 2 - 1;
@@ -166,8 +166,7 @@ static int __devinit sja1000_ofp_probe(struct platform_device *ofdev)
 		priv->cdr |= CDR_CLK_OFF; /* default */
 	}
 
-	prop = of_get_property(np, "nxp,no-comparator-bypass", NULL);
-	if (!prop)
+	if (!of_property_read_bool(np, "nxp,no-comparator-bypass"))
 		priv->cdr |= CDR_CBP; /* default */
 
 	priv->irq_flags = IRQF_SHARED;
-- 
1.8.1.2

[PATCH 005/118] ath9k_hw: change AR9580 initvals to fix a stability issue

[Luis Henriques]

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

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

From: Felix Fietkau <nbd@openwrt.org>

commit f09a878511997c25a76bf111a32f6b8345a701a5 upstream.

The hardware parsing of Control Wrapper Frames needs to be disabled, as
it has been causing spurious decryption error reports. The initvals for
other chips have been updated to disable it, but AR9580 was left out for
some reason.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
index 06b3f0d..c16bea4 100644
--- a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
@@ -648,7 +648,7 @@ static const u32 ar9580_1p0_mac_core[][2] = {
 	{0x00008258, 0x00000000},
 	{0x0000825c, 0x40000000},
 	{0x00008260, 0x00080922},
-	{0x00008264, 0x9bc00010},
+	{0x00008264, 0x9d400010},
 	{0x00008268, 0xffffffff},
 	{0x0000826c, 0x0000ffff},
 	{0x00008270, 0x00000000},
-- 
1.8.1.2

[PATCH 006/118] ARM: 7696/1: Fix kexec by setting outer_cache.inv_all for Feroceon

[Luis Henriques]

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

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

From: Illia Ragozin <illia.ragozin@grapecom.com>

commit cd272d1ea71583170e95dde02c76166c7f9017e6 upstream.

On Feroceon the L2 cache becomes non-coherent with the CPU
when the L1 caches are disabled. Thus the L2 needs to be invalidated
after both L1 caches are disabled.

On kexec before the starting the code for relocation the kernel,
the L1 caches are disabled in cpu_froc_fin (cpu_v7_proc_fin for Feroceon),
but after L2 cache is never invalidated, because inv_all is not set
in cache-feroceon-l2.c.
So kernel relocation and decompression may has (and usually has) errors.
Setting the function enables L2 invalidation and fixes the issue.

Signed-off-by: Illia Ragozin <illia.ragozin@grapecom.com>
Acked-by: Jason Cooper <jason@lakedaemon.net>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/mm/cache-feroceon-l2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dd3d591..48bc3c0 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 
-- 
1.8.1.2

[PATCH 007/118] ARM: 7698/1: perf: fix group validation when using enable_on_exec

[Luis Henriques]

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

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

From: Will Deacon <will.deacon@arm.com>

commit cb2d8b342aa084d1f3ac29966245dec9163677fb upstream.

Events may be created with attr->disabled == 1 and attr->enable_on_exec
== 1, which confuses the group validation code because events with the
PERF_EVENT_STATE_OFF are not considered candidates for scheduling, which
may lead to failure at group scheduling time.

This patch fixes the validation check for ARM, so that events in the
OFF state are still considered when enable_on_exec is true.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Reported-by: Sudeep KarkadaNagesha <Sudeep.KarkadaNagesha@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/kernel/perf_event.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index a02eada..952a5a7 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -319,7 +319,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct hw_perf_event fake_event = event->hw;
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
-- 
1.8.1.2

[PATCH 008/118] hugetlbfs: add swap entry check in follow_hugetlb_page()

[Luis Henriques]

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

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

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit 9cc3a5bd40067b9a0fbd49199d0780463fc2140f upstream.

With applying the previous patch "hugetlbfs: stop setting VM_DONTDUMP in
initializing vma(VM_HUGETLB)" to reenable hugepage coredump, if a memory
error happens on a hugepage and the affected processes try to access the
error hugepage, we hit VM_BUG_ON(atomic_read(&page->_count) <= 0) in
get_page().

The reason for this bug is that coredump-related code doesn't recognise
"hugepage hwpoison entry" with which a pmd entry is replaced when a memory
error occurs on a hugepage.

In other words, physical address information is stored in different bit
layout between hugepage hwpoison entry and pmd entry, so
follow_hugetlb_page() which is called in get_dump_page() returns a wrong
page from a given address.

The expected behavior is like this:

  absent   is_swap_pte   FOLL_DUMP   Expected behavior
  -------------------------------------------------------------------
   true     false         false       hugetlb_fault
   false    true          false       hugetlb_fault
   false    false         false       return page
   true     false         true        skip page (to avoid allocation)
   false    true          true        hugetlb_fault
   false    false         true        return page

With this patch, we can call hugetlb_fault() and take proper actions (we
wait for migration entries, fail with VM_FAULT_HWPOISON_LARGE for
hwpoisoned entries,) and as the result we can dump all hugepages except
for hwpoisoned ones.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 mm/hugetlb.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f30e463..74b8327 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2907,7 +2907,17 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
-		if (absent ||
+		/*
+		 * We need call hugetlb_fault for both hugepages under migration
+		 * (in which case hugetlb_fault waits for the migration,) and
+		 * hwpoisoned hugepages (in which case we need to prevent the
+		 * caller from accessing to them.) In order to do this, we use
+		 * here is_swap_pte instead of is_hugetlb_entry_migration and
+		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
+		 * both cases, and because we can't follow correct pages
+		 * directly from any kind of swap entries.
+		 */
+		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
 		    ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
-- 
1.8.1.2

[PATCH 009/118] kernel/signal.c: stop info leak via the tkill and the tgkill syscalls

[Luis Henriques]

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

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

From: Emese Revfy <re.emese@gmail.com>

commit b9e146d8eb3b9ecae5086d373b50fa0c1f3e7f0f upstream.

This fixes a kernel memory contents leak via the tkill and tgkill syscalls
for compat processes.

This is visible in the siginfo_t->_sifields._rt.si_sigval.sival_ptr field
when handling signals delivered from tkill.

The place of the infoleak:

int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
{
        ...
        put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
        ...
}

Signed-off-by: Emese Revfy <re.emese@gmail.com>
Reviewed-by: PaX Team <pageexec@freemail.hu>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/signal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index 0e9b729..c0356f9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2885,7 +2885,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 
 static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
-	struct siginfo info;
+	struct siginfo info = {};
 
 	info.si_signo = sig;
 	info.si_errno = 0;
-- 
1.8.1.2

[PATCH 010/118] hfsplus: fix potential overflow in hfsplus_file_truncate()

[Luis Henriques]

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

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

From: Vyacheslav Dubeyko <slava@dubeyko.com>

commit 12f267a20aecf8b84a2a9069b9011f1661c779b4 upstream.

Change a u32 to loff_t hfsplus_file_truncate().

Signed-off-by: Vyacheslav Dubeyko <slava@dubeyko.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Hin-Tak Leung <htl10@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/hfsplus/extents.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 5849e3e..32b12e5 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -517,7 +517,7 @@ void hfsplus_file_truncate(struct inode *inode)
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
-		u32 size = inode->i_size;
+		loff_t size = inode->i_size;
 
 		res = pagecache_write_begin(NULL, mapping, size, 0,
 						AOP_FLAG_UNINTERRUPTIBLE,
-- 
1.8.1.2

[PATCH 011/118] sched: Convert BUG_ON()s in try_to_wake_up_local() to WARN_ON_ONCE()s

[Luis Henriques]

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

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

From: Tejun Heo <tj@kernel.org>

commit 383efcd00053ec40023010ce5034bd702e7ab373 upstream.

try_to_wake_up_local() should only be invoked to wake up another
task in the same runqueue and BUG_ON()s are used to enforce the
rule. Missing try_to_wake_up_local() can stall workqueue
execution but such stalls are likely to be finite either by
another work item being queued or the one blocked getting
unblocked.  There's no reason to trigger BUG while holding rq
lock crashing the whole system.

Convert BUG_ON()s in try_to_wake_up_local() to WARN_ON_ONCE()s.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20130318192234.GD3042@htj.dyndns.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/sched/core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3231df8..473cac3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1651,8 +1651,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
 
-	BUG_ON(rq != this_rq());
-	BUG_ON(p == current);
+	if (WARN_ON_ONCE(rq != this_rq()) ||
+	    WARN_ON_ONCE(p == current))
+		return;
+
 	lockdep_assert_held(&rq->lock);
 
 	if (!raw_spin_trylock(&p->pi_lock)) {
-- 
1.8.1.2

[PATCH 012/118] crypto: algif - suppress sending source address information in recvmsg

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 72a763d805a48ac8c0bf48fdb510e84c12de51fe upstream.

The current code does not set the msg_namelen member to 0 and therefore
makes net/socket.c leak the local sockaddr_storage variable to userland
-- 128 bytes of kernel stack memory. Fix that.

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 crypto/algif_hash.c     | 2 ++
 crypto/algif_skcipher.c | 1 +
 2 files changed, 3 insertions(+)

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index ef5356c..0262210 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -161,6 +161,8 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
 	else if (len < ds)
 		msg->msg_flags |= MSG_TRUNC;
 
+	msg->msg_namelen = 0;
+
 	lock_sock(sk);
 	if (ctx->more) {
 		ctx->more = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 6a6dfc0..a1c4f0a 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -432,6 +432,7 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 	long copied = 0;
 
 	lock_sock(sk);
+	msg->msg_namelen = 0;
 	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
-- 
1.8.1.2

[PATCH 012/118] crypto: algif - suppress sending source address information in recvmsg

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 72a763d805a48ac8c0bf48fdb510e84c12de51fe upstream.

The current code does not set the msg_namelen member to 0 and therefore
makes net/socket.c leak the local sockaddr_storage variable to userland
-- 128 bytes of kernel stack memory. Fix that.

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 crypto/algif_hash.c     | 2 ++
 crypto/algif_skcipher.c | 1 +
 2 files changed, 3 insertions(+)

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index ef5356c..0262210 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -161,6 +161,8 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
 	else if (len < ds)
 		msg->msg_flags |= MSG_TRUNC;
 
+	msg->msg_namelen = 0;
+
 	lock_sock(sk);
 	if (ctx->more) {
 		ctx->more = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 6a6dfc0..a1c4f0a 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -432,6 +432,7 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 	long copied = 0;
 
 	lock_sock(sk);
+	msg->msg_namelen = 0;
 	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
-- 
1.8.1.2

[PATCH 013/118] perf: Treat attr.config as u64 in perf_swevent_init()

[Luis Henriques]

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

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

From: Tommi Rantala <tt.rantala@gmail.com>

commit 8176cced706b5e5d15887584150764894e94e02f upstream.

Trinity discovered that we fail to check all 64 bits of
attr.config passed by user space, resulting to out-of-bounds
access of the perf_swevent_enabled array in
sw_perf_event_destroy().

Introduced in commit b0a873ebb ("perf: Register PMU
implementations").

Signed-off-by: Tommi Rantala <tt.rantala@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Link: http://lkml.kernel.org/r/1365882554-30259-1-git-send-email-tt.rantala@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 11409af..0181cbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5129,7 +5129,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 
 static int perf_swevent_init(struct perf_event *event)
 {
-	int event_id = event->attr.config;
+	u64 event_id = event->attr.config;
 
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
-- 
1.8.1.2

[PATCH 014/118] perf/x86: Fix offcore_rsp valid mask for SNB/IVB

[Luis Henriques]

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

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

From: Stephane Eranian <eranian@google.com>

commit f1923820c447e986a9da0fc6bf60c1dccdf0408e upstream.

The valid mask for both offcore_response_0 and
offcore_response_1 was wrong for SNB/SNB-EP,
IVB/IVB-EP. It was possible to write to
reserved bit and cause a GP fault crashing
the kernel.

This patch fixes the problem by correctly marking the
reserved bits in the valid mask for all the processors
mentioned above.

A distinction between desktop and server parts is introduced
because bits 24-30 are only available on the server parts.

This version of the  patch is just a rebase to perf/urgent tree
and should apply to older kernels as well.

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: jolsa@redhat.com
Cc: gregkh@linuxfoundation.org
Cc: security@kernel.org
Cc: ak@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[ luis: backport to 3.5: dropped IvyBridge changes ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 187c294..54082f7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -126,8 +126,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -1920,7 +1926,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 45)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
-- 
1.8.1.2

[PATCH 015/118] vm: add vm_iomap_memory() helper function

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit b4cbb197c7e7a68dbad0d491242e3ca67420c13e upstream.

Various drivers end up replicating the code to mmap() their memory
buffers into user space, and our core memory remapping function may be
very flexible but it is unnecessarily complicated for the common cases
to use.

Our internal VM uses pfn's ("page frame numbers") which simplifies
things for the VM, and allows us to pass physical addresses around in a
denser and more efficient format than passing a "phys_addr_t" around,
and having to shift it up and down by the page size.  But it just means
that drivers end up doing that shifting instead at the interface level.

It also means that drivers end up mucking around with internal VM things
like the vma details (vm_pgoff, vm_start/end) way more than they really
need to.

So this just exports a function to map a certain physical memory range
into user space (using a phys_addr_t based interface that is much more
natural for a driver) and hides all the complexity from the driver.
Some drivers will still end up tweaking the vm_page_prot details for
things like prefetching or cacheability etc, but that's actually
relevant to the driver, rather than caring about what the page offset of
the mapping is into the particular IO memory region.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/mm.h |  2 ++
 mm/memory.c        | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f9f279c..920beba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1503,6 +1503,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
+
 
 struct page *follow_page(struct vm_area_struct *, unsigned long address,
 			unsigned int foll_flags);
diff --git a/mm/memory.c b/mm/memory.c
index b1014bf..05414ef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2334,6 +2334,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long vm_len, pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start + len < start)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	len += start & ~PAGE_MASK;
+	pfn = start >> PAGE_SHIFT;
+	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vma->vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vma->vm_pgoff;
+	pages -= vma->vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	vm_len = vma->vm_end - vma->vm_start;
+	if (vm_len >> PAGE_SHIFT > pages)
+		return -EINVAL;
+
+	/* Ok, let it rip */
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
-- 
1.8.1.2

[PATCH 016/118] vm: convert HPET mmap to vm_iomap_memory() helper

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 2323036dfec8ce3ce6e1c86a49a31b039f3300d1 upstream.

This is my example conversion of a few existing mmap users.  The HPET
case is simple, widely available, and easy to test (Clemens Ladisch sent
a trivial test-program for it).

Test-program-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/char/hpet.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index dfd7876..0ff5c2e 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -373,26 +373,14 @@ static int hpet_mmap(struct file *file, struct vm_area_struct *vma)
 	struct hpet_dev *devp;
 	unsigned long addr;
 
-	if (((vma->vm_end - vma->vm_start) != PAGE_SIZE) || vma->vm_pgoff)
-		return -EINVAL;
-
 	devp = file->private_data;
 	addr = devp->hd_hpets->hp_hpet_phys;
 
 	if (addr & (PAGE_SIZE - 1))
 		return -ENOSYS;
 
-	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (io_remap_pfn_range(vma, vma->vm_start, addr >> PAGE_SHIFT,
-					PAGE_SIZE, vma->vm_page_prot)) {
-		printk(KERN_ERR "%s: io_remap_pfn_range failed\n",
-			__func__);
-		return -EAGAIN;
-	}
-
-	return 0;
+	return vm_iomap_memory(vma, addr, PAGE_SIZE);
 #else
 	return -ENOSYS;
 #endif
-- 
1.8.1.2

[PATCH 017/118] vm: convert fb_mmap to vm_iomap_memory() helper

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit fc9bbca8f650e5f738af8806317c0a041a48ae4a upstream.

This is my example conversion of a few existing mmap users.  The
fb_mmap() case is a good example because it is a bit more complicated
than some: fb_mmap() mmaps one of two different memory areas depending
on the page offset of the mmap (but happily there is never any mixing of
the two, so the helper function still works).

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/video/fbmem.c | 40 ++++++++++++++--------------------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index e4cc585..0a49456 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1373,15 +1373,12 @@ fb_mmap(struct file *file, struct vm_area_struct * vma)
 {
 	struct fb_info *info = file_fb_info(file);
 	struct fb_ops *fb;
-	unsigned long off;
+	unsigned long mmio_pgoff;
 	unsigned long start;
 	u32 len;
 
 	if (!info)
 		return -ENODEV;
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
-		return -EINVAL;
-	off = vma->vm_pgoff << PAGE_SHIFT;
 	fb = info->fbops;
 	if (!fb)
 		return -ENODEV;
@@ -1393,33 +1390,24 @@ fb_mmap(struct file *file, struct vm_area_struct * vma)
 		return res;
 	}
 
-	/* frame buffer memory */
+	/*
+	 * Ugh. This can be either the frame buffer mapping, or
+	 * if pgoff points past it, the mmio mapping.
+	 */
 	start = info->fix.smem_start;
-	len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.smem_len);
-	if (off >= len) {
-		/* memory mapped io */
-		off -= len;
-		if (info->var.accel_flags) {
-			mutex_unlock(&info->mm_lock);
-			return -EINVAL;
-		}
+	len = info->fix.smem_len;
+	mmio_pgoff = PAGE_ALIGN((start & ~PAGE_MASK) + len) >> PAGE_SHIFT;
+	if (vma->vm_pgoff >= mmio_pgoff) {
+		vma->vm_pgoff -= mmio_pgoff;
 		start = info->fix.mmio_start;
-		len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.mmio_len);
+		len = info->fix.mmio_len;
 	}
 	mutex_unlock(&info->mm_lock);
-	start &= PAGE_MASK;
-	if ((vma->vm_end - vma->vm_start + off) > len)
-		return -EINVAL;
-	off += start;
-	vma->vm_pgoff = off >> PAGE_SHIFT;
-	/* This is an IO map - tell maydump to skip this VMA */
-	vma->vm_flags |= VM_IO | VM_RESERVED;
+
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-	fb_pgprotect(file, vma, off);
-	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-			     vma->vm_end - vma->vm_start, vma->vm_page_prot))
-		return -EAGAIN;
-	return 0;
+	fb_pgprotect(file, vma, start);
+
+	return vm_iomap_memory(vma, start, len);
 }
 
 static int
-- 
1.8.1.2

[PATCH 018/118] vm: convert snd_pcm_lib_mmap_iomem() to vm_iomap_memory() helper

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 0fe09a45c4848b5b5607b968d959fdc1821c161d upstream.

This is my example conversion of a few existing mmap users.  The pcm
mmap case is one of the more straightforward ones.

Acked-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 sound/core/pcm_native.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index bf3bf43..7203c9a 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3219,18 +3219,10 @@ EXPORT_SYMBOL_GPL(snd_pcm_lib_default_mmap);
 int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream,
 			   struct vm_area_struct *area)
 {
-	long size;
-	unsigned long offset;
+	struct snd_pcm_runtime *runtime = substream->runtime;;
 
 	area->vm_page_prot = pgprot_noncached(area->vm_page_prot);
-	area->vm_flags |= VM_IO;
-	size = area->vm_end - area->vm_start;
-	offset = area->vm_pgoff << PAGE_SHIFT;
-	if (io_remap_pfn_range(area, area->vm_start,
-				(substream->runtime->dma_addr + offset) >> PAGE_SHIFT,
-				size, area->vm_page_prot))
-		return -EAGAIN;
-	return 0;
+	return vm_iomap_memory(area, runtime->dma_addr, runtime->dma_bytes);
 }
 
 EXPORT_SYMBOL(snd_pcm_lib_mmap_iomem);
-- 
1.8.1.2

[PATCH 019/118] vm: convert mtdchar mmap to vm_iomap_memory() helper

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 8558e4a26b00225efeb085725bc319f91201b239 upstream.

This is my example conversion of a few existing mmap users.  The mtdchar
case is actually disabled right now (and stays disabled), but I did it
because it showed up on my "git grep", and I was familiar with the code
due to fixing an overflow problem in the code in commit 9c603e53d380
("mtdchar: fix offset overflow detection").

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/mtd/mtdchar.c | 23 ++---------------------
 1 file changed, 2 insertions(+), 21 deletions(-)

diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 2cfb1a8..9e33653 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -1132,36 +1132,17 @@ static int mtdchar_mmap(struct file *file, struct vm_area_struct *vma)
 	struct mtd_file_info *mfi = file->private_data;
 	struct mtd_info *mtd = mfi->mtd;
 	struct map_info *map = mtd->priv;
-	unsigned long start;
-	unsigned long off;
-	u32 len;
 
         /* This is broken because it assumes the MTD device is map-based
 	   and that mtd->priv is a valid struct map_info.  It should be
 	   replaced with something that uses the mtd_get_unmapped_area()
 	   operation properly. */
 	if (0 /*mtd->type == MTD_RAM || mtd->type == MTD_ROM*/) {
-		off = vma->vm_pgoff << PAGE_SHIFT;
-		start = map->phys;
-		len = PAGE_ALIGN((start & ~PAGE_MASK) + map->size);
-		start &= PAGE_MASK;
-		if ((vma->vm_end - vma->vm_start + off) > len)
-			return -EINVAL;
-
-		off += start;
-		vma->vm_pgoff = off >> PAGE_SHIFT;
-		vma->vm_flags |= VM_IO | VM_RESERVED;
-
 #ifdef pgprot_noncached
-		if (file->f_flags & O_DSYNC || off >= __pa(high_memory))
+		if (file->f_flags & O_DSYNC || map->phys >= __pa(high_memory))
 			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 #endif
-		if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-				       vma->vm_end - vma->vm_start,
-				       vma->vm_page_prot))
-			return -EAGAIN;
-
-		return 0;
+		return vm_iomap_memory(vma, map->phys, map->size);
 	}
 	return -ENOSYS;
 #else
-- 
1.8.1.2

[PATCH 020/118] regulator: fixed regulator_bulk_enable unwinding code

[Luis Henriques]

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

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

From: Andrzej Hajda <a.hajda@samsung.com>

commit fbe31057fafebdc2811a7101b8b4a0460f5417d1 upstream.

Unwinding code disables all successfully enabled regulators.
Error is logged for every failed regulator.

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Jonghwan Choi <jhbird.choi@samsung.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/regulator/core.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 8b4b382..4a4d12e 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2769,9 +2769,13 @@ int regulator_bulk_enable(int num_consumers,
 	return 0;
 
 err:
-	pr_err("Failed to enable %s: %d\n", consumers[i].supply, ret);
-	while (--i >= 0)
-		regulator_disable(consumers[i].consumer);
+	for (i = 0; i < num_consumers; i++) {
+		if (consumers[i].ret < 0)
+			pr_err("Failed to enable %s: %d\n", consumers[i].supply,
+			       consumers[i].ret);
+		else
+			regulator_disable(consumers[i].consumer);
+	}
 
 	return ret;
 }
-- 
1.8.1.2

[PATCH 021/118] perf: Fix error return code

[Luis Henriques]

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

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

From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>

commit c481420248c6730246d2a1b1773d5d7007ae0835 upstream.

Fix to return -ENOMEM in the allocation error case instead of 0
(if pmu_bus_running == 1), as done elsewhere in this function.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: a.p.zijlstra@chello.nl
Cc: paulus@samba.org
Cc: acme@ghostprotocols.net
Link: http://lkml.kernel.org/r/CAPgLHd8j_fWcgqe%3DKLWjpBj%2B%3Do0Pw6Z-SEq%3DNTPU08c2w1tngQ@mail.gmail.com
[ Tweaked the error code setting placement and the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jonghwan Choi <jhbird.choi@samsung.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/events/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0181cbd..1a6deb7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5763,6 +5763,7 @@ skip_type:
 	if (pmu->pmu_cpu_context)
 		goto got_cpu_context;
 
+	ret = -ENOMEM;
 	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
 	if (!pmu->pmu_cpu_context)
 		goto free_dev;
-- 
1.8.1.2

[PATCH 022/118] xen/smp: Fix leakage of timer interrupt line for every CPU online/offline.

[Luis Henriques]

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

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

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

commit 888b65b4bc5e7fcbbb967023300cd5d44dba1950 upstream.

In the PVHVM path when we do CPU online/offline path we would
leak the timer%d IRQ line everytime we do a offline event. The
online path (xen_hvm_setup_cpu_clockevents via
x86_cpuinit.setup_percpu_clockev) would allocate a new interrupt
line for the timer%d.

But we would still use the old interrupt line leading to:

kernel BUG at /home/konrad/ssd/konrad/linux/kernel/hrtimer.c:1261!
invalid opcode: 0000 [#1] SMP
RIP: 0010:[<ffffffff810b9e21>]  [<ffffffff810b9e21>] hrtimer_interrupt+0x261/0x270
.. snip..
 <IRQ>
 [<ffffffff810445ef>] xen_timer_interrupt+0x2f/0x1b0
 [<ffffffff81104825>] ? stop_machine_cpu_stop+0xb5/0xf0
 [<ffffffff8111434c>] handle_irq_event_percpu+0x7c/0x240
 [<ffffffff811175b9>] handle_percpu_irq+0x49/0x70
 [<ffffffff813a74a3>] __xen_evtchn_do_upcall+0x1c3/0x2f0
 [<ffffffff813a760a>] xen_evtchn_do_upcall+0x2a/0x40
 [<ffffffff8167c26d>] xen_hvm_callback_vector+0x6d/0x80
 <EOI>
 [<ffffffff81666d01>] ? start_secondary+0x193/0x1a8
 [<ffffffff81666cfd>] ? start_secondary+0x18f/0x1a8

There is also the oddity (timer1) in the /proc/interrupts after
offlining CPU1:

  64:       1121          0  xen-percpu-virq      timer0
  78:          0          0  xen-percpu-virq      timer1
  84:          0       2483  xen-percpu-virq      timer2

This patch fixes it.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/xen/smp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index afb250d..150178e 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -669,6 +669,7 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+	xen_teardown_timer(cpu);
 	native_cpu_die(cpu);
 }
 
-- 
1.8.1.2

[PATCH 023/118] xen/smp/spinlock: Fix leakage of the spinlock interrupt line for every CPU online/offline

[Luis Henriques]

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

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

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

commit 66ff0fe9e7bda8aec99985b24daad03652f7304e upstream.

While we don't use the spinlock interrupt line (see for details
commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 -
xen: disable PV spinlocks on HVM) - we should still do the proper
init / deinit sequence. We did not do that correctly and for the
CPU init for PVHVM guest we would allocate an interrupt line - but
failed to deallocate the old interrupt line.

This resulted in leakage of an irq_desc but more importantly this splat
as we online an offlined CPU:

genirq: Flags mismatch irq 71. 0002cc20 (spinlock1) vs. 0002cc20 (spinlock1)
Pid: 2542, comm: init.late Not tainted 3.9.0-rc6upstream #1
Call Trace:
 [<ffffffff811156de>] __setup_irq+0x23e/0x4a0
 [<ffffffff81194191>] ? kmem_cache_alloc_trace+0x221/0x250
 [<ffffffff811161bb>] request_threaded_irq+0xfb/0x160
 [<ffffffff8104c6f0>] ? xen_spin_trylock+0x20/0x20
 [<ffffffff813a8423>] bind_ipi_to_irqhandler+0xa3/0x160
 [<ffffffff81303758>] ? kasprintf+0x38/0x40
 [<ffffffff8104c6f0>] ? xen_spin_trylock+0x20/0x20
 [<ffffffff810cad35>] ? update_max_interval+0x15/0x40
 [<ffffffff816605db>] xen_init_lock_cpu+0x3c/0x78
 [<ffffffff81660029>] xen_hvm_cpu_notify+0x29/0x33
 [<ffffffff81676bdd>] notifier_call_chain+0x4d/0x70
 [<ffffffff810bb2a9>] __raw_notifier_call_chain+0x9/0x10
 [<ffffffff8109402b>] __cpu_notify+0x1b/0x30
 [<ffffffff8166834a>] _cpu_up+0xa0/0x14b
 [<ffffffff816684ce>] cpu_up+0xd9/0xec
 [<ffffffff8165f754>] store_online+0x94/0xd0
 [<ffffffff8141d15b>] dev_attr_store+0x1b/0x20
 [<ffffffff81218f44>] sysfs_write_file+0xf4/0x170
 [<ffffffff811a2864>] vfs_write+0xb4/0x130
 [<ffffffff811a302a>] sys_write+0x5a/0xa0
 [<ffffffff8167ada9>] system_call_fastpath+0x16/0x1b
cpu 1 spinlock event irq -16
smpboot: Booting Node 0 Processor 1 APIC 0x2

And if one looks at the /proc/interrupts right after
offlining (CPU1):

  70:          0          0  xen-percpu-ipi       spinlock0
  71:          0          0  xen-percpu-ipi       spinlock1
  77:          0          0  xen-percpu-ipi       spinlock2

There is the oddity of the 'spinlock1' still being present.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/xen/smp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 150178e..caeff44 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -669,6 +669,7 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
 	unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
+	xen_uninit_lock_cpu(cpu);
 	xen_teardown_timer(cpu);
 	native_cpu_die(cpu);
 }
-- 
1.8.1.2

[PATCH 024/118] xen/time: Fix kasprintf splat when allocating timer%d IRQ line.

[Luis Henriques]

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

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

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

commit 7918c92ae9638eb8a6ec18e2b4a0de84557cccc8 upstream.

When we online the CPU, we get this splat:

smpboot: Booting Node 0 Processor 1 APIC 0x2
installing Xen timer for CPU 1
BUG: sleeping function called from invalid context at /home/konrad/ssd/konrad/linux/mm/slab.c:3179
in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/1
Pid: 0, comm: swapper/1 Not tainted 3.9.0-rc6upstream-00001-g3884fad #1
Call Trace:
 [<ffffffff810c1fea>] __might_sleep+0xda/0x100
 [<ffffffff81194617>] __kmalloc_track_caller+0x1e7/0x2c0
 [<ffffffff81303758>] ? kasprintf+0x38/0x40
 [<ffffffff813036eb>] kvasprintf+0x5b/0x90
 [<ffffffff81303758>] kasprintf+0x38/0x40
 [<ffffffff81044510>] xen_setup_timer+0x30/0xb0
 [<ffffffff810445af>] xen_hvm_setup_cpu_clockevents+0x1f/0x30
 [<ffffffff81666d0a>] start_secondary+0x19c/0x1a8

The solution to that is use kasprintf in the CPU hotplug path
that 'online's the CPU. That is, do it in in xen_hvm_cpu_notify,
and remove the call to in xen_hvm_setup_cpu_clockevents.

Unfortunatly the later is not a good idea as the bootup path
does not use xen_hvm_cpu_notify so we would end up never allocating
timer%d interrupt lines when booting. As such add the check for
atomic() to continue.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/x86/xen/enlighten.c | 5 ++++-
 arch/x86/xen/time.c      | 6 +++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 18b55fa..0b4f9c7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1533,8 +1533,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 		xen_vcpu_setup(cpu);
-		if (xen_have_vector_callback)
+		if (xen_have_vector_callback) {
 			xen_init_lock_cpu(cpu);
+			if (xen_feature(XENFEAT_hvm_safe_pvclock))
+				xen_setup_timer(cpu);
+		}
 		break;
 	default:
 		break;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0296a95..054cc01 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -497,7 +497,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 {
 	int cpu = smp_processor_id();
 	xen_setup_runstate_info(cpu);
-	xen_setup_timer(cpu);
+	/*
+	 * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence
+	 * doing it xen_hvm_cpu_notify (which gets called by smp_init during
+	 * early bootup and also during CPU hotplug events).
+	 */
 	xen_setup_cpu_clockevents();
 }
 
-- 
1.8.1.2

[PATCH 025/118] s390/memory hotplug: prevent offline of active memory increments

[Luis Henriques]

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

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

From: Heiko Carstens <heiko.carstens@de.ibm.com>

commit 94c163663fc1dcfc067a5fb3cc1446b9469975ce upstream.

In case a machine supports memory hotplug all active memory increments
present at IPL time have been initialized with a "usecount" of 1.
This is wrong if the memory increment size is larger than the memory
section size of the memory hotplug code. If that is the case the
usecount must be initialized with the number of memory sections that
fit into one memory increment.
Otherwise it is possible to put a memory increment into standby state
even if there are still active sections.
Afterwards addressing exceptions might happen which cause the kernel
to panic.
However even worse, if a memory increment was put into standby state
and afterwards into active state again, it's contents would have been
zeroed, leading to memory corruption.

This was only an issue for machines that support standby memory and
have at least 256GB memory.

This is broken since commit fdb1bb15 "[S390] sclp/memory hotplug: fix
initial usecount of increments".

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/s390/char/sclp_cmd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 766cb7b..1845ab5 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -529,6 +529,8 @@ static void __init sclp_add_standby_memory(void)
 	add_memory_merged(0);
 }
 
+#define MEM_SCT_SIZE (1UL << SECTION_SIZE_BITS)
+
 static void __init insert_increment(u16 rn, int standby, int assigned)
 {
 	struct memory_increment *incr, *new_incr;
@@ -541,7 +543,7 @@ static void __init insert_increment(u16 rn, int standby, int assigned)
 	new_incr->rn = rn;
 	new_incr->standby = standby;
 	if (!standby)
-		new_incr->usecount = 1;
+		new_incr->usecount = rzm > MEM_SCT_SIZE ? rzm/MEM_SCT_SIZE : 1;
 	last_rn = 0;
 	prev = &sclp_mem_list;
 	list_for_each_entry(incr, &sclp_mem_list, list) {
-- 
1.8.1.2

[PATCH 026/118] aio: fix possible invalid memory access when DEBUG is enabled

[Luis Henriques]

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

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

From: Zhao Hongjiang <zhaohongjiang@huawei.com>

commit 91d80a84bbc8f28375cca7e65ec666577b4209ad upstream.

dprintk() shouldn't access @ring after it's unmapped.

Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/aio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/aio.c b/fs/aio.c
index 55c4c76..cf8e5a7 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1094,9 +1094,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 	spin_unlock(&info->ring_lock);
 
 out:
-	kunmap_atomic(ring);
 	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
 		 (unsigned long)ring->head, (unsigned long)ring->tail);
+	kunmap_atomic(ring);
 	return ret;
 }
 
-- 
1.8.1.2

[PATCH 027/118] TTY: do not update atime/mtime on read/write

[Luis Henriques]

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

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

From: Jiri Slaby <jslaby@suse.cz>

commit b0de59b5733d18b0d1974a060860a8b5c1b36a2e upstream.

On http://vladz.devzero.fr/013_ptmx-timing.php, we can see how to find
out length of a password using timestamps of /dev/ptmx. It is
documented in "Timing Analysis of Keystrokes and Timing Attacks on
SSH". To avoid that problem, do not update time when reading
from/writing to a TTY.

I am afraid of regressions as this is a behavior we have since 0.97
and apps may expect the time to be current, e.g. for monitoring
whether there was a change on the TTY. Now, there is no change. So
this would better have a lot of testing before it goes upstream.

References: CVE-2013-0160

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/tty/tty_io.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index b425c79..e0767b7 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -975,8 +975,7 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count,
 	else
 		i = -EIO;
 	tty_ldisc_deref(ld);
-	if (i > 0)
-		inode->i_atime = current_fs_time(inode->i_sb);
+
 	return i;
 }
 
@@ -1077,11 +1076,8 @@ static inline ssize_t do_tty_write(
 			break;
 		cond_resched();
 	}
-	if (written) {
-		struct inode *inode = file->f_path.dentry->d_inode;
-		inode->i_mtime = current_fs_time(inode->i_sb);
+	if (written)
 		ret = written;
-	}
 out:
 	tty_write_unlock(tty);
 	return ret;
-- 
1.8.1.2

[PATCH 028/118] TTY: fix atime/mtime regression

[Luis Henriques]

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

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

From: Jiri Slaby <jslaby@suse.cz>

commit 37b7f3c76595e23257f61bd80b223de8658617ee upstream.

In commit b0de59b5733d ("TTY: do not update atime/mtime on read/write")
we removed timestamps from tty inodes to fix a security issue and waited
if something breaks.  Well, 'w', the utility to find out logged users
and their inactivity time broke.  It shows that users are inactive since
the time they logged in.

To revert to the old behaviour while still preventing attackers to
guess the password length, we update the timestamps in one-minute
intervals by this patch.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: backport to 3.5: don't use file_inode() ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/tty/tty_io.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index e0767b7..95a37fa 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -939,6 +939,14 @@ void start_tty(struct tty_struct *tty)
 
 EXPORT_SYMBOL(start_tty);
 
+static void tty_update_time(struct timespec *time)
+{
+	unsigned long sec = get_seconds();
+	sec -= sec % 60;
+	if ((long)(sec - time->tv_sec) > 0)
+		time->tv_sec = sec;
+}
+
 /**
  *	tty_read	-	read method for tty device files
  *	@file: pointer to tty file
@@ -976,6 +984,9 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count,
 		i = -EIO;
 	tty_ldisc_deref(ld);
 
+	if (i > 0)
+		tty_update_time(&inode->i_atime);
+
 	return i;
 }
 
@@ -1076,8 +1087,11 @@ static inline ssize_t do_tty_write(
 			break;
 		cond_resched();
 	}
-	if (written)
+	if (written) {
+		struct inode *inode = file->f_path.dentry->d_inode;
+		tty_update_time(&inode->i_mtime);
 		ret = written;
+	}
 out:
 	tty_write_unlock(tty);
 	return ret;
-- 
1.8.1.2

[PATCH 029/118] atm: update msg_namelen in vcc_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 9b3e617f3df53822345a8573b6d358f6b9e5ed87 upstream.

The current code does not fill the msg_name member in case it is set.
It also does not set the msg_namelen member to 0 and therefore makes
net/socket.c leak the local, uninitialized sockaddr_storage variable
to userland -- 128 bytes of kernel stack memory.

Fix that by simply setting msg_namelen to 0 as obviously nobody cared
about vcc_recvmsg() not filling the msg_name in case it was set.

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/atm/common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/atm/common.c b/net/atm/common.c
index 0c0ad93..f0a9b7e 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -520,6 +520,8 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	struct sk_buff *skb;
 	int copied, error = -EINVAL;
 
+	msg->msg_namelen = 0;
+
 	if (sock->state != SS_CONNECTED)
 		return -ENOTCONN;
 
-- 
1.8.1.2

[PATCH 030/118] ax25: fix info leak via msg_name in ax25_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit ef3313e84acbf349caecae942ab3ab731471f1a1 upstream.

When msg_namelen is non-zero the sockaddr info gets filled out, as
requested, but the code fails to initialize the padding bytes of struct
sockaddr_ax25 inserted by the compiler for alignment. Additionally the
msg_namelen value is updated to sizeof(struct full_sockaddr_ax25) but is
not always filled up to this size.

Both issues lead to the fact that the code will leak uninitialized
kernel stack bytes in net/socket.c.

Fix both issues by initializing the memory with memset(0).

Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ax25/af_ax25.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 779095d..d53a123 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1647,6 +1647,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 		ax25_address src;
 		const unsigned char *mac = skb_mac_header(skb);
 
+		memset(sax, 0, sizeof(struct full_sockaddr_ax25));
 		ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
 				&digi, NULL, NULL);
 		sax->sax25_family = AF_AX25;
-- 
1.8.1.2

[PATCH 031/118] Bluetooth: fix possible info leak in bt_sock_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 4683f42fde3977bdb4e8a09622788cc8b5313778 upstream.

In case the socket is already shutting down, bt_sock_recvmsg() returns
with 0 without updating msg_namelen leading to net/socket.c leaking the
local, uninitialized sockaddr_storage variable to userland -- 128 bytes
of kernel stack memory.

Fix this by moving the msg_namelen assignment in front of the shutdown
test.

Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/bluetooth/af_bluetooth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 3e18af4..821e9d3 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -240,6 +240,8 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags & (MSG_OOB))
 		return -EOPNOTSUPP;
 
+	msg->msg_namelen = 0;
+
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -247,8 +249,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		return err;
 	}
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
-- 
1.8.1.2

[PATCH 032/118] Bluetooth: RFCOMM - Fix missing msg_namelen update in rfcomm_sock_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit e11e0455c0d7d3d62276a0c55d9dfbc16779d691 upstream.

If RFCOMM_DEFER_SETUP is set in the flags, rfcomm_sock_recvmsg() returns
early with 0 without updating the possibly set msg_namelen member. This,
in turn, leads to a 128 byte kernel stack leak in net/socket.c.

Fix this by updating msg_namelen in this case. For all other cases it
will be handled in bt_sock_stream_recvmsg().

Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/bluetooth/rfcomm/sock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 20bd148..514bead 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -629,6 +629,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
 		rfcomm_dlc_accept(d);
+		msg->msg_namelen = 0;
 		return 0;
 	}
 
-- 
1.8.1.2

[PATCH 033/118] caif: Fix missing msg_namelen update in caif_seqpkt_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 2d6fbfe733f35c6b355c216644e08e149c61b271 upstream.

The current code does not fill the msg_name member in case it is set.
It also does not set the msg_namelen member to 0 and therefore makes
net/socket.c leak the local, uninitialized sockaddr_storage variable
to userland -- 128 bytes of kernel stack memory.

Fix that by simply setting msg_namelen to 0 as obviously nobody cared
about caif_seqpkt_recvmsg() not filling the msg_name in case it was
set.

Cc: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/caif/caif_socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 78f1cda..21a1840 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -286,6 +286,8 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (m->msg_flags&MSG_OOB)
 		goto read_error;
 
+	m->msg_namelen = 0;
+
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
 	if (!skb)
 		goto read_error;
-- 
1.8.1.2

[PATCH 034/118] irda: Fix missing msg_namelen update in irda_recvmsg_dgram()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 5ae94c0d2f0bed41d6718be743985d61b7f5c47d upstream.

The current code does not fill the msg_name member in case it is set.
It also does not set the msg_namelen member to 0 and therefore makes
net/socket.c leak the local, uninitialized sockaddr_storage variable
to userland -- 128 bytes of kernel stack memory.

Fix that by simply setting msg_namelen to 0 as obviously nobody cared
about irda_recvmsg_dgram() not filling the msg_name in case it was
set.

Cc: Samuel Ortiz <samuel@sortiz.org>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/irda/af_irda.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index d6c291c..bd25678 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1386,6 +1386,8 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 
 	IRDA_DEBUG(4, "%s()\n", __func__);
 
+	msg->msg_namelen = 0;
+
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)
-- 
1.8.1.2

[PATCH 035/118] iucv: Fix missing msg_namelen update in iucv_sock_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit a5598bd9c087dc0efc250a5221e5d0e6f584ee88 upstream.

The current code does not fill the msg_name member in case it is set.
It also does not set the msg_namelen member to 0 and therefore makes
net/socket.c leak the local, uninitialized sockaddr_storage variable
to userland -- 128 bytes of kernel stack memory.

Fix that by simply setting msg_namelen to 0 as obviously nobody cared
about iucv_sock_recvmsg() not filling the msg_name in case it was set.

Cc: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/iucv/af_iucv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index cd6f7a9..625bc50 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1331,6 +1331,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff *skb, *rskb, *cskb;
 	int err = 0;
 
+	msg->msg_namelen = 0;
+
 	if ((sk->sk_state == IUCV_DISCONN) &&
 	    skb_queue_empty(&iucv->backlog_skb_q) &&
 	    skb_queue_empty(&sk->sk_receive_queue) &&
-- 
1.8.1.2

[PATCH 036/118] llc: Fix missing msg_namelen update in llc_ui_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit c77a4b9cffb6215a15196ec499490d116dfad181 upstream.

For stream sockets the code misses to update the msg_namelen member
to 0 and therefore makes net/socket.c leak the local, uninitialized
sockaddr_storage variable to userland -- 128 bytes of kernel stack
memory. The msg_namelen update is also missing for datagram sockets
in case the socket is shutting down during receive.

Fix both issues by setting msg_namelen to 0 early. It will be
updated later if we're going to fill the msg_name member.

Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/llc/af_llc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index a13c3e2..445882cb 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -720,6 +720,8 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int target;	/* Read at least this many bytes */
 	long timeo;
 
+	msg->msg_namelen = 0;
+
 	lock_sock(sk);
 	copied = -ENOTCONN;
 	if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
-- 
1.8.1.2

[PATCH 037/118] netrom: fix info leak via msg_name in nr_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 3ce5efad47b62c57a4f5c54248347085a750ce0e upstream.

In case msg_name is set the sockaddr info gets filled out, as
requested, but the code fails to initialize the padding bytes of
struct sockaddr_ax25 inserted by the compiler for alignment. Also
the sax25_ndigis member does not get assigned, leaking four more
bytes.

Both issues lead to the fact that the code will leak uninitialized
kernel stack bytes in net/socket.c.

Fix both issues by initializing the memory with memset(0).

Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/netrom/af_netrom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1b9024e..72cad6c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1177,6 +1177,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	if (sax != NULL) {
+		memset(sax, 0, sizeof(sax));
 		sax->sax25_family = AF_NETROM;
 		skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
 			      AX25_ADDR_LEN);
-- 
1.8.1.2

[PATCH 038/118] netrom: fix invalid use of sizeof in nr_recvmsg()

[Luis Henriques]

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

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

From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>

commit c802d759623acbd6e1ee9fbdabae89159a513913 upstream.

sizeof() when applied to a pointer typed expression gives the size of the
pointer, not that of the pointed data.
Introduced by commit 3ce5ef(netrom: fix info leak via msg_name in nr_recvmsg)

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/netrom/af_netrom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 72cad6c..7ed9b1d 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1177,7 +1177,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	if (sax != NULL) {
-		memset(sax, 0, sizeof(sax));
+		memset(sax, 0, sizeof(*sax));
 		sax->sax25_family = AF_NETROM;
 		skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
 			      AX25_ADDR_LEN);
-- 
1.8.1.2

[PATCH 039/118] NFC: llcp: fix info leaks via msg_name in llcp_sock_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit d26d6504f23e803824e8ebd14e52d4fc0a0b09cb upstream.

The code in llcp_sock_recvmsg() does not initialize all the members of
struct sockaddr_nfc_llcp when filling the sockaddr info. Nor does it
initialize the padding bytes of the structure inserted by the compiler
for alignment.

Also, if the socket is in state LLCP_CLOSED or is shutting down during
receive the msg_namelen member is not updated to 0 while otherwise
returning with 0, i.e. "success". The msg_namelen update is also
missing for stream and seqpacket sockets which don't fill the sockaddr
info.

Both issues lead to the fact that the code will leak uninitialized
kernel stack bytes in net/socket.c.

Fix the first issue by initializing the memory used for sockaddr info
with memset(0). Fix the second one by setting msg_namelen to 0 early.
It will be updated later if we're going to fill the msg_name member.

Cc: Lauro Ramos Venancio <lauro.venancio@openbossa.org>
Cc: Aloisio Almeida Jr <aloisio.almeida@openbossa.org>
Cc: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: 3.5 is not affected by first issue. ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/nfc/llcp/sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c
index e06d458..80200ac 100644
--- a/net/nfc/llcp/sock.c
+++ b/net/nfc/llcp/sock.c
@@ -570,6 +570,8 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	pr_debug("%p %zu\n", sk, len);
 
+	msg->msg_namelen = 0;
+
 	lock_sock(sk);
 
 	if (sk->sk_state == LLCP_CLOSED &&
-- 
1.8.1.2

[PATCH 040/118] rose: fix info leak via msg_name in rose_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 4a184233f21645cf0b719366210ed445d1024d72 upstream.

The code in rose_recvmsg() does not initialize all of the members of
struct sockaddr_rose/full_sockaddr_rose when filling the sockaddr info.
Nor does it initialize the padding bytes of the structure inserted by
the compiler for alignment. This will lead to leaking uninitialized
kernel stack bytes in net/socket.c.

Fix the issue by initializing the memory used for sockaddr info with
memset(0).

Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/rose/af_rose.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index c4719ce..7f645d1 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1257,6 +1257,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
 	if (srose != NULL) {
+		memset(srose, 0, msg->msg_namelen);
 		srose->srose_family = AF_ROSE;
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;
-- 
1.8.1.2

[PATCH 041/118] tipc: fix info leaks via msg_name in recv_msg/recv_stream

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit 60085c3d009b0df252547adb336d1ccca5ce52ec upstream.

The code in set_orig_addr() does not initialize all of the members of
struct sockaddr_tipc when filling the sockaddr info -- namely the union
is only partly filled. This will make recv_msg() and recv_stream() --
the only users of this function -- leak kernel stack memory as the
msg_name member is a local variable in net/socket.c.

Additionally to that both recv_msg() and recv_stream() fail to update
the msg_namelen member to 0 while otherwise returning with 0, i.e.
"success". This is the case for, e.g., non-blocking sockets. This will
lead to a 128 byte kernel stack leak in net/socket.c.

Fix the first issue by initializing the memory of the union with
memset(0). Fix the second one by setting msg_namelen to 0 early as it
will be updated later if we're going to fill the msg_name member.

Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/tipc/socket.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 5577a44..91fd130 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -802,6 +802,7 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
 	if (addr) {
 		addr->family = AF_TIPC;
 		addr->addrtype = TIPC_ADDR_ID;
+		memset(&addr->addr, 0, sizeof(addr->addr));
 		addr->addr.id.ref = msg_origport(msg);
 		addr->addr.id.node = msg_orignode(msg);
 		addr->addr.name.domain = 0;	/* could leave uninitialized */
@@ -916,6 +917,9 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
+	/* will be updated in set_orig_addr() if needed */
+	m->msg_namelen = 0;
+
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 restart:
 
@@ -1032,6 +1036,9 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
+	/* will be updated in set_orig_addr() if needed */
+	m->msg_namelen = 0;
+
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
-- 
1.8.1.2

[PATCH 042/118] cbq: incorrect processing of high limits

[Luis Henriques]

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

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

From: Vasily Averin <vvs@parallels.com>

commit f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2 upstream.

currently cbq works incorrectly for limits > 10% real link bandwidth,
and practically does not work for limits > 50% real link bandwidth.
Below are results of experiments taken on 1 Gbit link

 In shaper | Actual Result
-----------+---------------
  100M     | 108 Mbps
  200M     | 244 Mbps
  300M     | 412 Mbps
  500M     | 893 Mbps

This happen because of q->now changes incorrectly in cbq_dequeue():
when it is called before real end of packet transmitting,
L2T is greater than real time delay, q_now gets an extra boost
but never compensate it.

To fix this problem we prevent change of q->now until its synchronization
with real time.

Signed-off-by: Vasily Averin <vvs@openvz.org>
Reviewed-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/sched/sch_cbq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 564b9fc..611d5e9 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -963,8 +963,11 @@ cbq_dequeue(struct Qdisc *sch)
 		cbq_update(q);
 		if ((incr -= incr2) < 0)
 			incr = 0;
+		q->now += incr;
+	} else {
+		if (now > q->now)
+			q->now = now;
 	}
-	q->now += incr;
 	q->now_rt = now;
 
 	for (;;) {
-- 
1.8.1.2

[PATCH 043/118] net IPv6 : Fix broken IPv6 routing table after loopback down-up

[Luis Henriques]

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

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

From: Balakumaran Kannan <kumaran.4353@gmail.com>

commit 25fb6ca4ed9cad72f14f61629b68dc03c0d9713f upstream.

IPv6 Routing table becomes broken once we do ifdown, ifup of the loopback(lo)
interface. After down-up, routes of other interface's IPv6 addresses through
'lo' are lost.

IPv6 addresses assigned to all interfaces are routed through 'lo' for internal
communication. Once 'lo' is down, those routing entries are removed from routing
table. But those removed entries are not being re-created properly when 'lo' is
brought up. So IPv6 addresses of other interfaces becomes unreachable from the
same machine. Also this breaks communication with other machines because of
NDISC packet processing failure.

This patch fixes this issue by reading all interface's IPv6 addresses and adding
them to IPv6 routing table while bringing up 'lo'.

==Testing==
Before applying the patch:
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$

After applying the patch:
$ route -A inet6
Kernel IPv6 routing
table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination                    Next Hop                   Flag Met Ref Use If
2000::20/128                   ::                         U    256 0     0 eth0
fe80::/64                      ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
::1/128                        ::                         Un   0   1     0 lo
2000::20/128                   ::                         Un   0   1     0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128  ::                         Un   0   1     0 lo
ff00::/8                       ::                         U    256 0     0 eth0
::/0                           ::                         !n   -1  1     1 lo
$

Signed-off-by: Balakumaran Kannan <Balakumaran.Kannan@ap.sony.com>
Signed-off-by: Maruthi Thotad <Maruthi.Thotad@ap.sony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv6/addrconf.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 00188b3..2078f4e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2402,6 +2402,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
 static void init_loopback(struct net_device *dev)
 {
 	struct inet6_dev  *idev;
+	struct net_device *sp_dev;
+	struct inet6_ifaddr *sp_ifa;
+	struct rt6_info *sp_rt;
 
 	/* ::1 */
 
@@ -2413,6 +2416,30 @@ static void init_loopback(struct net_device *dev)
 	}
 
 	add_addr(idev, &in6addr_loopback, 128, IFA_HOST);
+
+	/* Add routes to other interface's IPv6 addresses */
+	for_each_netdev(dev_net(dev), sp_dev) {
+		if (!strcmp(sp_dev->name, dev->name))
+			continue;
+
+		idev = __in6_dev_get(sp_dev);
+		if (!idev)
+			continue;
+
+		read_lock_bh(&idev->lock);
+		list_for_each_entry(sp_ifa, &idev->addr_list, if_list) {
+
+			if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
+				continue;
+
+			sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0);
+
+			/* Failure cases are ignored */
+			if (!IS_ERR(sp_rt))
+				ip6_ins_rt(sp_rt);
+		}
+		read_unlock_bh(&idev->lock);
+	}
 }
 
 static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr)
-- 
1.8.1.2

[PATCH 044/118] net: count hw_addr syncs so that unsync works properly.

[Luis Henriques]

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

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

From: Vlad Yasevich <vyasevic@redhat.com>

commit 4543fbefe6e06a9e40d9f2b28d688393a299f079 upstream.

A few drivers use dev_uc_sync/unsync to synchronize the
address lists from master down to slave/lower devices.  In
some cases (bond/team) a single address list is synched down
to multiple devices.  At the time of unsync, we have a leak
in these lower devices, because "synced" is treated as a
boolean and the address will not be unsynced for anything after
the first device/call.

Treat "synced" as a count (same as refcount) and allow all
unsync calls to work.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/netdevice.h | 2 +-
 net/core/dev_addr_lists.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b52070a..735cb59 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -233,9 +233,9 @@ struct netdev_hw_addr {
 #define NETDEV_HW_ADDR_T_SLAVE		3
 #define NETDEV_HW_ADDR_T_UNICAST	4
 #define NETDEV_HW_ADDR_T_MULTICAST	5
-	bool			synced;
 	bool			global_use;
 	int			refcount;
+	int			synced;
 	struct rcu_head		rcu_head;
 };
 
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 716f363..fb898d7 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -38,7 +38,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
 	ha->type = addr_type;
 	ha->refcount = 1;
 	ha->global_use = global;
-	ha->synced = false;
+	ha->synced = 0;
 	list_add_tail_rcu(&ha->list, &list->list);
 	list->count++;
 
@@ -164,7 +164,7 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
 					    addr_len, ha->type);
 			if (err)
 				break;
-			ha->synced = true;
+			ha->synced++;
 			ha->refcount++;
 		} else if (ha->refcount == 1) {
 			__hw_addr_del(to_list, ha->addr, addr_len, ha->type);
@@ -185,7 +185,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 		if (ha->synced) {
 			__hw_addr_del(to_list, ha->addr,
 				      addr_len, ha->type);
-			ha->synced = false;
+			ha->synced--;
 			__hw_addr_del(from_list, ha->addr,
 				      addr_len, ha->type);
 		}
-- 
1.8.1.2

[PATCH 045/118] atl1e: limit gso segment size to prevent generation of wrong ip length fields

[Luis Henriques]

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

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

From: Hannes Frederic Sowa <hannes@stressinduktion.org>

commit 31d1670e73f4911fe401273a8f576edc9c2b5fea upstream.

The limit of 0x3c00 is taken from the windows driver.

Suggested-by: Huang, Xiong <xiong@qca.qualcomm.com>
Cc: Huang, Xiong <xiong@qca.qualcomm.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-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>
---
 drivers/net/ethernet/atheros/atl1e/atl1e.h      | 2 +-
 drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e.h b/drivers/net/ethernet/atheros/atl1e/atl1e.h
index edfdf6b..b5fd934 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e.h
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e.h
@@ -186,7 +186,7 @@ struct atl1e_tpd_desc {
 /* how about 0x2000 */
 #define MAX_TX_BUF_LEN      0x2000
 #define MAX_TX_BUF_SHIFT    13
-/*#define MAX_TX_BUF_LEN  0x3000 */
+#define MAX_TSO_SEG_SIZE    0x3c00
 
 /* rrs word 1 bit 0:31 */
 #define RRS_RX_CSUM_MASK	0xFFFF
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 38f7093..56b04c4 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -2352,6 +2352,7 @@ static int __devinit atl1e_probe(struct pci_dev *pdev,
 
 	INIT_WORK(&adapter->reset_task, atl1e_reset_task);
 	INIT_WORK(&adapter->link_chg_task, atl1e_link_chg_task);
+	netif_set_gso_max_size(netdev, MAX_TSO_SEG_SIZE);
 	err = register_netdev(netdev);
 	if (err) {
 		netdev_err(netdev, "register netdevice failed\n");
-- 
1.8.1.2

[PATCH 046/118] bonding: fix bonding_masters race condition in bond unloading

[Luis Henriques]

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

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

From: "nikolay@redhat.com" <nikolay@redhat.com>

commit 69b0216ac255f523556fa3d4ff030d857eaaa37f upstream.

While the bonding module is unloading, it is considered that after
rtnl_link_unregister all bond devices are destroyed but since no
synchronization mechanism exists, a new bond device can be created
via bonding_masters before unregister_pernet_subsys which would
lead to multiple problems (e.g. NULL pointer dereference, wrong RIP,
list corruption).

This patch fixes the issue by removing any bond devices left in the
netns after bonding_masters is removed from sysfs.

Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Acked-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/bonding/bond_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1a6b118..5fc31a1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4870,9 +4870,18 @@ static int __net_init bond_net_init(struct net *net)
 static void __net_exit bond_net_exit(struct net *net)
 {
 	struct bond_net *bn = net_generic(net, bond_net_id);
+	struct bonding *bond, *tmp_bond;
+	LIST_HEAD(list);
 
 	bond_destroy_sysfs(bn);
 	bond_destroy_proc_dir(bn);
+
+	/* Kill off any bonds created after unregistering bond rtnl ops */
+	rtnl_lock();
+	list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
+		unregister_netdevice_queue(bond->dev, &list);
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
 }
 
 static struct pernet_operations bond_net_ops = {
-- 
1.8.1.2

[PATCH 047/118] bonding: IFF_BONDING is not stripped on enslave failure

[Luis Henriques]

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

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

From: "nikolay@redhat.com" <nikolay@redhat.com>

commit b6a5a7b9a528a8b4c8bec940b607c5dd9102b8cc upstream.

While enslaving a new device and after IFF_BONDING flag is set, in case
of failure it is not stripped from the device's priv_flags while
cleaning up, which could lead to other problems.
Cleaning at err_close because the flag is set after dev_open().

v2: no change

Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5fc31a1..1e1ae64 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1897,6 +1897,7 @@ err_detach:
 	write_unlock_bh(&bond->lock);
 
 err_close:
+	slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
 
 err_unset_master:
-- 
1.8.1.2

[PATCH 048/118] af_unix: If we don't care about credentials coallesce all messages

[Luis Henriques]

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

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

From: "Eric W. Biederman" <ebiederm@xmission.com>

commit 0e82e7f6dfeec1013339612f74abc2cdd29d43d2 upstream.

It was reported that the following LSB test case failed
https://lsbbugs.linuxfoundation.org/attachment.cgi?id=2144 because we
were not coallescing unix stream messages when the application was
expecting us to.

The problem was that the first send was before the socket was accepted
and thus sock->sk_socket was NULL in maybe_add_creds, and the second
send after the socket was accepted had a non-NULL value for sk->socket
and thus we could tell the credentials were not needed so we did not
bother.

The unnecessary credentials on the first message cause
unix_stream_recvmsg to start verifying that all messages had the same
credentials before coallescing and then the coallescing failed because
the second message had no credentials.

Ignoring credentials when we don't care in unix_stream_recvmsg fixes a
long standing pessimization which would fail to coallesce messages when
reading from a unix stream socket if the senders were different even if
we did not care about their credentials.

I have tested this and verified that the in the LSB test case mentioned
above that the messages do coallesce now, while the were failing to
coallesce without this change.

Reported-by: Karel Srot <ksrot@redhat.com>
Reported-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 023db69..ce7db4b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1996,7 +1996,7 @@ again:
 			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
 			    (UNIXCB(skb).cred != siocb->scm->cred))
 				break;
-		} else {
+		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
 			scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred);
 			check_creds = 1;
-- 
1.8.1.2

[PATCH 049/118] netfilter: don't reset nf_trace in nf_reset()

[Luis Henriques]

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

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

From: Patrick McHardy <kaber@trash.net>

commit 124dff01afbdbff251f0385beca84ba1b9adda68 upstream.

Commit 130549fe ("netfilter: reset nf_trace in nf_reset") added code
to reset nf_trace in nf_reset(). This is wrong and unnecessary.

nf_reset() is used in the following cases:

- when passing packets up the the socket layer, at which point we want to
  release all netfilter references that might keep modules pinned while
  the packet is queued. nf_trace doesn't matter anymore at this point.

- when encapsulating or decapsulating IPsec packets. We want to continue
  tracing these packets after IPsec processing.

- when passing packets through virtual network devices. Only devices on
  that encapsulate in IPv4/v6 matter since otherwise nf_trace is not
  used anymore. Its not entirely clear whether those packets should
  be traced after that, however we've always done that.

- when passing packets through virtual network devices that make the
  packet cross network namespace boundaries. This is the only cases
  where we clearly want to reset nf_trace and is also what the
  original patch intended to fix.

Add a new function nf_reset_trace() and use it in dev_forward_skb() to
fix this properly.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/skbuff.h | 7 +++++++
 net/core/dev.c         | 1 +
 2 files changed, 8 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5af4bef..e1c1e64 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2404,6 +2404,13 @@ static inline void nf_reset(struct sk_buff *skb)
 #endif
 }
 
+static inline void nf_reset_trace(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+	skb->nf_trace = 0;
+#endif
+}
+
 /* Note: This doesn't put any conntrack and bridge info in dst. */
 static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 845a83a..196bc5f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1627,6 +1627,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 	skb->mark = 0;
 	secpath_reset(skb);
 	nf_reset(skb);
+	nf_reset_trace(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
-- 
1.8.1.2

[PATCH 050/118] rtnetlink: Call nlmsg_parse() with correct header length

[Luis Henriques]

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

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

From: Michael Riesch <michael.riesch@omicron.at>

commit 88c5b5ce5cb57af6ca2a7cf4d5715fa320448ff9 upstream.

Signed-off-by: Michael Riesch <michael.riesch@omicron.at>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Benc <jbenc@redhat.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-kernel@vger.kernel.org
Acked-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/core/rtnetlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 844ccc6..ef7f0ab 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1073,7 +1073,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX,
+	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
 			ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
@@ -1916,7 +1916,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
 
-	if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX,
+	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
 			ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
-- 
1.8.1.2

[PATCH 051/118] tcp: incoming connections might use wrong route under synflood

[Luis Henriques]

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

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

From: Dmitry Popov <dp@highloadlab.com>

commit d66954a066158781ccf9c13c91d0316970fe57b6 upstream.

There is a bug in cookie_v4_check (net/ipv4/syncookies.c):
	flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
			   RT_SCOPE_UNIVERSE, IPPROTO_TCP,
			   inet_sk_flowi_flags(sk),
			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
			   ireq->loc_addr, th->source, th->dest);

Here we do not respect sk->sk_bound_dev_if, therefore wrong dst_entry may be
taken. This dst_entry is used by new socket (get_cookie_sock ->
tcp_v4_syn_recv_sock), so its packets may take the wrong path.

Signed-off-by: Dmitry Popov <dp@highloadlab.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/syncookies.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index eab2a7f..550aa2a 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -347,8 +347,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
-			   RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
 			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
 			   ireq->loc_addr, th->source, th->dest);
-- 
1.8.1.2

[PATCH 052/118] tcp: Reallocate headroom if it would overflow csum_start

[Luis Henriques]

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

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

From: Thomas Graf <tgraf@suug.ch>

commit 50bceae9bd3569d56744882f3012734d48a1d413 upstream.

If a TCP retransmission gets partially ACKed and collapsed multiple
times it is possible for the headroom to grow beyond 64K which will
overflow the 16bit skb->csum_start which is based on the start of
the headroom. It has been observed rarely in the wild with IPoIB due
to the 64K MTU.

Verify if the acking and collapsing resulted in a headroom exceeding
what csum_start can cover and reallocate the headroom if so.

A big thank you to Jim Foraker <foraker1@llnl.gov> and the team at
LLNL for helping out with the investigation and testing.

Reported-by: Jim Foraker <foraker1@llnl.gov>
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/tcp_output.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e0cd660..ae12c92 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2175,8 +2175,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
-	/* make sure skb->data is aligned on arches that require it */
-	if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+	/* make sure skb->data is aligned on arches that require it
+	 * and check if ack-trimming & collapsing extended the headroom
+	 * beyond what csum_start can cover.
+	 */
+	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
+		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-- 
1.8.1.2

[PATCH 053/118] esp4: fix error return code in esp_output()

[Luis Henriques]

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

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

From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>

commit 06848c10f720cbc20e3b784c0df24930b7304b93 upstream.

Fix to return a negative error code from the error handling
case instead of 0, as returned elsewhere in this function.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/esp4.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index cb982a6..e814e2a 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	/* skb is pure payload to encrypt */
 
-	err = -ENOMEM;
-
 	esp = x->data;
 	aead = esp->aead;
 	alen = crypto_aead_authsize(aead);
@@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	}
 
 	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
-	if (!tmp)
+	if (!tmp) {
+		err = -ENOMEM;
 		goto error;
+	}
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
-- 
1.8.1.2

[PATCH 054/118] net: sctp: sctp_auth_key_put: use kzfree instead of kfree

[Luis Henriques]

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

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

From: Daniel Borkmann <dborkman@redhat.com>

commit 586c31f3bf04c290dc0a0de7fc91d20aa9a5ee53 upstream.

For sensitive data like keying material, it is common practice to zero
out keys before returning the memory back to the allocator. Thus, use
kzfree instead of kfree.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/sctp/auth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index bf81204..333926d 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -71,7 +71,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key)
 		return;
 
 	if (atomic_dec_and_test(&key->refcnt)) {
-		kfree(key);
+		kzfree(key);
 		SCTP_DBG_OBJCNT_DEC(keys);
 	}
 }
-- 
1.8.1.2

[PATCH 055/118] tcp: call tcp_replace_ts_recent() from tcp_ack()

[Luis Henriques]

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

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

From: Eric Dumazet <edumazet@google.com>

commit 12fb3dd9dc3c64ba7d64cec977cca9b5fb7b1d4e upstream.

commit bd090dfc634d (tcp: tcp_replace_ts_recent() should not be called
from tcp_validate_incoming()) introduced a TS ecr bug in slow path
processing.

1 A > B P. 1:10001(10000) ack 1 <nop,nop,TS val 1001 ecr 200>
2 B < A . 1:1(0) ack 1 win 257 <sack 9001:10001,TS val 300 ecr 1001>
3 A > B . 1:1001(1000) ack 1 win 227 <nop,nop,TS val 1002 ecr 200>
4 A > B . 1001:2001(1000) ack 1 win 227 <nop,nop,TS val 1002 ecr 200>

(ecr 200 should be ecr 300 in packets 3 & 4)

Problem is tcp_ack() can trigger send of new packets (retransmits),
reflecting the prior TSval, instead of the TSval contained in the
currently processed incoming packet.

Fix this by calling tcp_replace_ts_recent() from tcp_ack() after the
checks, but before the actions.

Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/tcp_input.c | 64 +++++++++++++++++++++++++---------------------------
 1 file changed, 31 insertions(+), 33 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e75e4fb..e8139f8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -117,6 +117,7 @@ int sysctl_tcp_early_retrans __read_mostly = 2;
 #define FLAG_DSACKING_ACK	0x800 /* SACK blocks contained D-SACK info */
 #define FLAG_NONHEAD_RETRANS_ACKED	0x1000 /* Non-head rexmitted data was ACKed */
 #define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
+#define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -3783,6 +3784,27 @@ static void tcp_send_challenge_ack(struct sock *sk)
 	}
 }
 
+static void tcp_store_ts_recent(struct tcp_sock *tp)
+{
+	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
+	tp->rx_opt.ts_recent_stamp = get_seconds();
+}
+
+static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+{
+	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
+		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
+		 * extra check below makes sure this can only happen
+		 * for pure ACK frames.  -DaveM
+		 *
+		 * Not only, also it occurs for expired timestamps.
+		 */
+
+		if (tcp_paws_check(&tp->rx_opt, 0))
+			tcp_store_ts_recent(tp);
+	}
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
@@ -3835,6 +3857,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	prior_fackets = tp->fackets_out;
 	prior_in_flight = tcp_packets_in_flight(tp);
 
+	/* ts_recent update must be made after we are sure that the packet
+	 * is in window.
+	 */
+	if (flag & FLAG_UPDATE_TS_RECENT)
+		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
 	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
 		/* Window is constant, pure forward advance.
 		 * No more checks are required.
@@ -4131,27 +4159,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 EXPORT_SYMBOL(tcp_parse_md5sig_option);
 #endif
 
-static inline void tcp_store_ts_recent(struct tcp_sock *tp)
-{
-	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
-}
-
-static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
-{
-	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
-		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
-		 * extra check below makes sure this can only happen
-		 * for pure ACK frames.  -DaveM
-		 *
-		 * Not only, also it occurs for expired timestamps.
-		 */
-
-		if (tcp_paws_check(&tp->rx_opt, 0))
-			tcp_store_ts_recent(tp);
-	}
-}
-
 /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
  *
  * It is not fatal. If this ACK does _not_ change critical state (seqs, window)
@@ -5738,14 +5745,9 @@ slow_path:
 		return 0;
 
 step5:
-	if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
+	if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0)
 		goto discard;
 
-	/* ts_recent update must be made after we are sure that the packet
-	 * is in window.
-	 */
-	tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
 	tcp_rcv_rtt_measure_ts(sk, skb);
 
 	/* Process urgent data. */
@@ -6117,7 +6119,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
 	/* step 5: check the ACK field */
 	if (th->ack) {
-		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
+		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
+						  FLAG_UPDATE_TS_RECENT) > 0;
 
 		switch (sk->sk_state) {
 		case TCP_SYN_RECV:
@@ -6224,11 +6227,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	} else
 		goto discard;
 
-	/* ts_recent update must be made after we are sure that the packet
-	 * is in window.
-	 */
-	tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
 	/* step 6: check the URG bit */
 	tcp_urg(sk, skb, th);
 
-- 
1.8.1.2

[PATCH 056/118] net: rate-limit warn-bad-offload splats.

[Luis Henriques]

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

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

From: Ben Greear <greearb@candelatech.com>

commit c846ad9b880ece01bb4d8d07ba917734edf0324f upstream.

If one does do something unfortunate and allow a
bad offload bug into the kernel, this the
skb_warn_bad_offload can effectively live-lock the
system, filling the logs with the same error over
and over.

Add rate limitation to this so that box remains otherwise
functional in this case.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/core/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 196bc5f..ba9d7a7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1893,6 +1893,9 @@ static void skb_warn_bad_offload(const struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	const char *driver = "";
 
+	if (!net_ratelimit())
+		return;
+
 	if (dev && dev->dev.parent)
 		driver = dev_driver_string(dev->dev.parent);
 
-- 
1.8.1.2

[PATCH 057/118] net: fix incorrect credentials passing

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 83f1b4ba917db5dc5a061a44b3403ddb6e783494 upstream.

Commit 257b5358b32f ("scm: Capture the full credentials of the scm
sender") changed the credentials passing code to pass in the effective
uid/gid instead of the real uid/gid.

Obviously this doesn't matter most of the time (since normally they are
the same), but it results in differences for suid binaries when the wrong
uid/gid ends up being used.

This just undoes that (presumably unintentional) part of the commit.

Reported-by: Andy Lutomirski <luto@amacapital.net>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Serge E. Hallyn <serge@hallyn.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: backport to 3.5 based on davem backport to 3.4 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/socket.h |  3 ++-
 include/net/scm.h      |  2 +-
 net/core/sock.c        | 14 ++++++++++----
 3 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 25d6322..2a32b9d 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -316,7 +316,8 @@ struct ucred {
 /* IPX options */
 #define IPX_TYPE	1
 
-extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred);
+extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred,
+			  bool use_effective);
 
 extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
diff --git a/include/net/scm.h b/include/net/scm.h
index 0c0017c..9f211cf 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -50,7 +50,7 @@ static __inline__ void scm_set_cred(struct scm_cookie *scm,
 {
 	scm->pid  = get_pid(pid);
 	scm->cred = cred ? get_cred(cred) : NULL;
-	cred_to_ucred(pid, cred, &scm->creds);
+	cred_to_ucred(pid, cred, &scm->creds, false);
 }
 
 static __inline__ void scm_destroy_cred(struct scm_cookie *scm)
diff --git a/net/core/sock.c b/net/core/sock.c
index c5f765c..5d30122 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -807,15 +807,20 @@ EXPORT_SYMBOL(sock_setsockopt);
 
 
 void cred_to_ucred(struct pid *pid, const struct cred *cred,
-		   struct ucred *ucred)
+		   struct ucred *ucred, bool use_effective)
 {
 	ucred->pid = pid_vnr(pid);
 	ucred->uid = ucred->gid = -1;
 	if (cred) {
 		struct user_namespace *current_ns = current_user_ns();
 
-		ucred->uid = from_kuid(current_ns, cred->euid);
-		ucred->gid = from_kgid(current_ns, cred->egid);
+		if (use_effective) {
+			ucred->uid = from_kuid(current_ns, cred->euid);
+			ucred->gid = from_kgid(current_ns, cred->egid);
+		} else {
+			ucred->uid = from_kuid(current_ns, cred->uid);
+			ucred->gid = from_kgid(current_ns, cred->gid);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(cred_to_ucred);
@@ -976,7 +981,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		struct ucred peercred;
 		if (len > sizeof(peercred))
 			len = sizeof(peercred);
-		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
+		cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred,
+			      &peercred, true);
 		if (copy_to_user(optval, &peercred, len))
 			return -EFAULT;
 		goto lenout;
-- 
1.8.1.2

[PATCH 058/118] net: drop dst before queueing fragments

[Luis Henriques]

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

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

From: Eric Dumazet <edumazet@google.com>

commit 97599dc792b45b1669c3cdb9a4b365aad0232f65 upstream.

Commit 4a94445c9a5c (net: Use ip_route_input_noref() in input path)
added a bug in IP defragmentation handling, as non refcounted
dst could escape an RCU protected section.

Commit 64f3b9e203bd068 (net: ip_expire() must revalidate route) fixed
the case of timeouts, but not the general problem.

Tom Parkin noticed crashes in UDP stack and provided a patch,
but further analysis permitted us to pinpoint the root cause.

Before queueing a packet into a frag list, we must drop its dst,
as this dst has limited lifetime (RCU protected)

When/if a packet is finally reassembled, we use the dst of the very
last skb, still protected by RCU and valid, as the dst of the
reassembled packet.

Use same logic in IPv6, as there is no need to hold dst references.

Reported-by: Tom Parkin <tparkin@katalix.com>
Tested-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/ipv4/ip_fragment.c | 15 +++++++++++----
 net/ipv6/reassembly.c  | 13 +++++++++++--
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d513c62..3599757 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -251,8 +251,7 @@ static void ip_expire(unsigned long arg)
 		if (!head->dev)
 			goto out_rcu_unlock;
 
-		/* skb dst is stale, drop it, and perform route lookup again */
-		skb_dst_drop(head);
+		/* skb has no dst, perform route lookup again */
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
@@ -517,8 +516,16 @@ found:
 		qp->q.last_in |= INET_FRAG_FIRST_IN;
 
 	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-	    qp->q.meat == qp->q.len)
-		return ip_frag_reasm(qp, prev, dev);
+	    qp->q.meat == qp->q.len) {
+		unsigned long orefdst = skb->_skb_refdst;
+
+		skb->_skb_refdst = 0UL;
+		err = ip_frag_reasm(qp, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return err;
+	}
+
+	skb_dst_drop(skb);
 
 	write_lock(&ip4_frags.lock);
 	list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 66d2096..3673b8f 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -386,8 +386,17 @@ found:
 	}
 
 	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-	    fq->q.meat == fq->q.len)
-		return ip6_frag_reasm(fq, prev, dev);
+	    fq->q.meat == fq->q.len) {
+		int res;
+		unsigned long orefdst = skb->_skb_refdst;
+
+		skb->_skb_refdst = 0UL;
+		res = ip6_frag_reasm(fq, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return res;
+	}
+
+	skb_dst_drop(skb);
 
 	write_lock(&ip6_frags.lock);
 	list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
-- 
1.8.1.2

[PATCH 059/118] sparc64: Fix race in TLB batch processing.

[Luis Henriques]

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

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

From: "David S. Miller" <davem@davemloft.net>

[ Commits f36391d2790d04993f48da6a45810033a2cdf847 and
  f0af97070acbad5d6a361f485828223a4faaa0ee upstream. ]

As reported by Dave Kleikamp, when we emit cross calls to do batched
TLB flush processing we have a race because we do not synchronize on
the sibling cpus completing the cross call.

So meanwhile the TLB batch can be reset (tb->tlb_nr set to zero, etc.)
and either flushes are missed or flushes will flush the wrong
addresses.

Fix this by using generic infrastructure to synchonize on the
completion of the cross call.

This first required getting the flush_tlb_pending() call out from
switch_to() which operates with locks held and interrupts disabled.
The problem is that smp_call_function_many() cannot be invoked with
IRQs disabled and this is explicitly checked for with WARN_ON_ONCE().

We get the batch processing outside of locked IRQ disabled sections by
using some ideas from the powerpc port. Namely, we only batch inside
of arch_{enter,leave}_lazy_mmu_mode() calls.  If we're not in such a
region, we flush TLBs synchronously.

1) Get rid of xcall_flush_tlb_pending and per-cpu type
   implementations.

2) Do TLB batch cross calls instead via:

	smp_call_function_many()
		tlb_pending_func()
			__flush_tlb_pending()

3) Batch only in lazy mmu sequences:

	a) Add 'active' member to struct tlb_batch
	b) Define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
	c) Set 'active' in arch_enter_lazy_mmu_mode()
	d) Run batch and clear 'active' in arch_leave_lazy_mmu_mode()
	e) Check 'active' in tlb_batch_add_one() and do a synchronous
           flush if it's clear.

4) Add infrastructure for synchronous TLB page flushes.

	a) Implement __flush_tlb_page and per-cpu variants, patch
	   as needed.
	b) Likewise for xcall_flush_tlb_page.
	c) Implement smp_flush_tlb_page() to invoke the cross-call.
	d) Wire up global_flush_tlb_page() to the right routine based
           upon CONFIG_SMP

5) It turns out that singleton batches are very common, 2 out of every
   3 batch flushes have only a single entry in them.

   The batch flush waiting is very expensive, both because of the poll
   on sibling cpu completeion, as well as because passing the tlb batch
   pointer to the sibling cpus invokes a shared memory dereference.

   Therefore, in flush_tlb_pending(), if there is only one entry in
   the batch perform a completely asynchronous global_flush_tlb_page()
   instead.

Reported-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Luis Henriques<luis.henriques@canonical.com>
---
 arch/sparc/include/asm/pgtable_64.h   |   1 +
 arch/sparc/include/asm/switch_to_64.h |   3 +-
 arch/sparc/include/asm/tlbflush_64.h  |  37 +++++++++--
 arch/sparc/kernel/smp_64.c            |  41 ++++++++++--
 arch/sparc/mm/tlb.c                   |  39 +++++++++--
 arch/sparc/mm/tsb.c                   |  57 +++++++++++-----
 arch/sparc/mm/ultra.S                 | 119 +++++++++++++++++++++++++++-------
 7 files changed, 242 insertions(+), 55 deletions(-)

diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 61210db..d319489 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -776,6 +776,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
 }
 
+#include <asm/tlbflush.h>
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index 7923c4a..9c2a92d 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -18,8 +18,7 @@ do {						\
 	 * and 2 stores in this critical code path.  -DaveM
 	 */
 #define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
-	save_and_clear_fpu();						\
+do {	save_and_clear_fpu();						\
 	/* If you are tempted to conditionalize the following */	\
 	/* so that ASI is only written if it changes, think again. */	\
 	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 2ef4634..f0d6a97 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -11,24 +11,40 @@
 struct tlb_batch {
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
+	unsigned long active;
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-#define flush_tlb_range(vma,start,end)	\
-	do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr)	flush_tlb_pending()
-#define flush_tlb_mm(mm)		flush_tlb_pending()
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
 extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
 extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do {	flush_tsb_kernel_range(start,end); \
 	__flush_tlb_kernel_range(start,end); \
 } while (0)
 
+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
 	smp_flush_tlb_kernel_range(start, end); \
 } while (0)
 
+#define global_flush_tlb_page(mm, vaddr) \
+	smp_flush_tlb_page(mm, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index f591598..b8870b6 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -852,7 +852,7 @@ void smp_tsb_sync(struct mm_struct *mm)
 }
 
 extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
 extern unsigned long xcall_flush_tlb_kernel_range;
 extern unsigned long xcall_fetch_glob_regs;
 extern unsigned long xcall_receive_signal;
@@ -1066,23 +1066,56 @@ local_flush_and_out:
 	put_cpu();
 }
 
+struct tlb_pending_info {
+	unsigned long ctx;
+	unsigned long nr;
+	unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+	struct tlb_pending_info *t = info;
+
+	__flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
 void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
+	struct tlb_pending_info info;
 	int cpu = get_cpu();
 
+	info.ctx = ctx;
+	info.nr = nr;
+	info.vaddrs = vaddrs;
+
 	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
 		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
 	else
-		smp_cross_call_masked(&xcall_flush_tlb_pending,
-				      ctx, nr, (unsigned long) vaddrs,
-				      mm_cpumask(mm));
+		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+				       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
 	put_cpu();
 }
 
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long context = CTX_HWBITS(mm->context);
+	int cpu = get_cpu();
+
+	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+	else
+		smp_cross_call_masked(&xcall_flush_tlb_page,
+				      context, vaddr, 0,
+				      mm_cpumask(mm));
+	__flush_tlb_page(context, vaddr);
+
+	put_cpu();
+}
+
 void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	start &= PAGE_MASK;
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b1f279c..afd021e 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 void flush_tlb_pending(void)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+	struct mm_struct *mm = tb->mm;
 
-	if (tb->tlb_nr) {
-		flush_tsb_user(tb);
+	if (!tb->tlb_nr)
+		goto out;
 
-		if (CTX_VALID(tb->mm->context)) {
+	flush_tsb_user(tb);
+
+	if (CTX_VALID(mm->context)) {
+		if (tb->tlb_nr == 1) {
+			global_flush_tlb_page(mm, tb->vaddrs[0]);
+		} else {
 #ifdef CONFIG_SMP
 			smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
 					      &tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
 					    tb->tlb_nr, &tb->vaddrs[0]);
 #endif
 		}
-		tb->tlb_nr = 0;
 	}
 
+	tb->tlb_nr = 0;
+
+out:
 	put_cpu_var(tlb_batch);
 }
 
+void arch_enter_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	if (tb->tlb_nr)
+		flush_tlb_pending();
+	tb->active = 0;
+}
+
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
@@ -90,6 +114,12 @@ no_cache_flush:
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		global_flush_tlb_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr);
+		goto out;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 
@@ -98,5 +128,6 @@ no_cache_flush:
 	if (nr >= TLB_BATCH_NR)
 		flush_tlb_pending();
 
+out:
 	put_cpu_var(tlb_batch);
 }
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 7c2d9ac..8adc660 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -7,11 +7,10 @@
 #include <linux/preempt.h>
 #include <linux/slab.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
+#include <asm/mmu_context.h>
 #include <asm/tsb.h>
+#include <asm/tlb.h>
 #include <asm/oplib.h>
 
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
-static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
-			    unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+				  unsigned long hash_shift,
+				  unsigned long nentries)
 {
-	unsigned long i;
+	unsigned long tag, ent, hash;
 
-	for (i = 0; i < tb->tlb_nr; i++) {
-		unsigned long v = tb->vaddrs[i];
-		unsigned long tag, ent, hash;
+	v &= ~0x1UL;
+	hash = tsb_hash(v, hash_shift, nentries);
+	ent = tsb + (hash * sizeof(struct tsb));
+	tag = (v >> 22UL);
 
-		v &= ~0x1UL;
+	tsb_flush(ent, tag);
+}
 
-		hash = tsb_hash(v, hash_shift, nentries);
-		ent = tsb + (hash * sizeof(struct tsb));
-		tag = (v >> 22UL);
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+			    unsigned long tsb, unsigned long nentries)
+{
+	unsigned long i;
 
-		tsb_flush(ent, tag);
-	}
+	for (i = 0; i < tb->tlb_nr; i++)
+		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long nentries, base, flags;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+		base = __pa(base);
+	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+	}
+#endif
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
 #if defined(CONFIG_SPARC64_PAGE_SIZE_8KB)
 #define HV_PGSZ_IDX_BASE	HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE	HV_PGSZ_MASK_8K
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index 874162a..dd10caa 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -53,6 +53,33 @@ __flush_tlb_mm:		/* 18 insns */
 	nop
 
 	.align		32
+	.globl		__flush_tlb_page
+__flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, %pstate
+	mov		SECONDARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	andn		%o1, 1, %o3
+	be,pn		%icc, 1f
+	 or		%o3, 0x10, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	retl
+	 wrpr		%g7, 0x0, %pstate
+	nop
+	nop
+	nop
+	nop
+
+	.align		32
 	.globl		__flush_tlb_pending
 __flush_tlb_pending:	/* 26 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, 0x0, %pstate
+	wrpr		%g0, 1, %tl
+	mov		PRIMARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %o3
+	sllx		%o3, CTX_PGSZ1_NUC_SHIFT, %o3
+	or		%o0, %o3, %o0	/* Preserve nucleus page size fields */
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	be,pn		%icc, 1f
+	 andn		%o1, 1, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	wrpr		%g0, 0, %tl
+	retl
+	 wrpr		%g7, 0x0, %pstate
+
 __cheetah_flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */
 	retl
 	 nop
 
+__hypervisor_flush_tlb_page: /* 11 insns */
+	/* %o0 = context, %o1 = vaddr */
+	mov		%o0, %g2
+	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
+	mov		%g2, %o1	      /* ARG1: mmu context */
+	mov		HV_MMU_ALL, %o2	      /* ARG2: flags */
+	srlx		%o0, PAGE_SHIFT, %o0
+	sllx		%o0, PAGE_SHIFT, %o0
+	ta		HV_MMU_UNMAP_ADDR_TRAP
+	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
+	retl
+	 nop
+
 __hypervisor_flush_tlb_pending: /* 16 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		19, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm:	/* 21 insns */
 	nop
 	nop
 
-	.globl		xcall_flush_tlb_pending
-xcall_flush_tlb_pending:	/* 21 insns */
-	/* %g5=context, %g1=nr, %g7=vaddrs[] */
-	sllx		%g1, 3, %g1
+	.globl		xcall_flush_tlb_page
+xcall_flush_tlb_page:	/* 17 insns */
+	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
 	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending:	/* 21 insns */
 	or		%g5, %g4, %g5
 	mov		PRIMARY_CONTEXT, %g4
 	stxa		%g5, [%g4] ASI_DMMU
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %g5
-	andcc		%g5, 0x1, %g0
+	andcc		%g1, 0x1, %g0
 	be,pn		%icc, 2f
-
-	 andn		%g5, 0x1, %g5
+	 andn		%g1, 0x1, %g5
 	stxa		%g0, [%g5] ASI_IMMU_DEMAP
 2:	stxa		%g0, [%g5] ASI_DMMU_DEMAP
 	membar		#Sync
-	brnz,pt		%g1, 1b
-	 nop
 	stxa		%g2, [%g4] ASI_DMMU
 	retry
 	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
 xcall_flush_tlb_kernel_range:	/* 25 insns */
@@ -596,15 +664,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	membar		#Sync
 	retry
 
-	.globl		__hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
-	/* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
-	sllx		%g1, 3, %g1
+	.globl		__hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
 	mov		%o2, %g4
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %o0	/* ARG0: virtual address */
+	mov		%g1, %o0	        /* ARG0: virtual address */
 	mov		%g5, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2		/* ARG2: flags */
 	srlx		%o0, PAGE_SHIFT, %o0
@@ -613,8 +679,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
 	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
 	 mov		%o0, %g5
-	brnz,pt		%g1, 1b
-	 nop
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
@@ -697,6 +761,13 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		10, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
@@ -728,12 +799,12 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		21, %o2
 
-	sethi		%hi(xcall_flush_tlb_pending), %o0
-	or		%o0, %lo(xcall_flush_tlb_pending), %o0
-	sethi		%hi(__hypervisor_xcall_flush_tlb_pending), %o1
-	or		%o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+	sethi		%hi(xcall_flush_tlb_page), %o0
+	or		%o0, %lo(xcall_flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		17, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
-- 
1.8.1.2

[PATCH 060/118] l2tp: fix info leak in l2tp_ip6_recvmsg()

[Luis Henriques]

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

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

From: Mathias Krause <minipli@googlemail.com>

commit b860d3cc62877fad02863e2a08efff69a19382d2 upstream.

The L2TP code for IPv6 fails to initialize the l2tp_conn_id member of
struct sockaddr_l2tpip6 and therefore leaks four bytes kernel stack
in l2tp_ip6_recvmsg() in case msg_name is set.

Initialize l2tp_conn_id with 0 to avoid the info leak.

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/l2tp/l2tp_ip6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 9275471..2c9ccce 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -684,6 +684,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		lsa->l2tp_addr = ipv6_hdr(skb)->saddr;
 		lsa->l2tp_flowinfo = 0;
 		lsa->l2tp_scope_id = 0;
+		lsa->l2tp_conn_id = 0;
 		if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
 			lsa->l2tp_scope_id = IP6CB(skb)->iif;
 	}
-- 
1.8.1.2

[PATCH 061/118] tracing: Use stack of calling function for stack tracer

[Luis Henriques]

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

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

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

commit 87889501d0adfae10e3b0f0e6f2d7536eed9ae84 upstream.

Use the stack of stack_trace_call() instead of check_stack() as
the test pointer for max stack size. It makes it a bit cleaner
and a little more accurate.

Adding stable, as a later fix depends on this patch.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace_stack.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index aa4270a..6ee97e5 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -40,20 +40,21 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long *stack)
 {
 	unsigned long this_size, flags;
 	unsigned long *p, *top, *start;
 	int i;
 
-	this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
 	this_size = THREAD_SIZE - this_size;
 
 	if (this_size <= max_stack_size)
 		return;
 
 	/* we do not handle interrupt stacks yet */
-	if (!object_is_on_stack(&this_size))
+	if (!object_is_on_stack(stack))
 		return;
 
 	local_irq_save(flags);
@@ -74,7 +75,7 @@ static inline void check_stack(void)
 	 * Now find where in the stack these are.
 	 */
 	i = 0;
-	start = &this_size;
+	start = stack;
 	top = (unsigned long *)
 		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
 
@@ -113,6 +114,7 @@ static inline void check_stack(void)
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip)
 {
+	unsigned long stack;
 	int cpu;
 
 	if (unlikely(!ftrace_enabled || stack_trace_disabled))
@@ -125,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	check_stack();
+	check_stack(&stack);
 
  out:
 	per_cpu(trace_active, cpu)--;
-- 
1.8.1.2

[PATCH 062/118] tracing: Fix stack tracer with fentry use

[Luis Henriques]

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

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

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

commit d4ecbfc49b4b1d4b597fb5ba9e4fa25d62f105c5 upstream.

When gcc 4.6 on x86 is used, the function tracer will use the new
option -mfentry which does a call to "fentry" at every function
instead of "mcount". The significance of this is that fentry is
called as the first operation of the function instead of the mcount
usage of being called after the stack.

This causes the stack tracer to show some bogus results for the size
of the last function traced, as well as showing "ftrace_call" instead
of the function. This is due to the stack frame not being set up
by the function that is about to be traced.

 # cat stack_trace
        Depth    Size   Location    (48 entries)
        -----    ----   --------
  0)     4824     216   ftrace_call+0x5/0x2f
  1)     4608     112   ____cache_alloc+0xb7/0x22d
  2)     4496      80   kmem_cache_alloc+0x63/0x12f

The 216 size for ftrace_call includes both the ftrace_call stack
(which includes the saving of registers it does), as well as the
stack size of the parent.

To fix this, if CC_USING_FENTRY is defined, then the stack_tracer
will reserve the first item in stack_dump_trace[] array when
calling save_stack_trace(), and it will fill it in with the parent ip.
Then the code will look for the parent pointer on the stack and
give the real size of the parent's stack pointer:

 # cat stack_trace
        Depth    Size   Location    (14 entries)
        -----    ----   --------
  0)     2640      48   update_group_power+0x26/0x187
  1)     2592     224   update_sd_lb_stats+0x2a5/0x4ac
  2)     2368     160   find_busiest_group+0x31/0x1f1
  3)     2208     256   load_balance+0xd9/0x662

I'm Cc'ing stable, although it's not urgent, as it only shows bogus
size for item #0, the rest of the trace is legit. It should still be
corrected in previous stable releases.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace_stack.c | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 6ee97e5..2e341fe 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,13 +20,27 @@
 
 #define STACK_TRACE_ENTRIES 500
 
+/*
+ * If fentry is used, then the function being traced will
+ * jump to fentry directly before it sets up its stack frame.
+ * We need to ignore that one and record the parent. Since
+ * the stack frame for the traced function wasn't set up yet,
+ * the stack_trace wont see the parent. That needs to be added
+ * manually to stack_dump_trace[] as the first element.
+ */
+#ifdef CC_USING_FENTRY
+# define add_func	1
+#else
+# define add_func	0
+#endif
+
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
 static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
 
 static struct stack_trace max_stack_trace = {
-	.max_entries		= STACK_TRACE_ENTRIES,
-	.entries		= stack_dump_trace,
+	.max_entries		= STACK_TRACE_ENTRIES - add_func,
+	.entries		= &stack_dump_trace[add_func],
 };
 
 static unsigned long max_stack_size;
@@ -41,7 +55,7 @@ int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
 static inline void
-check_stack(unsigned long *stack)
+check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags;
 	unsigned long *p, *top, *start;
@@ -72,6 +86,17 @@ check_stack(unsigned long *stack)
 	save_stack_trace(&max_stack_trace);
 
 	/*
+	 * When fentry is used, the traced function does not get
+	 * its stack frame set up, and we lose the parent.
+	 * Add that one in manally. We set up save_stack_trace()
+	 * to not touch the first element in this case.
+	 */
+	if (add_func) {
+		stack_dump_trace[0] = ip;
+		max_stack_trace.nr_entries++;
+	}
+
+	/*
 	 * Now find where in the stack these are.
 	 */
 	i = 0;
@@ -127,7 +152,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	check_stack(&stack);
+	check_stack(parent_ip, &stack);
 
  out:
 	per_cpu(trace_active, cpu)--;
-- 
1.8.1.2

[PATCH 063/118] tracing: Remove most or all of stack tracer stack size from stack_max_size

[Luis Henriques]

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

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

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

commit 4df297129f622bdc18935c856f42b9ddd18f9f28 upstream.

Currently, the depth reported in the stack tracer stack_trace file
does not match the stack_max_size file. This is because the stack_max_size
includes the overhead of stack tracer itself while the depth does not.

The first time a max is triggered, a calculation is not performed that
figures out the overhead of the stack tracer and subtracts it from
the stack_max_size variable. The overhead is stored and is subtracted
from the reported stack size for comparing for a new max.

Now the stack_max_size corresponds to the reported depth:

 # cat stack_max_size
4640

 # cat stack_trace
        Depth    Size   Location    (48 entries)
        -----    ----   --------
  0)     4640      32   _raw_spin_lock+0x18/0x24
  1)     4608     112   ____cache_alloc+0xb7/0x22d
  2)     4496      80   kmem_cache_alloc+0x63/0x12f
  3)     4416      16   mempool_alloc_slab+0x15/0x17
[...]

While testing against and older gcc on x86 that uses mcount instead
of fentry, I found that pasing in ip + MCOUNT_INSN_SIZE let the
stack trace show one more function deep which was missing before.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace_stack.c | 75 +++++++++++++++++++++++++++++++++-------------
 1 file changed, 54 insertions(+), 21 deletions(-)

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2e341fe..0cdcba3 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,27 +20,24 @@
 
 #define STACK_TRACE_ENTRIES 500
 
-/*
- * If fentry is used, then the function being traced will
- * jump to fentry directly before it sets up its stack frame.
- * We need to ignore that one and record the parent. Since
- * the stack frame for the traced function wasn't set up yet,
- * the stack_trace wont see the parent. That needs to be added
- * manually to stack_dump_trace[] as the first element.
- */
 #ifdef CC_USING_FENTRY
-# define add_func	1
+# define fentry		1
 #else
-# define add_func	0
+# define fentry		0
 #endif
 
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
 static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
 
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
 static struct stack_trace max_stack_trace = {
-	.max_entries		= STACK_TRACE_ENTRIES - add_func,
-	.entries		= &stack_dump_trace[add_func],
+	.max_entries		= STACK_TRACE_ENTRIES - 1,
+	.entries		= &stack_dump_trace[1],
 };
 
 static unsigned long max_stack_size;
@@ -59,10 +56,14 @@ check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags;
 	unsigned long *p, *top, *start;
+	static int tracer_frame;
+	int frame_size = ACCESS_ONCE(tracer_frame);
 	int i;
 
 	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
 	this_size = THREAD_SIZE - this_size;
+	/* Remove the frame of the tracer */
+	this_size -= frame_size;
 
 	if (this_size <= max_stack_size)
 		return;
@@ -74,6 +75,10 @@ check_stack(unsigned long ip, unsigned long *stack)
 	local_irq_save(flags);
 	arch_spin_lock(&max_stack_lock);
 
+	/* In case another CPU set the tracer_frame on us */
+	if (unlikely(!frame_size))
+		this_size -= tracer_frame;
+
 	/* a race could have already updated it */
 	if (this_size <= max_stack_size)
 		goto out;
@@ -86,15 +91,12 @@ check_stack(unsigned long ip, unsigned long *stack)
 	save_stack_trace(&max_stack_trace);
 
 	/*
-	 * When fentry is used, the traced function does not get
-	 * its stack frame set up, and we lose the parent.
-	 * Add that one in manally. We set up save_stack_trace()
-	 * to not touch the first element in this case.
+	 * Add the passed in ip from the function tracer.
+	 * Searching for this on the stack will skip over
+	 * most of the overhead from the stack tracer itself.
 	 */
-	if (add_func) {
-		stack_dump_trace[0] = ip;
-		max_stack_trace.nr_entries++;
-	}
+	stack_dump_trace[0] = ip;
+	max_stack_trace.nr_entries++;
 
 	/*
 	 * Now find where in the stack these are.
@@ -124,6 +126,18 @@ check_stack(unsigned long ip, unsigned long *stack)
 				found = 1;
 				/* Start the search from here */
 				start = p + 1;
+				/*
+				 * We do not want to show the overhead
+				 * of the stack tracer stack in the
+				 * max stack. If we haven't figured
+				 * out what that is, then figure it out
+				 * now.
+				 */
+				if (unlikely(!tracer_frame) && i == 1) {
+					tracer_frame = (p - stack) *
+						sizeof(unsigned long);
+					max_stack_size -= tracer_frame;
+				}
 			}
 		}
 
@@ -152,7 +166,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	check_stack(parent_ip, &stack);
+	/*
+	 * When fentry is used, the traced function does not get
+	 * its stack frame set up, and we lose the parent.
+	 * The ip is pretty useless because the function tracer
+	 * was called before that function set up its stack frame.
+	 * In this case, we use the parent ip.
+	 *
+	 * By adding the return address of either the parent ip
+	 * or the current ip we can disregard most of the stack usage
+	 * caused by the stack tracer itself.
+	 *
+	 * The function tracer always reports the address of where the
+	 * mcount call was, but the stack will hold the return address.
+	 */
+	if (fentry)
+		ip = parent_ip;
+	else
+		ip += MCOUNT_INSN_SIZE;
+
+	check_stack(ip, &stack);
 
  out:
 	per_cpu(trace_active, cpu)--;
-- 
1.8.1.2

[PATCH 064/118] tracing: Fix ftrace_dump()

[Luis Henriques]

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

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

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

commit 7fe70b579c9e3daba71635e31b6189394e7b79d3 upstream.

ftrace_dump() had a lot of issues. What ftrace_dump() does, is when
ftrace_dump_on_oops is set (via a kernel parameter or sysctl), it
will dump out the ftrace buffers to the console when either a oops,
panic, or a sysrq-z occurs.

This was written a long time ago when ftrace was fragile to recursion.
But it wasn't written well even for that.

There's a possible deadlock that can occur if a ftrace_dump() is happening
and an NMI triggers another dump. This is because it grabs a lock
before checking if the dump ran.

It also totally disables ftrace, and tracing for no good reasons.

As the ring_buffer now checks if it is read via a oops or NMI, where
there's a chance that the buffer gets corrupted, it will disable
itself. No need to have ftrace_dump() do the same.

ftrace_dump() is now cleaned up where it uses an atomic counter to
make sure only one dump happens at a time. A simple atomic_inc_return()
is enough that is needed for both other CPUs and NMIs. No need for
a spinlock, as if one CPU is running the dump, no other CPU needs
to do it too.

The tracing_on variable is turned off and not turned on. The original
code did this, but it wasn't pretty. By just disabling this variable
we get the result of not seeing traces that happen between crashes.

For sysrq-z, it doesn't get turned on, but the user can always write
a '1' to the tracing_on file. If they are using sysrq-z, then they should
know about tracing_on.

The new code is much easier to read and less error prone. No more
deadlock possibility when an NMI triggers here.

Reported-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
[ luis: backport to 3.5:
  - adjust context
  - use the static per_cpu arrays ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace.c          | 62 ++++++++++++++++++-------------------------
 kernel/trace/trace_selftest.c |  9 ++++---
 2 files changed, 31 insertions(+), 40 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 34c61b2..28e2b14 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4968,36 +4968,32 @@ void trace_init_global_iter(struct trace_iterator *iter)
 	iter->cpu_file = TRACE_PIPE_ALL_CPU;
 }
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-	static arch_spinlock_t ftrace_dump_lock =
-		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
+	static atomic_t dump_running;
 	unsigned int old_userobj;
-	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
 
-	/* only one dump */
-	local_irq_save(flags);
-	arch_spin_lock(&ftrace_dump_lock);
-	if (dump_ran)
-		goto out;
-
-	dump_ran = 1;
+	/* Only allow one dump user at a time. */
+	if (atomic_inc_return(&dump_running) != 1) {
+		atomic_dec(&dump_running);
+		return;
+	}
 
+	/*
+	 * Always turn off tracing when we dump.
+	 * We don't need to show trace output of what happens
+	 * between multiple crashes.
+	 *
+	 * If the user does a sysrq-z, then they can re-enable
+	 * tracing with echo 1 > tracing_on.
+	 */
 	tracing_off();
 
-	/* Did function tracer already get disabled? */
-	if (ftrace_is_dead()) {
-		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
-		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
-	}
-
-	if (disable_tracing)
-		ftrace_kill();
+	local_irq_save(flags);
 
 	trace_init_global_iter(&iter);
 
@@ -5030,6 +5026,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
+	/* Did function tracer already get disabled? */
+	if (ftrace_is_dead()) {
+		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
+	}
+
 	/*
 	 * We need to stop all tracing on all CPUS to read the
 	 * the next buffer. This is a bit expensive, but is
@@ -5069,26 +5071,14 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		printk(KERN_TRACE "---------------------------------\n");
 
  out_enable:
-	/* Re-enable tracing if requested */
-	if (!disable_tracing) {
-		trace_flags |= old_userobj;
+	trace_flags |= old_userobj;
 
-		for_each_tracing_cpu(cpu) {
-			atomic_dec(&iter.tr->data[cpu]->disabled);
-		}
-		tracing_on();
+	for_each_tracing_cpu(cpu) {
+		atomic_dec(&iter.tr->data[cpu]->disabled);
 	}
-
- out:
-	arch_spin_unlock(&ftrace_dump_lock);
+ 	atomic_dec(&dump_running);
 	local_irq_restore(flags);
 }
-
-/* By default: disable tracing after the dump */
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
-{
-	__ftrace_dump(true, oops_dump_mode);
-}
 EXPORT_SYMBOL_GPL(ftrace_dump);
 
 __init static int tracer_alloc_buffers(void)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 288541f..09fd98a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -461,8 +461,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST	100000000
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -472,8 +470,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
 		ftrace_graph_stop();
 		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
-		if (ftrace_dump_on_oops)
-			__ftrace_dump(false, DUMP_ALL);
+		if (ftrace_dump_on_oops) {
+			ftrace_dump(DUMP_ALL);
+			/* ftrace_dump() disables tracing */
+			tracing_on();
+		}
 		return 0;
 	}
 
-- 
1.8.1.2

[PATCH 065/118] Wrong asm register contraints in the futex implementation

[Luis Henriques]

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

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

From: Stephan Schreiber <info@fs-driver.org>

commit 136f39ddc53db3bcee2befbe323a56d4fbf06da8 upstream.

The Linux Kernel contains some inline assembly source code which has
wrong asm register constraints in arch/ia64/include/asm/futex.h.

I observed this on Kernel 3.2.23 but it is also true on the most
recent Kernel 3.9-rc1.

File arch/ia64/include/asm/futex.h:

static inline int
futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
			      u32 oldval, u32 newval)
{
	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
		return -EFAULT;

	{
		register unsigned long r8 __asm ("r8");
		unsigned long prev;
		__asm__ __volatile__(
			"	mf;;					\n"
			"	mov %0=r0				\n"
			"	mov ar.ccv=%4;;				\n"
			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
			"[2:]"
			: "=r" (r8), "=r" (prev)
			: "r" (uaddr), "r" (newval),
			  "rO" ((long) (unsigned) oldval)
			: "memory");
		*uval = prev;
		return r8;
	}
}

The list of output registers is
			: "=r" (r8), "=r" (prev)
The constraint "=r" means that the GCC has to maintain that these vars
are in registers and contain valid info when the program flow leaves
the assembly block (output registers).
But "=r" also means that GCC can put them in registers that are used
as input registers. Input registers are uaddr, newval, oldval on the
example.
The second assembly instruction
			"	mov %0=r0				\n"
is the first one which writes to a register; it sets %0 to 0. %0 means
the first register operand; it is r8 here. (The r0 is read-only and
always 0 on the Itanium; it can be used if an immediate zero value is
needed.)
This instruction might overwrite one of the other registers which are
still needed.
Whether it really happens depends on how GCC decides what registers it
uses and how it optimizes the code.

The objdump utility can give us disassembly.
The futex_atomic_cmpxchg_inatomic() function is inline, so we have to
look for a module that uses the funtion. This is the
cmpxchg_futex_value_locked() function in
kernel/futex.c:

static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
				      u32 uval, u32 newval)
{
	int ret;

	pagefault_disable();
	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
	pagefault_enable();

	return ret;
}

Now the disassembly. At first from the Kernel package 3.2.23 which has
been compiled with GCC 4.4, remeber this Kernel seemed to work:
objdump -d linux-3.2.23/debian/build/build_ia64_none_mckinley/kernel/futex.o

0000000000000230 <cmpxchg_futex_value_locked>:
      230:	0b 18 80 1b 18 21 	[MMI]       adds r3=3168,r13;;
      236:	80 40 0d 00 42 00 	            adds r8=40,r3
      23c:	00 00 04 00       	            nop.i 0x0;;
      240:	0b 50 00 10 10 10 	[MMI]       ld4 r10=[r8];;
      246:	90 08 28 00 42 00 	            adds r9=1,r10
      24c:	00 00 04 00       	            nop.i 0x0;;
      250:	09 00 00 00 01 00 	[MMI]       nop.m 0x0
      256:	00 48 20 20 23 00 	            st4 [r8]=r9
      25c:	00 00 04 00       	            nop.i 0x0;;
      260:	08 10 80 06 00 21 	[MMI]       adds r2=32,r3
      266:	00 00 00 02 00 00 	            nop.m 0x0
      26c:	02 08 f1 52       	            extr.u r16=r33,0,61
      270:	05 40 88 00 08 e0 	[MLX]       addp4 r8=r34,r0
      276:	ff ff 0f 00 00 e0 	            movl r15=0xfffffffbfff;;
      27c:	f1 f7 ff 65
      280:	09 70 00 04 18 10 	[MMI]       ld8 r14=[r2]
      286:	00 00 00 02 00 c0 	            nop.m 0x0
      28c:	f0 80 1c d0       	            cmp.ltu p6,p7=r15,r16;;
      290:	08 40 fc 1d 09 3b 	[MMI]       cmp.eq p8,p9=-1,r14
      296:	00 00 00 02 00 40 	            nop.m 0x0
      29c:	e1 08 2d d0       	            cmp.ltu p10,p11=r14,r33
      2a0:	56 01 10 00 40 10 	[BBB] (p10) br.cond.spnt.few 2e0
<cmpxchg_futex_value_locked+0xb0>
      2a6:	02 08 00 80 21 03 	      (p08) br.cond.dpnt.few 2b0
<cmpxchg_futex_value_locked+0x80>
      2ac:	40 00 00 41       	      (p06) br.cond.spnt.few 2e0
<cmpxchg_futex_value_locked+0xb0>
      2b0:	0a 00 00 00 22 00 	[MMI]       mf;;
      2b6:	80 00 00 00 42 00 	            mov r8=r0
      2bc:	00 00 04 00       	            nop.i 0x0
      2c0:	0b 00 20 40 2a 04 	[MMI]       mov.m ar.ccv=r8;;
      2c6:	10 1a 85 22 20 00 	            cmpxchg4.acq r33=[r33],r35,ar.ccv
      2cc:	00 00 04 00       	            nop.i 0x0;;
      2d0:	10 00 84 40 90 11 	[MIB]       st4 [r32]=r33
      2d6:	00 00 00 02 00 00 	            nop.i 0x0
      2dc:	20 00 00 40       	            br.few 2f0
<cmpxchg_futex_value_locked+0xc0>
      2e0:	09 40 c8 f9 ff 27 	[MMI]       mov r8=-14
      2e6:	00 00 00 02 00 00 	            nop.m 0x0
      2ec:	00 00 04 00       	            nop.i 0x0;;
      2f0:	0b 58 20 1a 19 21 	[MMI]       adds r11=3208,r13;;
      2f6:	20 01 2c 20 20 00 	            ld4 r18=[r11]
      2fc:	00 00 04 00       	            nop.i 0x0;;
      300:	0b 88 fc 25 3f 23 	[MMI]       adds r17=-1,r18;;
      306:	00 88 2c 20 23 00 	            st4 [r11]=r17
      30c:	00 00 04 00       	            nop.i 0x0;;
      310:	11 00 00 00 01 00 	[MIB]       nop.m 0x0
      316:	00 00 00 02 00 80 	            nop.i 0x0
      31c:	08 00 84 00       	            br.ret.sptk.many b0;;

The lines
      2b0:	0a 00 00 00 22 00 	[MMI]       mf;;
      2b6:	80 00 00 00 42 00 	            mov r8=r0
      2bc:	00 00 04 00       	            nop.i 0x0
      2c0:	0b 00 20 40 2a 04 	[MMI]       mov.m ar.ccv=r8;;
      2c6:	10 1a 85 22 20 00 	            cmpxchg4.acq r33=[r33],r35,ar.ccv
      2cc:	00 00 04 00       	            nop.i 0x0;;
are the instructions of the assembly block.
The line
      2b6:	80 00 00 00 42 00 	            mov r8=r0
sets the r8 register to 0 and after that
      2c0:	0b 00 20 40 2a 04 	[MMI]       mov.m ar.ccv=r8;;
prepares the 'oldvalue' for the cmpxchg but it takes it from r8. This
is wrong.
What happened here is what I explained above: An input register is
overwritten which is still needed.
The register operand constraints in futex.h are wrong.

(The problem doesn't occur when the Kernel is compiled with GCC 4.6.)

The attached patch fixes the register operand constraints in futex.h.
The code after patching of it:

static inline int
futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
			      u32 oldval, u32 newval)
{
	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
		return -EFAULT;

	{
		register unsigned long r8 __asm ("r8") = 0;
		unsigned long prev;
		__asm__ __volatile__(
			"	mf;;					\n"
			"	mov ar.ccv=%4;;				\n"
			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
			"[2:]"
			: "+r" (r8), "=&r" (prev)
			: "r" (uaddr), "r" (newval),
			  "rO" ((long) (unsigned) oldval)
			: "memory");
		*uval = prev;
		return r8;
	}
}

I also initialized the 'r8' var with the C programming language.
The _asm qualifier on the definition of the 'r8' var forces GCC to use
the r8 processor register for it.
I don't believe that we should use inline assembly for zeroing out a
local variable.
The constraint is
"+r" (r8)
what means that it is both an input register and an output register.
Note that the page fault handler will modify the r8 register which
will be the return value of the function.
The real fix is
"=&r" (prev)
The & means that GCC must not use any of the input registers to place
this output register in.

Patched the Kernel 3.2.23 and compiled it with GCC4.4:

0000000000000230 <cmpxchg_futex_value_locked>:
      230:	0b 18 80 1b 18 21 	[MMI]       adds r3=3168,r13;;
      236:	80 40 0d 00 42 00 	            adds r8=40,r3
      23c:	00 00 04 00       	            nop.i 0x0;;
      240:	0b 50 00 10 10 10 	[MMI]       ld4 r10=[r8];;
      246:	90 08 28 00 42 00 	            adds r9=1,r10
      24c:	00 00 04 00       	            nop.i 0x0;;
      250:	09 00 00 00 01 00 	[MMI]       nop.m 0x0
      256:	00 48 20 20 23 00 	            st4 [r8]=r9
      25c:	00 00 04 00       	            nop.i 0x0;;
      260:	08 10 80 06 00 21 	[MMI]       adds r2=32,r3
      266:	20 12 01 10 40 00 	            addp4 r34=r34,r0
      26c:	02 08 f1 52       	            extr.u r16=r33,0,61
      270:	05 40 00 00 00 e1 	[MLX]       mov r8=r0
      276:	ff ff 0f 00 00 e0 	            movl r15=0xfffffffbfff;;
      27c:	f1 f7 ff 65
      280:	09 70 00 04 18 10 	[MMI]       ld8 r14=[r2]
      286:	00 00 00 02 00 c0 	            nop.m 0x0
      28c:	f0 80 1c d0       	            cmp.ltu p6,p7=r15,r16;;
      290:	08 40 fc 1d 09 3b 	[MMI]       cmp.eq p8,p9=-1,r14
      296:	00 00 00 02 00 40 	            nop.m 0x0
      29c:	e1 08 2d d0       	            cmp.ltu p10,p11=r14,r33
      2a0:	56 01 10 00 40 10 	[BBB] (p10) br.cond.spnt.few 2e0
<cmpxchg_futex_value_locked+0xb0>
      2a6:	02 08 00 80 21 03 	      (p08) br.cond.dpnt.few 2b0
<cmpxchg_futex_value_locked+0x80>
      2ac:	40 00 00 41       	      (p06) br.cond.spnt.few 2e0
<cmpxchg_futex_value_locked+0xb0>
      2b0:	0b 00 00 00 22 00 	[MMI]       mf;;
      2b6:	00 10 81 54 08 00 	            mov.m ar.ccv=r34
      2bc:	00 00 04 00       	            nop.i 0x0;;
      2c0:	09 58 8c 42 11 10 	[MMI]       cmpxchg4.acq r11=[r33],r35,ar.ccv
      2c6:	00 00 00 02 00 00 	            nop.m 0x0
      2cc:	00 00 04 00       	            nop.i 0x0;;
      2d0:	10 00 2c 40 90 11 	[MIB]       st4 [r32]=r11
      2d6:	00 00 00 02 00 00 	            nop.i 0x0
      2dc:	20 00 00 40       	            br.few 2f0
<cmpxchg_futex_value_locked+0xc0>
      2e0:	09 40 c8 f9 ff 27 	[MMI]       mov r8=-14
      2e6:	00 00 00 02 00 00 	            nop.m 0x0
      2ec:	00 00 04 00       	            nop.i 0x0;;
      2f0:	0b 88 20 1a 19 21 	[MMI]       adds r17=3208,r13;;
      2f6:	30 01 44 20 20 00 	            ld4 r19=[r17]
      2fc:	00 00 04 00       	            nop.i 0x0;;
      300:	0b 90 fc 27 3f 23 	[MMI]       adds r18=-1,r19;;
      306:	00 90 44 20 23 00 	            st4 [r17]=r18
      30c:	00 00 04 00       	            nop.i 0x0;;
      310:	11 00 00 00 01 00 	[MIB]       nop.m 0x0
      316:	00 00 00 02 00 80 	            nop.i 0x0
      31c:	08 00 84 00       	            br.ret.sptk.many b0;;

Much better.
There is a
      270:	05 40 00 00 00 e1 	[MLX]       mov r8=r0
which was generated by C code r8 = 0. Below
      2b6:	00 10 81 54 08 00 	            mov.m ar.ccv=r34
what means that oldval is no longer overwritten.

This is Debian bug#702641
(http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=702641).

The patch is applicable on Kernel 3.9-rc1, 3.2.23 and many other versions.

Signed-off-by: Stephan Schreiber <info@fs-driver.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/ia64/include/asm/futex.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index d2bf1fd..76acbcd 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -106,16 +106,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8");
+		register unsigned long r8 __asm ("r8") = 0;
 		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
-			"	mov %0=r0				\n"
 			"	mov ar.ccv=%4;;				\n"
 			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (r8), "=r" (prev)
+			: "+r" (r8), "=&r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");
-- 
1.8.1.2

[PATCH 066/118] Wrong asm register contraints in the kvm implementation

[Luis Henriques]

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

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

From: Stephan Schreiber <info@fs-driver.org>

commit de53e9caa4c6149ef4a78c2f83d7f5b655848767 upstream.

The Linux Kernel contains some inline assembly source code which has
wrong asm register constraints in arch/ia64/kvm/vtlb.c.

I observed this on Kernel 3.2.35 but it is also true on the most
recent Kernel 3.9-rc1.

File arch/ia64/kvm/vtlb.c:

u64 guest_vhpt_lookup(u64 iha, u64 *pte)
{
	u64 ret;
	struct thash_data *data;

	data = __vtr_lookup(current_vcpu, iha, D_TLB);
	if (data != NULL)
		thash_vhpt_insert(current_vcpu, data->page_flags,
			data->itir, iha, D_TLB);

	asm volatile (
			"rsm psr.ic|psr.i;;"
			"srlz.d;;"
			"ld8.s r9=[%1];;"
			"tnat.nz p6,p7=r9;;"
			"(p6) mov %0=1;"
			"(p6) mov r9=r0;"
			"(p7) extr.u r9=r9,0,53;;"
			"(p7) mov %0=r0;"
			"(p7) st8 [%2]=r9;;"
			"ssm psr.ic;;"
			"srlz.d;;"
			"ssm psr.i;;"
			"srlz.d;;"
			: "=r"(ret) : "r"(iha), "r"(pte):"memory");

	return ret;
}

The list of output registers is
			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
The constraint "=r" means that the GCC has to maintain that these vars
are in registers and contain valid info when the program flow leaves
the assembly block (output registers).
But "=r" also means that GCC can put them in registers that are used
as input registers. Input registers are iha, pte on the example.
If the predicate p7 is true, the 8th assembly instruction
			"(p7) mov %0=r0;"
is the first one which writes to a register which is maintained by the
register constraints; it sets %0. %0 means the first register operand;
it is ret here.
This instruction might overwrite the %2 register (pte) which is needed
by the next instruction:
			"(p7) st8 [%2]=r9;;"
Whether it really happens depends on how GCC decides what registers it
uses and how it optimizes the code.

The attached patch  fixes the register operand constraints in
arch/ia64/kvm/vtlb.c.
The register constraints should be
			: "=&r"(ret) : "r"(iha), "r"(pte):"memory");
The & means that GCC must not use any of the input registers to place
this output register in.

This is Debian bug#702639
(http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=702639).

The patch is applicable on Kernel 3.9-rc1, 3.2.35 and many other versions.

Signed-off-by: Stephan Schreiber <info@fs-driver.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/ia64/kvm/vtlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 4332f7e..a7869f8 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte)
 			"srlz.d;;"
 			"ssm psr.i;;"
 			"srlz.d;;"
-			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
+			: "=&r"(ret) : "r"(iha), "r"(pte) : "memory");
 
 	return ret;
 }
-- 
1.8.1.2

[PATCH 067/118] cgroup: fix an off-by-one bug which may trigger BUG_ON()

[Luis Henriques]

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

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

From: Li Zefan <lizefan@huawei.com>

commit 3ac1707a13a3da9cfc8f242a15b2fae6df2c5f88 upstream.

The 3rd parameter of flex_array_prealloc() is the number of elements,
not the index of the last element.

The effect of the bug is, when opening cgroup.procs, a flex array will
be allocated and all elements of the array is allocated with
GFP_KERNEL flag, but the last one is GFP_ATOMIC, and if we fail to
allocate memory for it, it'll trigger a BUG_ON().

Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 87fbb45..5168e37 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2079,7 +2079,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	if (!group)
 		return -ENOMEM;
 	/* pre-allocate to guarantee space while iterating in rcu read-side. */
-	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+	retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
 	if (retval)
 		goto out_free_group_list;
 
-- 
1.8.1.2

[PATCH 068/118] PCI / ACPI: Don't query OSC support with all possible controls

[Luis Henriques]

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

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

From: Yinghai Lu <yinghai@kernel.org>

commit 545d6e189a41c94c11f55045a771118eccc9d9eb upstream.

Found problem on system that firmware that could handle pci aer.
Firmware get error reporting after pci injecting error, before os boots.
But after os boots, firmware can not get report anymore, even pci=noaer
is passed.

Root cause: BIOS _OSC has problem with query bit checking.
It turns out that BIOS vendor is copying example code from ACPI Spec.
In ACPI Spec 5.0, page 290:

	If (Not(And(CDW1,1))) // Query flag clear?
	{	// Disable GPEs for features granted native control.
		If (And(CTRL,0x01)) // Hot plug control granted?
		{
			Store(0,HPCE) // clear the hot plug SCI enable bit
			Store(1,HPCS) // clear the hot plug SCI status bit
		}
	...
	}

When Query flag is set, And(CDW1,1) will be 1, Not(1) will return 0xfffffffe.
So it will get into code path that should be for control set only.
BIOS acpi code should be changed to "If (LEqual(And(CDW1,1), 0)))"

Current kernel code is using _OSC query to notify firmware about support
from OS and then use _OSC to set control bits.
During query support, current code is using all possible controls.
So will execute code that should be only for control set stage.

That will have problem when pci=noaer or aer firmware_first is used.
As firmware have that control set for os aer already in query support stage,
but later will not os aer handling.

We should avoid passing all possible controls, just use osc_control_set
instead.
That should workaround BIOS bugs with affected systems on the field
as more bios vendors are copying sample code from ACPI spec.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/acpi/pci_root.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 7aff631..5b0f075 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -247,8 +247,8 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
 		*control &= OSC_PCI_CONTROL_MASKS;
 		capbuf[OSC_CONTROL_TYPE] = *control | root->osc_control_set;
 	} else {
-		/* Run _OSC query for all possible controls. */
-		capbuf[OSC_CONTROL_TYPE] = OSC_PCI_CONTROL_MASKS;
+		/* Run _OSC query only with existing controls. */
+		capbuf[OSC_CONTROL_TYPE] = root->osc_control_set;
 	}
 
 	status = acpi_pci_run_osc(root->device->handle, capbuf, &result);
-- 
1.8.1.2

[PATCH 069/118] Fix initialization of CMCI/CMCP interrupts

[Luis Henriques]

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

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

From: Tony Luck <tony.luck@intel.com>

commit d303e9e98fce56cdb3c6f2ac92f626fc2bd51c77 upstream.

Back 2010 during a revamp of the irq code some initializations
were moved from ia64_mca_init() to ia64_mca_late_init() in

	commit c75f2aa13f5b268aba369b5dc566088b5194377c
	Cannot use register_percpu_irq() from ia64_mca_init()

But this was hideously wrong. First of all these initializations
are now down far too late. Specifically after all the other cpus
have been brought up and initialized their own CMC vectors from
smp_callin(). Also ia64_mca_late_init() may be called from any cpu
so the line:
	ia64_mca_cmc_vector_setup();       /* Setup vector on BSP */
is generally not executed on the BSP, and so the CMC vector isn't
setup at all on that processor.

Make use of the arch_early_irq_init() hook to get this code executed
at just the right moment: not too early, not too late.

Reported-by: Fred Hartnett <fred.hartnett@hp.com>
Tested-by: Fred Hartnett <fred.hartnett@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/ia64/include/asm/mca.h |  1 +
 arch/ia64/kernel/irq.c      |  8 ++++++++
 arch/ia64/kernel/mca.c      | 37 ++++++++++++++++++++++++-------------
 3 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h
index 43f96ab..8c70961 100644
--- a/arch/ia64/include/asm/mca.h
+++ b/arch/ia64/include/asm/mca.h
@@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS];
 extern int cpe_vector;
 extern int ia64_cpe_irq;
 extern void ia64_mca_init(void);
+extern void ia64_mca_irq_init(void);
 extern void ia64_mca_cpu_init(void *);
 extern void ia64_os_mca_dispatch(void);
 extern void ia64_os_mca_dispatch_end(void);
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index ad69606..f2c41828 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -23,6 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 
+#include <asm/mca.h>
+
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.
@@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask)
 
 #endif /* CONFIG_SMP */
 
+int __init arch_early_irq_init(void)
+{
+	ia64_mca_irq_init();
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 unsigned int vectors_in_migration[NR_IRQS];
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 65bf9cd..d7396db 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -2074,22 +2074,16 @@ ia64_mca_init(void)
 	printk(KERN_INFO "MCA related initialization done\n");
 }
 
+
 /*
- * ia64_mca_late_init
- *
- *	Opportunity to setup things that require initialization later
- *	than ia64_mca_init.  Setup a timer to poll for CPEs if the
- *	platform doesn't support an interrupt driven mechanism.
- *
- *  Inputs  :   None
- *  Outputs :   Status
+ * These pieces cannot be done in ia64_mca_init() because it is called before
+ * early_irq_init() which would wipe out our percpu irq registrations. But we
+ * cannot leave them until ia64_mca_late_init() because by then all the other
+ * processors have been brought online and have set their own CMC vectors to
+ * point at a non-existant action. Called from arch_early_irq_init().
  */
-static int __init
-ia64_mca_late_init(void)
+void __init ia64_mca_irq_init(void)
 {
-	if (!mca_init)
-		return 0;
-
 	/*
 	 *  Configure the CMCI/P vector and handler. Interrupts for CMC are
 	 *  per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c).
@@ -2108,6 +2102,23 @@ ia64_mca_late_init(void)
 	/* Setup the CPEI/P handler */
 	register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
 #endif
+}
+
+/*
+ * ia64_mca_late_init
+ *
+ *	Opportunity to setup things that require initialization later
+ *	than ia64_mca_init.  Setup a timer to poll for CPEs if the
+ *	platform doesn't support an interrupt driven mechanism.
+ *
+ *  Inputs  :   None
+ *  Outputs :   Status
+ */
+static int __init
+ia64_mca_late_init(void)
+{
+	if (!mca_init)
+		return 0;
 
 	register_hotcpu_notifier(&mca_cpu_notifier);
 
-- 
1.8.1.2

[PATCH 070/118] sysfs: fix use after free in case of concurrent read/write and readdir

[Luis Henriques]

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

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

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

commit f7db5e7660b122142410dcf36ba903c73d473250 upstream.

The inode->i_mutex isn't hold when updating filp->f_pos
in read()/write(), so the filp->f_pos might be read as
0 or 1 in readdir() when there is concurrent read()/write()
on this same file, then may cause use after free in readdir().

The bug can be reproduced with Li Zefan's test code on the
link:

	https://patchwork.kernel.org/patch/2160771/

This patch fixes the use after free under this situation.

Reported-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/sysfs/dir.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 8777436..1a32e0f 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -1013,6 +1013,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	enum kobj_ns_type type;
 	const void *ns;
 	ino_t ino;
+	loff_t off;
 
 	type = sysfs_ns_type(parent_sd);
 	ns = sysfs_info(dentry->d_sb)->ns[type];
@@ -1035,6 +1036,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 			return 0;
 	}
 	mutex_lock(&sysfs_mutex);
+	off = filp->f_pos;
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
@@ -1046,19 +1048,24 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		len = strlen(name);
 		ino = pos->s_ino;
 		type = dt_type(pos);
-		filp->f_pos = pos->s_hash;
+		off = filp->f_pos = pos->s_hash;
 		filp->private_data = sysfs_get(pos);
 
 		mutex_unlock(&sysfs_mutex);
-		ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+		ret = filldir(dirent, name, len, off, ino, type);
 		mutex_lock(&sysfs_mutex);
 		if (ret < 0)
 			break;
 	}
 	mutex_unlock(&sysfs_mutex);
-	if ((filp->f_pos > 1) && !pos) { /* EOF */
-		filp->f_pos = INT_MAX;
+
+	/* don't reference last entry if its refcount is dropped */
+	if (!pos) {
 		filp->private_data = NULL;
+
+		/* EOF and not changed as 0 or 1 in read/write path */
+		if (off == filp->f_pos && off > 1)
+			filp->f_pos = INT_MAX;
 	}
 	return 0;
 }
-- 
1.8.1.2

[PATCH 071/118] usb/misc/appledisplay: Add 24" LED Cinema display

[Luis Henriques]

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

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

From: Ben Jencks <ben@bjencks.net>

commit e7d3b6e22c871ba36d052ca99bc8ceca4d546a60 upstream.

Add the Apple 24" LED Cinema display to the supported devices.

Signed-off-by: Ben Jencks <ben@bjencks.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/misc/appledisplay.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/misc/appledisplay.c b/drivers/usb/misc/appledisplay.c
index 0fc6e5f..ba6a5d6 100644
--- a/drivers/usb/misc/appledisplay.c
+++ b/drivers/usb/misc/appledisplay.c
@@ -63,6 +63,7 @@ static const struct usb_device_id appledisplay_table[] = {
 	{ APPLEDISPLAY_DEVICE(0x9219) },
 	{ APPLEDISPLAY_DEVICE(0x921c) },
 	{ APPLEDISPLAY_DEVICE(0x921d) },
+	{ APPLEDISPLAY_DEVICE(0x9236) },
 
 	/* Terminating entry */
 	{ }
-- 
1.8.1.2

[PATCH 072/118] ext4/jbd2: don't wait (forever) for stale tid caused by wraparound

[Luis Henriques]

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

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

From: Theodore Ts'o <tytso@mit.edu>

commit d76a3a77113db020d9bb1e894822869410450bd9 upstream.

In the case where an inode has a very stale transaction id (tid) in
i_datasync_tid or i_sync_tid, it's possible that after a very large
(2**31) number of transactions, that the tid number space might wrap,
causing tid_geq()'s calculations to fail.

Commit deeeaf13 "jbd2: fix fsync() tid wraparound bug", later modified
by commit e7b04ac0 "jbd2: don't wake kjournald unnecessarily",
attempted to fix this problem, but it only avoided kjournald spinning
forever by fixing the logic in jbd2_log_start_commit().

Unfortunately, in the codepaths in fs/ext4/fsync.c and fs/ext4/inode.c
that might call jbd2_log_start_commit() with a stale tid, those
functions will subsequently call jbd2_log_wait_commit() with the same
stale tid, and then wait for a very long time.  To fix this, we
replace the calls to jbd2_log_start_commit() and
jbd2_log_wait_commit() with a call to a new function,
jbd2_complete_transaction(), which will correctly handle stale tid's.

As a bonus, jbd2_complete_transaction() will avoid locking
j_state_lock for writing unless a commit needs to be started.  This
should have a small (but probably not measurable) improvement for
ext4's scalability.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Ben Hutchings <ben@decadent.org.uk>
Reported-by: George Barnett <gbarnett@atlassian.com>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/fsync.c      |  3 +--
 fs/ext4/inode.c      |  3 +--
 fs/jbd2/journal.c    | 31 +++++++++++++++++++++++++++++++
 include/linux/jbd2.h |  1 +
 4 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index bb6c7d8..a8d03a4 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -260,8 +260,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		needs_barrier = true;
-	jbd2_log_start_commit(journal, commit_tid);
-	ret = jbd2_log_wait_commit(journal, commit_tid);
+	ret = jbd2_complete_transaction(journal, commit_tid);
 	if (needs_barrier)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
  out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c14b394..0ec3a3f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -216,8 +216,7 @@ void ext4_evict_inode(struct inode *inode)
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
-			jbd2_log_start_commit(journal, commit_tid);
-			jbd2_log_wait_commit(journal, commit_tid);
+			jbd2_complete_transaction(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
 		truncate_inode_pages(&inode->i_data, 0);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0f16edd..dfb0e5b 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -699,6 +699,37 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 }
 
 /*
+ * When this function returns the transaction corresponding to tid
+ * will be completed.  If the transaction has currently running, start
+ * committing that transaction before waiting for it to complete.  If
+ * the transaction id is stale, it is by definition already completed,
+ * so just return SUCCESS.
+ */
+int jbd2_complete_transaction(journal_t *journal, tid_t tid)
+{
+	int	need_to_wait = 1;
+
+	read_lock(&journal->j_state_lock);
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == tid) {
+		if (journal->j_commit_request != tid) {
+			/* transaction not yet started, so request it */
+			read_unlock(&journal->j_state_lock);
+			jbd2_log_start_commit(journal, tid);
+			goto wait_commit;
+		}
+	} else if (!(journal->j_committing_transaction &&
+		     journal->j_committing_transaction->t_tid == tid))
+		need_to_wait = 0;
+	read_unlock(&journal->j_state_lock);
+	if (!need_to_wait)
+		return 0;
+wait_commit:
+	return jbd2_log_wait_commit(journal, tid);
+}
+EXPORT_SYMBOL(jbd2_complete_transaction);
+
+/*
  * Log buffer allocation routines:
  */
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 3efc43f..deee02a 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1211,6 +1211,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
 int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
 int jbd2_journal_force_commit_nested(journal_t *journal);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
 
-- 
1.8.1.2

[PATCH 073/118] jbd2: fix race between jbd2_journal_remove_checkpoint and ->j_commit_callback

[Luis Henriques]

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

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

From: Dmitry Monakhov <dmonakhov@openvz.org>

commit 794446c6946513c684d448205fbd76fa35f38b72 upstream.

The following race is possible:

[kjournald2]                              other_task
jbd2_journal_commit_transaction()
  j_state = T_FINISHED;
  spin_unlock(&journal->j_list_lock);
                                         ->jbd2_journal_remove_checkpoint()
					   ->jbd2_journal_free_transaction();
					     ->kmem_cache_free(transaction)
  ->j_commit_callback(journal, transaction);
    -> USE_AFTER_FREE

WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250()
Hardware name:
list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b
Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod
Pid: 16400, comm: jbd2/dm-1-8 Tainted: G        W    3.8.0-rc3+ #107
Call Trace:
 [<ffffffff8106fb0d>] warn_slowpath_common+0xad/0xf0
 [<ffffffff8106fc06>] warn_slowpath_fmt+0x46/0x50
 [<ffffffff813637e9>] ? ext4_journal_commit_callback+0x99/0xc0
 [<ffffffff8148cae0>] __list_del_entry+0x1c0/0x250
 [<ffffffff813637bf>] ext4_journal_commit_callback+0x6f/0xc0
 [<ffffffff813ca336>] jbd2_journal_commit_transaction+0x23a6/0x2570
 [<ffffffff8108aa42>] ? try_to_del_timer_sync+0x82/0xa0
 [<ffffffff8108b491>] ? del_timer_sync+0x91/0x1e0
 [<ffffffff813d3ecf>] kjournald2+0x19f/0x6a0
 [<ffffffff810ad630>] ? wake_up_bit+0x40/0x40
 [<ffffffff813d3d30>] ? bit_spin_lock+0x80/0x80
 [<ffffffff810ac6be>] kthread+0x10e/0x120
 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70
 [<ffffffff818ff6ac>] ret_from_fork+0x7c/0xb0
 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70

In order to demonstrace this issue one should mount ext4 with mount -o
discard option on SSD disk.  This makes callback longer and race
window becomes wider.

In order to fix this we should mark transaction as finished only after
callbacks have completed

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/jbd2/commit.c     | 50 ++++++++++++++++++++++++++++----------------------
 include/linux/jbd2.h |  1 +
 2 files changed, 29 insertions(+), 22 deletions(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 216f429..a7826ec 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -382,7 +382,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int space_left = 0;
 	int first_tag = 0;
 	int tag_flag;
-	int i, to_free = 0;
+	int i;
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
@@ -1108,7 +1108,7 @@ restart_loop:
 	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
 	spin_unlock(&journal->j_history_lock);
 
-	commit_transaction->t_state = T_FINISHED;
+	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;
 	journal->j_committing_transaction = NULL;
@@ -1123,38 +1123,44 @@ restart_loop:
 				journal->j_average_commit_time*3) / 4;
 	else
 		journal->j_average_commit_time = commit_time;
+
 	write_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
-		__jbd2_journal_drop_transaction(journal, commit_transaction);
-		to_free = 1;
+	if (journal->j_checkpoint_transactions == NULL) {
+		journal->j_checkpoint_transactions = commit_transaction;
+		commit_transaction->t_cpnext = commit_transaction;
+		commit_transaction->t_cpprev = commit_transaction;
 	} else {
-		if (journal->j_checkpoint_transactions == NULL) {
-			journal->j_checkpoint_transactions = commit_transaction;
-			commit_transaction->t_cpnext = commit_transaction;
-			commit_transaction->t_cpprev = commit_transaction;
-		} else {
-			commit_transaction->t_cpnext =
-				journal->j_checkpoint_transactions;
-			commit_transaction->t_cpprev =
-				commit_transaction->t_cpnext->t_cpprev;
-			commit_transaction->t_cpnext->t_cpprev =
-				commit_transaction;
-			commit_transaction->t_cpprev->t_cpnext =
+		commit_transaction->t_cpnext =
+			journal->j_checkpoint_transactions;
+		commit_transaction->t_cpprev =
+			commit_transaction->t_cpnext->t_cpprev;
+		commit_transaction->t_cpnext->t_cpprev =
+			commit_transaction;
+		commit_transaction->t_cpprev->t_cpnext =
 				commit_transaction;
-		}
 	}
 	spin_unlock(&journal->j_list_lock);
-
+	/* Drop all spin_locks because commit_callback may be block.
+	 * __journal_remove_checkpoint() can not destroy transaction
+	 * under us because it is not marked as T_FINISHED yet */
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
-	if (to_free)
-		jbd2_journal_free_transaction(commit_transaction);
 
+	write_lock(&journal->j_state_lock);
+	spin_lock(&journal->j_list_lock);
+	commit_transaction->t_state = T_FINISHED;
+	/* Recheck checkpoint lists after j_list_lock was dropped */
+	if (commit_transaction->t_checkpoint_list == NULL &&
+	    commit_transaction->t_checkpoint_io_list == NULL) {
+		__jbd2_journal_drop_transaction(journal, commit_transaction);
+		jbd2_journal_free_transaction(commit_transaction);
+	}
+	spin_unlock(&journal->j_list_lock);
+	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
 }
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index deee02a..ade60e7 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -498,6 +498,7 @@ struct transaction_s
 		T_COMMIT,
 		T_COMMIT_DFLUSH,
 		T_COMMIT_JFLUSH,
+		T_COMMIT_CALLBACK,
 		T_FINISHED
 	}			t_state;
 
-- 
1.8.1.2

[PATCH 074/118] ext4: fix journal callback list traversal

[Luis Henriques]

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

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

From: Dmitry Monakhov <dmonakhov@openvz.org>

commit 5d3ee20855e28169d711b394857ee608a5023094 upstream.

It is incorrect to use list_for_each_entry_safe() for journal callback
traversial because ->next may be removed by other task:
->ext4_mb_free_metadata()
  ->ext4_mb_free_metadata()
    ->ext4_journal_callback_del()

This results in the following issue:

WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250()
Hardware name:
list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b
Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod
Pid: 16400, comm: jbd2/dm-1-8 Tainted: G        W    3.8.0-rc3+ #107
Call Trace:
 [<ffffffff8106fb0d>] warn_slowpath_common+0xad/0xf0
 [<ffffffff8106fc06>] warn_slowpath_fmt+0x46/0x50
 [<ffffffff813637e9>] ? ext4_journal_commit_callback+0x99/0xc0
 [<ffffffff8148cae0>] __list_del_entry+0x1c0/0x250
 [<ffffffff813637bf>] ext4_journal_commit_callback+0x6f/0xc0
 [<ffffffff813ca336>] jbd2_journal_commit_transaction+0x23a6/0x2570
 [<ffffffff8108aa42>] ? try_to_del_timer_sync+0x82/0xa0
 [<ffffffff8108b491>] ? del_timer_sync+0x91/0x1e0
 [<ffffffff813d3ecf>] kjournald2+0x19f/0x6a0
 [<ffffffff810ad630>] ? wake_up_bit+0x40/0x40
 [<ffffffff813d3d30>] ? bit_spin_lock+0x80/0x80
 [<ffffffff810ac6be>] kthread+0x10e/0x120
 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70
 [<ffffffff818ff6ac>] ret_from_fork+0x7c/0xb0
 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70

This patch fix the issue as follows:
- ext4_journal_commit_callback() make list truly traversial safe
  simply by always starting from list_head
- fix race between two ext4_journal_callback_del() and
  ext4_journal_callback_try_del()

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/ext4_jbd2.h | 6 +++++-
 fs/ext4/mballoc.c   | 8 ++++----
 fs/ext4/super.c     | 7 +++++--
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index f440e8f1..d4253e1 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -164,16 +164,20 @@ static inline void ext4_journal_callback_add(handle_t *handle,
  * ext4_journal_callback_del: delete a registered callback
  * @handle: active journal transaction handle on which callback was registered
  * @jce: registered journal callback entry to unregister
+ * Return true if object was sucessfully removed
  */
-static inline void ext4_journal_callback_del(handle_t *handle,
+static inline bool ext4_journal_callback_try_del(handle_t *handle,
 					     struct ext4_journal_cb_entry *jce)
 {
+	bool deleted;
 	struct ext4_sb_info *sbi =
 			EXT4_SB(handle->h_transaction->t_journal->j_private);
 
 	spin_lock(&sbi->s_md_lock);
+	deleted = !list_empty(&jce->jce_list);
 	list_del_init(&jce->jce_list);
 	spin_unlock(&sbi->s_md_lock);
+	return deleted;
 }
 
 int
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 18571ac..9777e2f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4433,11 +4433,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_prev(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(entry, new_entry)) {
+		if (can_merge(entry, new_entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_start_cluster = entry->efd_start_cluster;
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
@@ -4445,10 +4445,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_next(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(new_entry, entry)) {
+		if (can_merge(new_entry, entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 79881a6..df4b8db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -480,10 +480,13 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	struct super_block		*sb = journal->j_private;
 	struct ext4_sb_info		*sbi = EXT4_SB(sb);
 	int				error = is_journal_aborted(journal);
-	struct ext4_journal_cb_entry	*jce, *tmp;
+	struct ext4_journal_cb_entry	*jce;
 
+	BUG_ON(txn->t_state == T_FINISHED);
 	spin_lock(&sbi->s_md_lock);
-	list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) {
+	while (!list_empty(&txn->t_private_list)) {
+		jce = list_entry(txn->t_private_list.next,
+				 struct ext4_journal_cb_entry, jce_list);
 		list_del_init(&jce->jce_list);
 		spin_unlock(&sbi->s_md_lock);
 		jce->jce_func(sb, jce, error);
-- 
1.8.1.2

[PATCH 075/118] usb: chipidea: udc: fix memory access of shared memory on armv5 machines

[Luis Henriques]

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

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

From: Michael Grzeschik <m.grzeschik@pengutronix.de>

commit a9c174302b1590ef3ead485d804a303c5f89174b upstream.

The udc uses an shared dma memory space between hard and software. This
memory layout is described in ci13xxx_qh and ci13xxx_td which are marked
with the attribute ((packed)).

The compiler currently does not know about the alignment of the memory
layout, and will create strb and ldrb operations.

The Datasheet of the synopsys core describes, that some operations on
the mapped memory need to be atomic double word operations. I.e. the
next pointer addressing in the qhead, as otherwise the hardware will
read wrong data and totally stuck.

This is also possible while working with the current active td queue,
and preparing the td->ptr.next in software while the hardware is still
working with the current active td which is supposed to be changed:

writeb(0xde, &td->ptr.next + 0x0); /* strb */
writeb(0xad, &td->ptr.next + 0x1); /* strb */

<----- hardware reads value of td->ptr.next and get stuck!

writeb(0xbe, &td->ptr.next + 0x2); /* strb */
writeb(0xef, &td->ptr.next + 0x3); /* strb */

This appeares on armv5 machines where the hardware does not support
unaligned 32bit operations.

This patch adds the attribute ((aligned(4))) to the structures to tell
the compiler to use 32bit operations. It also adds an wmb() for the
prepared TD data before it gets enqueued into the qhead.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/chipidea/udc.c | 2 ++
 drivers/usb/chipidea/udc.h | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index ea271d7..60bcf1c 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -439,6 +439,8 @@ static int _hardware_enqueue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
 		mReq->ptr->page[i] =
 			(mReq->req.dma + i * CI13XXX_PAGE_SIZE) & ~TD_RESERVED_MASK;
 
+	wmb();
+
 	if (!list_empty(&mEp->qh.queue)) {
 		struct ci13xxx_req *mReqPrev;
 		int n = hw_ep_bit(mEp->num, mEp->dir);
diff --git a/drivers/usb/chipidea/udc.h b/drivers/usb/chipidea/udc.h
index 4ff2384d..d12e8b5 100644
--- a/drivers/usb/chipidea/udc.h
+++ b/drivers/usb/chipidea/udc.h
@@ -40,7 +40,7 @@ struct ci13xxx_td {
 #define TD_CURR_OFFSET        (0x0FFFUL <<  0)
 #define TD_FRAME_NUM          (0x07FFUL <<  0)
 #define TD_RESERVED_MASK      (0x0FFFUL <<  0)
-} __attribute__ ((packed));
+} __attribute__ ((packed, aligned(4)));
 
 /* DMA layout of queue heads */
 struct ci13xxx_qh {
@@ -57,7 +57,7 @@ struct ci13xxx_qh {
 	/* 9 */
 	u32 RESERVED;
 	struct usb_ctrlrequest   setup;
-} __attribute__ ((packed));
+} __attribute__ ((packed, aligned(4)));
 
 /**
  * struct ci13xxx_req - usb request representation
-- 
1.8.1.2

[PATCH 076/118] NFSv4: Handle NFS4ERR_DELAY and NFS4ERR_GRACE in nfs4_open_delegation_recall

[Luis Henriques]

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

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

From: Trond Myklebust <Trond.Myklebust@netapp.com>

commit 8b6cc4d6f841d31f72fe7478453759166d366274 upstream.

A server shouldn't normally return NFS4ERR_GRACE if the client holds a
delegation, since no conflicting lock reclaims can be granted, however
the spec does not require the server to grant the open in this
instance

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/nfs/nfs4proc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b96aa12..480918e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1381,6 +1381,12 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -ENOMEM:
 				err = 0;
 				goto out;
+			case -NFS4ERR_DELAY:
+			case -NFS4ERR_GRACE:
+				set_bit(NFS_DELEGATED_STATE, &state->flags);
+				ssleep(1);
+				err = -EAGAIN;
+				goto out;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
-- 
1.8.1.2

[PATCH 077/118] usb: chipidea: udc: fix memory leak in _ep_nuke

[Luis Henriques]

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

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

From: Michael Grzeschik <m.grzeschik@pengutronix.de>

commit 7ca2cd291fd84ae499390f227a255ccba2780a81 upstream.

In hardware_enqueue code adds one extra td with dma_pool_alloc if
mReq->req.zero is true. When _ep_nuke will be called for that endpoint,
dma_pool_free will not be called to free that memory again. That patch
fixes this.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/chipidea/udc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 60bcf1c..113b4f1 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -541,6 +541,12 @@ __acquires(mEp->lock)
 		struct ci13xxx_req *mReq = \
 			list_entry(mEp->qh.queue.next,
 				   struct ci13xxx_req, queue);
+
+		if (mReq->zptr) {
+			dma_pool_free(mEp->td_pool, mReq->zptr, mReq->zdma);
+			mReq->zptr = NULL;
+		}
+
 		list_del_init(&mReq->queue);
 		mReq->req.status = -ESHUTDOWN;
 
-- 
1.8.1.2

[PATCH 078/118] USB: add ftdi_sio USB ID for GDM Boost V1.x

[Luis Henriques]

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

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

From: Stefani Seibold <stefani@seibold.net>

commit 58f8b6c4fa5a13cb2ddb400e26e9e65766d71e38 upstream.

This patch add a missing usb device id for the GDMBoost V1.x device

The patch is against 3.9-rc5

Signed-off-by: Stefani Seibold <stefani@seibold.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/ftdi_sio.c     | 1 +
 drivers/usb/serial/ftdi_sio_ids.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index a93f958..527fb35 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -195,6 +195,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_OPENDCC_THROTTLE_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OPENDCC_GATEWAY_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OPENDCC_GBM_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_OPENDCC_GBM_BOOST_PID) },
 	{ USB_DEVICE(NEWPORT_VID, NEWPORT_AGILIS_PID) },
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) },
 	{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e79861e..3c00351 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -74,6 +74,7 @@
 #define FTDI_OPENDCC_THROTTLE_PID	0xBFDA
 #define FTDI_OPENDCC_GATEWAY_PID	0xBFDB
 #define FTDI_OPENDCC_GBM_PID	0xBFDC
+#define FTDI_OPENDCC_GBM_BOOST_PID	0xBFDD
 
 /* NZR SEM 16+ USB (http://www.nzr.de) */
 #define FTDI_NZR_SEM_USB_PID	0xC1E0	/* NZR SEM-LOG16+ */
-- 
1.8.1.2

[PATCH 079/118] hrtimer: Add expiry time overflow check in hrtimer_interrupt

[Luis Henriques]

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

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

From: Prarit Bhargava <prarit@redhat.com>

commit 8f294b5a139ee4b75e890ad5b443c93d1e558a8b upstream.

The settimeofday01 test in the LTP testsuite effectively does

        gettimeofday(current time);
        settimeofday(Jan 1, 1970 + 100 seconds);
        settimeofday(current time);

This test causes a stack trace to be displayed on the console during the
setting of timeofday to Jan 1, 1970 + 100 seconds:

[  131.066751] ------------[ cut here ]------------
[  131.096448] WARNING: at kernel/time/clockevents.c:209 clockevents_program_event+0x135/0x140()
[  131.104935] Hardware name: Dinar
[  131.108150] Modules linked in: sg nfsv3 nfs_acl nfsv4 auth_rpcgss nfs dns_resolver fscache lockd sunrpc nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6table_mangle ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ip_tables kvm_amd kvm sp5100_tco bnx2 i2c_piix4 crc32c_intel k10temp fam15h_power ghash_clmulni_intel amd64_edac_mod pcspkr serio_raw edac_mce_amd edac_core microcode xfs libcrc32c sr_mod sd_mod cdrom ata_generic crc_t10dif pata_acpi radeon i2c_algo_bit drm_kms_helper ttm drm ahci pata_atiixp libahci libata usb_storage i2c_core dm_mirror dm_region_hash dm_log dm_mod
[  131.176784] Pid: 0, comm: swapper/28 Not tainted 3.8.0+ #6
[  131.182248] Call Trace:
[  131.184684]  <IRQ>  [<ffffffff810612af>] warn_slowpath_common+0x7f/0xc0
[  131.191312]  [<ffffffff8106130a>] warn_slowpath_null+0x1a/0x20
[  131.197131]  [<ffffffff810b9fd5>] clockevents_program_event+0x135/0x140
[  131.203721]  [<ffffffff810bb584>] tick_program_event+0x24/0x30
[  131.209534]  [<ffffffff81089ab1>] hrtimer_interrupt+0x131/0x230
[  131.215437]  [<ffffffff814b9600>] ? cpufreq_p4_target+0x130/0x130
[  131.221509]  [<ffffffff81619119>] smp_apic_timer_interrupt+0x69/0x99
[  131.227839]  [<ffffffff8161805d>] apic_timer_interrupt+0x6d/0x80
[  131.233816]  <EOI>  [<ffffffff81099745>] ? sched_clock_cpu+0xc5/0x120
[  131.240267]  [<ffffffff814b9ff0>] ? cpuidle_wrap_enter+0x50/0xa0
[  131.246252]  [<ffffffff814b9fe9>] ? cpuidle_wrap_enter+0x49/0xa0
[  131.252238]  [<ffffffff814ba050>] cpuidle_enter_tk+0x10/0x20
[  131.257877]  [<ffffffff814b9c89>] cpuidle_idle_call+0xa9/0x260
[  131.263692]  [<ffffffff8101c42f>] cpu_idle+0xaf/0x120
[  131.268727]  [<ffffffff815f8971>] start_secondary+0x255/0x257
[  131.274449] ---[ end trace 1151a50552231615 ]---

When we change the system time to a low value like this, the value of
timekeeper->offs_real will be a negative value.

It seems that the WARN occurs because an hrtimer has been started in the time
between the releasing of the timekeeper lock and the IPI call (via a call to
on_each_cpu) in clock_was_set() in the do_settimeofday() code.  The end result
is that a REALTIME_CLOCK timer has been added with softexpires = expires =
KTIME_MAX.  The hrtimer_interrupt() fires/is called and the loop at
kernel/hrtimer.c:1289 is executed.  In this loop the code subtracts the
clock base's offset (which was set to timekeeper->offs_real in
do_settimeofday()) from the current hrtimer_cpu_base->expiry value (which
was KTIME_MAX):

	KTIME_MAX - (a negative value) = overflow

A simple check for an overflow can resolve this problem.  Using KTIME_MAX
instead of the overflow value will result in the hrtimer function being run,
and the reprogramming of the timer after that.

Cc: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
[jstultz: Tweaked commit subject]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/hrtimer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index e4cee8d..97d3742 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1308,6 +1308,8 @@ retry:
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
 						    base->offset);
+				if (expires.tv64 < 0)
+					expires.tv64 = KTIME_MAX;
 				if (expires.tv64 < expires_next.tv64)
 					expires_next = expires;
 				break;
-- 
1.8.1.2

[PATCH 080/118] hrtimer: Fix ktime_add_ns() overflow on 32bit architectures

[Luis Henriques]

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

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

From: David Engraf <david.engraf@sysgo.com>

commit 51fd36f3fad8447c487137ae26b9d0b3ce77bb25 upstream.

One can trigger an overflow when using ktime_add_ns() on a 32bit
architecture not supporting CONFIG_KTIME_SCALAR.

When passing a very high value for u64 nsec, e.g. 7881299347898368000
the do_div() function converts this value to seconds (7881299347) which
is still to high to pass to the ktime_set() function as long. The result
in is a negative value.

The problem on my system occurs in the tick-sched.c,
tick_nohz_stop_sched_tick() when time_delta is set to
timekeeping_max_deferment(). The check for time_delta < KTIME_MAX is
valid, thus ktime_add_ns() is called with a too large value resulting in
a negative expire value. This leads to an endless loop in the ticker code:

time_delta: 7881299347898368000
expires = ktime_add_ns(last_update, time_delta)
expires: negative value

This fix caps the value to KTIME_MAX.

This error doesn't occurs on 64bit or architectures supporting
CONFIG_KTIME_SCALAR (e.g. ARM, x86-32).

Signed-off-by: David Engraf <david.engraf@sysgo.com>
[jstultz: Minor tweaks to commit message & header]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/hrtimer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 97d3742..60f7e32 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -298,6 +298,10 @@ ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec)
 	} else {
 		unsigned long rem = do_div(nsec, NSEC_PER_SEC);
 
+		/* Make sure nsec fits into long */
+		if (unlikely(nsec > KTIME_SEC_MAX))
+			return (ktime_t){ .tv64 = KTIME_MAX };
+
 		tmp = ktime_set((long)nsec, rem);
 	}
 
-- 
1.8.1.2

[PATCH 081/118] ARM: omap3: cpuidle: enable time keeping

[Luis Henriques]

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

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

From: Daniel Lezcano <daniel.lezcano@linaro.org>

commit 0d97558901c446a989de202a5d9ae94ec53644e5 upstream.

The TIME_VALID flag is specified for the different states but
the time residency computation is not done, no tk flag, no time
computation in the idle function.

Set the en_core_tk_irqen flag to activate it.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Kevin Hilman <khilman@linaro.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/mach-omap2/cpuidle34xx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index 207bc1c..36f65a8 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -284,8 +284,9 @@ select_state:
 DEFINE_PER_CPU(struct cpuidle_device, omap3_idle_dev);
 
 struct cpuidle_driver omap3_idle_driver = {
-	.name = 	"omap3_idle",
-	.owner = 	THIS_MODULE,
+	.name             = "omap3_idle",
+	.owner            = THIS_MODULE,
+	.en_core_tk_irqen = 1,
 	.states = {
 		{
 			.enter		  = omap3_enter_idle,
-- 
1.8.1.2

[PATCH 082/118] tracing: Fix off-by-one on allocating stat->pages

[Luis Henriques]

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

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

From: Namhyung Kim <namhyung.kim@lge.com>

commit 39e30cd1537937d3c00ef87e865324e981434e5b upstream.

The first page was allocated separately, so no need to start from 0.

Link: http://lkml.kernel.org/r/1364820385-32027-2-git-send-email-namhyung@kernel.org

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/ftrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 38353bf..80b2000 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -624,7 +624,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 
 	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
 
-	for (i = 0; i < pages; i++) {
+	for (i = 1; i < pages; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!pg->next)
 			goto out_free;
-- 
1.8.1.2

[PATCH 083/118] USB: option: add a D-Link DWM-156 variant

[Luis Henriques]

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

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

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

commit a2a2d6c7f93e160b52a4ad0164db1f43f743ae0f upstream.

Adding support for a Mediatek based device labelled as
D-Link Model: DWM-156, H/W Ver: A7

Also adding two other device IDs found in the Debian(!)
packages included on the embedded device driver CD.

This is a composite MBIM + serial ports + card reader device:

T:  Bus=04 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 14 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=2001 ProdID=7d01 Rev= 3.00
S:  Manufacturer=D-Link,Inc
S:  Product=D-Link DWM-156
C:* #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=500mA
A:  FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=88(I) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=02 Prot=01 Driver=option
E:  Ad=87(I) Atr=03(Int.) MxPS=  64 Ivl=500us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/option.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index dd442c0..3038ba9 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1350,6 +1350,12 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CHANGHONG_VENDOR_ID, CHANGHONG_PRODUCT_CH690) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d01, 0xff, 0x02, 0x01) },	/* D-Link DWM-156 (variant) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d01, 0xff, 0x00, 0x00) },	/* D-Link DWM-156 (variant) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x02, 0x01) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x00, 0x00) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
-- 
1.8.1.2

[PATCH 084/118] ext4: fix big-endian bug in metadata checksum calculations

[Luis Henriques]

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

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

From: Dmitry Monakhov <dmonakhov@openvz.org>

commit 171a7f21a76a0958c225b97c00a97a10390d40ee upstream.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/inode.c | 8 ++++----
 fs/ext4/mmp.c   | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0ec3a3f..55006fa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -55,21 +55,21 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 	__u16 csum_hi = 0;
 	__u32 csum;
 
-	csum_lo = raw->i_checksum_lo;
+	csum_lo = le16_to_cpu(raw->i_checksum_lo);
 	raw->i_checksum_lo = 0;
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
 	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = raw->i_checksum_hi;
+		csum_hi = le16_to_cpu(raw->i_checksum_hi);
 		raw->i_checksum_hi = 0;
 	}
 
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
 			   EXT4_INODE_SIZE(inode->i_sb));
 
-	raw->i_checksum_lo = csum_lo;
+	raw->i_checksum_lo = cpu_to_le16(csum_lo);
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
 	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = csum_hi;
+		raw->i_checksum_hi = cpu_to_le16(csum_hi);
 
 	return csum;
 }
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index b4d5088..f0e2c96 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -7,7 +7,7 @@
 #include "ext4.h"
 
 /* Checksumming functions */
-static __u32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
+static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int offset = offsetof(struct mmp_struct, mmp_checksum);
-- 
1.8.1.2

[PATCH 085/118] tracing: Reset ftrace_graph_filter_enabled if count is zero

[Luis Henriques]

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

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

From: Namhyung Kim <namhyung.kim@lge.com>

commit 9f50afccfdc15d95d7331acddcb0f7703df089ae upstream.

The ftrace_graph_count can be decreased with a "!" pattern, so that
the enabled flag should be updated too.

Link: http://lkml.kernel.org/r/1365663698-2413-1-git-send-email-namhyung@kernel.org

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/ftrace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 80b2000..36759bf 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3579,7 +3579,8 @@ out:
 	if (fail)
 		return -EINVAL;
 
-	ftrace_graph_filter_enabled = 1;
+	ftrace_graph_filter_enabled = !!(*idx);
+
 	return 0;
 }
 
-- 
1.8.1.2

[PATCH 086/118] tracing: Check return value of tracing_init_dentry()

[Luis Henriques]

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

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

From: Namhyung Kim <namhyung.kim@lge.com>

commit ed6f1c996bfe4b6e520cf7a74b51cd6988d84420 upstream.

Check return value and bail out if it's NULL.

Link: http://lkml.kernel.org/r/1365553093-10180-2-git-send-email-namhyung@kernel.org

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/trace/trace.c       | 2 ++
 kernel/trace/trace_stack.c | 2 ++
 kernel/trace/trace_stat.c  | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 28e2b14..0ae8b32 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4832,6 +4832,8 @@ static __init int tracer_init_debugfs(void)
 	trace_access_lock_init();
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
 	trace_create_file("tracing_enabled", 0644, d_tracer,
 			&global_trace, &tracing_ctrl_fops);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 0cdcba3..8298997 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -433,6 +433,8 @@ static __init int stack_trace_init(void)
 	struct dentry *d_tracer;
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
 	trace_create_file("stack_max_size", 0644, d_tracer,
 			&max_stack_size, &stack_max_size_fops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 96cffb2..847f88a 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -307,6 +307,8 @@ static int tracing_stat_init(void)
 	struct dentry *d_tracing;
 
 	d_tracing = tracing_init_dentry();
+	if (!d_tracing)
+		return 0;
 
 	stat_dir = debugfs_create_dir("trace_stat", d_tracing);
 	if (!stat_dir)
-- 
1.8.1.2

[PATCH 087/118] serial_core.c: add put_device() after device_find_child()

[Luis Henriques]

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

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

From: Federico Vaga <federico.vaga@gmail.com>

commit 5a65dcc04cda41f4122aacc37a5a348454645399 upstream.

The serial core uses device_find_child() but does not drop the reference to
the retrieved child after using it. This patch add the missing put_device().

What I have done to test this issue.

I used a machine with an AMBA PL011 serial driver. I tested the patch on
next-20120408 because the last branch [next-20120415] does not boot on this
board.

For test purpose, I added some pr_info() messages to print the refcount
after device_find_child() (lines: 1937,2009), and after put_device()
(lines: 1947, 2021).

Boot the machine *without* put_device(). Then:

echo reboot > /sys/power/disk
echo disk > /sys/power/state
[   87.058575] uart_suspend_port:1937 refcount 4
[   87.058582] uart_suspend_port:1947 refcount 4
[   87.098083] uart_resume_port:2009refcount 5
[   87.098088] uart_resume_port:2021 refcount 5

echo disk > /sys/power/state
[  103.055574] uart_suspend_port:1937 refcount 6
[  103.055580] uart_suspend_port:1947 refcount 6
[  103.095322] uart_resume_port:2009 refcount 7
[  103.095327] uart_resume_port:2021 refcount 7

echo disk > /sys/power/state
[  252.459580] uart_suspend_port:1937 refcount 8
[  252.459586] uart_suspend_port:1947 refcount 8
[  252.499611] uart_resume_port:2009 refcount 9
[  252.499616] uart_resume_port:2021 refcount 9

The refcount continuously increased.

Boot the machine *with* this patch. Then:

echo reboot > /sys/power/disk
echo disk > /sys/power/state
[  159.333559] uart_suspend_port:1937 refcount 4
[  159.333566] uart_suspend_port:1947 refcount 3
[  159.372751] uart_resume_port:2009 refcount 4
[  159.372755] uart_resume_port:2021 refcount 3

echo disk > /sys/power/state
[  185.713614] uart_suspend_port:1937 refcount 4
[  185.713621] uart_suspend_port:1947 refcount 3
[  185.752935] uart_resume_port:2009 refcount 4
[  185.752940] uart_resume_port:2021 refcount 3

echo disk > /sys/power/state
[  207.458584] uart_suspend_port:1937 refcount 4
[  207.458591] uart_suspend_port:1947 refcount 3
[  207.498598] uart_resume_port:2009 refcount 4
[  207.498605] uart_resume_port:2021 refcount 3

The refcount correctly handled.

Signed-off-by: Federico Vaga <federico.vaga@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/tty/serial/serial_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 246b823..4185cc5 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1877,6 +1877,8 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport)
 		mutex_unlock(&port->mutex);
 		return 0;
 	}
+	put_device(tty_dev);
+
 	if (console_suspend_enabled || !uart_console(uport))
 		uport->suspended = 1;
 
@@ -1942,9 +1944,11 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport)
 			disable_irq_wake(uport->irq);
 			uport->irq_wake = 0;
 		}
+		put_device(tty_dev);
 		mutex_unlock(&port->mutex);
 		return 0;
 	}
+	put_device(tty_dev);
 	uport->suspended = 0;
 
 	/*
-- 
1.8.1.2

[PATCH 088/118] PCI/PM: Fix fallback to PCI_D0 in pci_platform_power_transition()

[Luis Henriques]

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

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

From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>

commit 769ba7212f2059ca9fe0c73371e3d415c8c1c529 upstream.

Commit b51306c (PCI: Set device power state to PCI_D0 for device
without native PM support) modified pci_platform_power_transition()
by adding code causing dev->current_state for devices that don't
support native PCI PM but are power-manageable by the platform to be
changed to PCI_D0 regardless of the value returned by the preceding
platform_pci_set_power_state().  In particular, that also is done
if the platform_pci_set_power_state() has been successful, which
causes the correct power state of the device set by
pci_update_current_state() in that case to be overwritten by PCI_D0.

Fix that mistake by making the fallback to PCI_D0 only happen if
the platform_pci_set_power_state() has returned an error.

[bhelgaas: folded in Yinghai's simplification, added URL & stable info]
Reference: http://lkml.kernel.org/r/27806FC4E5928A408B78E88BBC67A2306F466BBA@ORSMSX101.amr.corp.intel.com
Reported-by: Chris J. Benenati <chris.j.benenati@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/pci/pci.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 447e834..fa7c0f0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -674,15 +674,11 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
 		error = platform_pci_set_power_state(dev, state);
 		if (!error)
 			pci_update_current_state(dev, state);
-		/* Fall back to PCI_D0 if native PM is not supported */
-		if (!dev->pm_cap)
-			dev->current_state = PCI_D0;
-	} else {
+	} else
 		error = -ENODEV;
-		/* Fall back to PCI_D0 if native PM is not supported */
-		if (!dev->pm_cap)
-			dev->current_state = PCI_D0;
-	}
+
+	if (error && !dev->pm_cap) /* Fall back to PCI_D0 */
+		dev->current_state = PCI_D0;
 
 	return error;
 }
-- 
1.8.1.2

[PATCH 089/118] wireless: regulatory: fix channel disabling race condition

[Luis Henriques]

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

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

From: Johannes Berg <johannes.berg@intel.com>

commit 990de49f74e772b6db5208457b7aa712a5f4db86 upstream.

When a full scan 2.4 and 5 GHz scan is scheduled, but then the 2.4 GHz
part of the scan disables a 5.2 GHz channel due to, e.g. receiving
country or frequency information, that 5.2 GHz channel might already
be in the list of channels to scan next. Then, when the driver checks
if it should do a passive scan, that will return false and attempt an
active scan. This is not only wrong but can also lead to the iwlwifi
device firmware crashing since it checks regulatory as well.

Fix this by not setting the channel flags to just disabled but rather
OR'ing in the disabled flag. That way, even if the race happens, the
channel will be scanned passively which is still (mostly) correct.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 net/wireless/reg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 4dc8347..796a0ee 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -862,7 +862,7 @@ static void handle_channel(struct wiphy *wiphy,
 			return;
 
 		REG_DBG_PRINT("Disabling freq %d MHz\n", chan->center_freq);
-		chan->flags = IEEE80211_CHAN_DISABLED;
+		chan->flags |= IEEE80211_CHAN_DISABLED;
 		return;
 	}
 
-- 
1.8.1.2

[PATCH 090/118] usbfs: Always allow ctrl requests with USB_RECIP_ENDPOINT on the ctrl ep

[Luis Henriques]

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

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

From: Hans de Goede <hdegoede@redhat.com>

commit 1361bf4b9f9ef45e628a5b89e0fd9bedfdcb7104 upstream.

When usbfs receives a ctrl-request from userspace it calls check_ctrlrecip,
which for a request with USB_RECIP_ENDPOINT tries to map this to an interface
to see if this interface is claimed, except for ctrl-requests with a type of
USB_TYPE_VENDOR.

When trying to use this device: http://www.akaipro.com/eiepro
redirected to a Windows vm running on qemu on top of Linux.

The windows driver makes a ctrl-req with USB_TYPE_CLASS and
USB_RECIP_ENDPOINT with index 0, and the mapping of the endpoint (0) to
the interface fails since ep 0 is the ctrl endpoint and thus never is
part of an interface.

This patch fixes this ctrl-req failing by skipping the checkintf call for
USB_RECIP_ENDPOINT ctrl-reqs on the ctrl endpoint.

Reported-by: Dave Stikkolorum <d.r.stikkolorum@hhs.nl>
Tested-by: Dave Stikkolorum <d.r.stikkolorum@hhs.nl>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/core/devio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 62679bc..f70b887 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -681,6 +681,8 @@ static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
 	index &= 0xff;
 	switch (requesttype & USB_RECIP_MASK) {
 	case USB_RECIP_ENDPOINT:
+		if ((index & ~USB_DIR_IN) == 0)
+			return 0;
 		ret = findintfep(ps->dev, index);
 		if (ret >= 0)
 			ret = checkintf(ps, ret);
-- 
1.8.1.2

[PATCH 091/118] iwlwifi: fix freeing uninitialized pointer

[Luis Henriques]

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

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

From: Stanislaw Gruszka <sgruszka@redhat.com>

commit 3309ccf7fcebceef540ebe90c65d2f94d745a45b upstream.

If on iwl_dump_nic_event_log() error occurs before that function
initialize buf, we process uninitiated pointer in
iwl_dbgfs_log_event_read() and can hit "BUG at mm/slub.c:3409"

Resolves:
https://bugzilla.redhat.com/show_bug.cgi?id=951241

Reported-by: ian.odette@eprize.com
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
[ luis: backport to 3.5:
  - file rename: dvm/debugfs.c -> iwl-debugfs.c ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/iwlwifi/iwl-debugfs.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
index 5000690..ba376ec 100644
--- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
@@ -2248,15 +2248,15 @@ static ssize_t iwl_dbgfs_log_event_read(struct file *file,
 					 size_t count, loff_t *ppos)
 {
 	struct iwl_priv *priv = file->private_data;
-	char *buf;
-	int pos = 0;
-	ssize_t ret = -ENOMEM;
+	char *buf = NULL;
+	ssize_t ret;
 
-	ret = pos = iwl_dump_nic_event_log(priv, true, &buf, true);
-	if (buf) {
-		ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos);
-		kfree(buf);
-	}
+	ret = iwl_dump_nic_event_log(priv, true, &buf, true);
+	if (ret < 0)
+		goto err;
+	ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
+err:
+	kfree(buf);
 	return ret;
 }
 
-- 
1.8.1.2

[PATCH 092/118] iwlwifi: dvm: don't send zeroed LQ cmd

[Luis Henriques]

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

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

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

commit 63b77bf489881747c5118476918cc8c29378ee63 upstream.

When the stations are being restored because of unassoc
RXON, the LQ cmd may not have been initialized because it
is initialized only after association.
Sending zeroed LQ_CMD makes the fw unhappy: it raises
SYSASSERT_2078.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
[move zero_lq and make static const]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
[ luis: backport to 3.5:
  - file rename: dvm/sta.c -> iwl-agn-sta.c ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/iwlwifi/iwl-agn-sta.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
index 287fdd0..b4f0661 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c
@@ -723,6 +723,7 @@ void iwl_clear_ucode_stations(struct iwl_priv *priv,
 void iwl_restore_stations(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 {
 	struct iwl_addsta_cmd sta_cmd;
+	static const struct iwl_link_quality_cmd zero_lq = {};
 	struct iwl_link_quality_cmd lq;
 	int i;
 	bool found = false;
@@ -761,7 +762,9 @@ void iwl_restore_stations(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 				else
 					memcpy(&lq, priv->stations[i].lq,
 					       sizeof(struct iwl_link_quality_cmd));
-				send_lq = true;
+
+				if (!memcmp(&lq, &zero_lq, sizeof(lq)))
+					send_lq = true;
 			}
 			spin_unlock_bh(&priv->sta_lock);
 			ret = iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
-- 
1.8.1.2

[PATCH 093/118] LOCKD: Ensure that nlmclnt_block resets block->b_status after a server reboot

[Luis Henriques]

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

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

From: Trond Myklebust <Trond.Myklebust@netapp.com>

commit 1dfd89af8697a299e7982ae740d4695ecd917eef upstream.

After a server reboot, the reclaimer thread will recover all the existing
locks. For locks that are blocked, however, it will change the value
of block->b_status to nlm_lck_denied_grace_period in order to signal that
they need to wake up and resend the original blocking lock request.

Due to a bug, however, the block->b_status never gets reset after the
blocked locks have been woken up, and so the process goes into an
infinite loop of resends until the blocked lock is satisfied.

Reported-by: Marc Eshel <eshel@us.ibm.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/lockd/clntlock.c | 3 +++
 fs/lockd/clntproc.c | 3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index ca0a080..193f04c 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -144,6 +144,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 			timeout);
 	if (ret < 0)
 		return -ERESTARTSYS;
+	/* Reset the lock status after a server reboot so we resend */
+	if (block->b_status == nlm_lck_denied_grace_period)
+		block->b_status = nlm_lck_blocked;
 	req->a_res.status = block->b_status;
 	return 0;
 }
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index a3a0987..8392cb8 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -551,9 +551,6 @@ again:
 		status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT);
 		if (status < 0)
 			break;
-		/* Resend the blocking lock request after a server reboot */
-		if (resp->status ==  nlm_lck_denied_grace_period)
-			continue;
 		if (resp->status != nlm_lck_blocked)
 			break;
 	}
-- 
1.8.1.2

[PATCH 094/118] ext4: fix online resizing for ext3-compat file systems

[Luis Henriques]

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

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

From: Theodore Ts'o <tytso@mit.edu>

commit c5c72d814cf0f650010337c73638b25e6d14d2d4 upstream.

Commit fb0a387dcdc restricts block allocations for indirect-mapped
files to block groups less than s_blockfile_groups.  However, the
online resizing code wasn't setting s_blockfile_groups, so the newly
added block groups were not available for non-extent mapped files.

Reported-by: Eric Sandeen <sandeen@redhat.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, 2 insertions(+)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index a2289bf..097a7b0 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1255,6 +1255,8 @@ static void ext4_update_super(struct super_block *sb,
 
 	/* Update the global fs size fields */
 	sbi->s_groups_count += flex_gd->count;
+	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
-- 
1.8.1.2

[PATCH 095/118] ext4: fix Kconfig documentation for CONFIG_EXT4_DEBUG

[Luis Henriques]

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

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

From: Theodore Ts'o <tytso@mit.edu>

commit 7f3e3c7cfcec148ccca9c0dd2dbfd7b00b7ac10f upstream.

Fox the Kconfig documentation for CONFIG_EXT4_DEBUG to match the
change made by commit a0b30c1229: ext4: use module parameters instead
of debugfs for mballoc_debug

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/ext4/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index c22f170..e38370b 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -84,4 +84,5 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
+	  with a command such as:
+		echo 1 > /sys/module/ext4/parameters/mballoc_debug
-- 
1.8.1.2

[PATCH 096/118] rt2x00: Fix transmit power troubles on some Ralink RT30xx cards

[Luis Henriques]

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

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

From: "Alex A. Mihaylov" <minimumlaw@rambler.ru>

commit 7e9dafd873034dd64ababcb858be424c4780ae13 upstream.

Some cards on Ralink RT30xx chipset not have correctly TX_MIXER_GAIN
value in them EEPROM/EFUSE. In this case, we must use default value,
but always used EEPROM/EFUSE value. As result we have tranmitt power
range from -10dBm to +6dBm instead 0dBm to +16dBm.

Correctly value in EEPROM/EFUSE is one or more for RT3070 and two or
more for other RT30xx chips.

Tested on Canyon CNP-WF518N1 usb Wi-Fi dongle and Jorjin WN8020 usb
embedded Wi-Fi module.

Signed-off-by: Alex A. Mihaylov <minimumlaw@rambler.ru>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/rt2x00/rt2800lib.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 346af52..6d0c1ec 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -3862,7 +3862,9 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev)
 	rt2800_register_write(rt2x00dev, OPT_14_CSR, reg);
 
 	if (!rt2x00_rt(rt2x00dev, RT5390) &&
-		!rt2x00_rt(rt2x00dev, RT5392)) {
+	    !rt2x00_rt(rt2x00dev, RT5392)) {
+		u8 min_gain = rt2x00_rt(rt2x00dev, RT3070) ? 1 : 2;
+
 		rt2800_rfcsr_read(rt2x00dev, 17, &rfcsr);
 		rt2x00_set_field8(&rfcsr, RFCSR17_TX_LO1_EN, 0);
 		if (rt2x00_rt(rt2x00dev, RT3070) ||
@@ -3873,8 +3875,10 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev)
 				      &rt2x00dev->cap_flags))
 				rt2x00_set_field8(&rfcsr, RFCSR17_R, 1);
 		}
-		rt2x00_set_field8(&rfcsr, RFCSR17_TXMIXER_GAIN,
-				  drv_data->txmixer_gain_24g);
+		if (drv_data->txmixer_gain_24g >= min_gain) {
+			rt2x00_set_field8(&rfcsr, RFCSR17_TXMIXER_GAIN,
+					  drv_data->txmixer_gain_24g);
+		}
 		rt2800_rfcsr_write(rt2x00dev, 17, rfcsr);
 	}
 
-- 
1.8.1.2

[PATCH 097/118] USB: ftdi_sio: correct ST Micro Connect Lite PIDs

[Luis Henriques]

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

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

From: Adrian Thomasset <adrian.thomasset@st.com>

commit 9f06d15f8db6946e41f73196a122b84a37938878 upstream.

The current ST Micro Connect Lite uses the FT4232H hi-speed quad USB
UART FTDI chip. It is also possible to drive STM reference targets
populated with an on-board JTAG debugger based on the FT2232H chip with
the same STMicroelectronics tools.

For this reason, the ST Micro Connect Lite PIDs should be
ST_STMCLT_2232_PID: 0x3746
ST_STMCLT_4232_PID: 0x3747

Signed-off-by: Adrian Thomasset <adrian.thomasset@st.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/ftdi_sio.c     | 4 +++-
 drivers/usb/serial/ftdi_sio_ids.h | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 527fb35..ecfd525 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -877,7 +877,9 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) },
 	{ USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
-	{ USB_DEVICE(ST_VID, ST_STMCLT1030_PID),
+	{ USB_DEVICE(ST_VID, ST_STMCLT_2232_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(ST_VID, ST_STMCLT_4232_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_stmclite_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_RF_R106) },
 	{ USB_DEVICE(FTDI_VID, FTDI_DISTORTEC_JTAG_LOCK_PICK_PID),
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 3c00351..9852827 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1151,7 +1151,8 @@
  * STMicroelectonics
  */
 #define ST_VID			0x0483
-#define ST_STMCLT1030_PID	0x3747 /* ST Micro Connect Lite STMCLT1030 */
+#define ST_STMCLT_2232_PID	0x3746
+#define ST_STMCLT_4232_PID	0x3747
 
 /*
  * Papouch products (http://www.papouch.com/)
-- 
1.8.1.2

[PATCH 098/118] USB: serial: option: Added support Olivetti Olicard 145

[Luis Henriques]

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

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

From: Filippo Turato <nnj7585@gmail.com>

commit d19bf5cedfd7d53854a3bd699c98b467b139833b upstream.

This adds PID for Olivetti Olicard 145 in option.c

Signed-off-by: Filippo Turato <nnj7585@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.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 3038ba9..c5a50c9 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -347,6 +347,7 @@ static void option_instat_callback(struct urb *urb);
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
 #define OLIVETTI_PRODUCT_OLICARD100		0xc000
+#define OLIVETTI_PRODUCT_OLICARD145		0xc003
 
 /* Celot products */
 #define CELOT_VENDOR_ID				0x211f
@@ -1273,6 +1274,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
 
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) },
 	{ USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */
 	{ USB_DEVICE(ONDA_VENDOR_ID, ONDA_MT825UP) }, /* ONDA MT825UP modem */
 	{ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/
-- 
1.8.1.2

[PATCH 099/118] usb-storage: CY7C68300A chips do not support Cypress ATACB

[Luis Henriques]

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

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

From: Tormod Volden <debian.tormod@gmail.com>

commit 671b4b2ba9266cbcfe7210a704e9ea487dcaa988 upstream.

Many cards based on CY7C68300A/B/C use the USB ID 04b4:6830 but only the
B and C variants (EZ-USB AT2LP) support the ATA Command Block
functionality, according to the data sheets. The A variant (EZ-USB AT2)
locks up if ATACB is attempted, until a typical 30 seconds timeout runs
out and a USB reset is performed.

https://bugs.launchpad.net/bugs/428469

It seems that one way to spot a CY7C68300A (at least where the card
manufacturer left Cypress' EEPROM default vaules, against Cypress'
recommendations) is to look at the USB string descriptor indices.

A http://media.digikey.com/pdf/Data%20Sheets/Cypress%20PDFs/CY7C68300A.pdf
B http://www.farnell.com/datasheets/43456.pdf
C http://www.cypress.com/?rID=14189

Note that a CY7C68300B/C chip appears as CY7C68300A if it is running
in Backward Compatibility Mode, and if ATACB would be supported in this
case there is anyway no way to tell which chip it really is.

For 5 years my external USB drive has been locking up for half a minute
when plugged in and ata_id is run by udev, or anytime hdparm or similar
is run on it.

Finally looking at the /correct/ datasheet I think I found the reason. I
am aware the quirk in this patch is a bit hacky, but the hardware
manufacturers haven't made it easy for us.

Signed-off-by: Tormod Volden <debian.tormod@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/storage/cypress_atacb.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/storage/cypress_atacb.c b/drivers/usb/storage/cypress_atacb.c
index 5fe451d..c1f6751 100644
--- a/drivers/usb/storage/cypress_atacb.c
+++ b/drivers/usb/storage/cypress_atacb.c
@@ -248,14 +248,26 @@ static int cypress_probe(struct usb_interface *intf,
 {
 	struct us_data *us;
 	int result;
+	struct usb_device *device;
 
 	result = usb_stor_probe1(&us, intf, id,
 			(id - cypress_usb_ids) + cypress_unusual_dev_list);
 	if (result)
 		return result;
 
-	us->protocol_name = "Transparent SCSI with Cypress ATACB";
-	us->proto_handler = cypress_atacb_passthrough;
+	/* Among CY7C68300 chips, the A revision does not support Cypress ATACB
+	 * Filter out this revision from EEPROM default descriptor values
+	 */
+	device = interface_to_usbdev(intf);
+	if (device->descriptor.iManufacturer != 0x38 ||
+	    device->descriptor.iProduct != 0x4e ||
+	    device->descriptor.iSerialNumber != 0x64) {
+		us->protocol_name = "Transparent SCSI with Cypress ATACB";
+		us->proto_handler = cypress_atacb_passthrough;
+	} else {
+		us->protocol_name = "Transparent SCSI";
+		us->proto_handler = usb_stor_transparent_scsi_command;
+	}
 
 	result = usb_stor_probe2(us);
 	return result;
-- 
1.8.1.2

[PATCH 100/118] USB: ftdi_sio: enable two UART ports on ST Microconnect Lite

[Luis Henriques]

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

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

From: Adrian Thomasset <adrian.thomasset@st.com>

commit 71d9a2b95fc9c9474d46d764336efd7a5a805555 upstream.

The FT4232H used in the ST Micro Connect Lite has four hi-speed UART ports.
The first two ports are reserved for the JTAG interface.

We enable by default ports 2 and 3 as UARTs (where port 2 is a
conventional RS-232 UART)

Signed-off-by: Adrian Thomasset <adrian.thomasset@st.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/serial/ftdi_sio.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ecfd525..d5b9a74 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1799,20 +1799,24 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial)
 }
 
 /*
- * First and second port on STMCLiteadaptors is reserved for JTAG interface
- * and the forth port for pio
+ * First two ports on JTAG adaptors using an FT4232 such as STMicroelectronics's
+ * ST Micro Connect Lite are reserved for JTAG or other non-UART interfaces and
+ * can be accessed from userspace.
+ * The next two ports are enabled as UARTs by default, where port 2 is
+ * a conventional RS-232 UART.
  */
 static int ftdi_stmclite_probe(struct usb_serial *serial)
 {
 	struct usb_device *udev = serial->dev;
 	struct usb_interface *interface = serial->interface;
 
-	if (interface == udev->actconfig->interface[2])
-		return 0;
-
-	dev_info(&udev->dev, "Ignoring serial port reserved for JTAG\n");
+	if (interface == udev->actconfig->interface[0] ||
+	    interface == udev->actconfig->interface[1]) {
+		dev_info(&udev->dev, "Ignoring serial port reserved for JTAG\n");
+		return -ENODEV;
+	}
 
-	return -ENODEV;
+	return 0;
 }
 
 /*
-- 
1.8.1.2

[PATCH 101/118] gianfar: do not advertise any alarm capability.

[Luis Henriques]

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

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

From: Richard Cochran <richardcochran@gmail.com>

commit cd4baaaa04b4aaa3b0ec4d13a6f3d203b92eadbd upstream.

An early draft of the PHC patch series included an alarm in the
gianfar driver. During the review process, the alarm code was dropped,
but the capability removal was overlooked. This patch fixes the issue
by advertising zero alarms.

This patch should be applied to every 3.x stable kernel.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Reported-by: Chris LaRocque <clarocq@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/freescale/gianfar_ptp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 0daa66b..d81c7af 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -127,7 +127,6 @@ struct gianfar_ptp_registers {
 
 #define DRIVER		"gianfar_ptp"
 #define DEFAULT_CKSEL	1
-#define N_ALARM		1 /* first alarm is used internally to reset fipers */
 #define N_EXT_TS	2
 #define REG_SIZE	sizeof(struct gianfar_ptp_registers)
 
@@ -410,7 +409,7 @@ static struct ptp_clock_info ptp_gianfar_caps = {
 	.owner		= THIS_MODULE,
 	.name		= "gianfar clock",
 	.max_adj	= 512000,
-	.n_alarm	= N_ALARM,
+	.n_alarm	= 0,
 	.n_ext_ts	= N_EXT_TS,
 	.n_per_out	= 0,
 	.pps		= 1,
-- 
1.8.1.2

[PATCH 102/118] clockevents: Set dummy handler on CPU_DEAD shutdown

[Luis Henriques]

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

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

From: Thomas Gleixner <tglx@linutronix.de>

commit 6f7a05d7018de222e40ca003721037a530979974 upstream.

Vitaliy reported that a per cpu HPET timer interrupt crashes the
system during hibernation. What happens is that the per cpu HPET timer
gets shut down when the nonboot cpus are stopped. When the nonboot
cpus are onlined again the HPET code sets up the MSI interrupt which
fires before the clock event device is registered. The event handler
is still set to hrtimer_interrupt, which then crashes the machine due
to highres mode not being active.

See http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=700333

There is no real good way to avoid that in the HPET code. The HPET
code alrady has a mechanism to detect spurious interrupts when event
handler == NULL for a similar reason.

We can handle that in the clockevent/tick layer and replace the
previous functional handler with a dummy handler like we do in
tick_setup_new_device().

The original clockevents code did this in clockevents_exchange_device(),
but that got removed by commit 7c1e76897 (clockevents: prevent
clockevent event_handler ending up handler_noop) which forgot to fix
it up in tick_shutdown(). Same issue with the broadcast device.

Reported-by: Vitaliy Fillipov <vitalif@yourcmc.ru>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: 700333@bugs.debian.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 kernel/time/tick-broadcast.c | 4 ++++
 kernel/time/tick-common.c    | 1 +
 2 files changed, 5 insertions(+)

diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index a13987a..239a323 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -66,6 +66,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
+	struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
 	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
 	    (tick_broadcast_device.evtdev &&
 	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
@@ -73,6 +75,8 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 		return 0;
 
 	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	if (cur)
+		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index da6c9ec..ead79bc 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -323,6 +323,7 @@ static void tick_shutdown(unsigned int *cpup)
 		 */
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
+		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-- 
1.8.1.2

[PATCH 103/118] ixgbe: fix EICR write in ixgbe_msix_other

[Luis Henriques]

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

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

From: Jacob Keller <jacob.e.keller@intel.com>

commit d87d830720a1446403ed38bfc2da268be0d356d1 upstream.

Previously, the ixgbe_msix_other was writing the full 32bits of the set
interrupts, instead of only the ones which the ixgbe_msix_other is
handling. This resulted in a loss of performance when the X540's PPS feature is
enabled due to sometimes clearing queue interrupts which resulted in the driver
not getting the interrupt for cleaning the q_vector rings often enough. The fix
is to simply mask the lower 16bits off so that this handler does not write them
in the EICR, which causes them to remain high and be properly handled by the
clean_rings interrupt routine as normal.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ab8d882..543659a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2293,6 +2293,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data)
 	 * with the write to EICR.
 	 */
 	eicr = IXGBE_READ_REG(hw, IXGBE_EICS);
+
+	/* The lower 16bits of the EICR register are for the queue interrupts
+	 * which should be masked here in order to not accidently clear them if
+	 * the bits are high when ixgbe_msix_other is called. There is a race
+	 * condition otherwise which results in possible performance loss
+	 * especially if the ixgbe_msix_other interrupt is triggering
+	 * consistently (as it would when PPS is turned on for the X540 device)
+	 */
+	eicr &= 0xFFFF0000;
+
 	IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr);
 
 	if (eicr & IXGBE_EICR_LSC)
-- 
1.8.1.2

[PATCH 104/118] mwifiex: Use pci_release_region() instead of a pci_release_regions()

[Luis Henriques]

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

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

From: Yogesh Ashok Powar <yogeshp@marvell.com>

commit c380aafb77b7435d010698fe3ca6d3e1cd745fde upstream.

PCI regions are associated with the device using
pci_request_region() call. Hence use pci_release_region()
instead of pci_release_regions().

Signed-off-by: Yogesh Ashok Powar <yogeshp@marvell.com>
Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Avinash Patil <patila@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/mwifiex/pcie.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 0bbea88..ce2c101 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1831,8 +1831,8 @@ static void mwifiex_pcie_cleanup(struct mwifiex_adapter *adapter)
 	if (pdev) {
 		pci_iounmap(pdev, card->pci_mmap);
 		pci_iounmap(pdev, card->pci_mmap1);
-
-		pci_release_regions(pdev);
+		pci_release_region(pdev, 2);
+		pci_release_region(pdev, 0);
 		pci_disable_device(pdev);
 		pci_set_drvdata(pdev, NULL);
 	}
-- 
1.8.1.2

[PATCH 105/118] mwifiex: Call pci_release_region after calling pci_disable_device

[Luis Henriques]

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

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

From: Yogesh Ashok Powar <yogeshp@marvell.com>

commit 5b0d9b218b74042ff72bf4bfda6eeb2e4bf98397 upstream.

"drivers should call pci_release_region() AFTER
calling pci_disable_device()"

Please refer section 3.2 Request MMIO/IOP resources
in Documentation/PCI/pci.txt

Signed-off-by: Avinash Patil <patila@marvell.com>
Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Yogesh Ashok Powar <yogeshp@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/net/wireless/mwifiex/pcie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index ce2c101..b7a5387 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1831,9 +1831,9 @@ static void mwifiex_pcie_cleanup(struct mwifiex_adapter *adapter)
 	if (pdev) {
 		pci_iounmap(pdev, card->pci_mmap);
 		pci_iounmap(pdev, card->pci_mmap1);
+		pci_disable_device(pdev);
 		pci_release_region(pdev, 2);
 		pci_release_region(pdev, 0);
-		pci_disable_device(pdev);
 		pci_set_drvdata(pdev, NULL);
 	}
 }
-- 
1.8.1.2

[PATCH 106/118] fs/fscache/stats.c: fix memory leak

[Luis Henriques]

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

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

From: Anurup m <anurup.m@huawei.com>

commit ec686c9239b4d472052a271c505d04dae84214cc upstream.

There is a kernel memory leak observed when the proc file
/proc/fs/fscache/stats is read.

The reason is that in fscache_stats_open, single_open is called and the
respective release function is not called during release.  Hence fix
with correct release function - single_release().

Addresses https://bugzilla.kernel.org/show_bug.cgi?id=57101

Signed-off-by: Anurup m <anurup.m@huawei.com>
Cc: shyju pv <shyju.pv@huawei.com>
Cc: Sanil kumar <sanil.kumar@huawei.com>
Cc: Nataraj m <nataraj.m@huawei.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/fscache/stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190..73c0bd7 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -276,5 +276,5 @@ const struct file_operations fscache_stats_fops = {
 	.open		= fscache_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release        = single_release,
 };
-- 
1.8.1.2

[PATCH 107/118] mm: allow arch code to control the user page table ceiling

[Luis Henriques]

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

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

From: Hugh Dickins <hughd@google.com>

commit 6ee8630e02be6dd89926ca0fbc21af68b23dc087 upstream.

On architectures where a pgd entry may be shared between user and kernel
(e.g.  ARM+LPAE), freeing page tables needs a ceiling other than 0.
This patch introduces a generic USER_PGTABLES_CEILING that arch code can
override.  It is the responsibility of the arch code setting the ceiling
to ensure the complete freeing of the page tables (usually in
pgd_free()).

[catalin.marinas@arm.com: commit log; shift_arg_pages(), asm-generic/pgtables.h changes]
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/exec.c                     |  4 ++--
 include/asm-generic/pgtable.h | 10 ++++++++++
 mm/mmap.c                     |  4 ++--
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 858423a..2013724 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -623,7 +623,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * when the old and new regions overlap clear from new_end.
 		 */
 		free_pgd_range(&tlb, new_end, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	} else {
 		/*
 		 * otherwise, clean from old_start; this is done to not touch
@@ -632,7 +632,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * for the others its just a little faster.
 		 */
 		free_pgd_range(&tlb, old_start, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
 	tlb_finish_mmu(&tlb, new_end, old_end);
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index ff4947b..0084135 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -7,6 +7,16 @@
 #include <linux/mm_types.h>
 #include <linux/bug.h>
 
+/*
+ * On almost all architectures and configurations, 0 can be used as the
+ * upper ceiling to free_pgtables(): on many architectures it has the same
+ * effect as using TASK_SIZE.  However, there is one configuration which
+ * must impose a more careful limit, to avoid freeing kernel pgtables.
+ */
+#ifndef USER_PGTABLES_CEILING
+#define USER_PGTABLES_CEILING	0UL
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
diff --git a/mm/mmap.c b/mm/mmap.c
index 5603d88..76b70c9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1913,7 +1913,7 @@ static void unmap_region(struct mm_struct *mm,
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
-				 next ? next->vm_start : 0);
+				 next ? next->vm_start : USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, start, end);
 }
 
@@ -2295,7 +2295,7 @@ void exit_mmap(struct mm_struct *mm)
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
 
-	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 
 	/*
-- 
1.8.1.2

[PATCH 108/118] arm: set the page table freeing ceiling to TASK_SIZE

[Luis Henriques]

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

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

From: Catalin Marinas <catalin.marinas@arm.com>

commit 104ad3b32d7a71941c8ab2dee78eea38e8a23309 upstream.

ARM processors with LPAE enabled use 3 levels of page tables, with an
entry in the top level (pgd) covering 1GB of virtual space.  Because of
the branch relocation limitations on ARM, the loadable modules are
mapped 16MB below PAGE_OFFSET, making the corresponding 1GB pgd shared
between kernel modules and user space.

If free_pgtables() is called with the default ceiling 0,
free_pgd_range() (and subsequently called functions) also frees the page
table shared between user space and kernel modules (which is normally
handled by the ARM-specific pgd_free() function).  This patch changes
defines the ARM USER_PGTABLES_CEILING to TASK_SIZE when CONFIG_ARM_LPAE
is enabled.

Note that the pgd_free() function already checks the presence of the
shared pmd page allocated by pgd_alloc() and frees it, though with
ceiling 0 this wasn't necessary.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/include/asm/pgtable.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 41dc31f..cc5e50f 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -61,6 +61,15 @@ extern void __pgd_error(const char *file, int line, pgd_t);
 #define FIRST_USER_ADDRESS	PAGE_SIZE
 
 /*
+ * Use TASK_SIZE as the ceiling argument for free_pgtables() and
+ * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd
+ * page shared between user and kernel).
+ */
+#ifdef CONFIG_ARM_LPAE
+#define USER_PGTABLES_CEILING	TASK_SIZE
+#endif
+
+/*
  * The pgprot_* and protection_map entries will be fixed up in runtime
  * to include the cachable and bufferable bits based on memory policy,
  * as well as any architecture dependent bits like global/ASID and SMP
-- 
1.8.1.2

[PATCH 109/118] drivers/rtc/rtc-cmos.c: don't disable hpet emulation on suspend

[Luis Henriques]

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

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

From: Derek Basehore <dbasehore@chromium.org>

commit e005715efaf674660ae59af83b13822567e3a758 upstream.

There's a bug where rtc alarms are ignored after the rtc cmos suspends
but before the system finishes suspend.  Since hpet emulation is
disabled and it still handles the interrupts, a wake event is never
registered which is done from the rtc layer.

This patch reverts commit d1b2efa83fbf ("rtc: disable hpet emulation on
suspend") which disabled hpet emulation.  To fix the problem mentioned
in that commit, hpet_rtc_timer_init() is called directly on resume.

Signed-off-by: Derek Basehore <dbasehore@chromium.org>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/rtc/rtc-cmos.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 4267789..6a4adf7 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -805,9 +805,8 @@ static int cmos_suspend(struct device *dev)
 			mask = RTC_IRQMASK;
 		tmp &= ~mask;
 		CMOS_WRITE(tmp, RTC_CONTROL);
+		hpet_mask_rtc_irq_bit(mask);
 
-		/* shut down hpet emulation - we don't need it for alarm */
-		hpet_mask_rtc_irq_bit(RTC_PIE|RTC_AIE|RTC_UIE);
 		cmos_checkintr(cmos, tmp);
 	}
 	spin_unlock_irq(&rtc_lock);
@@ -872,6 +871,7 @@ static int cmos_resume(struct device *dev)
 			rtc_update_irq(cmos->rtc, 1, mask);
 			tmp &= ~RTC_AIE;
 			hpet_mask_rtc_irq_bit(RTC_AIE);
+			hpet_rtc_timer_init();
 		} while (mask & RTC_AIE);
 		spin_unlock_irq(&rtc_lock);
 	}
-- 
1.8.1.2

[PATCH 110/118] drivers/rtc/rtc-at91rm9200.c: fix missing iounmap

[Luis Henriques]

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

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

From: Johan Hovold <jhovold@gmail.com>

commit 3427de92ac70a064098ff843c72ac76c420bb1cb upstream.

Add missing iounmap to probe error path and remove.

Signed-off-by: Johan Hovold <jhovold@gmail.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/rtc/rtc-at91rm9200.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index dc474bc..9f2762c 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -297,7 +297,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	if (ret) {
 		printk(KERN_ERR "at91_rtc: IRQ %d already in use.\n",
 				irq);
-		return ret;
+		goto err_unmap;
 	}
 
 	/* cpu init code should really have flagged this device as
@@ -309,13 +309,20 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	rtc = rtc_device_register(pdev->name, &pdev->dev,
 				&at91_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc)) {
-		free_irq(irq, pdev);
-		return PTR_ERR(rtc);
+		ret = PTR_ERR(rtc);
+		goto err_free_irq;
 	}
 	platform_set_drvdata(pdev, rtc);
 
 	printk(KERN_INFO "AT91 Real Time Clock driver.\n");
 	return 0;
+
+err_free_irq:
+	free_irq(irq, pdev);
+err_unmap:
+	iounmap(at91_rtc_regs);
+
+	return ret;
 }
 
 /*
@@ -332,6 +339,7 @@ static int __exit at91_rtc_remove(struct platform_device *pdev)
 	free_irq(irq, pdev);
 
 	rtc_device_unregister(rtc);
+	iounmap(at91_rtc_regs);
 	platform_set_drvdata(pdev, NULL);
 
 	return 0;
-- 
1.8.1.2

[PATCH 111/118] md: bad block list should default to disabled.

[Luis Henriques]

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

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

From: NeilBrown <neilb@suse.de>

commit 486adf72ccc0c235754923d47a2270c5dcb0c98b upstream.

Maintenance of a bad-block-list currently defaults to 'enabled'
and is then disabled when it cannot be supported.
This is backwards and causes problem for dm-raid which didn't know
to disable it.

So fix the defaults, and only enabled for v1.x metadata which
explicitly has bad blocks enabled.

The problem with dm-raid has been present since badblock support was
added in v3.1, so this patch is suitable for any -stable from 3.1
onwards.

Reported-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/md/md.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8a6f63c..cc4d68d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1629,8 +1629,8 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 					     sector, count, 1) == 0)
 				return -EINVAL;
 		}
-	} else if (sb->bblog_offset == 0)
-		rdev->badblocks.shift = -1;
+	} else if (sb->bblog_offset != 0)
+		rdev->badblocks.shift = 0;
 
 	if (!refdev) {
 		ret = 1;
@@ -3280,7 +3280,7 @@ int md_rdev_init(struct md_rdev *rdev)
 	 * be used - I wonder if that matters
 	 */
 	rdev->badblocks.count = 0;
-	rdev->badblocks.shift = 0;
+	rdev->badblocks.shift = -1; /* disabled until explicitly enabled */
 	rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	seqlock_init(&rdev->badblocks.lock);
 	if (rdev->badblocks.page == NULL)
@@ -3352,9 +3352,6 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 			goto abort_free;
 		}
 	}
-	if (super_format == -1)
-		/* hot-add for 0.90, or non-persistent: so no badblocks */
-		rdev->badblocks.shift = -1;
 
 	return rdev;
 
-- 
1.8.1.2

[PATCH 112/118] inotify: invalid mask should return a error number but not set it

[Luis Henriques]

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

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

From: Zhao Hongjiang <zhaohongjiang@huawei.com>

commit 04df32fa10ab9a6f0643db2949d42efc966bc844 upstream.

When we run the crackerjack testsuite, the inotify_add_watch test is
stalled.

This is caused by the invalid mask 0 - the task is waiting for the event
but it never comes.  inotify_add_watch() should return -EINVAL as it did
before commit 676a0675cf92 ("inotify: remove broken mask checks causing
unmount to be EINVAL").  That commit removes the invalid mask check, but
that check is needed.

Check the mask's ALL_INOTIFY_BITS before the inotify_arg_to_mask() call.
If none are set, just return -EINVAL.

Because IN_UNMOUNT is in ALL_INOTIFY_BITS, this change will not trigger
the problem that above commit fixed.

[akpm@linux-foundation.org: fix build]
Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com>
Acked-by: Jim Somerville <Jim.Somerville@windriver.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Eric Paris <eparis@parisplace.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/notify/inotify/inotify_user.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 6f292dd..f255d37 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -577,7 +577,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	int add = (arg & IN_MASK_ADD);
 	int ret;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
@@ -628,7 +627,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
@@ -757,6 +755,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	int ret, fput_needed;
 	unsigned flags = 0;
 
+	/* don't allow invalid bits: we don't want flags set */
+	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
+		return -EINVAL;
+
 	filp = fget_light(fd, &fput_needed);
 	if (unlikely(!filp))
 		return -EBADF;
-- 
1.8.1.2

[PATCH 113/118] fs/dcache.c: add cond_resched() to shrink_dcache_parent()

[Luis Henriques]

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

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

From: Greg Thelen <gthelen@google.com>

commit 421348f1ca0bf17769dee0aed4d991845ae0536d upstream.

Call cond_resched() in shrink_dcache_parent() to maintain interactivity.

Before this patch:

	void shrink_dcache_parent(struct dentry * parent)
	{
		while ((found = select_parent(parent, &dispose)) != 0)
			shrink_dentry_list(&dispose);
	}

select_parent() populates the dispose list with dentries which
shrink_dentry_list() then deletes.  select_parent() carefully uses
need_resched() to avoid doing too much work at once.  But neither
shrink_dcache_parent() nor its called functions call cond_resched().  So
once need_resched() is set select_parent() will return single dentry
dispose list which is then deleted by shrink_dentry_list().  This is
inefficient when there are a lot of dentry to process.  This can cause
softlockup and hurts interactivity on non preemptable kernels.

This change adds cond_resched() in shrink_dcache_parent().  The benefit
of this is that need_resched() is quickly cleared so that future calls
to select_parent() are able to efficiently return a big batch of dentry.

These additional cond_resched() do not seem to impact performance, at
least for the workload below.

Here is a program which can cause soft lockup if other system activity
sets need_resched().

	int main()
	{
	        struct rlimit rlim;
	        int i;
	        int f[100000];
	        char buf[20];
	        struct timeval t1, t2;
	        double diff;

	        /* cleanup past run */
	        system("rm -rf x");

	        /* boost nfile rlimit */
	        rlim.rlim_cur = 200000;
	        rlim.rlim_max = 200000;
	        if (setrlimit(RLIMIT_NOFILE, &rlim))
	                err(1, "setrlimit");

	        /* make directory for files */
	        if (mkdir("x", 0700))
	                err(1, "mkdir");

	        if (gettimeofday(&t1, NULL))
	                err(1, "gettimeofday");

	        /* populate directory with open files */
	        for (i = 0; i < 100000; i++) {
	                snprintf(buf, sizeof(buf), "x/%d", i);
	                f[i] = open(buf, O_CREAT);
	                if (f[i] == -1)
	                        err(1, "open");
	        }

	        /* close some of the files */
	        for (i = 0; i < 85000; i++)
	                close(f[i]);

	        /* unlink all files, even open ones */
	        system("rm -rf x");

	        if (gettimeofday(&t2, NULL))
	                err(1, "gettimeofday");

	        diff = (((double)t2.tv_sec * 1000000 + t2.tv_usec) -
	                ((double)t1.tv_sec * 1000000 + t1.tv_usec));

	        printf("done: %g elapsed\n", diff/1e6);
	        return 0;
	}

Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/dcache.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 458ec45..9b36632 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1254,8 +1254,10 @@ void shrink_dcache_parent(struct dentry * parent)
 	LIST_HEAD(dispose);
 	int found;
 
-	while ((found = select_parent(parent, &dispose)) != 0)
+	while ((found = select_parent(parent, &dispose)) != 0) {
 		shrink_dentry_list(&dispose);
+		cond_resched();
+	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 
-- 
1.8.1.2

[PATCH 114/118] exec: do not abuse ->cred_guard_mutex in threadgroup_lock()

[Luis Henriques]

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

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

From: Oleg Nesterov <oleg@redhat.com>

commit e56fb2874015370e3b7f8d85051f6dce26051df9 upstream.

threadgroup_lock() takes signal->cred_guard_mutex to ensure that
thread_group_leader() is stable.  This doesn't look nice, the scope of
this lock in do_execve() is huge.

And as Dave pointed out this can lead to deadlock, we have the
following dependencies:

	do_execve:		cred_guard_mutex -> i_mutex
	cgroup_mount:		i_mutex -> cgroup_mutex
	attach_task_by_pid:	cgroup_mutex -> cred_guard_mutex

Change de_thread() to take threadgroup_change_begin() around the
switch-the-leader code and change threadgroup_lock() to avoid
->cred_guard_mutex.

Note that de_thread() can't sleep with ->group_rwsem held, this can
obviously deadlock with the exiting leader if the writer is active, so it
does threadgroup_change_end() before schedule().

Reported-by: Dave Jones <davej@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ luis: adjust context ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 fs/exec.c             |  3 +++
 include/linux/sched.h | 18 ++++--------------
 2 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 2013724..5a76464 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -905,11 +905,13 @@ static int de_thread(struct task_struct *tsk)
 
 		sig->notify_count = -1;	/* for exit_notify() */
 		for (;;) {
+			threadgroup_change_begin(tsk);
 			write_lock_irq(&tasklist_lock);
 			if (likely(leader->exit_state))
 				break;
 			__set_current_state(TASK_UNINTERRUPTIBLE);
 			write_unlock_irq(&tasklist_lock);
+			threadgroup_change_end(tsk);
 			schedule();
 		}
 
@@ -965,6 +967,7 @@ static int de_thread(struct task_struct *tsk)
 		if (unlikely(leader->ptrace))
 			__wake_up_parent(leader, leader->parent);
 		write_unlock_irq(&tasklist_lock);
+		threadgroup_change_end(tsk);
 
 		release_task(leader);
 	}
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3a9e314..ebd15f9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2445,27 +2445,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk)
  *
  * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
  * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * perform exec.  This is useful for cases where the threadgroup needs to
- * stay stable across blockable operations.
+ * change ->group_leader/pid.  This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
  *
  * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
  * synchronization.  While held, no new task will be added to threadgroup
  * and no existing live task will have its PF_EXITING set.
  *
- * During exec, a task goes and puts its thread group through unusual
- * changes.  After de-threading, exclusive access is assumed to resources
- * which are usually shared by tasks in the same group - e.g. sighand may
- * be replaced with a new one.  Also, the exec'ing task takes over group
- * leader role including its pid.  Exclude these changes while locked by
- * grabbing cred_guard_mutex which is used to synchronize exec path.
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
  */
 static inline void threadgroup_lock(struct task_struct *tsk)
 {
-	/*
-	 * exec uses exit for de-threading nesting group_rwsem inside
-	 * cred_guard_mutex. Grab cred_guard_mutex first.
-	 */
-	mutex_lock(&tsk->signal->cred_guard_mutex);
 	down_write(&tsk->signal->group_rwsem);
 }
 
@@ -2478,7 +2469,6 @@ static inline void threadgroup_lock(struct task_struct *tsk)
 static inline void threadgroup_unlock(struct task_struct *tsk)
 {
 	up_write(&tsk->signal->group_rwsem);
-	mutex_unlock(&tsk->signal->cred_guard_mutex);
 }
 #else
 static inline void threadgroup_change_begin(struct task_struct *tsk) {}
-- 
1.8.1.2

[PATCH 115/118] tty: fix up atime/mtime mess, take three

[Luis Henriques]

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

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

From: Linus Torvalds <torvalds@linux-foundation.org>

commit b0b885657b6c8ef63a46bc9299b2a7715d19acde upstream.

We first tried to avoid updating atime/mtime entirely (commit
b0de59b5733d: "TTY: do not update atime/mtime on read/write"), and then
limited it to only update it occasionally (commit 37b7f3c76595: "TTY:
fix atime/mtime regression"), but it turns out that this was both
insufficient and overkill.

It was insufficient because we let people attach to the shared ptmx node
to see activity without even reading atime/mtime, and it was overkill
because the "only once a minute" means that you can't really tell an
idle person from an active one with 'w'.

So this tries to fix the problem properly.  It marks the shared ptmx
node as un-notifiable, and it lowers the "only once a minute" to a few
seconds instead - still long enough that you can't time individual
keystrokes, but short enough that you can tell whether somebody is
active or not.

Reported-by: Simon Kirby <sim@hostway.ca>
Acked-by: Jiri Slaby <jslaby@suse.cz>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/tty/pty.c    | 3 +++
 drivers/tty/tty_io.c | 4 ++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index ce53594..33b1526 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -616,6 +616,9 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	nonseekable_open(inode, filp);
 
+	/* We refuse fsnotify events on ptmx, since it's a shared resource */
+	filp->f_mode |= FMODE_NONOTIFY;
+
 	retval = tty_alloc_file(filp);
 	if (retval)
 		return retval;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 95a37fa..67ea9cf 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -939,10 +939,10 @@ void start_tty(struct tty_struct *tty)
 
 EXPORT_SYMBOL(start_tty);
 
+/* We limit tty time update visibility to every 8 seconds or so. */
 static void tty_update_time(struct timespec *time)
 {
-	unsigned long sec = get_seconds();
-	sec -= sec % 60;
+	unsigned long sec = get_seconds() & ~7;
 	if ((long)(sec - time->tv_sec) > 0)
 		time->tv_sec = sec;
 }
-- 
1.8.1.2

[PATCH 116/118] ipc: sysv shared memory limited to 8TiB

[Luis Henriques]

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

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

From: Robin Holt <holt@sgi.com>

commit d69f3bad4675ac519d41ca2b11e1c00ca115cecd upstream.

Trying to run an application which was trying to put data into half of
memory using shmget(), we found that having a shmall value below 8EiB-8TiB
would prevent us from using anything more than 8TiB.  By setting
kernel.shmall greater than 8EiB-8TiB would make the job work.

In the newseg() function, ns->shm_tot which, at 8TiB is INT_MAX.

ipc/shm.c:
 458 static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 459 {
...
 465         int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT;
...
 474         if (ns->shm_tot + numpages > ns->shm_ctlall)
 475                 return -ENOSPC;

[akpm@linux-foundation.org: make ipc/shm.c:newseg()'s numpages size_t, not int]
Signed-off-by: Robin Holt <holt@sgi.com>
Reported-by: Alex Thorlton <athorlton@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 include/linux/ipc_namespace.h | 2 +-
 ipc/shm.c                     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 5499c92..c731973 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -42,8 +42,8 @@ struct ipc_namespace {
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
+	unsigned long	shm_tot;
 	int		shm_ctlmni;
-	int		shm_tot;
 	/*
 	 * Defines whether IPC_RMID is forced for _all_ shm segments regardless
 	 * of shmctl()
diff --git a/ipc/shm.c b/ipc/shm.c
index 41c1285..f5ba6ac 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -462,7 +462,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	size_t size = params->u.size;
 	int error;
 	struct shmid_kernel *shp;
-	int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT;
+	size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	struct file * file;
 	char name[13];
 	int id;
-- 
1.8.1.2

[PATCH 117/118] Revert "drm/i915: GFX_MODE Flush TLB Invalidate Mode must be '1' for scanline waits"

[Luis Henriques]

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

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

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

This reverts commit 899b5509abbdfee2eab408e7178e559346091ad3, which is commit
f05bb0c7b624252a5e768287e340e8e45df96e42 in Linus' tree.

This commit has been shown to cause GPU hangs on Sandy Bridge GPUs

BugLink: http://bugs.launchpad.net/bugs/1140716

Signed-off-by: Steve Conklin <sconklin@canonical.com>
Acked-by: Brad Figg <brad.figg@canonical.com>
Acked-by: Luis Henriques <luis.henriques@canonical.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e75d794..78486c7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -421,11 +421,6 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
-	/* Required for the hardware to program scanline values for waiting */
-	if (INTEL_INFO(dev)->gen == 6)
-		I915_WRITE(GFX_MODE,
-			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_ALWAYS));
-
 	if (IS_GEN7(dev))
 		I915_WRITE(GFX_MODE_GEN7,
 			   _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
-- 
1.8.1.2

[PATCH 118/118] ARM: 7699/1: sched_clock: Add more notrace to prevent recursion

[Luis Henriques]

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

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

From: Stephen Boyd <sboyd@codeaurora.org>

commit cea15092f098b7018e89f64a5a14bb71955965d5 upstream.

cyc_to_sched_clock() is called by sched_clock() and cyc_to_ns()
is called by cyc_to_sched_clock(). I suspect that some compilers
inline both of these functions into sched_clock() and so we've
been getting away without having a notrace marking. It seems that
my compiler isn't inlining cyc_to_sched_clock() though, so I'm
hitting a recursion bug when I enable the function graph tracer,
causing my system to crash. Marking these functions notrace fixes
it. Technically cyc_to_ns() doesn't need the notrace because it's
already marked inline, but let's just add it so that if we ever
remove inline from that function it doesn't blow up.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Jonghwan Choi <jhbird.choi@samsung.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 arch/arm/kernel/sched_clock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 6bbf936..926c98f 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -39,12 +39,12 @@ static u32 notrace jiffy_sched_clock_read(void)
 
 static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;
-- 
1.8.1.2