By definition of (the algorithm of) QFQ+, the system virtual time must
be pushed up only if there is no 'eligible' aggregate, i.e. no
aggregate that would have started to be served also in the ideal
system emulated by QFQ+.  QFQ+ serves only eligible aggregates, hence
the aggregate currently in service is eligible.  As a consequence, to
decide whether there is no eligible aggregate, QFQ+ must also check
whether there is no aggregate in service.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Reviewed-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Aggregate budgets are computed so as to guarantee that, after an
aggregate has been selected for service, that aggregate has enough
budget to serve at least one maximum-size packet for the classes it
contains. For this reason, after a new aggregate has been selected
for service, its next packet is immediately dequeued, without any
further control.

The maximum packet size for a class, lmax, can be changed through
qfq_change_class(). In case the user sets lmax to a lower value than
the the size of some of the still-to-arrive packets, QFQ+ will
automatically push up lmax as it enqueues these packets.  This
automatic push up is likely to happen with TSO/GSO.

In any case, if lmax is assigned a lower value than the size of some
of the packets already enqueued for the class, then the following
problem may occur: the size of the next packet to dequeue for the
class may happen to be larger than lmax, after the aggregate to which
the class belongs has been just selected for service. In this case,
even the budget of the aggregate, which is an unsigned value, may be
lower than the size of the next packet to dequeue. After dequeueing
this packet and subtracting its size from the budget, the latter would
wrap around.

This fix prevents the budget from wrapping around after any packet
dequeue.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Reviewed-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If no aggregate is in service, then the function qfq_dequeue() does
not dequeue any packet. For this reason, to guarantee QFQ+ to be work
conserving, a just-activated aggregate must be set as in service
immediately if it happens to be the only active aggregate.
This is done by the function qfq_enqueue().

Unfortunately, the function qfq_add_to_agg(), used to add a class to
an aggregate, does not perform this important additional operation.
In particular, if: 1) qfq_add_to_agg() is invoked to complete the move
of a class from a source aggregate, becoming, for this move, inactive,
to a destination aggregate, becoming instead active, and 2) the
destination aggregate becomes the only active aggregate, then this
aggregate is not however set as in service. QFQ+ remains then in a
non-work-conserving state until a new invocation of qfq_enqueue()
recovers the situation.

This fix solves the problem by moving the logic for setting an
aggregate as in service directly into the function qfq_activate_agg().
Hence, from whatever point qfq_activate_aggregate() is invoked, QFQ+
remains work conserving.  Since the more-complex logic of this new
version of activate_aggregate() is not necessary, in qfq_dequeue(), to
reschedule an aggregate that finishes its budget, then the aggregate
is now rescheduled by invoking directly the functions needed.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Reviewed-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Between two invocations of make_eligible, the system virtual time may
happen to grow enough that, in its binary representation, a bit with
higher order than 31 flips. This happens especially with
TSO/GSO. Before this fix, the mask used in make_eligible was computed
as (1UL<<index_of_last_flipped_bit)-1, whose value is well defined on
a 64-bit architecture, because index_of_flipped_bit <= 63, but is in
general undefined on a 32-bit architecture if index_of_flipped_bit > 31.
The fix just replaces 1UL with 1ULL.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Reviewed-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

QFQ+ schedules the active aggregates in a group using a bucket list
(one list per group). The bucket in which each aggregate is inserted
depends on the aggregate's timestamps, and the number
of buckets in a group is enough to accomodate the possible (range of)
values of the timestamps of all the aggregates in the group. For this
property to hold, timestamps must however be computed correctly.  One
necessary condition for computing timestamps correctly is that the
number of bits dequeued for each aggregate, while the aggregate is in
service, does not exceed the maximum budget budgetmax assigned to the
aggregate.

For each aggregate, budgetmax is proportional to the number of classes
in the aggregate. If the number of classes of the aggregate is
decreased through qfq_change_class(), then budgetmax is decreased
automatically as well.  Problems may occur if the aggregate is in
service when budgetmax is decreased, because the current remaining
budget of the aggregate and/or the service already received by the
aggregate may happen to be larger than the new value of budgetmax.  In
this case, when the aggregate is eventually deselected and its
timestamps are updated, the aggregate may happen to have received an
amount of service larger than budgetmax.  This may cause the aggregate
to be assigned a higher virtual finish time than the maximum
acceptable value for the last bucket in the bucket list of the group.

This fix introduces a cap that addresses this issue.
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Reviewed-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

DTR/RTS need to be raised, regardless of the open() mode, but not
if the port has already shutdown.
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Without a memory and compiler barrier, the task state change
can migrate relative to the condition testing in a blocking loop.
However, the task state change must be visible across all cpus
prior to testing those conditions. Failing to do this can result
in the familiar 'lost wakeup' and this task will hang until killed.
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Although tty_lock() already protects concurrent update to
blocked_open, that fails to meet the separation-of-concerns between
tty_port and tty.
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Saving the port count bump is unsafe. If the tty is hung up while
this open was blocking, the port count is zeroed.

Explicitly check if the tty was hung up while blocking, and correct
the port count if not.
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jeff Kirsher says:

===================
This series contains fixes to e1000e and igb.

The e1000e fix resolves an issue at 1000Mbps link speed, where one of the
MAC's internal clocks can be stopped for up to 4us when entering K1 (a
power mode of the MAC-PHY interconnect).  If the MAC is waiting for
completion indications for 2 DMA write requests into Host memory
(e.g. descriptor writeback or Rx packet writing) and the
indications occur while the clock is stopped, both indications will be
missed by the MAC causing the MAC to wait for the completion indications
and be unable to generate further DMA write requests.  This results in an
apparent hardware hang.  The patch works-around the issue by disabling
the de-assertion of the clock request when 1000Mbps link is acquired (K1
must be disabled while doing this).

The igb fix to drop BUILD_BUG_ON check from igb_build_rx_buffer resolves
a build error on s390 devices.  The igb driver was throwing a build error
due to the fact that a frame built using build_skb would be larger than 2K.
Since this is not likely to change at any point in the future we are better
off just dropping the check since we already had a check in
igb_set_rx_buffer_len that will just disable the usage of build_skb anyway.

The igb fix for i210 link setup changes the setup copper link function
to use a switch statement, so that the appropriate setup link function
is called for the given PHY types.

Lastly, the igb fix for a lockdep issue in igb_get_i2c_client resolves
the issue by re-factoring the initialization and usage of the i2c_client.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull powerpc fixes from Ben Herrenschmidt:
 "Here are a few powerpc bits & fixes for rc1.  A couple of str*cpy
  fixes, some fixes in handling the FSCR register on Power8 (controls
  the enabling of processor features), a 32-bit build fix and a couple
  more nits."

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: Set DSCR bit in FSCR setup
  powerpc: Add DSCR FSCR register bit definition
  powerpc: Fix setting FSCR for HV=0 and on secondary CPUs
  powerpc: Wireup the kcmp syscall to sys_ni
  powerpc: Remove unused BITOP_LE_SWIZZLE macro
  powerpc: Avoid link stack corruption in MMU on syscall entry path
  drivers/tty/hvc: Use strlcpy instead of strncpy
  powerpc/pseries/hvcserver: Fix strncpy buffer limit in location code
  powerpc: Fix compile of sha1-powerpc-asm.S on 32-bit

Pull virtio hwrng fix from Rusty Russell:
 "Nasty side-effect of vmalloc'ing modules: their static vars cannot be
  put into scatterlists.  Jens has a check queued for this, so it
  shouldn't happen again.

  We could fix this in virtio_rng, but it's actually far easier to just
  do it in the core"

* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux:
  hw_random: make buffer usable in scatterlist.

Pull networking fixes from David Miller:
 "A moderately sized pile of fixes, some specifically for merge window
  introduced regressions although others are for longer standing items
  and have been queued up for -stable.

  I'm kind of tired of all the RDS protocol bugs over the years, to be
  honest, it's way out of proportion to the number of people who
  actually use it.

   1) Fix missing range initialization in netfilter IPSET, from Jozsef
      Kadlecsik.

   2) ieee80211_local->tim_lock needs to use BH disabling, from Johannes
      Berg.

   3) Fix DMA syncing in SFC driver, from Ben Hutchings.

   4) Fix regression in BOND device MAC address setting, from Jiri
      Pirko.

   5) Missing usb_free_urb in ISDN Hisax driver, from Marina Makienko.

   6) Fix UDP checksumming in bnx2x driver for 57710 and 57711 chips,
      fix from Dmitry Kravkov.

   7) Missing cfgspace_lock initialization in BCMA driver.

   8) Validate parameter size for SCTP assoc stats getsockopt(), from
      Guenter Roeck.

   9) Fix SCTP association hangs, from Lee A Roberts.

  10) Fix jumbo frame handling in r8169, from Francois Romieu.

  11) Fix phy_device memory leak, from Petr Malat.

  12) Omit trailing FCS from frames received in BGMAC driver, from Hauke
      Mehrtens.

  13) Missing socket refcount release in L2TP, from Guillaume Nault.

  14) sctp_endpoint_init should respect passed in gfp_t, rather than use
      GFP_KERNEL unconditionally.  From Dan Carpenter.

  15) Add AISX AX88179 USB driver, from Freddy Xin.

  16) Remove MAINTAINERS entries for drivers deleted during the merge
      window, from Cesar Eduardo Barros.

  17) RDS protocol can try to allocate huge amounts of memory, check
      that the user's request length makes sense, from Cong Wang.

  18) SCTP should use the provided KMALLOC_MAX_SIZE instead of it's own,
      bogus, definition.  From Cong Wang.

  19) Fix deadlocks in FEC driver by moving TX reclaim into NAPI poll,
      from Frank Li.  Also, fix a build error introduced in the merge
      window.

  20) Fix bogus purging of default routes in ipv6, from Lorenzo Colitti.

  21) Don't double count RTT measurements when we leave the TCP receive
      fast path, from Neal Cardwell."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
  tcp: fix double-counted receiver RTT when leaving receiver fast path
  CAIF: fix sparse warning for caif_usb
  rds: simplify a warning message
  net: fec: fix build error in no MXC platform
  net: ipv6: Don't purge default router if accept_ra=2
  net: fec: put tx to napi poll function to fix dead lock
  sctp: use KMALLOC_MAX_SIZE instead of its own MAX_KMALLOC_SIZE
  rds: limit the size allocated by rds_message_alloc()
  MAINTAINERS: remove eexpress
  MAINTAINERS: remove drivers/net/wan/cycx*
  MAINTAINERS: remove 3c505
  caif_dev: fix sparse warnings for caif_flow_cb
  ax88179_178a: ASIX AX88179_178A USB 3.0/2.0 to gigabit ethernet adapter driver
  sctp: use the passed in gfp flags instead GFP_KERNEL
  ipv[4|6]: correct dropwatch false positive in local_deliver_finish
  l2tp: Restore socket refcount when sendmsg succeeds
  net/phy: micrel: Disable asymmetric pause for KSZ9021
  bgmac: omit the fcs
  phy: Fix phy_device_free memory leak
  bnx2x: Fix KR2 work-around condition
  ...

Pull irq fixes and cleanups from Thomas Gleixner:
 "Commit e5ab012c ("nohz: Make tick_nohz_irq_exit() irq safe") is
  the first commit in the series and the minimal necessary bugfix, which
  needs to go back into stable.

  The remanining commits enforce irq disabling in irq_exit(), sanitize
  the hardirq/softirq preempt count transition and remove a bunch of no
  longer necessary conditionals."

I personally love getting rid of the very subtle and confusing
IRQ_EXIT_OFFSET thing.  Even apart from the whole "more lines removed
than added" thing.

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irq: Don't re-enable interrupts at the end of irq_exit
  irq: Remove IRQ_EXIT_OFFSET workaround
  Revert "nohz: Make tick_nohz_irq_exit() irq safe"
  irq: Sanitize invoke_softirq
  irq: Ensure irq_exit() code runs with interrupts disabled
  nohz: Make tick_nohz_irq_exit() irq safe

Pull smpboot bugfix from Thomas Gleixner:
 "A single bugfix for a regression introduced with the conversion of the
  stop machine threads to the generic smpboot thread management
  facility"

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  stop_machine: Mark per cpu stopper enabled early

Pull second round of GPIO changes from Grant Likely:
 "This branch contains a few bug fixes that I missed the first time
  around and updates to the gpio_desc series included in the first pull
  request.  This tag has been retagged to drop the 2 head commits
  because the one of them caused a build failure."

* tag 'gpio-for-linus' of git://git.secretlab.ca/git/linux:
  gpio/gpio-ich: fix ichx_gpio_check_available() return what callers expect
  gpiolib: move comment to right function
  gpiolib: use const parameters when possible
  gpiolib: check descriptors validity before use

Pull md updates from NeilBrown:
 "Mostly little bugfixes.

  Only "feature" is a new RAID10 layout which slightly improves the
  number of sets of devices that can concurrently fail, without data
  loss."

* tag 'md-3.9' of git://neil.brown.name/md:
  md: expedite metadata update when switching  read-auto -> active
  md: remove CONFIG_MULTICORE_RAID456
  md/raid1,raid10: fix deadlock with freeze_array()
  md/raid0: improve error message when converting RAID4-with-spares to RAID0
  md: raid0: fix error return from create_stripe_zones.
  md: fix two bugs when attempting to resize RAID0 array.
  DM RAID: Add support for MD's RAID10 "far" and "offset" algorithms
  MD RAID10: Improve redundancy for 'far' and 'offset' algorithms (part 2)
  MD RAID10: Improve redundancy for 'far' and 'offset' algorithms (part 1)
  MD RAID10: Minor non-functional code changes
  md: raid1,10: Handle REQ_WRITE_SAME flag in write bios
  md: protect against crash upon fsync on ro array

This patch fixes a lockdep warning in igb_get_i2c_client by
refactoring the initialization and usage of the i2c_client
completely.  There is no on the fly allocation of the single
client needed today.
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch changes the setup copper link function to use a switch
statement for the PHY id's available for the given PHY types.  It
also adds a case for the I210 PHY id, so the appropriate setup link
function is called for it.
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

On s390 the igb driver was throwing a build error due to the fact that a frame
built using build_skb would be larger than 2K.  Since this is not likely to
change at any point in the future we are better off just dropping the check
since we already had a check in igb_set_rx_buffer_len that will just disable
the usage of build_skb anyway.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

At 1000Mbps link speed, one of the MAC's internal clocks can be stopped for
up to 4us when entering K1 (a power mode of the MAC-PHY interconnect).  If
the MAC is waiting for completion indications for 2 DMA write requests into
Host memory (e.g. descriptor writeback or Rx packet writing) and the
indications occur while the clock is stopped, both indications will be
missed by the MAC causing the MAC to wait for the completion indications
and be unable to generate further DMA write requests.  This results in an
apparent hardware hang.

Work-around the issue by disabling the de-assertion of the clock request
when 1000Mbps link is acquired (K1 must be disabled while doing this).
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

We support DSCR (Data Stream Control Register) so we should make sure we set it
in the FSCR (Facility Status & Control Register) incase some firmwares don't
set it.  If we don't set this, we'll take a facility unavailable exception when
using the DSCR.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

This sets the DSCR (Data Stream Control Register) in the FSCR (Facility Status
& Control Register).

Also harmonise TAR (Target Address Register) FSCR bit definition too.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Currently we only set the FSCR (Facility Status and Control Register) when HV=1
but this feature is available when HV=0 also.  This patch sets FSCR when HV=0.

Also, we currently only set the FSCR on the master CPU.  This patch also sets
the FSCR on secondary CPUs.
Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Since kmp takes 2 unsigned long args there should be a compat wrapper.
Since one isn't provided I think it's safer just to hook this up to not
implemented.  If we need it later we can do it properly then.
Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

The BITOP_LE_SWIZZLE macro was used in the little-endian bitops functions
for powerpc.  But these functions were converted to generic bitops and
the BITOP_LE_SWIZZLE is not used anymore.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Currently we use the link register to branch up high in the early MMU on
syscall entry path.  Unfortunately, this trashes the link stack as the
address we are going to is not associated with the earlier mflr.

This patch simply converts us to used the count register (volatile over
syscalls anyway) instead.  This is much better at predicting in this
scenario and doesn't trash link stack causing a bunch of additional
branch mispredicts later.  Benchmarking this on POWER8 saves a bunch of
cycles on Anton's null syscall benchmark here:
   http://ozlabs.org/~anton/junkcode/null_syscall.cSigned-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

when strlen pi->location_code is larger than HVCS_CLC_LENGTH + 1,
    original implementation can not let hvcsd->p_location_code NUL terminated.
  so need fix it (also can simplify the code)
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

the dest buf len is 80 (HVCS_CLC_LENGTH + 1).
  the src buf len is PAGE_SIZE.
  if src buf string len is more than 80, it will cause issue.
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

When building with CRYPTO_SHA1_PPC enabled we fail with:

powerpc/crypto/sha1-powerpc-asm.S: Assembler messages:
powerpc/crypto/sha1-powerpc-asm.S:116: Error: can't resolve `0' {*ABS* section} - `STACKFRAMESIZE' {*UND* section}
powerpc/crypto/sha1-powerpc-asm.S:116: Error: expression too complex
powerpc/crypto/sha1-powerpc-asm.S:178: Error: unsupported relocation against STACKFRAMESIZE

Use INT_FRAME_SIZE instead of STACKFRAMESIZE.
Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
Tested-by: Christian Kujau <lists@nerdbynature.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

virtio_rng feeds the randomness buffer handed by the core directly
into the scatterlist, since commit bb347d98.

However, if CONFIG_HW_RANDOM=m, the static buffer isn't a linear address
(at least on most archs).  We could fix this in virtio_rng, but it's actually
far easier to just do it in the core as virtio_rng would have to allocate
a buffer every time (it doesn't know how much the core will want to read).
Reported-by: Aurelien Jarno <aurelien@aurel32.net>
Tested-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: stable@kernel.org

We should not update ts_recent and call tcp_rcv_rtt_measure_ts() both
before and after going to step5. That wastes CPU and double-counts the
receiver-side RTT sample.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This fixes the following sparse warning:
net/caif/caif_usb.c:84:16: warning: symbol 'cfusbl_create' was not
declared. Should it be static?
Signed-off-by: Silviu-Mihai Popescu <silviupopescu1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Cc: David S. Miller <davem@davemloft.net>
Cc: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

build error cause by
Commit ff43da86
("NET: FEC: dynamtic check DMA desc buff type")

drivers/net/ethernet/freescale/fec.c: In function ‘fec_enet_get_nextdesc’:
drivers/net/ethernet/freescale/fec.c:215:18: error: invalid use of undefined type ‘struct bufdesc_ex’
drivers/net/ethernet/freescale/fec.c: In function ‘fec_enet_get_prevdesc’:
drivers/net/ethernet/freescale/fec.c:224:18: error: invalid use of undefined type ‘struct bufdesc_ex’
drivers/net/ethernet/freescale/fec.c: In function ‘fec_enet_start_xmit’:
drivers/net/ethernet/freescale/fec.c:286:37: error: arithmetic on pointer to an incomplete type
drivers/net/ethernet/freescale/fec.c:287:13: error: arithmetic on pointer to an incomplete type
drivers/net/ethernet/freescale/fec.c:324:7: error: dereferencing pointer to incomplete type etc....
Signed-off-by: Frank Li <Frank.Li@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Setting net.ipv6.conf.<interface>.accept_ra=2 causes the kernel
to accept RAs even when forwarding is enabled. However, enabling
forwarding purges all default routes on the system, breaking
connectivity until the next RA is received. Fix this by not
purging default routes on interfaces that have accept_ra=2.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

up stack ndo_start_xmit already hold lock.
fec_enet_start_xmit needn't spin lock.
stat_xmit just update fep->cur_tx
fec_enet_tx just update fep->dirty_tx

Reserve a empty bdb to check full or empty
cur_tx == dirty_tx    means full
cur_tx == dirty_tx +1 means empty

So needn't is_full variable.

Fix spin lock deadlock

=================================
[ INFO: inconsistent lock state ]
3.8.0-rc5+ #107 Not tainted
---------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes:
 (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50
 {HARDIRQ-ON-W} state was registered at:
 [<80067250>] mark_lock+0x154/0x4e8
 [<800676f4>] mark_irqflags+0x110/0x1a4
 [<80069208>] __lock_acquire+0x494/0x9c0
 [<80069ce8>] lock_acquire+0x90/0xa4
 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54
 [<804877e0>] first_packet_length+0x38/0x1f0
 [<804879e4>] udp_poll+0x4c/0x5c
 [<804231f8>] sock_poll+0x24/0x28
 [<800d27f0>] do_poll.isra.10+0x120/0x254
 [<800d36e4>] do_sys_poll+0x15c/0x1e8
 [<800d3828>] sys_poll+0x60/0xc8
 [<8000e780>] ret_fast_syscall+0x0/0x3c

 *** DEADLOCK ***

 1 lock held by ptp4l/615:
  #0:  (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268
  stack backtrace:
  Backtrace:
  [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c)
  r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000
  [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4)
  [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88)
  r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000
  [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270)
  r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000
  [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8)
  [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4)
  [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0)
  r5:00000002 r4:bf38b2f8
  [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4)
  [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60)
  [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50)
  r6:bfbb2180 r5:bf1d0190 r4:bf1d0184
  [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188)
  r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000
  [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0)
  r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004
  [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268)
  r6:c089d260 r5:00001c00 r4:bfbd0000
  [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8)
  [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0)
  [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64)
  [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c)
  r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000
  [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38)
  r5:807130c8 r4:00000096
  [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4)
  r4:8071d280 r3:00000180
  [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64)
  r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c
  r3:00000000
  [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c)
  Exception stack(0xbf0ddef8 to 0xbf0ddf40)
Signed-off-by: Frank Li <Frank.Li@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Don't definite its own MAX_KMALLOC_SIZE, use the one
defined in mm.

Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Sridhar Samudrala <sri@us.ibm.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Dave Jones reported the following bug:

"When fed mangled socket data, rds will trust what userspace gives it,
and tries to allocate enormous amounts of memory larger than what
kmalloc can satisfy."

WARNING: at mm/page_alloc.c:2393 __alloc_pages_nodemask+0xa0d/0xbe0()
Hardware name: GA-MA78GM-S2H
Modules linked in: vmw_vsock_vmci_transport vmw_vmci vsock fuse bnep dlci bridge 8021q garp stp mrp binfmt_misc l2tp_ppp l2tp_core rfcomm s
Pid: 24652, comm: trinity-child2 Not tainted 3.8.0+ #65
Call Trace:
 [<ffffffff81044155>] warn_slowpath_common+0x75/0xa0
 [<ffffffff8104419a>] warn_slowpath_null+0x1a/0x20
 [<ffffffff811444ad>] __alloc_pages_nodemask+0xa0d/0xbe0
 [<ffffffff8100a196>] ? native_sched_clock+0x26/0x90
 [<ffffffff810b2128>] ? trace_hardirqs_off_caller+0x28/0xc0
 [<ffffffff810b21cd>] ? trace_hardirqs_off+0xd/0x10
 [<ffffffff811861f8>] alloc_pages_current+0xb8/0x180
 [<ffffffff8113eaaa>] __get_free_pages+0x2a/0x80
 [<ffffffff811934fe>] kmalloc_order_trace+0x3e/0x1a0
 [<ffffffff81193955>] __kmalloc+0x2f5/0x3a0
 [<ffffffff8104df0c>] ? local_bh_enable_ip+0x7c/0xf0
 [<ffffffffa0401ab3>] rds_message_alloc+0x23/0xb0 [rds]
 [<ffffffffa04043a1>] rds_sendmsg+0x2b1/0x990 [rds]
 [<ffffffff810b21cd>] ? trace_hardirqs_off+0xd/0x10
 [<ffffffff81564620>] sock_sendmsg+0xb0/0xe0
 [<ffffffff810b2052>] ? get_lock_stats+0x22/0x70
 [<ffffffff810b24be>] ? put_lock_stats.isra.23+0xe/0x40
 [<ffffffff81567f30>] sys_sendto+0x130/0x180
 [<ffffffff810b872d>] ? trace_hardirqs_on+0xd/0x10
 [<ffffffff816c547b>] ? _raw_spin_unlock_irq+0x3b/0x60
 [<ffffffff816cd767>] ? sysret_check+0x1b/0x56
 [<ffffffff810b8695>] ? trace_hardirqs_on_caller+0x115/0x1a0
 [<ffffffff81341d8e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff816cd742>] system_call_fastpath+0x16/0x1b
---[ end trace eed6ae990d018c8b ]---
Reported-by: Dave Jones <davej@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
Acked-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>