if kprobe is placed within update or delete hash map helpers
that hold bucket spin lock and triggered bpf program is trying to
grab the spinlock for the same bucket on the same cpu, it will
deadlock.
Fix it by extending existing recursion prevention mechanism.

Note, map_lookup and other tracing helpers don't have this problem,
since they don't hold any locks and don't modify global data.
bpf_trace_printk has its own recursive check and ok as well.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Michal Kubecek says:

====================
ipv6: per netns FIB6 walkers and garbage collector

Commit 2ac3ac8f ("ipv6: prevent fib6_run_gc() contention") reduced
the risk of contention on FIB6 garbage collector lock on systems with
many CPUs. However, one of our customers can still observe heavy
contention on fib6_gc_lock which can even trigger the soft lockup
detector.

This is caused by garbage collector running in forced mode from a timer.
While there is one timer per network namespace, the instances of
fib6_run_gc() running from them are protected by one global spinlock so
that only one garbage collector can run at any moment and other
namespaces have to wait. As most relevant data structures are separated
per netns, there is little reason for garbage collectors blocking each
other.

Similar problem exists for walkers: changes in one tree do not need to
adjust (and block) walkers traversing FIB trees in other namespaces.

This series separates both the walkers infrastructure and garbage
collector so that they work independently in network namespaces.

v2: get rid of ifdef in ipv6_route_seq_setup_walk(), pass net from
callers instead
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

One of our customers observed issues with FIB6 garbage collectors
running in different network namespaces blocking each other, resulting
in soft lockups (fib6_run_gc() initiated from timer runs always in
forced mode).

Now that FIB6 walkers are separated per namespace, there is no more need
for instances of fib6_run_gc() in different namespaces blocking each
other. There is still a call to icmp6_dst_gc() which operates on shared
data but this function is protected by its own shared lock.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IPv6 FIB data structures are separated per network namespace but
there is still only one global walkers list and one global walker list
lock. This means changes in one namespace unnecessarily interfere with
walkers in other namespaces.

Replace the global list with per-netns lists (and give each its own
lock).
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Global variable gc_args is only used in fib6_run_gc() and functions
called from it. As fib6_run_gc() makes sure there is at most one
instance of fib6_clean_all() running at any moment, we can replace
gc_args with a local variable which will be needed once multiple
instances (per netns) of garbage collector are allowed.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Michael Chan says:

====================
bnxt_en: Updates for net-next.

Updates to support autoneg for all supported speeds, add PF port statistics,
and Advanced Error Reporting.

v2: Fixed patch 3 to not use parentheses on function return.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Add pci_error_handler callbacks to support for pcie advanced error
recovery.
Signed-off-by: Satish Baddipadige <sbaddipa@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Include the more useful port statistics in ethtool -S for the PF device.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Include some of the port error counters (e.g. crc) in ->ndo_get_stats64()
for the PF device.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Gather periodic port statistics if the device is PF and link is up.  This
is triggered in bnxt_timer() every one second to request firmware to DMA
the counters.
Signed-off-by: Michael Chan <michael.chan@broadocm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Allow all autoneg speeds aupported by firmware to be advertised.  If
the advertising parameter is 0, then all supported speeds will be
advertised.

Remove BNXT_ALL_COPPER_ETHTOOL_SPEED which is no longer used as all
supported speeds can be advertised.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The supported bits and advertising bits in ethtool have the same
definitions.  The same is true for the firmware bits.  So use the
common function to handle the conversion for both supported and
advertising bits.

v2: Don't use parentheses on function return.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

And report actual pause settings to ETHTOOL_GPAUSEPARAM to let ethtool
resolve the actual pause settings.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Include the conversion of pause bits and add one extra call layer so
that the same refactored function can be reused to get the link partner
advertisement bits.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This fix is for dsmark similar to commit 3557619f
("net_sched: prio: use qdisc_dequeue_peeked")
and makes use of qdisc_dequeue_peeked() instead of direct dequeue() call.

First time, wrr peeks dsmark, which will then peek into sfq.
sfq dequeues an skb and it's stored in sch->gso_skb.
Next time, wrr tries to dequeue from dsmark, which will call sfq dequeue
directly. This results skipping the previously peeked skb.

So changed dsmark dequeue to call qdisc_dequeue_peeked() instead to use
peeked skb if exists.
Signed-off-by: Kyeong Yoo <kyeong.yoo@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter updates for your net-next tree,
they are:

1) Remove useless debug message when deleting IPVS service, from
   Yannick Brosseau.

2) Get rid of compilation warning when CONFIG_PROC_FS is unset in
   several spots of the IPVS code, from Arnd Bergmann.

3) Add prandom_u32 support to nft_meta, from Florian Westphal.

4) Remove unused variable in xt_osf, from Sudip Mukherjee.

5) Don't calculate IP checksum twice from netfilter ipv4 defrag hook
   since fixing af_packet defragmentation issues, from Joe Stringer.

6) On-demand hook registration for iptables from netns. Instead of
   registering the hooks for every available netns whenever we need
   one of the support tables, we register this on the specific netns
   that needs it, patchset from Florian Westphal.

7) Add missing port range selection to nf_tables masquerading support.

BTW, just for the record, there is a typo in the description of
5f6c253e ("netfilter: bridge: register hooks only when bridge
interface is added") that refers to the cluster match as deprecated, but
it is actually the CLUSTERIP target (which registers hooks
inconditionally) the one that is scheduled for removal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Daniel Borkmann says:

====================
BPF updates

Couple of misc updates to BPF, besides others this series adds
bpf_csum_diff() to be used with L3 csums, allows for managing
tunnel options for collect meta data mode, and enabling ipv6
traffic class for collect meta data in vxlan specifically (geneve
already supports it). For more details, please see individual
patches.

The series requires net to be merged into net-next first to
avoid any further pending merge conflicts.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

We can already do that for IPv4, but IPv6 support was missing. Add
it for vxlan, so it can be used with collect metadata frontends.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

The assumptions from commit 0c1d70af ("net: use dst_cache for vxlan
device"), 468dfffc ("geneve: add dst caching support") and 3c1cb4d2
("net/ipv4: add dst cache support for gre lwtunnels") on dst_cache usage
when ip_tunnel_info is used is unfortunately not always valid as assumed.

While it seems correct for ip_tunnel_info front-ends such as OVS, eBPF
however can fill in ip_tunnel_info for consumers like vxlan, geneve or gre
with different remote dsts, tos, etc, therefore they cannot be assumed as
packet independent.

Right now vxlan, geneve, gre would cache the dst for eBPF and every packet
would reuse the same entry that was first created on the initial route
lookup. eBPF doesn't store/cache the ip_tunnel_info, so each skb may have
a different one.

Fix it by adding a flag that checks the ip_tunnel_info. Also the !tos test
in vxlan needs to be handeled differently in this context as it is currently
inferred from ip_tunnel_info as well if present. ip_tunnel_dst_cache_usable()
helper is added for the three tunnel cases, which checks if we can use dst
cache.

Fixes: 0c1d70af ("net: use dst_cache for vxlan device")
Fixes: 468dfffc ("geneve: add dst caching support")
Fixes: 3c1cb4d2 ("net/ipv4: add dst cache support for gre lwtunnels")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

After eBPF being able to programmatically access/manage tunnel key meta
data via commit d3aa45ce ("bpf: add helpers to access tunnel metadata")
and more recently also for IPv6 through c6c33454 ("bpf: support ipv6
for bpf_skb_{set,get}_tunnel_key"), this work adds two complementary
helpers to generically access their auxiliary tunnel options.

Geneve and vxlan support this facility. For geneve, TLVs can be pushed,
and for the vxlan case its GBP extension. I.e. setting tunnel key for geneve
case only makes sense, if we can also read/write TLVs into it. In the GBP
case, it provides the flexibility to easily map the group policy ID in
combination with other helpers or maps.

I chose to model this as two separate helpers, bpf_skb_{set,get}_tunnel_opt(),
for a couple of reasons. bpf_skb_{set,get}_tunnel_key() is already rather
complex by itself, and there may be cases for tunnel key backends where
tunnel options are not always needed. If we would have integrated this
into bpf_skb_{set,get}_tunnel_key() nevertheless, we are very limited with
remaining helper arguments, so keeping compatibility on structs in case of
passing in a flat buffer gets more cumbersome. Separating both also allows
for more flexibility and future extensibility, f.e. options could be fed
directly from a map, etc.

Moreover, change geneve's xmit path to test only for info->options_len
instead of TUNNEL_GENEVE_OPT flag. This makes it more consistent with vxlan's
xmit path and allows for avoiding to specify a protocol flag in the API on
xmit, so it can be protocol agnostic. Having info->options_len is enough
information that is needed. Tested with vxlan and geneve.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Added by 9a628224 ("ip_tunnel: Add dont fragment flag."), allow to
feed df flag into tunneling facilities (currently supported on TX by
vxlan, geneve and gre) as a hint from eBPF's bpf_skb_set_tunnel_key()
helper.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

They are only used here, so there's no reason they should not be static.
Only the vlan push/pop protos are used in the test_bpf suite.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

When overwriting parts of the packet with bpf_skb_store_bytes() that
were fed previously into skb->hash calculation, we should clear the
current hash with skb_clear_hash(), so that a next skb_get_hash() call
can determine the correct hash related to this skb.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Commit 7d672345 ("bpf: add generic bpf_csum_diff helper") added a
generic checksum diff helper that can feed bpf_l4_csum_replace() with
a target __wsum diff that is to be applied to the L4 checksum. This
facility is very flexible, can be cascaded, allows for adding, removing,
or diffing data, or for calculating the pseudo header checksum from
scratch, but it can also be reused for working with the IPv4 header
checksum.

Thus, analogous to bpf_l4_csum_replace(), add a case for header field
value of 0 to change the checksum at a given offset through a new helper
csum_replace_by_diff(). Also, in addition to that, this provides an
easy to use interface for feeding precalculated diffs f.e. coming from
a map. It nicely complements bpf_l3_csum_replace() that currently allows
only for csum updates of 2 and 4 byte diffs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Several cases of overlapping changes, as well as one instance
(vxlan) of a bug fix in 'net' overlapping with code movement
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull networking fixes from David Miller:

 1) Fix ordering of WEXT netlink messages so we don't see a newlink
    after a dellink, from Johannes Berg.

 2) Out of bounds access in minstrel_ht_set_best_prob_rage, from
    Konstantin Khlebnikov.

 3) Paging buffer memory leak in iwlwifi, from Matti Gottlieb.

 4) Wrong units used to set initial TCP rto from cached metrics, also
    from Konstantin Khlebnikov.

 5) Fix stale IP options data in the SKB control block from leaking
    through layers of encapsulation, from Bernie Harris.

 6) Zero padding len miscalculated in bnxt_en, from Michael Chan.

 7) Only CHECKSUM_PARTIAL packets should be passed down through GSO, fix
    from Hannes Frederic Sowa.

 8) Fix suspend/resume with JME networking devices, from Diego Violat
    and Guo-Fu Tseng.

 9) Checksums not validated properly in bridge multicast support due to
    the placement of the SKB header pointers at the time of the check,
    fix from Álvaro Fernández Rojas.

10) Fix hang/tiemout with r8169 if a stats fetch is done while the
    device is runtime suspended.  From Chun-Hao Lin.

11) The forwarding database netlink dump facilities don't track the
    state of the dump properly, resulting in skipped/missed entries.
    From Minoura Makoto.

12) Fix regression from a recent 3c59x bug fix, from Neil Horman.

13) Fix list corruption in bna driver, from Ivan Vecera.

14) Big endian machines crash on vlan add in bnx2x, fix from Michal
    Schmidt.

15) Ethtool RSS configuration not propagated properly in mlx5 driver,
    from Tariq Toukan.

16) Fix regression in PHY probing in stmmac driver, from Gabriel
    Fernandez.

17) Fix SKB tailroom calculation in igmp/mld code, from Benjamin
    Poirier.

18) A past change to skip empty routing headers in ipv6 extention header
    parsing accidently caused fragment headers to not be matched any
    longer.  Fix from Florian Westphal.

19) eTSEC-106 erratum needs to be applied to more gianfar chips, from
    Atsushi Nemoto.

20) Fix netdev reference after free via workqueues in usb networking
    drivers, from Oliver Neukum and Bjørn Mork.

21) mdio->irq is now an array rather than a pointer to dynamic memory,
    but several drivers were still trying to free it :-/ Fixes from
    Colin Ian King.

22) act_ipt iptables action forgets to set the family field, thus LOG
    netfilter targets don't work with it.  Fix from Phil Sutter.

23) SKB leak in ibmveth when skb_linearize() fails, from Thomas Falcon.

24) pskb_may_pull() cannot be called with interrupts disabled, fix code
    that tries to do this in vmxnet3 driver, from Neil Horman.

25) be2net driver leaks iomap'd memory on removal, fix from Douglas
    Miller.

26) Forgotton RTNL mutex unlock in ppp_create_interface() error paths,
    from Guillaume Nault.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (97 commits)
  ppp: release rtnl mutex when interface creation fails
  cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind
  tcp: fix tcpi_segs_in after connection establishment
  net: hns: fix the bug about loopback
  jme: Fix device PM wakeup API usage
  jme: Do not enable NIC WoL functions on S0
  udp6: fix UDP/IPv6 encap resubmit path
  be2net: Don't leak iomapped memory on removal.
  vmxnet3: avoid calling pskb_may_pull with interrupts disabled
  net: ethernet: Add missing MFD_SYSCON dependency on HAS_IOMEM
  ibmveth: check return of skb_linearize in ibmveth_start_xmit
  cdc_ncm: toggle altsetting to force reset before setup
  usbnet: cleanup after bind() in probe()
  mlxsw: pci: Correctly determine if descriptor queue is full
  mlxsw: spectrum: Always decrement bridge's ref count
  tipc: fix nullptr crash during subscription cancel
  net: eth: altera: do not free array priv->mdio->irq
  net/ethoc: do not free array priv->mdio->irq
  net: sched: fix act_ipt for LOG target
  asix: do not free array priv->mdio->irq
  ...

Pull overlayfs fixes from Miklos Szeredi:
 "Overlayfs bug fixes.  All marked as -stable material"

* 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: copy new uid/gid into overlayfs runtime inode
  ovl: ignore lower entries when checking purity of non-directory entries
  ovl: fix getcwd() failure after unsuccessful rmdir
  ovl: fix working on distributed fs as lower layer

This reverts commit dbb17a21.

It turns out that commit can cause problems for systems with multiple
GPUs, and causes X to hang on at least a HP Pavilion dv7 with hybrid
graphics.

This got noticed originally in 4.4.4, where this patch had already
gotten back-ported, but 4.5-rc7 was verified to have the same problem.

Alexander Deucher says:
 "It looks like you have a muxed system so I suspect what's happening is
  that one of the display is being reported as connected for both the
  IGP and the dGPU and then the desktop environment gets confused or
  there some sort problem in the detect functions since the mux is not
  switched to the dGPU.  I don't see an easy fix unless Dave has any
  ideas.  I'd say just revert for now"
Reported-by: Jörg-Volker Peetz <jvpeetz@web.de>
Acked-by: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: Dave Airlie <airlied@gmail.com>
Cc: stable@kernel.org  # wherever dbb17a21 got back-ported
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Add missing rtnl_unlock() in the error path of ppp_create_interface().

Fixes: 58a89eca ("ppp: fix lockdep splat in ppp_dev_uninit()")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

usbnet_link_change will call schedule_work and should be
avoided if bind is failing. Otherwise we will end up with
scheduled work referring to a netdev which has gone away.

Instead of making the call conditional, we can just defer
it to usbnet_probe, using the driver_info flag made for
this purpose.

Fixes: 8a34b0ae ("usbnet: cdc_ncm: apply usbnet_link_change")
Reported-by: Andrey Konovalov <andreyknvl@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>

If final packet (ACK) of 3WHS is lost, it appears we do not properly
account the following incoming segment into tcpi_segs_in

While we are at it, starts segs_in with one, to count the SYN packet.

We do not yet count number of SYN we received for a request sock, we
might add this someday.

packetdrill script showing proper behavior after fix :

// Tests tcpi_segs_in when 3rd packet (ACK) of 3WHS is lost
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop>
   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+.020 < P. 1:1001(1000) ack 1 win 32792

   +0 accept(3, ..., ...) = 4

+.000 %{ assert tcpi_segs_in == 2, 'tcpi_segs_in=%d' % tcpi_segs_in }%

Fixes: 2efd055c ("tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It will always be passed if the soc is tested the loopback cases. This
patch will fix this bug.
Signed-off-by: Kejian Yan <yankejian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

According to Documentation/power/devices.txt

The driver should not use device_set_wakeup_enable() which is the policy
for user to decide.

Using device_init_wakeup() to initialize dev->power.should_wakeup and
dev->power.can_wakeup on driver initialization.

And use device_may_wakeup() on suspend to decide if WoL function should
be enabled on NIC.
Reported-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: Guo-Fu Tseng <cooldavid@cooldavid.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Otherwise it might be back on resume right after going to suspend in
some hardware.
Reported-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: Guo-Fu Tseng <cooldavid@cooldavid.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

During hot add, vmbus_device_register() is called from vmbus_onoffer(), on
the same workqueue as the subchannel offer message work-queue, so
subchannel offer won't be processed until the vmbus_device_register()/...
/netvsc_probe() is done.
Also, vmbus_device_register() is called with channel_mutex locked, which
prevents subchannel processing too. So the "waiting for sub-channel
processing" will not success in hot add case. But, in usual module loading,
the netvsc_probe() is called from different code path, and doesn't fail.

This patch resolves the deadlock during NIC hot-add, and speeds up NIC
loading time.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

IPv4 interprets a negative return value from a protocol handler as a
request to redispatch to a new protocol.  In contrast, IPv6 interprets a
negative value as an error, and interprets a positive value as a request
for redispatch.

UDP for IPv6 was unaware of this difference.  Change __udp6_lib_rcv() to
return a positive value for redispatch.  Note that the socket's
encap_rcv hook still needs to return a negative value to request
dispatch, and in the case of IPv6 packets, adjust IP6CB(skb)->nhoff to
identify the byte containing the next protocol.
Signed-off-by: Bill Sommerfeld <wsommerfeld@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The adapter->pcicfg resource is either mapped via pci_iomap() or
derived from adapter->db. During be_remove() this resource was ignored
and so could remain mapped after remove.

Add a flag to track whether adapter->pcicfg was mapped or not, then
use that flag in be_unmap_pci_bars() to unmap if required.

Fixes: 25848c90 ("use PCI MMIO read instead of config read for errors")
Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

vmxnet3 has a function vmxnet3_parse_and_copy_hdr which, among other operations,
uses pskb_may_pull to linearize the header portion of an skb.  That operation
eventually uses local_bh_disable/enable to ensure that it doesn't race with the
drivers bottom half handler.  Unfortunately, vmxnet3 preforms this
parse_and_copy operation with a spinlock held and interrupts disabled.  This
causes us to run afoul of the WARN_ON_ONCE(irqs_disabled()) warning in
local_bh_enable, resulting in this:

WARNING: at kernel/softirq.c:159 local_bh_enable+0x59/0x90() (Not tainted)
Hardware name: VMware Virtual Platform
Modules linked in: ipv6 ppdev parport_pc parport microcode e1000 vmware_balloon
vmxnet3 i2c_piix4 sg ext4 jbd2 mbcache sd_mod crc_t10dif sr_mod cdrom mptspi
mptscsih mptbase scsi_transport_spi pata_acpi ata_generic ata_piix vmwgfx ttm
drm_kms_helper drm i2c_core dm_mirror dm_region_hash dm_log dm_mod [last
unloaded: mperf]
Pid: 6229, comm: sshd Not tainted 2.6.32-616.el6.i686 #1
Call Trace:
 [<c04624d9>] ? warn_slowpath_common+0x89/0xe0
 [<c0469e99>] ? local_bh_enable+0x59/0x90
 [<c046254b>] ? warn_slowpath_null+0x1b/0x20
 [<c0469e99>] ? local_bh_enable+0x59/0x90
 [<c07bb936>] ? skb_copy_bits+0x126/0x210
 [<f8d1d9fe>] ? ext4_ext_find_extent+0x24e/0x2d0 [ext4]
 [<c07bc49e>] ? __pskb_pull_tail+0x6e/0x2b0
 [<f95a6164>] ? vmxnet3_xmit_frame+0xba4/0xef0 [vmxnet3]
 [<c05d15a6>] ? selinux_ip_postroute+0x56/0x320
 [<c0615988>] ? cfq_add_rq_rb+0x98/0x110
 [<c0852df8>] ? packet_rcv+0x48/0x350
 [<c07c5839>] ? dev_queue_xmit_nit+0xc9/0x140
...

Fix it by splitting vmxnet3_parse_and_copy_hdr into two functions:

vmxnet3_parse_hdr, which sets up the internal/on stack ctx datastructure, and
pulls the skb (both of which can be done without holding the spinlock with irqs
disabled

and

vmxnet3_copy_header, which just copies the skb to the tx ring under the lock
safely.

tested and shown to correct the described problem.  Applies cleanly to the head
of the net tree
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Shrikrishna Khare <skhare@vmware.com>
CC: "VMware, Inc." <pv-drivers@vmware.com>
CC: "David S. Miller" <davem@davemloft.net>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Manish Chopra says:

====================
qed/qede: Add hardware GRO support

This patch series enables hardware GRO and add support for handling
HW aggregated TCP packets in driver receive flow by skipping
software GRO handling in stack.

Please consider applying this series to net-next.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch configures hardware to use GRO and adds support
for fastpath APIs to handle HW aggregated packets.
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>