In commit 8e4d980a ("tcp: fix behavior for epoll edge trigger")
we fixed a possible hang of TCP sockets under memory pressure,
by allowing sk_stream_alloc_skb() to use sk_forced_mem_schedule()
if no packet is in socket write queue.

It turns out there are other cases where we want to force memory
schedule :

tcp_fragment() & tso_fragment() need to split a big TSO packet into
two smaller ones. If we block here because of TCP memory pressure,
we can effectively block TCP socket from sending new data.
If no further ACK is coming, this hang would be definitive, and socket
has no chance to effectively reduce its memory usage.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

[1] When entering NUD_PROBE state via neigh_update(), perhaps received
    from userspace, correctly (re)initialize the probes count to zero.

    This is useful for forcing revalidation of a neighbor (for example
    if the host is attempting to do DNA [IPv4 4436, IPv6 6059]).

[2] Notify listeners when a neighbor goes into NUD_PROBE state.

    By sending notifications on entry to NUD_PROBE state listeners get
    more timely warnings of imminent connectivity issues.

    The current notifications on entry to NUD_STALE have somewhat
    limited usefulness: NUD_STALE is a perfectly normal state, as is
    NUD_DELAY, whereas notifications on entry to NUD_FAILURE come after
    a neighbor reachability problem has been confirmed (typically after
    three probes).
Signed-off-by: NErik Kline <ek@google.com>
Acked-By: NLorenzo Colitti <lorenzo@google.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ip_do_nat() function was removed prior to kernel 3.4. Remove the
unnecessary function prototype as well.
Reported-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NAndy Zhou <azhou@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This work as a follow-up of commit f7b3bec6 ("net: allow setting ecn
via routing table") and adds RFC3168 section 6.1.1.1. fallback for outgoing
ECN connections. In other words, this work adds a retry with a non-ECN
setup SYN packet, as suggested from the RFC on the first timeout:

  [...] A host that receives no reply to an ECN-setup SYN within the
  normal SYN retransmission timeout interval MAY resend the SYN and
  any subsequent SYN retransmissions with CWR and ECE cleared. [...]

Schematic client-side view when assuming the server is in tcp_ecn=2 mode,
that is, Linux default since 2009 via commit 255cac91 ("tcp: extend
ECN sysctl to allow server-side only ECN"):

 1) Normal ECN-capable path:

    SYN ECE CWR ----->
                <----- SYN ACK ECE
            ACK ----->

 2) Path with broken middlebox, when client has fallback:

    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
            SYN ----->
                <----- SYN ACK
            ACK ----->

In case we would not have the fallback implemented, the middlebox drop
point would basically end up as:

    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)

In any case, it's rather a smaller percentage of sites where there would
occur such additional setup latency: it was found in end of 2014 that ~56%
of IPv4 and 65% of IPv6 servers of Alexa 1 million list would negotiate
ECN (aka tcp_ecn=2 default), 0.42% of these webservers will fail to connect
when trying to negotiate with ECN (tcp_ecn=1) due to timeouts, which the
fallback would mitigate with a slight latency trade-off. Recent related
paper on this topic:

  Brian Trammell, Mirja Kühlewind, Damiano Boppart, Iain Learmonth,
  Gorry Fairhurst, and Richard Scheffenegger:
    "Enabling Internet-Wide Deployment of Explicit Congestion Notification."
    Proc. PAM 2015, New York.
  http://ecn.ethz.ch/ecn-pam15.pdf

Thus, when net.ipv4.tcp_ecn=1 is being set, the patch will perform RFC3168,
section 6.1.1.1. fallback on timeout. For users explicitly not wanting this
which can be in DC use case, we add a net.ipv4.tcp_ecn_fallback knob that
allows for disabling the fallback.

tp->ecn_flags are not being cleared in tcp_ecn_clear_syn() on output, but
rather we let tcp_ecn_rcv_synack() take that over on input path in case a
SYN ACK ECE was delayed. Thus a spurious SYN retransmission will not prevent
ECN being negotiated eventually in that case.

Reference: https://www.ietf.org/proceedings/92/slides/slides-92-iccrg-1.pdf
Reference: https://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdfSigned-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NMirja Kühlewind <mirja.kuehlewind@tik.ee.ethz.ch>
Signed-off-by: NBrian Trammell <trammell@tik.ee.ethz.ch>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Dave That <dave.taht@gmail.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Hariprasad Shenai says:

====================
cxgb4: Remove dead code and replace byte-oder functions

This series removes dead fn t4_read_edc and t4_read_mc, also replaces
ntoh{s,l} and hton{s,l} calls with the generic byteorder.

PATCH 2/2 was sent as a single PATCH, but had some byte-ordering issues
in t4_read_edc and t4_read_mc function. Found that t4_read_edc and
t4_read_mc is unused, so PATCH 1/2 is added to remove it.

This patch series is created against net-next tree and includes
patches on cxgb4 driver.

We have included all the maintainers of respective drivers. Kindly review
the change and let us know in case of any review comments.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

replace ntoh{s,l} and hton{s,l} calls with the generic byteorder in
cxgb4/t4_hw.c file
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge tag 'mac80211-next-for-davem-2015-05-19' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next

Johannes Berg says:

====================
This just has a few fixes:
 * LED throughput trigger was crashing
 * fast-xmit wasn't treating QoS changes in IBSS correctly
 * TDLS could use the wrong channel definition
 * using a reserved channel context could use the wrong channel width
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The hwmon interface in the be2net driver causes a link error when
be2net is built-in while the hwmon subsystem is a loadable module:

drivers/built-in.o: In function `be_probe':
drivers/net/ethernet/emulex/benet/be_main.c:5761: undefined reference to `devm_hwmon_device_register_with_groups'

This adds a new Kconfig symbol, following the example of multiple
other drivers that have the same problem. The new CONFIG_BE2NET_HWMON
will not be available when (BE2NET=y && HWMON=m) to avoid this
problem.

We have to also mark be_hwmon_show_temp as 'static' to ensure the
compiler can optimize out all the unused code.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Fixes: 29e9122b ("be2net: Export board temperature using hwmon-sysfs interface.")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the getsockopt() requesting the cached contents of the syn
packet headers will fail silently if the caller uses a buffer that is
too small to contain the requested data.  Rather than fail silently and
discard the headers, getsockopt() should return an error and report the
required size to hold the data.
Signed-off-by: NEric B Munson <emunson@akamai.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NParav Pandit <parav.pandit@avagotech.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Andy Zhou says:

====================
fragmentation ICMP

Currently, we send ICMP packets when errors occur during fragmentation or
de-fragmentation.  However, it is a bug when sending those ICMP packets
in the context of using netfilter for bridging.

Those ICMP packets are only expected in the context of routing, not in
bridging mode.

The local stack is not involved in bridging forward decisions, thus
should be not used for deciding the reverse path for those ICMP messages.

This bug only affects IPV4, not in IPv6.

v1->v2:  restructure the patches into two patches that fix defragmentation and
         fragmentation respectively.

	 A bit is add in IPCB to control whether ICMP packet should be
	 generated for defragmentation.

	 Fragmentation ICMP is now removed by restructuring the
	 ip_fragment() API.

v2->v3:  Add droping icmp for bridging contrack users
         drop exporting ip_fragment() API.

v3->v4:  Remove unnecessary parentheses in 'return' statements

v4->v5:  Drop the patch that sets and checks a bit in IPCB
         that prevents ip_defrag to send ICMP.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When bridge netfilter re-fragments an IP packet for output, all
packets that can not be re-fragmented to their original input size
should be silently discarded.

However, current bridge netfilter output path generates an ICMP packet
with 'size exceeded MTU' message for such packets, this is a bug.

This patch refactors the ip_fragment() API to allow two separate
use cases. The bridge netfilter user case will not
send ICMP, the routing output will, as before.
Signed-off-by: NAndy Zhou <azhou@nicira.com>
Acked-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

users in [IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BR_IN]
should not ICMP message also.
Reported-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NAndy Zhou <azhou@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Improve readability of skip ICMP for de-fragmentation expiration logic.
This change will also make the logic easier to maintain when the
following patches in this series are applied.
Signed-off-by: NAndy Zhou <azhou@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

psock_fanout tests the various fanout modes. Change the test for
rollover mode to expect early rollover due to socket pressure
as implemented in 2ccdbaa6 ("packet: rollover lock contention
avoidance").
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We expect that MC_CMD_SRIOV will fail if the card has no VFs configured.
So output a readable message instead of a cryptic MCDI error.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for net-next. Briefly
speaking, cleanups and minor fixes for ipset from Jozsef Kadlecsik and
Serget Popovich, more incremental updates to make br_netfilter a better
place from Florian Westphal, ARP support to the x_tables mark match /
target from and context Zhang Chunyu and the addition of context to know
that the x_tables runs through nft_compat. More specifically, they are:

1) Fix sparse warning in ipset/ip_set_hash_ipmark.c when fetching the
   IPSET_ATTR_MARK netlink attribute, from Jozsef Kadlecsik.

2) Rename STREQ macro to STRNCMP in ipset, also from Jozsef.

3) Use skb->network_header to calculate the transport offset in
   ip_set_get_ip{4,6}_port(). From Alexander Drozdov.

4) Reduce memory consumption per element due to size miscalculation,
   this patch and follow up patches from Sergey Popovich.

5) Expand nomatch field from 1 bit to 8 bits to allow to simplify
   mtype_data_reset_flags(), also from Sergey.

6) Small clean for ipset macro trickery.

7) Fix error reporting when both ip_set_get_hostipaddr4() and
   ip_set_get_extensions() from per-set uadt functions.

8) Simplify IPSET_ATTR_PORT netlink attribute validation.

9) Introduce HOST_MASK instead of hardcoded 32 in ipset.

10) Return true/false instead of 0/1 in functions that return boolean
    in the ipset code.

11) Validate maximum length of the IPSET_ATTR_COMMENT netlink attribute.

12) Allow to dereference from ext_*() ipset macros.

13) Get rid of incorrect definitions of HKEY_DATALEN.

14) Include linux/netfilter/ipset/ip_set.h in the x_tables set match.

15) Reduce nf_bridge_info size in br_netfilter, from Florian Westphal.

16) Release nf_bridge_info after POSTROUTING since this is only needed
    from the physdev match, also from Florian.

17) Reduce size of ipset code by deinlining ip_set_put_extensions(),
    from Denys Vlasenko.

18) Oneliner to add ARP support to the x_tables mark match/target, from
    Zhang Chunyu.

19) Add context to know if the x_tables extension runs from nft_compat,
    to address minor problems with three existing extensions.

20) Correct return value in several seqfile *_show() functions in the
    netfilter tree, from Joe Perches.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ursula Braun says:

====================
s390: network patches for net-next

here are s390 related patches for net-next
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

An attempt to configure a CTC device as LCS results in the
following error message:

  (null): Detecting a network adapter for LCS devices failed
          with rc=-5 (0xfffffffb)

"(null)" results from access to &card->dev->dev in lcs_new_device()
which is only initialized later in the function. Fix this by using
&ccwgdev->dev instead which is initialized before lcs_new_device()
is called.
Signed-off-by: NPeter Oberparleiter <oberpar@linux.vnet.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since recently, `checkpatch.pl` advices that ENOSYS should not be
used for anything other than "invalid syscall nr". This patch
replaces ENOSYS return code with EOPNOTSUPP for the "unsupported
function" conditions.
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Forbid enabling IFF_PROMISC reflection to BRIDGEPORT when a role
is already assigned, and forbid direct manipulation of the role
when reflection mode is engaged.
Reviewed-by: NThomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OSA Ethernet hardware is introducing BRIDGEPORT functionality
similar (but not identical) to HiperSockets BRIDGEPORT. This
patch makes HiperSockets BRIDGEPORT related sysfs attributes
and udev events work with OSA hardware too.
Reviewed-by: NThomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OSA and HiperSocket devices do not support promiscuous mode proper,
but they support "BRIDGE PORT" mode that is functionally similar.
This update introduces sysfs attribute that, when set, makes the driver
try to "reflect" setting and resetting of the IFF_PROMISC flag on the
interface into setting and resetting PRIMARY or SECONDARY bridge port
role on the underlying OSA or HiperSocket device.
Reviewed-by: NThomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Locking is probably unnecessary in this case, and the rest of the
qeth sysfs code does not use locks in the *_show() functions.
Remove locks from the layer2 *_show() functions in which they where
accidentally introduced.
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Function that executes IPA commands returns the result code from the
IPA response block. If non-negative, it needs to be transformed into
errno-compatible code before returning to the caller.
Signed-off-by: NEugene Crosser <Eugene.Crosser@ru.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ethtool is used to change some device driver features
such as RX/TX hardware checksum offloading.
The qeth device driver callback function to
turn on/off RX hardware check sum handling never changes
the hardware configuration.
The NETIF_F_RXCSUM bit is cleared when the feature bitset
type netdev_features_t(64bit) is assigned to 32 a bit
variable.

This patch fixes the NETIF_F_RXCSUM handling.
Also there is no need to manipulate the device's features
bit set as this is done by the caller when no error occurs.
Signed-off-by: NThomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: NUrsula Braun <ursula.braun@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently we use a global rover to select a port ID that is unique.
This used to work consistently when it was protected with a global
lock.  However as we're now lockless, the global rover can exhibit
pathological behaviour should multiple threads all stomp on it at
the same time.

Granted this will eventually resolve itself but the process is
suboptimal.

This patch replaces the global rover with a pseudorandom starting
point to avoid this issue.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The spinlock is used to protect netns_ids which is per net,
so there is no need to use a global spinlock.

Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MoCA interfaces require the use of an user-space daemon (mocad) which
will typically use cmd->autoneg to force the link. This is causing other
network manager applications not to get proper carrier down
notifications because of the following sequence of events:

- link down interrupt is received, link is set to 0 by the interrupt
  handler
- fixed_link update callback runs and updates the BMSR register
  accordingly
- PHY library polls the PHY for link status, sees the link is down,
  proceeds with reporting that
- mocad gets notified of the link state and call phy_ethtool_sset()
  with cmd->autoneg set to the link status (0)
- phy_start_aneg() is called at the end of phy_ethtool_sset() and sets
  the PHY state to PHY_FORCING

Just make sure we notify the interface carrier appropriately when we
detect that the link is down in our fixed_link update callback. This is
made local to the bcm_sf2 driver as the PHY library does the right thing
in any case. This is similar to the GENET change introduced in
54d7c01d ("net: bcmgenet: enable MoCA
link state change detection").

Fixes: 246d7f77 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes: 06635a35 ("flow_dissect: use programable dissector in skb_flow_dissect and friends")
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the struct netvsc_stats has a member s_sync
of type u64_stats_sync.
This definition will break kernel build as the macro
netdev_alloc_pcpu_stats requires this member name to be syncp.
(see netdev_alloc_pcpu_stats definition in ./include/linux/netdevice.h)

This patch changes netvsc_stats's member name from s_sync to syncp to fix
the build break.
Signed-off-by: NSimon Xiao <sixiao@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- introduce port fdb obj and generic switchdev_port_fdb_add/del/dump()
- use switchdev_port_fdb_add/del/dump in rocker/team/bonding ndo ops.
- add support for fdb obj in switchdev_port_obj_add/del/dump()
- switch rocker to implement fdb ops via switchdev_ops

v3: updated to sync with named union changes.
Signed-off-by: NSridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Eric Dumazet says:

====================
tcp: better handling of memory pressure

When testing commit 790ba456 ("tcp: set SOCK_NOSPACE under memory
pressure") using edge triggered epoll applications, I found various
issues under memory pressure and thousands of active sockets.

This patch series is a first round to solve these issues, in send
and receive paths. There are probably other fixes needed, but
with this series, my tests now all succeed.

v2: fix typo in "allow one skb to be received per socket under memory pressure",
as spotted by Jason Baron.
====================
Acked-by: NJason Baron <jbaron@akamai.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allowing tcp to use ~19% of physical memory is way too much,
and allowed bugs to be hidden. Add to this that some drivers use a full
page per incoming frame, so real cost can be twice the advertized one.

Reduce tcp_mem by 50 % as a first step to sanity.

tcp_mem[0,1,2] defaults are now 4.68%, 6.25%, 9.37% of physical memory.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While testing tight tcp_mem settings, I found tcp sessions could be
stuck because we do not allow even one skb to be received on them.

By allowing one skb to be received, we introduce fairness and
eventuallu force memory hogs to release their allocation.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Under memory pressure, tcp_sendmsg() can fail to queue a packet
while no packet is present in write queue. If we return -EAGAIN
with no packet in write queue, no ACK packet will ever come
to raise EPOLLOUT.

We need to allow one skb per TCP socket, and make sure that
tcp sockets can release their forward allocations under pressure.

This is a followup to commit 790ba456 ("tcp: set SOCK_NOSPACE
under memory pressure")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce an optimized version of sk_under_memory_pressure()
for TCP. Our intent is to use it in fast paths.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We plan to use sk_forced_wmem_schedule() in input path as well,
so make it non static and rename it.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sk_mem_reclaim_partial() goal is to ensure each socket has
one SK_MEM_QUANTUM forward allocation. This is needed both for
performance and better handling of memory pressure situations in
follow up patches.

SK_MEM_QUANTUM is currently a page, but might be reduced to 4096 bytes
as some arches have 64KB pages.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>