If we get an ENOMEM during rds_ib_recv_refill, we might never come
back and refill again later. Patch makes sure to kick krdsd into
helping out.

To achieve this we add RDS_RECV_REFILL flag and update in the refill
path based on that so that at least some therad will keep posting
receive buffers.

Since krdsd and softirq both might race for refill, we decide to
schedule on work queue based on ring_low instead of ring_empty.
Reviewed-by: NAjaykumar Hotchandani <ajaykumar.hotchandani@oracle.com>
Signed-off-by: NSantosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the ip address tables hasn't changed, there is no need to remove
them only to be added back again.

Lets fix it.
Reviewed-by: NAjaykumar Hotchandani <ajaykumar.hotchandani@oracle.com>
Signed-off-by: NSantosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Destroy ib state early during shutdown. Otherwise we can get callbacks
after the QP isn't really able to handle them.
Reviewed-by: NAjaykumar Hotchandani <ajaykumar.hotchandani@oracle.com>
Signed-off-by: NSantosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We were still seeing rare occurrences of the WARN_ON(recv->r_frag) which
indicates that the recv refill path was finding allocated frags in ring
entries that were marked free. These were usually followed by OOM crashes.
They only seem to be occurring in the presence of completion errors and
connection resets.

This patch ensures that we free the frag as we mark the ring entry free.
This should stop the refill path from finding allocated frags in ring
entries that were marked free.
Reviewed-by: NAjaykumar Hotchandani <ajaykumar.hotchandani@oracle.com>
Signed-off-by: NSantosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In rds_cmsg_rdma_args() 'ret' is used by rds_pin_pages() which returns
number of pinned pages on success. And the same value is returned to the
caller of rds_cmsg_rdma_args() on success which is not intended.

Commit f4a3fc03 ("RDS: Clean up error handling in rds_cmsg_rdma_args")
removed the 'ret = 0' line which broke RDS RDMA mode.

Fix it by restoring the return value on rds_pin_pages() success
keeping the clean-up in place.
Signed-off-by: NSantosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: NSantosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When TCP pacing was added back in linux-3.12, we chose
to apply a fixed ratio of 200 % against current rate,
to allow probing for optimal throughput even during
slow start phase, where cwnd can be doubled every other gRTT.

At Google, we found it was better applying a different ratio
while in Congestion Avoidance phase.
This ratio was set to 120 %.

We've used the normal tcp_in_slow_start() helper for a while,
then tuned the condition to select the conservative ratio
as soon as cwnd >= ssthresh/2 :

- After cwnd reduction, it is safer to ramp up more slowly,
  as we approach optimal cwnd.
- Initial ramp up (ssthresh == INFINITY) still allows doubling
  cwnd every other RTT.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Directs route lookups to VRF table. Compiles out if NET_VRF is not
enabled. With this patch able to successfully bring up ipsec tunnels
in VRFs, even with duplicate network configuration.
Signed-off-by: NDavid Ahern <dsa@cumulusnetworks.com>
Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: NSteffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

slow start after idle might reduce cwnd, but we perform this
after first packet was cooked and sent.

With TSO/GSO, it means that we might send a full TSO packet
even if cwnd should have been reduced to IW10.

Moving the SSAI check in skb_entail() makes sense, because
we slightly reduce number of times this check is done,
especially for large send() and TCP Small queue callbacks from
softirq context.

As Neal pointed out, we also need to perform the check
if/when receive window opens.

Tested:

Following packetdrill test demonstrates the problem
// Test of slow start after idle

`sysctl -q net.ipv4.tcp_slow_start_after_idle=1`

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 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+0    > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.100 < . 1:1(0) ack 1 win 511
+0    accept(3, ..., ...) = 4
+0    setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0

+0    write(4, ..., 26000) = 26000
+0    > . 1:5001(5000) ack 1
+0    > . 5001:10001(5000) ack 1
+0    %{ assert tcpi_snd_cwnd == 10 }%

+.100 < . 1:1(0) ack 10001 win 511
+0    %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
+0    > . 10001:20001(10000) ack 1
+0    > P. 20001:26001(6000) ack 1

+.100 < . 1:1(0) ack 26001 win 511
+0    %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%

+4 write(4, ..., 20000) = 20000
// If slow start after idle works properly, we should send 5 MSS here (cwnd/2)
+0    > . 26001:31001(5000) ack 1
+0    %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+0    > . 31001:36001(5000) ack 1
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Taku Izumi says:

====================
FUJITSU Extended Socket network device driver

This patchsets adds FUJITSU Extended Socket network device driver.
Extended Socket network device is a shared memory based high-speed
network interface between Extended Partitions of PRIMEQUEST 2000 E2
series.

You can get some information about Extended Partition and Extended
Socket by referring the following manual.

http://globalsp.ts.fujitsu.com/dmsp/Publications/public/CA92344-0537.pdf
    3.2.1 Extended Partitioning
    3.2.2 Extended Socke

v2.2 -> v3:
   - Fix up according to David's comment (No functional change)
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds implementation for ethtool support.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds implementation of handling IRQ
of other receiver's receive cancellation request.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds epstop_task.
This task is used to process other receiver's
cancellation request.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds update_zone_task.
Zoning information can be changed by user.
This task is used to monitor if zoning information is
changed or not.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds unshare_watch_task.
Shared buffer's status can be changed into unshared.
This task is used to monitor shared buffer's status.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds force_close_task.
This task is used to close network device forcibly.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds interrupt_watch_task.
This task is used to prevent delay of interrupts.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_vlan_rx_add_vid and
net_device_ops.ndo_vlan_rx_kill_vid callback.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_tx_timeout callback.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_change_mtu.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_get_stats64 callback.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds NAPI polling function and receive related work.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds tx_stall_task.
When receiver's buffer is full, sender stops
its tx queue. This task is used to monitor
receiver's status and when receiver's buffer
is avairable, it resumes tx queue.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch add raise_intr_rxdata_task.
Extended Socket Network Device is shared memory
based, so someone's transmission denotes other's
reception. In order to notify receivers, sender
has to raise interruption of receivers.
raise_intr_rxdata_task does this work.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_start_xmit callback,
which is called when sending packets.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds net_device_ops.ndo_open and .ndo_stop
callback. These function is called when network device
activation and deactivation.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds buffer address regist/unregistration routine.

This function is mainly invoked when network device's
activation (open) and deactivation (close)
in order to retist/unregist shared buffer address.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds ES information acquisition routine.
ES information can be retrieved issuing information
request command. ES information includes which
receiver is same zone.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements platform_driver's .probe and .remove
routine, and also adds board specific private data structure.

This driver registers net_device at platform_driver's .probe
routine and unregisters net_device at its .remove routine.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds hardware cleanup routine to be
invoked at driver's .remove routine.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds hardware initialization routine to be
invoked at driver's .probe routine.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds the basic code of FUJITSU Extended Socket
Network Device driver.

When "PNP0C02" is found in ACPI DSDT, it evaluates "_STR"
to check if "PNP0C02" is for Extended Socket device driver
and retrieves ACPI resource information. Then creates
platform_device.
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This BQL patch is based on work done by Tino Reichardt.

Tested on 0000:05:00.0: 3Com PCI 3c905C Tornado at ffffc90000e6e000 by running
Flent several times.
Signed-off-by: NLoganaden Velvindron <logan@elandsys.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Tom Herbert says:

====================
ila: Precompute checksums

This patch set:
 - Adds argument ot LWT build_state that holds a pointer to the fib
   configuration being applied to the new route
 - Adds support in ILA to precompute checksum difference for
   performance optimization

v2:
 - Move return argument in build_state to end of arguments

v3:
 - Update the signature for ip6_tun_build_state()
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the ILA build state for LWT compute the checksum difference to apply
to transport checksums that include the IPv6 pseudo header. The
difference is between the route destination (from fib6_config) and the
locator to write.
Signed-off-by: NTom Herbert <tom@herbertland.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add cfg and family arguments to lwt build state functions. cfg is a void
pointer and will either be a pointer to a fib_config or fib6_config
structure. The family parameter indicates which one (either AF_INET
or AF_INET6).

LWT encpasulation implementation may use the fib configuration to build
the LWT state.
Signed-off-by: NTom Herbert <tom@herbertland.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

By implementing config_intr & ack_interrupt, now the phy can support
link connect/disconnect interrupt.
Signed-off-by: NShaohui Xie <Shaohui.Xie@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Samuel Ortiz says:

====================
NFC 4.3 pull request

This is the NFC pull request for 4.3.
With this one we have:

- A new driver for Samsung's S3FWRN5 NFC chipset. In order to
  properly support this driver, a few NCI core routines needed
  to be exported. Future drivers like Intel's Fields Peak will
  benefit from this.

- SPI support as a physical transport for STM st21nfcb.

- An additional netlink API for sending replies back to userspace
  from vendor commands.

- 2 small fixes for TI's trf7970a

- A few st-nci fixes.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

__recnt and related fields need to be in its own cacheline for performance
reasons. Commit 61adedf3 ("route: move lwtunnel state to dst_entry")
broke that on 32bit archs, causing BUILD_BUG_ON in dst_hold to be triggered.

This patch fixes the breakage by moving the lwtunnel state to the end of
dst_entry on 32bit archs. Unfortunately, this makes it share the cacheline
with __refcnt and may affect performance, thus further patches may be
needed.
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Fixes: 61adedf3 ("route: move lwtunnel state to dst_entry")
Signed-off-by: NJiri Benc <jbenc@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge tag 'linux-can-next-for-4.3-20150820' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next

Marc Kleine-Budde says:

====================
this is a pull request of a two patches for net-next.

The first patch is by Nik Nyby and fixes a typo in a function name. The
second patch by Lucas Stach demotes register output to debug level.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jon Maloy says:

====================
tipc: fix link failover/synch problems

We fix three problems with the new link failover/synch implementation,
which was introduced earlier in this release cycle. They are all related
to situations where there is a very short interval between the disabling
and enabling of interfaces.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>