The function tipc_msg_init() has turned out to be of limited value
in many cases. It take too few parameters to be usable for creating
a complete message, it makes too many assumptions about what the
message should be used for, and it does not allocate any buffer to
be returned to the caller.

Therefore, we now introduce the new function tipc_msg_create(), which
takes all the parameters needed to create a full message, and returns
a buffer of the requested size. The new function will be very useful
for the changes we will be doing in later commits in this series.
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pulling to get some TIPC fixes that a net-next series depends
upon.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Upon timeout, undo (via both timestamps/Eifel and DSACKs) was
disabled if any retransmits were still in flight.  The concern was
perhaps that spurious retransmission sent in a previous recovery
episode may trigger DSACKs to falsely undo the current recovery.

However, this inadvertently misses undo opportunities (using either
TCP timestamps or DSACKs) when timeout occurs during a loss episode,
i.e.  recurring timeouts or timeout during fast recovery. In these
cases some retransmissions will be in flight but we should allow
undo. Furthermore, we should only reset undo_marker and undo_retrans
upon timeout if we are starting a new recovery episode. Finally,
when we do reset our undo state, we now do so in a manner similar
to tcp_enter_recovery(), so that we require a DSACK for each of
the outstsanding retransmissions. This will achieve the original
goal by requiring that we receive the same number of DSACKs as
retransmissions.

This patch increases the undo events by 50% on Google servers.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bare register numbers are used despite <uapi/linux/mdio.h> has MDIO_DEVS[12]
#define'd for those.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As a followup to commit 676d2369 ("net: Fix use after free by
removing length arg from sk_data_ready callbacks"), we can remove
some useless code in sock_queue_rcv_skb() and rxrpc_queue_rcv_skb()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ktime_get_ns() replaces ktime_to_ns(ktime_get())

ktime_get_real_ns() replaces ktime_to_ns(ktime_get_real())
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The first initializer in the following

        union vxlan_addr ipa = {
            .sin.sin_addr.s_addr = tip,
            .sa.sa_family = AF_INET,
        };

is optimised away by the compiler, due to the second initializer,
therefore initialising .sin.sin_addr.s_addr always to 0.
This results in netlink messages indicating a L3 miss never contain the
missed IP address. This was observed with GCC 4.8 and 4.9. I do not know about previous versions.
The problem affects user space programs relying on an IP address being
sent as part of a netlink message indicating a L3 miss.

Changing
            .sa.sa_family = AF_INET,
to
            .sin.sin_family = AF_INET,
fixes the problem.
Signed-off-by: NGerhard Stenzel <gerhard.stenzel@de.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Marc Kleine-Budde says:

====================
pull-request: can-next 2014-08-20

this is a pull request of 10 patches for net-next/master.

There is one patch by Wolfram Sang to clean up the build system.
Two patches by Stefan Agner that add vf610 support to the flexcan
driver. Dong Aisheng add support for bosch's m_can core, which is found
in the new freescale ARM SoCs. Sergei Shtylyov improves the rcar_can
driver by supporting all input clocks and adding device tree support.
The next patch is a small cleanup for the bit rate calculation function
by Lad, Prabhakar. And finally a patch by Himangi Saraogi, which
converts the mcp251x driver to use dmam_alloc_coherent.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge tag 'pwm/for-3.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm

Pull pwm fix from Thierry Reding:
 "Just one bugfix for the PWM lookup table code that would cause a PWM
  channel to be set to the wrong period and polarity for non-perfect
  matches"

* tag 'pwm/for-3.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm:
  pwm: Fix period and polarity in pwm_get() for non-perfect matches

The new_ctx pointer is set only for non-chanctx drivers.  This yielded a
crash for chanctx-based drivers during channel switch finalization:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
  IP: ieee80211_vif_use_reserved_switch+0x71c/0xb00 [mac80211]

Use an adequate chanctx pointer to fix this.
Reported-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NMichal Kazior <michal.kazior@tieto.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Pull networking fixes from David Miller:
 "Here are some bug fixes that have piled up during ksummit/linuxcon.

   1) Fix endian problems in ibmveth, from Anton Blanchard.

   2) IPV6 routing code does GFP_KERNEL allocation in atomic, fix from
      Benjamin Block.

   3) SCTP association fixes from Daniel Borkmann.

   4) When multiple VLAN headers are present we have to make sure the
      second and subsequent ones are pullable in the SKB otherwise we
      blindly dereference garbage.  From Jiri Benc.

   5) The argument adjustment of the signature of hlist_add_after*()
      introduced a regression in the batman-adv code, fix from Sven
      Eckelmann.

   6) Fix TX hang handling to avoid a panic in i40e, from Anjali Singhai
      Jain.

   7) PTP flag test is inverted in i40e driver, from Jesse Brandeburg.

   8) ATM LEC driver needs to hold RTNL mutex over MTU changes, from
      Chas Williams.

   9) Truncate packets larger then the TPACKET_V3 format configured
      buffers, otherwise we overwrite past the end of said buffers.
      From Eric Dumazet.

  10) Fix endianness bugs in qlcnic firmware handling, from Rajesh
      Borundia and Shahed Shaikh.

  11) CXGB4 sometimes doesn't get all of the TX completion events it
      should resulting in SKBs getting stuck in the TX queue, from
      Hariprasad Shenai.

  12) When the FEC chip's PTP clock is disabled, you can't access the
      register.  Add necessary checks to avoid the resulting hang, from
      Fugang Duan"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (37 commits)
  drivers: isdn: eicon: xdi_msg.h: Fix typo in #ifndef
  net: sctp: fix suboptimal edge-case on non-active active/retrans path selection
  net: sctp: spare unnecessary comparison in sctp_trans_elect_best
  net: ethernet: broadcom: bnx2x: Remove redundant #ifdef
  ibmveth: Fix endian issues with rx_no_buffer statistic
  net: xgene: fix possible NULL dereference in xgene_enet_free_desc_rings()
  openvswitch: fix panic with multiple vlan headers
  net: ipv6: fib: don't sleep inside atomic lock
  net: fec: ptp: avoid register access when ipg clock is disabled
  cxgb4: Free completed tx skbs promptly
  cxgb4: Fix race condition in cleanup
  sctp: not send SCTP_PEER_ADDR_CHANGE notifications with failed probe
  bnx2x: Revert UNDI flushing mechanism
  qlcnic: Fix endianess issue in firmware load from file operation
  qlcnic: Fix endianess issue in FW dump template header
  qlcnic: Fix flash access interface to application
  MAINTAINERS: Add section for MRF24J40 IEEE 802.15.4 radio driver
  macvlan: Allow setting multicast filter on all macvlan types
  packet: handle too big packets for PACKET_V3
  MAINTAINERS: add entry for ec_bhf driver
  ...

Event timestamp status messages have a variable length, ranging from
1 to 5 words (16 bit words). The current code however requires
a minimum message length of sizeof(*phy_txts). In most cases this
condition is fulfilled due to padding bytes. However, if several events
are signaled in a single message, padding bytes may not be present.
For short event timestamp status messages, the length check will fail,
and the event timestamp will be dropped.
Signed-off-by: NChristian Riesch <christian.riesch@omicron.at>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds fix_mac_speed() support for
Altera socfpga Ethernet controller. Emac splitter is a
soft IP core in FPGA system that converts GMII interface from
Synopsys mac to RGMII/SGMII interface. This splitter core is
an optional IP if user would like to use RGMII/SGMII
interface in their system. Software needs to update a register
in splitter core when there is speed change.
Signed-off-by: NLey Foon Tan <lftan@altera.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RTL8168H is Realtek PCIe Gigabit Ethernet controller.
RTL8107E is Realtek PCIe Fast Ethernet controller.

This patch add support for these two chips.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Userspace needs to be notified if one changes some option.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Acked-by: NVeaceslav Falico <vfalico@gmail.com>
Acked-by: NAndy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Yuval Mintz says:

====================
bnx2x: Start utilizing 7.10.51

This series will enable bnx2x to start utlizing its 7.10.51 FW.
In addition, it will also add timestamping support, as well as a couple
of routine semantic cleanups.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is mostly a semantic change which modifies the code parsing and printing
of FW asserts.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prevent dereference of pointer in case it's NULL.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Trying to disable sriov when VFs are assigned may lead to all kinds of problems.
This patch unifies the call in the driver to pci_disable_sriov() and prevents
them if some of the PF's child VFs are marked as assigned.

[Notice this is a bad scenario either way; User should not reach a point where
the OS tries to disable SRIOV when a VF is assigned - but currently there's no
way of preventing the user from doing so, and the ill-effect for the driver is
smaller this way]
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It's possible there's a bad chip configuration which will result with
PCIe IOV capabilities, but with no available interrupts for VFs.

In such case, we want to gracefully prevent the PF from initializing its
IOV capabilities rather than encounter difficulties further along the way.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bnx2x panic dump spills a lot of information from the driver's
fastpath, but may be called while some of the fastpath is uninitialized.

This patch verifies that pointers are already allocated before dereferencing
them to prevent possible kernel panics.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch does several semantic things:
  - Fixing typos.
  - Removing unnecessary prints.
  - Removing unused functions and definitions.
  - Change 'strange' usage of boolean variables.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds a PHC to the bnx2x driver. Driver supports timestamping send/receive
PTP packets, as well as adjusting the on-chip clock.

The driver has been tested with linuxptp project.
Signed-off-by: NMichal Kalderon <Michal.Kalderon@qlogic.com>
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

 - (L2) In some multi-function configurations, inter-PF and inter-VF
   Tx switching is incorrectly enabled.

 - (L2) Wrong assert code in FLR final cleanup in case it is sent not
   after FLR.

 - (L2) Chip may stall in very rare cases under heavy traffic with FW GRO
   enabled.

 - (L2) VF malicious notification error fixes.

 - (L2) Default gre tunnel to IPGRE which allows proper RSS for IPGRE packets,
   L2GRE traffic will reach single queue.

 - (FCoE) Fix data being placed in wrong buffer when corrupt FCoE frame is
   received.

 - (FCoE) Burst of FIP packets with destination MAC of ALL-FCF_MACs
   causes FCoE traffic to stop.
Signed-off-by: NDmitry Kravkov <Dmitry.Kravkov@qlogic.com>
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the Coccinelle semantic patch making this change
is as follows:

@change@
expression E1,E2,E3;
@@
- jiffies - E1 >= (E2*E3)
+ time_after_eq(jiffies, E1+E2*E3)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the Coccinelle semantic patch making this change
is as follows:

@change@
expression E1,E2;
@@
- (jiffies - E1) >= E2
+ time_after_eq(jiffies, E1+E2)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the Coccinelle semantic patch making this change
is as follows:

@change@
expression E1,E2;
@@
- jiffies - E1 < E2
+ time_before(jiffies, E1+E2)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the Coccinelle semantic patch making this change
is as follows:

@change@
expression E1,E2;
@@

(
- (jiffies - E1) < E2
+ time_before(jiffies, E1+E2)
)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The use of "rcu_assign_pointer()" is NULLing out the pointer.
According to RCU_INIT_POINTER()'s block comment:
"1.   This use of RCU_INIT_POINTER() is NULLing out the pointer"
it is better to use it instead of rcu_assign_pointer() because it has a
smaller overhead.

The following Coccinelle semantic patch was used:
@@
@@

- rcu_assign_pointer
+ RCU_INIT_POINTER
  (..., NULL)
Signed-off-by: NAndreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The "rcu_dereference()" call is used directly in a condition.
Since its return value is never dereferenced it is recommended to use
"rcu_access_pointer()" instead of "rcu_dereference()".
Therefore, this patch makes the replacement.

The following Coccinelle semantic patch was used:
@@
@@

(
 if(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
|
 while(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
)
Signed-off-by: NAndreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The "rcu_dereference()" call is used directly in a condition.
Since its return value is never dereferenced it is recommended to use
"rcu_access_pointer()" instead of "rcu_dereference()".
Therefore, this patch makes the replacement.

The following Coccinelle semantic patch was used:
@@
@@

(
 if(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
|
 while(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
)
Signed-off-by: NAndreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This "rcu_dereference()" call is used directly in a condition.
Since its return value is never dereferenced it is recommended to use
"rcu_access_pointer()" instead of "rcu_dereference()".
Therefore, this patch makes this replacement.

The following Coccinelle semantic patch was used for solving it:
@@
@@

(
 if(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
 ...+>)) {...}
|
 while(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
)
Signed-off-by: NAndreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The "rcu_dereference()" calls are used directly in conditions.
Since their return values are never dereferenced it is recommended to use
"rcu_access_pointer()" instead of "rcu_dereference()".
Therefore, this patch makes the replacements.

The following Coccinelle semantic patch was used:
@@
@@

(
 if(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
|
 while(
 (<+...
- rcu_dereference
+ rcu_access_pointer
  (...)
  ...+>)) {...}
)
Signed-off-by: NAndreea-Cristina Bernat <bernat.ada@gmail.com>
Acked-by: NMichael Chan <mchan@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 7a9bc9b8 ("ipv4: Elide fib_validate_source() completely when possible.")
introduced a short-circuit to avoid calling fib_validate_source when not
needed. That change took rp_filter into account, but not accept_local.
This resulted in a change of behaviour: with rp_filter and accept_local
off, incoming packets with a local address in the source field should be
dropped.

Here is how to reproduce the change pre/post 7a9bc9b8 commit:
-configure the same IPv4 address on hosts A and B.
-try to send an ARP request from B to A.
-The ARP request will be dropped before that commit, but accepted and answered
after that commit.

This adds a check for ACCEPT_LOCAL, to maintain full
fib validation in case it is 0. We also leave __fib_validate_source() earlier
when possible, based on the same check as fib_validate_source(), once the
accept_local stuff is verified.

Cc: Gregory Detal <gregory.detal@uclouvain.be>
Cc: Christoph Paasch <christoph.paasch@uclouvain.be>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NSébastien Barré <sebastien.barre@uclouvain.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces the use of the function usb_endpoint_num.

The Coccinelle semantic patch that makes these changes is as follows:

@@ struct usb_endpoint_descriptor *epd; @@

- (epd->bEndpointAddress & \(USB_ENDPOINT_NUMBER_MASK\|0x0f\))
+ usb_endpoint_num(epd)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Acked-by: NTilman Schmidt <tilman@imap.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces the use of the function usb_endpoint_num.

The Coccinelle semantic patch that makes these changes is as follows:

@@ struct usb_endpoint_descriptor *epd; @@

- (epd->bEndpointAddress & \(USB_ENDPOINT_NUMBER_MASK\|0x0f\))
+ usb_endpoint_num(epd)
Signed-off-by: NHimangi Saraogi <himangi774@gmail.com>
Acked-by: NJulia Lawall <julia.lawall@lip6.fr>
Acked-by: NTilman Schmidt <tilman@imap.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the buffer is too small for a packet from VMBus, a bigger buffer will be
allocated in netvsc_channel_cb() and retry reading the packet from VMBus.
Increasing this buffer size will reduce the retry overhead.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NDexuan Cui <decui@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Test for definedness of the macro which is actually defined (the
change is hard to see: it is s/SSS/SSA/).
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In SCTP, selection of active (T.ACT) and retransmission (T.RET)
transports is being done whenever transport control operations
(UP, DOWN, PF, ...) are engaged through sctp_assoc_control_transport().

Commits 4c47af4d ("net: sctp: rework multihoming retransmission
path selection to rfc4960") and a7288c4d ("net: sctp: improve
sctp_select_active_and_retran_path selection") have both improved
it towards a more fine-grained and optimal path selection.

Currently, the selection algorithm for T.ACT and T.RET is as follows:

1) Elect the two most recently used ACTIVE transports T1, T2 for
   T.ACT, T.RET, where T.ACT<-T1 and T1 is most recently used
2) In case primary path T.PRI not in {T1, T2} but ACTIVE, set
   T.ACT<-T.PRI and T.RET<-T1
3) If only T1 is ACTIVE from the set, set T.ACT<-T1 and T.RET<-T1
4) If none is ACTIVE, set T.ACT<-best(T.PRI, T.RET, T3) where
   T3 is the most recently used (if avail) in PF, set T.RET<-T.PRI

Prior to above commits, 4) was simply a camp on T.ACT<-T.PRI and
T.RET<-T.PRI, ignoring possible paths in PF. Camping on T.PRI is
still slightly suboptimal as it can lead to the following scenario:

Setup:
        <A>                                <B>
    T1: p1p1 (10.0.10.10) <==>  .'`)  <==> p1p1 (10.0.10.12)  <= T.PRI
    T2: p1p2 (10.0.10.20) <==> (_ . ) <==> p1p2 (10.0.10.22)

    net.sctp.rto_min = 1000
    net.sctp.path_max_retrans = 2
    net.sctp.pf_retrans = 0
    net.sctp.hb_interval = 1000

T.PRI is permanently down, T2 is put briefly into PF state (e.g. due to
link flapping). Here, the first time transmission is sent over PF path
T2 as it's the only non-INACTIVE path, but the retransmitted data-chunks
are sent over the INACTIVE path T1 (T.PRI), which is not good.

After the patch, it's choosing better transports in both cases by
modifying step 4):

4) If none is ACTIVE, set T.ACT_new<-best(T.ACT_old, T3) where T3 is
   the most recently used (if avail) in PF, set T.RET<-T.ACT_new

This will still select a best possible path in PF if available (which
can also include T.PRI/T.RET), and set both T.ACT/T.RET to it.

In case sctp_assoc_control_transport() *just* put T.ACT_old into INACTIVE
as it transitioned from ACTIVE->PF->INACTIVE and stays in INACTIVE just
for a very short while before going back ACTIVE, it will guarantee that
this path will be reselected for T.ACT/T.RET since T3 (PF) is not
available.

Previously, this was not possible, as we would only select between T.PRI
and T.RET, and a possible T3 would be NULL due to the fact that we have
just transitioned T3 in sctp_assoc_control_transport() from PF->INACTIVE
and would select a suboptimal path when T.PRI/T.RET have worse properties.

In the case that T.ACT_old permanently went to INACTIVE during this
transition and there's no PF path available, plus T.PRI and T.RET are
INACTIVE as well, we would now camp on T.ACT_old, but if everything is
being INACTIVE there's really not much we can do except hoping for a
successful HB to bring one of the transports back up again and, thus
cause a new selection through sctp_assoc_control_transport().

Now both tests work fine:

Case 1:

 1. T1 S(ACTIVE) T.ACT
    T2 S(ACTIVE) T.RET

 2. T1 S(ACTIVE) T.ACT, T.RET
    T2 S(PF)

 3. T1 S(ACTIVE) T.ACT, T.RET
    T2 S(INACTIVE)

 5. T1 S(PF) T.ACT, T.RET
    T2 S(INACTIVE)

[ 5.1 T1 S(INACTIVE) T.ACT, T.RET
      T2 S(INACTIVE) ]

 6. T1 S(ACTIVE) T.ACT, T.RET
    T2 S(INACTIVE)

 7. T1 S(ACTIVE) T.ACT
    T2 S(ACTIVE) T.RET

Case 2:

 1. T1 S(ACTIVE) T.ACT
    T2 S(ACTIVE) T.RET

 2. T1 S(PF)
    T2 S(ACTIVE) T.ACT, T.RET

 3. T1 S(INACTIVE)
    T2 S(ACTIVE) T.ACT, T.RET

 5. T1 S(INACTIVE)
    T2 S(PF) T.ACT, T.RET

[ 5.1 T1 S(INACTIVE)
      T2 S(INACTIVE) T.ACT, T.RET ]

 6. T1 S(INACTIVE)
    T2 S(ACTIVE) T.ACT, T.RET

 7. T1 S(ACTIVE) T.ACT
    T2 S(ACTIVE) T.RET
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Acked-by: NVlad Yasevich <vyasevich@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>