In function sctp_select_active_and_retran_path(), we walk the
transport list in order to look for the two most recently used
ACTIVE transports (trans_pri, trans_sec). In case we didn't find
anything ACTIVE, we currently just camp on a possibly PF or
INACTIVE transport that is primary path; this behavior actually
dates back to linux-history tree of the very early days of
lksctp, and can yield a behavior that chooses suboptimal
transport paths.

Instead, be a bit more clever by reusing and extending the
recently introduced sctp_trans_elect_best() handler. In case
both transports are evaluated to have the same score resulting
from their states, break the tie by looking at: 1) transport
patch error count 2) last_time_heard value from each transport.

This is analogous to Nishida's Quick Failover draft [1],
section 5.1, 3:

  The sender SHOULD avoid data transmission to PF destinations.
  When all destinations are in either PF or Inactive state,
  the sender MAY either move the destination from PF to active
  state (and transmit data to the active destination) or the
  sender MAY transmit data to a PF destination. In the former
  scenario, (i) the sender MUST NOT notify the ULP about the
  state transition, and (ii) MUST NOT clear the destination's
  error counter. It is recommended that the sender picks the
  PF destination with least error count (fewest consecutive
  timeouts) for data transmission. In case of a tie (multiple PF
  destinations with same error count), the sender MAY choose the
  last active destination.

Thus for sctp_select_active_and_retran_path(), we keep track of
the best, if any, transport that is in PF state and in case no
ACTIVE transport has been found (hence trans_{pri,sec} is NULL),
we select the best out of the three: current primary_path and
retran_path as well as a possible PF transport.

The secondary may still camp on the original primary_path as
before. The change in sctp_trans_elect_best() with a more fine
grained tie selection also improves at the same time path selection
for sctp_assoc_update_retran_path() in case of non-ACTIVE states.

  [1] http://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Be more precise in transport path selection and use ktime
helpers instead of jiffies to compare and pick the better
primary and secondary recently used transports. This also
avoids any side-effects during a possible roll-over, and
could lead to better path decision-making.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch just refactors and moves the code for the active
path selection into its own helper function outside of
sctp_assoc_control_transport() which is already big enough.
No functional changes here.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add two minimal helper functions analogous to time_before() and
time_after() that will later on both be needed by SCTP code.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Phoebe Buckheister says:

====================
Recent llsec code introduced a memory leak on decryption failures during rx.
This fixes said leak, and optimizes the receive loops for monitor and wpan
devices to only deliver skbs to devices that are actually up. Also changes a
dev_kfree_skb to kfree_skb when an invalid packet is dropped before being
pushed into the stack.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Only one WPAN devices can be active at any given time, so only deliver
packets to that one interface that is actually up. Multiple monitors may
be up at any given time, but we don't have to deliver to monitors that
are down either.
Signed-off-by: NPhoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mac802154 RX did not free skbs on decryption failure, assuming that the
caller would when the local rx handler returned _DROP. This was false.
Signed-off-by: NPhoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MAX_DMA_CHANNELS is defined in asm/scatterlist.h of the powerpc
architecture.  Rename this #define in xgbe.h to avoid the
redefined warning issued during compilation.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use dma_addr_t for DMA address parameters and u32 for shared memory
offset parameters.

Do not assume that dma_addr_t is the same as unsigned long; it will
not be in PAE configurations.  Truncate DMA addresses to 32 bits when
printing them.  This is OK because the DMA mask for this device is
32-bit (per default).

Also rename the DMA address parameters from 'skb' to 'dma'.

Compile-tested only.
Signed-off-by: NBen Hutchings <ben@decadent.org.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Or Gerlitz says:

====================
mlx4 SRIOV fixes

The patch from Wei Yang is a designed fix to a regression introduced by earlier commit
of him. Jack added a fix to the resource management which we got from IBM.

Let's get that into 3.16-rc1 1st and later see to what stable version/s this should go.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Following commit befdf897 "net/mlx4_core: Preserve pci_dev_data after
__mlx4_remove_one()", there are two mlx4 pci callbacks which will
attempt to release the mlx4_priv object -- .shutdown and .remove.

This leads to a use-after-free access to the already freed mlx4_priv
instance and trigger a "Kernel access of bad area" crash when both
.shutdown and .remove are called.

During reboot or kexec, .shutdown is called, with the VFs probed to
the host going through shutdown first and then the PF. Later, the PF
will trigger VFs' .remove since VFs still have driver attached.

Fix that by keeping only one driver entry which releases mlx4_priv.

Fixes: befdf897 ('net/mlx4_core: Preserve pci_dev_data after __mlx4_remove_one()')
CC: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NWei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Hypervisor driver tracks free slots and reserved slots at the global level
and tracks allocated slots and guaranteed slots per VF.

Guaranteed slots are treated as reserved by the driver, so the total
reserved slots is the sum of all guaranteed slots over all the VFs.

As VFs allocate resources, free (global) is decremented and allocated (per VF)
is incremented for those resources. However, reserved (global) is never changed.

This means that effectively, when a VF allocates a resource from its
guaranteed pool, it is actually reducing that resource's free pool (since
the global reserved count was not also reduced).

The fix for this problem is the following: For each resource, as long as a
VF's allocated count is <= its guaranteed number, when allocating for that
VF, the reserved count (global) should be reduced by the allocation as well.

When the global reserved count reaches zero, the remaining global free count
is still accessible as the free pool for that resource.

When the VF frees resources, the reverse happens: the global reserved count
for a resource is incremented only once the VFs allocated number falls below
its guaranteed number.

This fix was developed by Rick Kready <kready@us.ibm.com>
Reported-by: NRick Kready <kready@us.ibm.com>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Logical conjunction always evaluates to false:  minor < 2 && minor > 1
I guess what you wanted is rather: minor > 2 || minor < 1

This was partly found using a static code analysis program called cppcheck.
Signed-off-by: NRickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A check on a memory allocation is checked incorrectly.

This was partly found using a static code analysis program called cppcheck.
Signed-off-by: NRickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Acked-by: NGeoff Levand <geoff@infradead.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix following compilation warning:
[...]
  CC      drivers/net/phy/amd-xgbe-phy.o
drivers/net/phy/amd-xgbe-phy.c:1353:30: warning:
‘amd_xgbe_phy_ids’ defined but not used [-Wunused-variable]
 static struct mdio_device_id amd_xgbe_phy_ids[] = {
                              ^
Signed-off-by: NFrancois Romieu <romieu@fr.zoreil.com>
Acked-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- 'struct nlattr' must be 2 byte aligned
- provide big-endian input data for nlattr/nlattr_nest tests
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Acked-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The macro 'A' used in internal BPF interpreter:
 #define A regs[insn->a_reg]
was easily confused with the name of classic BPF register 'A', since
'A' would mean two different things depending on context.

This patch is trying to clean up the naming and clarify its usage in the
following way:

- A and X are names of two classic BPF registers

- BPF_REG_A denotes internal BPF register R0 used to map classic register A
  in internal BPF programs generated from classic

- BPF_REG_X denotes internal BPF register R7 used to map classic register X
  in internal BPF programs generated from classic

- internal BPF instruction format:
struct sock_filter_int {
        __u8    code;           /* opcode */
        __u8    dst_reg:4;      /* dest register */
        __u8    src_reg:4;      /* source register */
        __s16   off;            /* signed offset */
        __s32   imm;            /* signed immediate constant */
};

- BPF_X/BPF_K is 1 bit used to encode source operand of instruction
In classic:
  BPF_X - means use register X as source operand
  BPF_K - means use 32-bit immediate as source operand
In internal:
  BPF_X - means use 'src_reg' register as source operand
  BPF_K - means use 32-bit immediate as source operand
Suggested-by: NChema Gonzalez <chema@google.com>
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Acked-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NChema Gonzalez <chema@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Linus Lüssing says:

====================
bridge: multicast snooping patches / exports

The first patch is simply a cosmetic patch. So far I (and maybe others
too?) have been regularly confusing these two structs, therefore I'd
suggest renaming them and therefore making the follow-up patches easier
to understand and nicer to fit in.

The second patch fixes a minor issue, but probably not worth for stable.

On the other hand the first two patches are also preparations for the
third and fourth patch:

These two patches are exporting functionality needed to marry the bridge
multicast snooping with the batman-adv multicast optimizations recently
added for the 3.15 kernel, allowing to use these optimzations in common
setups having a bridge on top of e.g. bat0, too. So far these bridged
setups would fall back to simple flooding through the batman-adv mesh
network for any multicast packet entering bat0.

More information about the batman-adv multicast optimizations currently
implemented can be found here:

http://www.open-mesh.org/projects/batman-adv/wiki/Basic-multicast-optimizations

The integration on the batman-adv side could afterwards look like this,
for instance:

http://git.open-mesh.org/batman-adv.git/commitdiff/576b59dd3e34737c702e548b21fa72059262f796?hp=f95ce7131746c65fbcdffcf2089cab59e2c2f7ac
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding bridge support to the batman-adv multicast optimization requires
batman-adv knowing about the existence of bridged-in IGMP/MLD queriers
to be able to reliably serve any multicast listener behind this same
bridge.
Signed-off-by: NLinus Lüssing <linus.luessing@web.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With this new, exported function br_multicast_list_adjacent(net_dev) a
list of IPv4/6 addresses is returned. This list contains all multicast
addresses sensed by the bridge multicast snooping feature on all bridge
ports of the bridge interface of net_dev, excluding addresses from the
specified net_device itself.

Adding bridge support to the batman-adv multicast optimization requires
batman-adv knowing about the existence of bridged-in multicast
listeners to be able to reliably serve them with multicast packets.
Signed-off-by: NLinus Lüssing <linus.luessing@web.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MLDv1 (RFC2710 section 6), MLDv2 (RFC3810 section 7.6.2), IGMPv2
(RFC2236 section 3) and IGMPv3 (RFC3376 section 6.6.2) specify that the
querier with lowest source address shall become the selected
querier.

So far the bridge stopped its querier as soon as it heard another
querier regardless of its source address. This results in the "wrong"
querier potentially becoming the active querier or a potential,
unnecessary querying delay.

With this patch the bridge memorizes the source address of the currently
selected querier and ignores queries from queriers with a higher source
address than the currently selected one. This slight optimization is
supposed to make it more RFC compliant (but is rather uncritical and
therefore probably not necessary to be queued for stable kernels).
Signed-off-by: NLinus Lüssing <linus.luessing@web.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current naming of these two structs is very random, in that
reversing their naming would not make any semantical difference.

This patch tries to make the naming less confusing by giving them a more
specific, distinguishable naming.

This is also useful for the upcoming patches reintroducing the
"struct bridge_mcast_querier" but for storing information about the
selected querier (no matter if our own or a foreign querier).
Signed-off-by: NLinus Lüssing <linus.luessing@web.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Hariprasad Shenai says:

====================
Adds support for CIQ and other misc. fixes for rdma/cxgb4

This patch series adds support to allocate and use IQs specifically for
indirect interrupts, adds fixes to align ISS for iWARP connections & fixes
related to tcp snd/rvd window for Chelsio T4/T5 adapters on iw_cxgb4.
Also changes Interrupt Holdoff Packet Count threshold of response queues for
cxgb4 driver.

The patches series is created against 'net-next' tree.
And includes patches on cxgb4 and iw_cxgb4 driver.

Since this patch-series contains cxgb4 and iw_cxgb4 patches, we would like to
request this patch series to get merged via David Miller's 'net-next' tree.

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>

Based on original work by Casey Leedom <leedom@chelsio.com>
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixed a bug that shows up with recv window sizes that exceed the size of
the RCV_BUFSIZ field in opt0 (>= 1024K).  If the recv window exceeds
this, then we specify the max possible in opt0, add add the rest in via
a RX_DATA_ACK credits.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Select the appropriate hw mtu index and initial sequence number to optimize
hw memory performance.

Add new cxgb4_best_aligned_mtu() which allows callers to provide enough
information to be used to [possibly] select an MTU which will result in the
TCP Data Segment Size (AKA Maximum Segment Size) to be an aligned value.

If an RTR message exhange is required, then align the ISS to 8B - 1 + 4, so
that after the SYN the send seqno will align on a 4B boundary. The RTR
message exchange will leave the send seqno aligned on an 8B boundary.
If an RTR is not required, then align the ISS to 8B - 1.  The goal is
to have the send seqno be 8B aligned when we send the first FPDU.

Based on original work by Casey Leedom <leeedom@chelsio.com> and
Steve Wise <swise@opengridcomputing.com>
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently indirect interrupts for RDMA CQs funnel through the LLD's RDMA
RXQs, which also handle direct interrupts for offload CPLs during RDMA
connection setup/teardown.  The intended T4 usage model, however, is to
have indirect interrupts flow through dedicated IQs. IE not to mix
indirect interrupts with CPL messages in an IQ.  This patch adds the
concept of RDMA concentrator IQs, or CIQs, setup and maintained by the
LLD and exported to iw_cxgb4 for use when creating CQs. RDMA CPLs will
flow through the LLD's RDMA RXQs, and CQ interrupts flow through the
CIQs.

Design:

cxgb4 creates and exports an array of CIQs for the RDMA ULD.  These IQs
are sized according to the max available CQs available at adapter init.
In addition, these IQs don't need FL buffers since they only service
indirect interrupts.  One CIQ is setup per RX channel similar to the
RDMA RXQs.

iw_cxgb4 will utilize these CIQs based on the vector value passed into
create_cq().  The num_comp_vectors advertised by iw_cxgb4 will be the
number of CIQs configured, and thus the vector value will be the index
into the array of CIQs.

Based on original work by Steve Wise <swise@opengridcomputing.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to require forcing device down on a Ethernet GRE (gretap)
tunnel to change the MAC address.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_fragment can be called from process context (from tso_fragment).
Add a new gfp parameter to allow it to preserve atomic memory if
possible.
Signed-off-by: NOctavian Purdila <octavian.purdila@intel.com>
Reviewed-by: NChristoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-06-09

This series contains more updates to i40e and i40evf.

Shannon adds checks for error status bits on the admin event queue and
provides notification if seen.  Cleans up unused variable and memory
allocation which was used earlier in driver development and is no longer
needed.  Also fixes the driver to not complain about removing
non-existent MAC addresses.  Bumps the driver versions for both i40e
and i40evf.

Catherine fixes a function header comment to make sure the comment correctly
reflects the function name.

Mitch adds code to allow for additional VSIs since the number of VSIs that
the firmware reports to us is a guaranteed minimum, not an absolute
maximum.  The hardware actually supports for more than the reported value,
which we often need.  Implements anti-spoofing for VFs for both MAC
addresses and VLANs, as well as enable this feature by default for all VFs.

Anjali changes the interrupt distribution policy to change the way
resources for special features are handled.  Fixes the driver to not fall
back to one queue if the only feature enabled is ATR, since FD_SB
and FD_ATR need to be checked independently in order to decide if we
will support multiple queue or not.  Allows the RSS table entry range
and GPS to be any number, not necessarily a power of 2 because hardware
does not restrict us to use a power of 2 GPS in the case of RSS as long as
we are not sharing the RSS table with another VSI (VMDq).

Frank modifies the driver to keep SR-IOV enabled in the case that RSS,
VMFq, FD_SB and DCB are disabled so that SR-IOV does not get turned off
unnecessarily.

Jesse fixes a bug in receive checksum where the driver was not marking
packets with bad checksums correctly, especially IPv6 packets with a bad
checksum.  To do this correctly, we need a define that may be set by
hardware in rare cases.

Greg fixes the driver to delete all the old and stale MAC filters for the
VF VSI when the host administrator changes the VF MAC address from under
its feet.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bumpity and Fred Worm say it's time to change the numbers again.
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Change-ID: I658731d022ea23cedede4be2bfecd8b4cc68d270
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We tell the HW upper boundary of power of 2 in VSI config,
but the HW does not restrict us to use just power of 2 GPS in
case of RSS as long as we are not sharing the RSS table with
another VSI (VMDq). We at present are not doing RSS in VMDq
VSI.
If we were to enable that and if the system had CPU count which
was not power 2, the VMDq VSIs will see a little skewed distribution.

Change-ID: I3ea797ce9065a3ca4fc4d04251bf195463410473
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Delete all the old and stale MAC filters for the VF VSI when the host
administrator changes the VF MAC address from under its feet.  Also don't
bother to add a filter for the VSI when its going to go away anyway.
Just record the new address and punch the VF reset.

Change-ID: Ic0d12055926f41989d1965ccf500053729c063ad
Signed-off-by: NGreg Rose <gregory.v.rose@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

FD_SB and FD_ATR needs to be checked independently in order to decide if
we will support multiple queues or not.

Change-ID: I9d3274f5924c79e29efdbcf66a2fcca1fee2107f
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The driver was not marking packets with bad checksums
correctly, especially IPv6 packets with a bad checksum.
To do this correctly we need a define that may be set by
hardware in rare cases.

Change-ID: I1a997b72b491ded27a78ac3bce1197b2d2611130
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Modify the logic in i40e_determine_queue_usage() so that
SR-IOV doesn't get turned off unnecessarily.

Change-ID: I86ca304fa9f742a50e9ea831b887f358a6a9d53d
Signed-off-by: NFrank Zhang <frank_1.zhang@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch changes the way resources are distributed to special features.

Change-ID: I847e49d714a1d70e97f3f994cb39bfb5e02ab016
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Our hardware supports VF antispoofing for both MAC addresses and VLANs.
Enable this feature by default for all VFs and implement the netdev op
to control it from the command line.

Change-ID: Ifb941da22785848aa3aba6b2231be135b8ea8f31
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We don't need to complain in the log about mac addresses that
can't be deleted because they don't exist.

Change-ID: I4e6370df175bf72726f06d2206c03bcbfded8387
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This was a vestige of early driver development that no longer
has any actual use.

Change-ID: I95b5b19c4bbfaff8759197af671ebaf716cb6ab5
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>