Some Ethernet PHY devices/switches may not properly release the MDIO bus
during turn-around time, and fail to drive it low, which can be seen by
some controllers as a read failure, while the data clocked in is still
correct.

Add a boolean property "broken-turn-around" which is parsed by the
generic MDIO bus probing code and will set the corresponding bit in the
MDIO bus phy_ignore_ta_mask bitmask for MDIO bus drivers to utilize that
information.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some PHY devices/switches will not release the turn-around line as they
should do at the end of a MDIO transaction. To help with such
situations, allow MDIO bus drivers to be made aware of such
restrictions.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit eeb1bd5c ("net: Add a struct net parameter to
sock_create_kern"), we should use sock_create_kern() to create kernel
socket as the interface doesn't reference count struct net any more.
Signed-off-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix compile error in net/sched/cls_flower.c

    net/sched/cls_flower.c: In function ‘fl_set_key’:
    net/sched/cls_flower.c:240:3: error: implicit declaration of
     function ‘tcf_change_indev’ [-Werror=implicit-function-declaration]
       err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);

Introduced in 77b9900e

Fixes: 77b9900e ("tc: introduce Flower classifier")
Signed-off-by: NBrian Haley <brian.haley@hp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jon Maloy says:

====================
tipc: some link layer improvements

We continue eliminating redundant complexity at the link layer, and
add a couple of improvements to the packet sending functionality.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, the packet sequence number is updated and added to each
packet at the moment a packet is added to the link backlog queue.
This is wasteful, since it forces the code to traverse the send
packet list packet by packet when adding them to the backlog queue.
It would be better to just splice the whole packet list into the
backlog queue when that is the right action to do.

In this commit, we do this change. Also, since the sequence numbers
cannot now be assigned to the packets at the moment they are added
the backlog queue, we do instead calculate and add them at the moment
of transmission, when the backlog queue has to be traversed anyway.
We do this in the function tipc_link_push_packet().
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The link congestion algorithm used until now implies two problems.

- It is too generous towards lower-level messages in situations of high
  load by giving "absolute" bandwidth guarantees to the different
  priority levels. LOW traffic is guaranteed 10%, MEDIUM is guaranted
  20%, HIGH is guaranteed 30%, and CRITICAL is guaranteed 40% of the
  available bandwidth. But, in the absence of higher level traffic, the
  ratio between two distinct levels becomes unreasonable. E.g. if there
  is only LOW and MEDIUM traffic on a system, the former is guaranteed
  1/3 of the bandwidth, and the latter 2/3. This again means that if
  there is e.g. one LOW user and 10 MEDIUM users, the  former will have
  33.3% of the bandwidth, and the others will have to compete for the
  remainder, i.e. each will end up with 6.7% of the capacity.

- Packets of type MSG_BUNDLER are created at SYSTEM importance level,
  but only after the packets bundled into it have passed the congestion
  test for their own respective levels. Since bundled packets don't
  result in incrementing the level counter for their own importance,
  only occasionally for the SYSTEM level counter, they do in practice
  obtain SYSTEM level importance. Hence, the current implementation
  provides a gap in the congestion algorithm that in the worst case
  may lead to a link reset.

We now refine the congestion algorithm as follows:

- A message is accepted to the link backlog only if its own level
  counter, and all superior level counters, permit it.

- The importance of a created bundle packet is set according to its
  contents. A bundle packet created from messges at levels LOW to
  CRITICAL is given importance level CRITICAL, while a bundle created
  from a SYSTEM level message is given importance SYSTEM. In the latter
  case only subsequent SYSTEM level messages are allowed to be bundled
  into it.

This solves the first problem described above, by making the bandwidth
guarantee relative to the total number of users at all levels; only
the upper limit for each level remains absolute. In the example
described above, the single LOW user would use 1/11th of the bandwidth,
the same as each of the ten MEDIUM users, but he still has the same
guarantee against starvation as the latter ones.

The fix also solves the second problem. If the CRITICAL level is filled
up by bundle packets of that level, no lower level packets will be
accepted any more.
Suggested-by: NGergely Kiss <gergely.kiss@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We change the sequence number checkpointing that is performed
by the timer in order to discover if the peer is active. Currently,
we store a checkpoint of the next expected sequence number "rcv_nxt"
at each timer expiration, and compare it to the current expected
number at next timeout expiration. Instead, we now use the already
existing field "silent_intv_cnt" for this task. We step the counter
at each timeout expiration, and zero it at each valid received packet.
If no valid packet has been received from the peer after "abort_limit"
number of silent timer intervals, the link is declared faulty and reset.

We also remove the multiple instances of timer activation from inside
the FSM function "link_state_event()", and now do it at only one place;
at the end of the timer function itself.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We rename some fields in struct tipc_link, in order to give them more
descriptive names:

next_in_no -> rcv_nxt
next_out_no-> snd_nxt
fsm_msg_cnt-> silent_intv_cnt
cont_intv  -> keepalive_intv
last_retransmitted -> last_retransm

There are no functional changes in this commit.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Although the sequence number in the TIPC protocol is 16 bits, we have
until now stored it internally as an unsigned 32 bits integer.
We got around this by always doing explicit modulo-65535 operations
whenever we need to access a sequence number.

We now make the incoming and outgoing sequence numbers to unsigned
16-bit integers, and remove the modulo operations where applicable.

We also move the arithmetic inline functions for 16 bit integers
to core.h, and the function buf_seqno() to msg.h, so they can easily
be accessed from anywhere in the code.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we try to add new inline functions in the code, we sometimes
run into circular include dependencies.

The main problem is that the file core.h, which really should be at
the root of the dependency chain, instead is a leaf. I.e., core.h
includes a number of header files that themselves should be allowed
to include core.h. In reality this is unnecessary, because core.h does
not need to know the full signature of any of the structs it refers to,
only their type declaration.

In this commit, we remove all dependencies from core.h towards any
other tipc header file.

As a consequence of this change, we can now move the function
tipc_own_addr(net) from addr.c to addr.h, and make it inline.

There are no functional changes in this commit.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prior to this commit, the link timer has been running at a "continuity
interval" of configured link tolerance/4. When a timer wakes up and
discovers that there has been no sign of life from the peer during the
previous interval, it divides its own timer interval by another factor
four, and starts sending one probe per new interval. When the configured
link tolerance time has passed without answer, i.e. after 16 unacked
probes, the link is declared faulty and reset.

This is unnecessary complex. It is sufficient to continue with the
original continuity interval, and instead reset the link after four
missed probe responses. This makes the timer handling in the link
simpler, and opens up for some planned later changes in this area.
This commit implements this change.
Reviewed-by: NRichard Alpe <richard.alpe@ericsson.com>
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since commit 4b475e3f2f8e4e241de101c8240f1d74d0470494
("tipc: eliminate delayed link deletion at link failover") the extra
boolean parameter "shutting_down" is not any longer needed for the
functions bearer_disable() and tipc_link_delete_list().

Furhermore, the function tipc_link_reset_links(), called from
bearer_reset()  is now unnecessary. We can just as well delete
all the links, as we do in bearer_disable(), and start over with
creating new links.

This commit introduces those changes.
Reviewed-by: NErik Hugne <erik.hugne@ericsson.com>
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Venkat Duvvuru says:

====================
be2net: patch-set

The following patch set has one new feature addition and two fixes.

Patch 1 adds support for hwmon sysfs interface to display board temperature.
Board temperature display through ethtool statistics is removed.

Patch 2 reports "link down" in a few more error cases which are not handled
currently.

Patch 3 adds support for os2bmc. OS2BMC feature will allow the server to
communicate with the on-board BMC/idrac (Baseboard Management Controller)
over the LOM via standard Ethernet. More details are added in the commit log.

Please review.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OS2BMC feature will allow the server to communicate with the on-board
BMC/idrac (Baseboard Management Controller) over the LOM via
standard Ethernet.

When OS2BMC feature is enabled, the LOM will filter traffic coming
from the host. If the destination MAC address matches the iDRAC MAC
address, it will forward the packet to the NC-SI side band interface
for iDRAC processing. Otherwise, it would send it out on the wire to
the external network. Broadcast and multicast packets are sent on the
side-band NC-SI channel and on the wire as well. Some of the packet
filters are not supported in the NIC and hence driver will identify
such packets and will hint the NIC to send those packets to the BMC.
This is done by duplicating packets on the management ring. Packets
are sent to the management ring, by setting mgmt bit in the wrb header.
The NIC will forward the packets on the management ring to the BMC
through the side-band NC-SI channel.

Please refer to this online document for more details,
http://www.dell.com/downloads/global/products/pedge/
os_to_bmc_passthrough_a_new_chapter_in_system_management.pdf
Signed-off-by: NVenkat Duvvuru <VenkatKumar.Duvvuru@Emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When an error (related to HW or FW) is detected on a function, the driver
must pro-actively report a "link down" to the stack so that a possible
failover can be initiated. This is being done currently only for some
HW errors. This patch reports a "link down" even for fatal FW errors and
EEH errors.
Signed-off-by: NVenkat Duvvuru <VenkatKumar.Duvvuru@Emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ethtool statistics is not the right place to display board temperature.
This patch adds support to export die temperature of devices supported
by be2net driver via the sysfs hwmon interface.
Signed-off-by: NVenkat Duvvuru <VenkatKumar.Duvvuru@Emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pablo Neira Ayuso says:

====================
Netfilter ingress support (v4)

This is the v4 round of patches to add the Netfilter ingress hook, it basically
comes in two steps:

1) Add the CONFIG_NET_INGRESS switch to wrap the ingress static key around it.
   The idea is to use the same global static key to avoid adding more code to
   the hot path.

2) Add the Netfilter ingress hook after the tc ingress hook, under the global
   ingress_needed static key. As I said, the netfilter ingress hook also has
   its own static key, that is nested under the global static key. Please, see
   patch 5/5 for performance numbers and more information.

I originally started this next round, as it was suggested, exploring the
independent static key for netfilter ingress just after tc ingress, but the
results that I gathered from that patch are not good for non-users:

Result: OK: 6425927(c6425843+d83) usec, 100000000 (60byte,0frags)
  15561955pps 7469Mb/sec (7469738400bps) errors: 100000000

this roughly means 500Kpps less performance wrt. the base numbers, so that's
the reason why I discarded that approach and I focused on this.

The idea of this patchset is to open the window to nf_tables, which comes with
features that will work out-of-the-box (once the boiler plate code to support
the 'netdev' table family is in place), to avoid repeating myself [1], the most
relevant features are:

1) Multi-dimensional key dictionary lookups.
2) Arbitrary stateful flow tables.
3) Transactions and good support for dynamic updates.

But there are also interest aspects to consider from userspace, such as the
ability to support new layer 2 protocols without kernel updates, a well-defined
netlink interface, userspace libraries and utilities for third party
applications, among others.

I hope we can be happy with this approach.

Please, apply. Thanks.

[1] http://marc.info/?l=netfilter-devel&m=143033337020328&w=2
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds the Netfilter ingress hook just after the existing tc ingress
hook, that seems to be the consensus solution for this.

Note that the Netfilter hook resides under the global static key that enables
ingress filtering. Nonetheless, Netfilter still also has its own static key for
minimal impact on the existing handle_ing().

* Without this patch:

Result: OK: 6216490(c6216338+d152) usec, 100000000 (60byte,0frags)
  16086246pps 7721Mb/sec (7721398080bps) errors: 100000000

    42.46%  kpktgend_0   [kernel.kallsyms]   [k] __netif_receive_skb_core
    25.92%  kpktgend_0   [kernel.kallsyms]   [k] kfree_skb
     7.81%  kpktgend_0   [pktgen]            [k] pktgen_thread_worker
     5.62%  kpktgend_0   [kernel.kallsyms]   [k] ip_rcv
     2.70%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_internal
     2.34%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_sk
     1.44%  kpktgend_0   [kernel.kallsyms]   [k] __build_skb

* With this patch:

Result: OK: 6214833(c6214731+d101) usec, 100000000 (60byte,0frags)
  16090536pps 7723Mb/sec (7723457280bps) errors: 100000000

    41.23%  kpktgend_0      [kernel.kallsyms]  [k] __netif_receive_skb_core
    26.57%  kpktgend_0      [kernel.kallsyms]  [k] kfree_skb
     7.72%  kpktgend_0      [pktgen]           [k] pktgen_thread_worker
     5.55%  kpktgend_0      [kernel.kallsyms]  [k] ip_rcv
     2.78%  kpktgend_0      [kernel.kallsyms]  [k] netif_receive_skb_internal
     2.06%  kpktgend_0      [kernel.kallsyms]  [k] netif_receive_skb_sk
     1.43%  kpktgend_0      [kernel.kallsyms]  [k] __build_skb

* Without this patch + tc ingress:

        tc filter add dev eth4 parent ffff: protocol ip prio 1 \
                u32 match ip dst 4.3.2.1/32

Result: OK: 9269001(c9268821+d179) usec, 100000000 (60byte,0frags)
  10788648pps 5178Mb/sec (5178551040bps) errors: 100000000

    40.99%  kpktgend_0   [kernel.kallsyms]  [k] __netif_receive_skb_core
    17.50%  kpktgend_0   [kernel.kallsyms]  [k] kfree_skb
    11.77%  kpktgend_0   [cls_u32]          [k] u32_classify
     5.62%  kpktgend_0   [kernel.kallsyms]  [k] tc_classify_compat
     5.18%  kpktgend_0   [pktgen]           [k] pktgen_thread_worker
     3.23%  kpktgend_0   [kernel.kallsyms]  [k] tc_classify
     2.97%  kpktgend_0   [kernel.kallsyms]  [k] ip_rcv
     1.83%  kpktgend_0   [kernel.kallsyms]  [k] netif_receive_skb_internal
     1.50%  kpktgend_0   [kernel.kallsyms]  [k] netif_receive_skb_sk
     0.99%  kpktgend_0   [kernel.kallsyms]  [k] __build_skb

* With this patch + tc ingress:

        tc filter add dev eth4 parent ffff: protocol ip prio 1 \
                u32 match ip dst 4.3.2.1/32

Result: OK: 9308218(c9308091+d126) usec, 100000000 (60byte,0frags)
  10743194pps 5156Mb/sec (5156733120bps) errors: 100000000

    42.01%  kpktgend_0   [kernel.kallsyms]   [k] __netif_receive_skb_core
    17.78%  kpktgend_0   [kernel.kallsyms]   [k] kfree_skb
    11.70%  kpktgend_0   [cls_u32]           [k] u32_classify
     5.46%  kpktgend_0   [kernel.kallsyms]   [k] tc_classify_compat
     5.16%  kpktgend_0   [pktgen]            [k] pktgen_thread_worker
     2.98%  kpktgend_0   [kernel.kallsyms]   [k] ip_rcv
     2.84%  kpktgend_0   [kernel.kallsyms]   [k] tc_classify
     1.96%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_internal
     1.57%  kpktgend_0   [kernel.kallsyms]   [k] netif_receive_skb_sk

Note that the results are very similar before and after.

I can see gcc gets the code under the ingress static key out of the hot path.
Then, on that cold branch, it generates the code to accomodate the netfilter
ingress static key. My explanation for this is that this reduces the pressure
on the instruction cache for non-users as the new code is out of the hot path,
and it comes with minimal impact for tc ingress users.

Using gcc version 4.8.4 on:

Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                8
[...]
L1d cache:             16K
L1i cache:             64K
L2 cache:              2048K
L3 cache:              8192K
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This new config switch enables the ingress filtering infrastructure that is
controlled through the ingress_needed static key. This prepares the
introduction of the Netfilter ingress hook that resides under this unique
static key.

Note that CONFIG_SCH_INGRESS automatically selects this, that should be no
problem since this also depends on CONFIG_NET_CLS_ACT.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In preparation to have netfilter ingress per-device hook list.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bitwise tests are always true here because it uses '|' where '&' is
intended.

Fixes: 98b5a0f4 ('net: macb: Add support for jumbo frames')
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When I had inlined __alloc_rx_skb into __netdev_alloc_skb and
__napi_alloc_skb I had overlooked the fact that there was a return in the
__alloc_rx_skb.  As a result we weren't reserving headroom or setting the
skb->dev in certain cases.  This change corrects that by adding a couple of
jump labels to jump to depending on __alloc_skb either succeeding or failing.

Fixes: 9451980a ("net: Use cached copy of pfmemalloc to avoid accessing page")
Reported-by: NFelipe Balbi <balbi@ti.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Tested-by: NKevin Hilman <khilman@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

John W. Linville says:

====================
add GENEVE netdev tunnel driver

This 5-patch kernel series adds a netdev implementation of a GENEVE
tunnel driver, and the single iproute2 patch enables creation and
such for those netdevs.  This makes use of the existing GENEVE
infrastructure already used by the OVS code.  The net/ipv4/geneve.c
file is renamed as net/ipv4/geneve_core.c as part of these changes.

 drivers/net/Kconfig            |   14 +
 drivers/net/Makefile           |    1
 drivers/net/geneve.c           |  503 +++++++++++++++++++++++++++++++++++++++++
 include/net/geneve.h           |    5
 include/uapi/linux/if_link.h   |    9
 net/ipv4/Kconfig               |    4
 net/ipv4/Makefile              |    2
 net/ipv4/geneve.c              |    6
 net/ipv4/geneve_core.c         |    4
 net/openvswitch/Kconfig        |    2
 net/openvswitch/vport-geneve.c |    5
 11 files changed, 538 insertions(+), 17 deletions(-)

The overall structure of the GENEVE netdev driver is strongly
influenced by the VXLAN netdev driver.  This is not surprising, as the
two drivers are intended to serve similar purposes.  As development of
the GENEVE driver continues, it is likely that those similarities will
grow stronger.  This will include both simple configuration options
(e.g. TOS and TTL settings) and new control plane support.

The current implementation is very simple, restricting itself to point
to point links over IPv4.  This is due only to the simplicity of the
implementation, and no such limit is inherent to GENEVE in any way.
Support for IPv6 links and more sophisticated control plane options
are predictable enhancements.

Using the included iproute2 patch, a GENEVE tunnel is created thusly:

        ip link add dev gnv0 type geneve remote 192.168.22.1 vni 1234
        ip link set gnv0 up
        ip addr add 10.1.1.1/24 dev gnv0

After a corresponding tunnel interface is created at the link partner,
traffic should proceed as expected.

Please let me know if anyone has problems...thanks!
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is an initial implementation of a netdev driver for GENEVE
tunnels.  This implementation uses a fixed UDP port, and only supports
point-to-point links with specific partner endpoints.  Only IPv4
links are supported at this time.
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net/ipv4/geneve.c -> net/ipv4/geneve_core.c

This name better reflects the purpose of the module.
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a static inline with identical definitions in multiple places...
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This file is essentially a library for implementing the geneve
encapsulation protocol.  The file does not register any rtnl_link_ops,
so the MODULE_ALIAS_RTNL_LINK macro is inappropriate here.
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes 4577139b ("net: use jump label patching for ingress qdisc in
__netif_receive_skb_core").

The only client of this is sch_ingress and it depends on NET_CLS_ACT. So
there is no way these definition can be of any help.

Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Willem de Bruijn says:

====================
refine packet socket rollover:

1. mitigate a case of lock contention
2. avoid exporting resource exhaustion to other sockets,
   by migrating only to a victim socket that has ample room
3. avoid reordering of most flows on the socket,
   by migrating first the flow responsible for load imbalance
4. help processes detect load imbalance,
   by exporting rollover counters

Context: rollover implements flow migration in packet socket fanout
groups in case of extreme load imbalance. It is a specific
implementation of migration that minimizes reordering by selecting
the same victim socket when possible (and by selecting subsequent
victims in a round robin fashion, from which its name derives).

Changes:
  v2 -> v3:
    - statistics: replace unsigned long with __aligned_u64
  v1 -> v2:
    - huge flow detection: run lockless
    - huge flow detection: replace stored index with random
    - contention avoidance: test in packet_poll while lock held
    - contention avoidance: clear pressure sooner

          packet_poll and packet_recvmsg would clear only if the sock
          is empty to avoid taking the necessary lock. But,
          * packet_poll already holds this lock, so a lockless variant
            __packet_rcv_has_room is cheap.
          * packet_recvmsg is usually called only for non-ring sockets,
            which also runs lockless.

    - preparation: drop "single return" patch

          packet_rcv_has_room is now a locked wrapper around
          __packet_rcv_has_room, achieving the same (single footer).

The benchmark mentioned in the patches is at
https://github.com/wdebruij/kerneltools/blob/master/tests/bench_rollover.c
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rollover indicates exceptional conditions. Export a counter to inform
socket owners of this state.

If no socket with sufficient room is found, rollover fails. Also count
these events.

Finally, also count when flows are rolled over early thanks to huge
flow detection, to validate its correctness.

Tested:
  Read counters in bench_rollover on all other tests in the patchset
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Migrate flows from a socket to another socket in the fanout group not
only when the socket is full. Start migrating huge flows early, to
divert possible 4-tuple attacks without affecting normal traffic.

Introduce fanout_flow_is_huge(). This detects huge flows, which are
defined as taking up more than half the load. It does so cheaply, by
storing the rxhashes of the N most recent packets. If over half of
these are the same rxhash as the current packet, then drop it. This
only protects against 4-tuple attacks. N is chosen to fit all data in
a single cache line.

Tested:
  Ran bench_rollover for 10 sec with 1.5 Mpps of single flow input.

    lpbb5:/export/hda3/willemb# ./bench_rollover -l 1000 -r -s
    cpu         rx       rx.k     drop.k   rollover     r.huge   r.failed
      0         14         14          0          0          0          0
      1         20         20          0          0          0          0
      2         16         16          0          0          0          0
      3    6168824    6168824          0    4867721    4867721          0
      4    4867741    4867741          0          0          0          0
      5         12         12          0          0          0          0
      6         15         15          0          0          0          0
      7         17         17          0          0          0          0
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rollover has to call packet_rcv_has_room on sockets in the fanout
group to find a socket to migrate to. This operation is expensive
especially if the packet sockets use rings, when a lock has to be
acquired.

Avoid pounding on the lock by all sockets by temporarily marking a
socket as "under memory pressure" when such pressure is detected.
While set, only the socket owner may call packet_rcv_has_room on the
socket. Once it detects normal conditions, it clears the flag. The
socket is not used as a victim by any other socket in the meantime.

Under reasonably balanced load, each socket writer frequently calls
packet_rcv_has_room and clears its own pressure field. As a backup
for when the socket is rarely written to, also clear the flag on
reading (packet_recvmsg, packet_poll) if this can be done cheaply
(i.e., without calling packet_rcv_has_room). This is only for
edge cases.

Tested:
  Ran bench_rollover: a process with 8 sockets in a single fanout
  group, each pinned to a single cpu that receives one nic recv
  interrupt. RPS and RFS are disabled. The benchmark uses packet
  rx_ring, which has to take a lock when determining whether a
  socket has room.

  Sent 3.5 Mpps of UDP traffic with sufficient entropy to spread
  uniformly across the packet sockets (and inserted an iptables
  rule to drop in PREROUTING to avoid protocol stack processing).

  Without this patch, all sockets try to migrate traffic to
  neighbors, causing lock contention when searching for a non-
  empty neighbor. The lock is the top 9 entries.

    perf record -a -g sleep 5

    -  17.82%   bench_rollover  [kernel.kallsyms]    [k] _raw_spin_lock
       - _raw_spin_lock
          - 99.00% spin_lock
    	 + 81.77% packet_rcv_has_room.isra.41
    	 + 18.23% tpacket_rcv
          + 0.84% packet_rcv_has_room.isra.41
    +   5.20%      ksoftirqd/6  [kernel.kallsyms]    [k] _raw_spin_lock
    +   5.15%      ksoftirqd/1  [kernel.kallsyms]    [k] _raw_spin_lock
    +   5.14%      ksoftirqd/2  [kernel.kallsyms]    [k] _raw_spin_lock
    +   5.12%      ksoftirqd/7  [kernel.kallsyms]    [k] _raw_spin_lock
    +   5.12%      ksoftirqd/5  [kernel.kallsyms]    [k] _raw_spin_lock
    +   5.10%      ksoftirqd/4  [kernel.kallsyms]    [k] _raw_spin_lock
    +   4.66%      ksoftirqd/0  [kernel.kallsyms]    [k] _raw_spin_lock
    +   4.45%      ksoftirqd/3  [kernel.kallsyms]    [k] _raw_spin_lock
    +   1.55%   bench_rollover  [kernel.kallsyms]    [k] packet_rcv_has_room.isra.41

  On net-next with this patch, this lock contention is no longer a
  top entry. Most time is spent in the actual read function. Next up
  are other locks:

    +  15.52%  bench_rollover  bench_rollover     [.] reader
    +   4.68%         swapper  [kernel.kallsyms]  [k] memcpy_erms
    +   2.77%         swapper  [kernel.kallsyms]  [k] packet_lookup_frame.isra.51
    +   2.56%     ksoftirqd/1  [kernel.kallsyms]  [k] memcpy_erms
    +   2.16%         swapper  [kernel.kallsyms]  [k] tpacket_rcv
    +   1.93%         swapper  [kernel.kallsyms]  [k] mlx4_en_process_rx_cq

  Looking closer at the remaining _raw_spin_lock, the cost of probing
  in rollover is now comparable to the cost of taking the lock later
  in tpacket_rcv.

    -   1.51%         swapper  [kernel.kallsyms]  [k] _raw_spin_lock
       - _raw_spin_lock
          + 33.41% packet_rcv_has_room
          + 28.15% tpacket_rcv
          + 19.54% enqueue_to_backlog
          + 6.45% __free_pages_ok
          + 2.78% packet_rcv_fanout
          + 2.13% fanout_demux_rollover
          + 2.01% netif_receive_skb_internal
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Only migrate flows to sockets that have sufficient headroom, where
sufficient is defined as having at least 25% empty space.

The kernel has three different buffer types: a regular socket, a ring
with frames (TPACKET_V[12]) or a ring with blocks (TPACKET_V3). The
latter two do not expose a read pointer to the kernel, so headroom is
not computed easily. All three needs a different implementation to
estimate free space.

Tested:
  Ran bench_rollover for 10 sec with 1.5 Mpps of single flow input.

  bench_rollover has as many sockets as there are NIC receive queues
  in the system. Each socket is owned by a process that is pinned to
  one of the receive cpus. RFS is disabled. RPS is enabled with an
  identity mapping (cpu x -> cpu x), to count drops with softnettop.

    lpbb5:/export/hda3/willemb# ./bench_rollover -r -l 1000 -s
    Press [Enter] to exit

    cpu         rx       rx.k     drop.k   rollover     r.huge   r.failed
      0         16         16          0          0          0          0
      1         21         21          0          0          0          0
      2    5227502    5227502          0          0          0          0
      3         18         18          0          0          0          0
      4    6083289    6083289          0    5227496          0          0
      5         22         22          0          0          0          0
      6         21         21          0          0          0          0
      7          9          9          0          0          0          0
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Replace rollover state per fanout group with state per socket. Future
patches will add fields to the new structure.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

packet_rcv_fanout calls fanout_demux_rollover twice. Move all rollover
logic into the callee to simplify these callsites, especially with
upcoming changes.

The main differences between the two callsites is that the FLAG
variant tests whether the socket previously selected by another
mode (RR, RND, HASH, ..) has room before migrating flows, whereas the
rollover mode has no original socket to test.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

__ip_local_out_sk() is only used from net/ipv4/ip_output.c

net/ipv4/ip_output.c:94:5: warning: symbol '__ip_local_out_sk' was not
declared. Should it be static?

Fixes: 7026b1dd ("netfilter: Pass socket pointer down through okfn().")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>