Tom Herbert says:

====================
udp: Generalize GSO for UDP tunnels

This patch set generalizes the UDP tunnel segmentation functions so
that they can work with various protocol encapsulations. The primary
change is to set the inner_protocol field in the skbuff when creating
the encapsulated packet, and then in skb_udp_tunnel_segment this data
is used to determine the function for segmenting the encapsulated
packet. The inner_protocol field is overloaded to take either an
Ethertype or IP protocol.

The inner_protocol is set on transmit using skb_set_inner_ipproto or
skb_set_inner_protocol functions. VXLAN and IP tunnels (for fou GSO)
were modified to call these.

Notes:
  - GSO for GRE/UDP where GRE checksum is enabled does not work.
    Handling this will require some special case code.
  - Software GSO now supports many varieties of encapsulation with
    SKB_GSO_UDP_TUNNEL{_CSUM}. We still need a mechanism to query
    for device support of particular combinations (I intend to
    add ndo_gso_check for that).
  - MPLS seems to be the only previous user of inner_protocol. I don't
    believe these patches can affect that. For supporting GSO with
    MPLS over UDP, the inner_protocol should be set using the
    helper functions in this patch.
  - GSO for L2TP/UDP should also be straightforward now.

v2:
  - Respin for Eric's restructuring of skbuff.

Tested GRE, IPIP, and SIT over fou as well as VLXAN. This was
done using 200 TCP_STREAMs in netperf.

 GRE
    IPv4, FOU, UDP checksum enabled
      TCP_STREAM TSO enabled on tun interface
        14.04% TX CPU utilization
        13.17% RX CPU utilization
        9211 Mbps
      TCP_STREAM TSO disabled on tun interface
        27.82% TX CPU utilization
        25.41% RX CPU utilization
        9336 Mbps
    IPv4, FOU, UDP checksum disabled
      TCP_STREAM TSO enabled on tun interface
        13.14% TX CPU utilization
        23.18% RX CPU utilization
        9277 Mbps
      TCP_STREAM TSO disabled on tun interface
        30.00% TX CPU utilization
        31.28% RX CPU utilization
        9327 Mbps

  IPIP
    FOU, UDP checksum enabled
      TCP_STREAM TSO enabled on tun interface
        15.28% TX CPU utilization
        13.92% RX CPU utilization
        9342 Mbps
      TCP_STREAM TSO disabled on tun interface
        27.82% TX CPU utilization
        25.41% RX CPU utilization
        9336 Mbps
    FOU, UDP checksum disabled
      TCP_STREAM TSO enabled on tun interface
        15.08% TX CPU utilization
        24.64% RX CPU utilization
        9226 Mbps
      TCP_STREAM TSO disabled on tun interface
        30.00% TX CPU utilization
        31.28% RX CPU utilization
        9327 Mbps

  SIT
    FOU, UDP checksum enabled
      TCP_STREAM TSO enabled on tun interface
        14.47% TX CPU utilization
        14.58% RX CPU utilization
        9106 Mbps
      TCP_STREAM TSO disabled on tun interface
        31.82% TX CPU utilization
        30.82% RX CPU utilization
        9204 Mbps
    FOU, UDP checksum disabled
      TCP_STREAM TSO enabled on tun interface
        15.70% TX CPU utilization
        27.93% RX CPU utilization
        9097 Mbps
      TCP_STREAM TSO disabled on tun interface
        33.48% TX CPU utilization
        37.36% RX CPU utilization
        9197 Mbps

   VXLAN
      TCP_STREAM TSO enabled on tun interface
        16.42% TX CPU utilization
        23.66% RX CPU utilization
        9081 Mbps
      TCP_STREAM TSO disabled on tun interface
        30.32% TX CPU utilization
        30.55% RX CPU utilization
        9185 Mbps

   Baseline (no encp, TSO and LRO enabled)
      TCP_STREAM
        11.85% TX CPU utilization
        15.13% RX CPU utilization
        9452 Mbps
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call skb_set_inner_protocol to set inner Ethernet protocol to
ETH_P_TEB before transmit. This is needed for GSO with UDP tunnels.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call skb_set_inner_protocol to set inner Ethernet protocol to
protocol being encapsulation by GRE before tunnel_xmit. This is
needed for GSO if UDP encapsulation (fou) is being done.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call skb_set_inner_ipproto to set inner IP protocol to IPPROTO_IPV4
before tunnel_xmit. This is needed if UDP encapsulation (fou) is
being done.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call skb_set_inner_ipproto to set inner IP protocol to IPPROTO_IPV6
before tunnel_xmit. This is needed if UDP encapsulation (fou) is
being done.
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb_udp_segment is the function called from udp4_ufo_fragment to
segment a UDP tunnel packet. This function currently assumes
segmentation is transparent Ethernet bridging (i.e. VXLAN
encapsulation). This patch generalizes the function to
operate on either Ethertype or IP protocol.

The inner_protocol field must be set to the protocol of the inner
header. This can now be either an Ethertype or an IP protocol
(in a union). A new flag in the skbuff indicates which type is
effective. skb_set_inner_protocol and skb_set_inner_ipproto
helper functions were added to set the inner_protocol. These
functions are called from the point where the tunnel encapsulation
is occuring.

When skb_udp_tunnel_segment is called, the function to segment the
inner packet is selected based on the inner IP or Ethertype. In the
case of an IP protocol encapsulation, the function is derived from
inet[6]_offloads. In the case of Ethertype, skb->protocol is
set to the inner_protocol and skb_mac_gso_segment is called. (GRE
currently does this, but it might be possible to lookup the protocol
in offload_base and call the appropriate segmenation function
directly).
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexei Starovoitov says:

====================
bpf: add search pruning optimization and tests

patch #1 commit log explains why eBPF verifier has to examine some
instructions multiple times and describes the search pruning optimization
that improves verification speed for branchy programs and allows more
complex programs to be verified successfully.
This patch completes the core verifier logic.

patch #2 adds more verifier tests related to branches and search pruning

I'm still working on Andy's 'bitmask for stack slots' suggestion. It will be
done on top of this patch.

The current verifier algorithm is brute force depth first search with
state pruning. If anyone can come up with another algorithm that demonstrates
better results, we'll replace the algorithm without affecting user space.

Note verifier doesn't guarantee that all possible valid programs are accepted.
Overly complex programs may still be rejected.
Verifier improvements/optimizations will guarantee that if a program
was passing verification in the past, it will still be passing.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

add 4 extra tests to cover jump verification better
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

consider C program represented in eBPF:
int filter(int arg)
{
    int a, b, c, *ptr;

    if (arg == 1)
        ptr = &a;
    else if (arg == 2)
        ptr = &b;
    else
        ptr = &c;

    *ptr = 0;
    return 0;
}
eBPF verifier has to follow all possible paths through the program
to recognize that '*ptr = 0' instruction would be safe to execute
in all situations.
It's doing it by picking a path towards the end and observes changes
to registers and stack at every insn until it reaches bpf_exit.
Then it comes back to one of the previous branches and goes towards
the end again with potentially different values in registers.
When program has a lot of branches, the number of possible combinations
of branches is huge, so verifer has a hard limit of walking no more
than 32k instructions. This limit can be reached and complex (but valid)
programs could be rejected. Therefore it's important to recognize equivalent
verifier states to prune this depth first search.

Basic idea can be illustrated by the program (where .. are some eBPF insns):
    1: ..
    2: if (rX == rY) goto 4
    3: ..
    4: ..
    5: ..
    6: bpf_exit
In the first pass towards bpf_exit the verifier will walk insns: 1, 2, 3, 4, 5, 6
Since insn#2 is a branch the verifier will remember its state in verifier stack
to come back to it later.
Since insn#4 is marked as 'branch target', the verifier will remember its state
in explored_states[4] linked list.
Once it reaches insn#6 successfully it will pop the state recorded at insn#2 and
will continue.
Without search pruning optimization verifier would have to walk 4, 5, 6 again,
effectively simulating execution of insns 1, 2, 4, 5, 6
With search pruning it will check whether state at #4 after jumping from #2
is equivalent to one recorded in explored_states[4] during first pass.
If there is an equivalent state, verifier can prune the search at #4 and declare
this path to be safe as well.
In other words two states at #4 are equivalent if execution of 1, 2, 3, 4 insns
and 1, 2, 4 insns produces equivalent registers and stack.
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- Copy short frames and keep the buffers mapped, re-allocate skb instead of
  memory copy for long frames.
- Add support for setting/getting rx_copybreak using generic ethtool tunable

Changes V3:
* As Eric Dumazet's suggestion that removing the copybreak module parameter
  and only keep the ethtool API support for rx_copybreak.

Changes V2:
* Implements rx_copybreak
* Rx_copybreak provides module parameter to change this value
* Add tunable_ops support for rx_copybreak
Signed-off-by: NFugang Duan <B38611@freescale.com>
Signed-off-by: NFrank Li <Frank.Li@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fast clone cloning can actually avoid an atomic_inc(), if we
guarantee prior clone_ref value is 1.

This requires a change kfree_skbmem(), to perform the
atomic_dec_and_test() on clone_ref before setting fclone to
SKB_FCLONE_UNAVAILABLE.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ccid_activate is only called by __init ccid_initialize_builtins in same module.
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

dccp_mib_init is only called by __init dccp_init in same module.
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tested on RTL8168d/8111d model using 'super_netperf 40' with TCP/UDP_STREAM.

Output of
while true; do
    for n in inflight limit; do
          echo -n $n\ ; cat $n;
    done;
    sleep 1;
done

during netperf run, 100mbit peer:

inflight 0
limit 3028
inflight 6056
limit 4542

[ trimmed output for brevity, no limit/inflight changes during
  test steady-state ]

limit 4542
inflight 3028
limit 6122
inflight 0
limit 6122
[ changed cable to 1gbit peer, restart netperf ]
inflight 37850
limit 36336
inflight 33308
limit 31794
inflight 33308
limit 31794
inflight 27252
limit 25738
[ again, no changes during test ]
inflight 27252
limit 25738
inflight 0
limit 28766
[ change cable to 100mbit peer, restart netperf ]
limit 28766
inflight 27370
limit 28766
inflight 4542
limit 5990
inflight 6056
limit 4542
[ .. ]
inflight 6056
limit 4542
inflight 0

[end of test]

Cc: Francois Romieu <romieu@fr.zoreil.com>
Cc: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Acked-by: NEric Dumazet <edumazet@google.com>
Acked-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Lets use a proper structure to clearly document and implement
skb fast clones.

Then, we might experiment more easily alternative layouts.

This patch adds a new skb_fclone_busy() helper, used by tcp and xfrm,
to stop leaking of implementation details.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently we have two different policies for orphan sockets
that repeatedly stall on zero window ACKs. If a socket gets
a zero window ACK when it is transmitting data, the RTO is
used to probe the window. The socket is aborted after roughly
tcp_orphan_retries() retries (as in tcp_write_timeout()).

But if the socket was idle when it received the zero window ACK,
and later wants to send more data, we use the probe timer to
probe the window. If the receiver always returns zero window ACKs,
icsk_probes keeps getting reset in tcp_ack() and the orphan socket
can stall forever until the system reaches the orphan limit (as
commented in tcp_probe_timer()). This opens up a simple attack
to create lots of hanging orphan sockets to burn the memory
and the CPU, as demonstrated in the recent netdev post "TCP
connection will hang in FIN_WAIT1 after closing if zero window is
advertised." http://www.spinics.net/lists/netdev/msg296539.html

This patch follows the design in RTO-based probe: we abort an orphan
socket stalling on zero window when the probe timer reaches both
the maximum backoff and the maximum RTO. For example, an 100ms RTT
connection will timeout after roughly 153 seconds (0.3 + 0.6 +
.... + 76.8) if the receiver keeps the window shut. If the orphan
socket passes this check, but the system already has too many orphans
(as in tcp_out_of_resources()), we still abort it but we'll also
send an RST packet as the connection may still be active.

In addition, we change TCP_USER_TIMEOUT to cover (life or dead)
sockets stalled on zero-window probes. This changes the semantics
of TCP_USER_TIMEOUT slightly because it previously only applies
when the socket has pending transmission.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Reported-by: NAndrey Dmitrov <andrey.dmitrov@oktetlabs.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

cipso_v4_cache_init is only called by __init cipso_v4_init
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ip4_frags_ctl_register is only called by __init ipfrag_init
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_init_mem is only called by __init tcp_init.
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These two functions are used to inform dash firmware that driver is been
brought up or brought down. So call these two functions only when hardware dash
function is enabled.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In function "rtl8168_oob_notify", using function "rtl_eri_write" to access
eri register 0xe8, instead of using MAC register "ERIDR" and "ERIAR" to
access it.

For using function "rtl_eri_write" in function "rtl8168_oob_notify", need to
move down "rtl8168_oob_notify" related functions under the function
"rtl_eri_write".
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

DASH function not only RTL8168DP can support, but also RTL8168EP.
So change the name of function "r8168dp_check_dash" to "r8168_check_dash".
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Change the name of function "rtl_w1w0_eri" to "rtl_w0w1_eri".

In this function, the local variable "val" is "write zeros then write ones".
Please see below code.

(val & ~m) | p

In this patch, change the function name from "xx_w1w0_xx" to "xx_w0w1_xx".
The changed function name is more suitable for it's behavior.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Change function name from "rtl_w1w0_phy" to "rtl_w0w1_phy".
And its behavior from "write ones then write zeros" to
"write zeros then write ones".

In Realtek internal driver, bitwise operations are almost "write zeros then
write ones". For easy to port hardware parameters from Realtek internal driver
to Linux kernal driver "r8169", we would like to change this function's
behavior and its name.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For RTL8168F RTL8168FB RTL8168G RTL8168GU RTL8411 RTL8411B RTL8402 RTL8107E,
the magic packet enable bit is changed to eri 0xde bit0.

In this patch, change magic packet enable bit of these chips to eri 0xde bit0.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RTL8168FB RTL8168G RTL8168GU RTL8411 RTL8411B RTL8106EUS RTL8402 can
support get mac address from backup mac address register.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RTL8411B can support disable/enable pll function.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RTL8168G also can disable/enable pll function.
Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NChun-Hao Lin <hau@realtek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One of the error cases for vnet_start_xmit()'s "out_dropped" label
is port == NULL, so only mess with port->clean_timer when port is not NULL.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The dsa_switch_suspend() and dsa_switch_resume() functions are only used
when PM_SLEEP is enabled, so they need #ifdef CONFIG_PM_SLEEP protection
to avoid a compiler warning.
Signed-off-by: NThierry Reding <treding@nvidia.com>
Acked-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Calling ether_setup is redundant since alloc_etherdev calls it.
Signed-off-by: NSubbaraya Sundeep Bhatta <sbhatta@xilinx.com>
Signed-off-by: NMichal Simek <michal.simek@xilinx.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Proper CHECKSUM_COMPLETE support needs to adjust skb->csum
when we remove one header. Its done using skb_gro_postpull_rcsum()

In the case of IPv4, we know that the adjustment is not really needed,
because the checksum over IPv4 header is 0. Lets add a comment to
ease code comprehension and avoid copy/paste errors.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 3243acd3
("ieee802154: add __init to lowpan_frags_sysctl_register")

added __init to lowpan_frags_ns_sysctl_register instead of
lowpan_frags_sysctl_register
Suggested-by: NAlexander Aring <alex.aring@gmail.com>
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

David L Stevens says:

====================
sunvnet: add jumbo frames support

This patch set updates the sunvnet driver to version 1.6 of the VIO protocol
to support per-port exchange of MTU information and allow non-standard MTU
sizes, including jumbo frames.

Using large MTUs shows a nearly 5X throughput improvement Linux-Solaris
and > 10X throughput improvement Linux-Linux.

Changes from v8:
	-add a short timeout to free pending skbs if a new transmit doesn't
	 do it first per Dave Miller <davem@davemloft.net>
Changes from v7:
	-handle skb allocation failures in vnet_skb_shape()
	 per Dave Miller <davem@davemloft.net>
Changes from v6:
	-made kernel transmit path zero-copy to remove memory n^2 scaling issue
	 raised by Raghuram Kothakota <Raghuram.Kothakota@oracle.com>
Changes from v5:
	- fixed comment per Sowmini Varadhan <sowmini.varadhan@oracle.com>
Changes from v4:
	- changed VNET_MAXPACKET per David Laight <David.Laight@ACULAB.COM>
	- added cookies to support non-contiguous buffers of max size
Changes from v3:
	- added version functions per Dave Miller <davem@davemloft.net>
	- moved rmtu to vnet_port per Dave Miller <davem@davemloft.net>
	- explicitly set options bits and capability flags to 0 per
		Raghuram Kothakota <Raghuram.Kothakota@oracle.com>
Changes from v2:
	- make checkpatch clean
Changes from v1:
	- fix brace formatting per Dave Miller <davem@davemloft.net>
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch sends ICMP and ICMPv6 messages for Path MTU Discovery when a remote
port MTU is smaller than the device MTU. This allows mixing newer VIO protocol
devices that support MTU negotiation with older devices that do not on the
same vswitch. It also allows Linux-Linux LDOMs to use 64K-1 data packets even
though Solaris vswitch is limited to <16K MTU.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch allows an admin to set the MTU on a sunvnet device to arbitrary
values between the minimum (68) and maximum (65535) IPv4 packet sizes.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch removes pre-allocated transmit buffers and instead directly maps
pending packets on demand. This saves O(n^2) maximum-sized transmit buffers,
for n hosts on a vswitch, as well as a copy to those buffers.

Single-stream TCP throughput linux-solaris dropped ~5% for 1500-byte MTU,
but linux-linux at 1500-bytes increased ~20%.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch upgrades the sunvnet driver to support VIO protocol version 1.6.
In particular, it adds per-port MTU negotiation, allowing MTUs other than
ETH_FRAMELEN with ports using newer VIO protocol versions.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>