After my change to neigh_hh_init to obtain the protocol from the
neigh_table there are no more users of protocol in struct dst_ops.
Remove the protocol field from dst_ops and all of it's initializers.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that the root of the trie contains a key_vector, by
doing this we make room to essentially collapse the entire trie by at least
one cache line as we can store the information about the tnode or leaf that
is pointed to in the root.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change pulls the parent pointer from the key_vector and places it in
the tnode structure.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This pulls the information about the child array out of the key_vector and
places it in the tnode since that is where it is needed.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RCU is only needed once for the entire node, not once per key_vector so we
can pull that out and move it to the tnode structure.

In addition add accessors to be used inside the RCU functions so that we
can more easily get from the key vector to either the tnode or the trie
pointers.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change pulls the fields not explicitly needed in the key_vector and
placed them in the new tnode structure.  By doing this we will eventually
be able to reduce the key_vector down to 16 bytes on 64 bit systems, and
12 bytes on 32 bit systems.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We are now checking the length of a key_vector instead of a tnode so it
makes sense to probably just rename this to child_length since it would
probably even be applicable to a leaf.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I am replacing the tnode_get_child call with get_child since we are
techically pulling the child out of a key_vector now and not a tnode.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rename the tnode to key_vector.  The key_vector will be the eventual
container for all of the information needed by either a leaf or a tnode.
The final result should be much smaller than the 40 bytes currently needed
for either one.

This also updates the trie struct so that it contains an array of size 1 of
tnode pointers.  This is to bring the structure more inline with how an
actual tnode itself is configured.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Resize related functions now all return a pointer to the pointer that
references the object that was resized.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change just does a couple of minor cleanups on
fib_table_flush_external.  Specifically it addresses the fact that resize
was being called even though nothing was being removed from the table, and
it drops an unecessary indent since we could just call continue on the
inverse of the fi && flag check.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As per RFC4821 7.3.  Selecting Probe Size, a probe timer should
be armed once probing has converged. Once this timer expired,
probing again to take advantage of any path PMTU change. The
recommended probing interval is 10 minutes per RFC1981. Probing
interval could be sysctled by sysctl_tcp_probe_interval.

Eric Dumazet suggested to implement pseudo timer based on 32bits
jiffies tcp_time_stamp instead of using classic timer for such
rare event.
Signed-off-by: NFan Du <fan.du@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Current probe_size is chosen by doubling mss_cache,
the probing process will end shortly with a sub-optimal
mss size, and the link mtu will not be taken full
advantage of, in return, this will make user to tweak
tcp_base_mss with care.

Use binary search to choose probe_size in a fine
granularity manner, an optimal mss will be found
to boost performance as its maxmium.

In addition, introduce a sysctl_tcp_probe_threshold
to control when probing will stop in respect to
the width of search range.

Test env:
Docker instance with vxlan encapuslation(82599EB)
iperf -c 10.0.0.24  -t 60

before this patch:
1.26 Gbits/sec

After this patch: increase 26%
1.59 Gbits/sec
Signed-off-by: NFan Du <fan.du@intel.com>
Acked-by: NJohn Heffner <johnwheffner@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net/ipv4/fib_trie.c: In function ‘fib_table_flush_external’:
net/ipv4/fib_trie.c:1572:6: warning: unused variable ‘found’ [-Wunused-variable]
  int found = 0;
      ^
net/ipv4/fib_trie.c:1571:16: warning: unused variable ‘slen’ [-Wunused-variable]
  unsigned char slen;
                ^
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Call into the switchdev driver any time an IPv4 fib entry is
added/modified/deleted from the kernel's FIB.  The switchdev driver may or
may not install the route to the offload device.  In the case where the
driver tries to install the route and something goes wrong (device's routing
table is full, etc), then all of the offloaded routes will be flushed from the
device, route forwarding falls back to the kernel, and no more routes are
offloading.

We can refine this logic later.  For now, use the simplist model of offloading
routes up to the point of failure, and then on failure, undo everything and
mark IPv4 offloading disabled.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Keep switchdev FIB offload model simple for now and don't allow custom ip
rules.
Signed-off-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

timewait sockets now share a common base with established sockets.

inet_twsk_diag_dump() can use inet_diag_bc_sk() instead of duplicating
code, granted that inet_diag_bc_sk() does proper userlocks
initialization.

twsk_build_assert() will catch any future changes that could break
the assumptions.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

xt_cluster supersedes ipt_CLUSTERIP since it can be also used in
gateway configurations (not only from the backend side).

ipt_CLUSTER is also known to leak the netdev that it uses on
device removal, which requires a rather large fix to workaround
the problem: http://patchwork.ozlabs.org/patch/358629/

So let's deprecate this so we can probably kill code this in the
future.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

This patch adds code to prevent us from attempting to allocate a tnode with
a size larger than what can be represented by size_t.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change updates the fib_table_lookup function so that it is in sync
with the fib_find_node function in terms of the explanation for the index
check based on the bits value.

I have also updated it from doing a mask to just doing a compare as I have
found that seems to provide more options to the compiler as I have seen it
turn this into a shift of the value and test under some circumstances.

In addition I addressed one minor issue in which we kept computing the key
^ n->key when checking the fib aliases.  I pulled the xor out of the loop
in order to reduce the number of memory reads in the lookup.  As a result
we should save a couple cycles since the xor is only done once much earlier
in the lookup.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The fib_table was wrapped in several places with an
rcu_read_lock/rcu_read_unlock however after looking over the code I found
several spots where the tables were being accessed as just standard
pointers without any protections.  This change fixes that so that all of
the proper protections are in place when accessing the table to take RCU
replacement or removal of the table into account.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we are going to compact the leaf and tnode we first need to make sure
the fields are all in the same place.  In that regard I am moving the leaf
pointer which represents the fib_alias hash list to occupy what is
currently the first key_vector pointer.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that the insert and delete functions make use of
the tnode pointer returned in the fib_find_node call.  By doing this we
will not have to rely on the parent pointer in the leaf which will be going
away soon.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that the parent pointer is returned by reference in
fib_find_node.  By doing this I can use it to find the parent node when I
am performing an insertion and I don't have to look for it again in
fib_insert_node.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that leaf_walk_rcu takes a tnode and a key instead
of the trie and a leaf.

The main idea behind this is to avoid using the leaf parent pointer as that
can have additional overhead in the future as I am trying to reduce the
size of a leaf down to 16 bytes on 64b systems and 12b on 32b systems.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change makes it so that we only call resize on the tnodes, instead of
from each of the leaves.  By doing this we can significantly reduce the
amount of time spent resizing as we can update all of the leaves in the
tnode first before we make any determinations about resizing.  As a result
we can simply free the tnode in the case that all of the leaves from a
given tnode are flushed instead of resizing with each leaf removed.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While looking at the mpls code I found myself writing yet another
version of neigh_lookup_noref.  We currently have __ipv4_lookup_noref
and __ipv6_lookup_noref.

So to make my work a little easier and to make it a smidge easier to
verify/maintain the mpls code in the future I stopped and wrote
___neigh_lookup_noref.  Then I rewote __ipv4_lookup_noref and
__ipv6_lookup_noref in terms of this new function.  I tested my new
version by verifying that the same code is generated in
ip_finish_output2 and ip6_finish_output2 where these functions are
inlined.

To get to ___neigh_lookup_noref I added a new neighbour cache table
function key_eq.  So that the static size of the key would be
available.

I also added __neigh_lookup_noref for people who want to to lookup
a neighbour table entry quickly but don't know which neibhgour table
they are going to look up.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If an over-MTU UDP datagram is sent through a SOCK_RAW socket to a
UFO-capable device, ip_ufo_append_data() sets skb->ip_summed to
CHECKSUM_PARTIAL unconditionally as all GSO code assumes transport layer
checksum is to be computed on segmentation. However, in this case,
skb->csum_start and skb->csum_offset are never set as raw socket
transmit path bypasses udp_send_skb() where they are usually set. As a
result, driver may access invalid memory when trying to calculate the
checksum and store the result (as observed in virtio_net driver).

Moreover, the very idea of modifying the userspace provided UDP header
is IMHO against raw socket semantics (I wasn't able to find a document
clearly stating this or the opposite, though). And while allowing
CHECKSUM_NONE in the UFO case would be more efficient, it would be a bit
too intrusive change just to handle a corner case like this. Therefore
disallowing UFO for packets from SOCK_DGRAM seems to be the best option.
Signed-off-by: NMichal Kubecek <mkubecek@suse.cz>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp resets are never emitted if the packet that triggers the
reject/reset has an invalid checksum.

For icmp error responses there was no such check.
It allows to distinguish icmp response generated via

iptables -I INPUT -p udp --dport 42 -j REJECT

and those emitted by network stack (won't respond if csum is invalid,
REJECT does).

Arguably its possible to avoid this by using conntrack and only
using REJECT with -m conntrack NEW/RELATED.

However, this doesn't work when connection tracking is not in use
or when using nf_conntrack_checksum=0.

Furthermore, sending errors in response to invalid csums doesn't make
much sense so just add similar test as in nf_send_reset.

Validate csum if needed and only send the response if it is ok.

Reference: http://bugzilla.redhat.com/show_bug.cgi?id=1169829Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

- Add protocol to neigh_tbl so that dst->ops->protocol is not needed
- Acquire the device from neigh->dev

This results in a neigh_hh_init that will cache the samve values
regardless of the packets flowing through it.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are no more callers so kill this function.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The special case has been pushed out into ax25_neigh_construct so there
is no need to keep this code in arp.c
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After TIPC doesn't depend on iocb argument in its internal
implementations of sendmsg() and recvmsg() hooks defined in proto
structure, no any user is using iocb argument in them at all now.
Then we can drop the redundant iocb argument completely from kinds of
implementations of both sendmsg() and recvmsg() in the entire
networking stack.

Cc: Christoph Hellwig <hch@lst.de>
Suggested-by: NAl Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As part of an effort to move skb->dropcount to skb->cb[] use a common
macro in protocol families using skb->cb[] for ancillary data to
validate available room in skb->cb[].
Signed-off-by: NEyal Birger <eyal.birger@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_fastopen_create_child() is static and should not be exported.

tcp4_gso_segment() and tcp6_gso_segment() should be static.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Another TCP issue is triggered by ECN.

Under pressure, receiver gets ECN marks, and send back ACK packets
with ECE TCP flag. Senders enter CA_CWR state.

In this state, tcp_tso_should_defer() is short cut :

if (icsk->icsk_ca_state != TCP_CA_Open)
    goto send_now;

This means that about all ACK packets we receive are triggering
a partial send, and because cwnd is kept small, we can only send
a small amount of data for each incoming ACK,
which in return generate more ACK packets.

Allowing CA_Open and CA_CWR states to enable TSO defer in
tcp_tso_should_defer() brings performance back :
TSO autodefer has more chance to defer under pressure.

This patch increases TSO and LRO/GRO efficiency back to normal levels,
and does not impact overall ECN behavior.
Signed-off-by: NEric Dumazet <edumazet@google.com>
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>

With sysctl_tcp_min_tso_segs being 4, it is very possible
that tcp_tso_should_defer() decides not sending last 2 MSS
of initial window of 10 packets. This also applies if
autosizing decides to send X MSS per GSO packet, and cwnd
is not a multiple of X.

This patch implements an heuristic based on age of first
skb in write queue : If it was sent very recently (less than half srtt),
we can predict that no ACK packet will come in less than half rtt,
so deferring might cause an under utilization of our window.

This is visible on initial send (IW10) on web servers,
but more generally on some RPC, as the last part of the message
might need an extra RTT to get delivered.

Tested:

Ran following packetdrill test
// A simple server-side test that sends exactly an initial window (IW10)
// worth of packets.

`sysctl -e -q net.ipv4.tcp_min_tso_segs=4`

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0    setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0    bind(3, ..., ...) = 0
+0    listen(3, 1) = 0

+.1   < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
+0    > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.1   < . 1:1(0) ack 1 win 257
+0    accept(3, ..., ...) = 4

+0    write(4, ..., 14600) = 14600
+0    > . 1:5841(5840) ack 1 win 457
+0    > . 5841:11681(5840) ack 1 win 457
// Following packet should be sent right now.
+0    > P. 11681:14601(2920) ack 1 win 457

+.1   < . 1:1(0) ack 14601 win 257

+0    close(4) = 0
+0    > F. 14601:14601(0) ack 1
+.1   < F. 1:1(0) ack 14602 win 257
+0    > . 14602:14602(0) ack 2
Signed-off-by: NEric Dumazet <edumazet@google.com>
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>

TSO relies on ability to defer sending a small amount of packets.
Heuristic is to wait for future ACKS in hope to send more packets at once.
Current algorithm uses a per socket tso_deferred field as a pseudo timer.

This pseudo timer relies on future ACK, but there is no guarantee
we receive them in time.

Fix would be to use a real timer, but cost of such timer is probably too
expensive for typical cases.

This patch changes the logic to test the time of last transmit,
because we should not add bursts of more than 1ms for any given flow.

We've used this patch for about two years at Google, before FQ/pacing
as it would reduce a fair amount of bursts.
Signed-off-by: NEric Dumazet <edumazet@google.com>
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>

At this point the leaf_info hash is redundant.  By adding the suffix length
to the fib_alias hash list we no longer have need of leaf_info as we can
determine the prefix length from fa_slen.  So we can compress things by
dropping the leaf_info structure from fib_trie and instead directly connect
the leaves to the fib_alias hash list.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>