[ 3897.923145] BUG: unable to handle kernel NULL pointer dereference at
 0000000000000080
[ 3897.931025] IP: [<ffffffffa9f27686>] reqsk_timer_handler+0x1a6/0x243

There is a race when reqsk_timer_handler() and tcp_check_req() call
inet_csk_reqsk_queue_unlink() on the same req at the same time.

Before commit fa76ce73 ("inet: get rid of central tcp/dccp listener
timer"), listener spinlock was held and race could not happen.

To solve this bug, we change reqsk_queue_unlink() to not assume req
must be found, and we return a status, to conditionally release a
refcount on the request sock.

This also means tcp_check_req() in non fastopen case might or not
consume req refcount, so tcp_v6_hnd_req() & tcp_v4_hnd_req() have
to properly handle this.

(Same remark for dccp_check_req() and its callers)

inet_csk_reqsk_queue_drop() is now too big to be inlined, as it is
called 4 times in tcp and 3 times in dccp.

Fixes: fa76ce73 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using a timer wheel for timewait sockets was nice ~15 years ago when
memory was expensive and machines had a single processor.

This does not scale, code is ugly and source of huge latencies
(Typically 30 ms have been seen, cpus spinning on death_lock spinlock.)

We can afford to use an extra 64 bytes per timewait sock and spread
timewait load to all cpus to have better behavior.

Tested:

On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1
on the target (lpaa24)

Before patch :

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
419594

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
437171

While test is running, we can observe 25 or even 33 ms latencies.

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms
rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms
rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2

After patch :

About 90% increase of throughput :

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
810442

lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0
800992

And latencies are kept to minimal values during this load, even
if network utilization is 90% higher :

lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23
...
1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms
rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Lookup key for tcp_md5_do_lookup() has to be taken
from addr_sk, not sk (which can be the listener)

Fixes: fd3a154a ("tcp: md5: get rid of tcp_v[46]_reqsk_md5_lookup()")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ipv4 code uses a mixture of coding styles. In some instances check
for non-NULL pointer is done as x != NULL and sometimes as x. x is
preferred according to checkpatch and this patch makes the code
consistent by adopting the latter form.

No changes detected by objdiff.
Signed-off-by: NIan Morris <ipm@chirality.org.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ipv4 code uses a mixture of coding styles. In some instances check
for NULL pointer is done as x == NULL and sometimes as !x. !x is
preferred according to checkpatch and this patch makes the code
consistent by adopting the latter form.

No changes detected by objdiff.
Signed-off-by: NIan Morris <ipm@chirality.org.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit 1fb6f159 ("tcp: add tcp_conn_request"),
tcp_syn_flood_action() is no longer used from IPv6.

We can make it static, by moving it above tcp_conn_request()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NOctavian Purdila <octavian.purdila@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ss should display ipv4 mapped request sockets like this :

tcp    SYN-RECV   0      0  ::ffff:192.168.0.1:8080   ::ffff:192.0.2.1:35261

and not like this :

tcp    SYN-RECV   0      0  192.168.0.1:8080   192.0.2.1:35261

We should init ireq->ireq_family based on listener sk_family,
not the actual protocol carried by SYN packet.

This means we can set ireq_family in inet_reqsk_alloc()

Fixes: 3f66b083 ("inet: introduce ireq_family")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With request socks convergence, we no longer need
different lookup methods. A request socket can
use generic lookup function.

Add const qualifier to 2nd tcp_v[46]_md5_lookup() parameter.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since request and established sockets now have same base,
there is no need to pass two pointers to tcp_v4_md5_hash_skb()
or tcp_v6_md5_hash_skb()

Also add a const qualifier to their struct tcp_md5sig_key argument.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is guaranteed that both tcp_v4_rcv() and tcp_v6_rcv()
run from rcu read locked sections :

ip_local_deliver_finish() and ip6_input_finish() both
use rcu_read_lock()

Also align tcp_v6_inbound_md5_hash() on tcp_v4_inbound_md5_hash()
by returning a boolean.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On s390x, gcc 4.8 compiles this part of tcp_v6_early_demux()

        struct dst_entry *dst = sk->sk_rx_dst;

        if (dst)
                dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);

to code reading sk->sk_rx_dst twice, once for the test and once for
the argument of ip6_dst_check() (dst_check() is inline). This allows
ip6_dst_check() to be called with null first argument, causing a crash.

Protect sk->sk_rx_dst access by READ_ONCE() both in IPv4 and IPv6
TCP early demux code.

Fixes: 41063e9d ("ipv4: Early TCP socket demux.")
Fixes: c7109986 ("ipv6: Early TCP socket demux")
Signed-off-by: NMichal Kubecek <mkubecek@suse.cz>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Eric Hugne reported following error :

I'm hitting this warning on latest net-next when i try to SSH into a machine
with eth0 added to a bridge (but i think the problem is older than that)

Steps to reproduce:
node2 ~ # brctl addif br0 eth0
[  223.758785] device eth0 entered promiscuous mode
node2 ~ # ip link set br0 up
[  244.503614] br0: port 1(eth0) entered forwarding state
[  244.505108] br0: port 1(eth0) entered forwarding state
node2 ~ # [  251.160159] ------------[ cut here ]------------
[  251.160831] WARNING: CPU: 0 PID: 3 at include/net/request_sock.h:102 tcp_v4_err+0x6b1/0x720()
[  251.162077] Modules linked in:
[  251.162496] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 4.0.0-rc3+ #18
[  251.163334] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  251.164078]  ffffffff81a8365c ffff880038a6ba18 ffffffff8162ace4 0000000000009898
[  251.165084]  0000000000000000 ffff880038a6ba58 ffffffff8104da85 ffff88003fa437c0
[  251.166195]  ffff88003fa437c0 ffff88003fa74e00 ffff88003fa43bb8 ffff88003fad99a0
[  251.167203] Call Trace:
[  251.167533]  [<ffffffff8162ace4>] dump_stack+0x45/0x57
[  251.168206]  [<ffffffff8104da85>] warn_slowpath_common+0x85/0xc0
[  251.169239]  [<ffffffff8104db65>] warn_slowpath_null+0x15/0x20
[  251.170271]  [<ffffffff81559d51>] tcp_v4_err+0x6b1/0x720
[  251.171408]  [<ffffffff81630d03>] ? _raw_read_lock_irq+0x3/0x10
[  251.172589]  [<ffffffff81534e20>] ? inet_del_offload+0x40/0x40
[  251.173366]  [<ffffffff81569295>] icmp_socket_deliver+0x65/0xb0
[  251.174134]  [<ffffffff815693a2>] icmp_unreach+0xc2/0x280
[  251.174820]  [<ffffffff8156a82d>] icmp_rcv+0x2bd/0x3a0
[  251.175473]  [<ffffffff81534ea2>] ip_local_deliver_finish+0x82/0x1e0
[  251.176282]  [<ffffffff815354d8>] ip_local_deliver+0x88/0x90
[  251.177004]  [<ffffffff815350f0>] ip_rcv_finish+0xf0/0x310
[  251.177693]  [<ffffffff815357bc>] ip_rcv+0x2dc/0x390
[  251.178336]  [<ffffffff814f5da3>] __netif_receive_skb_core+0x713/0xa20
[  251.179170]  [<ffffffff814f7fca>] __netif_receive_skb+0x1a/0x80
[  251.179922]  [<ffffffff814f97d4>] process_backlog+0x94/0x120
[  251.180639]  [<ffffffff814f9612>] net_rx_action+0x1e2/0x310
[  251.181356]  [<ffffffff81051267>] __do_softirq+0xa7/0x290
[  251.182046]  [<ffffffff81051469>] run_ksoftirqd+0x19/0x30
[  251.182726]  [<ffffffff8106cc23>] smpboot_thread_fn+0x153/0x1d0
[  251.183485]  [<ffffffff8106cad0>] ? SyS_setgroups+0x130/0x130
[  251.184228]  [<ffffffff8106935e>] kthread+0xee/0x110
[  251.184871]  [<ffffffff81069270>] ? kthread_create_on_node+0x1b0/0x1b0
[  251.185690]  [<ffffffff81631108>] ret_from_fork+0x58/0x90
[  251.186385]  [<ffffffff81069270>] ? kthread_create_on_node+0x1b0/0x1b0
[  251.187216] ---[ end trace c947fc7b24e42ea1 ]---
[  259.542268] br0: port 1(eth0) entered forwarding state

Remove the double calls to reqsk_put()

[edumazet] :

I got confused because reqsk_timer_handler() _has_ to call
reqsk_put(req) after calling inet_csk_reqsk_queue_drop(), as
the timer handler holds a reference on req.
Signed-off-by: NFan Du <fan.du@intel.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NErik Hugne <erik.hugne@ericsson.com>
Fixes: fa76ce73 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_v4_err() can restrict lookups to ehash table, and not to listeners.

Note this patch creates the infrastructure, but this means that ICMP
messages for request sockets are ignored until complete conversion.

New tcp_req_err() helper is exported so that we can use it in IPv6
in following patch.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a low hanging fruit, as we'll get rid of syn_wait_lock eventually.

We hold syn_wait_lock for such small sections, that it makes no sense to use
a read/write lock. A spin lock is simply faster.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One of the major issue for TCP is the SYNACK rtx handling,
done by inet_csk_reqsk_queue_prune(), fired by the keepalive
timer of a TCP_LISTEN socket.

This function runs for awful long times, with socket lock held,
meaning that other cpus needing this lock have to spin for hundred of ms.

SYNACK are sent in huge bursts, likely to cause severe drops anyway.

This model was OK 15 years ago when memory was very tight.

We now can afford to have a timer per request sock.

Timer invocations no longer need to lock the listener,
and can be run from all cpus in parallel.

With following patch increasing somaxconn width to 32 bits,
I tested a listener with more than 4 million active request sockets,
and a steady SYNFLOOD of ~200,000 SYN per second.
Host was sending ~830,000 SYNACK per second.

This is ~100 times more what we could achieve before this patch.

Later, we will get rid of the listener hash and use ehash instead.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When request sock are put in ehash table, the whole notion
of having a previous request to update dl_next is pointless.

Also, following patch will get rid of big purge timer,
so we want to delete a request sock without holding listener lock.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to be able to use sk_ehashfn() for request socks,
we need to initialize their IPv6/IPv4 addresses.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Intent is to converge IPv4 & IPv6 inet_hash functions to
factorize code.

IPv4 sockets initialize sk_rcv_saddr and sk_v6_daddr
in this patch, thanks to new sk_daddr_set() and sk_rcv_saddr_set()
helpers.

__inet6_hash can now use sk_ehashfn() instead of a private
inet6_sk_ehashfn() and will simply use __inet_hash() in a
following patch.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a request socket is created, we do not cache ip route
dst entry, like for timewait sockets.

Let's use sk_fullsock() helper.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Before inserting request socks into general hash table,
fill their socket family.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ireq->ir_num contains local port, use it.

Also, get_openreq4() dumping listen_sk->refcnt makes litle sense.

inet_diag_fill_req() can also use ireq->ir_num
Signed-off-by: NEric Dumazet <edumazet@google.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>

Packetization Layer Path MTU Discovery works separately beside
Path MTU Discovery at IP level, different net namespace has
various requirements on which one to chose, e.g., a virutalized
container instance would require TCP PMTU to probe an usable
effective mtu for underlying tunnel, while the host would
employ classical ICMP based PMTU to function.

Hence making TCP PMTU mechanism per net namespace to decouple
two functionality. Furthermore the probe base MSS should also
be configured separately for each namespace.
Signed-off-by: NFan Du <fan.du@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit be9f4a44 ("ipv4: tcp: remove per net tcp_sock")
I tried to address contention on a socket lock, but the solution
I chose was horrible :

commit 3a7c384f ("ipv4: tcp: unicast_sock should not land outside
of TCP stack") addressed a selinux regression.

commit 0980e56e ("ipv4: tcp: set unicast_sock uc_ttl to -1")
took care of another regression.

commit b5ec8eea ("ipv4: fix ip_send_skb()") fixed another regression.

commit 811230cd ("tcp: ipv4: initialize unicast_sock sk_pacing_rate")
was another shot in the dark.

Really, just use a proper socket per cpu, and remove the skb_orphan()
call, to re-enable flow control.

This solves a serious problem with FQ packet scheduler when used in
hostile environments, as we do not want to allocate a flow structure
for every RST packet sent in response to a spoofed packet.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This work adds the possibility to define a per route/destination
congestion control algorithm. Generally, this opens up the possibility
for a machine with different links to enforce specific congestion
control algorithms with optimal strategies for each of them based
on their network characteristics, even transparently for a single
application listening on all links.

For our specific use case, this additionally facilitates deployment
of DCTCP, for example, applications can easily serve internal
traffic/dsts in DCTCP and external one with CUBIC. Other scenarios
would also allow for utilizing e.g. long living, low priority
background flows for certain destinations/routes while still being
able for normal traffic to utilize the default congestion control
algorithm. We also thought about a per netns setting (where different
defaults are possible), but given its actually a link specific
property, we argue that a per route/destination setting is the most
natural and flexible.

The administrator can utilize this through ip-route(8) by appending
"congctl [lock] <name>", where <name> denotes the name of a
congestion control algorithm and the optional lock parameter allows
to enforce the given algorithm so that applications in user space
would not be allowed to overwrite that algorithm for that destination.

The dst metric lookups are being done when a dst entry is already
available in order to avoid a costly lookup and still before the
algorithms are being initialized, thus overhead is very low when the
feature is not being used. While the client side would need to drop
the current reference on the module, on server side this can actually
even be avoided as we just got a flat-copied socket clone.

Joint work with Florian Westphal.
Suggested-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When I cooked commit c3658e8d ("tcp: fix possible NULL dereference in
tcp_vX_send_reset()") I missed other spots we could deref a NULL
skb_dst(skb)

Again, if a socket is provided, we do not need skb_dst() to get a
pointer to network namespace : sock_net(sk) is good enough.
Reported-by: NDann Frazier <dann.frazier@canonical.com>
Bisected-by: NDann Frazier <dann.frazier@canonical.com>
Tested-by: NDann Frazier <dann.frazier@canonical.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Fixes: ca777eff ("tcp: remove dst refcount false sharing for prequeue mode")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit ca777eff ("tcp: remove dst refcount false sharing for
prequeue mode") we have to relax check against skb dst in
tcp_v[46]_send_reset() if prequeue dropped the dst.

If a socket is provided, a full lookup was done to find this socket,
so the dst test can be skipped.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=88191Reported-by: NJaša Bartelj <jasa.bartelj@gmail.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NDaniel Borkmann <dborkman@redhat.com>
Fixes: ca777eff ("tcp: remove dst refcount false sharing for prequeue mode")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alternative to RPS/RFS is to use hardware support for multiple
queues.

Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.

Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.

We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.

After accept(), connect(), or even file descriptor passing around
processes, applications can use :

 int cpu;
 socklen_t len = sizeof(cpu);

 getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);

And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sk_mark_napi_id() is used to record for a flow napi id of incoming
packets for busypoll sake.
We should do this only on established flows, not on listeners.

This was 'working' by virtue of the socket cloning, but doing
this on SYN packets in unecessary cache line dirtying.

Even if we move sk_napi_id in the same cache line than sk_lock,
we are working to make SYN processing lockless, so it is desirable
to set sk_napi_id only for established flows.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The commit "net: Save TX flow hash in sock and set in skbuf on xmit"
introduced the inet_set_txhash() and ip6_set_txhash() routines to calculate
and record flow hash(sk_txhash) in the socket structure. sk_txhash is used
to set skb->hash which is used to spread flows across multiple TXQs.

But, the above routines are invoked before the source port of the connection
is created. Because of this all outgoing connections that just differ in the
source port get hashed into the same TXQ.

This patch fixes this problem for IPv4/6 by invoking the the above routines
after the source port is available for the socket.

Fixes: b73c3d0e("net: Save TX flow hash in sock and set in skbuf on xmit")
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We can retrieve opt from skb, no need to pass it as a parameter.
And opt should always be non-NULL, no need to check.

Cc: Krzysztof Kolasa <kkolasa@winsoft.pl>
Cc: Eric Dumazet <edumazet@google.com>
Tested-by: NKrzysztof Kolasa <kkolasa@winsoft.pl>
Signed-off-by: NCong Wang <cwang@twopensource.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

cookie_v4_check() allocates ip_options_rcu in the same way
with tcp_v4_save_options(), we can just make it a helper function.

Cc: Krzysztof Kolasa <kkolasa@winsoft.pl>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NCong Wang <cwang@twopensource.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP maintains lists of skb in write queue, and in receive queues
(in order and out of order queues)

Scanning these lists both in input and output path usually requires
access to skb->next, TCP_SKB_CB(skb)->seq, and TCP_SKB_CB(skb)->end_seq

These fields are currently in two different cache lines, meaning we
waste lot of memory bandwidth when these queues are big and flows
have either packet drops or packet reorders.

We can move TCP_SKB_CB(skb)->header at the end of TCP_SKB_CB, because
this header is not used in fast path. This allows TCP to search much faster
in the skb lists.

Even with regular flows, we save one cache line miss in fast path.

Thanks to Christoph Paasch for noticing we need to cleanup
skb->cb[] (IPCB/IP6CB) before entering IP stack in tx path,
and that I forgot IPCB use in tcp_v4_hnd_req() and tcp_v4_save_options().
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ip_options_echo() assumes struct ip_options is provided in &IPCB(skb)->opt
Lets break this assumption, but provide a helper to not change all call points.

ip_send_unicast_reply() gets a new struct ip_options pointer.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Per commit "77873803 net_dma: mark broken" net_dma is no longer used
and there is no plan to fix it.

This is the mechanical removal of bits in CONFIG_NET_DMA ifdef guards.
Reverting the remainder of the net_dma induced changes is deferred to
subsequent patches.

Marked for stable due to Roman's report of a memory leak in
dma_pin_iovec_pages():

    https://lkml.org/lkml/2014/9/3/177

Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Vinod Koul <vinod.koul@intel.com>
Cc: David Whipple <whipple@securedatainnovations.ch>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: <stable@vger.kernel.org>
Reported-by: NRoman Gushchin <klamm@yandex-team.ru>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

icsk_rto is a 32bit field, and icsk_backoff can reach 15 by default,
or more if some sysctl (eg tcp_retries2) are changed.

Better use 64bit to perform icsk_rto << icsk_backoff operations

As Joe Perches suggested, add a helper for this.

Yuchung spotted the tcp_v4_err() case.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Input path of TCP do not currently uses TCP_SKB_CB(skb)->tcp_flags,
which is only used in output path.

tcp_recvmsg(), looks at tcp_hdr(skb)->syn for every skb found in receive queue,
and its unfortunate because this bit is located in a cache line right before
the payload.

We can simplify TCP by copying tcp flags into TCP_SKB_CB(skb)->tcp_flags.

This patch does so, and avoids the cache line miss in tcp_recvmsg()

Following patches will
- allow a segment with FIN being coalesced in tcp_try_coalesce()
- simplify tcp_collapse() by not copying the headers.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexander Duyck reported high false sharing on dst refcount in tcp stack
when prequeue is used. prequeue is the mechanism used when a thread is
blocked in recvmsg()/read() on a TCP socket, using a blocking model
rather than select()/poll()/epoll() non blocking one.

We already try to use RCU in input path as much as possible, but we were
forced to take a refcount on the dst when skb escaped RCU protected
region. When/if the user thread runs on different cpu, dst_release()
will then touch dst refcount again.

Commit 09316255 (tcp: force a dst refcount when prequeue packet)
was an example of a race fix.

It turns out the only remaining usage of skb->dst for a packet stored
in a TCP socket prequeue is IP early demux.

We can add a logic to detect when IP early demux is probably going
to use skb->dst. Because we do an optimistic check rather than duplicate
existing logic, we need to guard inet_sk_rx_dst_set() and
inet6_sk_rx_dst_set() from using a NULL dst.

Many thanks to Alexander for providing a nice bug report, git bisection,
and reproducer.

Tested using Alexander script on a 40Gb NIC, 8 RX queues.
Hosts have 24 cores, 48 hyper threads.

echo 0 >/proc/sys/net/ipv4/tcp_autocorking

for i in `seq 0 47`
do
  for j in `seq 0 2`
  do
     netperf -H $DEST -t TCP_STREAM -l 1000 \
             -c -C -T $i,$i -P 0 -- \
             -m 64 -s 64K -D &
  done
done

Before patch : ~6Mpps and ~95% cpu usage on receiver
After patch : ~9Mpps and ~35% cpu usage on receiver.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit 740b0f18 ("tcp: switch rtt estimations to usec resolution"),
we no longer need to maintain timestamps in two different fields.

TCP_SKB_CB(skb)->when can be removed, as same information sits in skb_mstamp.stamp_jiffies
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>