At this point sk might contain garbage.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP listener refactoring, part 3 :

Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.

Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.

As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.

If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.

[ INET_TW_MATCH() is no longer needed ]

I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()

This way, SYN_RECV pseudo sockets will be supported the same.

A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].

Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()

Before patch :

dmesg | grep "TCP established"

TCP established hash table entries: 524288 (order: 11, 8388608 bytes)

After patch :

TCP established hash table entries: 524288 (order: 10, 4194304 bytes)
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The since the removal of the routing cache computing
fib_compute_spec_dst() does a fib_table lookup for each UDP multicast
packet received.  This has introduced a performance regression for some
UDP workloads.

This change skips populating the packet info for sockets that do not have
IP_PKTINFO set.

Benchmark results from a netperf UDP_RR test:
Before 89789.68 transactions/s
After  90587.62 transactions/s

Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.63us RTT
After  12.48us RTT
Signed-off-by: NShawn Bohrer <sbohrer@rgmadvisors.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The removal of the routing cache introduced a performance regression for
some UDP workloads since a dst lookup must be done for each packet.
This change caches the dst per socket in a similar manner to what we do
for TCP by implementing early_demux.

For UDP multicast we can only cache the dst if there is only one
receiving socket on the host.  Since caching only works when there is
one receiving socket we do the multicast socket lookup using RCU.

For UDP unicast we only demux sockets with an exact match in order to
not break forwarding setups.  Additionally since the hash chains may be
long we only check the first socket to see if it is a match and not
waste extra time searching the whole chain when we might not find an
exact match.

Benchmark results from a netperf UDP_RR test:
Before 87961.22 transactions/s
After  89789.68 transactions/s

Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.97us RTT
After  12.63us RTT
Signed-off-by: NShawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

UDP sockets can receive packets from multiple endpoints and thus may be
received on multiple receive queues.  Since packets packets can arrive
on multiple receive queues we should not mark the napi_id for all
packets.  This makes busy read/poll only work for connected UDP sockets.

This additionally enables busy read/poll for UDP multicast packets as
long as the socket is connected by moving the check into
__udp_queue_rcv_skb().
Signed-off-by: NShawn Bohrer <sbohrer@rgmadvisors.com>
Suggested-by: NEric Dumazet <edumazet@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When sending out multicast messages, the source address in inet->mc_addr is
ignored and rewritten by an autoselected one. This is caused by a typo in
commit 813b3b5d ("ipv4: Use caller's on-stack flowi as-is in output
route lookups").
Signed-off-by: NJiri Benc <jbenc@redhat.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Yuchung found following problem :

 There are bugs in the SACK processing code, merging part in
 tcp_shift_skb_data(), that incorrectly resets or ignores the sacked
 skbs FIN flag. When a receiver first SACK the FIN sequence, and later
 throw away ofo queue (e.g., sack-reneging), the sender will stop
 retransmitting the FIN flag, and hangs forever.

Following packetdrill test can be used to reproduce the bug.

$ cat sack-merge-bug.pkt
`sysctl -q net.ipv4.tcp_fack=0`

// Establish a connection and send 10 MSS.
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+.000 bind(3, ..., ...) = 0
+.000 listen(3, 1) = 0

+.050 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+.000 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.001 < . 1:1(0) ack 1 win 1024
+.000 accept(3, ..., ...) = 4

+.100 write(4, ..., 12000) = 12000
+.000 shutdown(4, SHUT_WR) = 0
+.000 > . 1:10001(10000) ack 1
+.050 < . 1:1(0) ack 2001 win 257
+.000 > FP. 10001:12001(2000) ack 1
+.050 < . 1:1(0) ack 2001 win 257 <sack 10001:11001,nop,nop>
+.050 < . 1:1(0) ack 2001 win 257 <sack 10001:12002,nop,nop>
// SACK reneg
+.050 < . 1:1(0) ack 12001 win 257
+0 %{ print "unacked: ",tcpi_unacked }%
+5 %{ print "" }%

First, a typo inverted left/right of one OR operation, then
code forgot to advance end_seq if the merged skb carried FIN.

Bug was added in 2.6.29 by commit 832d11c5
("tcp: Try to restore large SKBs while SACK processing")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Acked-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While working on tcp listener refactoring, I found that it
would really make things easier if sock_common could include
the IPv6 addresses needed in the lookups, instead of doing
very complex games to get their values (depending on sock
being SYN_RECV, ESTABLISHED, TIME_WAIT)

For this to happen, I need to be sure that tcp6_timewait_sock
and tcp_timewait_sock consume same number of cache lines.

This is possible if we only use 32bits for tw_ttd, as we remove
one 32bit hole in inet_timewait_sock

inet_tw_time_stamp() is defined and used, even if its current
implementation looks like tcp_time_stamp : We might need finer
resolution for tcp_time_stamp in the future.

Before patch : sizeof(struct tcp6_timewait_sock) = 0xc8

After patch : sizeof(struct tcp6_timewait_sock) = 0xc0
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The variable fully_acked is only assigned the values true and false.
Change its type to bool.

The simplified semantic patch that find this problem is as
follows (http://coccinelle.lip6.fr/):

@exists@
type T;
identifier b;
@@
- T
+ bool
  b = ...;
  ... when any
  b = \(true\|false\)
Signed-off-by: NPeter Senna Tschudin <peter.senna@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP listener refactoring, part 2 :

We can use a generic lookup, sockets being in whatever state, if
we are sure all relevant fields are at the same place in all socket
types (ESTABLISH, TIME_WAIT, SYN_RECV)

This patch removes these macros :

 inet_addrpair, inet_addrpair, tw_addrpair, tw_portpair

And adds :

 sk_portpair, sk_addrpair, sk_daddr, sk_rcv_saddr

Then, INET_TW_MATCH() is really the same than INET_MATCH()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 3ab5aee7 ("net: Convert TCP & DCCP hash tables to use RCU /
hlist_nulls") incorrectly used sock_put() on TIMEWAIT sockets.

We should instead use inet_twsk_put()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_fixup_sndbuf() is underestimating initial send buffer requirements.

It was not noticed because big GSO packets were escaping the limitation,
but with smaller TSO packets (or TSO/GSO/SG off), application hits
sk_sndbuf before having a chance to fill enough packets in socket write
queue.

- initial cwnd can be bigger than 10 for specific routes

- SKB_TRUESIZE() is a bit under real needs in some cases,
  because of power-of-two rounding in kmalloc()

- Fast Recovery (RFC 5681 3.2) : Cubic needs 70% factor

- Extra cushion (application might react slowly to POLLOUT)

tcp_v4_conn_req_fastopen() needs to call tcp_init_metrics() before
calling tcp_init_buffer_space()

Then we realize tcp_new_space() should call tcp_fixup_sndbuf()
instead of duplicating this stuff.

Rename tcp_fixup_sndbuf() to tcp_sndbuf_expand() to be more
descriptive.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NMaciej Żenczykowski <maze@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Because 'node' is the i'st child of 'oldnode',
thus, here 'i' equals
tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits)

we just get 1 more bit,
and need not care the detail value of this bits.

I apologize for the mistake.

I generated the patch on a branch version,
and did not notice the put_child has been changed.

I have redone the test on HEAD version with my patch.

two cases are used.
case 1. inflate a node which has a leaf child node.
case 2: inflate a node which has a an child node with skipped bits

test env:
  ip link set eth0 up
  ip a add dev eth0 192.168.11.1/32
here, we just focus on route table(MAIN),
so I use a "192.168.11.1/32" address to simplify the test case.

call trace:
+ fib_insert_node
+ + trie_rebalance
+ + + resize
+ + + + inflate

Test case 1:  inflate a node which has a leaf child node.

===========================================================
step 1. prepare a fib trie
------------------------------------------
  ip r a 192.168.0.0/24 via 192.168.11.1
  ip r a 192.168.1.0/24 via 192.168.11.1

we get a fib trie.
root@baker:~# cat /proc/net/fib_trie
Main:
  +-- 192.168.0.0/23 1 0 0
   |-- 192.168.0.0
    /24 universe UNICAST
   |-- 192.168.1.0
    /24 universe UNICAST
Local:
.....

step 2. Add the third route
------------------------------------------
root@baker:~# ip r a 192.168.2.0/24 via 192.168.11.1

A fib_trie leaf will be inserted in fib_insert_node before trie_rebalance.

For function 'inflate':
'inflate' is called with following trie.
  +-- 192.168.0.0/22 1 1 0 <=== tn node
    +-- 192.168.0.0/23 1 0 0    <== node a
        |-- 192.168.0.0
          /24 universe UNICAST
        |-- 192.168.1.0
          /24 universe UNICAST
      |-- 192.168.2.0          <== leaf(node b)

When process node b, which is a leaf. here:
i is 1,
node key "192.168.2.0"
oldnode is (pos:22, bits:1)

unpatch source:
tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1)
it equals:
tkey_extract_bits("192.168,2,0", 22 + 1, 1)

thus got 0, and call put_child(tn, 2*i, node); <== 2*i=2.

patched source:
tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits + 1),
tkey_extract_bits("192.168,2,0", 22, 1 + 1)  <== get 2.

Test case 2:  inflate a node which has a an child node with skipped bits
==========================================================================
step 1. prepare a fib trie.
  ip link set eth0 up
  ip a add dev eth0 192.168.11.1/32
  ip r a 192.168.128.0/24 via 192.168.11.1
  ip r a 192.168.0.0/24  via 192.168.11.1
  ip r a 192.168.16.0/24   via 192.168.11.1
  ip r a 192.168.32.0/24  via 192.168.11.1
  ip r a 192.168.48.0/24  via 192.168.11.1
  ip r a 192.168.144.0/24   via 192.168.11.1
  ip r a 192.168.160.0/24   via 192.168.11.1
  ip r a 192.168.176.0/24   via 192.168.11.1

check:
root@baker:~# cat /proc/net/fib_trie
Main:
  +-- 192.168.0.0/16 1 0 0
     +-- 192.168.0.0/18 2 0 0
        |-- 192.168.0.0
           /24 universe UNICAST
        |-- 192.168.16.0
           /24 universe UNICAST
        |-- 192.168.32.0
           /24 universe UNICAST
        |-- 192.168.48.0
           /24 universe UNICAST
     +-- 192.168.128.0/18 2 0 0
        |-- 192.168.128.0
           /24 universe UNICAST
        |-- 192.168.144.0
           /24 universe UNICAST
        |-- 192.168.160.0
           /24 universe UNICAST
        |-- 192.168.176.0
           /24 universe UNICAST
Local:
  ...

step 2. add a route to trigger inflate.
  ip r a 192.168.96.0/24   via 192.168.11.1

This command will call serveral times inflate.
In the first time, the fib_trie is:
________________________
+-- 192.168.128.0/(16, 1) <== tn node
 +-- 192.168.0.0/(17, 1)  <== node a
  +-- 192.168.0.0/(18, 2)
   |-- 192.168.0.0
   |-- 192.168.16.0
   |-- 192.168.32.0
   |-- 192.168.48.0
  |-- 192.168.96.0
 +-- 192.168.128.0/(18, 2) <== node b.
  |-- 192.168.128.0
  |-- 192.168.144.0
  |-- 192.168.160.0
  |-- 192.168.176.0

NOTE: node b is a interal node with skipped bits.
here,
i:1,
node->key "192.168.128.0",
oldnode:(pos:16, bits:1)
so
tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1)
it equals:
tkey_extract_bits("192.168,128,0", 16 + 1, 1) <=== 0

tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits, 1)
it equals:
tkey_extract_bits("192.168,128,0", 16, 1+1) <=== 2

2*i + 0 == 2, so the result is same.
Signed-off-by: Nbaker.zhang <baker.kernel@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_established_options assumes opts->options is 0 before calling,
as it read modify writes it.

For the tcp_current_mss() case the opts structure is not zeroed,
so this can be done with uninitialized values.

This is ok, because ->options is not read in this path.
But it's still better to avoid the operation on the uninitialized
field. This shuts up a static code analyzer, and presumably
may help the optimizer.

Cc: netdev@vger.kernel.org
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When queueing the netdevices for removal, we queue the
fallback device twice in ip_tunnel_destroy(). The first
time when we queue all netdevices in the namespace and
then again explicitly. Fix this by removing the explicit
queueing of the fallback device.

Bug was introduced when network namespace support was added
with commit 6c742e71 ("ipip: add x-netns support").

Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NSteffen Klassert <steffen.klassert@secunet.com>
Acked-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Git commit 0e6fbc5b ("ip_tunnels: extend iptunnel_xmit()")
moved the IP header installation to iptunnel_xmit() and
changed skb_push() to __skb_push(). This makes possible
bugs hard to track down, so change it back to skb_push().

Cc: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: NSteffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently we can not update the tunnel parameters of
the fallback tunnels because we don't find them in the
hash lists. Fix this by adding them on initialization.

Bug was introduced with commit c5441932
("GRE: Refactor GRE tunneling code.")

Cc: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: NSteffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We might extend the used aera of a skb beyond the total
headroom when we install the ipip header. Fix this by
calling skb_cow_head() unconditionally.

Bug was introduced with commit c5441932
("GRE: Refactor GRE tunneling code.")

Cc: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: NSteffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is possible for the timer handlers to run after the call to
ip_mc_down so use in_dev_put instead of __in_dev_put in the handler
function in order to do proper cleanup when the refcnt reaches 0.
Otherwise, the refcnt can reach zero without the in_device being
destroyed and we end up leaking a reference to the net_device and
see messages like the following,

unregister_netdevice: waiting for eth0 to become free. Usage count = 1

Tested on linux-3.4.43.
Signed-off-by: NSalam Noureddine <noureddine@aristanetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- Move sysctl_local_ports from a global variable into struct netns_ipv4.
- Modify inet_get_local_port_range to take a struct net, and update all
  of the callers.
- Move the initialization of sysctl_local_ports into
   sysctl_net_ipv4.c:ipv4_sysctl_init_net from inet_connection_sock.c

v2:
- Ensure indentation used tabs
- Fixed ip.h so it applies cleanly to todays net-next

v3:
- Compile fixes of strange callers of inet_get_local_port_range.
  This patch now successfully passes an allmodconfig build.
  Removed manual inlining of inet_get_local_port_range in ipv4_local_port_range
Originally-by: NSamya <samya@twitter.com>
Acked-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When TCP Small Queues was added, we used a sysctl to limit amount of
packets queues on Qdisc/device queues for a given TCP flow.

Problem is this limit is either too big for low rates, or too small
for high rates.

Now TCP stack has rate estimation in sk->sk_pacing_rate, and TSO
auto sizing, it can better control number of packets in Qdisc/device
queues.

New limit is two packets or at least 1 to 2 ms worth of packets.

Low rates flows benefit from this patch by having even smaller
number of packets in queues, allowing for faster recovery,
better RTT estimations.

High rates flows benefit from this patch by allowing more than 2 packets
in flight as we had reports this was a limiting factor to reach line
rate. [ In particular if TX completion is delayed because of coalescing
parameters ]

Example for a single flow on 10Gbp link controlled by FQ/pacing

14 packets in flight instead of 2

$ tc -s -d qd
qdisc fq 8001: dev eth0 root refcnt 32 limit 10000p flow_limit 100p
buckets 1024 quantum 3028 initial_quantum 15140
 Sent 1168459366606 bytes 771822841 pkt (dropped 0, overlimits 0
requeues 6822476)
 rate 9346Mbit 771713pps backlog 953820b 14p requeues 6822476
  2047 flow, 2046 inactive, 1 throttled, delay 15673 ns
  2372 gc, 0 highprio, 0 retrans, 9739249 throttled, 0 flows_plimit

Note that sk_pacing_rate is currently set to twice the actual rate, but
this might be refined in the future when a flow is in congestion
avoidance.

Additional change : skb->destructor should be set to tcp_wfree().

A future patch (for linux 3.13+) might remove tcp_limit_output_bytes
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While sending packet skb_cow_head() can change skb header which
invalidates inner_iph pointer to skb header. Following patch
avoid using it. Found by code inspection.

This bug was introduced by commit 0e6fbc5b (ip_tunnels: extend
iptunnel_xmit()).
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP packets hitting the SYN proxy through the SYNPROXY target are not
validated by TCP conntrack. When th->doff is below 5, an underflow happens
when calculating the options length, causing skb_header_pointer() to
return NULL and triggering the BUG_ON().

Handle this case gracefully by checking for NULL instead of using BUG_ON().
Reported-by: NMartin Topholm <mph@one.com>
Tested-by: NMartin Topholm <mph@one.com>
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

As mentioned in commit afe4fd06 ("pkt_sched: fq: Fair Queue packet
scheduler"), this patch adds a new socket option.

SO_MAX_PACING_RATE offers the application the ability to cap the
rate computed by transport layer. Value is in bytes per second.

u32 val = 1000000;
setsockopt(sockfd, SOL_SOCKET, SO_MAX_PACING_RATE, &val, sizeof(val));

To be effectively paced, a flow must use FQ packet scheduler.

Note that a packet scheduler takes into account the headers for its
computations. The effective payload rate depends on MSS and retransmits
if any.

I chose to make this pacing rate a SOL_SOCKET option instead of a
TCP one because this can be used by other protocols.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If IP_TOS or IP_TTL are specified as ancillary data, then sendmsg() sends out
packets with the specified TTL or TOS overriding the socket values specified
with the traditional setsockopt().

The struct inet_cork stores the values of TOS, TTL and priority that are
passed through the struct ipcm_cookie. If there are user-specified TOS
(tos != -1) or TTL (ttl != 0) in the struct ipcm_cookie, these values are
used to override the per-socket values. In case of TOS also the priority
is changed accordingly.

Two helper functions get_rttos and get_rtconn_flags are defined to take
into account the presence of a user specified TOS value when computing
RT_TOS and RT_CONN_FLAGS.
Signed-off-by: NFrancesco Fusco <ffusco@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch enables the IP_TTL and IP_TOS values passed from userspace to
be stored in the ipcm_cookie struct. Three fields are added to the struct:

- the TTL, expressed as __u8.
  The allowed values are in the [1-255].
  A value of 0 means that the TTL is not specified.

- the TOS, expressed as __s16.
  The allowed values are in the range [0,255].
  A value of -1 means that the TOS is not specified.

- the priority, expressed as a char and computed when
  handling the ancillary data.
Signed-off-by: NFrancesco Fusco <ffusco@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A host might need net_secret[] and never open a single socket.

Problem added in commit aebda156
("net: defer net_secret[] initialization")

Based on prior patch from Hannes Frederic Sowa.
Reported-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NHannes Frederic Sowa <hannes@strressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Dynamic Right Sizing (DRS) is supposed to open TCP receive window
automatically, but suffers from two bugs, presented by order
of importance.

1) tcp_rcv_space_adjust() fix :

Using twice the last received amount is very pessimistic,
because it doesn't allow fast recovery or proper slow start
ramp up, if sender wants to increase cwin by 100% every RTT.

copied = bytes received in previous RTT

2*copied = bytes we expect to receive in next RTT

4*copied = bytes we need to advertise in rwin at end of next RTT

DRS is one RTT late, it needs a 4x factor.

If sender is not using ABC, and increases cwin by 50% every rtt,
then we needed 1.5*1.5 = 2.25 factor.
This is probably why this bug was not really noticed.

2) There is no window adjustment after first RTT. DRS triggers only
  after the second RTT.
  DRS needs two RTT to initialize, so tcp_fixup_rcvbuf() should setup
  sk_rcvbuf to allow proper window grow for first two RTT.

This patch increases TCP efficiency particularly for large RTT flows
when autotuning is used at the receiver, and more particularly
in presence of packet losses.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Cc: Van Jacobson <vanj@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Halve mss table size to make blind cookie guessing more difficult.
This is sad since the tables were already small, but there
is little alternative except perhaps adding more precise mss information
in the tcp timestamp.  Timestamps are unfortunately not ubiquitous.

Guessing all possible cookie values still has 8-in 2**32 chance.
Reported-by: NJakob Lell <jakob@jakoblell.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We currently accept cookies that were created less than 4 minutes ago
(ie, cookies with counter delta 0-3).  Combined with the 8 mss table
values, this yields 32 possible values (out of 2**32) that will be valid.

Reducing the lifetime to < 2 minutes halves the guessing chance while
still providing a large enough period.

While at it, get rid of jiffies value -- they overflow too quickly on
32 bit platforms.

getnstimeofday is used to create a counter that increments every 64s.
perf shows getnstimeofday cost is negible compared to sha_transform;
normal tcp initial sequence number generation uses getnstimeofday, too.
Reported-by: NJakob Lell <jakob@jakoblell.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Redirect isn't an error condition, it should leave
the error handler without touching the socket.
Signed-off-by: NDuan Jiong <duanj.fnst@cn.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Redirect isn't an error condition, it should leave
the error handler without touching the socket.
Signed-off-by: NDuan Jiong <duanj.fnst@cn.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If local fragmentation is allowed, then ip_select_ident() and
ip_select_ident_more() need to generate unique IDs to ensure
correct defragmentation on the peer.

For example, if IPsec (tunnel mode) has to encrypt large skbs
that have local_df bit set, then all IP fragments that belonged
to different ESP datagrams would have used the same identificator.
If one of these IP fragments would get lost or reordered, then
peer could possibly stitch together wrong IP fragments that did
not belong to the same datagram. This would lead to a packet loss
or data corruption.
Signed-off-by: NAnsis Atteka <aatteka@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb->data already points to IP header, but for the sake of
consistency we can also use ip_hdr() to retrieve it.
Signed-off-by: NAnsis Atteka <aatteka@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 1b7fdd2a ("tcp: do not use cached RTT for RTT estimation")
did not correctly account for the fact that crtt is the RTT shifted
left 3 bits. Fix the calculation to consistently reflect this fact.
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Acked-By: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RESOURCE_MAX is far too general name, change it to RES_COUNTER_MAX.
Signed-off-by: NSha Zhengju <handai.szj@taobao.com>
Signed-off-by: NQiang Huang <h.huangqiang@huawei.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Jeff Liu <jeff.liu@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

TCP receive window handling is multi staged.

A socket has a memory budget, static or dynamic, in sk_rcvbuf.

Because we do not really know how this memory budget translates to
a TCP window (payload), TCP announces a small initial window
(about 20 MSS).

When a packet is received, we increase TCP rcv_win depending
on the payload/truesize ratio of this packet. Good citizen
packets give a hint that it's reasonable to have rcv_win = sk_rcvbuf/2

This heuristic takes place in tcp_grow_window()

Problem is : We currently call tcp_grow_window() only for in-order
packets.

This means that reorders or packet losses stop proper grow of
rcv_win, and senders are unable to benefit from fast recovery,
or proper reordering level detection.

Really, a packet being stored in OFO queue is not a bad citizen.
It should be part of the game as in-order packets.

In our traces, we very often see sender is limited by linux small
receive windows, even if linux hosts use autotuning (DRS) and should
allow rcv_win to grow to ~3MB.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit 0f7cc9a3 "tcp: increase throughput when reordering is high",
it only allows cwnd to increase in Open state. This mistakenly disables
slow start after timeout (CA_Loss). Moreover cwnd won't grow if the
state moves from Disorder to Open later in tcp_fastretrans_alert().

Therefore the correct logic should be to allow cwnd to grow as long
as the data is received in order in Open, Loss, or even Disorder state.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDave Jones <davej@fedoraproject.org>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>