linux-toradex.git/include/net/request_sock.h, branch v4.5-rc3

net: add inet_sk_transparent() helper

2015-12-22T22:03:05+00:00

Avoids cluttering tcp_v4_send_reset when followup patch extends
it to deal with timewait sockets.

Suggested-by: Eric Dumazet 
Signed-off-by: Florian Westphal 
Acked-by: Eric Dumazet 
Acked-by: Hannes Frederic Sowa 
Signed-off-by: David S. Miller

tcp/dccp: fix race at listener dismantle phase

2015-10-16T07:52:19+00:00

Under stress, a close() on a listener can trigger the
WARN_ON(sk->sk_ack_backlog) in inet_csk_listen_stop()

We need to test if listener is still active before queueing
a child in inet_csk_reqsk_queue_add()

Create a common inet_child_forget() helper, and use it
from inet_csk_reqsk_queue_add() and inet_csk_listen_stop()

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: shrink struct sock and request_sock by 8 bytes

2015-10-13T02:28:22+00:00

One 32bit hole is following skc_refcnt, use it.
skc_incoming_cpu can also be an union for request_sock rcv_wnd.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: align sk_refcnt on 128 bytes boundary

2015-10-13T02:28:22+00:00

sk->sk_refcnt is dirtied for every TCP/UDP incoming packet.
This is a performance issue if multiple cpus hit a common socket,
or multiple sockets are chained due to SO_REUSEPORT.

By moving sk_refcnt 8 bytes further, first 128 bytes of sockets
are mostly read. As they contain the lookup keys, this has
a considerable performance impact, as cpus can cache them.

These 8 bytes are not wasted, we use them as a place holder
for various fields, depending on the socket type.

Tested:
 SYN flood hitting a 16 RX queues NIC.
 TCP listener using 16 sockets and SO_REUSEPORT
 and SO_INCOMING_CPU for proper siloing.

 Could process 6.0 Mpps SYN instead of 4.2 Mpps

 Kernel profile looked like :
    11.68%  [kernel]  [k] sha_transform
     6.51%  [kernel]  [k] __inet_lookup_listener
     5.07%  [kernel]  [k] __inet_lookup_established
     4.15%  [kernel]  [k] memcpy_erms
     3.46%  [kernel]  [k] ipt_do_table
     2.74%  [kernel]  [k] fib_table_lookup
     2.54%  [kernel]  [k] tcp_make_synack
     2.34%  [kernel]  [k] tcp_conn_request
     2.05%  [kernel]  [k] __netif_receive_skb_core
     2.03%  [kernel]  [k] kmem_cache_alloc

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

tcp: avoid two atomic ops for syncookies

2015-10-05T09:45:27+00:00

inet_reqsk_alloc() is used to allocate a temporary request
in order to generate a SYNACK with a cookie. Then later,
syncookie validation also uses a temporary request.

These paths already took a reference on listener refcount,
we can avoid a couple of atomic operations.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: use sk_fullsock() in __netdev_pick_tx()

2015-10-05T09:45:25+00:00

SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a
sk_dst_cache pointer.

Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

tcp/dccp: add SLAB_DESTROY_BY_RCU flag for request sockets

2015-10-03T20:25:20+00:00

Before letting request sockets being put in TCP/DCCP regular
ehash table, we need to add either :

- SLAB_DESTROY_BY_RCU flag to their kmem_cache
- add RCU grace period before freeing them.

Since we carefully respected the SLAB_DESTROY_BY_RCU protocol
like ESTABLISH and TIMEWAIT sockets, use it here.

req_prot_init() being only used by TCP and DCCP, I did not add
a new slab_flags into their rsk_prot, but reuse prot->slab_flags

Since all reqsk_alloc() users are correctly dealing with a failure,
add the __GFP_NOWARN flag to avoid traces under pressure.

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

tcp: remove max_qlen_log

2015-10-03T11:32:44+00:00

This control variable was set at first listen(fd, backlog)
call, but not updated if application tried to increase or decrease
backlog. It made sense at the time listener had a non resizeable
hash table.

Also rounding to powers of two was not very friendly.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

tcp/dccp: remove struct listen_sock

2015-10-03T11:32:43+00:00

It is enough to check listener sk_state, no need for an extra
condition.

max_qlen_log can be moved into struct request_sock_queue

We can remove syn_wait_lock and the alignment it enforced.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

tcp/dccp: shrink struct listen_sock

2015-10-03T11:32:42+00:00

We no longer use hash_rnd, nr_table_entries and syn_table[]

For a listener with a backlog of 10 millions sockets, this
saves 80 MBytes of vmalloced memory.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller