diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-03 00:38:27 +0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-03 00:38:27 +0400 |
commit | aecdc33e111b2c447b622e287c6003726daa1426 (patch) | |
tree | 3e7657eae4b785e1a1fb5dfb225dbae0b2f0cfc6 /net/ipv4/inet_connection_sock.c | |
parent | a20acf99f75e49271381d65db097c9763060a1e8 (diff) | |
parent | a3a6cab5ea10cca64d036851fe0d932448f2fe4f (diff) | |
download | linux-aecdc33e111b2c447b622e287c6003726daa1426.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking changes from David Miller:
1) GRE now works over ipv6, from Dmitry Kozlov.
2) Make SCTP more network namespace aware, from Eric Biederman.
3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.
4) Make openvswitch network namespace aware, from Pravin B Shelar.
5) IPV6 NAT implementation, from Patrick McHardy.
6) Server side support for TCP Fast Open, from Jerry Chu and others.
7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
Borkmann.
8) Increate the loopback default MTU to 64K, from Eric Dumazet.
9) Use a per-task rather than per-socket page fragment allocator for
outgoing networking traffic. This benefits processes that have very
many mostly idle sockets, which is quite common.
From Eric Dumazet.
10) Use up to 32K for page fragment allocations, with fallbacks to
smaller sizes when higher order page allocations fail. Benefits are
a) less segments for driver to process b) less calls to page
allocator c) less waste of space.
From Eric Dumazet.
11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.
12) VXLAN device driver, one way to handle VLAN issues such as the
limitation of 4096 VLAN IDs yet still have some level of isolation.
From Stephen Hemminger.
13) As usual there is a large boatload of driver changes, with the scale
perhaps tilted towards the wireless side this time around.
Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
hyperv: Add buffer for extended info after the RNDIS response message.
hyperv: Report actual status in receive completion packet
hyperv: Remove extra allocated space for recv_pkt_list elements
hyperv: Fix page buffer handling in rndis_filter_send_request()
hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
hyperv: Fix the max_xfer_size in RNDIS initialization
vxlan: put UDP socket in correct namespace
vxlan: Depend on CONFIG_INET
sfc: Fix the reported priorities of different filter types
sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
sfc: Fix loopback self-test with separate_tx_channels=1
sfc: Fix MCDI structure field lookup
sfc: Add parentheses around use of bitfield macro arguments
sfc: Fix null function pointer in efx_sriov_channel_type
vxlan: virtual extensible lan
igmp: export symbol ip_mc_leave_group
netlink: add attributes to fdb interface
tg3: unconditionally select HWMON support when tg3 is enabled.
Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
gre: fix sparse warning
...
Diffstat (limited to 'net/ipv4/inet_connection_sock.c')
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 57 |
1 files changed, 51 insertions, 6 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7f75f21d7b83..f0c5b9c1a957 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -283,7 +283,9 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct sock *newsk; + struct request_sock *req; int error; lock_sock(sk); @@ -296,7 +298,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) goto out_err; /* Find already established connection */ - if (reqsk_queue_empty(&icsk->icsk_accept_queue)) { + if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ @@ -308,14 +310,32 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) if (error) goto out_err; } - - newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk); - WARN_ON(newsk->sk_state == TCP_SYN_RECV); + req = reqsk_queue_remove(queue); + newsk = req->sk; + + sk_acceptq_removed(sk); + if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) { + spin_lock_bh(&queue->fastopenq->lock); + if (tcp_rsk(req)->listener) { + /* We are still waiting for the final ACK from 3WHS + * so can't free req now. Instead, we set req->sk to + * NULL to signify that the child socket is taken + * so reqsk_fastopen_remove() will free the req + * when 3WHS finishes (or is aborted). + */ + req->sk = NULL; + req = NULL; + } + spin_unlock_bh(&queue->fastopenq->lock); + } out: release_sock(sk); + if (req) + __reqsk_free(req); return newsk; out_err: newsk = NULL; + req = NULL; *err = error; goto out; } @@ -720,13 +740,14 @@ EXPORT_SYMBOL_GPL(inet_csk_listen_start); void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *acc_req; struct request_sock *req; inet_csk_delete_keepalive_timer(sk); /* make all the listen_opt local to us */ - acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue); + acc_req = reqsk_queue_yank_acceptq(queue); /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -736,7 +757,7 @@ void inet_csk_listen_stop(struct sock *sk) * To be honest, we are not able to make either * of the variants now. --ANK */ - reqsk_queue_destroy(&icsk->icsk_accept_queue); + reqsk_queue_destroy(queue); while ((req = acc_req) != NULL) { struct sock *child = req->sk; @@ -754,6 +775,19 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) { + BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(sk != tcp_rsk(req)->listener); + + /* Paranoid, to prevent race condition if + * an inbound pkt destined for child is + * blocked by sock lock in tcp_v4_rcv(). + * Also to satisfy an assertion in + * tcp_v4_destroy_sock(). + */ + tcp_sk(child)->fastopen_rsk = NULL; + sock_put(sk); + } inet_csk_destroy_sock(child); bh_unlock_sock(child); @@ -763,6 +797,17 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); __reqsk_free(req); } + if (queue->fastopenq != NULL) { + /* Free all the reqs queued in rskq_rst_head. */ + spin_lock_bh(&queue->fastopenq->lock); + acc_req = queue->fastopenq->rskq_rst_head; + queue->fastopenq->rskq_rst_head = NULL; + spin_unlock_bh(&queue->fastopenq->lock); + while ((req = acc_req) != NULL) { + acc_req = req->dl_next; + __reqsk_free(req); + } + } WARN_ON(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); |