aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-06-06 18:39:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-06 18:39:49 -0700
commit1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21 (patch)
treedcc97181d4d187252e0cc8fdf29d9b365fa3ffd0 /net/ipv4/tcp_ipv4.c
parentMerge tag 'overflow-v4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux (diff)
parentstrparser: Add __strp_unpause and use it in ktls. (diff)
downloadlinux-dev-1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21.tar.xz
linux-dev-1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) Add Maglev hashing scheduler to IPVS, from Inju Song. 2) Lots of new TC subsystem tests from Roman Mashak. 3) Add TCP zero copy receive and fix delayed acks and autotuning with SO_RCVLOWAT, from Eric Dumazet. 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard Brouer. 5) Add ttl inherit support to vxlan, from Hangbin Liu. 6) Properly separate ipv6 routes into their logically independant components. fib6_info for the routing table, and fib6_nh for sets of nexthops, which thus can be shared. From David Ahern. 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP messages from XDP programs. From Nikita V. Shirokov. 8) Lots of long overdue cleanups to the r8169 driver, from Heiner Kallweit. 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau. 10) Add traffic condition monitoring to iwlwifi, from Luca Coelho. 11) Plumb extack down into fib_rules, from Roopa Prabhu. 12) Add Flower classifier offload support to igb, from Vinicius Costa Gomes. 13) Add UDP GSO support, from Willem de Bruijn. 14) Add documentation for eBPF helpers, from Quentin Monnet. 15) Add TLS tx offload to mlx5, from Ilya Lesokhin. 16) Allow applications to be given the number of bytes available to read on a socket via a control message returned from recvmsg(), from Soheil Hassas Yeganeh. 17) Add x86_32 eBPF JIT compiler, from Wang YanQing. 18) Add AF_XDP sockets, with zerocopy support infrastructure as well. From Björn Töpel. 19) Remove indirect load support from all of the BPF JITs and handle these operations in the verifier by translating them into native BPF instead. From Daniel Borkmann. 20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha. 21) Allow XDP programs to do lookups in the main kernel routing tables for forwarding. From David Ahern. 22) Allow drivers to store hardware state into an ELF section of kernel dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy. 23) Various RACK and loss detection improvements in TCP, from Yuchung Cheng. 24) Add TCP SACK compression, from Eric Dumazet. 25) Add User Mode Helper support and basic bpfilter infrastructure, from Alexei Starovoitov. 26) Support ports and protocol values in RTM_GETROUTE, from Roopa Prabhu. 27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard Brouer. 28) Add lots of forwarding selftests, from Petr Machata. 29) Add generic network device failover driver, from Sridhar Samudrala. * ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits) strparser: Add __strp_unpause and use it in ktls. rxrpc: Fix terminal retransmission connection ID to include the channel net: hns3: Optimize PF CMDQ interrupt switching process net: hns3: Fix for VF mailbox receiving unknown message net: hns3: Fix for VF mailbox cannot receiving PF response bnx2x: use the right constant Revert "net: sched: cls: Fix offloading when ingress dev is vxlan" net: dsa: b53: Fix for brcm tag issue in Cygnus SoC enic: fix UDP rss bits netdev-FAQ: clarify DaveM's position for stable backports rtnetlink: validate attributes in do_setlink() mlxsw: Add extack messages for port_{un, }split failures netdevsim: Add extack error message for devlink reload devlink: Add extack to reload and port_{un, }split operations net: metrics: add proper netlink validation ipmr: fix error path when ipmr_new_table fails ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds net: hns3: remove unused hclgevf_cfg_func_mta_filter netfilter: provide udp*_lib_lookup for nf_tproxy qed*: Utilize FW 8.37.2.0 ...
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c55
1 files changed, 49 insertions, 6 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2c970626b398..fed3f1c66167 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -110,8 +110,38 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
+ const struct inet_timewait_sock *tw = inet_twsk(sktw);
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
+ int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse;
+
+ if (reuse == 2) {
+ /* Still does not detect *everything* that goes through
+ * lo, since we require a loopback src or dst address
+ * or direct binding to 'lo' interface.
+ */
+ bool loopback = false;
+ if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX)
+ loopback = true;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (tw->tw_family == AF_INET6) {
+ if (ipv6_addr_loopback(&tw->tw_v6_daddr) ||
+ (ipv6_addr_v4mapped(&tw->tw_v6_daddr) &&
+ (tw->tw_v6_daddr.s6_addr[12] == 127)) ||
+ ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) ||
+ (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) &&
+ (tw->tw_v6_rcv_saddr.s6_addr[12] == 127)))
+ loopback = true;
+ } else
+#endif
+ {
+ if (ipv4_is_loopback(tw->tw_daddr) ||
+ ipv4_is_loopback(tw->tw_rcv_saddr))
+ loopback = true;
+ }
+ if (!loopback)
+ reuse = 0;
+ }
/* With PAWS, it is safe from the viewpoint
of data integrity. Even without PAWS it is safe provided sequence
@@ -125,8 +155,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
and use initial timestamp retrieved from peer table.
*/
if (tcptw->tw_ts_recent_stamp &&
- (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
- get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
+ (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
@@ -621,6 +650,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
struct sock *sk1 = NULL;
#endif
struct net *net;
+ struct sock *ctl_sk;
/* Never send a reset in response to a reset. */
if (th->rst)
@@ -723,11 +753,16 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
arg.tos = ip_hdr(skb)->tos;
arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
+ if (sk)
+ ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_mark : sk->sk_mark;
+ ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len);
+ ctl_sk->sk_mark = 0;
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
local_bh_enable();
@@ -759,6 +794,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
} rep;
struct net *net = sock_net(sk);
struct ip_reply_arg arg;
+ struct sock *ctl_sk;
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -809,11 +845,16 @@ static void tcp_v4_send_ack(const struct sock *sk,
arg.tos = tos;
arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
+ if (sk)
+ ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_mark : sk->sk_mark;
+ ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len);
+ ctl_sk->sk_mark = 0;
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
local_bh_enable();
}
@@ -1474,7 +1515,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
sk->sk_rx_dst = NULL;
}
}
- tcp_rcv_established(sk, skb, tcp_hdr(skb));
+ tcp_rcv_established(sk, skb);
return 0;
}
@@ -2481,7 +2522,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_orphan_retries = 0;
net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
- net->ipv4.sysctl_tcp_tw_reuse = 0;
+ net->ipv4.sysctl_tcp_tw_reuse = 2;
cnt = tcp_hashinfo.ehash_mask + 1;
net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
@@ -2524,6 +2565,8 @@ static int __net_init tcp_sk_init(struct net *net)
init_net.ipv4.sysctl_tcp_wmem,
sizeof(init_net.ipv4.sysctl_tcp_wmem));
}
+ net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
+ net->ipv4.sysctl_tcp_comp_sack_nr = 44;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;