summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 11:56:19 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 11:56:19 -0800
commit5bbcc0f595fadb4cac0eddc4401035ec0bd95b09 (patch)
tree3b65e490cc36a6c6fecac1fa24d9e0ac9ced4455 /net/ipv4/tcp_ipv4.c
parent892204e06cb9e89fbc4b299a678f9ca358e97cac (diff)
parent50895b9de1d3e0258e015e8e55128d835d9a9f19 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Maintain the TCP retransmit queue using an rbtree, with 1GB windows at 100Gb this really has become necessary. From Eric Dumazet. 2) Multi-program support for cgroup+bpf, from Alexei Starovoitov. 3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew Lunn. 4) Add meter action support to openvswitch, from Andy Zhou. 5) Add a data meta pointer for BPF accessible packets, from Daniel Borkmann. 6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet. 7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli. 8) More work to move the RTNL mutex down, from Florian Westphal. 9) Add 'bpftool' utility, to help with bpf program introspection. From Jakub Kicinski. 10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper Dangaard Brouer. 11) Support 'blocks' of transformations in the packet scheduler which can span multiple network devices, from Jiri Pirko. 12) TC flower offload support in cxgb4, from Kumar Sanghvi. 13) Priority based stream scheduler for SCTP, from Marcelo Ricardo Leitner. 14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg. 15) Add RED qdisc offloadability, and use it in mlxsw driver. From Nogah Frankel. 16) eBPF based device controller for cgroup v2, from Roman Gushchin. 17) Add some fundamental tracepoints for TCP, from Song Liu. 18) Remove garbage collection from ipv6 route layer, this is a significant accomplishment. From Wei Wang. 19) Add multicast route offload support to mlxsw, from Yotam Gigi" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits) tcp: highest_sack fix geneve: fix fill_info when link down bpf: fix lockdep splat net: cdc_ncm: GetNtbFormat endian fix openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start netem: remove unnecessary 64 bit modulus netem: use 64 bit divide by rate tcp: Namespace-ify sysctl_tcp_default_congestion_control net: Protect iterations over net::fib_notifier_ops in fib_seq_sum() ipv6: set all.accept_dad to 0 by default uapi: fix linux/tls.h userspace compilation error usbnet: ipheth: prevent TX queue timeouts when device not ready vhost_net: conditionally enable tx polling uapi: fix linux/rxrpc.h userspace compilation errors net: stmmac: fix LPI transitioning for dwmac4 atm: horizon: Fix irq release error net-sysfs: trigger netlink notification on ifalias change via sysfs openvswitch: Using kfree_rcu() to simplify the code openvswitch: Make local function ovs_nsh_key_attr_size() static openvswitch: Fix return value check in ovs_meter_cmd_features() ...
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c69
1 files changed, 64 insertions, 5 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5b027c69cbc5..c6bc0c4d19c6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,6 +85,8 @@
#include <crypto/hash.h>
#include <linux/scatterlist.h>
+#include <trace/events/tcp.h>
+
#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -480,7 +482,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
TCP_TIMEOUT_INIT;
icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
- skb = tcp_write_queue_head(sk);
+ skb = tcp_rtx_queue_head(sk);
BUG_ON(!skb);
tcp_mstamp_refresh(tp);
@@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
* routing might fail in this case. No choice here, if we choose to force
* input interface, we will misroute in case of asymmetric route.
*/
- if (sk)
+ if (sk) {
arg.bound_dev_if = sk->sk_bound_dev_if;
+ trace_tcp_send_reset(sk, skb);
+ }
BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -1783,8 +1787,9 @@ do_time_wait:
refcounted = false;
goto process;
}
- /* Fall through to ACK */
}
+ /* to ACK */
+ /* fall through */
case TCP_TW_ACK:
tcp_v4_timewait_ack(sk, skb);
break;
@@ -1864,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ trace_tcp_destroy_sock(sk);
+
tcp_clear_xmit_timers(sk);
tcp_cleanup_congestion_control(sk);
@@ -1896,6 +1903,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* If socket is aborted during connect operation */
tcp_free_fastopen_req(tp);
+ tcp_fastopen_destroy_cipher(sk);
tcp_saved_syn_free(tp);
sk_sockets_allocated_dec(sk);
@@ -2401,8 +2409,8 @@ struct proto tcp_prot = {
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
- .sysctl_wmem = sysctl_tcp_wmem,
- .sysctl_rmem = sysctl_tcp_rmem,
+ .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
@@ -2422,6 +2430,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
{
int cpu;
+ module_put(net->ipv4.tcp_congestion_control->owner);
+
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
free_percpu(net->ipv4.tcp_sk);
@@ -2476,6 +2486,50 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_sack = 1;
net->ipv4.sysctl_tcp_window_scaling = 1;
net->ipv4.sysctl_tcp_timestamps = 1;
+ net->ipv4.sysctl_tcp_early_retrans = 3;
+ net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION;
+ net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */
+ net->ipv4.sysctl_tcp_retrans_collapse = 1;
+ net->ipv4.sysctl_tcp_max_reordering = 300;
+ net->ipv4.sysctl_tcp_dsack = 1;
+ net->ipv4.sysctl_tcp_app_win = 31;
+ net->ipv4.sysctl_tcp_adv_win_scale = 1;
+ net->ipv4.sysctl_tcp_frto = 2;
+ net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+ /* This limits the percentage of the congestion window which we
+ * will allow a single TSO frame to consume. Building TSO frames
+ * which are too large can cause TCP streams to be bursty.
+ */
+ net->ipv4.sysctl_tcp_tso_win_divisor = 3;
+ /* Default TSQ limit of four TSO segments */
+ net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+ /* rfc5961 challenge ack rate limiting */
+ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+ net->ipv4.sysctl_tcp_min_tso_segs = 2;
+ net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
+ net->ipv4.sysctl_tcp_autocorking = 1;
+ net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+ net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
+ net->ipv4.sysctl_tcp_pacing_ca_ratio = 120;
+ if (net != &init_net) {
+ memcpy(net->ipv4.sysctl_tcp_rmem,
+ init_net.ipv4.sysctl_tcp_rmem,
+ sizeof(init_net.ipv4.sysctl_tcp_rmem));
+ memcpy(net->ipv4.sysctl_tcp_wmem,
+ init_net.ipv4.sysctl_tcp_wmem,
+ sizeof(init_net.ipv4.sysctl_tcp_wmem));
+ }
+ 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;
+ atomic_set(&net->ipv4.tfo_active_disable_times, 0);
+
+ /* Reno is always built in */
+ if (!net_eq(net, &init_net) &&
+ try_module_get(init_net.ipv4.tcp_congestion_control->owner))
+ net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
+ else
+ net->ipv4.tcp_congestion_control = &tcp_reno;
return 0;
fail:
@@ -2486,7 +2540,12 @@ fail:
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
+ struct net *net;
+
inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+ list_for_each_entry(net, net_exit_list, exit_list)
+ tcp_fastopen_ctx_destroy(net);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {