summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-03-19 10:05:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-03-19 10:05:34 -0700
commit1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch)
tree552e03de245cdbd0780ca1215914edc4a26540f7 /net/ipv4/tcp.c
parent6b5f04b6cf8ebab9a65d9c0026c650bb2538fd0f (diff)
parentfe30937b65354c7fec244caebbdaae68e28ca797 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Support more Realtek wireless chips, from Jes Sorenson. 2) New BPF types for per-cpu hash and arrap maps, from Alexei Starovoitov. 3) Make several TCP sysctls per-namespace, from Nikolay Borisov. 4) Allow the use of SO_REUSEPORT in order to do per-thread processing of incoming TCP/UDP connections. The muxing can be done using a BPF program which hashes the incoming packet. From Craig Gallek. 5) Add a multiplexer for TCP streams, to provide a messaged based interface. BPF programs can be used to determine the message boundaries. From Tom Herbert. 6) Add 802.1AE MACSEC support, from Sabrina Dubroca. 7) Avoid factorial complexity when taking down an inetdev interface with lots of configured addresses. We were doing things like traversing the entire address less for each address removed, and flushing the entire netfilter conntrack table for every address as well. 8) Add and use SKB bulk free infrastructure, from Jesper Brouer. 9) Allow offloading u32 classifiers to hardware, and implement for ixgbe, from John Fastabend. 10) Allow configuring IRQ coalescing parameters on a per-queue basis, from Kan Liang. 11) Extend ethtool so that larger link mode masks can be supported. From David Decotigny. 12) Introduce devlink, which can be used to configure port link types (ethernet vs Infiniband, etc.), port splitting, and switch device level attributes as a whole. From Jiri Pirko. 13) Hardware offload support for flower classifiers, from Amir Vadai. 14) Add "Local Checksum Offload". Basically, for a tunneled packet the checksum of the outer header is 'constant' (because with the checksum field filled into the inner protocol header, the payload of the outer frame checksums to 'zero'), and we can take advantage of that in various ways. From Edward Cree" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits) bonding: fix bond_get_stats() net: bcmgenet: fix dma api length mismatch net/mlx4_core: Fix backward compatibility on VFs phy: mdio-thunder: Fix some Kconfig typos lan78xx: add ndo_get_stats64 lan78xx: handle statistics counter rollover RDS: TCP: Remove unused constant RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket net: smc911x: convert pxa dma to dmaengine team: remove duplicate set of flag IFF_MULTICAST bonding: remove duplicate set of flag IFF_MULTICAST net: fix a comment typo ethernet: micrel: fix some error codes ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it bpf, dst: add and use dst_tclassid helper bpf: make skb->tc_classid also readable net: mvneta: bm: clarify dependencies cls_bpf: reset class and reuse major in da ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c ldmvsw: Add ldmvsw.c driver code ...
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c43
1 files changed, 21 insertions, 22 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4804645bdf02..08b8b960a8ed 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,8 +282,6 @@
#include <asm/unaligned.h>
#include <net/busy_poll.h>
-int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
-
int sysctl_tcp_min_tso_segs __read_mostly = 2;
int sysctl_tcp_autocorking __read_mostly = 1;
@@ -406,7 +404,7 @@ void tcp_init_sock(struct sock *sk)
tp->mss_cache = TCP_MSS_DEFAULT;
u64_stats_init(&tp->syncp);
- tp->reordering = sysctl_tcp_reordering;
+ tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
tcp_assign_congestion_control(sk);
@@ -558,20 +556,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return -EINVAL;
slow = lock_sock_fast(sk);
- if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
- answ = 0;
- else if (sock_flag(sk, SOCK_URGINLINE) ||
- !tp->urg_data ||
- before(tp->urg_seq, tp->copied_seq) ||
- !before(tp->urg_seq, tp->rcv_nxt)) {
-
- answ = tp->rcv_nxt - tp->copied_seq;
-
- /* Subtract 1, if FIN was received */
- if (answ && sock_flag(sk, SOCK_DONE))
- answ--;
- } else
- answ = tp->urg_seq - tp->copied_seq;
+ answ = tcp_inq(sk);
unlock_sock_fast(sk, slow);
break;
case SIOCATMARK:
@@ -1466,8 +1451,10 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
offset = seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
*off = offset;
return skb;
@@ -1657,8 +1644,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len)
goto found_ok_skb;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -2326,6 +2315,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct net *net = sock_net(sk);
int val;
int err = 0;
@@ -2522,7 +2512,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_LINGER2:
if (val < 0)
tp->linger2 = -1;
- else if (val > sysctl_tcp_fin_timeout / HZ)
+ else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ)
tp->linger2 = 0;
else
tp->linger2 = val * HZ;
@@ -2639,6 +2629,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
unsigned int start;
+ int notsent_bytes;
u64 rate64;
u32 rate;
@@ -2719,6 +2710,13 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = tp->segs_in;
+
+ notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt);
+ info->tcpi_notsent_bytes = max(0, notsent_bytes);
+
+ info->tcpi_min_rtt = tcp_min_rtt(tp);
+ info->tcpi_data_segs_in = tp->data_segs_in;
+ info->tcpi_data_segs_out = tp->data_segs_out;
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -2727,6 +2725,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
int val, len;
if (get_user(len, optlen))
@@ -2761,12 +2760,12 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
- val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+ val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
break;
case TCP_LINGER2:
val = tp->linger2;
if (val >= 0)
- val = (val ? : sysctl_tcp_fin_timeout) / HZ;
+ val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,