[IP_SOCKGLUE]: Remove most of the tcp specific calls
As DCCP needs to be called in the same spots.
Now we have a member in inet_sock (is_icsk), set at sock creation time from
struct inet_protosw->flags (if INET_PROTOSW_ICSK is set, like for TCP and
DCCP) to see if a struct sock instance is a inet_connection_sock for places
like the ones in ip_sockglue.c (v4 and v6) where we previously were looking if
sk_type was SOCK_STREAM, that is insufficient because we now use the same code
for DCCP, that has sk_type SOCK_DCCP.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d368cf2..617e858 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -302,6 +302,7 @@
sk->sk_reuse = 1;
inet = inet_sk(sk);
+ inet->is_icsk = INET_PROTOSW_ICSK & answer_flags;
if (SOCK_RAW == sock->type) {
inet->num = protocol;
@@ -869,7 +870,8 @@
.ops = &inet_stream_ops,
.capability = -1,
.no_check = 0,
- .flags = INET_PROTOSW_PERMANENT,
+ .flags = INET_PROTOSW_PERMANENT |
+ INET_PROTOSW_ICSK,
},
{
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 4f2d872..add019c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -29,8 +29,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
-#include <net/tcp.h>
-#include <linux/tcp.h>
+#include <net/tcp_states.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/netfilter.h>
@@ -427,8 +426,8 @@
err = ip_options_get_from_user(&opt, optval, optlen);
if (err)
break;
- if (sk->sk_type == SOCK_STREAM) {
- struct tcp_sock *tp = tcp_sk(sk);
+ if (inet->is_icsk) {
+ struct inet_connection_sock *icsk = inet_csk(sk);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
@@ -436,10 +435,10 @@
inet->daddr != LOOPBACK4_IPV6)) {
#endif
if (inet->opt)
- tp->ext_header_len -= inet->opt->optlen;
+ icsk->icsk_ext_hdr_len -= inet->opt->optlen;
if (opt)
- tp->ext_header_len += opt->optlen;
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ icsk->icsk_ext_hdr_len += opt->optlen;
+ icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
}
#endif
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eacfe6a..00aa80e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1914,7 +1914,7 @@
info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
- info->tcpi_pmtu = tp->pmtu_cookie;
+ info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7de6184..981d120 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2342,7 +2342,7 @@
if (nwin > tp->max_window) {
tp->max_window = nwin;
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie);
}
}
}
@@ -3967,12 +3967,12 @@
struct tcphdr *th, unsigned len)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, 0);
if (th->ack) {
- struct inet_connection_sock *icsk;
/* rfc793:
* "If the state is SYN-SENT then
* first check the ACK bit
@@ -4061,7 +4061,7 @@
if (tp->rx_opt.sack_ok && sysctl_tcp_fack)
tp->rx_opt.sack_ok |= 2;
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
/* Remember, tcp_poll() does not lock socket!
@@ -4071,8 +4071,6 @@
mb();
tcp_set_state(sk, TCP_ESTABLISHED);
- icsk = inet_csk(sk);
-
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
@@ -4173,7 +4171,7 @@
if (tp->ecn_flags&TCP_ECN_OK)
sock_set_flag(sk, SOCK_NO_LARGESEND);
- tcp_sync_mss(sk, tp->pmtu_cookie);
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c2fe61b..9b62d80 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -220,9 +220,9 @@
inet->dport = usin->sin_port;
inet->daddr = daddr;
- tp->ext_header_len = 0;
+ inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt)
- tp->ext_header_len = inet->opt->optlen;
+ inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
tp->rx_opt.mss_clamp = 536;
@@ -275,7 +275,6 @@
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
- struct tcp_sock *tp = tcp_sk(sk);
/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
* send out by Linux are always <576bytes so they should go through
@@ -304,7 +303,7 @@
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
- tp->pmtu_cookie > mtu) {
+ inet_csk(sk)->icsk_pmtu_cookie > mtu) {
tcp_sync_mss(sk, mtu);
/* Resend the TCP packet because it's
@@ -895,9 +894,9 @@
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = skb->nh.iph->ttl;
- newtp->ext_header_len = 0;
+ inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
- newtp->ext_header_len = newinet->opt->optlen;
+ inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
newinet->id = newtp->write_seq ^ jiffies;
tcp_sync_mss(newsk, dst_mtu(dst));
@@ -1266,6 +1265,7 @@
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
icsk->icsk_af_ops = &ipv4_specific;
+ icsk->icsk_sync_mss = tcp_sync_mss;
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index af1946c..3a0a914 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -621,7 +621,7 @@
It is minimum of user_mss and mss received with SYN.
It also does not include TCP options.
- tp->pmtu_cookie is last pmtu, seen by this function.
+ inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function.
tp->mss_cache is current effective sending mss, including
all tcp options except for SACKs. It is evaluated,
@@ -631,17 +631,18 @@
NOTE1. rfc1122 clearly states that advertised MSS
DOES NOT include either tcp or ip options.
- NOTE2. tp->pmtu_cookie and tp->mss_cache are READ ONLY outside
- this function. --ANK (980731)
+ NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache
+ are READ ONLY outside this function. --ANK (980731)
*/
unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
/* Calculate base mss without TCP options:
It is MMS_S - sizeof(tcphdr) of rfc1122
*/
- int mss_now = (pmtu - inet_csk(sk)->icsk_af_ops->net_header_len -
+ int mss_now = (pmtu - icsk->icsk_af_ops->net_header_len -
sizeof(struct tcphdr));
/* Clamp it (mss_clamp does not include tcp options) */
@@ -649,7 +650,7 @@
mss_now = tp->rx_opt.mss_clamp;
/* Now subtract optional transport overhead */
- mss_now -= tp->ext_header_len;
+ mss_now -= icsk->icsk_ext_hdr_len;
/* Then reserve room for full set of TCP options and 8 bytes of data */
if (mss_now < 48)
@@ -663,7 +664,7 @@
mss_now = max((tp->max_window>>1), 68U - tp->tcp_header_len);
/* And store cached results */
- tp->pmtu_cookie = pmtu;
+ icsk->icsk_pmtu_cookie = pmtu;
tp->mss_cache = mss_now;
return mss_now;
@@ -693,7 +694,7 @@
if (dst) {
u32 mtu = dst_mtu(dst);
- if (mtu != tp->pmtu_cookie)
+ if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
mss_now = tcp_sync_mss(sk, mtu);
}
@@ -706,7 +707,8 @@
if (doing_tso) {
xmit_size_goal = (65535 -
inet_csk(sk)->icsk_af_ops->net_header_len -
- tp->ext_header_len - tp->tcp_header_len);
+ inet_csk(sk)->icsk_ext_hdr_len -
+ tp->tcp_header_len);
if (tp->max_window &&
(xmit_size_goal > (tp->max_window >> 1)))
