*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_ipv4.c,v 1.240 2002/02/01 22:01:04 davem Exp $
- *
* IPv4 specific functions
*
*
#include <linux/init.h>
#include <linux/times.h>
+#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+
int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
-/* Check TCP sequence numbers in ICMP packets. */
-#define ICMP_MIN_LENGTH 8
-
-/* Socket used for sending RSTs */
-static struct socket *tcp_socket;
-
-void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
-struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
- .lhash_lock = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock),
- .lhash_users = ATOMIC_INIT(0),
- .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
-};
-
-static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
-{
- return inet_csk_get_port(&tcp_hashinfo, sk, snum,
- inet_csk_bind_conflict);
-}
-
-static void tcp_v4_hash(struct sock *sk)
+#ifdef CONFIG_TCP_MD5SIG
+static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
+ __be32 addr);
+static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
+ __be32 saddr, __be32 daddr,
+ struct tcphdr *th, unsigned int tcplen);
+#else
+static inline
+struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
- inet_hash(&tcp_hashinfo, sk);
+ return NULL;
}
+#endif
-void tcp_unhash(struct sock *sk)
-{
- inet_unhash(&tcp_hashinfo, sk);
-}
+struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
+ .lhash_lock = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock),
+ .lhash_users = ATOMIC_INIT(0),
+ .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
+};
-static inline __u32 tcp_v4_init_sequence(struct sock *sk, struct sk_buff *skb)
+static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
{
- return secure_tcp_sequence_number(skb->nh.iph->daddr,
- skb->nh.iph->saddr,
- skb->h.th->dest,
- skb->h.th->source);
+ return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr,
+ tcp_hdr(skb)->dest,
+ tcp_hdr(skb)->source);
}
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
*/
if (tcptw->tw_ts_recent_stamp &&
(twp == NULL || (sysctl_tcp_tw_reuse &&
- xtime.tv_sec - tcptw->tw_ts_recent_stamp > 1))) {
+ 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;
tmp = ip_route_connect(&rt, nexthop, inet->saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
- inet->sport, usin->sin_port, sk);
- if (tmp < 0)
+ inet->sport, usin->sin_port, sk, 1);
+ if (tmp < 0) {
+ if (tmp == -ENETUNREACH)
+ IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
return tmp;
+ }
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
struct inet_peer *peer = rt_get_peer(rt);
-
- /* VJ's idea. We save last timestamp seen from
- * the destination in peer table, when entering state TIME-WAIT
- * and initialize rx_opt.ts_recent from it, when trying new connection.
+ /*
+ * VJ's idea. We save last timestamp seen from
+ * the destination in peer table, when entering state
+ * TIME-WAIT * and initialize rx_opt.ts_recent from it,
+ * when trying new connection.
*/
-
- if (peer && peer->tcp_ts_stamp + TCP_PAWS_MSL >= xtime.tv_sec) {
+ if (peer != NULL &&
+ peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
if (err)
goto failure;
- err = ip_route_newports(&rt, IPPROTO_TCP, inet->sport, inet->dport, sk);
+ err = ip_route_newports(&rt, IPPROTO_TCP,
+ inet->sport, inet->dport, sk);
if (err)
goto failure;
return 0;
failure:
- /* This unhashes the socket and releases the local port, if necessary. */
+ /*
+ * This unhashes the socket and releases the local port,
+ * if necessary.
+ */
tcp_set_state(sk, TCP_CLOSE);
ip_rt_put(rt);
sk->sk_route_caps = 0;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
- * There is a small race when the user changes this flag in the
+ * There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2));
struct tcp_sock *tp;
struct inet_sock *inet;
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
struct sock *sk;
__u32 seq;
int err;
return;
}
- sk = inet_lookup(&tcp_hashinfo, iph->daddr, th->dest, iph->saddr,
- th->source, inet_iif(skb));
+ sk = inet_lookup(dev_net(skb->dev), &tcp_hashinfo, iph->daddr, th->dest,
+ iph->saddr, th->source, inet_iif(skb));
if (!sk) {
ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
return;
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
- NET_INC_STATS(LINUX_MIB_OUTOFWINDOWICMPS);
+ NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
{
struct inet_sock *inet = inet_sk(sk);
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- th->check = ~tcp_v4_check(th, len, inet->saddr, inet->daddr, 0);
- skb->csum = offsetof(struct tcphdr, check);
+ th->check = ~tcp_v4_check(len, inet->saddr,
+ inet->daddr, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
} else {
- th->check = tcp_v4_check(th, len, inet->saddr, inet->daddr,
+ th->check = tcp_v4_check(len, inet->saddr, inet->daddr,
csum_partial((char *)th,
th->doff << 2,
skb->csum));
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
- struct iphdr *iph;
+ const struct iphdr *iph;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
- iph = skb->nh.iph;
- th = skb->h.th;
+ iph = ip_hdr(skb);
+ th = tcp_hdr(skb);
th->check = 0;
- th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0);
- skb->csum = offsetof(struct tcphdr, check);
+ th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
return 0;
}
* Exception: precedence violation. We do not implement it in any case.
*/
-static void tcp_v4_send_reset(struct sk_buff *skb)
+static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
- struct tcphdr rth;
+ struct tcphdr *th = tcp_hdr(skb);
+ struct {
+ struct tcphdr th;
+#ifdef CONFIG_TCP_MD5SIG
+ __be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
+#endif
+ } rep;
struct ip_reply_arg arg;
+#ifdef CONFIG_TCP_MD5SIG
+ struct tcp_md5sig_key *key;
+#endif
/* Never send a reset in response to a reset. */
if (th->rst)
return;
- if (((struct rtable *)skb->dst)->rt_type != RTN_LOCAL)
+ if (skb->rtable->rt_type != RTN_LOCAL)
return;
/* Swap the send and the receive. */
- memset(&rth, 0, sizeof(struct tcphdr));
- rth.dest = th->source;
- rth.source = th->dest;
- rth.doff = sizeof(struct tcphdr) / 4;
- rth.rst = 1;
+ memset(&rep, 0, sizeof(rep));
+ rep.th.dest = th->source;
+ rep.th.source = th->dest;
+ rep.th.doff = sizeof(struct tcphdr) / 4;
+ rep.th.rst = 1;
if (th->ack) {
- rth.seq = th->ack_seq;
+ rep.th.seq = th->ack_seq;
} else {
- rth.ack = 1;
- rth.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
- skb->len - (th->doff << 2));
+ rep.th.ack = 1;
+ rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
+ skb->len - (th->doff << 2));
}
- memset(&arg, 0, sizeof arg);
- arg.iov[0].iov_base = (unsigned char *)&rth;
- arg.iov[0].iov_len = sizeof rth;
- arg.csum = csum_tcpudp_nofold(skb->nh.iph->daddr,
- skb->nh.iph->saddr, /*XXX*/
+ memset(&arg, 0, sizeof(arg));
+ arg.iov[0].iov_base = (unsigned char *)&rep;
+ arg.iov[0].iov_len = sizeof(rep.th);
+
+#ifdef CONFIG_TCP_MD5SIG
+ key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL;
+ if (key) {
+ rep.opt[0] = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_MD5SIG << 8) |
+ TCPOLEN_MD5SIG);
+ /* Update length and the length the header thinks exists */
+ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
+ rep.th.doff = arg.iov[0].iov_len / 4;
+
+ tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[1],
+ key,
+ ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr,
+ &rep.th, arg.iov[0].iov_len);
+ }
+#endif
+ arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr, /* XXX */
sizeof(struct tcphdr), IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
- ip_send_reply(tcp_socket->sk, skb, &arg, sizeof rth);
+ ip_send_reply(dev_net(skb->dst->dev)->ipv4.tcp_sock, skb,
+ &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
*/
static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
- u32 win, u32 ts)
+ u32 win, u32 ts, int oif,
+ struct tcp_md5sig_key *key)
{
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
struct {
struct tcphdr th;
- u32 tsopt[TCPOLEN_TSTAMP_ALIGNED >> 2];
+ __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
+#ifdef CONFIG_TCP_MD5SIG
+ + (TCPOLEN_MD5SIG_ALIGNED >> 2)
+#endif
+ ];
} rep;
struct ip_reply_arg arg;
memset(&rep.th, 0, sizeof(struct tcphdr));
- memset(&arg, 0, sizeof arg);
+ memset(&arg, 0, sizeof(arg));
arg.iov[0].iov_base = (unsigned char *)&rep;
arg.iov[0].iov_len = sizeof(rep.th);
if (ts) {
- rep.tsopt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
- rep.tsopt[1] = htonl(tcp_time_stamp);
- rep.tsopt[2] = htonl(ts);
- arg.iov[0].iov_len = sizeof(rep);
+ rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
+ rep.opt[1] = htonl(tcp_time_stamp);
+ rep.opt[2] = htonl(ts);
+ arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
}
/* Swap the send and the receive. */
rep.th.ack = 1;
rep.th.window = htons(win);
- arg.csum = csum_tcpudp_nofold(skb->nh.iph->daddr,
- skb->nh.iph->saddr, /*XXX*/
+#ifdef CONFIG_TCP_MD5SIG
+ if (key) {
+ int offset = (ts) ? 3 : 0;
+
+ rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_MD5SIG << 8) |
+ TCPOLEN_MD5SIG);
+ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
+ rep.th.doff = arg.iov[0].iov_len/4;
+
+ tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[offset],
+ key,
+ ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr,
+ &rep.th, arg.iov[0].iov_len);
+ }
+#endif
+ arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr, /* XXX */
arg.iov[0].iov_len, IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
+ if (oif)
+ arg.bound_dev_if = oif;
- ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);
+ ip_send_reply(dev_net(skb->dev)->ipv4.tcp_sock, skb,
+ &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
}
static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
- const struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
+ struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
- tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcptw->tw_ts_recent);
+ tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
+ tcptw->tw_ts_recent,
+ tw->tw_bound_dev_if,
+ tcp_twsk_md5_key(tcptw)
+ );
inet_twsk_put(tw);
}
-static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
+static void tcp_v4_reqsk_send_ack(struct sk_buff *skb,
+ struct request_sock *req)
{
- tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
- req->ts_recent);
+ tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
+ tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
+ req->ts_recent,
+ 0,
+ tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr));
}
/*
- * Send a SYN-ACK after having received an ACK.
+ * Send a SYN-ACK after having received a SYN.
* This still operates on a request_sock only, not on a big
* socket.
*/
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
- struct dst_entry *dst)
+static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
+ struct dst_entry *dst)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
/* First, grab a route. */
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
- goto out;
+ return -1;
skb = tcp_make_synack(sk, dst, req);
if (skb) {
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
- th->check = tcp_v4_check(th, skb->len,
+ th->check = tcp_v4_check(skb->len,
ireq->loc_addr,
ireq->rmt_addr,
csum_partial((char *)th, skb->len,
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
ireq->rmt_addr,
ireq->opt);
- if (err == NET_XMIT_CN)
- err = 0;
+ err = net_xmit_eval(err);
}
-out:
dst_release(dst);
return err;
}
+static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
+{
+ return __tcp_v4_send_synack(sk, req, NULL);
+}
+
/*
* IPv4 request_sock destructor.
*/
warntime = jiffies;
printk(KERN_INFO
"possible SYN flooding on port %d. Sending cookies.\n",
- ntohs(skb->h.th->dest));
+ ntohs(tcp_hdr(skb)->dest));
}
}
#endif
return dopt;
}
-struct request_sock_ops tcp_request_sock_ops = {
+#ifdef CONFIG_TCP_MD5SIG
+/*
+ * RFC2385 MD5 checksumming requires a mapping of
+ * IP address->MD5 Key.
+ * We need to maintain these in the sk structure.
+ */
+
+/* Find the Key structure for an address. */
+static struct tcp_md5sig_key *
+ tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int i;
+
+ if (!tp->md5sig_info || !tp->md5sig_info->entries4)
+ return NULL;
+ for (i = 0; i < tp->md5sig_info->entries4; i++) {
+ if (tp->md5sig_info->keys4[i].addr == addr)
+ return &tp->md5sig_info->keys4[i].base;
+ }
+ return NULL;
+}
+
+struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+ struct sock *addr_sk)
+{
+ return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr);
+}
+
+EXPORT_SYMBOL(tcp_v4_md5_lookup);
+
+static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
+ struct request_sock *req)
+{
+ return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
+}
+
+/* This can be called on a newly created socket, from other files */
+int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
+ u8 *newkey, u8 newkeylen)
+{
+ /* Add Key to the list */
+ struct tcp_md5sig_key *key;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp4_md5sig_key *keys;
+
+ key = tcp_v4_md5_do_lookup(sk, addr);
+ if (key) {
+ /* Pre-existing entry - just update that one. */
+ kfree(key->key);
+ key->key = newkey;
+ key->keylen = newkeylen;
+ } else {
+ struct tcp_md5sig_info *md5sig;
+
+ if (!tp->md5sig_info) {
+ tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
+ GFP_ATOMIC);
+ if (!tp->md5sig_info) {
+ kfree(newkey);
+ return -ENOMEM;
+ }
+ sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ }
+ if (tcp_alloc_md5sig_pool() == NULL) {
+ kfree(newkey);
+ return -ENOMEM;
+ }
+ md5sig = tp->md5sig_info;
+
+ if (md5sig->alloced4 == md5sig->entries4) {
+ keys = kmalloc((sizeof(*keys) *
+ (md5sig->entries4 + 1)), GFP_ATOMIC);
+ if (!keys) {
+ kfree(newkey);
+ tcp_free_md5sig_pool();
+ return -ENOMEM;
+ }
+
+ if (md5sig->entries4)
+ memcpy(keys, md5sig->keys4,
+ sizeof(*keys) * md5sig->entries4);
+
+ /* Free old key list, and reference new one */
+ kfree(md5sig->keys4);
+ md5sig->keys4 = keys;
+ md5sig->alloced4++;
+ }
+ md5sig->entries4++;
+ md5sig->keys4[md5sig->entries4 - 1].addr = addr;
+ md5sig->keys4[md5sig->entries4 - 1].base.key = newkey;
+ md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen;
+ }
+ return 0;
+}
+
+EXPORT_SYMBOL(tcp_v4_md5_do_add);
+
+static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
+ u8 *newkey, u8 newkeylen)
+{
+ return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr,
+ newkey, newkeylen);
+}
+
+int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int i;
+
+ for (i = 0; i < tp->md5sig_info->entries4; i++) {
+ if (tp->md5sig_info->keys4[i].addr == addr) {
+ /* Free the key */
+ kfree(tp->md5sig_info->keys4[i].base.key);
+ tp->md5sig_info->entries4--;
+
+ if (tp->md5sig_info->entries4 == 0) {
+ kfree(tp->md5sig_info->keys4);
+ tp->md5sig_info->keys4 = NULL;
+ tp->md5sig_info->alloced4 = 0;
+ } else if (tp->md5sig_info->entries4 != i) {
+ /* Need to do some manipulation */
+ memmove(&tp->md5sig_info->keys4[i],
+ &tp->md5sig_info->keys4[i+1],
+ (tp->md5sig_info->entries4 - i) *
+ sizeof(struct tcp4_md5sig_key));
+ }
+ tcp_free_md5sig_pool();
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+EXPORT_SYMBOL(tcp_v4_md5_do_del);
+
+static void tcp_v4_clear_md5_list(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ /* Free each key, then the set of key keys,
+ * the crypto element, and then decrement our
+ * hold on the last resort crypto.
+ */
+ if (tp->md5sig_info->entries4) {
+ int i;
+ for (i = 0; i < tp->md5sig_info->entries4; i++)
+ kfree(tp->md5sig_info->keys4[i].base.key);
+ tp->md5sig_info->entries4 = 0;
+ tcp_free_md5sig_pool();
+ }
+ if (tp->md5sig_info->keys4) {
+ kfree(tp->md5sig_info->keys4);
+ tp->md5sig_info->keys4 = NULL;
+ tp->md5sig_info->alloced4 = 0;
+ }
+}
+
+static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
+ int optlen)
+{
+ struct tcp_md5sig cmd;
+ struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
+ u8 *newkey;
+
+ if (optlen < sizeof(cmd))
+ return -EINVAL;
+
+ if (copy_from_user(&cmd, optval, sizeof(cmd)))
+ return -EFAULT;
+
+ if (sin->sin_family != AF_INET)
+ return -EINVAL;
+
+ if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
+ if (!tcp_sk(sk)->md5sig_info)
+ return -ENOENT;
+ return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
+ }
+
+ if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
+ return -EINVAL;
+
+ if (!tcp_sk(sk)->md5sig_info) {
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL);
+
+ if (!p)
+ return -EINVAL;
+
+ tp->md5sig_info = p;
+ sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ }
+
+ newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
+ if (!newkey)
+ return -ENOMEM;
+ return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr,
+ newkey, cmd.tcpm_keylen);
+}
+
+static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
+ __be32 saddr, __be32 daddr,
+ struct tcphdr *th,
+ unsigned int tcplen)
+{
+ struct tcp_md5sig_pool *hp;
+ struct tcp4_pseudohdr *bp;
+ int err;
+
+ /*
+ * Okay, so RFC2385 is turned on for this connection,
+ * so we need to generate the MD5 hash for the packet now.
+ */
+
+ hp = tcp_get_md5sig_pool();
+ if (!hp)
+ goto clear_hash_noput;
+
+ bp = &hp->md5_blk.ip4;
+
+ /*
+ * The TCP pseudo-header (in the order: source IP address,
+ * destination IP address, zero-padded protocol number, and
+ * segment length)
+ */
+ bp->saddr = saddr;
+ bp->daddr = daddr;
+ bp->pad = 0;
+ bp->protocol = IPPROTO_TCP;
+ bp->len = htons(tcplen);
+
+ err = tcp_calc_md5_hash(md5_hash, key, sizeof(*bp),
+ th, tcplen, hp);
+ if (err)
+ goto clear_hash;
+
+ /* Free up the crypto pool */
+ tcp_put_md5sig_pool();
+out:
+ return 0;
+clear_hash:
+ tcp_put_md5sig_pool();
+clear_hash_noput:
+ memset(md5_hash, 0, 16);
+ goto out;
+}
+
+int tcp_v4_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
+ struct sock *sk,
+ struct dst_entry *dst,
+ struct request_sock *req,
+ struct tcphdr *th,
+ unsigned int tcplen)
+{
+ __be32 saddr, daddr;
+
+ if (sk) {
+ saddr = inet_sk(sk)->saddr;
+ daddr = inet_sk(sk)->daddr;
+ } else {
+ struct rtable *rt = (struct rtable *)dst;
+ BUG_ON(!rt);
+ saddr = rt->rt_src;
+ daddr = rt->rt_dst;
+ }
+ return tcp_v4_do_calc_md5_hash(md5_hash, key,
+ saddr, daddr,
+ th, tcplen);
+}
+
+EXPORT_SYMBOL(tcp_v4_calc_md5_hash);
+
+static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
+{
+ /*
+ * This gets called for each TCP segment that arrives
+ * so we want to be efficient.
+ * We have 3 drop cases:
+ * o No MD5 hash and one expected.
+ * o MD5 hash and we're not expecting one.
+ * o MD5 hash and its wrong.
+ */
+ __u8 *hash_location = NULL;
+ struct tcp_md5sig_key *hash_expected;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
+ int genhash;
+ unsigned char newhash[16];
+
+ hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
+ hash_location = tcp_parse_md5sig_option(th);
+
+ /* We've parsed the options - do we have a hash? */
+ if (!hash_expected && !hash_location)
+ return 0;
+
+ if (hash_expected && !hash_location) {
+ LIMIT_NETDEBUG(KERN_INFO "MD5 Hash expected but NOT found "
+ "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n",
+ NIPQUAD(iph->saddr), ntohs(th->source),
+ NIPQUAD(iph->daddr), ntohs(th->dest));
+ return 1;
+ }
+
+ if (!hash_expected && hash_location) {
+ LIMIT_NETDEBUG(KERN_INFO "MD5 Hash NOT expected but found "
+ "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n",
+ NIPQUAD(iph->saddr), ntohs(th->source),
+ NIPQUAD(iph->daddr), ntohs(th->dest));
+ return 1;
+ }
+
+ /* Okay, so this is hash_expected and hash_location -
+ * so we need to calculate the checksum.
+ */
+ genhash = tcp_v4_do_calc_md5_hash(newhash,
+ hash_expected,
+ iph->saddr, iph->daddr,
+ th, skb->len);
+
+ if (genhash || memcmp(hash_location, newhash, 16) != 0) {
+ if (net_ratelimit()) {
+ printk(KERN_INFO "MD5 Hash failed for "
+ "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)%s\n",
+ NIPQUAD(iph->saddr), ntohs(th->source),
+ NIPQUAD(iph->daddr), ntohs(th->dest),
+ genhash ? " tcp_v4_calc_md5_hash failed" : "");
+ }
+ return 1;
+ }
+ return 0;
+}
+
+#endif
+
+struct request_sock_ops tcp_request_sock_ops __read_mostly = {
.family = PF_INET,
.obj_size = sizeof(struct tcp_request_sock),
.rtx_syn_ack = tcp_v4_send_synack,
.send_reset = tcp_v4_send_reset,
};
+#ifdef CONFIG_TCP_MD5SIG
+static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+ .md5_lookup = tcp_v4_reqsk_md5_lookup,
+};
+#endif
+
static struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp_timewait_sock),
.twsk_unique = tcp_twsk_unique,
+ .twsk_destructor= tcp_twsk_destructor,
};
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
struct inet_request_sock *ireq;
struct tcp_options_received tmp_opt;
struct request_sock *req;
- __be32 saddr = skb->nh.iph->saddr;
- __be32 daddr = skb->nh.iph->daddr;
+ __be32 saddr = ip_hdr(skb)->saddr;
+ __be32 daddr = ip_hdr(skb)->daddr;
__u32 isn = TCP_SKB_CB(skb)->when;
struct dst_entry *dst = NULL;
#ifdef CONFIG_SYN_COOKIES
#endif
/* Never answer to SYNs send to broadcast or multicast */
- if (((struct rtable *)skb->dst)->rt_flags &
- (RTCF_BROADCAST | RTCF_MULTICAST))
+ if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
goto drop;
/* TW buckets are converted to open requests without
if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
- req = reqsk_alloc(&tcp_request_sock_ops);
+ req = inet_reqsk_alloc(&tcp_request_sock_ops);
if (!req)
goto drop;
+#ifdef CONFIG_TCP_MD5SIG
+ tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
+#endif
+
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = 536;
tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
tcp_parse_options(skb, &tmp_opt, 0);
- if (want_cookie) {
+ if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
- tmp_opt.saw_tstamp = 0;
- }
if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) {
/* Some OSes (unknown ones, but I see them on web server, which
ireq->rmt_addr = saddr;
ireq->opt = tcp_v4_save_options(sk, skb);
if (!want_cookie)
- TCP_ECN_create_request(req, skb->h.th);
+ TCP_ECN_create_request(req, tcp_hdr(skb));
if (want_cookie) {
#ifdef CONFIG_SYN_COOKIES
syn_flood_warning(skb);
+ req->cookie_ts = tmp_opt.tstamp_ok;
#endif
isn = cookie_v4_init_sequence(sk, skb, &req->mss);
} else if (!isn) {
(dst = inet_csk_route_req(sk, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
- if (xtime.tv_sec < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
+ if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
(s32)(peer->tcp_ts - req->ts_recent) >
TCP_PAWS_WINDOW) {
NET_INC_STATS_BH(LINUX_MIB_PAWSPASSIVEREJECTED);
- dst_release(dst);
- goto drop_and_free;
+ goto drop_and_release;
}
}
/* Kill the following clause, if you dislike this way. */
* to the moment of synflood.
*/
LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open "
- "request from %u.%u.%u.%u/%u\n",
+ "request from " NIPQUAD_FMT "/%u\n",
NIPQUAD(saddr),
- ntohs(skb->h.th->source));
- dst_release(dst);
- goto drop_and_free;
+ ntohs(tcp_hdr(skb)->source));
+ goto drop_and_release;
}
- isn = tcp_v4_init_sequence(sk, skb);
+ isn = tcp_v4_init_sequence(skb);
}
tcp_rsk(req)->snt_isn = isn;
- if (tcp_v4_send_synack(sk, req, dst))
+ if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
goto drop_and_free;
- if (want_cookie) {
- reqsk_free(req);
- } else {
- inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
- }
+ inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
return 0;
+drop_and_release:
+ dst_release(dst);
drop_and_free:
reqsk_free(req);
drop:
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
+#ifdef CONFIG_TCP_MD5SIG
+ struct tcp_md5sig_key *key;
+#endif
if (sk_acceptq_is_full(sk))
goto exit_overflow;
newinet->opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
- newinet->mc_ttl = skb->nh.iph->ttl;
+ newinet->mc_ttl = ip_hdr(skb)->ttl;
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
tcp_initialize_rcv_mss(newsk);
- __inet_hash(&tcp_hashinfo, newsk, 0);
- __inet_inherit_port(&tcp_hashinfo, sk, newsk);
+#ifdef CONFIG_TCP_MD5SIG
+ /* Copy over the MD5 key from the original socket */
+ if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) {
+ /*
+ * We're using one, so create a matching key
+ * on the newsk structure. If we fail to get
+ * memory, then we end up not copying the key
+ * across. Shucks.
+ */
+ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
+ if (newkey != NULL)
+ tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr,
+ newkey, key->keylen);
+ }
+#endif
+
+ __inet_hash_nolisten(newsk);
+ __inet_inherit_port(sk, newsk);
return newsk;
static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
- struct iphdr *iph = skb->nh.iph;
+ struct tcphdr *th = tcp_hdr(skb);
+ const struct iphdr *iph = ip_hdr(skb);
struct sock *nsk;
struct request_sock **prev;
/* Find possible connection requests. */
if (req)
return tcp_check_req(sk, skb, req, prev);
- nsk = inet_lookup_established(&tcp_hashinfo, skb->nh.iph->saddr,
- th->source, skb->nh.iph->daddr,
- th->dest, inet_iif(skb));
+ nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr,
+ th->source, iph->daddr, th->dest, inet_iif(skb));
if (nsk) {
if (nsk->sk_state != TCP_TIME_WAIT) {
return sk;
}
-static int tcp_v4_checksum_init(struct sk_buff *skb)
+static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
{
+ const struct iphdr *iph = ip_hdr(skb);
+
if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr,
- skb->nh.iph->daddr, skb->csum)) {
+ if (!tcp_v4_check(skb->len, iph->saddr,
+ iph->daddr, skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
return 0;
}
}
- skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr, skb->nh.iph->daddr,
+ skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
skb->len, IPPROTO_TCP, 0);
if (skb->len <= 76) {
*/
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
+ struct sock *rsk;
+#ifdef CONFIG_TCP_MD5SIG
+ /*
+ * We really want to reject the packet as early as possible
+ * if:
+ * o We're expecting an MD5'd packet and this is no MD5 tcp option
+ * o There is an MD5 option and we're not expecting one
+ */
+ if (tcp_v4_inbound_md5_hash(sk, skb))
+ goto discard;
+#endif
+
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_established(sk, skb, skb->h.th, skb->len))
+ if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
+ rsk = sk;
goto reset;
+ }
TCP_CHECK_TIMER(sk);
return 0;
}
- if (skb->len < (skb->h.th->doff << 2) || tcp_checksum_complete(skb))
+ if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
goto discard;
if (nsk != sk) {
- if (tcp_child_process(sk, nsk, skb))
+ if (tcp_child_process(sk, nsk, skb)) {
+ rsk = nsk;
goto reset;
+ }
return 0;
}
}
TCP_CHECK_TIMER(sk);
- if (tcp_rcv_state_process(sk, skb, skb->h.th, skb->len))
+ if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
+ rsk = sk;
goto reset;
+ }
TCP_CHECK_TIMER(sk);
return 0;
reset:
- tcp_v4_send_reset(skb);
+ tcp_v4_send_reset(rsk, skb);
discard:
kfree_skb(skb);
/* Be careful here. If this function gets more complicated and
int tcp_v4_rcv(struct sk_buff *skb)
{
+ const struct iphdr *iph;
struct tcphdr *th;
struct sock *sk;
int ret;
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
goto discard_it;
- th = skb->h.th;
+ th = tcp_hdr(skb);
if (th->doff < sizeof(struct tcphdr) / 4)
goto bad_packet;
* Packet length and doff are validated by header prediction,
* provided case of th->doff==0 is eliminated.
* So, we defer the checks. */
- if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
- tcp_v4_checksum_init(skb)))
+ if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb))
goto bad_packet;
- th = skb->h.th;
+ th = tcp_hdr(skb);
+ iph = ip_hdr(skb);
TCP_SKB_CB(skb)->seq = ntohl(th->seq);
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff * 4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
TCP_SKB_CB(skb)->when = 0;
- TCP_SKB_CB(skb)->flags = skb->nh.iph->tos;
+ TCP_SKB_CB(skb)->flags = iph->tos;
TCP_SKB_CB(skb)->sacked = 0;
- sk = __inet_lookup(&tcp_hashinfo, skb->nh.iph->saddr, th->source,
- skb->nh.iph->daddr, th->dest,
- inet_iif(skb));
-
+ sk = __inet_lookup(dev_net(skb->dev), &tcp_hashinfo, iph->saddr,
+ th->source, iph->daddr, th->dest, inet_iif(skb));
if (!sk)
goto no_tcp_socket;
bad_packet:
TCP_INC_STATS_BH(TCP_MIB_INERRS);
} else {
- tcp_v4_send_reset(skb);
+ tcp_v4_send_reset(NULL, skb);
}
discard_it:
/* Discard frame. */
kfree_skb(skb);
- return 0;
+ return 0;
discard_and_relse:
sock_put(sk);
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
- struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
- skb->nh.iph->daddr,
- th->dest,
+ struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
+ &tcp_hashinfo,
+ iph->daddr, th->dest,
inet_iif(skb));
if (sk2) {
inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
if (peer) {
if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
- (peer->tcp_ts_stamp + TCP_PAWS_MSL < xtime.tv_sec &&
+ (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) {
peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp;
peer->tcp_ts = tp->rx_opt.ts_recent;
const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
- (peer->tcp_ts_stamp + TCP_PAWS_MSL < xtime.tv_sec &&
+ (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) {
peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp;
peer->tcp_ts = tcptw->tw_ts_recent;
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
+ .bind_conflict = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
#endif
};
+#ifdef CONFIG_TCP_MD5SIG
+static struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
+ .md5_lookup = tcp_v4_md5_lookup,
+ .calc_md5_hash = tcp_v4_calc_md5_hash,
+ .md5_add = tcp_v4_md5_add_func,
+ .md5_parse = tcp_v4_parse_md5_keys,
+};
+#endif
+
/* NOTE: A lot of things set to zero explicitly by call to
* sk_alloc() so need not be done here.
*/
icsk->icsk_af_ops = &ipv4_specific;
icsk->icsk_sync_mss = tcp_sync_mss;
+#ifdef CONFIG_TCP_MD5SIG
+ tp->af_specific = &tcp_sock_ipv4_specific;
+#endif
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
return 0;
}
-int tcp_v4_destroy_sock(struct sock *sk)
+void tcp_v4_destroy_sock(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_cleanup_congestion_control(sk);
/* Cleanup up the write buffer. */
- sk_stream_writequeue_purge(sk);
+ tcp_write_queue_purge(sk);
/* Cleans up our, hopefully empty, out_of_order_queue. */
- __skb_queue_purge(&tp->out_of_order_queue);
+ __skb_queue_purge(&tp->out_of_order_queue);
+
+#ifdef CONFIG_TCP_MD5SIG
+ /* Clean up the MD5 key list, if any */
+ if (tp->md5sig_info) {
+ tcp_v4_clear_md5_list(sk);
+ kfree(tp->md5sig_info);
+ tp->md5sig_info = NULL;
+ }
+#endif
#ifdef CONFIG_NET_DMA
/* Cleans up our sk_async_wait_queue */
- __skb_queue_purge(&sk->sk_async_wait_queue);
+ __skb_queue_purge(&sk->sk_async_wait_queue);
#endif
/* Clean prequeue, it must be empty really */
/* Clean up a referenced TCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash)
- inet_put_port(&tcp_hashinfo, sk);
+ inet_put_port(sk);
/*
* If sendmsg cached page exists, toss it.
}
atomic_dec(&tcp_sockets_allocated);
-
- return 0;
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
struct hlist_node *node;
struct sock *sk = cur;
struct tcp_iter_state* st = seq->private;
+ struct net *net = seq_file_net(seq);
if (!sk) {
st->bucket = 0;
if (st->state == TCP_SEQ_STATE_OPENREQ) {
struct request_sock *req = cur;
- icsk = inet_csk(st->syn_wait_sk);
+ icsk = inet_csk(st->syn_wait_sk);
req = req->dl_next;
while (1) {
while (req) {
- if (req->rsk_ops->family == st->family) {
+ if (req->rsk_ops->family == st->family &&
+ net_eq(sock_net(req->sk), net)) {
cur = req;
goto out;
}
req = req->dl_next;
}
- if (++st->sbucket >= TCP_SYNQ_HSIZE)
+ if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries)
break;
get_req:
req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
st->state = TCP_SEQ_STATE_LISTENING;
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
} else {
- icsk = inet_csk(sk);
+ icsk = inet_csk(sk);
read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
if (reqsk_queue_len(&icsk->icsk_accept_queue))
goto start_req;
}
get_sk:
sk_for_each_from(sk, node) {
- if (sk->sk_family == st->family) {
+ if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
cur = sk;
goto out;
}
- icsk = inet_csk(sk);
+ icsk = inet_csk(sk);
read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
start_req:
static void *established_get_first(struct seq_file *seq)
{
struct tcp_iter_state* st = seq->private;
+ struct net *net = seq_file_net(seq);
void *rc = NULL;
for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) {
struct sock *sk;
struct hlist_node *node;
struct inet_timewait_sock *tw;
+ rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
- /* We can reschedule _before_ having picked the target: */
- cond_resched_softirq();
-
- read_lock(&tcp_hashinfo.ehash[st->bucket].lock);
+ read_lock_bh(lock);
sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
- if (sk->sk_family != st->family) {
+ if (sk->sk_family != st->family ||
+ !net_eq(sock_net(sk), net)) {
continue;
}
rc = sk;
}
st->state = TCP_SEQ_STATE_TIME_WAIT;
inet_twsk_for_each(tw, node,
- &tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain) {
- if (tw->tw_family != st->family) {
+ &tcp_hashinfo.ehash[st->bucket].twchain) {
+ if (tw->tw_family != st->family ||
+ !net_eq(twsk_net(tw), net)) {
continue;
}
rc = tw;
goto out;
}
- read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
+ read_unlock_bh(lock);
st->state = TCP_SEQ_STATE_ESTABLISHED;
}
out:
struct inet_timewait_sock *tw;
struct hlist_node *node;
struct tcp_iter_state* st = seq->private;
+ struct net *net = seq_file_net(seq);
++st->num;
tw = cur;
tw = tw_next(tw);
get_tw:
- while (tw && tw->tw_family != st->family) {
+ while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
tw = tw_next(tw);
}
if (tw) {
cur = tw;
goto out;
}
- read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
+ read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
st->state = TCP_SEQ_STATE_ESTABLISHED;
- /* We can reschedule between buckets: */
- cond_resched_softirq();
-
if (++st->bucket < tcp_hashinfo.ehash_size) {
- read_lock(&tcp_hashinfo.ehash[st->bucket].lock);
+ read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain);
} else {
cur = NULL;
sk = sk_next(sk);
sk_for_each_from(sk, node) {
- if (sk->sk_family == st->family)
+ if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
goto found;
}
st->state = TCP_SEQ_STATE_TIME_WAIT;
- tw = tw_head(&tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain);
+ tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
goto get_tw;
found:
cur = sk;
while (rc && pos) {
rc = established_get_next(seq, rc);
--pos;
- }
+ }
return rc;
}
if (!rc) {
inet_listen_unlock(&tcp_hashinfo);
- local_bh_disable();
st->state = TCP_SEQ_STATE_ESTABLISHED;
rc = established_get_idx(seq, pos);
}
rc = listening_get_next(seq, v);
if (!rc) {
inet_listen_unlock(&tcp_hashinfo);
- local_bh_disable();
st->state = TCP_SEQ_STATE_ESTABLISHED;
rc = established_get_first(seq);
}
case TCP_SEQ_STATE_TIME_WAIT:
case TCP_SEQ_STATE_ESTABLISHED:
if (v)
- read_unlock(&tcp_hashinfo.ehash[st->bucket].lock);
- local_bh_enable();
+ read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
break;
}
}
static int tcp_seq_open(struct inode *inode, struct file *file)
{
struct tcp_seq_afinfo *afinfo = PDE(inode)->data;
- struct seq_file *seq;
struct tcp_iter_state *s;
- int rc;
+ int err;
- if (unlikely(afinfo == NULL))
- return -EINVAL;
+ err = seq_open_net(inode, file, &afinfo->seq_ops,
+ sizeof(struct tcp_iter_state));
+ if (err < 0)
+ return err;
- s = kzalloc(sizeof(*s), GFP_KERNEL);
- if (!s)
- return -ENOMEM;
+ s = ((struct seq_file *)file->private_data)->private;
s->family = afinfo->family;
- s->seq_ops.start = tcp_seq_start;
- s->seq_ops.next = tcp_seq_next;
- s->seq_ops.show = afinfo->seq_show;
- s->seq_ops.stop = tcp_seq_stop;
-
- rc = seq_open(file, &s->seq_ops);
- if (rc)
- goto out_kfree;
- seq = file->private_data;
- seq->private = s;
-out:
- return rc;
-out_kfree:
- kfree(s);
- goto out;
+ return 0;
}
-int tcp_proc_register(struct tcp_seq_afinfo *afinfo)
+int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
{
int rc = 0;
struct proc_dir_entry *p;
- if (!afinfo)
- return -EINVAL;
- afinfo->seq_fops->owner = afinfo->owner;
- afinfo->seq_fops->open = tcp_seq_open;
- afinfo->seq_fops->read = seq_read;
- afinfo->seq_fops->llseek = seq_lseek;
- afinfo->seq_fops->release = seq_release_private;
-
- p = proc_net_fops_create(afinfo->name, S_IRUGO, afinfo->seq_fops);
- if (p)
- p->data = afinfo;
- else
+ afinfo->seq_fops.open = tcp_seq_open;
+ afinfo->seq_fops.read = seq_read;
+ afinfo->seq_fops.llseek = seq_lseek;
+ afinfo->seq_fops.release = seq_release_net;
+
+ afinfo->seq_ops.start = tcp_seq_start;
+ afinfo->seq_ops.next = tcp_seq_next;
+ afinfo->seq_ops.stop = tcp_seq_stop;
+
+ p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
+ &afinfo->seq_fops, afinfo);
+ if (!p)
rc = -ENOMEM;
return rc;
}
-void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo)
+void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
- if (!afinfo)
- return;
- proc_net_remove(afinfo->name);
- memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
+ proc_net_remove(net, afinfo->name);
}
static void get_openreq4(struct sock *sk, struct request_sock *req,
- char *tmpbuf, int i, int uid)
+ struct seq_file *f, int i, int uid, int *len)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int ttd = req->expires - jiffies;
- sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p",
+ seq_printf(f, "%4d: %08X:%04X %08X:%04X"
+ " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n",
i,
ireq->loc_addr,
ntohs(inet_sk(sk)->sport),
0, /* non standard timer */
0, /* open_requests have no inode */
atomic_read(&sk->sk_refcnt),
- req);
+ req,
+ len);
}
-static void get_tcp4_sock(struct sock *sp, char *tmpbuf, int i)
+static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
{
int timer_active;
unsigned long timer_expires;
- struct tcp_sock *tp = tcp_sk(sp);
- const struct inet_connection_sock *icsk = inet_csk(sp);
- struct inet_sock *inet = inet_sk(sp);
- unsigned int dest = inet->daddr;
- unsigned int src = inet->rcv_saddr;
+ struct tcp_sock *tp = tcp_sk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_sock *inet = inet_sk(sk);
+ __be32 dest = inet->daddr;
+ __be32 src = inet->rcv_saddr;
__u16 destp = ntohs(inet->dport);
__u16 srcp = ntohs(inet->sport);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
- } else if (timer_pending(&sp->sk_timer)) {
+ } else if (timer_pending(&sk->sk_timer)) {
timer_active = 2;
- timer_expires = sp->sk_timer.expires;
+ timer_expires = sk->sk_timer.expires;
} else {
timer_active = 0;
timer_expires = jiffies;
}
- sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
- "%08X %5d %8d %lu %d %p %u %u %u %u %d",
- i, src, srcp, dest, destp, sp->sk_state,
+ seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
+ "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n",
+ i, src, srcp, dest, destp, sk->sk_state,
tp->write_seq - tp->snd_una,
- (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
+ sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog :
+ (tp->rcv_nxt - tp->copied_seq),
timer_active,
jiffies_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
- sock_i_uid(sp),
+ sock_i_uid(sk),
icsk->icsk_probes_out,
- sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp,
- icsk->icsk_rto,
- icsk->icsk_ack.ato,
+ sock_i_ino(sk),
+ atomic_read(&sk->sk_refcnt), sk,
+ jiffies_to_clock_t(icsk->icsk_rto),
+ jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
- tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh);
+ tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh,
+ len);
}
-static void get_timewait4_sock(struct inet_timewait_sock *tw, char *tmpbuf, int i)
+static void get_timewait4_sock(struct inet_timewait_sock *tw,
+ struct seq_file *f, int i, int *len)
{
__be32 dest, src;
__u16 destp, srcp;
destp = ntohs(tw->tw_dport);
srcp = ntohs(tw->tw_sport);
- sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p",
+ seq_printf(f, "%4d: %08X:%04X %08X:%04X"
+ " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p%n",
i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
- atomic_read(&tw->tw_refcnt), tw);
+ atomic_read(&tw->tw_refcnt), tw, len);
}
#define TMPSZ 150
static int tcp4_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state* st;
- char tmpbuf[TMPSZ + 1];
+ int len;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%-*s\n", TMPSZ - 1,
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
case TCP_SEQ_STATE_ESTABLISHED:
- get_tcp4_sock(v, tmpbuf, st->num);
+ get_tcp4_sock(v, seq, st->num, &len);
break;
case TCP_SEQ_STATE_OPENREQ:
- get_openreq4(st->syn_wait_sk, v, tmpbuf, st->num, st->uid);
+ get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
break;
case TCP_SEQ_STATE_TIME_WAIT:
- get_timewait4_sock(v, tmpbuf, st->num);
+ get_timewait4_sock(v, seq, st->num, &len);
break;
}
- seq_printf(seq, "%-*s\n", TMPSZ - 1, tmpbuf);
+ seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
out:
return 0;
}
-static struct file_operations tcp4_seq_fops;
static struct tcp_seq_afinfo tcp4_seq_afinfo = {
- .owner = THIS_MODULE,
.name = "tcp",
.family = AF_INET,
- .seq_show = tcp4_seq_show,
- .seq_fops = &tcp4_seq_fops,
+ .seq_fops = {
+ .owner = THIS_MODULE,
+ },
+ .seq_ops = {
+ .show = tcp4_seq_show,
+ },
+};
+
+static int tcp4_proc_init_net(struct net *net)
+{
+ return tcp_proc_register(net, &tcp4_seq_afinfo);
+}
+
+static void tcp4_proc_exit_net(struct net *net)
+{
+ tcp_proc_unregister(net, &tcp4_seq_afinfo);
+}
+
+static struct pernet_operations tcp4_net_ops = {
+ .init = tcp4_proc_init_net,
+ .exit = tcp4_proc_exit_net,
};
int __init tcp4_proc_init(void)
{
- return tcp_proc_register(&tcp4_seq_afinfo);
+ return register_pernet_subsys(&tcp4_net_ops);
}
void tcp4_proc_exit(void)
{
- tcp_proc_unregister(&tcp4_seq_afinfo);
+ unregister_pernet_subsys(&tcp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
- .sendmsg = tcp_sendmsg,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v4_do_rcv,
- .hash = tcp_v4_hash,
- .unhash = tcp_unhash,
- .get_port = tcp_v4_get_port,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
.obj_size = sizeof(struct tcp_sock),
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
+ .h.hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
};
-void __init tcp_v4_init(struct net_proto_family *ops)
+
+static int __net_init tcp_sk_init(struct net *net)
+{
+ return inet_ctl_sock_create(&net->ipv4.tcp_sock,
+ PF_INET, SOCK_RAW, IPPROTO_TCP, net);
+}
+
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+ inet_ctl_sock_destroy(net->ipv4.tcp_sock);
+}
+
+static struct pernet_operations __net_initdata tcp_sk_ops = {
+ .init = tcp_sk_init,
+ .exit = tcp_sk_exit,
+};
+
+void __init tcp_v4_init(void)
{
- if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW, IPPROTO_TCP) < 0)
+ if (register_pernet_device(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
}
EXPORT_SYMBOL(ipv4_specific);
EXPORT_SYMBOL(tcp_hashinfo);
EXPORT_SYMBOL(tcp_prot);
-EXPORT_SYMBOL(tcp_unhash);
EXPORT_SYMBOL(tcp_v4_conn_request);
EXPORT_SYMBOL(tcp_v4_connect);
EXPORT_SYMBOL(tcp_v4_do_rcv);
EXPORT_SYMBOL(tcp_proc_register);
EXPORT_SYMBOL(tcp_proc_unregister);
#endif
-EXPORT_SYMBOL(sysctl_local_port_range);
EXPORT_SYMBOL(sysctl_tcp_low_latency);