*
* 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/bottom_half.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.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 __read_mostly;
-
-void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
#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, int protocol,
- unsigned int tcplen);
+static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+ __be32 daddr, __be32 saddr, struct tcphdr *th);
+#else
+static inline
+struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
+{
+ return NULL;
+}
#endif
-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),
-};
+struct inet_hashinfo tcp_hashinfo;
static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
{
nexthop = inet->opt->faddr;
}
- tmp = ip_route_connect(&rt, nexthop, inet->saddr,
+ tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
- inet->sport, usin->sin_port, sk, 1);
+ inet->inet_sport, usin->sin_port, sk, 1);
if (tmp < 0) {
if (tmp == -ENETUNREACH)
- IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return tmp;
}
if (!inet->opt || !inet->opt->srr)
daddr = rt->rt_dst;
- if (!inet->saddr)
- inet->saddr = rt->rt_src;
- inet->rcv_saddr = inet->saddr;
+ if (!inet->inet_saddr)
+ inet->inet_saddr = rt->rt_src;
+ inet->inet_rcv_saddr = inet->inet_saddr;
- if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) {
+ if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
/* Reset inherited state */
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
* when trying new connection.
*/
if (peer != NULL &&
- peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) {
+ (u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
- inet->dport = usin->sin_port;
- inet->daddr = daddr;
+ inet->inet_dport = usin->sin_port;
+ inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
- tp->rx_opt.mss_clamp = 536;
+ tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;
/* Socket identity is still unknown (sport may be zero).
* However we set state to SYN-SENT and not releasing socket
goto failure;
err = ip_route_newports(&rt, IPPROTO_TCP,
- inet->sport, inet->dport, sk);
+ inet->inet_sport, inet->inet_dport, sk);
if (err)
goto failure;
sk_setup_caps(sk, &rt->u.dst);
if (!tp->write_seq)
- tp->write_seq = secure_tcp_sequence_number(inet->saddr,
- inet->daddr,
- inet->sport,
+ tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
+ inet->inet_daddr,
+ inet->inet_sport,
usin->sin_port);
- inet->id = tp->write_seq ^ jiffies;
+ inet->inet_id = tp->write_seq ^ jiffies;
err = tcp_connect(sk);
rt = NULL;
tcp_set_state(sk, TCP_CLOSE);
ip_rt_put(rt);
sk->sk_route_caps = 0;
- inet->dport = 0;
+ inet->inet_dport = 0;
return err;
}
*
*/
-void tcp_v4_err(struct sk_buff *skb, u32 info)
+void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
{
- struct iphdr *iph = (struct iphdr *)skb->data;
- struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2));
+ struct iphdr *iph = (struct iphdr *)icmp_skb->data;
+ struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
+ struct inet_connection_sock *icsk;
struct tcp_sock *tp;
struct inet_sock *inet;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
+ const int type = icmp_hdr(icmp_skb)->type;
+ const int code = icmp_hdr(icmp_skb)->code;
struct sock *sk;
+ struct sk_buff *skb;
__u32 seq;
+ __u32 remaining;
int err;
+ struct net *net = dev_net(icmp_skb->dev);
- if (skb->len < (iph->ihl << 2) + 8) {
- ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
+ if (icmp_skb->len < (iph->ihl << 2) + 8) {
+ ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
- sk = inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->daddr, th->dest,
- iph->saddr, th->source, inet_iif(skb));
+ sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
+ iph->saddr, th->source, inet_iif(icmp_skb));
if (!sk) {
- ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
+ ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
* servers this needs to be solved differently.
*/
if (sock_owned_by_user(sk))
- NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);
+ NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
+ icsk = inet_csk(sk);
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
- NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
+ NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
}
err = icmp_err_convert[code].errno;
+ /* check if icmp_skb allows revert of backoff
+ * (see draft-zimmermann-tcp-lcd) */
+ if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
+ break;
+ if (seq != tp->snd_una || !icsk->icsk_retransmits ||
+ !icsk->icsk_backoff)
+ break;
+
+ icsk->icsk_backoff--;
+ inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) <<
+ icsk->icsk_backoff;
+ tcp_bound_rto(sk);
+
+ skb = tcp_write_queue_head(sk);
+ BUG_ON(!skb);
+
+ remaining = icsk->icsk_rto - min(icsk->icsk_rto,
+ tcp_time_stamp - TCP_SKB_CB(skb)->when);
+
+ if (remaining) {
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ remaining, TCP_RTO_MAX);
+ } else if (sock_owned_by_user(sk)) {
+ /* RTO revert clocked out retransmission,
+ * but socket is locked. Will defer. */
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ HZ/20, TCP_RTO_MAX);
+ } else {
+ /* RTO revert clocked out retransmission.
+ * Will retransmit now */
+ tcp_retransmit_timer(sk);
+ }
+
break;
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
/* ICMPs are not backlogged, hence we cannot get
an established socket here.
*/
- BUG_TRAP(!req->sk);
+ WARN_ON(req->sk);
if (seq != tcp_rsk(req)->snt_isn) {
- NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
+ NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
struct tcphdr *th = tcp_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- th->check = ~tcp_v4_check(len, inet->saddr,
- inet->daddr, 0);
+ th->check = ~tcp_v4_check(len, inet->inet_saddr,
+ inet->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(len, inet->saddr, inet->daddr,
- csum_partial((char *)th,
+ th->check = tcp_v4_check(len, inet->inet_saddr,
+ inet->inet_daddr,
+ csum_partial(th,
th->doff << 2,
skb->csum));
}
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
+ struct net *net;
/* Never send a reset in response to a reset. */
if (th->rst)
return;
- if (skb->rtable->rt_type != RTN_LOCAL)
+ if (skb_rtable(skb)->rt_type != RTN_LOCAL)
return;
/* Swap the send and the receive. */
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, IPPROTO_TCP,
- arg.iov[0].iov_len);
+ tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1],
+ key, ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, &rep.th);
}
#endif
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr, /* XXX */
- sizeof(struct tcphdr), IPPROTO_TCP, 0);
+ arg.iov[0].iov_len, IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
+ arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
- ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);
+ net = dev_net(skb_dst(skb)->dev);
+ ip_send_reply(net->ipv4.tcp_sock, skb,
+ &arg, arg.iov[0].iov_len);
- TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
- TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
+ TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
+ TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
}
/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
- struct sk_buff *skb, u32 seq, u32 ack,
- u32 win, u32 ts)
+static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+ u32 win, u32 ts, int oif,
+ struct tcp_md5sig_key *key,
+ int reply_flags)
{
struct tcphdr *th = tcp_hdr(skb);
struct {
];
} rep;
struct ip_reply_arg arg;
-#ifdef CONFIG_TCP_MD5SIG
- struct tcp_md5sig_key *key;
- struct tcp_md5sig_key tw_key;
-#endif
+ struct net *net = dev_net(skb_dst(skb)->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
rep.th.window = htons(win);
#ifdef CONFIG_TCP_MD5SIG
- /*
- * The SKB holds an imcoming packet, but may not have a valid ->sk
- * pointer. This is especially the case when we're dealing with a
- * TIME_WAIT ack, because the sk structure is long gone, and only
- * the tcp_timewait_sock remains. So the md5 key is stashed in that
- * structure, and we use it in preference. I believe that (twsk ||
- * skb->sk) holds true, but we program defensively.
- */
- if (!twsk && skb->sk) {
- key = tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr);
- } else if (twsk && twsk->tw_md5_keylen) {
- tw_key.key = twsk->tw_md5_key;
- tw_key.keylen = twsk->tw_md5_keylen;
- key = &tw_key;
- } else
- key = NULL;
-
if (key) {
int offset = (ts) ? 3 : 0;
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, IPPROTO_TCP,
- arg.iov[0].iov_len);
+ tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset],
+ key, ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, &rep.th);
}
#endif
+ arg.flags = reply_flags;
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 (twsk)
- arg.bound_dev_if = twsk->tw_sk.tw_bound_dev_if;
+ if (oif)
+ arg.bound_dev_if = oif;
- ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);
+ ip_send_reply(net->ipv4.tcp_sock, skb,
+ &arg, arg.iov[0].iov_len);
- TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
+ TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
}
static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(tcptw, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ 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_ts_recent,
+ tw->tw_bound_dev_if,
+ tcp_twsk_md5_key(tcptw),
+ tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
+ );
inet_twsk_put(tw);
}
-static void tcp_v4_reqsk_send_ack(struct sk_buff *skb,
+static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
- tcp_v4_send_ack(NULL, skb, tcp_rsk(req)->snt_isn + 1,
+ tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
- req->ts_recent);
+ req->ts_recent,
+ 0,
+ tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
+ inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
}
/*
* 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 dst_entry *dst,
+ struct request_sock *req,
+ struct request_values *rvp)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
return -1;
- skb = tcp_make_synack(sk, dst, req);
+ skb = tcp_make_synack(sk, dst, req, rvp);
if (skb) {
struct tcphdr *th = tcp_hdr(skb);
th->check = tcp_v4_check(skb->len,
ireq->loc_addr,
ireq->rmt_addr,
- csum_partial((char *)th, skb->len,
+ csum_partial(th, skb->len,
skb->csum));
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
return err;
}
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
+static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
+ struct request_values *rvp)
{
- return __tcp_v4_send_synack(sk, req, NULL);
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ return tcp_v4_send_synack(sk, NULL, req, rvp);
}
/*
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);
+ return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
}
EXPORT_SYMBOL(tcp_v4_md5_lookup);
}
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
- if (tcp_alloc_md5sig_pool() == NULL) {
+ if (tcp_alloc_md5sig_pool(sk) == NULL) {
kfree(newkey);
return -ENOMEM;
}
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,
+ return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr,
newkey, newkeylen);
}
if (!tcp_sk(sk)->md5sig_info) {
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL);
+ struct tcp_md5sig_info *p;
+ p = kzalloc(sizeof(*p), sk->sk_allocation);
if (!p)
return -EINVAL;
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
- newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
+ newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation);
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, int protocol,
- unsigned int tcplen)
+static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
+ __be32 daddr, __be32 saddr, int nbytes)
{
- struct scatterlist sg[4];
- __u16 data_len;
- int block = 0;
- __sum16 old_checksum;
- struct tcp_md5sig_pool *hp;
struct tcp4_pseudohdr *bp;
- struct hash_desc *desc;
- int err;
- unsigned int nbytes = 0;
-
- /*
- * 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;
+ struct scatterlist sg;
bp = &hp->md5_blk.ip4;
- desc = &hp->md5_desc;
/*
* 1. the TCP pseudo-header (in the order: source IP address,
bp->saddr = saddr;
bp->daddr = daddr;
bp->pad = 0;
- bp->protocol = protocol;
- bp->len = htons(tcplen);
+ bp->protocol = IPPROTO_TCP;
+ bp->len = cpu_to_be16(nbytes);
- sg_init_table(sg, 4);
-
- sg_set_buf(&sg[block++], bp, sizeof(*bp));
- nbytes += sizeof(*bp);
-
- /* 2. the TCP header, excluding options, and assuming a
- * checksum of zero/
- */
- old_checksum = th->check;
- th->check = 0;
- sg_set_buf(&sg[block++], th, sizeof(struct tcphdr));
- nbytes += sizeof(struct tcphdr);
-
- /* 3. the TCP segment data (if any) */
- data_len = tcplen - (th->doff << 2);
- if (data_len > 0) {
- unsigned char *data = (unsigned char *)th + (th->doff << 2);
- sg_set_buf(&sg[block++], data, data_len);
- nbytes += data_len;
- }
+ sg_init_one(&sg, bp, sizeof(*bp));
+ return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
+}
- /* 4. an independently-specified key or password, known to both
- * TCPs and presumably connection-specific
- */
- sg_set_buf(&sg[block++], key->key, key->keylen);
- nbytes += key->keylen;
+static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+ __be32 daddr, __be32 saddr, struct tcphdr *th)
+{
+ struct tcp_md5sig_pool *hp;
+ struct hash_desc *desc;
- sg_mark_end(&sg[block - 1]);
+ hp = tcp_get_md5sig_pool();
+ if (!hp)
+ goto clear_hash_noput;
+ desc = &hp->md5_desc;
- /* Now store the Hash into the packet */
- err = crypto_hash_init(desc);
- if (err)
+ if (crypto_hash_init(desc))
goto clear_hash;
- err = crypto_hash_update(desc, sg, nbytes);
- if (err)
+ if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
goto clear_hash;
- err = crypto_hash_final(desc, md5_hash);
- if (err)
+ if (tcp_md5_hash_header(hp, th))
+ goto clear_hash;
+ if (tcp_md5_hash_key(hp, key))
+ goto clear_hash;
+ if (crypto_hash_final(desc, md5_hash))
goto clear_hash;
- /* Reset header, and free up the crypto */
tcp_put_md5sig_pool();
- th->check = old_checksum;
-
-out:
return 0;
+
clear_hash:
tcp_put_md5sig_pool();
clear_hash_noput:
memset(md5_hash, 0, 16);
- goto out;
+ return 1;
}
-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, int protocol,
- unsigned int tcplen)
+int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
+ struct sock *sk, struct request_sock *req,
+ struct sk_buff *skb)
{
+ struct tcp_md5sig_pool *hp;
+ struct hash_desc *desc;
+ struct tcphdr *th = tcp_hdr(skb);
__be32 saddr, daddr;
if (sk) {
- saddr = inet_sk(sk)->saddr;
- daddr = inet_sk(sk)->daddr;
+ saddr = inet_sk(sk)->inet_saddr;
+ daddr = inet_sk(sk)->inet_daddr;
+ } else if (req) {
+ saddr = inet_rsk(req)->loc_addr;
+ daddr = inet_rsk(req)->rmt_addr;
} else {
- struct rtable *rt = (struct rtable *)dst;
- BUG_ON(!rt);
- saddr = rt->rt_src;
- daddr = rt->rt_dst;
+ const struct iphdr *iph = ip_hdr(skb);
+ saddr = iph->saddr;
+ daddr = iph->daddr;
}
- return tcp_v4_do_calc_md5_hash(md5_hash, key,
- saddr, daddr,
- th, protocol, tcplen);
+
+ hp = tcp_get_md5sig_pool();
+ if (!hp)
+ goto clear_hash_noput;
+ desc = &hp->md5_desc;
+
+ if (crypto_hash_init(desc))
+ goto clear_hash;
+
+ if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
+ goto clear_hash;
+ if (tcp_md5_hash_header(hp, th))
+ goto clear_hash;
+ if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
+ goto clear_hash;
+ if (tcp_md5_hash_key(hp, key))
+ goto clear_hash;
+ if (crypto_hash_final(desc, md5_hash))
+ goto clear_hash;
+
+ tcp_put_md5sig_pool();
+ return 0;
+
+clear_hash:
+ tcp_put_md5sig_pool();
+clear_hash_noput:
+ memset(md5_hash, 0, 16);
+ return 1;
}
-EXPORT_SYMBOL(tcp_v4_calc_md5_hash);
+EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
{
struct tcp_md5sig_key *hash_expected;
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
- int length = (th->doff << 2) - sizeof(struct tcphdr);
int genhash;
- unsigned char *ptr;
unsigned char newhash[16];
hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
+ hash_location = tcp_parse_md5sig_option(th);
- /*
- * If the TCP option length is less than the TCP_MD5SIG
- * option length, then we can shortcut
- */
- if (length < TCPOLEN_MD5SIG) {
- if (hash_expected)
- return 1;
- else
- return 0;
- }
-
- /* Okay, we can't shortcut - we have to grub through the options */
- ptr = (unsigned char *)(th + 1);
- while (length > 0) {
- int opcode = *ptr++;
- int opsize;
-
- switch (opcode) {
- case TCPOPT_EOL:
- goto done_opts;
- case TCPOPT_NOP:
- length--;
- continue;
- default:
- opsize = *ptr++;
- if (opsize < 2)
- goto done_opts;
- if (opsize > length)
- goto done_opts;
-
- if (opcode == TCPOPT_MD5SIG) {
- hash_location = ptr;
- goto done_opts;
- }
- }
- ptr += opsize-2;
- length -= opsize;
- }
-done_opts:
/* 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));
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
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));
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
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, sk->sk_protocol,
- skb->len);
+ genhash = tcp_v4_md5_hash_skb(newhash,
+ hash_expected,
+ NULL, NULL, skb);
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),
+ printk(KERN_INFO "MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
+ &iph->saddr, ntohs(th->source),
+ &iph->daddr, ntohs(th->dest),
genhash ? " tcp_v4_calc_md5_hash failed" : "");
}
return 1;
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,
+ .rtx_syn_ack = tcp_v4_rtx_synack,
.send_ack = tcp_v4_reqsk_send_ack,
.destructor = tcp_v4_reqsk_destructor,
.send_reset = tcp_v4_send_reset,
+ .syn_ack_timeout = tcp_syn_ack_timeout,
};
#ifdef CONFIG_TCP_MD5SIG
-static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
.md5_lookup = tcp_v4_reqsk_md5_lookup,
+ .calc_md5_hash = tcp_v4_md5_hash_skb,
};
#endif
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct inet_request_sock *ireq;
+ struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ u8 *hash_location;
struct request_sock *req;
+ struct inet_request_sock *ireq;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = NULL;
__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
int want_cookie = 0;
#else
#endif
/* Never answer to SYNs send to broadcast or multicast */
- if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+ if (skb_rtable(skb)->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;
#endif
tcp_clear_options(&tmp_opt);
- tmp_opt.mss_clamp = 536;
- tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
+ tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
+ tmp_opt.user_mss = tp->rx_opt.user_mss;
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+
+ if (tmp_opt.cookie_plus > 0 &&
+ tmp_opt.saw_tstamp &&
+ !tp->rx_opt.cookie_out_never &&
+ (sysctl_tcp_cookie_size > 0 ||
+ (tp->cookie_values != NULL &&
+ tp->cookie_values->cookie_desired > 0))) {
+ u8 *c;
+ u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
+ int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
+
+ if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
+ goto drop_and_release;
- tcp_parse_options(skb, &tmp_opt, 0);
+ /* Secret recipe starts with IP addresses */
+ *mess++ ^= daddr;
+ *mess++ ^= saddr;
- if (want_cookie) {
- tcp_clear_options(&tmp_opt);
- tmp_opt.saw_tstamp = 0;
- }
+ /* plus variable length Initiator Cookie */
+ c = (u8 *)mess;
+ while (l-- > 0)
+ *c++ ^= *hash_location++;
- if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) {
- /* Some OSes (unknown ones, but I see them on web server, which
- * contains information interesting only for windows'
- * users) do not send their stamp in SYN. It is easy case.
- * We simply do not advertise TS support.
- */
- tmp_opt.saw_tstamp = 0;
- tmp_opt.tstamp_ok = 0;
+#ifdef CONFIG_SYN_COOKIES
+ want_cookie = 0; /* not our kind of cookie */
+#endif
+ tmp_ext.cookie_out_never = 0; /* false */
+ tmp_ext.cookie_plus = tmp_opt.cookie_plus;
+ } else if (!tp->rx_opt.cookie_in_always) {
+ /* redundant indications, but ensure initialization. */
+ tmp_ext.cookie_out_never = 1; /* true */
+ tmp_ext.cookie_plus = 0;
+ } else {
+ goto drop_and_release;
}
- tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
+ tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
- tcp_openreq_init(req, &tmp_opt, skb);
+ if (want_cookie && !tmp_opt.saw_tstamp)
+ tcp_clear_options(&tmp_opt);
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
+ tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
+ tcp_openreq_init(req, &tmp_opt, skb);
ireq = inet_rsk(req);
ireq->loc_addr = daddr;
ireq->rmt_addr = saddr;
+ ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
if (!want_cookie)
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 (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
+ if ((u32)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);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
goto drop_and_release;
}
}
* to destinations, already remembered
* to the moment of synflood.
*/
- LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open "
- "request from %u.%u.%u.%u/%u\n",
- NIPQUAD(saddr),
- ntohs(tcp_hdr(skb)->source));
+ LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI4/%u\n",
+ &saddr, ntohs(tcp_hdr(skb)->source));
goto drop_and_release;
}
}
tcp_rsk(req)->snt_isn = isn;
- if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
+ if (tcp_v4_send_synack(sk, dst, req,
+ (struct request_values *)&tmp_ext) ||
+ want_cookie)
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
- newinet->daddr = ireq->rmt_addr;
- newinet->rcv_saddr = ireq->loc_addr;
- newinet->saddr = ireq->loc_addr;
+ newinet->inet_daddr = ireq->rmt_addr;
+ newinet->inet_rcv_saddr = ireq->loc_addr;
+ newinet->inet_saddr = ireq->loc_addr;
newinet->opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
- newinet->id = newtp->write_seq ^ jiffies;
+ newinet->inet_id = newtp->write_seq ^ jiffies;
tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
+ if (tcp_sk(sk)->rx_opt.user_mss &&
+ tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
+ newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+
tcp_initialize_rcv_mss(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) {
+ key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
+ if (key != NULL) {
/*
* We're using one, so create a matching key
* on the newsk structure. If we fail to get
*/
char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
if (newkey != NULL)
- tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr,
+ tcp_v4_md5_do_add(newsk, newinet->inet_daddr,
newkey, key->keylen);
+ newsk->sk_route_caps &= ~NETIF_F_GSO_MASK;
}
#endif
- __inet_hash_nolisten(newsk);
+ __inet_hash_nolisten(newsk, NULL);
__inet_inherit_port(sk, newsk);
return newsk;
exit_overflow:
- NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit:
- NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
dst_release(dst);
return NULL;
}
if (req)
return tcp_check_req(sk, skb, req, prev);
- nsk = inet_lookup_established(sk->sk_net, &tcp_hashinfo, iph->saddr,
+ nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr,
th->source, iph->daddr, th->dest, inet_iif(skb));
if (nsk) {
return 0;
csum_err:
- TCP_INC_STATS_BH(TCP_MIB_INERRS);
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
}
struct tcphdr *th;
struct sock *sk;
int ret;
+ struct net *net = dev_net(skb->dev);
if (skb->pkt_type != PACKET_HOST)
goto discard_it;
/* Count it even if it's bad */
- TCP_INC_STATS_BH(TCP_MIB_INSEGS);
+ TCP_INC_STATS_BH(net, TCP_MIB_INSEGS);
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
goto discard_it;
TCP_SKB_CB(skb)->flags = iph->tos;
TCP_SKB_CB(skb)->sacked = 0;
- sk = __inet_lookup(skb->dev->nd_net, &tcp_hashinfo, iph->saddr,
- th->source, iph->daddr, th->dest, inet_iif(skb));
+ sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
if (!sk)
goto no_tcp_socket;
+ if (iph->ttl < inet_sk(sk)->min_ttl)
+ goto discard_and_relse;
+
process:
if (sk->sk_state == TCP_TIME_WAIT)
goto do_time_wait;
#ifdef CONFIG_NET_DMA
struct tcp_sock *tp = tcp_sk(sk);
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan)
ret = tcp_v4_do_rcv(sk, skb);
else
#endif
{
if (!tcp_prequeue(sk, skb))
- ret = tcp_v4_do_rcv(sk, skb);
+ ret = tcp_v4_do_rcv(sk, skb);
}
} else
sk_add_backlog(sk, skb);
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
- TCP_INC_STATS_BH(TCP_MIB_INERRS);
+ TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
} else {
tcp_v4_send_reset(NULL, skb);
}
}
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
- TCP_INC_STATS_BH(TCP_MIB_INERRS);
+ TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
- struct sock *sk2 = inet_lookup_listener(skb->dev->nd_net,
+ struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
&tcp_hashinfo,
iph->daddr, th->dest,
inet_iif(skb));
struct inet_peer *peer = NULL;
int release_it = 0;
- if (!rt || rt->rt_dst != inet->daddr) {
- peer = inet_getpeer(inet->daddr, 1);
+ if (!rt || rt->rt_dst != inet->inet_daddr) {
+ peer = inet_getpeer(inet->inet_daddr, 1);
release_it = 1;
} else {
if (!rt->peer)
if (peer) {
if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
- (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;
+ ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
+ peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
+ peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
peer->tcp_ts = tp->rx_opt.ts_recent;
}
if (release_it)
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 < get_seconds() &&
- peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) {
- peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp;
+ ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
+ peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
+ peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
peer->tcp_ts = tcptw->tw_ts_recent;
}
inet_putpeer(peer);
return 0;
}
-struct inet_connection_sock_af_ops ipv4_specific = {
+const struct inet_connection_sock_af_ops ipv4_specific = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
};
#ifdef CONFIG_TCP_MD5SIG
-static struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
+static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
.md5_lookup = tcp_v4_md5_lookup,
- .calc_md5_hash = tcp_v4_calc_md5_hash,
+ .calc_md5_hash = tcp_v4_md5_hash_skb,
.md5_add = tcp_v4_md5_add_func,
.md5_parse = tcp_v4_parse_md5_keys,
};
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
*/
- tp->snd_ssthresh = 0x7fffffff; /* Infinity */
+ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
- tp->mss_cache = 536;
+ tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = sysctl_tcp_reordering;
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
tp->af_specific = &tcp_sock_ipv4_specific;
#endif
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data_payload. */
+ tp->cookie_values =
+ kzalloc(sizeof(*tp->cookie_values),
+ sk->sk_allocation);
+ if (tp->cookie_values != NULL)
+ kref_init(&tp->cookie_values->kref);
+ }
+ /* Presumed zeroed, in order of appearance:
+ * cookie_in_always, cookie_out_never,
+ * s_data_constant, s_data_in, s_data_out
+ */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
- atomic_inc(&tcp_sockets_allocated);
+ local_bh_disable();
+ percpu_counter_inc(&tcp_sockets_allocated);
+ local_bh_enable();
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);
sk->sk_sndmsg_page = NULL;
}
- if (tp->defer_tcp_accept.request) {
- reqsk_free(tp->defer_tcp_accept.request);
- sock_put(tp->defer_tcp_accept.listen_sk);
- sock_put(sk);
- tp->defer_tcp_accept.listen_sk = NULL;
- tp->defer_tcp_accept.request = NULL;
+ /* TCP Cookie Transactions */
+ if (tp->cookie_values != NULL) {
+ kref_put(&tp->cookie_values->kref,
+ tcp_cookie_values_release);
+ tp->cookie_values = NULL;
}
- atomic_dec(&tcp_sockets_allocated);
-
- return 0;
+ percpu_counter_dec(&tcp_sockets_allocated);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */
-static inline struct inet_timewait_sock *tw_head(struct hlist_head *head)
+static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
{
- return hlist_empty(head) ? NULL :
+ return hlist_nulls_empty(head) ? NULL :
list_entry(head->first, struct inet_timewait_sock, tw_node);
}
static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
{
- return tw->tw_node.next ?
- hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
+ return !is_a_nulls(tw->tw_node.next) ?
+ hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}
static void *listening_get_next(struct seq_file *seq, void *cur)
{
struct inet_connection_sock *icsk;
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct sock *sk = cur;
- struct tcp_iter_state* st = seq->private;
- struct net *net = st->net;
+ struct inet_listen_hashbucket *ilb;
+ struct tcp_iter_state *st = seq->private;
+ struct net *net = seq_file_net(seq);
if (!sk) {
st->bucket = 0;
- sk = sk_head(&tcp_hashinfo.listening_hash[0]);
+ ilb = &tcp_hashinfo.listening_hash[0];
+ spin_lock_bh(&ilb->lock);
+ sk = sk_nulls_head(&ilb->head);
goto get_sk;
}
-
+ ilb = &tcp_hashinfo.listening_hash[st->bucket];
++st->num;
if (st->state == TCP_SEQ_STATE_OPENREQ) {
req = req->dl_next;
while (1) {
while (req) {
- if (req->rsk_ops->family == st->family &&
- req->sk->sk_net == net) {
+ if (req->rsk_ops->family == st->family) {
cur = req;
goto out;
}
sk = sk_next(sk);
}
get_sk:
- sk_for_each_from(sk, node) {
- if (sk->sk_family == st->family && sk->sk_net == net) {
+ sk_nulls_for_each_from(sk, node) {
+ if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
cur = sk;
goto out;
}
}
read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
}
+ spin_unlock_bh(&ilb->lock);
if (++st->bucket < INET_LHTABLE_SIZE) {
- sk = sk_head(&tcp_hashinfo.listening_hash[st->bucket]);
+ ilb = &tcp_hashinfo.listening_hash[st->bucket];
+ spin_lock_bh(&ilb->lock);
+ sk = sk_nulls_head(&ilb->head);
goto get_sk;
}
cur = NULL;
return rc;
}
+static inline int empty_bucket(struct tcp_iter_state *st)
+{
+ return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
+ hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+}
+
static void *established_get_first(struct seq_file *seq)
{
- struct tcp_iter_state* st = seq->private;
- struct net *net = st->net;
+ 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) {
+ for (st->bucket = 0; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
struct sock *sk;
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct inet_timewait_sock *tw;
- rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
+ spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
- read_lock_bh(lock);
- sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
+ /* Lockless fast path for the common case of empty buckets */
+ if (empty_bucket(st))
+ continue;
+
+ spin_lock_bh(lock);
+ sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
if (sk->sk_family != st->family ||
- sk->sk_net != net) {
+ !net_eq(sock_net(sk), net)) {
continue;
}
rc = sk;
inet_twsk_for_each(tw, node,
&tcp_hashinfo.ehash[st->bucket].twchain) {
if (tw->tw_family != st->family ||
- tw->tw_net != net) {
+ !net_eq(twsk_net(tw), net)) {
continue;
}
rc = tw;
goto out;
}
- read_unlock_bh(lock);
+ spin_unlock_bh(lock);
st->state = TCP_SEQ_STATE_ESTABLISHED;
}
out:
{
struct sock *sk = cur;
struct inet_timewait_sock *tw;
- struct hlist_node *node;
- struct tcp_iter_state* st = seq->private;
- struct net *net = st->net;
+ struct hlist_nulls_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 || tw->tw_net != net)) {
+ 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_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+ spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
st->state = TCP_SEQ_STATE_ESTABLISHED;
- if (++st->bucket < tcp_hashinfo.ehash_size) {
- read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
- sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain);
- } else {
- cur = NULL;
- goto out;
- }
+ /* Look for next non empty bucket */
+ while (++st->bucket <= tcp_hashinfo.ehash_mask &&
+ empty_bucket(st))
+ ;
+ if (st->bucket > tcp_hashinfo.ehash_mask)
+ return NULL;
+
+ spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+ sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
} else
- sk = sk_next(sk);
+ sk = sk_nulls_next(sk);
- sk_for_each_from(sk, node) {
- if (sk->sk_family == st->family && sk->sk_net == net)
+ sk_nulls_for_each_from(sk, node) {
+ if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
goto found;
}
static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
{
void *rc;
- struct tcp_iter_state* st = seq->private;
+ struct tcp_iter_state *st = seq->private;
- inet_listen_lock(&tcp_hashinfo);
st->state = TCP_SEQ_STATE_LISTENING;
rc = listening_get_idx(seq, &pos);
if (!rc) {
- inet_listen_unlock(&tcp_hashinfo);
st->state = TCP_SEQ_STATE_ESTABLISHED;
rc = established_get_idx(seq, pos);
}
static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct tcp_iter_state* st = seq->private;
+ struct tcp_iter_state *st = seq->private;
st->state = TCP_SEQ_STATE_LISTENING;
st->num = 0;
return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
void *rc = NULL;
- struct tcp_iter_state* st;
+ struct tcp_iter_state *st;
if (v == SEQ_START_TOKEN) {
rc = tcp_get_idx(seq, 0);
case TCP_SEQ_STATE_LISTENING:
rc = listening_get_next(seq, v);
if (!rc) {
- inet_listen_unlock(&tcp_hashinfo);
st->state = TCP_SEQ_STATE_ESTABLISHED;
rc = established_get_first(seq);
}
static void tcp_seq_stop(struct seq_file *seq, void *v)
{
- struct tcp_iter_state* st = seq->private;
+ struct tcp_iter_state *st = seq->private;
switch (st->state) {
case TCP_SEQ_STATE_OPENREQ:
}
case TCP_SEQ_STATE_LISTENING:
if (v != SEQ_START_TOKEN)
- inet_listen_unlock(&tcp_hashinfo);
+ spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
break;
case TCP_SEQ_STATE_TIME_WAIT:
case TCP_SEQ_STATE_ESTABLISHED:
if (v)
- read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+ spin_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;
- struct net *net;
- int rc;
-
- if (unlikely(afinfo == NULL))
- return -EINVAL;
-
- s = kzalloc(sizeof(*s), GFP_KERNEL);
- if (!s)
- return -ENOMEM;
+ int err;
- rc = -ENXIO;
- net = get_proc_net(inode);
- if (!net)
- goto out_kfree;
+ err = seq_open_net(inode, file, &afinfo->seq_ops,
+ sizeof(struct tcp_iter_state));
+ if (err < 0)
+ return err;
+ 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;
- s->net = net;
-
- rc = seq_open(file, &s->seq_ops);
- if (rc)
- goto out_put_net;
- seq = file->private_data;
- seq->private = s;
-out:
- return rc;
-out_put_net:
- put_net(net);
-out_kfree:
- kfree(s);
- goto out;
-}
-
-static int tcp_seq_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq = file->private_data;
- struct tcp_iter_state *s = seq->private;
-
- put_net(s->net);
- seq_release_private(inode, file);
return 0;
}
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 = tcp_seq_release;
-
- p = proc_net_fops_create(net, 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 net *net, struct tcp_seq_afinfo *afinfo)
{
- if (!afinfo)
- return;
proc_net_remove(net, afinfo->name);
- memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}
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),
+ ntohs(inet_sk(sk)->inet_sport),
ireq->rmt_addr,
ntohs(ireq->rmt_port),
TCP_SYN_RECV,
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 *sk, 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(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);
+ __be32 dest = inet->inet_daddr;
+ __be32 src = inet->inet_rcv_saddr;
+ __u16 destp = ntohs(inet->inet_dport);
+ __u16 srcp = ntohs(inet->inet_sport);
+ int rx_queue;
if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
timer_active = 1;
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",
+ if (sk->sk_state == TCP_LISTEN)
+ rx_queue = sk->sk_ack_backlog;
+ else
+ /*
+ * because we dont lock socket, we might find a transient negative value
+ */
+ rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+
+ 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,
- sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog :
- (tp->rcv_nxt - tp->copied_seq),
+ rx_queue,
timer_active,
jiffies_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
icsk->icsk_probes_out,
sock_i_ino(sk),
atomic_read(&sk->sk_refcnt), sk,
- icsk->icsk_rto,
- icsk->icsk_ack.ato,
+ 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);
+ tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh,
+ len);
}
static void get_timewait4_sock(struct inet_timewait_sock *tw,
- char *tmpbuf, int i)
+ 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];
+ struct tcp_iter_state *st;
+ 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)
+static int __net_init tcp4_proc_init_net(struct net *net)
{
return tcp_proc_register(net, &tcp4_seq_afinfo);
}
-static void tcp4_proc_exit_net(struct net *net)
+static void __net_exit tcp4_proc_exit_net(struct net *net)
{
tcp_proc_unregister(net, &tcp4_seq_afinfo);
}
}
#endif /* CONFIG_PROC_FS */
-DEFINE_PROTO_INUSE(tcp)
+struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+ struct iphdr *iph = skb_gro_network_header(skb);
+
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
+ skb->csum)) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ break;
+ }
+
+ /* fall through */
+ case CHECKSUM_NONE:
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+ }
+
+ return tcp_gro_receive(head, skb);
+}
+EXPORT_SYMBOL(tcp4_gro_receive);
+
+int tcp4_gro_complete(struct sk_buff *skb)
+{
+ struct iphdr *iph = ip_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
+
+ th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
+ iph->saddr, iph->daddr, 0);
+ skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+ return tcp_gro_complete(skb);
+}
+EXPORT_SYMBOL(tcp4_gro_complete);
struct proto tcp_prot = {
.name = "TCP",
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
- REF_PROTO_INUSE(tcp)
+};
+
+
+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 void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
+{
+ inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET);
+}
+
+static struct pernet_operations __net_initdata tcp_sk_ops = {
+ .init = tcp_sk_init,
+ .exit = tcp_sk_exit,
+ .exit_batch = tcp_sk_exit_batch,
};
void __init tcp_v4_init(void)
{
- if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW,
- IPPROTO_TCP) < 0)
+ inet_hashinfo_init(&tcp_hashinfo);
+ if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff