summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig6
-rw-r--r--net/ipv4/devinet.c1
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/inet_diag.c2
-rw-r--r--net/ipv4/inet_hashtables.c24
-rw-r--r--net/ipv4/inet_timewait_sock.c61
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/syncookies.c27
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_input.c59
-rw-r--r--net/ipv4/tcp_ipv4.c23
-rw-r--r--net/ipv4/tcp_minisocks.c10
-rw-r--r--net/ipv4/tcp_output.c18
-rw-r--r--net/ipv4/tcp_probe.c19
-rw-r--r--net/ipv4/tcp_timer.c29
-rw-r--r--net/ipv4/udp.c7
-rw-r--r--net/ipv4/xfrm4_policy.c14
19 files changed, 194 insertions, 119 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 70491d9035eb..0c94a1ac2946 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,7 +166,7 @@ config IP_PNP_DHCP
If unsure, say Y. Note that if you want to use DHCP, a DHCP server
must be operating on your network. Read
- <file:Documentation/filesystems/nfsroot.txt> for details.
+ <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_BOOTP
bool "IP: BOOTP support"
@@ -181,7 +181,7 @@ config IP_PNP_BOOTP
does BOOTP itself, providing all necessary information on the kernel
command line, you can say N here. If unsure, say Y. Note that if you
want to use BOOTP, a BOOTP server must be operating on your network.
- Read <file:Documentation/filesystems/nfsroot.txt> for details.
+ Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_RARP
bool "IP: RARP support"
@@ -194,7 +194,7 @@ config IP_PNP_RARP
older protocol which is being obsoleted by BOOTP and DHCP), say Y
here. Note that if you want to use RARP, a RARP server must be
operating on your network. Read
- <file:Documentation/filesystems/nfsroot.txt> for details.
+ <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
# not yet ready..
# bool ' IP: ARP support' CONFIG_IP_PNP_ARP
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5cdbc102a418..040c4f05b653 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1397,6 +1397,7 @@ static struct devinet_sysctl_table {
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
"accept_source_route"),
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"),
+ DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"),
DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3323168ee52d..82dbf711d6d0 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -252,6 +252,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
no_addr = in_dev->ifa_list == NULL;
rpf = IN_DEV_RPFILTER(in_dev);
accept_local = IN_DEV_ACCEPT_LOCAL(in_dev);
+ if (mark && !IN_DEV_SRC_VMARK(in_dev))
+ fl.mark = 0;
}
rcu_read_unlock();
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index bdb78dd180ce..1aaa8110d84b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -368,7 +368,7 @@ static int inet_diag_bc_run(const void *bc, int len,
yes = entry->sport >= op[1].no;
break;
case INET_DIAG_BC_S_LE:
- yes = entry->dport <= op[1].no;
+ yes = entry->sport <= op[1].no;
break;
case INET_DIAG_BC_D_GE:
yes = entry->dport >= op[1].no;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 21e5e32d8c60..2b79377b468d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -351,12 +351,13 @@ static inline u32 inet_sk_port_offset(const struct sock *sk)
inet->inet_dport);
}
-void __inet_hash_nolisten(struct sock *sk)
+int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
spinlock_t *lock;
struct inet_ehash_bucket *head;
+ int twrefcnt = 0;
WARN_ON(!sk_unhashed(sk));
@@ -367,8 +368,13 @@ void __inet_hash_nolisten(struct sock *sk)
spin_lock(lock);
__sk_nulls_add_node_rcu(sk, list);
+ if (tw) {
+ WARN_ON(sk->sk_hash != tw->tw_hash);
+ twrefcnt = inet_twsk_unhash(tw);
+ }
spin_unlock(lock);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ return twrefcnt;
}
EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
@@ -378,7 +384,7 @@ static void __inet_hash(struct sock *sk)
struct inet_listen_hashbucket *ilb;
if (sk->sk_state != TCP_LISTEN) {
- __inet_hash_nolisten(sk);
+ __inet_hash_nolisten(sk, NULL);
return;
}
@@ -427,7 +433,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **),
- void (*hash)(struct sock *sk))
+ int (*hash)(struct sock *sk, struct inet_timewait_sock *twp))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
const unsigned short snum = inet_sk(sk)->inet_num;
@@ -435,6 +441,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct inet_bind_bucket *tb;
int ret;
struct net *net = sock_net(sk);
+ int twrefcnt = 1;
if (!snum) {
int i, remaining, low, high, port;
@@ -493,13 +500,18 @@ ok:
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- hash(sk);
+ twrefcnt += hash(sk, tw);
}
+ if (tw)
+ twrefcnt += inet_twsk_bind_unhash(tw, hinfo);
spin_unlock(&head->lock);
if (tw) {
inet_twsk_deschedule(tw, death_row);
- inet_twsk_put(tw);
+ while (twrefcnt) {
+ twrefcnt--;
+ inet_twsk_put(tw);
+ }
}
ret = 0;
@@ -510,7 +522,7 @@ ok:
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- hash(sk);
+ hash(sk, NULL);
spin_unlock_bh(&head->lock);
return 0;
} else {
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 0fdf45e4c90c..cc94cc2d8b2d 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -15,9 +15,13 @@
#include <net/ip.h>
-/*
- * unhash a timewait socket from established hash
- * lock must be hold by caller
+/**
+ * inet_twsk_unhash - unhash a timewait socket from established hash
+ * @tw: timewait socket
+ *
+ * unhash a timewait socket from established hash, if hashed.
+ * ehash lock must be held by caller.
+ * Returns 1 if caller should call inet_twsk_put() after lock release.
*/
int inet_twsk_unhash(struct inet_timewait_sock *tw)
{
@@ -26,6 +30,37 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw)
hlist_nulls_del_rcu(&tw->tw_node);
sk_nulls_node_init(&tw->tw_node);
+ /*
+ * We cannot call inet_twsk_put() ourself under lock,
+ * caller must call it for us.
+ */
+ return 1;
+}
+
+/**
+ * inet_twsk_bind_unhash - unhash a timewait socket from bind hash
+ * @tw: timewait socket
+ * @hashinfo: hashinfo pointer
+ *
+ * unhash a timewait socket from bind hash, if hashed.
+ * bind hash lock must be held by caller.
+ * Returns 1 if caller should call inet_twsk_put() after lock release.
+ */
+int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
+ struct inet_hashinfo *hashinfo)
+{
+ struct inet_bind_bucket *tb = tw->tw_tb;
+
+ if (!tb)
+ return 0;
+
+ __hlist_del(&tw->tw_bind_node);
+ tw->tw_tb = NULL;
+ inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+ /*
+ * We cannot call inet_twsk_put() ourself under lock,
+ * caller must call it for us.
+ */
return 1;
}
@@ -34,7 +69,6 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
struct inet_bind_hashbucket *bhead;
- struct inet_bind_bucket *tb;
int refcnt;
/* Unlink from established hashes. */
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
@@ -46,15 +80,11 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
+
spin_lock(&bhead->lock);
- tb = tw->tw_tb;
- if (tb) {
- __hlist_del(&tw->tw_bind_node);
- tw->tw_tb = NULL;
- inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
- refcnt++;
- }
+ refcnt += inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
+
#ifdef SOCK_REFCNT_DEBUG
if (atomic_read(&tw->tw_refcnt) != 1) {
printk(KERN_DEBUG "%s timewait_sock %p refcnt=%d\n",
@@ -126,7 +156,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
/*
* Notes :
- * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
+ * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
* - We add one reference for the bhash link
* - We add one reference for the ehash link
* - We want this refcnt update done before allowing other
@@ -136,7 +166,6 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_unlock(lock);
}
-
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state)
@@ -177,7 +206,6 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
return tw;
}
-
EXPORT_SYMBOL_GPL(inet_twsk_alloc);
/* Returns non-zero if quota exceeded. */
@@ -256,7 +284,6 @@ void inet_twdr_hangman(unsigned long data)
out:
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twdr_hangman);
void inet_twdr_twkill_work(struct work_struct *work)
@@ -287,7 +314,6 @@ void inet_twdr_twkill_work(struct work_struct *work)
spin_unlock_bh(&twdr->death_lock);
}
}
-
EXPORT_SYMBOL_GPL(inet_twdr_twkill_work);
/* These are always called from BH context. See callers in
@@ -307,7 +333,6 @@ void inet_twsk_deschedule(struct inet_timewait_sock *tw,
spin_unlock(&twdr->death_lock);
__inet_twsk_kill(tw, twdr->hashinfo);
}
-
EXPORT_SYMBOL(inet_twsk_deschedule);
void inet_twsk_schedule(struct inet_timewait_sock *tw,
@@ -388,7 +413,6 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw,
mod_timer(&twdr->tw_timer, jiffies + twdr->period);
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twsk_schedule);
void inet_twdr_twcal_tick(unsigned long data)
@@ -449,7 +473,6 @@ out:
#endif
spin_unlock(&twdr->death_lock);
}
-
EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
void inet_twsk_purge(struct inet_hashinfo *hashinfo,
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e34013a78ef4..3451799e3dbf 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -254,7 +254,7 @@ int ip_mc_output(struct sk_buff *skb)
*/
if (rt->rt_flags&RTCF_MULTICAST) {
- if ((!sk || inet_sk(sk)->mc_loop)
+ if (sk_mc_loop(sk)
#ifdef CONFIG_IP_MROUTE
/* Small optimization: do not loopback not local frames,
which returned after forwarding; they will be dropped
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4e08b7f2331c..10a6a604bf32 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config);
/*
* Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel
- * command line parameter. See Documentation/filesystems/nfsroot.txt.
+ * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt.
*/
static int __init ic_proto_name(char *name)
{
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e446496f564f..d62b05d33384 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -586,7 +586,9 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
+#ifdef CONFIG_NET_CLS_ROUTE
remove_proc_entry("rt_acct", net->proc_net);
+#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 26399ad2a289..66fd80ef2473 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -277,6 +277,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
if (!req)
@@ -292,6 +299,12 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
ireq->loc_addr = ip_hdr(skb)->daddr;
ireq->rmt_addr = ip_hdr(skb)->saddr;
ireq->ecn_ok = 0;
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -340,20 +353,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
}
}
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-
/* Try to redo what tcp_v4_send_synack did. */
req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c8666b70cde0..b0a26bb25e2e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2540,11 +2540,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
ctd.tcpct_cookie_desired = cvp->cookie_desired;
ctd.tcpct_s_data_desired = cvp->s_data_desired;
- /* Cookie(s) saved, return as nonce */
- if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) {
- /* impossible? */
- return -EINVAL;
- }
memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0],
cvp->cookie_pair_size);
ctd.tcpct_used = cvp->cookie_pair_size;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 57ae96a04220..28e029632493 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2717,6 +2717,35 @@ static void tcp_try_undo_dsack(struct sock *sk)
}
}
+/* We can clear retrans_stamp when there are no retransmissions in the
+ * window. It would seem that it is trivially available for us in
+ * tp->retrans_out, however, that kind of assumptions doesn't consider
+ * what will happen if errors occur when sending retransmission for the
+ * second time. ...It could the that such segment has only
+ * TCPCB_EVER_RETRANS set at the present time. It seems that checking
+ * the head skb is enough except for some reneging corner cases that
+ * are not worth the effort.
+ *
+ * Main reason for all this complexity is the fact that connection dying
+ * time now depends on the validity of the retrans_stamp, in particular,
+ * that successive retransmissions of a segment must not advance
+ * retrans_stamp under any conditions.
+ */
+static int tcp_any_retrans_done(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (tp->retrans_out)
+ return 1;
+
+ skb = tcp_write_queue_head(sk);
+ if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
+ return 1;
+
+ return 0;
+}
+
/* Undo during fast recovery after partial ACK. */
static int tcp_try_undo_partial(struct sock *sk, int acked)
@@ -2729,7 +2758,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked)
/* Plain luck! Hole if filled with delayed
* packet, rather than with a retransmit.
*/
- if (tp->retrans_out == 0)
+ if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
@@ -2788,7 +2817,7 @@ static void tcp_try_keep_open(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
int state = TCP_CA_Open;
- if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+ if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
state = TCP_CA_Disorder;
if (inet_csk(sk)->icsk_ca_state != state) {
@@ -2803,7 +2832,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
tcp_verify_left_out(tp);
- if (!tp->frto_counter && tp->retrans_out == 0)
+ if (!tp->frto_counter && !tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
if (flag & FLAG_ECE)
@@ -3698,7 +3727,7 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- u8 **hvpp, int estab, struct dst_entry *dst)
+ u8 **hvpp, int estab)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
@@ -3737,8 +3766,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
+ !estab && sysctl_tcp_window_scaling) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
@@ -3754,8 +3782,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && sysctl_tcp_timestamps &&
- !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
+ (!estab && sysctl_tcp_timestamps))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3763,8 +3790,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && sysctl_tcp_sack &&
- !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
+ !estab && sysctl_tcp_sack) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
}
@@ -3849,7 +3875,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
return 1;
}
@@ -4104,10 +4130,8 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
- !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4136,15 +4160,13 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
- !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -5399,11 +5421,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 29002ab26e0d..65b8ebfd078a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1262,20 +1262,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif
- 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);
-
- dst = inet_csk_route_req(sk, req);
- if(!dst)
- goto drop_and_free;
-
tcp_clear_options(&tmp_opt);
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, dst);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
@@ -1319,8 +1309,14 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
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_release;
+ goto drop_and_free;
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
@@ -1345,6 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
+ (dst = inet_csk_route_req(sk, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
@@ -1464,7 +1461,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
}
#endif
- __inet_hash_nolisten(newsk);
+ __inet_hash_nolisten(newsk, NULL);
__inet_inherit_port(sk, newsk);
return newsk;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 87accec8d097..f206ee5dda80 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -95,9 +95,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
int paws_reject = 0;
+ tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -526,9 +526,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
int paws_reject = 0;
- if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) {
- tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
+ tmp_opt.saw_tstamp = 0;
+ if (th->doff > (sizeof(struct tcphdr)>>2)) {
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 93316a96d820..383ce237640f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -553,7 +553,6 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
- struct dst_entry *dst = __sk_dst_get(sk);
unsigned remaining = MAX_TCP_OPTION_SPACE;
u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
tcp_cookie_size_check(cvp->cookie_desired) :
@@ -581,22 +580,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
- if (likely(sysctl_tcp_timestamps &&
- !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
- *md5 == NULL)) {
+ if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
+ if (likely(sysctl_tcp_window_scaling)) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sysctl_tcp_sack &&
- !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
+ if (likely(sysctl_tcp_sack)) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -2527,9 +2522,7 @@ static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr) +
- (sysctl_tcp_timestamps &&
- (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
- TCPOLEN_TSTAMP_ALIGNED : 0));
+ (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk) != NULL)
@@ -2555,8 +2548,7 @@ static void tcp_connect_init(struct sock *sk)
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- (sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
+ sysctl_tcp_window_scaling,
&rcv_wscale);
tp->rx_opt.rcv_wscale = rcv_wscale;
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index bb110c5ce1d2..9bc805df95d2 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -39,9 +39,9 @@ static int port __read_mostly = 0;
MODULE_PARM_DESC(port, "Port to match (0=all)");
module_param(port, int, 0);
-static int bufsize __read_mostly = 4096;
+static unsigned int bufsize __read_mostly = 4096;
MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)");
-module_param(bufsize, int, 0);
+module_param(bufsize, uint, 0);
static int full __read_mostly;
MODULE_PARM_DESC(full, "Full log (1=every ack packet received, 0=only cwnd changes)");
@@ -75,12 +75,12 @@ static struct {
static inline int tcp_probe_used(void)
{
- return (tcp_probe.head - tcp_probe.tail) % bufsize;
+ return (tcp_probe.head - tcp_probe.tail) & (bufsize - 1);
}
static inline int tcp_probe_avail(void)
{
- return bufsize - tcp_probe_used();
+ return bufsize - tcp_probe_used() - 1;
}
/*
@@ -116,7 +116,7 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
p->ssthresh = tcp_current_ssthresh(sk);
p->srtt = tp->srtt >> 3;
- tcp_probe.head = (tcp_probe.head + 1) % bufsize;
+ tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
tcp_probe.lastcwnd = tp->snd_cwnd;
spin_unlock(&tcp_probe.lock);
@@ -149,7 +149,7 @@ static int tcpprobe_open(struct inode * inode, struct file * file)
static int tcpprobe_sprint(char *tbuf, int n)
{
const struct tcp_log *p
- = tcp_probe.log + tcp_probe.tail % bufsize;
+ = tcp_probe.log + tcp_probe.tail;
struct timespec tv
= ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start));
@@ -192,7 +192,7 @@ static ssize_t tcpprobe_read(struct file *file, char __user *buf,
width = tcpprobe_sprint(tbuf, sizeof(tbuf));
if (cnt + width < len)
- tcp_probe.tail = (tcp_probe.tail + 1) % bufsize;
+ tcp_probe.tail = (tcp_probe.tail + 1) & (bufsize - 1);
spin_unlock_bh(&tcp_probe.lock);
@@ -222,9 +222,10 @@ static __init int tcpprobe_init(void)
init_waitqueue_head(&tcp_probe.wait);
spin_lock_init(&tcp_probe.lock);
- if (bufsize < 0)
+ if (bufsize == 0)
return -EINVAL;
+ bufsize = roundup_pow_of_two(bufsize);
tcp_probe.log = kcalloc(bufsize, sizeof(struct tcp_log), GFP_KERNEL);
if (!tcp_probe.log)
goto err0;
@@ -236,7 +237,7 @@ static __init int tcpprobe_init(void)
if (ret)
goto err1;
- pr_info("TCP probe registered (port=%d)\n", port);
+ pr_info("TCP probe registered (port=%d) bufsize=%u\n", port, bufsize);
return 0;
err1:
proc_net_remove(&init_net, procname);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8353a538cd4c..8816a20c2597 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -132,6 +132,35 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
}
}
+/* This function calculates a "timeout" which is equivalent to the timeout of a
+ * TCP connection after "boundary" unsucessful, exponentially backed-off
+ * retransmissions with an initial RTO of TCP_RTO_MIN.
+ */
+static bool retransmits_timed_out(struct sock *sk,
+ unsigned int boundary)
+{
+ unsigned int timeout, linear_backoff_thresh;
+ unsigned int start_ts;
+
+ if (!inet_csk(sk)->icsk_retransmits)
+ return false;
+
+ if (unlikely(!tcp_sk(sk)->retrans_stamp))
+ start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
+ else
+ start_ts = tcp_sk(sk)->retrans_stamp;
+
+ linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+
+ if (boundary <= linear_backoff_thresh)
+ timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+ else
+ timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+ (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+
+ return (tcp_time_stamp - start_ts) >= timeout;
+}
+
/* A write timeout has occurred. Process the after effects. */
static int tcp_write_timeout(struct sock *sk)
{
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1f9534846ca9..f0126fdd7e04 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -216,9 +216,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
rand = (rand | 1) * (udptable->mask + 1);
- for (last = first + udptable->mask + 1;
- first != last;
- first++) {
+ last = first + udptable->mask + 1;
+ do {
hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
@@ -238,7 +237,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
snum += rand;
} while (snum != first);
spin_unlock_bh(&hslot->lock);
- }
+ } while (++first != last);
goto fail;
} else {
hslot = udp_hashslot(udptable, net, snum);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 8c08a28d8f83..67107d63c1cd 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -15,7 +15,6 @@
#include <net/xfrm.h>
#include <net/ip.h>
-static struct dst_ops xfrm4_dst_ops;
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
@@ -190,8 +189,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
- xfrm4_policy_afinfo.garbage_collect(&init_net);
- return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
+ struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
+
+ xfrm4_policy_afinfo.garbage_collect(net);
+ return (atomic_read(&ops->entries) > ops->gc_thresh * 2);
}
static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -268,7 +269,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
static struct ctl_table xfrm4_policy_table[] = {
{
.procname = "xfrm4_gc_thresh",
- .data = &xfrm4_dst_ops.gc_thresh,
+ .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
@@ -295,8 +296,6 @@ static void __exit xfrm4_policy_fini(void)
void __init xfrm4_init(int rt_max_size)
{
- xfrm4_state_init();
- xfrm4_policy_init();
/*
* Select a default value for the gc_thresh based on the main route
* table hash size. It seems to me the worst case scenario is when
@@ -308,6 +307,9 @@ void __init xfrm4_init(int rt_max_size)
* and start cleaning when were 1/2 full
*/
xfrm4_dst_ops.gc_thresh = rt_max_size/2;
+
+ xfrm4_state_init();
+ xfrm4_policy_init();
#ifdef CONFIG_SYSCTL
sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path,
xfrm4_policy_table);
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-27 23:25:31 +0000