summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c22
-rw-r--r--net/ipv4/fib_rules.c4
-rw-r--r--net/ipv4/fib_trie.c4
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c16
-rw-r--r--net/ipv4/ipmr.c110
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c137
-rw-r--r--net/ipv4/tcp.c19
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_output.c9
-rw-r--r--net/ipv4/tcp_timer.c4
-rw-r--r--net/ipv4/udp.c30
15 files changed, 192 insertions, 178 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c5376c725503..c6c43bcd1c6f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -419,7 +419,7 @@ int inet_release(struct socket *sock)
if (sk) {
long timeout;
- inet_rps_reset_flow(sk);
+ sock_rps_reset_flow(sk);
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
@@ -548,7 +548,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -561,9 +561,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeo;
}
@@ -722,7 +722,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
{
struct sock *sk = sock->sk;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
@@ -737,7 +737,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
{
struct sock *sk = sock->sk;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
@@ -755,7 +755,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
int addr_len = 0;
int err;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
@@ -1323,8 +1323,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto out_unlock;
- id = ntohl(*(u32 *)&iph->id);
- flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ id = ntohl(*(__be32 *)&iph->id);
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
@@ -1337,8 +1337,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if ((iph->protocol ^ iph2->protocol) |
(iph->tos ^ iph2->tos) |
- (iph->saddr ^ iph2->saddr) |
- (iph->daddr ^ iph2->daddr)) {
+ ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+ ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 3ec84fea5b71..76daeb5ff564 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -245,8 +245,8 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
rt_cache_flush(ops->fro_net, -1);
}
-static struct fib_rules_ops fib4_rules_ops_template = {
- .family = FIB_RULES_IPV4,
+static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
+ .family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
.action = fib4_rule_action,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 59a838795e3e..c98f115fb0fd 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -209,7 +209,9 @@ static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i)
{
struct node *ret = tnode_get_child(tn, i);
- return rcu_dereference(ret);
+ return rcu_dereference_check(ret,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
}
static inline int tnode_child_length(const struct tnode *tn)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8da6429269dd..e0a3e3537b14 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -234,7 +234,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
* having to remove and re-insert us on the wait queue.
*/
for (;;) {
- prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
if (reqsk_queue_empty(&icsk->icsk_accept_queue))
@@ -253,7 +253,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
if (!timeo)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d979710684b2..252897443ef9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -120,7 +120,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb)
newskb->pkt_type = PACKET_LOOPBACK;
newskb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(newskb));
- netif_rx(newskb);
+ netif_rx_ni(newskb);
return 0;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b0aa0546a3b3..ce231780a2b1 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -954,6 +954,22 @@ e_inval:
return -EINVAL;
}
+/**
+ * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * @sk: socket
+ * @skb: buffer
+ *
+ * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
+ * is not set, we drop skb dst entry now, while dst cache line is hot.
+ */
+int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
+ skb_dst_drop(skb);
+ return sock_queue_rcv_skb(sk, skb);
+}
+EXPORT_SYMBOL(ip_queue_rcv_skb);
+
int ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1aa498d7a0a5..f3f1c6b5c70c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -128,8 +128,8 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
int local);
static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- struct mfc_cache *c, struct rtmsg *rtm);
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -216,8 +216,8 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
return 0;
}
-static struct fib_rules_ops ipmr_rules_ops_template = {
- .family = FIB_RULES_IPMR,
+static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+ .family = RTNL_FAMILY_IPMR,
.rule_size = sizeof(struct ipmr_rule),
.addr_size = sizeof(u32),
.action = ipmr_rule_action,
@@ -831,7 +831,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
- if (ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
nlh->nlmsg_len = (skb_tail_pointer(skb) -
(u8 *)nlh);
} else {
@@ -1772,10 +1772,10 @@ int ip_mr_input(struct sk_buff *skb)
vif = ipmr_find_vif(mrt, skb->dev);
if (vif >= 0) {
- int err = ipmr_cache_unresolved(mrt, vif, skb);
+ int err2 = ipmr_cache_unresolved(mrt, vif, skb);
read_unlock(&mrt_lock);
- return err;
+ return err2;
}
read_unlock(&mrt_lock);
kfree_skb(skb);
@@ -1904,9 +1904,8 @@ drop:
}
#endif
-static int
-ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c,
- struct rtmsg *rtm)
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm)
{
int ct;
struct rtnexthop *nhp;
@@ -1994,11 +1993,93 @@ int ipmr_get_route(struct net *net,
if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
cache->mfc_flags |= MFC_NOTIFY;
- err = ipmr_fill_mroute(mrt, skb, cache, rtm);
+ err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
read_unlock(&mrt_lock);
return err;
}
+static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ u32 pid, u32 seq, struct mfc_cache *c)
+{
+ struct nlmsghdr *nlh;
+ struct rtmsg *rtm;
+
+ nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ rtm = nlmsg_data(nlh);
+ rtm->rtm_family = RTNL_FAMILY_IPMR;
+ rtm->rtm_dst_len = 32;
+ rtm->rtm_src_len = 32;
+ rtm->rtm_tos = 0;
+ rtm->rtm_table = mrt->id;
+ NLA_PUT_U32(skb, RTA_TABLE, mrt->id);
+ rtm->rtm_type = RTN_MULTICAST;
+ rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+ rtm->rtm_protocol = RTPROT_UNSPEC;
+ rtm->rtm_flags = 0;
+
+ NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin);
+ NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp);
+
+ if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct mr_table *mrt;
+ struct mfc_cache *mfc;
+ unsigned int t = 0, s_t;
+ unsigned int h = 0, s_h;
+ unsigned int e = 0, s_e;
+
+ s_t = cb->args[0];
+ s_h = cb->args[1];
+ s_e = cb->args[2];
+
+ read_lock(&mrt_lock);
+ ipmr_for_each_table(mrt, net) {
+ if (t < s_t)
+ goto next_table;
+ if (t > s_t)
+ s_h = 0;
+ for (h = s_h; h < MFC_LINES; h++) {
+ list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) {
+ if (e < s_e)
+ goto next_entry;
+ if (ipmr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0)
+ goto done;
+next_entry:
+ e++;
+ }
+ e = s_e = 0;
+ }
+ s_h = 0;
+next_table:
+ t++;
+ }
+done:
+ read_unlock(&mrt_lock);
+
+ cb->args[2] = e;
+ cb->args[1] = h;
+ cb->args[0] = t;
+
+ return skb->len;
+}
+
#ifdef CONFIG_PROC_FS
/*
* The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
@@ -2227,9 +2308,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
const struct ipmr_mfc_iter *it = seq->private;
const struct mr_table *mrt = it->mrt;
- seq_printf(seq, "%08lX %08lX %-3hd",
- (unsigned long) mfc->mfc_mcastgrp,
- (unsigned long) mfc->mfc_origin,
+ seq_printf(seq, "%08X %08X %-3hd",
+ (__force u32) mfc->mfc_mcastgrp,
+ (__force u32) mfc->mfc_origin,
mfc->mfc_parent);
if (it->cache != &mrt->mfc_unres_queue) {
@@ -2355,6 +2436,7 @@ int __init ip_mr_init(void)
goto add_proto_fail;
}
#endif
+ rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute);
return 0;
#ifdef CONFIG_IP_PIMSM_V2
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bbda0d5f9244..2c7a1639388a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -290,7 +290,7 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk, skb) < 0) {
+ if (ip_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cb562fdd9b9a..dea3f9264250 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ;
static int rt_chain_length_max __read_mostly = 20;
static struct delayed_work expires_work;
@@ -258,10 +257,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
(__raw_get_cpu_var(rt_cache_stat).field++)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
+ int genid)
{
- return jhash_3words((__force u32)(__be32)(daddr),
- (__force u32)(__be32)(saddr),
+ return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
@@ -378,12 +376,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
struct rtable *r = v;
int len;
- seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
- "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
+ seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
+ "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
r->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
+ r->u.dst.__use, 0, (__force u32)r->rt_src,
(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
(int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
dst_metric(&r->u.dst, RTAX_WINDOW),
@@ -685,18 +684,17 @@ static inline bool rt_caching(const struct net *net)
static inline bool compare_hash_inputs(const struct flowi *fl1,
const struct flowi *fl2)
{
- return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+ return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->iif ^ fl2->iif)) == 0);
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
+ return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
@@ -919,32 +917,11 @@ void rt_cache_flush_batch(void)
rt_do_flush(!in_softirq());
}
-/*
- * We change rt_genid and let gc do the cleanup
- */
-static void rt_secret_rebuild(unsigned long __net)
-{
- struct net *net = (struct net *)__net;
- rt_cache_invalidate(net);
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
-static void rt_secret_rebuild_oneshot(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
- rt_cache_invalidate(net);
- if (ip_rt_secret_interval)
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
static void rt_emergency_hash_rebuild(struct net *net)
{
- if (net_ratelimit()) {
+ if (net_ratelimit())
printk(KERN_WARNING "Route hash chain too long!\n");
- printk(KERN_WARNING "Adjust your secret_interval!\n");
- }
-
- rt_secret_rebuild_oneshot(net);
+ rt_cache_invalidate(net);
}
/*
@@ -2319,8 +2296,8 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->u.dst.rt_next)) {
- if (((rth->fl.fl4_dst ^ daddr) |
- (rth->fl.fl4_src ^ saddr) |
+ if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
+ ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
(rth->fl.iif ^ iif) |
rth->fl.oif |
(rth->fl.fl4_tos ^ tos)) == 0 &&
@@ -3102,48 +3079,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
return -EINVAL;
}
-static void rt_secret_reschedule(int old)
-{
- struct net *net;
- int new = ip_rt_secret_interval;
- int diff = new - old;
-
- if (!diff)
- return;
-
- rtnl_lock();
- for_each_net(net) {
- int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
- long time;
-
- if (!new)
- continue;
-
- if (deleted) {
- time = net->ipv4.rt_secret_timer.expires - jiffies;
-
- if (time <= 0 || (time += diff) <= 0)
- time = 0;
- } else
- time = new;
-
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
- }
- rtnl_unlock();
-}
-
-static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int old = ip_rt_secret_interval;
- int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
-
- rt_secret_reschedule(old);
-
- return ret;
-}
-
static ctl_table ipv4_route_table[] = {
{
.procname = "gc_thresh",
@@ -3252,13 +3187,6 @@ static ctl_table ipv4_route_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "secret_interval",
- .data = &ip_rt_secret_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = ipv4_sysctl_rt_secret_interval,
- },
{ }
};
@@ -3337,34 +3265,15 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
};
#endif
-
-static __net_init int rt_secret_timer_init(struct net *net)
+static __net_init int rt_genid_init(struct net *net)
{
- atomic_set(&net->ipv4.rt_genid,
- (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7))));
-
- net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
- net->ipv4.rt_secret_timer.data = (unsigned long)net;
- init_timer_deferrable(&net->ipv4.rt_secret_timer);
-
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires =
- jiffies + net_random() % ip_rt_secret_interval +
- ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ get_random_bytes(&net->ipv4.rt_genid,
+ sizeof(net->ipv4.rt_genid));
return 0;
}
-static __net_exit void rt_secret_timer_exit(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
-}
-
-static __net_initdata struct pernet_operations rt_secret_timer_ops = {
- .init = rt_secret_timer_init,
- .exit = rt_secret_timer_exit,
+static __net_initdata struct pernet_operations rt_genid_ops = {
+ .init = rt_genid_init,
};
@@ -3425,9 +3334,6 @@ int __init ip_rt_init(void)
schedule_delayed_work(&expires_work,
net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
- if (register_pernet_subsys(&rt_secret_timer_ops))
- printk(KERN_ERR "Unable to setup rt_secret_timer\n");
-
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
@@ -3439,6 +3345,7 @@ int __init ip_rt_init(void)
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&rt_genid_ops);
return rc;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0f8caf64caa3..8ce29747ad9b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -378,7 +378,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sock *sk = sock->sk;
struct tcp_sock *tp = tcp_sk(sk);
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -2298,7 +2298,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (sock_flag(sk, SOCK_KEEPOPEN) &&
!((1 << sk->sk_state) &
(TCPF_CLOSE | TCPF_LISTEN))) {
- __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ u32 elapsed = keepalive_time_elapsed(tp);
if (tp->keepalive_time > elapsed)
elapsed = tp->keepalive_time - elapsed;
else
@@ -2721,7 +2721,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct tcphdr *th2;
unsigned int len;
unsigned int thlen;
- unsigned int flags;
+ __be32 flags;
unsigned int mss = 1;
unsigned int hlen;
unsigned int off;
@@ -2771,10 +2771,10 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
found:
flush = NAPI_GRO_CB(p)->flush;
- flush |= flags & TCP_FLAG_CWR;
- flush |= (flags ^ tcp_flag_word(th2)) &
- ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
- flush |= th->ack_seq ^ th2->ack_seq;
+ flush |= (__force int)(flags & TCP_FLAG_CWR);
+ flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
+ ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
+ flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
for (i = sizeof(*th); i < thlen; i += 4)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
@@ -2795,8 +2795,9 @@ found:
out_check_final:
flush = len < mss;
- flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
- TCP_FLAG_SYN | TCP_FLAG_FIN);
+ flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
+ TCP_FLAG_RST | TCP_FLAG_SYN |
+ TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
pp = head;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ae3ec15fb630..e82162c211bf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4367,6 +4367,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
goto drop;
+ skb_dst_drop(skb);
__skb_pull(skb, th->doff * 4);
TCP_ECN_accept_cwr(tp, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ad08392a738c..771f8146a2e5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1286,8 +1286,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_release;
/* Secret recipe starts with IP addresses */
- *mess++ ^= daddr;
- *mess++ ^= saddr;
+ *mess++ ^= (__force u32)daddr;
+ *mess++ ^= (__force u32)saddr;
/* plus variable length Initiator Cookie */
c = (u8 *)mess;
@@ -1672,7 +1672,7 @@ process:
skb->dev = NULL;
- inet_rps_save_rxhash(sk, skb->rxhash);
+ sock_rps_save_rxhash(sk, skb->rxhash);
bh_lock_sock_nested(sk);
ret = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2b7d71fb8439..5db3a2c6cb33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -861,7 +861,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
- th->urg_ptr = 0xFFFF;
+ th->urg_ptr = htons(0xFFFF);
th->urg = 1;
}
}
@@ -888,7 +888,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
+ tcp_skb_pcount(skb));
err = icsk->icsk_af_ops->queue_xmit(skb);
if (likely(err <= 0))
@@ -2485,7 +2486,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
*tail-- ^= TCP_SKB_CB(skb)->seq + 1;
/* recommended */
- *tail-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
sha_transform((__u32 *)&xvp->cookie_bakery[0],
@@ -2503,7 +2504,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
th->window = htons(min(req->rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c732be00606b..440a5c6004f6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -517,7 +517,7 @@ static void tcp_keepalive_timer (unsigned long data)
struct sock *sk = (struct sock *) data;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- __u32 elapsed;
+ u32 elapsed;
/* Only process if socket is not in use. */
bh_lock_sock(sk);
@@ -554,7 +554,7 @@ static void tcp_keepalive_timer (unsigned long data)
if (tp->packets_out || tcp_send_head(sk))
goto resched;
- elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ elapsed = keepalive_time_elapsed(tp);
if (elapsed >= keepalive_time_when(tp)) {
if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 666b963496ff..4560b291180b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -307,13 +307,13 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr,
unsigned int port)
{
- return jhash_1word(saddr, net_hash_mix(net)) ^ port;
+ return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
- udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum);
+ udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
@@ -466,14 +466,14 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
daddr, hnum, dif,
hslot2, slot2);
if (!result) {
- hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum);
+ hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp4_lib_lookup2(net, saddr, sport,
- INADDR_ANY, hnum, dif,
+ htonl(INADDR_ANY), hnum, dif,
hslot2, slot2);
}
rcu_read_unlock();
@@ -1062,10 +1062,10 @@ static unsigned int first_packet_length(struct sock *sk)
spin_unlock_bh(&rcvq->lock);
if (!skb_queue_empty(&list_kill)) {
- lock_sock(sk);
+ lock_sock_bh(sk);
__skb_queue_purge(&list_kill);
sk_mem_reclaim_partial(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
return res;
}
@@ -1196,10 +1196,10 @@ out:
return err;
csum_copy_err:
- lock_sock(sk);
+ lock_sock_bh(sk);
if (!skb_kill_datagram(sk, skb, flags))
UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- release_sock(sk);
+ unlock_sock_bh(sk);
if (noblock)
return -EAGAIN;
@@ -1217,7 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags)
sk->sk_state = TCP_CLOSE;
inet->inet_daddr = 0;
inet->inet_dport = 0;
- inet_rps_save_rxhash(sk, 0);
+ sock_rps_save_rxhash(sk, 0);
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
@@ -1262,9 +1262,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
int rc;
if (inet_sk(sk)->inet_daddr)
- inet_rps_save_rxhash(sk, skb->rxhash);
+ sock_rps_save_rxhash(sk, skb->rxhash);
- rc = sock_queue_rcv_skb(sk, skb);
+ rc = ip_queue_rcv_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -1372,6 +1372,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto drop;
}
+
+ if (sk_rcvqueues_full(sk, skb))
+ goto drop;
+
rc = 0;
bh_lock_sock(sk);
@@ -1620,9 +1624,9 @@ int udp_rcv(struct sk_buff *skb)
void udp_destroy_sock(struct sock *sk)
{
- lock_sock(sk);
+ lock_sock_bh(sk);
udp_flush_pending_frames(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
/*