summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c25
-rw-r--r--net/ipv4/devinet.c215
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/inet_connection_sock.c45
-rw-r--r--net/ipv4/inet_fragment.c39
-rw-r--r--net/ipv4/inet_hashtables.c28
-rw-r--r--net/ipv4/ip_fragment.c50
-rw-r--r--net/ipv4/ip_gre.c8
-rw-r--r--net/ipv4/ip_input.c7
-rw-r--r--net/ipv4/ipcomp.c1
-rw-r--r--net/ipv4/ipip.c4
-rw-r--r--net/ipv4/ipmr.c120
-rw-r--r--net/ipv4/netfilter/arp_tables.c10
-rw-r--r--net/ipv4/netfilter/ip_tables.c10
-rw-r--r--net/ipv4/netfilter/ipt_ULOG.c12
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c82
-rw-r--r--net/ipv4/protocol.c6
-rw-r--r--net/ipv4/syncookies.c7
-rw-r--r--net/ipv4/sysctl_net_ipv4.c38
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_cong.c30
-rw-r--r--net/ipv4/tcp_input.c21
-rw-r--r--net/ipv4/tcp_ipv4.c7
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/udp.c63
26 files changed, 589 insertions, 254 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 24b384b7903e..1aec92bf8018 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,21 +263,6 @@ void build_ehash_secret(void)
}
EXPORT_SYMBOL(build_ehash_secret);
-static inline int inet_netns_ok(struct net *net, __u8 protocol)
-{
- const struct net_protocol *ipprot;
-
- if (net_eq(net, &init_net))
- return 1;
-
- ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot == NULL) {
- /* raw IP is OK */
- return 1;
- }
- return ipprot->netns_ok;
-}
-
/*
* Create an inet socket.
*/
@@ -350,10 +335,6 @@ lookup_protocol:
!ns_capable(net->user_ns, CAP_NET_RAW))
goto out_rcu_unlock;
- err = -EAFNOSUPPORT;
- if (!inet_netns_ok(net, protocol))
- goto out_rcu_unlock;
-
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
@@ -1306,6 +1287,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
+ SKB_GSO_SHARED_FRAG |
0)))
goto out;
@@ -1333,7 +1315,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
segs = ops->callbacks.gso_segment(skb, features);
rcu_read_unlock();
- if (!segs || IS_ERR(segs))
+ if (IS_ERR_OR_NULL(segs))
goto out;
skb = segs;
@@ -1705,12 +1687,11 @@ static struct packet_type ip_packet_type __read_mostly = {
static int __init inet_init(void)
{
- struct sk_buff *dummy_skb;
struct inet_protosw *q;
struct list_head *r;
int rc = -EINVAL;
- BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
+ BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
if (!sysctl_local_reserved_ports)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a8e4f2665d5e..5281314886c1 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -63,6 +63,7 @@
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
+#include <net/addrconf.h>
#include "fib_lookup.h"
@@ -93,6 +94,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_ADDRESS] = { .type = NLA_U32 },
[IFA_BROADCAST] = { .type = NLA_U32 },
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
+ [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
};
#define IN4_ADDR_HSIZE_SHIFT 8
@@ -417,6 +419,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
+static void check_lifetime(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
+
static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
u32 portid)
{
@@ -462,6 +468,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
inet_hash_insert(dev_net(in_dev->dev), ifa);
+ cancel_delayed_work(&check_lifetime_work);
+ schedule_delayed_work(&check_lifetime_work, 0);
+
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
@@ -573,7 +582,107 @@ errout:
return err;
}
-static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
+#define INFINITY_LIFE_TIME 0xFFFFFFFF
+
+static void check_lifetime(struct work_struct *work)
+{
+ unsigned long now, next, next_sec, next_sched;
+ struct in_ifaddr *ifa;
+ struct hlist_node *node;
+ int i;
+
+ now = jiffies;
+ next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
+
+ rcu_read_lock();
+ for (i = 0; i < IN4_ADDR_HSIZE; i++) {
+ hlist_for_each_entry_rcu(ifa, node,
+ &inet_addr_lst[i], hash) {
+ unsigned long age;
+
+ if (ifa->ifa_flags & IFA_F_PERMANENT)
+ continue;
+
+ /* We try to batch several events at once. */
+ age = (now - ifa->ifa_tstamp +
+ ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+
+ if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
+ age >= ifa->ifa_valid_lft) {
+ struct in_ifaddr **ifap ;
+
+ rtnl_lock();
+ for (ifap = &ifa->ifa_dev->ifa_list;
+ *ifap != NULL; ifap = &ifa->ifa_next) {
+ if (*ifap == ifa)
+ inet_del_ifa(ifa->ifa_dev,
+ ifap, 1);
+ }
+ rtnl_unlock();
+ } else if (ifa->ifa_preferred_lft ==
+ INFINITY_LIFE_TIME) {
+ continue;
+ } else if (age >= ifa->ifa_preferred_lft) {
+ if (time_before(ifa->ifa_tstamp +
+ ifa->ifa_valid_lft * HZ, next))
+ next = ifa->ifa_tstamp +
+ ifa->ifa_valid_lft * HZ;
+
+ if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) {
+ ifa->ifa_flags |= IFA_F_DEPRECATED;
+ rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
+ }
+ } else if (time_before(ifa->ifa_tstamp +
+ ifa->ifa_preferred_lft * HZ,
+ next)) {
+ next = ifa->ifa_tstamp +
+ ifa->ifa_preferred_lft * HZ;
+ }
+ }
+ }
+ rcu_read_unlock();
+
+ next_sec = round_jiffies_up(next);
+ next_sched = next;
+
+ /* If rounded timeout is accurate enough, accept it. */
+ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ))
+ next_sched = next_sec;
+
+ now = jiffies;
+ /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */
+ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX))
+ next_sched = now + ADDRCONF_TIMER_FUZZ_MAX;
+
+ schedule_delayed_work(&check_lifetime_work, next_sched - now);
+}
+
+static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
+ __u32 prefered_lft)
+{
+ unsigned long timeout;
+
+ ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED);
+
+ timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ if (addrconf_finite_timeout(timeout))
+ ifa->ifa_valid_lft = timeout;
+ else
+ ifa->ifa_flags |= IFA_F_PERMANENT;
+
+ timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ if (addrconf_finite_timeout(timeout)) {
+ if (timeout == 0)
+ ifa->ifa_flags |= IFA_F_DEPRECATED;
+ ifa->ifa_preferred_lft = timeout;
+ }
+ ifa->ifa_tstamp = jiffies;
+ if (!ifa->ifa_cstamp)
+ ifa->ifa_cstamp = ifa->ifa_tstamp;
+}
+
+static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
+ __u32 *pvalid_lft, __u32 *pprefered_lft)
{
struct nlattr *tb[IFA_MAX+1];
struct in_ifaddr *ifa;
@@ -633,24 +742,73 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ if (tb[IFA_CACHEINFO]) {
+ struct ifa_cacheinfo *ci;
+
+ ci = nla_data(tb[IFA_CACHEINFO]);
+ if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
+ err = -EINVAL;
+ goto errout;
+ }
+ *pvalid_lft = ci->ifa_valid;
+ *pprefered_lft = ci->ifa_prefered;
+ }
+
return ifa;
errout:
return ERR_PTR(err);
}
+static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
+{
+ struct in_device *in_dev = ifa->ifa_dev;
+ struct in_ifaddr *ifa1, **ifap;
+
+ if (!ifa->ifa_local)
+ return NULL;
+
+ for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
+ ifap = &ifa1->ifa_next) {
+ if (ifa1->ifa_mask == ifa->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, ifa) &&
+ ifa1->ifa_local == ifa->ifa_local)
+ return ifa1;
+ }
+ return NULL;
+}
+
static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr *ifa;
+ struct in_ifaddr *ifa_existing;
+ __u32 valid_lft = INFINITY_LIFE_TIME;
+ __u32 prefered_lft = INFINITY_LIFE_TIME;
ASSERT_RTNL();
- ifa = rtm_to_ifaddr(net, nlh);
+ ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
- return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+ ifa_existing = find_matching_ifa(ifa);
+ if (!ifa_existing) {
+ /* It would be best to check for !NLM_F_CREATE here but
+ * userspace alreay relies on not having to provide this.
+ */
+ set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+ return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
+ } else {
+ inet_free_ifa(ifa);
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL ||
+ !(nlh->nlmsg_flags & NLM_F_REPLACE))
+ return -EEXIST;
+
+ set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft);
+ }
+ return 0;
}
/*
@@ -852,6 +1010,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
ifa->ifa_prefixlen = 32;
ifa->ifa_mask = inet_make_mask(32);
}
+ set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
ret = inet_set_ifa(dev, ifa);
break;
@@ -1190,6 +1349,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
ifa->ifa_dev = in_dev;
ifa->ifa_scope = RT_SCOPE_HOST;
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ set_ifa_lifetime(ifa, INFINITY_LIFE_TIME,
+ INFINITY_LIFE_TIME);
inet_insert_ifa(ifa);
}
}
@@ -1246,11 +1407,30 @@ static size_t inet_nlmsg_size(void)
+ nla_total_size(IFNAMSIZ); /* IFA_LABEL */
}
+static inline u32 cstamp_delta(unsigned long cstamp)
+{
+ return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
+}
+
+static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp,
+ unsigned long tstamp, u32 preferred, u32 valid)
+{
+ struct ifa_cacheinfo ci;
+
+ ci.cstamp = cstamp_delta(cstamp);
+ ci.tstamp = cstamp_delta(tstamp);
+ ci.ifa_prefered = preferred;
+ ci.ifa_valid = valid;
+
+ return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci);
+}
+
static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
u32 portid, u32 seq, int event, unsigned int flags)
{
struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
+ u32 preferred, valid;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
if (nlh == NULL)
@@ -1259,10 +1439,31 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
ifm = nlmsg_data(nlh);
ifm->ifa_family = AF_INET;
ifm->ifa_prefixlen = ifa->ifa_prefixlen;
- ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT;
+ ifm->ifa_flags = ifa->ifa_flags;
ifm->ifa_scope = ifa->ifa_scope;
ifm->ifa_index = ifa->ifa_dev->dev->ifindex;
+ if (!(ifm->ifa_flags & IFA_F_PERMANENT)) {
+ preferred = ifa->ifa_preferred_lft;
+ valid = ifa->ifa_valid_lft;
+ if (preferred != INFINITY_LIFE_TIME) {
+ long tval = (jiffies - ifa->ifa_tstamp) / HZ;
+
+ if (preferred > tval)
+ preferred -= tval;
+ else
+ preferred = 0;
+ if (valid != INFINITY_LIFE_TIME) {
+ if (valid > tval)
+ valid -= tval;
+ else
+ valid = 0;
+ }
+ }
+ } else {
+ preferred = INFINITY_LIFE_TIME;
+ valid = INFINITY_LIFE_TIME;
+ }
if ((ifa->ifa_address &&
nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) ||
(ifa->ifa_local &&
@@ -1270,7 +1471,9 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
(ifa->ifa_broadcast &&
nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) ||
(ifa->ifa_label[0] &&
- nla_put_string(skb, IFA_LABEL, ifa->ifa_label)))
+ nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
+ put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp,
+ preferred, valid))
goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -1988,6 +2191,8 @@ void __init devinet_init(void)
register_gifconf(PF_INET, inet_gifconf);
register_netdevice_notifier(&ip_netdev_notifier);
+ schedule_delayed_work(&check_lifetime_work, 0);
+
rtnl_af_register(&inet_af_ops);
rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 5cd75e2dab2c..99f00d39d10b 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -974,7 +974,7 @@ static void nl_fib_input(struct sk_buff *skb)
nl_fib_lookup(frn, tb);
- portid = NETLINK_CB(skb).portid; /* pid of sending process */
+ portid = NETLINK_CB(skb).portid; /* netlink portid */
NETLINK_CB(skb).portid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d0670f00d524..11cb4979a465 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -59,6 +59,8 @@ int inet_csk_bind_conflict(const struct sock *sk,
struct sock *sk2;
struct hlist_node *node;
int reuse = sk->sk_reuse;
+ int reuseport = sk->sk_reuseport;
+ kuid_t uid = sock_i_uid((struct sock *)sk);
/*
* Unlike other sk lookup places we do not check
@@ -73,8 +75,11 @@ int inet_csk_bind_conflict(const struct sock *sk,
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
- if (!reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) {
+ if ((!reuse || !sk2->sk_reuse ||
+ sk2->sk_state == TCP_LISTEN) &&
+ (!reuseport || !sk2->sk_reuseport ||
+ (sk2->sk_state != TCP_TIME_WAIT &&
+ !uid_eq(uid, sock_i_uid(sk2))))) {
const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
sk2_rcv_saddr == sk_rcv_saddr(sk))
@@ -106,6 +111,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
int ret, attempts = 5;
struct net *net = sock_net(sk);
int smallest_size = -1, smallest_rover;
+ kuid_t uid = sock_i_uid(sk);
local_bh_disable();
if (!snum) {
@@ -125,9 +131,12 @@ again:
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, node, &head->chain)
if (net_eq(ib_net(tb), net) && tb->port == rover) {
- if (tb->fastreuse > 0 &&
- sk->sk_reuse &&
- sk->sk_state != TCP_LISTEN &&
+ if (((tb->fastreuse > 0 &&
+ sk->sk_reuse &&
+ sk->sk_state != TCP_LISTEN) ||
+ (tb->fastreuseport > 0 &&
+ sk->sk_reuseport &&
+ uid_eq(tb->fastuid, uid))) &&
(tb->num_owners < smallest_size || smallest_size == -1)) {
smallest_size = tb->num_owners;
smallest_rover = rover;
@@ -185,14 +194,18 @@ tb_found:
if (sk->sk_reuse == SK_FORCE_REUSE)
goto success;
- if (tb->fastreuse > 0 &&
- sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+ if (((tb->fastreuse > 0 &&
+ sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
+ (tb->fastreuseport > 0 &&
+ sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
smallest_size == -1) {
goto success;
} else {
ret = 1;
if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
- if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+ if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
+ (tb->fastreuseport > 0 &&
+ sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
smallest_size != -1 && --attempts >= 0) {
spin_unlock(&head->lock);
goto again;
@@ -212,9 +225,19 @@ tb_not_found:
tb->fastreuse = 1;
else
tb->fastreuse = 0;
- } else if (tb->fastreuse &&
- (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
- tb->fastreuse = 0;
+ if (sk->sk_reuseport) {
+ tb->fastreuseport = 1;
+ tb->fastuid = uid;
+ } else
+ tb->fastreuseport = 0;
+ } else {
+ if (tb->fastreuse &&
+ (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
+ tb->fastreuse = 0;
+ if (tb->fastreuseport &&
+ (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)))
+ tb->fastreuseport = 0;
+ }
success:
if (!inet_csk(sk)->icsk_bind_hash)
inet_bind_hash(sk, tb, snum);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 4750d2b74d79..2e453bde6992 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -73,8 +73,9 @@ EXPORT_SYMBOL(inet_frags_init);
void inet_frags_init_net(struct netns_frags *nf)
{
nf->nqueues = 0;
- atomic_set(&nf->mem, 0);
+ init_frag_mem_limit(nf);
INIT_LIST_HEAD(&nf->lru_list);
+ spin_lock_init(&nf->lru_lock);
}
EXPORT_SYMBOL(inet_frags_init_net);
@@ -91,6 +92,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
local_bh_disable();
inet_frag_evictor(nf, f, true);
local_bh_enable();
+
+ percpu_counter_destroy(&nf->mem);
}
EXPORT_SYMBOL(inet_frags_exit_net);
@@ -98,9 +101,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
{
write_lock(&f->lock);
hlist_del(&fq->list);
- list_del(&fq->lru_list);
fq->net->nqueues--;
write_unlock(&f->lock);
+ inet_frag_lru_del(fq);
}
void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
@@ -117,12 +120,8 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
EXPORT_SYMBOL(inet_frag_kill);
static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
- struct sk_buff *skb, int *work)
+ struct sk_buff *skb)
{
- if (work)
- *work -= skb->truesize;
-
- atomic_sub(skb->truesize, &nf->mem);
if (f->skb_free)
f->skb_free(skb);
kfree_skb(skb);
@@ -133,6 +132,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
{
struct sk_buff *fp;
struct netns_frags *nf;
+ unsigned int sum, sum_truesize = 0;
WARN_ON(!(q->last_in & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
@@ -143,13 +143,14 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
while (fp) {
struct sk_buff *xp = fp->next;
- frag_kfree_skb(nf, f, fp, work);
+ sum_truesize += fp->truesize;
+ frag_kfree_skb(nf, f, fp);
fp = xp;
}
-
+ sum = sum_truesize + f->qsize;
if (work)
- *work -= f->qsize;
- atomic_sub(f->qsize, &nf->mem);
+ *work -= sum;
+ sub_frag_mem_limit(q, sum);
if (f->destructor)
f->destructor(q);
@@ -164,22 +165,23 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
int work, evicted = 0;
if (!force) {
- if (atomic_read(&nf->mem) <= nf->high_thresh)
+ if (frag_mem_limit(nf) <= nf->high_thresh)
return 0;
}
- work = atomic_read(&nf->mem) - nf->low_thresh;
+ work = frag_mem_limit(nf) - nf->low_thresh;
while (work > 0) {
- read_lock(&f->lock);
+ spin_lock(&nf->lru_lock);
+
if (list_empty(&nf->lru_list)) {
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
break;
}
q = list_first_entry(&nf->lru_list,
struct inet_frag_queue, lru_list);
atomic_inc(&q->refcnt);
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
spin_lock(&q->lock);
if (!(q->last_in & INET_FRAG_COMPLETE))
@@ -233,9 +235,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &f->hash[hash]);
- list_add_tail(&qp->lru_list, &nf->lru_list);
nf->nqueues++;
write_unlock(&f->lock);
+ inet_frag_lru_add(nf, qp);
return qp;
}
@@ -250,7 +252,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
q->net = nf;
f->constructor(q, arg);
- atomic_add(f->qsize, &nf->mem);
+ add_frag_mem_limit(q, f->qsize);
+
setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
spin_lock_init(&q->lock);
atomic_set(&q->refcnt, 1);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index fa3ae8148710..0ce0595d9861 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -39,6 +39,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
write_pnet(&tb->ib_net, hold_net(net));
tb->port = snum;
tb->fastreuse = 0;
+ tb->fastreuseport = 0;
tb->num_owners = 0;
INIT_HLIST_HEAD(&tb->owners);
hlist_add_head(&tb->node, &head->chain);
@@ -151,16 +152,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
!ipv6_only_sock(sk)) {
__be32 rcv_saddr = inet->inet_rcv_saddr;
- score = sk->sk_family == PF_INET ? 1 : 0;
+ score = sk->sk_family == PF_INET ? 2 : 1;
if (rcv_saddr) {
if (rcv_saddr != daddr)
return -1;
- score += 2;
+ score += 4;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
return -1;
- score += 2;
+ score += 4;
}
}
return score;
@@ -176,6 +177,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
+ const __be32 saddr, __be16 sport,
const __be32 daddr, const unsigned short hnum,
const int dif)
{
@@ -183,17 +185,29 @@ struct sock *__inet_lookup_listener(struct net *net,
struct hlist_nulls_node *node;
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
- int score, hiscore;
+ int score, hiscore, matches = 0, reuseport = 0;
+ u32 phash = 0;
rcu_read_lock();
begin:
result = NULL;
- hiscore = -1;
+ hiscore = 0;
sk_nulls_for_each_rcu(sk, node, &ilb->head) {
score = compute_score(sk, net, hnum, daddr, dif);
if (score > hiscore) {
result = sk;
hiscore = score;
+ reuseport = sk->sk_reuseport;
+ if (reuseport) {
+ phash = inet_ehashfn(net, daddr, hnum,
+ saddr, sport);
+ matches = 1;
+ }
+ } else if (score == hiscore && reuseport) {
+ matches++;
+ if (((u64)phash * matches) >> 32 == 0)
+ result = sk;
+ phash = next_pseudo_random32(phash);
}
}
/*
@@ -501,7 +515,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
inet_bind_bucket_for_each(tb, node, &head->chain) {
if (net_eq(ib_net(tb), net) &&
tb->port == port) {
- if (tb->fastreuse >= 0)
+ if (tb->fastreuse >= 0 ||
+ tb->fastreuseport >= 0)
goto next_port;
WARN_ON(hlist_empty(&tb->owners));
if (!check_established(death_row, sk,
@@ -518,6 +533,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
break;
}
tb->fastreuse = -1;
+ tb->fastreuseport = -1;
goto ok;
next_port:
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index eb9d63a570cd..1211613c6c34 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -122,7 +122,7 @@ int ip_frag_nqueues(struct net *net)
int ip_frag_mem(struct net *net)
{
- return atomic_read(&net->ipv4.frags.mem);
+ return sum_frag_mem_limit(&net->ipv4.frags);
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
@@ -161,13 +161,6 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
qp->user == arg->user;
}
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf->mem);
- kfree_skb(skb);
-}
-
static void ip4_frag_init(struct inet_frag_queue *q, void *a)
{
struct ipq *qp = container_of(q, struct ipq, q);
@@ -340,6 +333,7 @@ static inline int ip_frag_too_far(struct ipq *qp)
static int ip_frag_reinit(struct ipq *qp)
{
struct sk_buff *fp;
+ unsigned int sum_truesize = 0;
if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
atomic_inc(&qp->q.refcnt);
@@ -349,9 +343,12 @@ static int ip_frag_reinit(struct ipq *qp)
fp = qp->q.fragments;
do {
struct sk_buff *xp = fp->next;
- frag_kfree_skb(qp->q.net, fp);
+
+ sum_truesize += fp->truesize;
+ kfree_skb(fp);
fp = xp;
} while (fp);
+ sub_frag_mem_limit(&qp->q, sum_truesize);
qp->q.last_in = 0;
qp->q.len = 0;
@@ -496,7 +493,8 @@ found:
qp->q.fragments = next;
qp->q.meat -= free_it->len;
- frag_kfree_skb(qp->q.net, free_it);
+ sub_frag_mem_limit(&qp->q, free_it->truesize);
+ kfree_skb(free_it);
}
}
@@ -519,7 +517,7 @@ found:
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
- atomic_add(skb->truesize, &qp->q.net->mem);
+ add_frag_mem_limit(&qp->q, skb->truesize);
if (offset == 0)
qp->q.last_in |= INET_FRAG_FIRST_IN;
@@ -531,9 +529,7 @@ found:
qp->q.meat == qp->q.len)
return ip_frag_reasm(qp, prev, dev);
- write_lock(&ip4_frags.lock);
- list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
- write_unlock(&ip4_frags.lock);
+ inet_frag_lru_move(&qp->q);
return -EINPROGRESS;
err:
@@ -617,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- atomic_add(clone->truesize, &qp->q.net->mem);
+ add_frag_mem_limit(&qp->q, clone->truesize);
}
skb_push(head, head->data - skb_network_header(head));
@@ -645,7 +641,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
}
fp = next;
}
- atomic_sub(sum_truesize, &qp->q.net->mem);
+ sub_frag_mem_limit(&qp->q, sum_truesize);
head->next = NULL;
head->dev = dev;
@@ -851,14 +847,22 @@ static inline void ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
- /*
- * Fragment cache limits. We will commit 256K at one time. Should we
- * cross that limit we will prune down to 192K. This should cope with
- * even the most extreme cases without allowing an attacker to
- * measurably harm machine performance.
+ /* Fragment cache limits.
+ *
+ * The fragment memory accounting code, (tries to) account for
+ * the real memory usage, by measuring both the size of frag
+ * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
+ * and the SKB's truesize.
+ *
+ * A 64K fragment consumes 129736 bytes (44*2944)+200
+ * (1500 truesize == 2944, sizeof(struct ipq) == 200)
+ *
+ * We will commit 4MB at one time. Should we cross that limit
+ * we will prune down to 3MB, making room for approx 8 big 64K
+ * fragments 8x128k.
*/
- net->ipv4.frags.high_thresh = 256 * 1024;
- net->ipv4.frags.low_thresh = 192 * 1024;
+ net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
+ net->ipv4.frags.low_thresh = 3 * 1024 * 1024;
/*
* Important NOTE! Fragment queue must be destroyed before MSL expires.
* RFC791 is wrong proposing to prolongate timer each fragment arrival
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e81b1caf2ea2..00a14b9864ea 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -738,7 +738,7 @@ drop:
static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- const struct iphdr *old_iph = ip_hdr(skb);
+ const struct iphdr *old_iph;
const struct iphdr *tiph;
struct flowi4 fl4;
u8 tos;
@@ -756,6 +756,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
skb_checksum_help(skb))
goto tx_error;
+ old_iph = ip_hdr(skb);
+
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
@@ -818,8 +820,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
ttl = tiph->ttl;
tos = tiph->tos;
- if (tos == 1) {
- tos = 0;
+ if (tos & 0x1) {
+ tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index f1395a6fb35f..87abd3e2bd32 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -208,13 +208,6 @@ static int ip_local_deliver_finish(struct sk_buff *skb)
if (ipprot != NULL) {
int ret;
- if (!net_eq(net, &init_net) && !ipprot->netns_ok) {
- net_info_ratelimited("%s: proto %d isn't netns-ready\n",
- __func__, protocol);
- kfree_skb(skb);
- goto out;
- }
-
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 9a46daed2f3c..f01d1b1aff7f 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -163,6 +163,7 @@ static const struct net_protocol ipcomp4_protocol = {
.handler = xfrm4_rcv,
.err_handler = ipcomp4_err,
.no_policy = 1,
+ .netns_ok = 1,
};
static int __init ipcomp4_init(void)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 191fc24a745a..8f024d41eefa 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -472,7 +472,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
__be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
- const struct iphdr *old_iph = ip_hdr(skb);
+ const struct iphdr *old_iph;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
@@ -486,6 +486,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
skb_checksum_help(skb))
goto tx_error;
+ old_iph = ip_hdr(skb);
+
if (tos & 1)
tos = old_iph->tos;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a9454cbd953c..7085b9b51e7f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -828,6 +828,49 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt,
return NULL;
}
+/* Look for a (*,*,oif) entry */
+static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt,
+ int vifi)
+{
+ int line = MFC_HASH(htonl(INADDR_ANY), htonl(INADDR_ANY));
+ struct mfc_cache *c;
+
+ list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list)
+ if (c->mfc_origin == htonl(INADDR_ANY) &&
+ c->mfc_mcastgrp == htonl(INADDR_ANY) &&
+ c->mfc_un.res.ttls[vifi] < 255)
+ return c;
+
+ return NULL;
+}
+
+/* Look for a (*,G) entry */
+static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt,
+ __be32 mcastgrp, int vifi)
+{
+ int line = MFC_HASH(mcastgrp, htonl(INADDR_ANY));
+ struct mfc_cache *c, *proxy;
+
+ if (mcastgrp == htonl(INADDR_ANY))
+ goto skip;
+
+ list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list)
+ if (c->mfc_origin == htonl(INADDR_ANY) &&
+ c->mfc_mcastgrp == mcastgrp) {
+ if (c->mfc_un.res.ttls[vifi] < 255)
+ return c;
+
+ /* It's ok if the vifi is part of the static tree */
+ proxy = ipmr_cache_find_any_parent(mrt,
+ c->mfc_parent);
+ if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
+ return c;
+ }
+
+skip:
+ return ipmr_cache_find_any_parent(mrt, vifi);
+}
+
/*
* Allocate a multicast cache entry
*/
@@ -1053,7 +1096,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
* MFC cache manipulation by user space mroute daemon
*/
-static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
+static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
{
int line;
struct mfc_cache *c, *next;
@@ -1062,7 +1105,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
- c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
+ c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr &&
+ (parent == -1 || parent == c->mfc_parent)) {
list_del_rcu(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_cache_free(c);
@@ -1073,7 +1117,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
}
static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
- struct mfcctl *mfc, int mrtsock)
+ struct mfcctl *mfc, int mrtsock, int parent)
{
bool found = false;
int line;
@@ -1086,7 +1130,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
- c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
+ c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr &&
+ (parent == -1 || parent == c->mfc_parent)) {
found = true;
break;
}
@@ -1103,7 +1148,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
return 0;
}
- if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
+ if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) &&
+ !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
return -EINVAL;
c = ipmr_cache_alloc();
@@ -1218,7 +1264,7 @@ static void mrtsock_destruct(struct sock *sk)
int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen)
{
- int ret;
+ int ret, parent = 0;
struct vifctl vif;
struct mfcctl mfc;
struct net *net = sock_net(sk);
@@ -1287,16 +1333,22 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
*/
case MRT_ADD_MFC:
case MRT_DEL_MFC:
+ parent = -1;
+ case MRT_ADD_MFC_PROXY:
+ case MRT_DEL_MFC_PROXY:
if (optlen != sizeof(mfc))
return -EINVAL;
if (copy_from_user(&mfc, optval, sizeof(mfc)))
return -EFAULT;
+ if (parent == 0)
+ parent = mfc.mfcc_parent;
rtnl_lock();
- if (optname == MRT_DEL_MFC)
- ret = ipmr_mfc_delete(mrt, &mfc);
+ if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY)
+ ret = ipmr_mfc_delete(mrt, &mfc, parent);
else
ret = ipmr_mfc_add(net, mrt, &mfc,
- sk == rtnl_dereference(mrt->mroute_sk));
+ sk == rtnl_dereference(mrt->mroute_sk),
+ parent);
rtnl_unlock();
return ret;
/*
@@ -1749,17 +1801,28 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
{
int psend = -1;
int vif, ct;
+ int true_vifi = ipmr_find_vif(mrt, skb->dev);
vif = cache->mfc_parent;
cache->mfc_un.res.pkt++;
cache->mfc_un.res.bytes += skb->len;
+ if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) {
+ struct mfc_cache *cache_proxy;
+
+ /* For an (*,G) entry, we only check that the incomming
+ * interface is part of the static tree.
+ */
+ cache_proxy = ipmr_cache_find_any_parent(mrt, vif);
+ if (cache_proxy &&
+ cache_proxy->mfc_un.res.ttls[true_vifi] < 255)
+ goto forward;
+ }
+
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
if (mrt->vif_table[vif].dev != skb->dev) {
- int true_vifi;
-
if (rt_is_output_route(skb_rtable(skb))) {
/* It is our own packet, looped back.
* Very complicated situation...
@@ -1776,7 +1839,6 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
}
cache->mfc_un.res.wrong_if++;
- true_vifi = ipmr_find_vif(mrt, skb->dev);
if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
@@ -1794,15 +1856,34 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
goto dont_forward;
}
+forward:
mrt->vif_table[vif].pkt_in++;
mrt->vif_table[vif].bytes_in += skb->len;
/*
* Forward the frame
*/
+ if (cache->mfc_origin == htonl(INADDR_ANY) &&
+ cache->mfc_mcastgrp == htonl(INADDR_ANY)) {
+ if (true_vifi >= 0 &&
+ true_vifi != cache->mfc_parent &&
+ ip_hdr(skb)->ttl >
+ cache->mfc_un.res.ttls[cache->mfc_parent]) {
+ /* It's an (*,*) entry and the packet is not coming from
+ * the upstream: forward the packet to the upstream
+ * only.
+ */
+ psend = cache->mfc_parent;
+ goto last_forward;
+ }
+ goto dont_forward;
+ }
for (ct = cache->mfc_un.res.maxvif - 1;
ct >= cache->mfc_un.res.minvif; ct--) {
- if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) {
+ /* For (*,G) entry, don't forward to the incoming interface */
+ if ((cache->mfc_origin != htonl(INADDR_ANY) ||
+ ct != true_vifi) &&
+ ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) {
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
@@ -1813,6 +1894,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
psend = ct;
}
}
+last_forward:
if (psend != -1) {
if (local) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
@@ -1902,6 +1984,13 @@ int ip_mr_input(struct sk_buff *skb)
/* already under rcu_read_lock() */
cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
+ if (cache == NULL) {
+ int vif = ipmr_find_vif(mrt, skb->dev);
+
+ if (vif >= 0)
+ cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr,
+ vif);
+ }
/*
* No usable cache entry
@@ -2107,7 +2196,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
rcu_read_lock();
cache = ipmr_cache_find(mrt, saddr, daddr);
+ if (cache == NULL && skb->dev) {
+ int vif = ipmr_find_vif(mrt, skb->dev);
+ if (vif >= 0)
+ cache = ipmr_cache_find_any(mrt, daddr, vif);
+ }
if (cache == NULL) {
struct sk_buff *skb2;
struct iphdr *iph;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3ea4127404d6..7dc6a9743592 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -901,7 +901,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name),
"arptable_%s", name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
struct arpt_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -958,7 +958,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
}
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
const struct xt_table_info *private = t->private;
duprintf("t->private->number = %u\n",
@@ -1001,7 +1001,7 @@ static int __do_replace(struct net *net, const char *name,
t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name),
"arptable_%s", name);
- if (!t || IS_ERR(t)) {
+ if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1158,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user,
}
t = xt_find_table_lock(net, NFPROTO_ARP, name);
- if (!t || IS_ERR(t)) {
+ if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free;
}
@@ -1646,7 +1646,7 @@ static int compat_get_entries(struct net *net,
xt_compat_lock(NFPROTO_ARP);
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 17c5e06da662..3efcf87400c3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1090,7 +1090,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
"iptable_%s", name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
struct ipt_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -1149,7 +1149,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
}
t = xt_find_table_lock(net, AF_INET, get.name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
const struct xt_table_info *private = t->private;
duprintf("t->private->number = %u\n", private->number);
if (get.size == private->size)
@@ -1189,7 +1189,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
"iptable_%s", name);
- if (!t || IS_ERR(t)) {
+ if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1347,7 +1347,7 @@ do_add_counters(struct net *net, const void __user *user,
}
t = xt_find_table_lock(net, AF_INET, name);
- if (!t || IS_ERR(t)) {
+ if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free;
}
@@ -1931,7 +1931,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
xt_compat_lock(AF_INET);
t = xt_find_table_lock(net, AF_INET, get.name);
- if (t && !IS_ERR(t)) {
+ if (!IS_ERR_OR_NULL(t)) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
duprintf("t->private->number = %u\n", private->number);
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index b5ef3cba2250..7d168dcbd135 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -88,10 +88,8 @@ static void ulog_send(unsigned int nlgroupnum)
{
ulog_buff_t *ub = &ulog_buffers[nlgroupnum];
- if (timer_pending(&ub->timer)) {
- pr_debug("ulog_send: timer was pending, deleting\n");
- del_timer(&ub->timer);
- }
+ pr_debug("ulog_send: timer is deleting\n");
+ del_timer(&ub->timer);
if (!ub->skb) {
pr_debug("ulog_send: nothing to send\n");
@@ -426,10 +424,8 @@ static void __exit ulog_tg_exit(void)
/* remove pending timers and free allocated skb's */
for (i = 0; i < ULOG_MAXNLGROUPS; i++) {
ub = &ulog_buffers[i];
- if (timer_pending(&ub->timer)) {
- pr_debug("timer was pending, deleting\n");
- del_timer(&ub->timer);
- }
+ pr_debug("timer is deleting\n");
+ del_timer(&ub->timer);
if (ub->skb) {
kfree_skb(ub->skb);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index fcdd0c2406e6..48990ada0e1e 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -420,54 +420,43 @@ static int ipv4_net_init(struct net *net)
{
int ret = 0;
- ret = nf_conntrack_l4proto_register(net,
- &nf_conntrack_l4proto_tcp4);
+ ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp4);
if (ret < 0) {
- pr_err("nf_conntrack_l4proto_tcp4 :protocol register failed\n");
+ pr_err("nf_conntrack_tcp4: pernet registration failed\n");
goto out_tcp;
}
- ret = nf_conntrack_l4proto_register(net,
- &nf_conntrack_l4proto_udp4);
+ ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp4);
if (ret < 0) {
- pr_err("nf_conntrack_l4proto_udp4 :protocol register failed\n");
+ pr_err("nf_conntrack_udp4: pernet registration failed\n");
goto out_udp;
}
- ret = nf_conntrack_l4proto_register(net,
- &nf_conntrack_l4proto_icmp);
+ ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmp);
if (ret < 0) {
- pr_err("nf_conntrack_l4proto_icmp4 :protocol register failed\n");
+ pr_err("nf_conntrack_icmp4: pernet registration failed\n");
goto out_icmp;
}
- ret = nf_conntrack_l3proto_register(net,
- &nf_conntrack_l3proto_ipv4);
+ ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4);
if (ret < 0) {
- pr_err("nf_conntrack_l3proto_ipv4 :protocol register failed\n");
+ pr_err("nf_conntrack_ipv4: pernet registration failed\n");
goto out_ipv4;
}
return 0;
out_ipv4:
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_icmp);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp);
out_icmp:
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_udp4);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4);
out_udp:
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_tcp4);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4);
out_tcp:
return ret;
}
static void ipv4_net_exit(struct net *net)
{
- nf_conntrack_l3proto_unregister(net,
- &nf_conntrack_l3proto_ipv4);
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_icmp);
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_udp4);
- nf_conntrack_l4proto_unregister(net,
- &nf_conntrack_l4proto_tcp4);
+ nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4);
+ nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4);
}
static struct pernet_operations ipv4_net_ops = {
@@ -500,16 +489,49 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
pr_err("nf_conntrack_ipv4: can't register hooks.\n");
goto cleanup_pernet;
}
+
+ ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4);
+ if (ret < 0) {
+ pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n");
+ goto cleanup_hooks;
+ }
+
+ ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4);
+ if (ret < 0) {
+ pr_err("nf_conntrack_ipv4: can't register udp4 proto.\n");
+ goto cleanup_tcp4;
+ }
+
+ ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp);
+ if (ret < 0) {
+ pr_err("nf_conntrack_ipv4: can't register icmpv4 proto.\n");
+ goto cleanup_udp4;
+ }
+
+ ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
+ if (ret < 0) {
+ pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
+ goto cleanup_icmpv4;
+ }
+
#if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
ret = nf_conntrack_ipv4_compat_init();
if (ret < 0)
- goto cleanup_hooks;
+ goto cleanup_proto;
#endif
return ret;
#if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
+ cleanup_proto:
+ nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
+#endif
+ cleanup_icmpv4:
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp);
+ cleanup_udp4:
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
+ cleanup_tcp4:
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
cleanup_hooks:
nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
-#endif
cleanup_pernet:
unregister_pernet_subsys(&ipv4_net_ops);
cleanup_sockopt:
@@ -523,6 +545,10 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
#if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
nf_conntrack_ipv4_compat_fini();
#endif
+ nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp);
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
+ nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
unregister_pernet_subsys(&ipv4_net_ops);
nf_unregister_sockopt(&so_getorigdst);
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 0f9d09f54bd9..ce848461acbb 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -37,6 +37,12 @@ const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
+ if (!prot->netns_ok) {
+ pr_err("Protocol %u is not namespace aware, cannot register.\n",
+ protocol);
+ return -EINVAL;
+ }
+
return !cmpxchg((const struct net_protocol **)&inet_protos[protocol],
NULL, prot) ? 0 : -1;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b236ef04914f..ef54377fb11c 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -232,7 +232,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
*
* return false if we decode an option that should not be.
*/
-bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok)
+bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
+ struct net *net, bool *ecn_ok)
{
/* echoed timestamp, lowest bits contain options */
u32 options = tcp_opt->rcv_tsecr & TSMASK;
@@ -247,7 +248,7 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok)
tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0;
*ecn_ok = (options >> 5) & 1;
- if (*ecn_ok && !sysctl_tcp_ecn)
+ if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn)
return false;
if (tcp_opt->sack_ok && !sysctl_tcp_sack)
@@ -295,7 +296,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
- if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
+ if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
ret = NULL;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d84400b65049..960fd29d9b8e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -27,6 +27,7 @@
#include <net/tcp_memcontrol.h>
static int zero;
+static int one = 1;
static int two = 2;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
@@ -232,8 +233,8 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
return 0;
}
-int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
{
ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
@@ -538,13 +539,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_ecn",
- .data = &sysctl_tcp_ecn,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_dsack",
.data = &sysctl_tcp_dsack,
.maxlen = sizeof(int),
@@ -556,14 +550,16 @@ static struct ctl_table ipv4_table[] = {
.data = &sysctl_tcp_wmem,
.maxlen = sizeof(sysctl_tcp_wmem),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.maxlen = sizeof(sysctl_tcp_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "tcp_app_win",
@@ -637,13 +633,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_tcp_congestion_control,
},
{
- .procname = "tcp_abc",
- .data = &sysctl_tcp_abc,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "tcp_mtu_probing",
.data = &sysctl_tcp_mtu_probing,
.maxlen = sizeof(int),
@@ -786,7 +775,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_rmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero
+ .extra1 = &one
},
{
.procname = "udp_wmem_min",
@@ -794,7 +783,7 @@ static struct ctl_table ipv4_table[] = {
.maxlen = sizeof(sysctl_udp_wmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero
+ .extra1 = &one
},
{ }
};
@@ -850,6 +839,13 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = ipv4_ping_group_range,
},
{
+ .procname = "tcp_ecn",
+ .data = &init_net.ipv4.sysctl_tcp_ecn,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
.procname = "tcp_mem",
.maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
.mode = 0644,
@@ -882,6 +878,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
&net->ipv4.sysctl_icmp_ratemask;
table[6].data =
&net->ipv4.sysctl_ping_group_range;
+ table[7].data =
+ &net->ipv4.sysctl_tcp_ecn;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2aa69c8ae60c..2c7e5963c2ea 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -896,6 +896,8 @@ new_segment:
skb_fill_page_desc(skb, i, page, offset, copy);
}
+ skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG;
+
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
@@ -2287,7 +2289,6 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
- tp->bytes_acked = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
tcp_clear_retrans(tp);
@@ -3032,6 +3033,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
+ SKB_GSO_SHARED_FRAG |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
@@ -3243,7 +3245,7 @@ __tcp_alloc_md5sig_pool(struct sock *sk)
struct crypto_hash *hash;
hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
- if (!hash || IS_ERR(hash))
+ if (IS_ERR_OR_NULL(hash))
goto out_free;
per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index cdf2e707bb10..019c2389a341 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -317,28 +317,11 @@ void tcp_slow_start(struct tcp_sock *tp)
snd_cwnd = 1U;
}
- /* RFC3465: ABC Slow start
- * Increase only after a full MSS of bytes is acked
- *
- * TCP sender SHOULD increase cwnd by the number of
- * previously unacknowledged bytes ACKed by each incoming
- * acknowledgment, provided the increase is not more than L
- */
- if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache)
- return;
-
if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */
else
cnt = snd_cwnd; /* exponential increase */
- /* RFC3465: ABC
- * We MAY increase by 2 if discovered delayed ack
- */
- if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache)
- cnt <<= 1;
- tp->bytes_acked = 0;
-
tp->snd_cwnd_cnt += cnt;
while (tp->snd_cwnd_cnt >= snd_cwnd) {
tp->snd_cwnd_cnt -= snd_cwnd;
@@ -378,20 +361,9 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
/* In "safe" area, increase. */
if (tp->snd_cwnd <= tp->snd_ssthresh)
tcp_slow_start(tp);
-
/* In dangerous area, increase slowly. */
- else if (sysctl_tcp_abc) {
- /* RFC3465: Appropriate Byte Count
- * increase once for each full cwnd acked
- */
- if (tp->bytes_acked >= tp->snd_cwnd*tp->mss_cache) {
- tp->bytes_acked -= tp->snd_cwnd*tp->mss_cache;
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- }
- } else {
+ else
tcp_cong_avoid_ai(tp, tp->snd_cwnd);
- }
}
EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ad70a962c20e..ea678b62e94f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -81,8 +81,6 @@ int sysctl_tcp_sack __read_mostly = 1;
int sysctl_tcp_fack __read_mostly = 1;
int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
EXPORT_SYMBOL(sysctl_tcp_reordering);
-int sysctl_tcp_ecn __read_mostly = 2;
-EXPORT_SYMBOL(sysctl_tcp_ecn);
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 1;
@@ -100,7 +98,6 @@ int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_thin_dupack __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_abc __read_mostly;
int sysctl_tcp_early_retrans __read_mostly = 2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
@@ -1242,13 +1239,13 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
*/
if (!skb_shinfo(prev)->gso_size) {
skb_shinfo(prev)->gso_size = mss;
- skb_shinfo(prev)->gso_type = sk->sk_gso_type;
+ skb_shinfo(prev)->gso_type |= sk->sk_gso_type;
}
/* CHECKME: To clear or not to clear? Mimics normal skb currently */
if (skb_shinfo(skb)->gso_segs <= 1) {
skb_shinfo(skb)->gso_size = 0;
- skb_shinfo(skb)->gso_type = 0;
+ skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG;
}
/* Difference in this won't matter, both ACKed by the same cumul. ACK */
@@ -2009,7 +2006,6 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->frto_counter = 0;
- tp->bytes_acked = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
@@ -2058,7 +2054,6 @@ void tcp_enter_loss(struct sock *sk, int how)
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->bytes_acked = 0;
tcp_clear_retrans_partial(tp);
if (tcp_is_reno(tp))
@@ -2686,7 +2681,6 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
struct tcp_sock *tp = tcp_sk(sk);
tp->high_seq = tp->snd_nxt;
- tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
tp->prior_cwnd = tp->snd_cwnd;
tp->prr_delivered = 0;
@@ -2737,7 +2731,6 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
struct tcp_sock *tp = tcp_sk(sk);
tp->prior_ssthresh = 0;
- tp->bytes_acked = 0;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
tp->undo_marker = 0;
tcp_init_cwnd_reduction(sk, set_ssthresh);
@@ -3419,7 +3412,6 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
- tp->bytes_acked = 0;
TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
@@ -3615,15 +3607,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (after(ack, prior_snd_una))
flag |= FLAG_SND_UNA_ADVANCED;
- if (sysctl_tcp_abc) {
- if (icsk->icsk_ca_state < TCP_CA_CWR)
- tp->bytes_acked += ack - prior_snd_una;
- else if (icsk->icsk_ca_state == TCP_CA_Loss)
- /* we assume just one segment left network */
- tp->bytes_acked += min(ack - prior_snd_una,
- tp->mss_cache);
- }
-
prior_fackets = tp->fackets_out;
prior_in_flight = tcp_packets_in_flight(tp);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index eadb693eef55..0eaf685bddc9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -657,7 +657,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
* no RST generated if md5 hash doesn't match.
*/
sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
- &tcp_hashinfo, ip_hdr(skb)->daddr,
+ &tcp_hashinfo, ip_hdr(skb)->saddr,
+ th->source, ip_hdr(skb)->daddr,
ntohs(th->source), inet_iif(skb));
/* don't send rst if it can't find key */
if (!sk1)
@@ -1570,7 +1571,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free;
if (!want_cookie || tmp_opt.tstamp_ok)
- TCP_ECN_create_request(req, skb);
+ TCP_ECN_create_request(req, skb, sock_net(sk));
if (want_cookie) {
isn = cookie_v4_init_sequence(sk, skb, &req->mss);
@@ -2077,6 +2078,7 @@ do_time_wait:
case TCP_TW_SYN: {
struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
&tcp_hashinfo,
+ iph->saddr, th->source,
iph->daddr, th->dest,
inet_iif(skb));
if (sk2) {
@@ -2891,6 +2893,7 @@ EXPORT_SYMBOL(tcp_prot);
static int __net_init tcp_sk_init(struct net *net)
{
+ net->ipv4.sysctl_tcp_ecn = 2;
return 0;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f35f2dfb6401..f0409287b5f4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -446,7 +446,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
*/
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- newtp->bytes_acked = 0;
newtp->frto_counter = 0;
newtp->frto_highmark = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5d451593ef16..367e2ec01da1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -314,7 +314,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
tp->ecn_flags = 0;
- if (sysctl_tcp_ecn == 1) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
tp->ecn_flags = TCP_ECN_OK;
}
@@ -1133,6 +1133,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
+ skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG;
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1140,11 +1141,10 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
*/
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
- skb_shinfo(skb)->gso_type = 0;
} else {
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
skb_shinfo(skb)->gso_size = mss_now;
- skb_shinfo(skb)->gso_type = sk->sk_gso_type;
+ skb_shinfo(skb)->gso_type |= sk->sk_gso_type;
}
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1f4d405eafba..6791aac06ea9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -139,6 +139,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
{
struct sock *sk2;
struct hlist_nulls_node *node;
+ kuid_t uid = sock_i_uid(sk);
sk_nulls_for_each(sk2, node, &hslot->head)
if (net_eq(sock_net(sk2), net) &&
@@ -147,6 +148,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ (!sk2->sk_reuseport || !sk->sk_reuseport ||
+ !uid_eq(uid, sock_i_uid(sk2))) &&
(*saddr_comp)(sk, sk2)) {
if (bitmap)
__set_bit(udp_sk(sk2)->udp_port_hash >> log,
@@ -169,6 +172,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
{
struct sock *sk2;
struct hlist_nulls_node *node;
+ kuid_t uid = sock_i_uid(sk);
int res = 0;
spin_lock(&hslot2->lock);
@@ -179,6 +183,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ (!sk2->sk_reuseport || !sk->sk_reuseport ||
+ !uid_eq(uid, sock_i_uid(sk2))) &&
(*saddr_comp)(sk, sk2)) {
res = 1;
break;
@@ -337,26 +343,26 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
!ipv6_only_sock(sk)) {
struct inet_sock *inet = inet_sk(sk);
- score = (sk->sk_family == PF_INET ? 1 : 0);
+ score = (sk->sk_family == PF_INET ? 2 : 1);
if (inet->inet_rcv_saddr) {
if (inet->inet_rcv_saddr != daddr)
return -1;
- score += 2;
+ score += 4;
}
if (inet->inet_daddr) {
if (inet->inet_daddr != saddr)
return -1;
- score += 2;
+ score += 4;
}
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
- score += 2;
+ score += 4;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
return -1;
- score += 2;
+ score += 4;
}
}
return score;
@@ -365,7 +371,6 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
/*
* In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
*/
-#define SCORE2_MAX (1 + 2 + 2 + 2)
static inline int compute_score2(struct sock *sk, struct net *net,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned int hnum, int dif)
@@ -380,21 +385,21 @@ static inline int compute_score2(struct sock *sk, struct net *net,
if (inet->inet_num != hnum)
return -1;
- score = (sk->sk_family == PF_INET ? 1 : 0);
+ score = (sk->sk_family == PF_INET ? 2 : 1);
if (inet->inet_daddr) {
if (inet->inet_daddr != saddr)
return -1;
- score += 2;
+ score += 4;
}
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
- score += 2;
+ score += 4;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
return -1;
- score += 2;
+ score += 4;
}
}
return score;
@@ -409,19 +414,29 @@ static struct sock *udp4_lib_lookup2(struct net *net,
{
struct sock *sk, *result;
struct hlist_nulls_node *node;
- int score, badness;
+ int score, badness, matches = 0, reuseport = 0;
+ u32 hash = 0;
begin:
result = NULL;
- badness = -1;
+ badness = 0;
udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
score = compute_score2(sk, net, saddr, sport,
daddr, hnum, dif);
if (score > badness) {
result = sk;
badness = score;
- if (score == SCORE2_MAX)
- goto exact_match;
+ reuseport = sk->sk_reuseport;
+ if (reuseport) {
+ hash = inet_ehashfn(net, daddr, hnum,
+ saddr, htons(sport));
+ matches = 1;
+ }
+ } else if (score == badness && reuseport) {
+ matches++;
+ if (((u64)hash * matches) >> 32 == 0)
+ result = sk;
+ hash = next_pseudo_random32(hash);
}
}
/*
@@ -431,9 +446,7 @@ begin:
*/
if (get_nulls_value(node) != slot2)
goto begin;
-
if (result) {
-exact_match:
if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
result = NULL;
else if (unlikely(compute_score2(result, net, saddr, sport,
@@ -457,7 +470,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
- int score, badness;
+ int score, badness, matches = 0, reuseport = 0;
+ u32 hash = 0;
rcu_read_lock();
if (hslot->count > 10) {
@@ -486,13 +500,24 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
}
begin:
result = NULL;
- badness = -1;
+ badness = 0;
sk_nulls_for_each_rcu(sk, node, &hslot->head) {
score = compute_score(sk, net, saddr, hnum, sport,
daddr, dport, dif);
if (score > badness) {
result = sk;
badness = score;
+ reuseport = sk->sk_reuseport;
+ if (reuseport) {
+ hash = inet_ehashfn(net, daddr, hnum,
+ saddr, htons(sport));
+ matches = 1;
+ }
+ } else if (score == badness && reuseport) {
+ matches++;
+ if (((u64)hash * matches) >> 32 == 0)
+ result = sk;
+ hash = next_pseudo_random32(hash);
}
}
/*
@@ -971,7 +996,7 @@ back_from_confirm:
sizeof(struct udphdr), &ipc, &rt,
msg->msg_flags);
err = PTR_ERR(skb);
- if (skb && !IS_ERR(skb))
+ if (!IS_ERR_OR_NULL(skb))
err = udp_send_skb(skb, fl4);
goto out;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-23 11:36:08 +0000