summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_frontend.c14
-rw-r--r--net/ipv4/fib_semantics.c3
-rw-r--r--net/ipv4/fib_trie.c2
-rw-r--r--net/ipv4/gre_offload.c3
-rw-r--r--net/ipv4/inet_connection_sock.c33
-rw-r--r--net/ipv4/inet_fragment.c6
-rw-r--r--net/ipv4/inet_hashtables.c39
-rw-r--r--net/ipv4/ip_fragment.c12
-rw-r--r--net/ipv4/ip_gre.c46
-rw-r--r--net/ipv4/ip_output.c9
-rw-r--r--net/ipv4/netfilter/Kconfig1
-rw-r--r--net/ipv4/netfilter/ipt_rpfilter.c4
-rw-r--r--net/ipv4/syncookies.c4
-rw-r--r--net/ipv4/tcp_dctcp.c2
-rw-r--r--net/ipv4/tcp_fastopen.c4
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_minisocks.c11
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/xfrm4_output.c2
-rw-r--r--net/ipv4/xfrm4_policy.c50
20 files changed, 174 insertions, 83 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index d7c2bb0c4f65..e786873c89f2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -867,9 +867,10 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
- fib_magic(RTM_NEWROUTE,
- dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
- prefix, ifa->ifa_prefixlen, prim);
+ if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
+ fib_magic(RTM_NEWROUTE,
+ dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+ prefix, ifa->ifa_prefixlen, prim);
/* Add network specific broadcasts, when it takes a sense */
if (ifa->ifa_prefixlen < 31) {
@@ -914,9 +915,10 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
}
} else if (!ipv4_is_zeronet(any) &&
(any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) {
- fib_magic(RTM_DELROUTE,
- dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
- any, ifa->ifa_prefixlen, prim);
+ if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
+ fib_magic(RTM_DELROUTE,
+ dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+ any, ifa->ifa_prefixlen, prim);
subnet = 1;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 42778d9d71e5..f30df0ee4f4d 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1564,7 +1564,8 @@ void fib_select_path(struct net *net, struct fib_result *res,
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
if (mp_hash < 0)
- mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr);
+ mp_hash = get_hash_from_flowi4(fl4) >> 1;
+
fib_select_multipath(res, mp_hash);
}
else
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 6c2af797f2f9..744e5936c10d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1569,7 +1569,7 @@ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key)
do {
/* record parent and next child index */
pn = n;
- cindex = key ? get_index(key, pn) : 0;
+ cindex = (key > pn->key) ? get_index(key, pn) : 0;
if (cindex >> pn->bits)
break;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 5aa46d4b44ef..5a8ee3282550 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP)))
+ SKB_GSO_IPIP |
+ SKB_GSO_SIT)))
goto out;
if (!skb->encapsulation)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8430bc8ccd58..1feb15f23de8 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -523,15 +523,15 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue,
struct request_sock *req)
{
struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo;
- spinlock_t *lock;
- bool found;
+ bool found = false;
- lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
-
- spin_lock(lock);
- found = __sk_nulls_del_node_init_rcu(req_to_sk(req));
- spin_unlock(lock);
+ if (sk_hashed(req_to_sk(req))) {
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash);
+ spin_lock(lock);
+ found = __sk_nulls_del_node_init_rcu(req_to_sk(req));
+ spin_unlock(lock);
+ }
if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
reqsk_put(req);
return found;
@@ -811,6 +811,25 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
+struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
+ struct request_sock *req, bool own_req)
+{
+ if (own_req) {
+ inet_csk_reqsk_queue_drop(sk, req);
+ reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+ inet_csk_reqsk_queue_add(sk, req, child);
+ /* Warning: caller must not call reqsk_put(req);
+ * child stole last reference on it.
+ */
+ return child;
+ }
+ /* Too bad, another child took ownership of the request, undo. */
+ bh_unlock_sock(child);
+ sock_put(child);
+ return NULL;
+}
+EXPORT_SYMBOL(inet_csk_complete_hashdance);
+
/*
* This routine closes sockets which have been at least partially
* opened, but not yet accepted.
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index d0a7c0319e3d..fe144dae7372 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -209,12 +209,6 @@ int inet_frags_init(struct inet_frags *f)
}
EXPORT_SYMBOL(inet_frags_init);
-void inet_frags_init_net(struct netns_frags *nf)
-{
- init_frag_mem_limit(nf);
-}
-EXPORT_SYMBOL(inet_frags_init_net);
-
void inet_frags_fini(struct inet_frags *f)
{
cancel_work_sync(&f->frags_work);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 958728a22001..ccc5980797fc 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -407,13 +407,13 @@ static u32 inet_sk_port_offset(const struct sock *sk)
/* insert a socket into ehash, and eventually remove another one
* (The another one can be a SYN_RECV or TIMEWAIT
*/
-int inet_ehash_insert(struct sock *sk, struct sock *osk)
+bool inet_ehash_insert(struct sock *sk, struct sock *osk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
struct inet_ehash_bucket *head;
spinlock_t *lock;
- int ret = 0;
+ bool ret = true;
WARN_ON_ONCE(!sk_unhashed(sk));
@@ -423,30 +423,41 @@ int inet_ehash_insert(struct sock *sk, struct sock *osk)
lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
spin_lock(lock);
- __sk_nulls_add_node_rcu(sk, list);
if (osk) {
- WARN_ON(sk->sk_hash != osk->sk_hash);
- sk_nulls_del_node_init_rcu(osk);
+ WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
+ ret = sk_nulls_del_node_init_rcu(osk);
}
+ if (ret)
+ __sk_nulls_add_node_rcu(sk, list);
spin_unlock(lock);
return ret;
}
-void __inet_hash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
{
- inet_ehash_insert(sk, osk);
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ bool ok = inet_ehash_insert(sk, osk);
+
+ if (ok) {
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ } else {
+ percpu_counter_inc(sk->sk_prot->orphan_count);
+ sk->sk_state = TCP_CLOSE;
+ sock_set_flag(sk, SOCK_DEAD);
+ inet_csk_destroy_sock(sk);
+ }
+ return ok;
}
-EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
+EXPORT_SYMBOL_GPL(inet_ehash_nolisten);
void __inet_hash(struct sock *sk, struct sock *osk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct inet_listen_hashbucket *ilb;
- if (sk->sk_state != TCP_LISTEN)
- return __inet_hash_nolisten(sk, osk);
-
+ if (sk->sk_state != TCP_LISTEN) {
+ inet_ehash_nolisten(sk, osk);
+ return;
+ }
WARN_ON(!sk_unhashed(sk));
ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
@@ -567,7 +578,7 @@ ok:
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- __inet_hash_nolisten(sk, (struct sock *)tw);
+ inet_ehash_nolisten(sk, (struct sock *)tw);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
@@ -584,7 +595,7 @@ ok:
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- __inet_hash_nolisten(sk, NULL);
+ inet_ehash_nolisten(sk, NULL);
spin_unlock_bh(&head->lock);
return 0;
} else {
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 5482745d5d68..1fe55ae81781 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -839,6 +839,8 @@ static void __init ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
+ int res;
+
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
@@ -862,9 +864,13 @@ static int __net_init ipv4_frags_init_net(struct net *net)
*/
net->ipv4.frags.timeout = IP_FRAG_TIME;
- inet_frags_init_net(&net->ipv4.frags);
-
- return ip4_frags_ns_ctl_register(net);
+ res = inet_frags_init_net(&net->ipv4.frags);
+ if (res)
+ return res;
+ res = ip4_frags_ns_ctl_register(net);
+ if (res)
+ inet_frags_uninit_net(&net->ipv4.frags);
+ return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index bd0679d90519..614521437e30 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -498,10 +498,26 @@ static struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
+static struct rtable *gre_get_rt(struct sk_buff *skb,
+ struct net_device *dev,
+ struct flowi4 *fl,
+ const struct ip_tunnel_key *key)
+{
+ struct net *net = dev_net(dev);
+
+ memset(fl, 0, sizeof(*fl));
+ fl->daddr = key->u.ipv4.dst;
+ fl->saddr = key->u.ipv4.src;
+ fl->flowi4_tos = RT_TOS(key->tos);
+ fl->flowi4_mark = skb->mark;
+ fl->flowi4_proto = IPPROTO_GRE;
+
+ return ip_route_output_key(net, fl);
+}
+
static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel_info *tun_info;
- struct net *net = dev_net(dev);
const struct ip_tunnel_key *key;
struct flowi4 fl;
struct rtable *rt;
@@ -516,14 +532,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
goto err_free_skb;
key = &tun_info->key;
- memset(&fl, 0, sizeof(fl));
- fl.daddr = key->u.ipv4.dst;
- fl.saddr = key->u.ipv4.src;
- fl.flowi4_tos = RT_TOS(key->tos);
- fl.flowi4_mark = skb->mark;
- fl.flowi4_proto = IPPROTO_GRE;
-
- rt = ip_route_output_key(net, &fl);
+ rt = gre_get_rt(skb, dev, &fl, key);
if (IS_ERR(rt))
goto err_free_skb;
@@ -566,6 +575,24 @@ err_free_skb:
dev->stats.tx_dropped++;
}
+static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ip_tunnel_info *info = skb_tunnel_info(skb);
+ struct rtable *rt;
+ struct flowi4 fl4;
+
+ if (ip_tunnel_info_af(info) != AF_INET)
+ return -EINVAL;
+
+ rt = gre_get_rt(skb, dev, &fl4, &info->key);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+
+ ip_rt_put(rt);
+ info->key.u.ipv4.src = fl4.saddr;
+ return 0;
+}
+
static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
struct net_device *dev)
{
@@ -1023,6 +1050,7 @@ static const struct net_device_ops gre_tap_netdev_ops = {
.ndo_change_mtu = ip_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
+ .ndo_fill_metadata_dst = gre_fill_metadata_dst,
};
static void ipgre_tap_setup(struct net_device *dev)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 50e29737b584..4233cbe47052 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -533,6 +533,11 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
dev = rt->dst.dev;
+ /* for offloaded checksums cleanup checksum before fragmentation */
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto fail;
+
/*
* Point into the IP datagram header.
*/
@@ -657,9 +662,6 @@ slow_path_clean:
}
slow_path:
- /* for offloaded checksums cleanup checksum before fragmentation */
- if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb))
- goto fail;
iph = ip_hdr(skb);
left = skb->len - hlen; /* Space per frame */
@@ -911,6 +913,7 @@ static int __ip_append_data(struct sock *sk,
if (transhdrlen &&
length + fragheaderlen <= mtu &&
rt->dst.dev->features & NETIF_F_V4_CSUM &&
+ !(flags & MSG_MORE) &&
!exthdrlen)
csummode = CHECKSUM_PARTIAL;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 690d27d3f2f9..a35584176535 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -75,6 +75,7 @@ endif # NF_TABLES
config NF_DUP_IPV4
tristate "Netfilter IPv4 packet duplication to alternate destination"
+ depends on !NF_CONNTRACK || NF_CONNTRACK
help
This option enables the nf_dup_ipv4 core, which duplicates an IPv4
packet to be rerouted to another destination.
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 74dd6671b66d..78cc64eddfc1 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -60,9 +60,7 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4,
if (FIB_RES_DEV(res) == dev)
dev_match = true;
#endif
- if (dev_match || flags & XT_RPFILTER_LOOSE)
- return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST;
- return dev_match;
+ return dev_match || flags & XT_RPFILTER_LOOSE;
}
static bool rpfilter_is_local(const struct sk_buff *skb)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 4c0892badb8b..4cbe9f0a4281 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -221,8 +221,10 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
+ bool own_req;
- child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
+ child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
+ NULL, &own_req);
if (child) {
atomic_set(&req->rsk_refcnt, 1);
sock_rps_save_rxhash(child, skb);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 7092a61c4dc8..7e538f71f5fb 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -209,7 +209,7 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
/* alpha = (1 - g) * alpha + g * F */
- alpha -= alpha >> dctcp_shift_g;
+ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
if (bytes_ecn) {
/* If dctcp_shift_g == 1, a 32bit value would overflow
* after 8 Mbytes.
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 93396bf7b475..55be6ac70cff 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -133,12 +133,14 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
u32 end_seq;
+ bool own_req;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
- child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+ child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
+ NULL, &own_req);
if (!child)
return NULL;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30dd45c1f568..1c2648bbac4b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1247,7 +1247,9 @@ EXPORT_SYMBOL(tcp_v4_conn_request);
*/
struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
- struct dst_entry *dst)
+ struct dst_entry *dst,
+ struct request_sock *req_unhash,
+ bool *own_req)
{
struct inet_request_sock *ireq;
struct inet_sock *newinet;
@@ -1323,7 +1325,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- __inet_hash_nolisten(newsk, NULL);
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
return newsk;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1fd5d413a664..3575dd1e5b67 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -580,6 +580,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
bool paws_reject = false;
+ bool own_req;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
@@ -767,18 +768,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* ESTABLISHED STATE. If it will be dropped after
* socket is created, wait for troubles.
*/
- child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+ child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
+ req, &own_req);
if (!child)
goto listen_overflow;
sock_rps_save_rxhash(child, skb);
tcp_synack_rtt_meas(child, req);
- inet_csk_reqsk_queue_drop(sk, req);
- inet_csk_reqsk_queue_add(sk, req, child);
- /* Warning: caller must not call reqsk_put(req);
- * child stole last reference on it.
- */
- return child;
+ return inet_csk_complete_hashdance(sk, child, req, own_req);
listen_overflow:
if (!sysctl_tcp_abort_on_overflow) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f6f7f9b4901b..cb7ca569052c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2963,9 +2963,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
skb_reserve(skb, MAX_TCP_HEADER);
if (attach_req) {
- skb->destructor = sock_edemux;
- sock_hold(req_to_sk(req));
- skb->sk = req_to_sk(req);
+ skb_set_owner_w(skb, req_to_sk(req));
} else {
/* sk is a const pointer, because we want to express multiple
* cpu might call us concurrently.
@@ -3410,7 +3408,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
*/
tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
skb_mstamp_get(&skb->skb_mstamp);
- NET_INC_STATS_BH(sock_net(sk), mib);
+ NET_INC_STATS(sock_net(sk), mib);
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 9f298d0dc9a1..7ee6518afa86 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -30,6 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
mtu = dst_mtu(skb_dst(skb));
if (skb->len > mtu) {
+ skb->protocol = htons(ETH_P_IP);
+
if (skb->sk)
xfrm_local_error(skb, mtu);
else
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index f2606b9056bb..1e0c3c835a63 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -127,7 +127,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
case IPPROTO_DCCP:
if (xprth + 4 < skb->data ||
pskb_may_pull(skb, xprth + 4 - skb->data)) {
- __be16 *ports = (__be16 *)xprth;
+ __be16 *ports;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ ports = (__be16 *)xprth;
fl4->fl4_sport = ports[!!reverse];
fl4->fl4_dport = ports[!reverse];
@@ -135,8 +138,12 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
break;
case IPPROTO_ICMP:
- if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
- u8 *icmp = xprth;
+ if (xprth + 2 < skb->data ||
+ pskb_may_pull(skb, xprth + 2 - skb->data)) {
+ u8 *icmp;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ icmp = xprth;
fl4->fl4_icmp_type = icmp[0];
fl4->fl4_icmp_code = icmp[1];
@@ -144,33 +151,50 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
break;
case IPPROTO_ESP:
- if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
- __be32 *ehdr = (__be32 *)xprth;
+ if (xprth + 4 < skb->data ||
+ pskb_may_pull(skb, xprth + 4 - skb->data)) {
+ __be32 *ehdr;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ ehdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ehdr[0];
}
break;
case IPPROTO_AH:
- if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
- __be32 *ah_hdr = (__be32 *)xprth;
+ if (xprth + 8 < skb->data ||
+ pskb_may_pull(skb, xprth + 8 - skb->data)) {
+ __be32 *ah_hdr;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ ah_hdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ah_hdr[1];
}
break;
case IPPROTO_COMP:
- if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
- __be16 *ipcomp_hdr = (__be16 *)xprth;
+ if (xprth + 4 < skb->data ||
+ pskb_may_pull(skb, xprth + 4 - skb->data)) {
+ __be16 *ipcomp_hdr;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ ipcomp_hdr = (__be16 *)xprth;
fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
}
break;
case IPPROTO_GRE:
- if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
- __be16 *greflags = (__be16 *)xprth;
- __be32 *gre_hdr = (__be32 *)xprth;
+ if (xprth + 12 < skb->data ||
+ pskb_may_pull(skb, xprth + 12 - skb->data)) {
+ __be16 *greflags;
+ __be32 *gre_hdr;
+
+ xprth = skb_network_header(skb) + iph->ihl * 4;
+ greflags = (__be16 *)xprth;
+ gre_hdr = (__be32 *)xprth;
if (greflags[0] & GRE_KEY) {
if (greflags[0] & GRE_CSUM)
@@ -244,7 +268,7 @@ static struct dst_ops xfrm4_dst_ops = {
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
- .gc_thresh = 32768,
+ .gc_thresh = INT_MAX,
};
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-01 18:17:52 +0300