summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-11-24 22:19:20 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-11-24 22:19:20 +0300
commit08ad43d554bacb9769c6a69d5f771f02f5ba411c (patch)
treeb0e5a5d8ffdf637963ba1c382abbfc343958acdf /net
parentcd89db60e22824b82f9458753fa6cb770cca8bde (diff)
parent661e5ebbafd26d9d2e3c749f5cf591e55c7364f5 (diff)
downloadlinux-08ad43d554bacb9769c6a69d5f771f02f5ba411c.tar.xz
Merge tag 'net-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni: "Including fixes from rxrpc, netfilter and xfrm. Current release - regressions: - dccp/tcp: fix bhash2 issues related to WARN_ON() in inet_csk_get_port() - l2tp: don't sleep and disable BH under writer-side sk_callback_lock - eth: ice: fix handling of burst tx timestamps Current release - new code bugs: - xfrm: squelch kernel warning in case XFRM encap type is not available - eth: mlx5e: fix possible race condition in macsec extended packet number update routine Previous releases - regressions: - neigh: decrement the family specific qlen - netfilter: fix ipset regression - rxrpc: fix race between conn bundle lookup and bundle removal [ZDI-CAN-15975] - eth: iavf: do not restart tx queues after reset task failure - eth: nfp: add port from netdev validation for EEPROM access - eth: mtk_eth_soc: fix potential memory leak in mtk_rx_alloc() Previous releases - always broken: - tipc: set con sock in tipc_conn_alloc - nfc: - fix potential memory leaks - fix incorrect sizing calculations in EVT_TRANSACTION - eth: octeontx2-af: fix pci device refcount leak - eth: bonding: fix ICMPv6 header handling when receiving IPv6 messages - eth: prestera: add missing unregister_netdev() in prestera_port_create() - eth: tsnep: fix rotten packets Misc: - usb: qmi_wwan: add support for LARA-L6" * tag 'net-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (95 commits) net: thunderx: Fix the ACPI memory leak octeontx2-af: Fix reference count issue in rvu_sdp_init() net: altera_tse: release phylink resources in tse_shutdown() virtio_net: Fix probe failed when modprobe virtio_net net: wwan: t7xx: Fix the ACPI memory leak octeontx2-pf: Add check for devm_kcalloc net: enetc: preserve TX ring priority across reconfiguration net: marvell: prestera: add missing unregister_netdev() in prestera_port_create() nfc: st-nci: fix incorrect sizing calculations in EVT_TRANSACTION nfc: st-nci: fix memory leaks in EVT_TRANSACTION nfc: st-nci: fix incorrect validating logic in EVT_TRANSACTION Documentation: networking: Update generic_netlink_howto URL net/cdc_ncm: Fix multicast RX support for CDC NCM devices with ZLP net: usb: qmi_wwan: add u-blox 0x1342 composition l2tp: Don't sleep and disable BH under writer-side sk_callback_lock net: dm9051: Fix missing dev_kfree_skb() in dm9051_loop_rx() arcnet: fix potential memory leak in com20020_probe() ipv4: Fix error return code in fib_table_insert() net: ethernet: mtk_eth_soc: fix memory leak in error path net: ethernet: mtk_eth_soc: fix resource leak in error path ...
Diffstat (limited to 'net')
-rw-r--r--net/core/flow_dissector.c2
-rw-r--r--net/core/lwtunnel.c4
-rw-r--r--net/core/neighbour.c58
-rw-r--r--net/dccp/ipv4.c23
-rw-r--r--net/dccp/ipv6.c24
-rw-r--r--net/dccp/proto.c3
-rw-r--r--net/ipv4/af_inet.c11
-rw-r--r--net/ipv4/esp4_offload.c3
-rw-r--r--net/ipv4/fib_trie.c6
-rw-r--r--net/ipv4/inet_hashtables.c84
-rw-r--r--net/ipv4/ip_input.c5
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c4
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_ipv4.c21
-rw-r--r--net/ipv6/esp6_offload.c3
-rw-r--r--net/ipv6/tcp_ipv6.c20
-rw-r--r--net/ipv6/xfrm6_policy.c6
-rw-r--r--net/key/af_key.c34
-rw-r--r--net/l2tp/l2tp_core.c17
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h2
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c8
-rw-r--r--net/netfilter/nf_conntrack_core.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c24
-rw-r--r--net/netfilter/nf_conntrack_standalone.c2
-rw-r--r--net/netfilter/nf_flow_table_offload.c4
-rw-r--r--net/netfilter/nf_tables_api.c6
-rw-r--r--net/netfilter/nft_ct.c6
-rw-r--r--net/netfilter/xt_connmark.c18
-rw-r--r--net/nfc/nci/core.c2
-rw-r--r--net/nfc/nci/data.c4
-rw-r--r--net/openvswitch/conntrack.c8
-rw-r--r--net/rxrpc/ar-internal.h1
-rw-r--r--net/rxrpc/conn_client.c38
-rw-r--r--net/sched/Kconfig2
-rw-r--r--net/sched/act_connmark.c4
-rw-r--r--net/sched/act_ct.c8
-rw-r--r--net/sched/act_ctinfo.c6
-rw-r--r--net/tipc/discover.c5
-rw-r--r--net/tipc/topsrv.c20
-rw-r--r--net/xfrm/xfrm_device.c15
-rw-r--r--net/xfrm/xfrm_replay.c2
41 files changed, 295 insertions, 223 deletions
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 25cd35f5922e..007730412947 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -296,7 +296,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb,
key->ct_zone = ct->zone.id;
#endif
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
- key->ct_mark = ct->mark;
+ key->ct_mark = READ_ONCE(ct->mark);
#endif
cl = nf_ct_labels_find(ct);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6fac2f0ef074..711cd3b4347a 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -48,9 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
return "RPL";
case LWTUNNEL_ENCAP_IOAM6:
return "IOAM6";
+ case LWTUNNEL_ENCAP_XFRM:
+ /* module autoload not supported for encap type */
+ return NULL;
case LWTUNNEL_ENCAP_IP6:
case LWTUNNEL_ENCAP_IP:
- case LWTUNNEL_ENCAP_XFRM:
case LWTUNNEL_ENCAP_NONE:
case __LWTUNNEL_ENCAP_MAX:
/* should not have got here */
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a77a85e357e0..952a54763358 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -307,7 +307,31 @@ static int neigh_del_timer(struct neighbour *n)
return 0;
}
-static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
+static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev,
+ int family)
+{
+ switch (family) {
+ case AF_INET:
+ return __in_dev_arp_parms_get_rcu(dev);
+ case AF_INET6:
+ return __in6_dev_nd_parms_get_rcu(dev);
+ }
+ return NULL;
+}
+
+static void neigh_parms_qlen_dec(struct net_device *dev, int family)
+{
+ struct neigh_parms *p;
+
+ rcu_read_lock();
+ p = neigh_get_dev_parms_rcu(dev, family);
+ if (p)
+ p->qlen--;
+ rcu_read_unlock();
+}
+
+static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net,
+ int family)
{
struct sk_buff_head tmp;
unsigned long flags;
@@ -321,13 +345,7 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
struct net_device *dev = skb->dev;
if (net == NULL || net_eq(dev_net(dev), net)) {
- struct in_device *in_dev;
-
- rcu_read_lock();
- in_dev = __in_dev_get_rcu(dev);
- if (in_dev)
- in_dev->arp_parms->qlen--;
- rcu_read_unlock();
+ neigh_parms_qlen_dec(dev, family);
__skb_unlink(skb, list);
__skb_queue_tail(&tmp, skb);
}
@@ -409,7 +427,8 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev, skip_perm);
pneigh_ifdown_and_unlock(tbl, dev);
- pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL);
+ pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL,
+ tbl->family);
if (skb_queue_empty_lockless(&tbl->proxy_queue))
del_timer_sync(&tbl->proxy_timer);
return 0;
@@ -1621,13 +1640,8 @@ static void neigh_proxy_process(struct timer_list *t)
if (tdif <= 0) {
struct net_device *dev = skb->dev;
- struct in_device *in_dev;
- rcu_read_lock();
- in_dev = __in_dev_get_rcu(dev);
- if (in_dev)
- in_dev->arp_parms->qlen--;
- rcu_read_unlock();
+ neigh_parms_qlen_dec(dev, tbl->family);
__skb_unlink(skb, &tbl->proxy_queue);
if (tbl->proxy_redo && netif_running(dev)) {
@@ -1821,7 +1835,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
cancel_delayed_work_sync(&tbl->managed_work);
cancel_delayed_work_sync(&tbl->gc_work);
del_timer_sync(&tbl->proxy_timer);
- pneigh_queue_purge(&tbl->proxy_queue, NULL);
+ pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family);
neigh_ifdown(tbl, NULL);
if (atomic_read(&tbl->entries))
pr_crit("neighbour leakage\n");
@@ -3539,18 +3553,6 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write,
return ret;
}
-static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev,
- int family)
-{
- switch (family) {
- case AF_INET:
- return __in_dev_arp_parms_get_rcu(dev);
- case AF_INET6:
- return __in6_dev_nd_parms_get_rcu(dev);
- }
- return NULL;
-}
-
static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p,
int index)
{
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 713b7b8dad7e..b780827f5e0a 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly;
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
- struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
- __be32 daddr, nexthop, prev_sk_rcv_saddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
+ __be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
@@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
daddr = fl4->daddr;
if (inet->inet_saddr == 0) {
- if (inet_csk(sk)->icsk_bind2_hash) {
- prev_addr_hashbucket =
- inet_bhashfn_portaddr(&dccp_hashinfo, sk,
- sock_net(sk),
- inet->inet_num);
- prev_sk_rcv_saddr = sk->sk_rcv_saddr;
- }
- inet->inet_saddr = fl4->saddr;
- }
-
- sk_rcv_saddr_set(sk, inet->inet_saddr);
-
- if (prev_addr_hashbucket) {
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+ err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET);
if (err) {
- inet->inet_saddr = 0;
- sk_rcv_saddr_set(sk, prev_sk_rcv_saddr);
ip_rt_put(rt);
return err;
}
+ } else {
+ sk_rcv_saddr_set(sk, inet->inet_saddr);
}
inet->inet_dport = usin->sin_port;
@@ -157,6 +143,7 @@ failure:
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
+ inet_bhash2_reset_saddr(sk);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index e57b43006074..602f3432d80b 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
}
if (saddr == NULL) {
- struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
- struct in6_addr prev_v6_rcv_saddr;
-
- if (icsk->icsk_bind2_hash) {
- prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo,
- sk, sock_net(sk),
- inet->inet_num);
- prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
- }
-
saddr = &fl6.saddr;
- sk->sk_v6_rcv_saddr = *saddr;
-
- if (prev_addr_hashbucket) {
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
- if (err) {
- sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr;
- goto failure;
- }
- }
+
+ err = inet_bhash2_update_saddr(sk, saddr, AF_INET6);
+ if (err)
+ goto failure;
}
/* set the source address */
@@ -985,6 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
+ inet_bhash2_reset_saddr(sk);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index c548ca3e9b0e..85e35c5e8890 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -279,8 +279,7 @@ int dccp_disconnect(struct sock *sk, int flags)
inet->inet_dport = 0;
- if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
- inet_reset_saddr(sk);
+ inet_bhash2_reset_saddr(sk);
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4728087c42a5..0da679411330 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw);
static int inet_sk_reselect_saddr(struct sock *sk)
{
- struct inet_bind_hashbucket *prev_addr_hashbucket;
struct inet_sock *inet = inet_sk(sk);
__be32 old_saddr = inet->inet_saddr;
__be32 daddr = inet->inet_daddr;
@@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk)
return 0;
}
- prev_addr_hashbucket =
- inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk,
- sock_net(sk), inet->inet_num);
-
- inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
-
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+ err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET);
if (err) {
- inet->inet_saddr = old_saddr;
- inet->inet_rcv_saddr = old_saddr;
ip_rt_put(rt);
return err;
}
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 170152772d33..3969fa805679 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_
xo->seq.low += skb_shinfo(skb)->gso_segs;
}
+ if (xo->seq.low < seq)
+ xo->seq.hi++;
+
esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
ip_hdr(skb)->tot_len = htons(skb->len);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 452ff177e4da..74d403dbd2b4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -126,7 +126,7 @@ struct key_vector {
/* This list pointer if valid if (pos | bits) == 0 (LEAF) */
struct hlist_head leaf;
/* This array is valid if (pos | bits) > 0 (TNODE) */
- struct key_vector __rcu *tnode[0];
+ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode);
};
};
@@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
/* The alias was already inserted, so the node must exist. */
l = l ? l : fib_find_node(t, &tp, key);
- if (WARN_ON_ONCE(!l))
+ if (WARN_ON_ONCE(!l)) {
+ err = -ENOENT;
goto out_free_new_fa;
+ }
if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
new_fa) {
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 033bf3c2538f..3cec471a2cd2 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
}
-int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk)
+static void inet_update_saddr(struct sock *sk, void *saddr, int family)
+{
+ if (family == AF_INET) {
+ inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
+ sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else {
+ sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
+ }
+#endif
+}
+
+static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
{
struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+ struct inet_bind_hashbucket *head, *head2;
struct inet_bind2_bucket *tb2, *new_tb2;
int l3mdev = inet_sk_bound_l3mdev(sk);
- struct inet_bind_hashbucket *head2;
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
+ int bhash;
+
+ if (!inet_csk(sk)->icsk_bind2_hash) {
+ /* Not bind()ed before. */
+ if (reset)
+ inet_reset_saddr(sk);
+ else
+ inet_update_saddr(sk, saddr, family);
+
+ return 0;
+ }
/* Allocate a bind2 bucket ahead of time to avoid permanently putting
* the bhash2 table in an inconsistent state if a new tb2 bucket
* allocation fails.
*/
new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
- if (!new_tb2)
+ if (!new_tb2) {
+ if (reset) {
+ /* The (INADDR_ANY, port) bucket might have already
+ * been freed, then we cannot fixup icsk_bind2_hash,
+ * so we give up and unlink sk from bhash/bhash2 not
+ * to leave inconsistency in bhash2.
+ */
+ inet_put_port(sk);
+ inet_reset_saddr(sk);
+ }
+
return -ENOMEM;
+ }
+ bhash = inet_bhashfn(net, port, hinfo->bhash_size);
+ head = &hinfo->bhash[bhash];
head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
- if (prev_saddr) {
- spin_lock_bh(&prev_saddr->lock);
- __sk_del_bind2_node(sk);
- inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
- inet_csk(sk)->icsk_bind2_hash);
- spin_unlock_bh(&prev_saddr->lock);
- }
+ /* If we change saddr locklessly, another thread
+ * iterating over bhash might see corrupted address.
+ */
+ spin_lock_bh(&head->lock);
- spin_lock_bh(&head2->lock);
+ spin_lock(&head2->lock);
+ __sk_del_bind2_node(sk);
+ inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
+ spin_unlock(&head2->lock);
+
+ if (reset)
+ inet_reset_saddr(sk);
+ else
+ inet_update_saddr(sk, saddr, family);
+
+ head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
+
+ spin_lock(&head2->lock);
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = new_tb2;
@@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc
}
sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
- spin_unlock_bh(&head2->lock);
+ spin_unlock(&head2->lock);
+
+ spin_unlock_bh(&head->lock);
if (tb2 != new_tb2)
kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);
return 0;
}
+
+int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+{
+ return __inet_bhash2_update_saddr(sk, saddr, family, false);
+}
EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
+void inet_bhash2_reset_saddr(struct sock *sk)
+{
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ __inet_bhash2_update_saddr(sk, NULL, 0, true);
+}
+EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+
/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
* Note that we use 32bit integers (vs RFC 'short integers')
* because 2^16 is not a multiple of num_ephemeral and this
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1b512390b3cf..e880ce77322a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
iph->tos, dev);
if (unlikely(err))
goto drop_error;
+ } else {
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f8e176c77d1c..b3cc416ed292 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
switch (ctinfo) {
case IP_CT_NEW:
- ct->mark = hash;
+ WRITE_ONCE(ct->mark, hash);
break;
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
@@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
#ifdef DEBUG
nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
#endif
- pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
+ pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark));
if (!clusterip_responsible(cipinfo->config, hash)) {
pr_debug("not responsible\n");
return NF_DROP;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 54836a6b81d6..4f2205756cfe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags)
inet->inet_dport = 0;
- if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
- inet_reset_saddr(sk);
+ inet_bhash2_reset_saddr(sk);
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 87d440f47a70..da46357f501b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_timewait_death_row *tcp_death_row;
- __be32 daddr, nexthop, prev_sk_rcv_saddr;
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct ip_options_rcu *inet_opt;
struct net *net = sock_net(sk);
__be16 orig_sport, orig_dport;
+ __be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
@@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (!inet->inet_saddr) {
- if (inet_csk(sk)->icsk_bind2_hash) {
- prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
- sk, net, inet->inet_num);
- prev_sk_rcv_saddr = sk->sk_rcv_saddr;
- }
- inet->inet_saddr = fl4->saddr;
- }
-
- sk_rcv_saddr_set(sk, inet->inet_saddr);
-
- if (prev_addr_hashbucket) {
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+ err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET);
if (err) {
- inet->inet_saddr = 0;
- sk_rcv_saddr_set(sk, prev_sk_rcv_saddr);
ip_rt_put(rt);
return err;
}
+ } else {
+ sk_rcv_saddr_set(sk, inet->inet_saddr);
}
if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
@@ -343,6 +331,7 @@ failure:
* if necessary.
*/
tcp_set_state(sk, TCP_CLOSE);
+ inet_bhash2_reset_saddr(sk);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 79d43548279c..242f4295940e 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -346,6 +346,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features
xo->seq.low += skb_shinfo(skb)->gso_segs;
}
+ if (xo->seq.low < seq)
+ xo->seq.hi++;
+
esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
len = skb->len - sizeof(struct ipv6hdr);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2a3f9296df1e..f0548dbcabd2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (!saddr) {
- struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
- struct in6_addr prev_v6_rcv_saddr;
-
- if (icsk->icsk_bind2_hash) {
- prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
- sk, net, inet->inet_num);
- prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
- }
saddr = &fl6.saddr;
- sk->sk_v6_rcv_saddr = *saddr;
- if (prev_addr_hashbucket) {
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
- if (err) {
- sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr;
- goto failure;
- }
- }
+ err = inet_bhash2_update_saddr(sk, saddr, AF_INET6);
+ if (err)
+ goto failure;
}
/* set the source address */
@@ -359,6 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
late_failure:
tcp_set_state(sk, TCP_CLOSE);
+ inet_bhash2_reset_saddr(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 4a4b0e49ec92..ea435eba3053 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -287,9 +287,13 @@ int __init xfrm6_init(void)
if (ret)
goto out_state;
- register_pernet_subsys(&xfrm6_net_ops);
+ ret = register_pernet_subsys(&xfrm6_net_ops);
+ if (ret)
+ goto out_protocol;
out:
return ret;
+out_protocol:
+ xfrm6_protocol_fini();
out_state:
xfrm6_state_fini();
out_policy:
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c85df5b958d2..95edcbedf6ef 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
break;
if (!aalg->pfkey_supported)
continue;
- if (aalg_tmpl_set(t, aalg) && aalg->available)
+ if (aalg_tmpl_set(t, aalg))
sz += sizeof(struct sadb_comb);
}
return sz + sizeof(struct sadb_prop);
@@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
if (!ealg->pfkey_supported)
continue;
- if (!(ealg_tmpl_set(t, ealg) && ealg->available))
+ if (!(ealg_tmpl_set(t, ealg)))
continue;
for (k = 1; ; k++) {
@@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
if (!aalg->pfkey_supported)
continue;
- if (aalg_tmpl_set(t, aalg) && aalg->available)
+ if (aalg_tmpl_set(t, aalg))
sz += sizeof(struct sadb_comb);
}
}
return sz + sizeof(struct sadb_prop);
}
-static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
+static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
{
struct sadb_prop *p;
+ int sz = 0;
int i;
p = skb_put(skb, sizeof(struct sadb_prop));
@@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
c->sadb_comb_soft_addtime = 20*60*60;
c->sadb_comb_hard_usetime = 8*60*60;
c->sadb_comb_soft_usetime = 7*60*60;
+ sz += sizeof(*c);
}
}
+
+ return sz + sizeof(*p);
}
-static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
+static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
{
struct sadb_prop *p;
+ int sz = 0;
int i, k;
p = skb_put(skb, sizeof(struct sadb_prop));
@@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t)
c->sadb_comb_soft_addtime = 20*60*60;
c->sadb_comb_hard_usetime = 8*60*60;
c->sadb_comb_soft_usetime = 7*60*60;
+ sz += sizeof(*c);
}
}
+
+ return sz + sizeof(*p);
}
static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c)
@@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
struct sadb_x_sec_ctx *sec_ctx;
struct xfrm_sec_ctx *xfrm_ctx;
int ctx_size = 0;
+ int alg_size = 0;
sockaddr_size = pfkey_sockaddr_size(x->props.family);
if (!sockaddr_size)
@@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
sizeof(struct sadb_x_policy);
if (x->id.proto == IPPROTO_AH)
- size += count_ah_combs(t);
+ alg_size = count_ah_combs(t);
else if (x->id.proto == IPPROTO_ESP)
- size += count_esp_combs(t);
+ alg_size = count_esp_combs(t);
if ((xfrm_ctx = x->security)) {
ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len);
size += sizeof(struct sadb_x_sec_ctx) + ctx_size;
}
- skb = alloc_skb(size + 16, GFP_ATOMIC);
+ skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC);
if (skb == NULL)
return -ENOMEM;
@@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
pol->sadb_x_policy_priority = xp->priority;
/* Set sadb_comb's. */
+ alg_size = 0;
if (x->id.proto == IPPROTO_AH)
- dump_ah_combs(skb, t);
+ alg_size = dump_ah_combs(skb, t);
else if (x->id.proto == IPPROTO_ESP)
- dump_esp_combs(skb, t);
+ alg_size = dump_esp_combs(skb, t);
+
+ hdr->sadb_msg_len += alg_size / 8;
/* security context */
if (xfrm_ctx) {
@@ -3382,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
hdr->sadb_msg_len = size / sizeof(uint64_t);
hdr->sadb_msg_errno = 0;
hdr->sadb_msg_reserved = 0;
- hdr->sadb_msg_seq = x->km.seq = get_acqseq();
+ hdr->sadb_msg_seq = x->km.seq;
hdr->sadb_msg_pid = 0;
/* SA */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 754fdda8a5f5..9a1415fe3fa7 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1474,11 +1474,12 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
}
sk = sock->sk;
- write_lock(&sk->sk_callback_lock);
-
+ write_lock_bh(&sk->sk_callback_lock);
ret = l2tp_validate_socket(sk, net, tunnel->encap);
if (ret < 0)
- goto err_sock;
+ goto err_inval_sock;
+ rcu_assign_sk_user_data(sk, tunnel);
+ write_unlock_bh(&sk->sk_callback_lock);
tunnel->l2tp_net = net;
pn = l2tp_pernet(net);
@@ -1507,8 +1508,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
};
setup_udp_tunnel_sock(net, sock, &udp_cfg);
- } else {
- rcu_assign_sk_user_data(sk, tunnel);
}
tunnel->old_sk_destruct = sk->sk_destruct;
@@ -1522,16 +1521,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
if (tunnel->fd >= 0)
sockfd_put(sock);
- write_unlock(&sk->sk_callback_lock);
return 0;
err_sock:
+ write_lock_bh(&sk->sk_callback_lock);
+ rcu_assign_sk_user_data(sk, NULL);
+err_inval_sock:
+ write_unlock_bh(&sk->sk_callback_lock);
+
if (tunnel->fd < 0)
sock_release(sock);
else
sockfd_put(sock);
-
- write_unlock(&sk->sk_callback_lock);
err:
return ret;
}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 3adc291d9ce1..7499192af586 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -916,7 +916,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
#ifdef IP_SET_HASH_WITH_MULTI
if (h->bucketsize >= AHASH_MAX_TUNED)
goto set_full;
- else if (h->bucketsize < multi)
+ else if (h->bucketsize <= multi)
h->bucketsize += AHASH_INIT_SIZE;
#endif
if (n->size >= AHASH_MAX(h)) {
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index dd30c03d5a23..75d556d71652 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -151,18 +151,16 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
return -ERANGE;
- if (retried) {
+ if (retried)
ip = ntohl(h->next.ip);
- e.ip = htonl(ip);
- }
for (; ip <= ip_to;) {
+ e.ip = htonl(ip);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
ip += hosts;
- e.ip = htonl(ip);
- if (e.ip == 0)
+ if (ip == 0)
return 0;
ret = 0;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f97bda06d2a9..2692139ce417 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1781,7 +1781,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
}
#ifdef CONFIG_NF_CONNTRACK_MARK
- ct->mark = exp->master->mark;
+ ct->mark = READ_ONCE(exp->master->mark);
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
ct->secmark = exp->master->secmark;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 7562b215b932..d71150a40fb0 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -328,9 +328,9 @@ nla_put_failure:
}
#ifdef CONFIG_NF_CONNTRACK_MARK
-static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct)
+static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark)
{
- if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark)))
+ if (nla_put_be32(skb, CTA_MARK, htonl(mark)))
goto nla_put_failure;
return 0;
@@ -543,7 +543,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb,
static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct)
{
if (ctnetlink_dump_status(skb, ct) < 0 ||
- ctnetlink_dump_mark(skb, ct) < 0 ||
+ ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 ||
ctnetlink_dump_secctx(skb, ct) < 0 ||
ctnetlink_dump_id(skb, ct) < 0 ||
ctnetlink_dump_use(skb, ct) < 0 ||
@@ -722,6 +722,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item)
struct sk_buff *skb;
unsigned int type;
unsigned int flags = 0, group;
+ u32 mark;
int err;
if (events & (1 << IPCT_DESTROY)) {
@@ -826,8 +827,9 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item)
}
#ifdef CONFIG_NF_CONNTRACK_MARK
- if ((events & (1 << IPCT_MARK) || ct->mark)
- && ctnetlink_dump_mark(skb, ct) < 0)
+ mark = READ_ONCE(ct->mark);
+ if ((events & (1 << IPCT_MARK) || mark) &&
+ ctnetlink_dump_mark(skb, mark) < 0)
goto nla_put_failure;
#endif
nlmsg_end(skb, nlh);
@@ -1154,7 +1156,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
}
#ifdef CONFIG_NF_CONNTRACK_MARK
- if ((ct->mark & filter->mark.mask) != filter->mark.val)
+ if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val)
goto ignore_entry;
#endif
status = (u32)READ_ONCE(ct->status);
@@ -2002,9 +2004,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct,
mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
mark = ntohl(nla_get_be32(cda[CTA_MARK]));
- newmark = (ct->mark & mask) ^ mark;
- if (newmark != ct->mark)
- ct->mark = newmark;
+ newmark = (READ_ONCE(ct->mark) & mask) ^ mark;
+ if (newmark != READ_ONCE(ct->mark))
+ WRITE_ONCE(ct->mark, newmark);
}
#endif
@@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
{
const struct nf_conntrack_zone *zone;
struct nlattr *nest_parms;
+ u32 mark;
zone = nf_ct_zone(ct);
@@ -2730,7 +2733,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
goto nla_put_failure;
#ifdef CONFIG_NF_CONNTRACK_MARK
- if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0)
+ mark = READ_ONCE(ct->mark);
+ if (mark && ctnetlink_dump_mark(skb, mark) < 0)
goto nla_put_failure;
#endif
if (ctnetlink_dump_labels(skb, ct) < 0)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 4ffe84c5a82c..bca839ab1ae8 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
goto release;
#if defined(CONFIG_NF_CONNTRACK_MARK)
- seq_printf(s, "mark=%u ", ct->mark);
+ seq_printf(s, "mark=%u ", READ_ONCE(ct->mark));
#endif
ct_show_secctx(s, ct);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index b04645ced89b..00b522890d77 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1098,6 +1098,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
struct flow_block_cb *block_cb, *next;
int err = 0;
+ down_write(&flowtable->flow_block_lock);
switch (cmd) {
case FLOW_BLOCK_BIND:
list_splice(&bo->cb_list, &flowtable->flow_block.cb_list);
@@ -1112,6 +1113,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable,
WARN_ON_ONCE(1);
err = -EOPNOTSUPP;
}
+ up_write(&flowtable->flow_block_lock);
return err;
}
@@ -1168,7 +1170,9 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
extack);
+ down_write(&flowtable->flow_block_lock);
err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
+ up_write(&flowtable->flow_block_lock);
if (err < 0)
return err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e7152d599d73..7a09421f19e1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5958,7 +5958,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
&timeout);
if (err)
return err;
- } else if (set->flags & NFT_SET_TIMEOUT) {
+ } else if (set->flags & NFT_SET_TIMEOUT &&
+ !(flags & NFT_SET_ELEM_INTERVAL_END)) {
timeout = set->timeout;
}
@@ -6024,7 +6025,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
err = -EOPNOTSUPP;
goto err_set_elem_expr;
}
- } else if (set->num_exprs > 0) {
+ } else if (set->num_exprs > 0 &&
+ !(flags & NFT_SET_ELEM_INTERVAL_END)) {
err = nft_set_elem_expr_clone(ctx, set, expr_array);
if (err < 0)
goto err_set_elem_expr_clone;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index a3f01f209a53..641dc21f92b4 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
return;
#ifdef CONFIG_NF_CONNTRACK_MARK
case NFT_CT_MARK:
- *dest = ct->mark;
+ *dest = READ_ONCE(ct->mark);
return;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
@@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr,
switch (priv->key) {
#ifdef CONFIG_NF_CONNTRACK_MARK
case NFT_CT_MARK:
- if (ct->mark != value) {
- ct->mark = value;
+ if (READ_ONCE(ct->mark) != value) {
+ WRITE_ONCE(ct->mark, value);
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index e5ebc0810675..ad3c033db64e 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
u_int32_t new_targetmark;
struct nf_conn *ct;
u_int32_t newmark;
+ u_int32_t oldmark;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
@@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
switch (info->mode) {
case XT_CONNMARK_SET:
- newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
+ oldmark = READ_ONCE(ct->mark);
+ newmark = (oldmark & ~info->ctmask) ^ info->ctmark;
if (info->shift_dir == D_SHIFT_RIGHT)
newmark >>= info->shift_bits;
else
newmark <<= info->shift_bits;
- if (ct->mark != newmark) {
- ct->mark = newmark;
+ if (READ_ONCE(ct->mark) != newmark) {
+ WRITE_ONCE(ct->mark, newmark);
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
@@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
else
new_targetmark <<= info->shift_bits;
- newmark = (ct->mark & ~info->ctmask) ^
+ newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^
new_targetmark;
- if (ct->mark != newmark) {
- ct->mark = newmark;
+ if (READ_ONCE(ct->mark) != newmark) {
+ WRITE_ONCE(ct->mark, newmark);
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_RESTORE:
- new_targetmark = (ct->mark & info->ctmask);
+ new_targetmark = (READ_ONCE(ct->mark) & info->ctmask);
if (info->shift_dir == D_SHIFT_RIGHT)
new_targetmark >>= info->shift_bits;
else
@@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (ct == NULL)
return false;
- return ((ct->mark & info->mask) == info->mark) ^ info->invert;
+ return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert;
}
static int connmark_mt_check(const struct xt_mtchk_param *par)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6a193cce2a75..4ffdf2f45c44 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -542,7 +542,7 @@ static int nci_open_device(struct nci_dev *ndev)
skb_queue_purge(&ndev->tx_q);
ndev->ops->close(ndev);
- ndev->flags = 0;
+ ndev->flags &= BIT(NCI_UNREG);
}
done:
diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index aa5e712adf07..3d36ea5701f0 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
nci_plen(skb->data));
conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data));
- if (!conn_info)
+ if (!conn_info) {
+ kfree_skb(skb);
return;
+ }
/* strip the nci data header */
skb_pull(skb, NCI_DATA_HDR_SIZE);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index c7b10234cf7c..c8eaf4234b2e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo)
static u32 ovs_ct_get_mark(const struct nf_conn *ct)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
- return ct ? ct->mark : 0;
+ return ct ? READ_ONCE(ct->mark) : 0;
#else
return 0;
#endif
@@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key,
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
u32 new_mark;
- new_mark = ct_mark | (ct->mark & ~(mask));
- if (ct->mark != new_mark) {
- ct->mark = new_mark;
+ new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask));
+ if (READ_ONCE(ct->mark) != new_mark) {
+ WRITE_ONCE(ct->mark, new_mark);
if (nf_ct_is_confirmed(ct))
nf_conntrack_event_cache(IPCT_MARK, ct);
key->ct.mark = new_mark;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 1ad0ec5afb50..8499ceb7719c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -399,6 +399,7 @@ enum rxrpc_conn_proto_state {
struct rxrpc_bundle {
struct rxrpc_conn_parameters params;
refcount_t ref;
+ atomic_t active; /* Number of active users */
unsigned int debug_id;
bool try_upgrade; /* True if the bundle is attempting upgrade */
bool alloc_conn; /* True if someone's getting a conn */
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 3c9eeb5b750c..bdb335cb2d05 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -40,6 +40,8 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
DEFINE_IDR(rxrpc_client_conn_ids);
static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
+static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
+
/*
* Get a connection ID and epoch for a client connection from the global pool.
* The connection struct pointer is then recorded in the idr radix tree. The
@@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
bundle->params = *cp;
rxrpc_get_peer(bundle->params.peer);
refcount_set(&bundle->ref, 1);
+ atomic_set(&bundle->active, 1);
spin_lock_init(&bundle->channel_lock);
INIT_LIST_HEAD(&bundle->waiting_calls);
}
@@ -149,7 +152,7 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle)
dead = __refcount_dec_and_test(&bundle->ref, &r);
- _debug("PUT B=%x %d", d, r);
+ _debug("PUT B=%x %d", d, r - 1);
if (dead)
rxrpc_free_bundle(bundle);
}
@@ -338,6 +341,7 @@ found_bundle_free:
rxrpc_free_bundle(candidate);
found_bundle:
rxrpc_get_bundle(bundle);
+ atomic_inc(&bundle->active);
spin_unlock(&local->client_bundles_lock);
_leave(" = %u [found]", bundle->debug_id);
return bundle;
@@ -435,6 +439,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
if (old)
trace_rxrpc_client(old, -1, rxrpc_client_replace);
candidate->bundle_shift = shift;
+ atomic_inc(&bundle->active);
bundle->conns[i] = candidate;
for (j = 0; j < RXRPC_MAXCALLS; j++)
set_bit(shift + j, &bundle->avail_chans);
@@ -725,6 +730,7 @@ granted_channel:
smp_rmb();
out_put_bundle:
+ rxrpc_deactivate_bundle(bundle);
rxrpc_put_bundle(bundle);
out:
_leave(" = %d", ret);
@@ -900,9 +906,8 @@ out:
static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
{
struct rxrpc_bundle *bundle = conn->bundle;
- struct rxrpc_local *local = bundle->params.local;
unsigned int bindex;
- bool need_drop = false, need_put = false;
+ bool need_drop = false;
int i;
_enter("C=%x", conn->debug_id);
@@ -921,15 +926,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
}
spin_unlock(&bundle->channel_lock);
- /* If there are no more connections, remove the bundle */
- if (!bundle->avail_chans) {
- _debug("maybe unbundle");
- spin_lock(&local->client_bundles_lock);
+ if (need_drop) {
+ rxrpc_deactivate_bundle(bundle);
+ rxrpc_put_connection(conn);
+ }
+}
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
- if (bundle->conns[i])
- break;
- if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) {
+/*
+ * Drop the active count on a bundle.
+ */
+static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
+{
+ struct rxrpc_local *local = bundle->params.local;
+ bool need_put = false;
+
+ if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) {
+ if (!bundle->params.exclusive) {
_debug("erase bundle");
rb_erase(&bundle->local_node, &local->client_bundles);
need_put = true;
@@ -939,10 +951,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
if (need_put)
rxrpc_put_bundle(bundle);
}
-
- if (need_drop)
- rxrpc_put_connection(conn);
- _leave("");
}
/*
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 1e8ab4749c6c..4662a6ce8a7e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY
config NET_ACT_CT
tristate "connection tracking tc action"
- depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE
+ depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE
help
Say Y here to allow sending the packets to conntrack module.
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 66b143bb04ac..d41002e4613f 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -61,7 +61,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
c = nf_ct_get(skb, &ctinfo);
if (c) {
- skb->mark = c->mark;
+ skb->mark = READ_ONCE(c->mark);
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
goto out;
@@ -81,7 +81,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
c = nf_ct_tuplehash_to_ctrack(thash);
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
- skb->mark = c->mark;
+ skb->mark = READ_ONCE(c->mark);
nf_ct_put(c);
out:
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index b38d91d6b249..4c7f7861ea96 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -178,7 +178,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
entry = tcf_ct_flow_table_flow_action_get_next(action);
entry->id = FLOW_ACTION_CT_METADATA;
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
- entry->ct_metadata.mark = ct->mark;
+ entry->ct_metadata.mark = READ_ONCE(ct->mark);
#endif
ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
IP_CT_ESTABLISHED_REPLY;
@@ -936,9 +936,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
if (!mask)
return;
- new_mark = mark | (ct->mark & ~(mask));
- if (ct->mark != new_mark) {
- ct->mark = new_mark;
+ new_mark = mark | (READ_ONCE(ct->mark) & ~(mask));
+ if (READ_ONCE(ct->mark) != new_mark) {
+ WRITE_ONCE(ct->mark, new_mark);
if (nf_ct_is_confirmed(ct))
nf_conntrack_event_cache(IPCT_MARK, ct);
}
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index d4102f0a9abd..eaa02f098d1c 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -32,7 +32,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
{
u8 dscp, newdscp;
- newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) &
+ newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) &
~INET_ECN_MASK;
switch (proto) {
@@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
struct sk_buff *skb)
{
ca->stats_cpmark_set++;
- skb->mark = ct->mark & cp->cpmarkmask;
+ skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask;
}
static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
@@ -130,7 +130,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
}
if (cp->mode & CTINFO_MODE_DSCP)
- if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask))
+ if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask))
tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto);
if (cp->mode & CTINFO_MODE_CPMARK)
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index e8630707901e..e8dcdf267c0c 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
u32 self;
int err;
- skb_linearize(skb);
+ if (skb_linearize(skb)) {
+ kfree_skb(skb);
+ return;
+ }
hdr = buf_msg(skb);
if (caps & TIPC_NODE_ID128)
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index d92ec92f0b71..e3b427a70398 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con)
conn_put(con);
}
-static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s)
+static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock)
{
struct tipc_conn *con;
int ret;
@@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s)
}
con->conid = ret;
s->idr_in_use++;
- spin_unlock_bh(&s->idr_lock);
set_bit(CF_CONNECTED, &con->flags);
con->server = s;
+ con->sock = sock;
+ conn_get(con);
+ spin_unlock_bh(&s->idr_lock);
return con;
}
@@ -467,7 +469,7 @@ static void tipc_topsrv_accept(struct work_struct *work)
ret = kernel_accept(lsock, &newsock, O_NONBLOCK);
if (ret < 0)
return;
- con = tipc_conn_alloc(srv);
+ con = tipc_conn_alloc(srv, newsock);
if (IS_ERR(con)) {
ret = PTR_ERR(con);
sock_release(newsock);
@@ -479,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work)
newsk->sk_data_ready = tipc_conn_data_ready;
newsk->sk_write_space = tipc_conn_write_space;
newsk->sk_user_data = con;
- con->sock = newsock;
write_unlock_bh(&newsk->sk_callback_lock);
/* Wake up receive process in case of 'SYN+' message */
newsk->sk_data_ready(newsk);
+ conn_put(con);
}
}
@@ -577,17 +579,17 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower,
sub.filter = filter;
*(u64 *)&sub.usr_handle = (u64)port;
- con = tipc_conn_alloc(tipc_topsrv(net));
+ con = tipc_conn_alloc(tipc_topsrv(net), NULL);
if (IS_ERR(con))
return false;
*conid = con->conid;
- con->sock = NULL;
rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub);
- if (rc >= 0)
- return true;
+ if (rc)
+ conn_put(con);
+
conn_put(con);
- return false;
+ return !rc;
}
void tipc_topsrv_kern_unsubscr(struct net *net, int conid)
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 5f5aafd418af..21269e8f2db4 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
}
}
+static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb)
+{
+ struct xfrm_offload *xo = xfrm_offload(skb);
+ __u32 seq = xo->seq.low;
+
+ seq += skb_shinfo(skb)->gso_segs;
+ if (unlikely(seq < xo->seq.low))
+ return true;
+
+ return false;
+}
+
struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again)
{
int err;
@@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
return skb;
}
- if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) {
+ if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) ||
+ unlikely(xmit_xfrm_check_overflow(skb)))) {
struct sk_buff *segs;
/* Packet got rerouted, fixup features and segment it. */
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 9f4d42eb090f..ce56d659c55a 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
oseq += skb_shinfo(skb)->gso_segs;
}
- if (unlikely(oseq < replay_esn->oseq)) {
+ if (unlikely(xo->seq.low < replay_esn->oseq)) {
XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
xo->seq.hi = oseq_hi;
replay_esn->oseq_hi = oseq_hi;