aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_netlink.c10
-rw-r--r--net/bluetooth/hci_core.c3
-rw-r--r--net/bluetooth/hci_sync.c1
-rw-r--r--net/bridge/br_netfilter_hooks.c21
-rw-r--r--net/can/bcm.c18
-rw-r--r--net/core/dev.c8
-rw-r--r--net/core/filter.c1
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/cipso_ipv4.c12
-rw-r--r--net/ipv4/fib_semantics.c4
-rw-r--r--net/ipv4/fib_trie.c2
-rw-r--r--net/ipv4/icmp.c20
-rw-r--r--net/ipv4/inet_timewait_sock.c3
-rw-r--r--net/ipv4/inetpeer.c12
-rw-r--r--net/ipv4/ip_tunnel_core.c2
-rw-r--r--net/ipv4/nexthop.c5
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c12
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_output.c4
-rw-r--r--net/ipv6/addrconf.c8
-rw-r--r--net/ipv6/icmp.c2
-rw-r--r--net/ipv6/route.c11
-rw-r--r--net/ipv6/seg6_hmac.c1
-rw-r--r--net/ipv6/seg6_iptunnel.c5
-rw-r--r--net/ipv6/seg6_local.c2
-rw-r--r--net/ipv6/sit.c8
-rw-r--r--net/mac80211/cfg.c4
-rw-r--r--net/mac80211/iface.c2
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/tx.c36
-rw-r--r--net/mac80211/util.c3
-rw-r--r--net/mac80211/wme.c4
-rw-r--r--net/mptcp/options.c10
-rw-r--r--net/mptcp/pm.c10
-rw-r--r--net/mptcp/pm_netlink.c46
-rw-r--r--net/mptcp/pm_userspace.c51
-rw-r--r--net/mptcp/protocol.c97
-rw-r--r--net/mptcp/protocol.h33
-rw-r--r--net/mptcp/subflow.c127
-rw-r--r--net/ncsi/ncsi-manage.c3
-rw-r--r--net/netfilter/nf_conntrack_core.c22
-rw-r--r--net/netfilter/nf_conntrack_netlink.c1
-rw-r--r--net/netfilter/nf_conntrack_standalone.c3
-rw-r--r--net/netfilter/nf_log_syslog.c8
-rw-r--r--net/netfilter/nf_tables_api.c81
-rw-r--r--net/netfilter/nf_tables_core.c24
-rw-r--r--net/netfilter/nf_tables_trace.c44
-rw-r--r--net/netfilter/nft_set_hash.c2
-rw-r--r--net/netfilter/nft_set_pipapo.c48
-rw-r--r--net/rose/rose_route.c4
-rw-r--r--net/rose/rose_timer.c34
-rw-r--r--net/sched/act_api.c22
-rw-r--r--net/sched/act_police.c2
-rw-r--r--net/socket.c16
-rw-r--r--net/sunrpc/xdr.c2
-rw-r--r--net/tipc/node.c41
-rw-r--r--net/tipc/socket.c1
-rw-r--r--net/tls/tls_device.c4
-rw-r--r--net/tls/tls_main.c7
-rw-r--r--net/tls/tls_sw.c8
-rw-r--r--net/wireless/sme.c3
-rw-r--r--net/xdp/xsk_buff_pool.c1
65 files changed, 673 insertions, 326 deletions
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 53b1955b027f..214532173536 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -182,10 +182,14 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
else if (dev->mtu > max_mtu)
return -EINVAL;
+ /* Note: If this initial vlan_changelink() fails, we need
+ * to call vlan_dev_free_egress_priority() to free memory.
+ */
err = vlan_changelink(dev, tb, data, extack);
- if (err)
- return err;
- err = register_vlan_dev(dev, extack);
+
+ if (!err)
+ err = register_vlan_dev(dev, extack);
+
if (err)
vlan_dev_free_egress_priority(dev);
return err;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 59a5c1341c26..a0f99baafd35 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -571,6 +571,7 @@ int hci_dev_close(__u16 dev)
goto done;
}
+ cancel_work_sync(&hdev->power_on);
if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF))
cancel_delayed_work(&hdev->power_off);
@@ -2675,6 +2676,8 @@ void hci_unregister_dev(struct hci_dev *hdev)
list_del(&hdev->list);
write_unlock(&hci_dev_list_lock);
+ cancel_work_sync(&hdev->power_on);
+
hci_cmd_sync_clear(hdev);
if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks))
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 286d6767f017..1739e8cb3291 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4088,7 +4088,6 @@ int hci_dev_close_sync(struct hci_dev *hdev)
bt_dev_dbg(hdev, "");
- cancel_work_sync(&hdev->power_on);
cancel_delayed_work(&hdev->power_off);
cancel_delayed_work(&hdev->ncmd_timer);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 4fd882686b04..ff4779036649 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -1012,9 +1012,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
return okfn(net, sk, skb);
ops = nf_hook_entries_get_hook_ops(e);
- for (i = 0; i < e->num_hook_entries &&
- ops[i]->priority <= NF_BR_PRI_BRNF; i++)
- ;
+ for (i = 0; i < e->num_hook_entries; i++) {
+ /* These hooks have already been called */
+ if (ops[i]->priority < NF_BR_PRI_BRNF)
+ continue;
+
+ /* These hooks have not been called yet, run them. */
+ if (ops[i]->priority > NF_BR_PRI_BRNF)
+ break;
+
+ /* take a closer look at NF_BR_PRI_BRNF. */
+ if (ops[i]->hook == br_nf_pre_routing) {
+ /* This hook diverted the skb to this function,
+ * hooks after this have not been run yet.
+ */
+ i++;
+ break;
+ }
+ }
nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
sk, net, okfn);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 65ee1b784a30..e60161bec850 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -100,6 +100,7 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset)
struct bcm_op {
struct list_head list;
+ struct rcu_head rcu;
int ifindex;
canid_t can_id;
u32 flags;
@@ -718,10 +719,9 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
return NULL;
}
-static void bcm_remove_op(struct bcm_op *op)
+static void bcm_free_op_rcu(struct rcu_head *rcu_head)
{
- hrtimer_cancel(&op->timer);
- hrtimer_cancel(&op->thrtimer);
+ struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu);
if ((op->frames) && (op->frames != &op->sframe))
kfree(op->frames);
@@ -732,6 +732,14 @@ static void bcm_remove_op(struct bcm_op *op)
kfree(op);
}
+static void bcm_remove_op(struct bcm_op *op)
+{
+ hrtimer_cancel(&op->timer);
+ hrtimer_cancel(&op->thrtimer);
+
+ call_rcu(&op->rcu, bcm_free_op_rcu);
+}
+
static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
{
if (op->rx_reg_dev == dev) {
@@ -757,6 +765,9 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
(op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
+ /* disable automatic timer on frame reception */
+ op->flags |= RX_NO_AUTOTIMER;
+
/*
* Don't care if we're bound or not (due to netdev
* problems) can_rx_unregister() is always a save
@@ -785,7 +796,6 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
bcm_rx_handler, op);
list_del(&op->list);
- synchronize_rcu();
bcm_remove_op(op);
return 1; /* done */
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 8e6f22961206..30a1603a7225 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4863,7 +4863,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
}
/* When doing generic XDP we have to bypass the qdisc layer and the
- * network taps in order to match in-driver-XDP behavior.
+ * network taps in order to match in-driver-XDP behavior. This also means
+ * that XDP packets are able to starve other packets going through a qdisc,
+ * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX
+ * queues, so they do not have this starvation issue.
*/
void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
{
@@ -4875,7 +4878,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
txq = netdev_core_pick_tx(dev, skb, NULL);
cpu = smp_processor_id();
HARD_TX_LOCK(dev, txq, cpu);
- if (!netif_xmit_stopped(txq)) {
+ if (!netif_xmit_frozen_or_drv_stopped(txq)) {
rc = netdev_start_xmit(skb, dev, txq, 0);
if (dev_xmit_complete(rc))
free_skb = false;
@@ -4883,6 +4886,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
HARD_TX_UNLOCK(dev, txq);
if (free_skb) {
trace_xdp_exception(dev, xdp_prog, XDP_TX);
+ dev_core_stats_tx_dropped_inc(dev);
kfree_skb(skb);
}
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 5d16d66727fc..2a6a0b0ce43e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6158,7 +6158,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
if (err)
return err;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
return seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 93da9f783bec..ac67f6b4ec70 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1246,7 +1246,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
if (new_saddr == old_saddr)
return 0;
- if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) {
pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
__func__, &old_saddr, &new_saddr);
}
@@ -1301,7 +1301,7 @@ int inet_sk_rebuild_header(struct sock *sk)
* Other protocols have to map its equivalent state to TCP_SYN_SENT.
* DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
*/
- if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr ||
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
sk->sk_state != TCP_SYN_SENT ||
(sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
(err = inet_sk_reselect_saddr(sk)) != 0)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 62d5f99760aa..6cd3b6c559f0 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -239,7 +239,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
struct cipso_v4_map_cache_entry *prev_entry = NULL;
u32 hash;
- if (!cipso_v4_cache_enabled)
+ if (!READ_ONCE(cipso_v4_cache_enabled))
return -ENOENT;
hash = cipso_v4_map_cache_hash(key, key_len);
@@ -296,13 +296,14 @@ static int cipso_v4_cache_check(const unsigned char *key,
int cipso_v4_cache_add(const unsigned char *cipso_ptr,
const struct netlbl_lsm_secattr *secattr)
{
+ int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize);
int ret_val = -EPERM;
u32 bkt;
struct cipso_v4_map_cache_entry *entry = NULL;
struct cipso_v4_map_cache_entry *old_entry = NULL;
u32 cipso_ptr_len;
- if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
+ if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0)
return 0;
cipso_ptr_len = cipso_ptr[1];
@@ -322,7 +323,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr,
bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1);
spin_lock_bh(&cipso_v4_cache[bkt].lock);
- if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
+ if (cipso_v4_cache[bkt].size < bkt_size) {
list_add(&entry->list, &cipso_v4_cache[bkt].list);
cipso_v4_cache[bkt].size += 1;
} else {
@@ -1199,7 +1200,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def,
/* This will send packets using the "optimized" format when
* possible as specified in section 3.4.2.6 of the
* CIPSO draft. */
- if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10)
+ if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 &&
+ ret_val <= 10)
tag_len = 14;
else
tag_len = 4 + ret_val;
@@ -1603,7 +1605,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
* all the CIPSO validations here but it doesn't
* really specify _exactly_ what we need to validate
* ... so, just make it a sysctl tunable. */
- if (cipso_v4_rbm_strictvalid) {
+ if (READ_ONCE(cipso_v4_rbm_strictvalid)) {
if (cipso_v4_map_lvl_valid(doi_def,
tag[3]) < 0) {
err_offset = opt_iter + 3;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a57ba23571c9..d9fdcbae16ee 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1230,7 +1230,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
nh->fib_nh_dev = in_dev->dev;
dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
- nh->fib_nh_scope = RT_SCOPE_HOST;
+ nh->fib_nh_scope = RT_SCOPE_LINK;
if (!netif_carrier_ok(nh->fib_nh_dev))
nh->fib_nh_flags |= RTNH_F_LINKDOWN;
err = 0;
@@ -1811,7 +1811,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
goto nla_put_failure;
if (nexthop_is_blackhole(fi->nh))
rtm->rtm_type = RTN_BLACKHOLE;
- if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode)
+ if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode))
goto offload;
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2734c3af7e24..46e8a5125853 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -498,7 +498,7 @@ static void tnode_free(struct key_vector *tn)
tn = container_of(head, struct tnode, rcu)->kv;
}
- if (tnode_free_size >= sysctl_fib_sync_mem) {
+ if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) {
tnode_free_size = 0;
synchronize_rcu();
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index efea0e796f06..57c4f0d87a7a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -253,11 +253,12 @@ bool icmp_global_allow(void)
spin_lock(&icmp_global.lock);
delta = min_t(u32, now - icmp_global.stamp, HZ);
if (delta >= HZ / 50) {
- incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+ incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
if (incr)
WRITE_ONCE(icmp_global.stamp, now);
}
- credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+ credit = min_t(u32, icmp_global.credit + incr,
+ READ_ONCE(sysctl_icmp_msgs_burst));
if (credit) {
/* We want to use a credit of one in average, but need to randomize
* it for security reasons.
@@ -281,7 +282,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
return true;
/* Limit if icmp type is enabled in ratemask. */
- if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
return true;
return false;
@@ -319,7 +320,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
vif = l3mdev_master_ifindex(dst->dev);
peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
- rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+ rc = inet_peer_xrlim_allow(peer,
+ READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
if (peer)
inet_putpeer(peer);
out:
@@ -692,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
rcu_read_lock();
if (rt_is_input_route(rt) &&
- net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
+ READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
if (dev)
@@ -932,7 +934,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
* get the other vendor to fix their kit.
*/
- if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
+ if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) &&
inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
&ip_hdr(skb)->saddr,
@@ -992,7 +994,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
net = dev_net(skb_dst(skb)->dev);
/* should there be an ICMP stat for ignored echos? */
- if (net->ipv4.sysctl_icmp_echo_ignore_all)
+ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
return SKB_NOT_DROPPED_YET;
icmp_param.data.icmph = *icmp_hdr(skb);
@@ -1027,7 +1029,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
u16 ident_len;
u8 status;
- if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+ if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
return false;
/* We currently only support probing interfaces on the proxy node
@@ -1248,7 +1250,7 @@ int icmp_rcv(struct sk_buff *skb)
*/
if ((icmph->type == ICMP_ECHO ||
icmph->type == ICMP_TIMESTAMP) &&
- net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
+ READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) {
reason = SKB_DROP_REASON_INVALID_PROTO;
goto error;
}
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 0ec501845cb3..47ccc343c9fb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -156,7 +156,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
{
struct inet_timewait_sock *tw;
- if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets)
+ if (refcount_read(&dr->tw_refcount) - 1 >=
+ READ_ONCE(dr->sysctl_max_tw_buckets))
return NULL;
tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index da21dfce24d7..e9fed83e9b3c 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -141,16 +141,20 @@ static void inet_peer_gc(struct inet_peer_base *base,
struct inet_peer *gc_stack[],
unsigned int gc_cnt)
{
+ int peer_threshold, peer_maxttl, peer_minttl;
struct inet_peer *p;
__u32 delta, ttl;
int i;
- if (base->total >= inet_peer_threshold)
+ peer_threshold = READ_ONCE(inet_peer_threshold);
+ peer_maxttl = READ_ONCE(inet_peer_maxttl);
+ peer_minttl = READ_ONCE(inet_peer_minttl);
+
+ if (base->total >= peer_threshold)
ttl = 0; /* be aggressive */
else
- ttl = inet_peer_maxttl
- - (inet_peer_maxttl - inet_peer_minttl) / HZ *
- base->total / inet_peer_threshold * HZ;
+ ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
+ base->total / peer_threshold * HZ;
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6b2dc7b2b612..cc1caab4a654 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -410,7 +410,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
u32 mtu = dst_mtu(encap_dst) - headroom;
if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
- (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu))
+ (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
return 0;
skb_dst_update_pmtu_no_confirm(skb, mtu);
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index e459a391e607..853a75a8fbaf 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1858,7 +1858,7 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
/* __ip6_del_rt does a release, so do a hold here */
fib6_info_hold(f6i);
ipv6_stub->ip6_del_rt(net, f6i,
- !net->ipv4.sysctl_nexthop_compat_mode);
+ !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode));
}
}
@@ -2361,7 +2361,8 @@ out:
if (!rc) {
nh_base_seq_inc(net);
nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
- if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode)
+ if (replace_notify &&
+ READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode))
nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f33c31dd7366..b387c4835155 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -273,7 +273,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
if (!ecn_ok)
return false;
- if (net->ipv4.sysctl_tcp_ecn)
+ if (READ_ONCE(net->ipv4.sysctl_tcp_ecn))
return true;
return dst_feature(dst, RTAX_FEATURE_ECN);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index cd448cdd3b38..108fd86f2718 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -599,6 +599,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{
.procname = "icmp_echo_enable_probe",
@@ -615,6 +617,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{
.procname = "icmp_ignore_bogus_error_responses",
@@ -622,6 +626,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{
.procname = "icmp_errors_use_inbound_ifaddr",
@@ -629,6 +635,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{
.procname = "icmp_ratelimit",
@@ -668,6 +676,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
},
{
.procname = "tcp_ecn_fallback",
@@ -675,6 +685,8 @@ static struct ctl_table ipv4_net_table[] = {
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
},
{
.procname = "ip_dynaddr",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 028513d3e2a2..2222dfdde316 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2715,7 +2715,8 @@ static void tcp_orphan_update(struct timer_list *unused)
static bool tcp_too_many_orphans(int shift)
{
- return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans;
+ return READ_ONCE(tcp_orphan_cache) << shift >
+ READ_ONCE(sysctl_tcp_max_orphans);
}
bool tcp_check_oom(struct sock *sk, int shift)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2e2a9ece9af2..3ec4edc37313 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6729,7 +6729,7 @@ static void tcp_ecn_create_request(struct request_sock *req,
ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
- ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
+ ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst;
if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
(ecn_ok_dst & DST_FEATURE_ECN_CA) ||
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fe8f23b95d32..da5a3c44c4fb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1964,7 +1964,10 @@ process:
struct sock *nsk;
sk = req->rsk_listener;
- drop_reason = tcp_inbound_md5_hash(sk, skb,
+ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+ drop_reason = SKB_DROP_REASON_XFRM_POLICY;
+ else
+ drop_reason = tcp_inbound_md5_hash(sk, skb,
&iph->saddr, &iph->daddr,
AF_INET, dif, sdif);
if (unlikely(drop_reason)) {
@@ -2016,6 +2019,7 @@ process:
}
goto discard_and_relse;
}
+ nf_reset_ct(skb);
if (nsk == sk) {
reqsk_put(req);
tcp_v4_restore_cb(skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1c054431e358..11aa0ab10bba 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -324,7 +324,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
- bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+ bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
if (!use_ecn) {
@@ -346,7 +346,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
{
- if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
/* tp->ecn_flags are cleared at a later point in time when
* SYN ACK is ultimatively being received.
*/
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1b1932502e9e..49cc6587dd77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1109,10 +1109,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
goto out;
}
- if (net->ipv6.devconf_all->disable_policy ||
- idev->cnf.disable_policy)
- f6i->dst_nopolicy = true;
-
neigh_parms_data_state_setall(idev->nd_parms);
ifa->addr = *cfg->pfx;
@@ -5172,9 +5168,9 @@ next:
fillargs->event = RTM_GETMULTICAST;
/* multicast address */
- for (ifmca = rcu_dereference(idev->mc_list);
+ for (ifmca = rtnl_dereference(idev->mc_list);
ifmca;
- ifmca = rcu_dereference(ifmca->next), ip_idx++) {
+ ifmca = rtnl_dereference(ifmca->next), ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
err = inet6_fill_ifmcaddr(skb, ifmca, fillargs);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 61770220774e..9d92d51c4757 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -925,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
case ICMPV6_EXT_ECHO_REQUEST:
if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
- net->ipv4.sysctl_icmp_echo_enable_probe)
+ READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
icmpv6_echo_reply(skb);
break;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d25dc83bac62..916417944ec8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4569,8 +4569,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
}
f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
- if (!IS_ERR(f6i))
+ if (!IS_ERR(f6i)) {
f6i->dst_nocount = true;
+
+ if (!anycast &&
+ (net->ipv6.devconf_all->disable_policy ||
+ idev->cnf.disable_policy))
+ f6i->dst_nopolicy = true;
+ }
+
return f6i;
}
@@ -5734,7 +5741,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (nexthop_is_blackhole(rt->nh))
rtm->rtm_type = RTN_BLACKHOLE;
- if (net->ipv4.sysctl_nexthop_compat_mode &&
+ if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) &&
rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
goto nla_put_failure;
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 6de01185cc68..d43c50a7310d 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -406,7 +406,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
return rhashtable_init(&sdata->hmac_infos, &rht_params);
}
-EXPORT_SYMBOL(seg6_hmac_net_init);
void seg6_hmac_exit(void)
{
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index d64855010948..e756ba705fd9 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, tot_len);
return 0;
@@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
return 0;
@@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb)
break;
}
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
nf_reset_ct(skb);
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 98a34287439c..2cd4a8d3b30a 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -826,7 +826,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
@@ -858,7 +857,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index c0b138c20992..6bcd5e419a08 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) :
NULL;
- rcu_read_lock();
-
ca = min(t->prl_count, cmax);
if (!kp) {
@@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
}
}
- c = 0;
+ rcu_read_lock();
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
@@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
if (kprl.addr != htonl(INADDR_ANY))
break;
}
-out:
+
rcu_read_unlock();
len = sizeof(*kp) * c;
@@ -362,7 +360,7 @@ out:
ret = -EFAULT;
kfree(kp);
-
+out:
return ret;
}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index f7896f257e1b..4ddf297f40f2 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4468,14 +4468,14 @@ EXPORT_SYMBOL_GPL(ieee80211_color_change_finish);
void
ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif,
- u64 color_bitmap)
+ u64 color_bitmap, gfp_t gfp)
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
if (sdata->vif.color_change_active || sdata->vif.csa_active)
return;
- cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap);
+ cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap, gfp);
}
EXPORT_SYMBOL_GPL(ieeee80211_obss_color_collision_notify);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 41531478437c..15a73b7fdd75 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -377,7 +377,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
bool cancel_scan;
struct cfg80211_nan_func *func;
+ spin_lock_bh(&local->fq.lock);
clear_bit(SDATA_STATE_RUNNING, &sdata->state);
+ spin_unlock_bh(&local->fq.lock);
cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata;
if (cancel_scan)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3c08ae04ddbc..1675f8cb87f1 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3217,7 +3217,8 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx)
IEEE80211_HE_OPERATION_BSS_COLOR_MASK);
if (color == bss_conf->he_bss_color.color)
ieeee80211_obss_color_collision_notify(&rx->sdata->vif,
- BIT_ULL(color));
+ BIT_ULL(color),
+ GFP_ATOMIC);
}
}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 0e4efc08c762..c425f4fb7c2e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2818,19 +2818,10 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
/*
* If the skb is shared we need to obtain our own copy.
*/
- if (skb_shared(skb)) {
- struct sk_buff *tmp_skb = skb;
-
- /* can't happen -- skb is a clone if info_id != 0 */
- WARN_ON(info_id);
-
- skb = skb_clone(skb, GFP_ATOMIC);
- kfree_skb(tmp_skb);
-
- if (!skb) {
- ret = -ENOMEM;
- goto free;
- }
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb)) {
+ ret = -ENOMEM;
+ goto free;
}
hdr.frame_control = fc;
@@ -3539,15 +3530,9 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
/* after this point (skb is modified) we cannot return false */
- if (skb_shared(skb)) {
- struct sk_buff *tmp_skb = skb;
-
- skb = skb_clone(skb, GFP_ATOMIC);
- kfree_skb(tmp_skb);
-
- if (!skb)
- return true;
- }
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ return true;
if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) &&
ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb))
@@ -4437,7 +4422,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
struct net_device *dev, struct sta_info *sta,
struct ieee80211_key *key, struct sk_buff *skb)
{
- struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ struct ieee80211_tx_info *info;
struct ieee80211_local *local = sdata->local;
struct tid_ampdu_tx *tid_tx;
u8 tid;
@@ -4452,6 +4437,11 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))
goto out_free;
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ return;
+
+ info = IEEE80211_SKB_CB(skb);
memset(info, 0, sizeof(*info));
ieee80211_aggr_check(sdata, sta, skb);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 1e26b5235add..dad42d42aa84 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -301,6 +301,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
local_bh_disable();
spin_lock(&fq->lock);
+ if (!test_bit(SDATA_STATE_RUNNING, &sdata->state))
+ goto out;
+
if (sdata->vif.type == NL80211_IFTYPE_AP)
ps = &sdata->bss->ps;
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 62c6733e0792..d50480b31750 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -147,8 +147,8 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
bool qos;
/* all mesh/ocb stations are required to support WME */
- if (sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
- sdata->vif.type == NL80211_IFTYPE_OCB)
+ if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
+ sdata->vif.type == NL80211_IFTYPE_OCB))
qos = true;
else if (sta)
qos = sta->sta.wme;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index be3b918a6d15..bd8f0f425be4 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -765,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu
opts->suboptions |= OPTION_MPTCP_RST;
opts->reset_transient = subflow->reset_transient;
opts->reset_reason = subflow->reset_reason;
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
return true;
}
@@ -788,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
opts->rcvr_key = msk->remote_key;
pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
return true;
}
@@ -809,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
opts->fail_seq = subflow->map_seq;
pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
return true;
}
@@ -833,13 +836,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
}
/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */
if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
}
return true;
}
@@ -966,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
goto reset;
subflow->mp_capable = 0;
pr_fallback(msk);
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
return false;
}
@@ -1583,6 +1584,9 @@ mp_rst:
*ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
TCPOLEN_MPTCP_PRIO,
opts->backup, TCPOPT_NOP);
+
+ MPTCP_INC_STATS(sock_net((const struct sock *)tp),
+ MPTCP_MIB_MPPRIOTX);
}
mp_capable_done:
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 59a85220edc9..45e2a48397b9 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -299,23 +299,21 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- struct sock *s = (struct sock *)msk;
pr_debug("fail_seq=%llu", fail_seq);
if (!READ_ONCE(msk->allow_infinite_fallback))
return;
- if (!READ_ONCE(subflow->mp_fail_response_expect)) {
+ if (!subflow->fail_tout) {
pr_debug("send MP_FAIL response and infinite map");
subflow->send_mp_fail = 1;
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
subflow->send_infinite_map = 1;
- } else if (!sock_flag(sk, SOCK_DEAD)) {
+ tcp_send_ack(sk);
+ } else {
pr_debug("MP_FAIL response received");
-
- sk_stop_timer(s, &s->sk_timer);
+ WRITE_ONCE(subflow->fail_tout, 0);
}
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index e099f2a12504..7c7395b58944 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -717,9 +717,10 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
}
}
-static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
- struct mptcp_addr_info *addr,
- u8 bkup)
+int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+ struct mptcp_addr_info *addr,
+ struct mptcp_addr_info *rem,
+ u8 bkup)
{
struct mptcp_subflow_context *subflow;
@@ -727,24 +728,29 @@ static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- struct sock *sk = (struct sock *)msk;
- struct mptcp_addr_info local;
+ struct mptcp_addr_info local, remote;
+ bool slow;
local_address((struct sock_common *)ssk, &local);
if (!mptcp_addresses_equal(&local, addr, addr->port))
continue;
+ if (rem && rem->family != AF_UNSPEC) {
+ remote_address((struct sock_common *)ssk, &remote);
+ if (!mptcp_addresses_equal(&remote, rem, rem->port))
+ continue;
+ }
+
+ slow = lock_sock_fast(ssk);
if (subflow->backup != bkup)
msk->last_snd = NULL;
subflow->backup = bkup;
subflow->send_mp_prio = 1;
subflow->request_bkup = bkup;
- __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX);
- spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for mp_prio");
- mptcp_subflow_send_ack(ssk);
- spin_lock_bh(&msk->pm.lock);
+ __mptcp_subflow_send_ack(ssk);
+ unlock_sock_fast(ssk, slow);
return 0;
}
@@ -801,7 +807,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
removed = true;
__MPTCP_INC_STATS(sock_net(sk), rm_type);
}
- __set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap);
+ if (rm_type == MPTCP_MIB_RMSUBFLOW)
+ __set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap);
if (!removed)
continue;
@@ -1816,8 +1823,10 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
list.ids[list.nr++] = addr->id;
+ spin_lock_bh(&msk->pm.lock);
mptcp_pm_nl_rm_subflow_received(msk, &list);
mptcp_pm_create_subflow_or_signal_addr(msk);
+ spin_unlock_bh(&msk->pm.lock);
}
static int mptcp_nl_set_flags(struct net *net,
@@ -1835,12 +1844,10 @@ static int mptcp_nl_set_flags(struct net *net,
goto next;
lock_sock(sk);
- spin_lock_bh(&msk->pm.lock);
if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
- ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup);
+ ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
mptcp_pm_nl_fullmesh(msk, addr);
- spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
next:
@@ -1854,6 +1861,9 @@ next:
static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
{
struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
+ struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
+ struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
+ struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
@@ -1866,6 +1876,12 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
if (ret < 0)
return ret;
+ if (attr_rem) {
+ ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote);
+ if (ret < 0)
+ return ret;
+ }
+
if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
bkup = 1;
if (addr.addr.family == AF_UNSPEC) {
@@ -1874,6 +1890,10 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
return -EOPNOTSUPP;
}
+ if (token)
+ return mptcp_userspace_pm_set_flags(sock_net(skb->sk),
+ token, &addr, &remote, bkup);
+
spin_lock_bh(&pernet->lock);
entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
if (!entry) {
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f56378e4f597..9e82250cbb70 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -5,6 +5,7 @@
*/
#include "protocol.h"
+#include "mib.h"
void mptcp_free_local_addr_list(struct mptcp_sock *msk)
{
@@ -306,15 +307,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
const struct mptcp_addr_info *local,
const struct mptcp_addr_info *remote)
{
- struct sock *sk = &msk->sk.icsk_inet.sk;
struct mptcp_subflow_context *subflow;
- struct sock *found = NULL;
if (local->family != remote->family)
return NULL;
- lock_sock(sk);
-
mptcp_for_each_subflow(msk, subflow) {
const struct inet_sock *issk;
struct sock *ssk;
@@ -347,16 +344,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
}
if (issk->inet_sport == local->port &&
- issk->inet_dport == remote->port) {
- found = ssk;
- goto found;
- }
+ issk->inet_dport == remote->port)
+ return ssk;
}
-found:
- release_sock(sk);
-
- return found;
+ return NULL;
}
int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
@@ -412,18 +404,51 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
}
sk = &msk->sk.icsk_inet.sk;
+ lock_sock(sk);
ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r);
if (ssk) {
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN);
mptcp_close_ssk(sk, ssk, subflow);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
err = 0;
} else {
err = -ESRCH;
}
+ release_sock(sk);
- destroy_err:
+destroy_err:
sock_put((struct sock *)msk);
return err;
}
+
+int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup)
+{
+ struct mptcp_sock *msk;
+ int ret = -EINVAL;
+ u32 token_val;
+
+ token_val = nla_get_u32(token);
+
+ msk = mptcp_token_get_sock(net, token_val);
+ if (!msk)
+ return ret;
+
+ if (!mptcp_pm_is_userspace(msk))
+ goto set_flags_err;
+
+ if (loc->addr.family == AF_UNSPEC ||
+ rem->addr.family == AF_UNSPEC)
+ goto set_flags_err;
+
+ lock_sock((struct sock *)msk);
+ ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup);
+ release_sock((struct sock *)msk);
+
+set_flags_err:
+ sock_put((struct sock *)msk);
+ return ret;
+}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 17e13396024a..21a3ed64226e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -500,19 +500,24 @@ static void mptcp_set_timeout(struct sock *sk)
__mptcp_set_timeout(sk, tout);
}
-static bool tcp_can_send_ack(const struct sock *ssk)
+static inline bool tcp_can_send_ack(const struct sock *ssk)
{
return !((1 << inet_sk_state_load(ssk)) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
}
+void __mptcp_subflow_send_ack(struct sock *ssk)
+{
+ if (tcp_can_send_ack(ssk))
+ tcp_send_ack(ssk);
+}
+
void mptcp_subflow_send_ack(struct sock *ssk)
{
bool slow;
slow = lock_sock_fast(ssk);
- if (tcp_can_send_ack(ssk))
- tcp_send_ack(ssk);
+ __mptcp_subflow_send_ack(ssk);
unlock_sock_fast(ssk, slow);
}
@@ -1245,7 +1250,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
pr_fallback(msk);
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
}
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
@@ -2175,21 +2180,6 @@ static void mptcp_retransmit_timer(struct timer_list *t)
sock_put(sk);
}
-static struct mptcp_subflow_context *
-mp_fail_response_expect_subflow(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow, *ret = NULL;
-
- mptcp_for_each_subflow(msk, subflow) {
- if (READ_ONCE(subflow->mp_fail_response_expect)) {
- ret = subflow;
- break;
- }
- }
-
- return ret;
-}
-
static void mptcp_timeout_timer(struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
@@ -2346,6 +2336,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
kfree_rcu(subflow, rcu);
} else {
/* otherwise tcp will dispose of the ssk and subflow ctx */
+ if (ssk->sk_state == TCP_LISTEN) {
+ tcp_set_state(ssk, TCP_CLOSE);
+ mptcp_subflow_queue_clean(ssk);
+ inet_csk_listen_stop(ssk);
+ }
__tcp_close(ssk, 0);
/* close acquired an extra ref */
@@ -2518,27 +2513,50 @@ reset_timer:
mptcp_reset_timer(sk);
}
+/* schedule the timeout timer for the relevant event: either close timeout
+ * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
+ */
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
+{
+ struct sock *sk = (struct sock *)msk;
+ unsigned long timeout, close_timeout;
+
+ if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
+ return;
+
+ close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;
+
+ /* the close timeout takes precedence on the fail one, and here at least one of
+ * them is active
+ */
+ timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;
+
+ sk_reset_timer(sk, &sk->sk_timer, timeout);
+}
+
static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
{
- struct mptcp_subflow_context *subflow;
- struct sock *ssk;
+ struct sock *ssk = msk->first;
bool slow;
- subflow = mp_fail_response_expect_subflow(msk);
- if (subflow) {
- pr_debug("MP_FAIL doesn't respond, reset the subflow");
+ if (!ssk)
+ return;
- ssk = mptcp_subflow_tcp_sock(subflow);
- slow = lock_sock_fast(ssk);
- mptcp_subflow_reset(ssk);
- unlock_sock_fast(ssk, slow);
- }
+ pr_debug("MP_FAIL doesn't respond, reset the subflow");
+
+ slow = lock_sock_fast(ssk);
+ mptcp_subflow_reset(ssk);
+ WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
+ unlock_sock_fast(ssk, slow);
+
+ mptcp_reset_timeout(msk, 0);
}
static void mptcp_worker(struct work_struct *work)
{
struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
struct sock *sk = &msk->sk.icsk_inet.sk;
+ unsigned long fail_tout;
int state;
lock_sock(sk);
@@ -2575,7 +2593,9 @@ static void mptcp_worker(struct work_struct *work)
if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
__mptcp_retrans(sk);
- mptcp_mp_fail_no_response(msk);
+ fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;
+ if (fail_tout && time_after(jiffies, fail_tout))
+ mptcp_mp_fail_no_response(msk);
unlock:
release_sock(sk);
@@ -2822,6 +2842,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
static void mptcp_close(struct sock *sk, long timeout)
{
struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
bool do_cancel_work = false;
lock_sock(sk);
@@ -2840,10 +2861,16 @@ static void mptcp_close(struct sock *sk, long timeout)
cleanup:
/* orphan all the subflows */
inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
- mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+ mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast_nested(ssk);
+ /* since the close timeout takes precedence on the fail one,
+ * cancel the latter
+ */
+ if (ssk == msk->first)
+ subflow->fail_tout = 0;
+
sock_orphan(ssk);
unlock_sock_fast(ssk, slow);
}
@@ -2852,13 +2879,13 @@ cleanup:
sock_hold(sk);
pr_debug("msk=%p state=%d", sk, sk->sk_state);
if (mptcp_sk(sk)->token)
- mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+ mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
if (sk->sk_state == TCP_CLOSE) {
__mptcp_destroy_sock(sk);
do_cancel_work = true;
} else {
- sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+ mptcp_reset_timeout(msk, 0);
}
release_sock(sk);
if (do_cancel_work)
@@ -2892,12 +2919,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
static int mptcp_disconnect(struct sock *sk, int flags)
{
- struct mptcp_subflow_context *subflow;
+ struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
inet_sk_state_store(sk, TCP_CLOSE);
- mptcp_for_each_subflow(msk, subflow) {
+ list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
__mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_FASTCLOSE);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 200f89f6d62f..480c5320b86e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -306,6 +306,7 @@ struct mptcp_sock {
u32 setsockopt_seq;
char ca_name[TCP_CA_NAME_MAX];
+ struct mptcp_sock *dl_next;
};
#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
@@ -468,7 +469,6 @@ struct mptcp_subflow_context {
local_id_valid : 1, /* local_id is correctly initialized */
valid_csum_seen : 1; /* at least one csum validated */
enum mptcp_data_avail data_avail;
- bool mp_fail_response_expect;
u32 remote_nonce;
u64 thmac;
u32 local_nonce;
@@ -482,6 +482,7 @@ struct mptcp_subflow_context {
u8 stale_count;
long delegated_status;
+ unsigned long fail_tout;
);
@@ -606,8 +607,10 @@ void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow);
+void __mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
@@ -662,6 +665,7 @@ void mptcp_get_options(const struct sk_buff *skb,
void mptcp_finish_connect(struct sock *sk);
void __mptcp_set_connected(struct sock *sk);
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout);
static inline bool mptcp_is_fully_established(struct sock *sk)
{
return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
@@ -768,6 +772,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq);
+int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+ struct mptcp_addr_info *addr,
+ struct mptcp_addr_info *rem,
+ u8 bkup);
bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
const struct mptcp_pm_addr_entry *entry);
void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
@@ -784,7 +792,9 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex);
-
+int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup);
int mptcp_pm_announce_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool echo);
@@ -926,12 +936,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}
-static inline void mptcp_do_fallback(struct sock *sk)
+static inline void mptcp_do_fallback(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct sock *sk = subflow->conn;
+ struct mptcp_sock *msk;
+ msk = mptcp_sk(sk);
__mptcp_do_fallback(msk);
+ if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) {
+ gfp_t saved_allocation = ssk->sk_allocation;
+
+ /* we are in a atomic (BH) scope, override ssk default for data
+ * fin allocation
+ */
+ ssk->sk_allocation = GFP_ATOMIC;
+ ssk->sk_shutdown |= SEND_SHUTDOWN;
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ ssk->sk_allocation = saved_allocation;
+ }
}
#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8841e8cd9ad8..63e8892ec807 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -843,7 +843,8 @@ enum mapping_status {
MAPPING_INVALID,
MAPPING_EMPTY,
MAPPING_DATA_FIN,
- MAPPING_DUMMY
+ MAPPING_DUMMY,
+ MAPPING_BAD_CSUM
};
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
@@ -958,11 +959,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
subflow->map_data_csum);
if (unlikely(csum)) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
- if (subflow->mp_join || subflow->valid_csum_seen) {
- subflow->send_mp_fail = 1;
- MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
- }
- return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
+ return MAPPING_BAD_CSUM;
}
subflow->valid_csum_seen = 1;
@@ -974,7 +971,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool csum_reqd = READ_ONCE(msk->csum_enabled);
- struct sock *sk = (struct sock *)msk;
struct mptcp_ext *mpext;
struct sk_buff *skb;
u16 data_len;
@@ -1016,9 +1012,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
pr_debug("infinite mapping received");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
subflow->map_data_len = 0;
- if (!sock_flag(ssk, SOCK_DEAD))
- sk_stop_timer(sk, &sk->sk_timer);
-
return MAPPING_INVALID;
}
@@ -1165,6 +1158,33 @@ static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
return !subflow->fully_established;
}
+static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ unsigned long fail_tout;
+
+ /* greceful failure can happen only on the MPC subflow */
+ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
+ return;
+
+ /* since the close timeout take precedence on the fail one,
+ * no need to start the latter when the first is already set
+ */
+ if (sock_flag((struct sock *)msk, SOCK_DEAD))
+ return;
+
+ /* we don't need extreme accuracy here, use a zero fail_tout as special
+ * value meaning no fail timeout at all;
+ */
+ fail_tout = jiffies + TCP_RTO_MAX;
+ if (!fail_tout)
+ fail_tout = 1;
+ WRITE_ONCE(subflow->fail_tout, fail_tout);
+ tcp_send_ack(ssk);
+
+ mptcp_reset_timeout(msk, subflow->fail_tout);
+}
+
static bool subflow_check_data_avail(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1184,10 +1204,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
status = get_mapping_status(ssk, msk);
trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
- if (unlikely(status == MAPPING_INVALID))
- goto fallback;
-
- if (unlikely(status == MAPPING_DUMMY))
+ if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY ||
+ status == MAPPING_BAD_CSUM))
goto fallback;
if (status != MAPPING_OK)
@@ -1229,22 +1247,17 @@ no_data:
fallback:
if (!__mptcp_check_fallback(msk)) {
/* RFC 8684 section 3.7. */
- if (subflow->send_mp_fail) {
+ if (status == MAPPING_BAD_CSUM &&
+ (subflow->mp_join || subflow->valid_csum_seen)) {
+ subflow->send_mp_fail = 1;
+
if (!READ_ONCE(msk->allow_infinite_fallback)) {
- ssk->sk_err = EBADMSG;
- tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
- tcp_send_active_reset(ssk, GFP_ATOMIC);
- while ((skb = skb_peek(&ssk->sk_receive_queue)))
- sk_eat_skb(ssk, skb);
- } else if (!sock_flag(ssk, SOCK_DEAD)) {
- WRITE_ONCE(subflow->mp_fail_response_expect, true);
- sk_reset_timer((struct sock *)msk,
- &((struct sock *)msk)->sk_timer,
- jiffies + TCP_RTO_MAX);
+ goto reset;
}
- WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
+ mptcp_subflow_fail(msk, ssk);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
return true;
}
@@ -1252,16 +1265,20 @@ fallback:
/* fatal protocol error, close the socket.
* subflow_error_report() will introduce the appropriate barriers
*/
- ssk->sk_err = EBADMSG;
- tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
+
+reset:
+ ssk->sk_err = EBADMSG;
+ tcp_set_state(ssk, TCP_CLOSE);
+ while ((skb = skb_peek(&ssk->sk_receive_queue)))
+ sk_eat_skb(ssk, skb);
tcp_send_active_reset(ssk, GFP_ATOMIC);
WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
return false;
}
- __mptcp_do_fallback(msk);
+ mptcp_do_fallback(ssk);
}
skb = skb_peek(&ssk->sk_receive_queue);
@@ -1706,6 +1723,58 @@ static void subflow_state_change(struct sock *sk)
}
}
+void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+{
+ struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
+ struct mptcp_sock *msk, *next, *head = NULL;
+ struct request_sock *req;
+
+ /* build a list of all unaccepted mptcp sockets */
+ spin_lock_bh(&queue->rskq_lock);
+ for (req = queue->rskq_accept_head; req; req = req->dl_next) {
+ struct mptcp_subflow_context *subflow;
+ struct sock *ssk = req->sk;
+ struct mptcp_sock *msk;
+
+ if (!sk_is_mptcp(ssk))
+ continue;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ if (!subflow || !subflow->conn)
+ continue;
+
+ /* skip if already in list */
+ msk = mptcp_sk(subflow->conn);
+ if (msk->dl_next || msk == head)
+ continue;
+
+ msk->dl_next = head;
+ head = msk;
+ }
+ spin_unlock_bh(&queue->rskq_lock);
+ if (!head)
+ return;
+
+ /* can't acquire the msk socket lock under the subflow one,
+ * or will cause ABBA deadlock
+ */
+ release_sock(listener_ssk);
+
+ for (msk = head; msk; msk = next) {
+ struct sock *sk = (struct sock *)msk;
+ bool slow;
+
+ slow = lock_sock_fast_nested(sk);
+ next = msk->dl_next;
+ msk->first = NULL;
+ msk->dl_next = NULL;
+ unlock_sock_fast(sk, slow);
+ }
+
+ /* we are still under the listener msk socket lock */
+ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
+}
+
static int subflow_ulp_init(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 78814417d753..80713febfac6 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1803,7 +1803,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
pdev = to_platform_device(dev->dev.parent);
if (pdev) {
np = pdev->dev.of_node;
- if (np && of_get_property(np, "mlx,multi-host", NULL))
+ if (np && (of_get_property(np, "mellanox,multi-host", NULL) ||
+ of_get_property(np, "mlx,multi-host", NULL)))
ndp->mlx_multi_host = true;
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 082a2fd8d85b..369aeabb94fe 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -729,6 +729,9 @@ static void nf_ct_gc_expired(struct nf_conn *ct)
if (!refcount_inc_not_zero(&ct->ct_general.use))
return;
+ /* load ->status after refcount increase */
+ smp_acquire__after_ctrl_dep();
+
if (nf_ct_should_gc(ct))
nf_ct_kill(ct);
@@ -795,6 +798,9 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
*/
ct = nf_ct_tuplehash_to_ctrack(h);
if (likely(refcount_inc_not_zero(&ct->ct_general.use))) {
+ /* re-check key after refcount */
+ smp_acquire__after_ctrl_dep();
+
if (likely(nf_ct_key_equal(h, tuple, zone, net)))
goto found;
@@ -1387,6 +1393,9 @@ static unsigned int early_drop_list(struct net *net,
if (!refcount_inc_not_zero(&tmp->ct_general.use))
continue;
+ /* load ->ct_net and ->status after refcount increase */
+ smp_acquire__after_ctrl_dep();
+
/* kill only if still in same netns -- might have moved due to
* SLAB_TYPESAFE_BY_RCU rules.
*
@@ -1536,6 +1545,9 @@ static void gc_worker(struct work_struct *work)
if (!refcount_inc_not_zero(&tmp->ct_general.use))
continue;
+ /* load ->status after refcount increase */
+ smp_acquire__after_ctrl_dep();
+
if (gc_worker_skip_ct(tmp)) {
nf_ct_put(tmp);
continue;
@@ -1775,6 +1787,16 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
if (!exp)
__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
+ /* Other CPU might have obtained a pointer to this object before it was
+ * released. Because refcount is 0, refcount_inc_not_zero() will fail.
+ *
+ * After refcount_set(1) it will succeed; ensure that zeroing of
+ * ct->status and the correct ct->net pointer are visible; else other
+ * core might observe CONFIRMED bit which means the entry is valid and
+ * in the hash table, but its not (anymore).
+ */
+ smp_wmb();
+
/* Now it is going to be associated with an sk_buff, set refcount to 1. */
refcount_set(&ct->ct_general.use, 1);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 722af5e309ba..f5905b5201a7 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1203,6 +1203,7 @@ restart:
hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (nf_ct_is_expired(ct)) {
+ /* need to defer nf_ct_kill() until lock is released */
if (i < ARRAY_SIZE(nf_ct_evict) &&
refcount_inc_not_zero(&ct->ct_general.use))
nf_ct_evict[i++] = ct;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 6ad7bbc90d38..05895878610c 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -306,6 +306,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use)))
return 0;
+ /* load ->status after refcount increase */
+ smp_acquire__after_ctrl_dep();
+
if (nf_ct_should_gc(ct)) {
nf_ct_kill(ct);
goto release;
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index 77bcb10fc586..cb894f0d63e9 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -67,7 +67,7 @@ dump_arp_packet(struct nf_log_buf *m,
unsigned int logflags;
struct arphdr _arph;
- ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+ ah = skb_header_pointer(skb, nhoff, sizeof(_arph), &_arph);
if (!ah) {
nf_log_buf_add(m, "TRUNCATED");
return;
@@ -96,7 +96,7 @@ dump_arp_packet(struct nf_log_buf *m,
ah->ar_pln != sizeof(__be32))
return;
- ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp);
+ ap = skb_header_pointer(skb, nhoff + sizeof(_arph), sizeof(_arpp), &_arpp);
if (!ap) {
nf_log_buf_add(m, " INCOMPLETE [%zu bytes]",
skb->len - sizeof(_arph));
@@ -149,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
prefix);
- dump_arp_packet(m, loginfo, skb, 0);
+ dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
nf_log_buf_close(m);
}
@@ -850,7 +850,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
if (in)
dump_mac_header(m, loginfo, skb);
- dump_ipv4_packet(net, m, loginfo, skb, 0);
+ dump_ipv4_packet(net, m, loginfo, skb, skb_network_offset(skb));
nf_log_buf_close(m);
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 51144fc66889..646d5fd53604 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5213,13 +5213,20 @@ static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
struct nft_data *data,
struct nlattr *attr)
{
+ u32 dtype;
int err;
err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr);
if (err < 0)
return err;
- if (desc->type != NFT_DATA_VERDICT && desc->len != set->dlen) {
+ if (set->dtype == NFT_DATA_VERDICT)
+ dtype = NFT_DATA_VERDICT;
+ else
+ dtype = NFT_DATA_VALUE;
+
+ if (dtype != desc->type ||
+ set->dlen != desc->len) {
nft_data_release(data, desc->type);
return -EINVAL;
}
@@ -5826,8 +5833,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL))
return -EINVAL;
- if (flags != 0)
- nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+ if (flags != 0) {
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+ if (err < 0)
+ return err;
+ }
if (set->flags & NFT_SET_MAP) {
if (nla[NFTA_SET_ELEM_DATA] == NULL &&
@@ -5936,7 +5946,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (err < 0)
goto err_set_elem_expr;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+ if (err < 0)
+ goto err_parse_key;
}
if (nla[NFTA_SET_ELEM_KEY_END]) {
@@ -5945,22 +5957,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (err < 0)
goto err_parse_key;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ if (err < 0)
+ goto err_parse_key_end;
}
if (timeout > 0) {
- nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
- if (timeout != set->timeout)
- nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
+ if (err < 0)
+ goto err_parse_key_end;
+
+ if (timeout != set->timeout) {
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+ if (err < 0)
+ goto err_parse_key_end;
+ }
}
if (num_exprs) {
for (i = 0; i < num_exprs; i++)
size += expr_array[i]->ops->size;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
- sizeof(struct nft_set_elem_expr) +
- size);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
+ sizeof(struct nft_set_elem_expr) + size);
+ if (err < 0)
+ goto err_parse_key_end;
}
if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
@@ -5975,7 +5996,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
err = PTR_ERR(obj);
goto err_parse_key_end;
}
- nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+ if (err < 0)
+ goto err_parse_key_end;
}
if (nla[NFTA_SET_ELEM_DATA] != NULL) {
@@ -6009,7 +6032,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
NFT_VALIDATE_NEED);
}
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+ if (err < 0)
+ goto err_parse_data;
}
/* The full maximum length of userdata can exceed the maximum
@@ -6019,9 +6044,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
ulen = 0;
if (nla[NFTA_SET_ELEM_USERDATA] != NULL) {
ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]);
- if (ulen > 0)
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
- ulen);
+ if (ulen > 0) {
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
+ ulen);
+ if (err < 0)
+ goto err_parse_data;
+ }
}
err = -ENOMEM;
@@ -6249,8 +6277,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
nft_set_ext_prepare(&tmpl);
- if (flags != 0)
- nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+ if (flags != 0) {
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+ if (err < 0)
+ return err;
+ }
if (nla[NFTA_SET_ELEM_KEY]) {
err = nft_setelem_parse_key(ctx, set, &elem.key.val,
@@ -6258,16 +6289,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
if (err < 0)
return err;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+ if (err < 0)
+ goto fail_elem;
}
if (nla[NFTA_SET_ELEM_KEY_END]) {
err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
nla[NFTA_SET_ELEM_KEY_END]);
if (err < 0)
- return err;
+ goto fail_elem;
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+ if (err < 0)
+ goto fail_elem_key_end;
}
err = -ENOMEM;
@@ -6275,7 +6310,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
elem.key_end.val.data, NULL, 0, 0,
GFP_KERNEL_ACCOUNT);
if (elem.priv == NULL)
- goto fail_elem;
+ goto fail_elem_key_end;
ext = nft_set_elem_ext(set, elem.priv);
if (flags)
@@ -6299,6 +6334,8 @@ fail_ops:
kfree(trans);
fail_trans:
kfree(elem.priv);
+fail_elem_key_end:
+ nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
fail_elem:
nft_data_release(&elem.key.val, NFT_DATA_VALUE);
return err;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 53f40e473855..3ddce24ac76d 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -25,9 +25,7 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info,
const struct nft_chain *chain,
enum nft_trace_types type)
{
- const struct nft_pktinfo *pkt = info->pkt;
-
- if (!info->trace || !pkt->skb->nf_trace)
+ if (!info->trace || !info->nf_trace)
return;
info->chain = chain;
@@ -42,11 +40,24 @@ static inline void nft_trace_packet(struct nft_traceinfo *info,
enum nft_trace_types type)
{
if (static_branch_unlikely(&nft_trace_enabled)) {
+ const struct nft_pktinfo *pkt = info->pkt;
+
+ info->nf_trace = pkt->skb->nf_trace;
info->rule = rule;
__nft_trace_packet(info, chain, type);
}
}
+static inline void nft_trace_copy_nftrace(struct nft_traceinfo *info)
+{
+ if (static_branch_unlikely(&nft_trace_enabled)) {
+ const struct nft_pktinfo *pkt = info->pkt;
+
+ if (info->trace)
+ info->nf_trace = pkt->skb->nf_trace;
+ }
+}
+
static void nft_bitwise_fast_eval(const struct nft_expr *expr,
struct nft_regs *regs)
{
@@ -85,6 +96,7 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
const struct nft_chain *chain,
const struct nft_regs *regs)
{
+ const struct nft_pktinfo *pkt = info->pkt;
enum nft_trace_types type;
switch (regs->verdict.code) {
@@ -92,8 +104,13 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
case NFT_RETURN:
type = NFT_TRACETYPE_RETURN;
break;
+ case NF_STOLEN:
+ type = NFT_TRACETYPE_RULE;
+ /* can't access skb->nf_trace; use copy */
+ break;
default:
type = NFT_TRACETYPE_RULE;
+ info->nf_trace = pkt->skb->nf_trace;
break;
}
@@ -254,6 +271,7 @@ next_rule:
switch (regs.verdict.code) {
case NFT_BREAK:
regs.verdict.code = NFT_CONTINUE;
+ nft_trace_copy_nftrace(&info);
continue;
case NFT_CONTINUE:
nft_trace_packet(&info, chain, rule,
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index 5041725423c2..1163ba9c1401 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -7,7 +7,7 @@
#include <linux/module.h>
#include <linux/static_key.h>
#include <linux/hash.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/skbuff.h>
@@ -25,22 +25,6 @@
DEFINE_STATIC_KEY_FALSE(nft_trace_enabled);
EXPORT_SYMBOL_GPL(nft_trace_enabled);
-static int trace_fill_id(struct sk_buff *nlskb, struct sk_buff *skb)
-{
- __be32 id;
-
- /* using skb address as ID results in a limited number of
- * values (and quick reuse).
- *
- * So we attempt to use as many skb members that will not
- * change while skb is with netfilter.
- */
- id = (__be32)jhash_2words(hash32_ptr(skb), skb_get_hash(skb),
- skb->skb_iif);
-
- return nla_put_be32(nlskb, NFTA_TRACE_ID, id);
-}
-
static int trace_fill_header(struct sk_buff *nlskb, u16 type,
const struct sk_buff *skb,
int off, unsigned int len)
@@ -186,6 +170,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
struct nlmsghdr *nlh;
struct sk_buff *skb;
unsigned int size;
+ u32 mark = 0;
u16 event;
if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE))
@@ -229,7 +214,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type)))
goto nla_put_failure;
- if (trace_fill_id(skb, pkt->skb))
+ if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_TRACE_CHAIN, info->chain->name))
@@ -249,16 +234,24 @@ void nft_trace_notify(struct nft_traceinfo *info)
case NFT_TRACETYPE_RULE:
if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict))
goto nla_put_failure;
+
+ /* pkt->skb undefined iff NF_STOLEN, disable dump */
+ if (info->verdict->code == NF_STOLEN)
+ info->packet_dumped = true;
+ else
+ mark = pkt->skb->mark;
+
break;
case NFT_TRACETYPE_POLICY:
+ mark = pkt->skb->mark;
+
if (nla_put_be32(skb, NFTA_TRACE_POLICY,
htonl(info->basechain->policy)))
goto nla_put_failure;
break;
}
- if (pkt->skb->mark &&
- nla_put_be32(skb, NFTA_TRACE_MARK, htonl(pkt->skb->mark)))
+ if (mark && nla_put_be32(skb, NFTA_TRACE_MARK, htonl(mark)))
goto nla_put_failure;
if (!info->packet_dumped) {
@@ -283,9 +276,20 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt,
const struct nft_verdict *verdict,
const struct nft_chain *chain)
{
+ static siphash_key_t trace_key __read_mostly;
+ struct sk_buff *skb = pkt->skb;
+
info->basechain = nft_base_chain(chain);
info->trace = true;
+ info->nf_trace = pkt->skb->nf_trace;
info->packet_dumped = false;
info->pkt = pkt;
info->verdict = verdict;
+
+ net_get_random_once(&trace_key, sizeof(trace_key));
+
+ info->skbid = (u32)siphash_3u32(hash32_ptr(skb),
+ skb_get_hash(skb),
+ skb->skb_iif,
+ &trace_key);
}
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index df40314de21f..76de6c8d9865 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -143,6 +143,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
/* Another cpu may race to insert the element with the same key */
if (prev) {
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
he = prev;
}
@@ -152,6 +153,7 @@ out:
err2:
nft_set_elem_destroy(set, he, true);
+ atomic_dec(&set->nelems);
err1:
return false;
}
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 2c8051d8cca6..4f9299b9dcdd 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2125,6 +2125,32 @@ out_scratch:
}
/**
+ * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array
+ * @set: nftables API set representation
+ * @m: matching data pointing to key mapping array
+ */
+static void nft_set_pipapo_match_destroy(const struct nft_set *set,
+ struct nft_pipapo_match *m)
+{
+ struct nft_pipapo_field *f;
+ int i, r;
+
+ for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
+ ;
+
+ for (r = 0; r < f->rules; r++) {
+ struct nft_pipapo_elem *e;
+
+ if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
+ continue;
+
+ e = f->mt[r].e;
+
+ nft_set_elem_destroy(set, e, true);
+ }
+}
+
+/**
* nft_pipapo_destroy() - Free private data for set and all committed elements
* @set: nftables API set representation
*/
@@ -2132,26 +2158,13 @@ static void nft_pipapo_destroy(const struct nft_set *set)
{
struct nft_pipapo *priv = nft_set_priv(set);
struct nft_pipapo_match *m;
- struct nft_pipapo_field *f;
- int i, r, cpu;
+ int cpu;
m = rcu_dereference_protected(priv->match, true);
if (m) {
rcu_barrier();
- for (i = 0, f = m->f; i < m->field_count - 1; i++, f++)
- ;
-
- for (r = 0; r < f->rules; r++) {
- struct nft_pipapo_elem *e;
-
- if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e)
- continue;
-
- e = f->mt[r].e;
-
- nft_set_elem_destroy(set, e, true);
- }
+ nft_set_pipapo_match_destroy(set, m);
#ifdef NFT_PIPAPO_ALIGN
free_percpu(m->scratch_aligned);
@@ -2165,6 +2178,11 @@ static void nft_pipapo_destroy(const struct nft_set *set)
}
if (priv->clone) {
+ m = priv->clone;
+
+ if (priv->dirty)
+ nft_set_pipapo_match_destroy(set, m);
+
#ifdef NFT_PIPAPO_ALIGN
free_percpu(priv->clone->scratch_aligned);
#endif
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index fee6409c2bb3..eb0b8197ac82 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -227,8 +227,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh)
{
struct rose_neigh *s;
- rose_stop_ftimer(rose_neigh);
- rose_stop_t0timer(rose_neigh);
+ del_timer_sync(&rose_neigh->ftimer);
+ del_timer_sync(&rose_neigh->t0timer);
skb_queue_purge(&rose_neigh->queue);
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index b3138fc2e552..f06ddbed3fed 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct timer_list *);
void rose_start_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
sk->sk_timer.function = rose_heartbeat_expiry;
sk->sk_timer.expires = jiffies + 5 * HZ;
- add_timer(&sk->sk_timer);
+ sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
}
void rose_start_t1timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t1;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t2timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t2;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_t3timer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->t3;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_hbtimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->timer);
+ sk_stop_timer(sk, &rose->timer);
rose->timer.function = rose_timer_expiry;
rose->timer.expires = jiffies + rose->hb;
- add_timer(&rose->timer);
+ sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}
void rose_start_idletimer(struct sock *sk)
{
struct rose_sock *rose = rose_sk(sk);
- del_timer(&rose->idletimer);
+ sk_stop_timer(sk, &rose->idletimer);
if (rose->idle > 0) {
rose->idletimer.function = rose_idletimer_expiry;
rose->idletimer.expires = jiffies + rose->idle;
- add_timer(&rose->idletimer);
+ sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
}
}
void rose_stop_heartbeat(struct sock *sk)
{
- del_timer(&sk->sk_timer);
+ sk_stop_timer(sk, &sk->sk_timer);
}
void rose_stop_timer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->timer);
+ sk_stop_timer(sk, &rose_sk(sk)->timer);
}
void rose_stop_idletimer(struct sock *sk)
{
- del_timer(&rose_sk(sk)->idletimer);
+ sk_stop_timer(sk, &rose_sk(sk)->idletimer);
}
static void rose_heartbeat_expiry(struct timer_list *t)
@@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
bh_unlock_sock(sk);
rose_destroy_socket(sk);
+ sock_put(sk);
return;
}
break;
@@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
rose_start_heartbeat(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_timer_expiry(struct timer_list *t)
@@ -181,6 +183,7 @@ static void rose_timer_expiry(struct timer_list *t)
break;
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void rose_idletimer_expiry(struct timer_list *t)
@@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index da9733da9868..817065aa2833 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -588,7 +588,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p)
}
static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
- const struct tc_action_ops *ops)
+ const struct tc_action_ops *ops,
+ struct netlink_ext_ack *extack)
{
struct nlattr *nest;
int n_i = 0;
@@ -604,20 +605,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
if (nla_put_string(skb, TCA_KIND, ops->kind))
goto nla_put_failure;
+ ret = 0;
mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, tmp, id) {
if (IS_ERR(p))
continue;
ret = tcf_idr_release_unsafe(p);
- if (ret == ACT_P_DELETED) {
+ if (ret == ACT_P_DELETED)
module_put(ops->owner);
- n_i++;
- } else if (ret < 0) {
- mutex_unlock(&idrinfo->lock);
- goto nla_put_failure;
- }
+ else if (ret < 0)
+ break;
+ n_i++;
}
mutex_unlock(&idrinfo->lock);
+ if (ret < 0) {
+ if (n_i)
+ NL_SET_ERR_MSG(extack, "Unable to flush all TC actions");
+ else
+ goto nla_put_failure;
+ }
ret = nla_put_u32(skb, TCA_FCNT, n_i);
if (ret)
@@ -638,7 +644,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
struct tcf_idrinfo *idrinfo = tn->idrinfo;
if (type == RTM_DELACTION) {
- return tcf_del_walker(idrinfo, skb, ops);
+ return tcf_del_walker(idrinfo, skb, ops, extack);
} else if (type == RTM_GETACTION) {
return tcf_dump_walker(idrinfo, skb, cb);
} else {
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 79c8901f66ab..b759628a47c2 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -442,7 +442,7 @@ static int tcf_police_act_to_flow_act(int tc_act, u32 *extval,
act_id = FLOW_ACTION_JUMP;
*extval = tc_act & TC_ACT_EXT_VAL_MASK;
} else if (tc_act == TC_ACT_UNSPEC) {
- NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform/exceed action is \"continue\"");
+ act_id = FLOW_ACTION_CONTINUE;
} else {
NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload");
}
diff --git a/net/socket.c b/net/socket.c
index 2bc8773d9dc5..96300cdc0625 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2149,10 +2149,13 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
struct sockaddr __user *addr, int __user *addr_len)
{
+ struct sockaddr_storage address;
+ struct msghdr msg = {
+ /* Save some cycles and don't copy the address if not needed */
+ .msg_name = addr ? (struct sockaddr *)&address : NULL,
+ };
struct socket *sock;
struct iovec iov;
- struct msghdr msg;
- struct sockaddr_storage address;
int err, err2;
int fput_needed;
@@ -2163,14 +2166,6 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
if (!sock)
goto out;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- /* Save some cycles and don't copy the address if not needed */
- msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
- /* We assume all kernel code knows the size of sockaddr_storage */
- msg.msg_namelen = 0;
- msg.msg_iocb = NULL;
- msg.msg_flags = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, flags);
@@ -2375,6 +2370,7 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
return -EFAULT;
kmsg->msg_control_is_user = true;
+ kmsg->msg_get_inq = 0;
kmsg->msg_control_user = msg.msg_control;
kmsg->msg_controllen = msg.msg_controllen;
kmsg->msg_flags = msg.msg_flags;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index f87a2d8f23a7..5d2b3e6979fb 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -984,7 +984,7 @@ static noinline __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
p = page_address(*xdr->page_ptr);
xdr->p = p + frag2bytes;
space_left = xdr->buf->buflen - xdr->buf->len;
- if (space_left - nbytes >= PAGE_SIZE)
+ if (space_left - frag1bytes >= PAGE_SIZE)
xdr->end = p + PAGE_SIZE;
else
xdr->end = p + space_left - frag1bytes;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6ef95ce565bd..b48d97cbbe29 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -472,8 +472,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
bool preliminary)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_link *l, *snd_l = tipc_bc_sndlink(net);
struct tipc_node *n, *temp_node;
- struct tipc_link *l;
unsigned long intv;
int bearer_id;
int i;
@@ -488,6 +488,16 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
goto exit;
/* A preliminary node becomes "real" now, refresh its data */
tipc_node_write_lock(n);
+ if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+ tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+ n->capabilities, &n->bc_entry.inputq1,
+ &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+ pr_warn("Broadcast rcv link refresh failed, no memory\n");
+ tipc_node_write_unlock_fast(n);
+ tipc_node_put(n);
+ n = NULL;
+ goto exit;
+ }
n->preliminary = false;
n->addr = addr;
hlist_del_rcu(&n->hash);
@@ -567,7 +577,16 @@ update:
n->signature = INVALID_NODE_SIG;
n->active_links[0] = INVALID_BEARER_ID;
n->active_links[1] = INVALID_BEARER_ID;
- n->bc_entry.link = NULL;
+ if (!preliminary &&
+ !tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+ tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+ n->capabilities, &n->bc_entry.inputq1,
+ &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+ pr_warn("Broadcast rcv link creation failed, no memory\n");
+ kfree(n);
+ n = NULL;
+ goto exit;
+ }
tipc_node_get(n);
timer_setup(&n->timer, tipc_node_timeout, 0);
/* Start a slow timer anyway, crypto needs it */
@@ -1155,7 +1174,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
bool *respond, bool *dupl_addr)
{
struct tipc_node *n;
- struct tipc_link *l, *snd_l;
+ struct tipc_link *l;
struct tipc_link_entry *le;
bool addr_match = false;
bool sign_match = false;
@@ -1175,22 +1194,6 @@ void tipc_node_check_dest(struct net *net, u32 addr,
return;
tipc_node_write_lock(n);
- if (unlikely(!n->bc_entry.link)) {
- snd_l = tipc_bc_sndlink(net);
- if (!tipc_link_bc_create(net, tipc_own_addr(net),
- addr, peer_id, U16_MAX,
- tipc_link_min_win(snd_l),
- tipc_link_max_win(snd_l),
- n->capabilities,
- &n->bc_entry.inputq1,
- &n->bc_entry.namedq, snd_l,
- &n->bc_entry.link)) {
- pr_warn("Broadcast rcv link creation failed, no mem\n");
- tipc_node_write_unlock_fast(n);
- tipc_node_put(n);
- return;
- }
- }
le = &n->links[b->identity];
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 17f8c523e33b..43509c7e90fc 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sock_init_data(sock, sk);
tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
+ sk_free(sk);
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index ec6f4b699a2b..ce827e79c66a 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1419,9 +1419,9 @@ static struct notifier_block tls_dev_notifier = {
.notifier_call = tls_dev_event,
};
-void __init tls_device_init(void)
+int __init tls_device_init(void)
{
- register_netdevice_notifier(&tls_dev_notifier);
+ return register_netdevice_notifier(&tls_dev_notifier);
}
void __exit tls_device_cleanup(void)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 2ffede463e4a..d80ab3d1764e 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -1048,7 +1048,12 @@ static int __init tls_register(void)
if (err)
return err;
- tls_device_init();
+ err = tls_device_init();
+ if (err) {
+ unregister_pernet_subsys(&tls_proc_ops);
+ return err;
+ }
+
tcp_register_ulp(&tcp_tls_ulp_ops);
return 0;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0513f82b8537..e30649f6dde5 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -267,9 +267,6 @@ static int tls_do_decryption(struct sock *sk,
}
darg->async = false;
- if (ret == -EBADMSG)
- TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR);
-
return ret;
}
@@ -1579,8 +1576,11 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
}
err = decrypt_internal(sk, skb, dest, NULL, darg);
- if (err < 0)
+ if (err < 0) {
+ if (err == -EBADMSG)
+ TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR);
return err;
+ }
if (darg->async)
goto decrypt_next;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index ff4d48fcbfb2..607a68911047 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1031,7 +1031,8 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid)
{
ASSERT_WDEV_LOCK(wdev);
- if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
+ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION &&
+ wdev->iftype != NL80211_IFTYPE_P2P_CLIENT))
return;
if (WARN_ON(!wdev->current_bss) ||
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 87bdd71c7bb6..f70112176b7c 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -332,6 +332,7 @@ static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
for (i = 0; i < dma_map->dma_pages_cnt; i++) {
dma = &dma_map->dma_pages[i];
if (*dma) {
+ *dma &= ~XSK_NEXT_PG_CONTIG_MASK;
dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
DMA_BIDIRECTIONAL, attrs);
*dma = 0;