diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-12-22 09:54:33 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-12-22 09:54:33 -0800 |
commit | 78bac77b521b032f96077c21241cc5d5668482c5 (patch) | |
tree | 587f81f6f40d045d6322d40171b2ab43aff21235 /net | |
parent | 0dd1e3773ae8afc4bfdce782bdeffc10f9cae6ec (diff) | |
parent | 4bfeadfc0712bbc8a6556eef6d47cbae1099dea3 (diff) | |
download | linux-78bac77b521b032f96077c21241cc5d5668482c5.tar.gz linux-78bac77b521b032f96077c21241cc5d5668482c5.tar.bz2 linux-78bac77b521b032f96077c21241cc5d5668482c5.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller:
1) Several nf_flow_table_offload fixes from Pablo Neira Ayuso,
including adding a missing ipv6 match description.
2) Several heap overflow fixes in mwifiex from qize wang and Ganapathi
Bhat.
3) Fix uninit value in bond_neigh_init(), from Eric Dumazet.
4) Fix non-ACPI probing of nxp-nci, from Stephan Gerhold.
5) Fix use after free in tipc_disc_rcv(), from Tuong Lien.
6) Enforce limit of 33 tail calls in mips and riscv JIT, from Paul
Chaignon.
7) Multicast MAC limit test is off by one in qede, from Manish Chopra.
8) Fix established socket lookup race when socket goes from
TCP_ESTABLISHED to TCP_LISTEN, because there lacks an intervening
RCU grace period. From Eric Dumazet.
9) Don't send empty SKBs from tcp_write_xmit(), also from Eric Dumazet.
10) Fix active backup transition after link failure in bonding, from
Mahesh Bandewar.
11) Avoid zero sized hash table in gtp driver, from Taehee Yoo.
12) Fix wrong interface passed to ->mac_link_up(), from Russell King.
13) Fix DSA egress flooding settings in b53, from Florian Fainelli.
14) Memory leak in gmac_setup_txqs(), from Navid Emamdoost.
15) Fix double free in dpaa2-ptp code, from Ioana Ciornei.
16) Reject invalid MTU values in stmmac, from Jose Abreu.
17) Fix refcount leak in error path of u32 classifier, from Davide
Caratti.
18) Fix regression causing iwlwifi firmware crashes on boot, from Anders
Kaseorg.
19) Fix inverted return value logic in llc2 code, from Chan Shu Tak.
20) Disable hardware GRO when XDP is attached to qede, frm Manish
Chopra.
21) Since we encode state in the low pointer bits, dst metrics must be
at least 4 byte aligned, which is not necessarily true on m68k. Add
annotations to fix this, from Geert Uytterhoeven.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (160 commits)
sfc: Include XDP packet headroom in buffer step size.
sfc: fix channel allocation with brute force
net: dst: Force 4-byte alignment of dst_metrics
selftests: pmtu: fix init mtu value in description
hv_netvsc: Fix unwanted rx_table reset
net: phy: ensure that phy IDs are correctly typed
mod_devicetable: fix PHY module format
qede: Disable hardware gro when xdp prog is installed
net: ena: fix issues in setting interrupt moderation params in ethtool
net: ena: fix default tx interrupt moderation interval
net/smc: unregister ib devices in reboot_event
net: stmmac: platform: Fix MDIO init for platforms without PHY
llc2: Fix return statement of llc_stat_ev_rx_null_dsap_xid_c (and _test_c)
net: hisilicon: Fix a BUG trigered by wrong bytes_compl
net: dsa: ksz: use common define for tag len
s390/qeth: don't return -ENOTSUPP to userspace
s390/qeth: fix promiscuous mode after reset
s390/qeth: handle error due to unsupported transport mode
cxgb4: fix refcount init for TC-MQPRIO offload
tc-testing: initial tdc selftests for cls_u32
...
Diffstat (limited to 'net')
50 files changed, 583 insertions, 274 deletions
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index af7800103e51..59980ecfc962 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -662,6 +662,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index de09b0a65791..f7587428febd 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -423,9 +423,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); - struct j1939_priv *priv = jsk->priv; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct j1939_priv *priv; + struct sock *sk; + struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); @@ -434,6 +434,10 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sock->sk); + priv = jsk->priv; + sk = sock->sk; + net = sock_net(sk); + /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not diff --git a/net/core/filter.c b/net/core/filter.c index c19dd0973e0c..28b3c258188c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2055,6 +2055,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 652da6369037..920784a9b7ff 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5c4624298996..4c826b8bf9b1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger rx_queue_release call which + * decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; - dev_hold(queue->dev); - if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) diff --git a/net/core/sock.c b/net/core/sock.c index 043db3ce023e..8459ad579f73 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2916,7 +2916,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eb29e5adc84d..9f9e00ba3ad7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -288,6 +288,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -298,6 +299,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9ef2caa13f27..c66abbed4daf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -124,7 +124,8 @@ static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, return NULL; } -struct dsa_link *dsa_link_touch(struct dsa_port *dp, struct dsa_port *link_dp) +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 73605bcbb385..90d055c4df9e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -84,8 +84,6 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ -#define KSZ8795_INGRESS_TAG_LEN 1 - #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -96,12 +94,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ8795_INGRESS_TAG_LEN); + nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); if (!nskb) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(nskb); *tag = 1 << dp->index; @@ -124,7 +122,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ8795_INGRESS_TAG_LEN, + .overhead = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3e50ac24fe41..d885ba868822 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1087,8 +1087,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1419,8 +1418,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 32772d6ded4e..a6545ef0d27b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92282f98dc82..1c7326e04f9b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b184f03d7437..1f7735ca8f22 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1725,7 +1725,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -2260,7 +2260,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 98d82305d6de..39d861d00377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 63cb0028b02d..9fc2968856c0 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -442,7 +442,7 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, return 0; sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx > sband->n_bitrates) + if (!sband || status->rate_idx >= sband->n_bitrates) return 0; rate = &sband->bitrates[status->rate_idx]; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b3c9001d1f43..c80b1e163ea4 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -201,8 +201,6 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; s64 deficit[IEEE80211_NUM_ACS]; - u32 q_depth[IEEE80211_NUM_ACS]; - u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -214,6 +212,56 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime_weight, + deficit[0], deficit[1], deficit[2], deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + +static ssize_t sta_aql_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 400; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u32 q_depth[IEEE80211_NUM_ACS]; + u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->active_txq_lock[ac]); @@ -221,12 +269,8 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, } p += scnprintf(p, bufsz + buf - p, - "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n" "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3], q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]), @@ -236,11 +280,10 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return rv; } -static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, +static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; - struct ieee80211_local *local = sta->sdata->local; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; @@ -251,7 +294,7 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; - if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h) + if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; @@ -261,17 +304,10 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].rx_airtime = 0; - sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); - } - return count; } -STA_OPS_RW(airtime); +STA_OPS_RW(aql); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -996,6 +1032,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AQL)) + DEBUGFS_ADD(aql); + debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6cca0853f183..4c2b5ba3ac09 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -672,9 +672,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } - local->airtime_flags = AIRTIME_USE_TX | - AIRTIME_USE_RX | - AIRTIME_USE_AQL; + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; local->aql_threshold = IEEE80211_AQL_THRESHOLD; atomic_set(&local->aql_total_pending_airtime, 0); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 8eafd81e97b4..0f5f40678885 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1916,6 +1916,9 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, { int tx_pending; + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) + return; + if (!tx_completed) { if (sta) atomic_add(tx_airtime, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ad5d8a4ae56d..c00e28585f9d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,7 +127,6 @@ enum ieee80211_agg_stop_reason { /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) -#define AIRTIME_USE_AQL BIT(2) struct airtime_info { u64 rx_airtime; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b696b9136f4c..a8a7306a1f56 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2256,6 +2256,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | @@ -3668,7 +3677,7 @@ begin: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (local->airtime_flags & AIRTIME_USE_AQL) { + if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -3790,7 +3799,7 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct sta_info *sta; struct ieee80211_local *local = hw_to_local(hw); - if (!(local->airtime_flags & AIRTIME_USE_AQL)) + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return true; if (!txq->sta) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0af1898af2b8..f475fec84536 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -895,9 +895,10 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } /* Resolve race on insertion if this protocol allows this. */ -static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +static __cold noinline int +nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_tuple_hash *h) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d8d33ef52ce0..6a1c8f1f6171 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3626,6 +3626,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index c54c9a6cc981..de7a0d1e15c8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -28,6 +28,7 @@ struct nf_flow_key { struct flow_dissector_key_basic basic; union { struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ports tp; @@ -57,6 +58,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); @@ -69,9 +71,18 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->ipv4.dst = tuple->dst_v4.s_addr; mask->ipv4.dst = 0xffffffff; break; + case AF_INET6: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + key->basic.n_proto = htons(ETH_P_IPV6); + key->ipv6.src = tuple->src_v6; + memset(&mask->ipv6.src, 0xff, sizeof(mask->ipv6.src)); + key->ipv6.dst = tuple->dst_v6; + memset(&mask->ipv6.dst, 0xff, sizeof(mask->ipv6.dst)); + break; default: return -EOPNOTSUPP; } + match->dissector.used_keys |= BIT(key->control.addr_type); mask->basic.n_proto = 0xffff; switch (tuple->l4proto) { @@ -96,14 +107,13 @@ static int nf_flow_rule_match(struct nf_flow_match *match, match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; } static void flow_offload_mangle(struct flow_action_entry *entry, - enum flow_action_mangle_base htype, - u32 offset, u8 *value, u8 *mask) + enum flow_action_mangle_base htype, u32 offset, + const __be32 *value, const __be32 *mask) { entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; @@ -140,12 +150,12 @@ static int flow_offload_eth_src(struct net *net, memcpy(&val16, dev->dev_addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0xffffffff; memcpy(&val, dev->dev_addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, - (u8 *)&val, (u8 *)&mask); + &val, &mask); dev_put(dev); return 0; @@ -170,13 +180,13 @@ static int flow_offload_eth_dst(struct net *net, mask = ~0xffffffff; memcpy(&val, n->ha, 4); flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0x0000ffff; memcpy(&val16, n->ha + 4, 2); val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); neigh_release(n); return 0; @@ -206,7 +216,7 @@ static void flow_offload_ipv4_snat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv4_dnat(struct net *net, @@ -233,12 +243,12 @@ static void flow_offload_ipv4_dnat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, unsigned int offset, - u8 *addr, u8 *mask) + const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; int i; @@ -246,8 +256,7 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, - &addr[i], mask); + offset + i, &addr[i], mask); } } @@ -257,23 +266,23 @@ static void flow_offload_ipv6_snat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static void flow_offload_ipv6_dnat(struct net *net, @@ -282,23 +291,23 @@ static void flow_offload_ipv6_dnat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static int flow_offload_l4proto(const struct flow_offload *flow) @@ -326,25 +335,24 @@ static void flow_offload_port_snat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff0000); - __be16 port; + u32 mask = ~htonl(0xffff0000), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port << 16); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_port_dnat(struct net *net, @@ -353,25 +361,24 @@ static void flow_offload_port_dnat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff); - __be16 port; + u32 mask = ~htonl(0xffff), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_ipv4_checksum(struct net *net, @@ -574,7 +581,7 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, cls_flow.rule = flow_rule->rule; list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { - err = block_cb->cb(TC_SETUP_FT, &cls_flow, + err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) continue; @@ -599,7 +606,7 @@ static void flow_offload_tuple_del(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; } @@ -656,7 +663,7 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); memcpy(stats, &cls_flow.stats, sizeof(*stats)); } @@ -822,7 +829,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); if (err < 0) return err; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a2b58de82600..f8f52ff99cfb 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -189,7 +189,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c26a5663795e..273f3838318b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4519,8 +4519,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4756,14 +4758,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5476,7 +5484,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = nft_obj_type_get(net, objtype); + type = __nft_obj_type_get(objtype); nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 431f3b803bfb..a9ea29afb09f 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -44,6 +44,9 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + if (num_actions == 0) + return ERR_PTR(-EOPNOTSUPP); + flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); @@ -577,6 +580,9 @@ static int nft_offload_netdev_event(struct notifier_block *this, struct net *net = dev_net(dev); struct nft_chain *chain; + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); if (chain) diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 02afa752dd2e..10e9d50e4e19 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -80,7 +80,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -89,7 +89,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index b8092069f868..8a28c127effc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -81,6 +81,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 57123259452f..a9f804f7a04a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -74,8 +74,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -88,7 +93,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +144,10 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,7 +155,11 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 53c1d41fb1c9..118cd66b7516 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, msec = 1; div = ecmd.base.speed / 1000; } - } + } else + return DEFAULT_PRB_RETIRE_TOV; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 461d75274fb3..971c73c7d34c 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a0e6fac613de..66c6bcec16cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,10 +1108,33 @@ erridr: return err; } +static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) +{ + int i; + + if (!ht) + return true; + if (!ht->is_root) { + *non_root_ht = true; + return false; + } + if (*non_root_ht) + return false; + if (ht->refcnt < 2) + return true; + + for (i = 0; i <= ht->divisor; i++) { + if (rtnl_dereference(ht->ht[i])) + return false; + } + return true; +} + static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; + bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1124,6 +1147,8 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; + if (u32_hnode_empty(ht, &non_root_ht)) + return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fbbf19128c2d..78af2fcf90cc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e83cdaa2ab76..6a30392068a0 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,8 +84,10 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->out); return ret; + } stream->outcnt = outcnt; return 0; @@ -100,8 +102,10 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->in); return ret; + } stream->incnt = incnt; return 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b997072c72e5..cee5bf4a9bb9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bb92c7c6214c..e419ff277e55 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1287,7 +1287,7 @@ static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); - + smc_ib_unregister_client(); return 0; } diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 55aeba681cf4..656ebc79c64e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index b043e8c6397a..bfe43da127c0 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -194,6 +194,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); + u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); @@ -242,9 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, return; if (!tipc_in_scope(legacy, b->domain, src)) return; - tipc_node_check_dest(net, src, peer_id, b, caps, signature, - msg_peer_net_hash(hdr), &maddr, &respond, - &dupl_addr); + tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, + &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92d04dc2a44b..359b2bc888cf 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -36,6 +36,7 @@ #include <net/sock.h> #include <linux/list_sort.h> +#include <linux/rbtree_augmented.h> #include "core.h" #include "netlink.h" #include "name_table.h" @@ -51,6 +52,7 @@ * @lower: service range lower bound * @upper: service range upper bound * @tree_node: member of service range RB tree + * @max: largest 'upper' in this node subtree * @local_publ: list of identical publications made from this node * Used by closest_first lookup and multicast lookup algorithm * @all_publ: all publications identical to this one, whatever node and scope @@ -60,6 +62,7 @@ struct service_range { u32 lower; u32 upper; struct rb_node tree_node; + u32 max; struct list_head local_publ; struct list_head all_publ; }; @@ -84,6 +87,130 @@ struct tipc_service { struct rcu_head rcu; }; +#define service_range_upper(sr) ((sr)->upper) +RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks, + struct service_range, tree_node, u32, max, + service_range_upper) + +#define service_range_entry(rbtree_node) \ + (container_of(rbtree_node, struct service_range, tree_node)) + +#define service_range_overlap(sr, start, end) \ + ((sr)->lower <= (end) && (sr)->upper >= (start)) + +/** + * service_range_foreach_match - iterate over tipc service rbtree for each + * range match + * @sr: the service range pointer as a loop cursor + * @sc: the pointer to tipc service which holds the service range rbtree + * @start, end: the range (end >= start) for matching + */ +#define service_range_foreach_match(sr, sc, start, end) \ + for (sr = service_range_match_first((sc)->ranges.rb_node, \ + start, \ + end); \ + sr; \ + sr = service_range_match_next(&(sr)->tree_node, \ + start, \ + end)) + +/** + * service_range_match_first - find first service range matching a range + * @n: the root node of service range rbtree for searching + * @start, end: the range (end >= start) for matching + * + * Return: the leftmost service range node in the rbtree that overlaps the + * specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_first(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *l, *r; + + /* Non overlaps in tree at all? */ + if (!n || service_range_entry(n)->max < start) + return NULL; + + while (n) { + l = n->rb_left; + if (l && service_range_entry(l)->max >= start) { + /* A leftmost overlap range node must be one in the left + * subtree. If not, it has lower > end, then nodes on + * the right side cannot satisfy the condition either. + */ + n = l; + continue; + } + + /* No one in the left subtree can match, return if this node is + * an overlap i.e. leftmost. + */ + sr = service_range_entry(n); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup on the right side */ + r = n->rb_right; + if (sr->lower <= end && + r && service_range_entry(r)->max >= start) { + n = r; + continue; + } + break; + } + + return NULL; +} + +/** + * service_range_match_next - find next service range matching a range + * @n: a node in service range rbtree from which the searching starts + * @start, end: the range (end >= start) for matching + * + * Return: the next service range node to the given node in the rbtree that + * overlaps the specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_next(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *p, *r; + + while (n) { + r = n->rb_right; + if (r && service_range_entry(r)->max >= start) + /* A next overlap range node must be one in the right + * subtree. If not, it has lower > end, then any next + * successor (- an ancestor) of this node cannot + * satisfy the condition either. + */ + return service_range_match_first(r, start, end); + + /* No one in the right subtree can match, go up to find an + * ancestor of this node which is parent of a left-hand child. + */ + while ((p = rb_parent(n)) && n == p->rb_right) + n = p; + if (!p) + break; + + /* Return if this ancestor is an overlap */ + sr = service_range_entry(p); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup more from this ancestor */ + if (sr->lower <= end) { + n = p; + continue; + } + break; + } + + return NULL; +} + static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); @@ -139,84 +266,51 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) return service; } -/** - * tipc_service_first_range - find first service range in tree matching instance - * - * Very time-critical, so binary search through range rb tree - */ -static struct service_range *tipc_service_first_range(struct tipc_service *sc, - u32 instance) -{ - struct rb_node *n = sc->ranges.rb_node; - struct service_range *sr; - - while (n) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > instance) - n = n->rb_left; - else if (sr->upper < instance) - n = n->rb_right; - else - return sr; - } - return NULL; -} - /* tipc_service_find_range - find service range matching publication parameters */ static struct service_range *tipc_service_find_range(struct tipc_service *sc, u32 lower, u32 upper) { - struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; - sr = tipc_service_first_range(sc, lower); - if (!sr) - return NULL; - - /* Look for exact match */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { + /* Look for exact match */ + if (sr->lower == lower && sr->upper == upper) + return sr; } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - return sr; + return NULL; } static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { struct rb_node **n, *parent = NULL; - struct service_range *sr, *tmp; + struct service_range *sr; n = &sc->ranges.rb_node; while (*n) { - tmp = container_of(*n, struct service_range, tree_node); parent = *n; - tmp = container_of(parent, struct service_range, tree_node); - if (lower < tmp->lower) - n = &(*n)->rb_left; - else if (lower > tmp->lower) - n = &(*n)->rb_right; - else if (upper < tmp->upper) - n = &(*n)->rb_left; - else if (upper > tmp->upper) - n = &(*n)->rb_right; + sr = service_range_entry(parent); + if (lower == sr->lower && upper == sr->upper) + return sr; + if (sr->max < upper) + sr->max = upper; + if (lower <= sr->lower) + n = &parent->rb_left; else - return tmp; + n = &parent->rb_right; } sr = kzalloc(sizeof(*sr), GFP_ATOMIC); if (!sr) return NULL; sr->lower = lower; sr->upper = upper; + sr->max = upper; INIT_LIST_HEAD(&sr->local_publ); INIT_LIST_HEAD(&sr->all_publ); rb_link_node(&sr->tree_node, parent, n); - rb_insert_color(&sr->tree_node, &sc->ranges); + rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); return sr; } @@ -310,7 +404,6 @@ static void tipc_service_subscribe(struct tipc_service *service, struct list_head publ_list; struct service_range *sr; struct tipc_name_seq ns; - struct rb_node *n; u32 filter; ns.type = tipc_sub_read(sb, seq.type); @@ -325,13 +418,7 @@ static void tipc_service_subscribe(struct tipc_service *service, return; INIT_LIST_HEAD(&publ_list); - for (n = rb_first(&service->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > ns.upper) - break; - if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper)) - continue; - + service_range_foreach_match(sr, service, ns.lower, ns.upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) @@ -425,7 +512,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, /* Remove service range item if this was its last publication */ if (list_empty(&sr->all_publ)) { - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } @@ -473,34 +560,39 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) rcu_read_lock(); sc = tipc_service_find(net, type); if (unlikely(!sc)) - goto not_found; + goto exit; spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); - if (unlikely(!sr)) - goto no_match; - - /* Select lookup algorithm: local, closest-first or round-robin */ - if (*dnode == self) { - list = &sr->local_publ; - if (list_empty(list)) - goto no_match; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { - list = &sr->local_publ; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else { - list = &sr->all_publ; - p = list_first_entry(list, struct publication, all_publ); - list_move_tail(&p->all_publ, &sr->all_publ); + service_range_foreach_match(sr, sc, instance, instance) { + /* Select lookup algo: local, closest-first or round-robin */ + if (*dnode == self) { + list = &sr->local_publ; + if (list_empty(list)) + continue; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { + list = &sr->local_publ; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else { + list = &sr->all_publ; + p = list_first_entry(list, struct publication, + all_publ); + list_move_tail(&p->all_publ, &sr->all_publ); + } + port = p->port; + node = p->node; + /* Todo: as for legacy, pick the first matching range only, a + * "true" round-robin will be performed as needed. + */ + break; } - port = p->port; - node = p->node; -no_match: spin_unlock_bh(&sc->lock); -not_found: + +exit: rcu_read_unlock(); *dnode = node; return port; @@ -523,7 +615,8 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); + /* Todo: a full search i.e. service_range_foreach_match() instead? */ + sr = service_range_match_first(sc->ranges.rb_node, instance, instance); if (!sr) goto no_match; @@ -552,7 +645,6 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -560,13 +652,7 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { if (p->scope == scope || (!exact && p->scope < scope)) tipc_dest_push(dports, 0, p->port); @@ -587,7 +673,6 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -595,13 +680,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { tipc_nlist_add(nodes, p->node); } @@ -799,7 +878,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } hlist_del_init_rcu(&sc->service_list); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 41688da233ab..6552f986774c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1364,8 +1364,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dport, dnode = 0; - u32 type, inst; + u32 dport = 0, dnode = 0; + u32 type = 0, inst = 0; int mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) @@ -1418,23 +1418,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) type = dest->addr.name.name.type; inst = dest->addr.name.name.instance; dnode = dest->addr.name.domain; - msg_set_type(hdr, TIPC_NAMED_MSG); - msg_set_hdr_sz(hdr, NAMED_H_SIZE); - msg_set_nametype(hdr, type); - msg_set_nameinst(hdr, inst); - msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); dport = tipc_nametbl_translate(net, type, inst, &dnode); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; - msg_set_type(hdr, TIPC_DIRECT_MSG); - msg_set_lookup_scope(hdr, 0); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dest->addr.id.ref); - msg_set_hdr_sz(hdr, BASIC_H_SIZE); } else { return -EINVAL; } @@ -1445,6 +1433,22 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; + if (dest->addrtype == TIPC_ADDR_NAME) { + msg_set_type(hdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(hdr, NAMED_H_SIZE); + msg_set_nametype(hdr, type); + msg_set_nameinst(hdr, inst); + msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dport); + } else { /* TIPC_ADDR_ID */ + msg_set_type(hdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(hdr, 0); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dest->addr.id.ref); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e5ea29c6bca7..6abec3fc81d1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -34,6 +34,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); + if (WARN_ON(!t)) + return NULL; + return container_of(t, struct virtio_transport, transport); } @@ -161,15 +164,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +/* This function can only be used on connecting/connected sockets, + * since a socket assigned to a transport is required. + * + * Do not use on listener sockets! + */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 src_cid, src_port, dst_cid, dst_port; + const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid(); + t_ops = virtio_transport_get_ops(vsk); + if (unlikely(!t_ops)) + return -EFAULT; + + src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; @@ -202,7 +215,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_inc_tx_pkt(vvs, pkt); - return virtio_transport_get_ops(vsk)->send_pkt(pkt); + return t_ops->send_pkt(pkt); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, @@ -1021,18 +1034,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, int ret; if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } @@ -1054,7 +1067,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); sock_put(child); return ret; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 350513744575..3e25229a059d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1102,6 +1102,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c34f7d077604..2efe44a34644 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -659,6 +659,12 @@ static int x25_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sock_set_flag(sk, SOCK_DESTROY); break; + + case X25_STATE_5: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_disconnect(sk, 0, 0, 0); + __x25_destroy_socket(sk); + goto out; } sock_orphan(sk); @@ -1054,6 +1060,8 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, if (test_bit(X25_ACCPT_APPRV_FLAG, &makex25->flags)) { x25_write_internal(make, X25_CALL_ACCEPTED); makex25->state = X25_STATE_3; + } else { + makex25->state = X25_STATE_5; } /* diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f97c43344e95..4d3bb46aaae0 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -382,6 +382,35 @@ out_clear: return 0; } +/* + * State machine for state 5, Call Accepted / Call Connected pending (X25_ACCPT_APPRV_FLAG). + * The handling of the timer(s) is in file x25_timer.c + * Handling of state 0 and connection release is in af_x25.c. + */ +static int x25_state5_machine(struct sock *sk, struct sk_buff *skb, int frametype) +{ + struct x25_sock *x25 = x25_sk(sk); + + switch (frametype) { + case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) { + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; + } + + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); + x25_disconnect(sk, 0, skb->data[3], skb->data[4]); + break; + + default: + break; + } + + return 0; +} + /* Higher level upcall for a LAPB frame */ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) { @@ -406,6 +435,9 @@ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) case X25_STATE_4: queued = x25_state4_machine(sk, skb, frametype); break; + case X25_STATE_5: + queued = x25_state5_machine(sk, skb, frametype); + break; } x25_kick(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 956793893c9d..328f661b83b2 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -334,12 +334,21 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct xdp_sock *xs) +static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; + int err; + + rcu_read_lock(); + err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); + rcu_read_unlock(); + + return err; +} - return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - XDP_WAKEUP_TX); +static int xsk_zc_xmit(struct xdp_sock *xs) +{ + return xsk_wakeup(xs, XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -453,19 +462,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct net_device *dev; struct xdp_umem *umem; if (unlikely(!xsk_is_bound(xs))) return mask; - dev = xs->dev; umem = xs->umem; if (umem->need_wakeup) { - if (dev->netdev_ops->ndo_xsk_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (xs->zc) + xsk_wakeup(xs, umem->need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); |