diff options
author | Jakub Kicinski <kuba@kernel.org> | 2022-07-15 00:19:42 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-07-15 01:27:35 +0300 |
commit | 816cd1688331e0ffa1927889c15e7ed56650a183 (patch) | |
tree | 30cbcb7d5d4e1dd226fda651f25ca094e54714a0 /net | |
parent | b126047f43f11f61f1dd64802979765d71795dae (diff) | |
parent | db886979683a8360ced9b24ab1125ad0c4d2cf76 (diff) | |
download | linux-816cd1688331e0ffa1927889c15e7ed56650a183.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
include/net/sock.h
310731e2f161 ("net: Fix data-races around sysctl_mem.")
e70f3c701276 ("Revert "net: set SK_MEM_QUANTUM to 4096"")
https://lore.kernel.org/all/20220711120211.7c8b7cba@canb.auug.org.au/
net/ipv4/fib_semantics.c
747c14307214 ("ip: fix dflt addr selection for connected nexthop")
d62607c3fe45 ("net: rename reference+tracking helpers")
net/tls/tls.h
include/net/tls.h
3d8c51b25a23 ("net/tls: Check for errors in tls_device_init")
587903142308 ("tls: create an internal header")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
36 files changed, 192 insertions, 103 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/core/dev.c b/net/core/dev.c index 978ed0622d8f..d588fd0a54ce 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 4ef77ec5255e..59aada9c4e19 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6204,7 +6204,6 @@ 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 7abd652a558f..fac552e98eb9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1247,7 +1247,7 @@ 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); } @@ -1302,7 +1302,7 @@ 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 a5439a8414d4..14f037e8ac55 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; netdev_hold(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; @@ -1812,7 +1812,7 @@ 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/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 21bdee88383b..96b6e9c22068 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2784,7 +2784,8 @@ 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 80cb112ef142..acee998c14b2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6726,7 +6726,7 @@ 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_output.c b/net/ipv4/tcp_output.c index d1ca3df275df..858a15cc2cc9 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/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 70cd50c1fa6f..69252eb462b2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5741,7 +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_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/mac80211/cfg.c b/net/mac80211/cfg.c index fd6c4291c971..64801ab545c1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4463,14 +4463,14 @@ 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.bss_conf.color_change_active || sdata->vif.bss_conf.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 56dd831fe45f..d5e904bff624 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -380,7 +380,9 @@ 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 834d2171f344..304b9909f025 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3199,7 +3199,8 @@ 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 b2430cf8332b..b58c85abcb1b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2802,19 +2802,10 @@ 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; @@ -3522,15 +3513,9 @@ 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)) @@ -4341,7 +4326,7 @@ 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; @@ -4356,6 +4341,11 @@ 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 bcb4aa7d7599..645f75b0f89f 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 fc36c8e9d1d2..ecc1de2e68a5 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -148,8 +148,8 @@ 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/protocol.c b/net/mptcp/protocol.c index 6cf5fa191b12..57f23f4e3a7c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2884,12 +2884,12 @@ 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/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 d6b59beab3a9..646d5fd53604 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5833,8 +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 && @@ -5943,7 +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]) { @@ -5952,22 +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) { @@ -5982,7 +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) { @@ -6016,7 +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 @@ -6026,9 +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; @@ -6256,8 +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, @@ -6265,16 +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; @@ -6282,7 +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) @@ -6306,6 +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/tls/tls.h b/net/tls/tls.h index 8005ee25157d..e0ccc96a0850 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -133,7 +133,7 @@ static inline struct tls_msg *tls_msg(struct sk_buff *skb) } #ifdef CONFIG_TLS_DEVICE -void tls_device_init(void); +int tls_device_init(void); void tls_device_cleanup(void); int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); void tls_device_free_resources_tx(struct sock *sk); @@ -143,7 +143,7 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, struct sk_buff *skb, struct strp_msg *rxm); #else -static inline void tls_device_init(void) {} +static inline int tls_device_init(void) { return 0; } static inline void tls_device_cleanup(void) {} static inline int diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 227b92a3064a..6f9dff1c11f6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1420,9 +1420,9 @@ 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 f71b46568112..9703636cfc60 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1141,7 +1141,12 @@ 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/wireless/sme.c b/net/wireless/sme.c index 00be498aab2e..22996d63c15f 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1236,7 +1236,8 @@ 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->connected) || |