diff options
Diffstat (limited to 'net')
51 files changed, 408 insertions, 179 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 98a30a5b8664..59555f0f8fc8 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -443,7 +443,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { - flgs = vlandev->flags; + flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4663c3dad3f5..c4802f3bd4c5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2854,9 +2854,11 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, * state. If we were running both LE and BR/EDR inquiry * simultaneously, and BR/EDR inquiry is already * finished, stop discovery, otherwise BR/EDR inquiry - * will stop discovery when finished. + * will stop discovery when finished. If we will resolve + * remote device name, do not change discovery state. */ - if (!test_bit(HCI_INQUIRY, &hdev->flags)) + if (!test_bit(HCI_INQUIRY, &hdev->flags) && + hdev->discovery.state != DISCOVERY_RESOLVING) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } else { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4b6722f8f179..22fd0419b314 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1072,7 +1072,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } @@ -1822,7 +1822,7 @@ static void br_multicast_query_expired(struct net_bridge *br, if (query->startup_sent < br->multicast_startup_query_count) query->startup_sent++; - RCU_INIT_POINTER(querier, NULL); + RCU_INIT_POINTER(querier->port, NULL); br_multicast_send_query(br, NULL, query); spin_unlock(&br->multicast_lock); } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index ab55e2472beb..60ddfbeb47f5 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,10 +37,6 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> -#if IS_ENABLED(CONFIG_NF_CONNTRACK) -#include <net/netfilter/nf_conntrack.h> -#endif - #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL @@ -350,24 +346,15 @@ free_skb: return 0; } -static bool dnat_took_place(const struct sk_buff *skb) +static bool daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) { -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_untracked(ct)) - return false; - - return test_bit(IPS_DST_NAT_BIT, &ct->status); -#else - return false; -#endif + return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. + * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -421,7 +408,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (dnat_took_place(skb)) { + if (daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -632,6 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { + struct nf_bridge_info *nf_bridge; struct net_bridge_port *p; struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); @@ -669,6 +657,9 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (!setup_pre_routing(skb)) return NF_DROP; + nf_bridge = nf_bridge_info_get(skb); + nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 4fcaa67750fd..7caf7fae2d5b 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -97,7 +97,9 @@ static void br_forward_delay_timer_expired(unsigned long arg) netif_carrier_on(br->dev); } br_log_state(p); + rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, p); + rcu_read_unlock(); spin_unlock(&br->lock); } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 4ec0c803aef1..112ad784838a 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -373,6 +377,10 @@ static int caif_stream_recvmsg(struct socket *sock, struct msghdr *msg, struct sk_buff *skb; lock_sock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } skb = skb_dequeue(&sk->sk_receive_queue); caif_check_flow_release(sk); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 41a4abc7e98e..c4ec9239249a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1306,8 +1306,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, if (list_empty(&req->r_osd_item)) req->r_osd = NULL; } - - list_del_init(&req->r_req_lru_item); /* can be on notarget */ ceph_osdc_put_request(req); } @@ -2017,20 +2015,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, err = __map_request(osdc, req, force_resend || force_resend_writes); dout("__map_request returned %d\n", err); - if (err == 0) - continue; /* no change and no osd was specified */ if (err < 0) continue; /* hrm! */ - if (req->r_osd == NULL) { - dout("tid %llu maps to no valid osd\n", req->r_tid); - needmap++; /* request a newer map */ - continue; - } + if (req->r_osd == NULL || err > 0) { + if (req->r_osd == NULL) { + dout("lingering %p tid %llu maps to no osd\n", + req, req->r_tid); + /* + * A homeless lingering request makes + * no sense, as it's job is to keep + * a particular OSD connection open. + * Request a newer map and kick the + * request, knowing that it won't be + * resent until we actually get a map + * that can tell us where to send it. + */ + needmap++; + } - dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_request(osdc, req); - __unregister_linger_request(osdc, req); + dout("kicking lingering %p tid %llu osd%d\n", req, + req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); + __register_request(osdc, req); + __unregister_linger_request(osdc, req); + } } reset_changed_osds(osdc); mutex_unlock(&osdc->request_mutex); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 666e0928ba40..8de36824018d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2416,6 +2416,9 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, { struct sk_buff *skb; + if (dev->reg_state != NETREG_REGISTERED) + return; + skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e6f6cc3a1bcf..392e29a0227d 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -359,7 +359,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, */ ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) - return NULL; + return ERR_PTR(-ENOMEM); ds->dst = dst; ds->index = index; @@ -370,7 +370,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, ret = dsa_switch_setup_one(ds, parent); if (ret) - return NULL; + return ERR_PTR(ret); return ds; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 421a80b09b62..30b544f025ac 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -256,7 +256,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) aead_givcrypt_set_crypt(req, sg, sg, clen, iv); aead_givcrypt_set_assoc(req, asg, assoclen); aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_givencrypt(req); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e13fcc602da2..09b62e17dd8c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1164,6 +1164,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; + new_fa->tb_id = tb->tb_id; err = netdev_switch_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1764,7 +1765,7 @@ void fib_table_flush_external(struct fib_table *tb) /* record local slen */ slen = fa->fa_slen; - if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD)) continue; netdev_switch_fib_ipv4_del(n->key, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9f7269f3c54a..0c152087ca15 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; - skb->mark = be32_to_cpu(tunnel->parms.i_key); return xfrm_input(skb, nexthdr, spi, encap_type); } @@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + u32 orig_mark = skb->mark; + int ret; if (!tunnel) return 1; @@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(tunnel->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); @@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(tunnel->parms.o_key); - switch (skb->protocol) { case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); @@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); + return vti_xmit(skb, dev, &fl); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 13bfe84bf3ca..a61200754f4b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1075,6 +1075,9 @@ static int do_replace(struct net *net, const void __user *user, /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1499,6 +1502,9 @@ static int compat_do_replace(struct net *net, void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c69db7fa25ee..2d0e265fef6e 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1262,6 +1262,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1809,6 +1812,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bff62fc87b8e..f45f2a12f37b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -902,6 +902,10 @@ static int ip_error(struct sk_buff *skb) bool send; int code; + /* IP on this device is disabled. */ + if (!in_dev) + goto out; + net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46efa03d2b11..f1377f2a0472 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -402,6 +402,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; + u64_stats_init(&tp->syncp); tp->reordering = sysctl_tcp_reordering; tcp_enable_early_retrans(tp); @@ -2598,6 +2599,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; + unsigned int start; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,10 +2667,11 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate = READ_ONCE(sk->sk_max_pacing_rate); info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; - spin_lock_bh(&sk->sk_lock.slock); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; - spin_unlock_bh(&sk->sk_lock.slock); + do { + start = u64_stats_fetch_begin_irq(&tp->syncp); + info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; + } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 7a5ae50c80c8..84be008c945c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; + icsk->icsk_ca_setsockopt = 1; if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); @@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) rcu_read_lock(); ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ - if (ca == icsk->icsk_ca_ops) + if (ca == icsk->icsk_ca_ops) { + icsk->icsk_ca_setsockopt = 1; goto out; + } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3c673d5e6cff..46b087a27503 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,10 @@ static bool tcp_fastopen_create_child(struct sock *sk, skb_set_owner_r(skb2, child); __skb_queue_tail(&child->sk_receive_queue, skb2); tp->syn_data_acked = 1; + + /* u64_stats_update_begin(&tp->syncp) not needed here, + * as we certainly are not changing upper 32bit value (0) + */ tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; } else { end_seq = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bc790ea9960f..c9ab964189a0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2698,16 +2698,21 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); + if ((flag & FLAG_SND_UNA_ADVANCED) && + tcp_try_undo_loss(sk, false)) + return; + if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ /* Step 3.b. A timeout is spurious if not all data are * lost, i.e., never-retransmitted data are (s)acked. */ - if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) return; - if (after(tp->snd_nxt, tp->high_seq) && - (flag & FLAG_DATA_SACKED || is_dupack)) { - tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ + if (after(tp->snd_nxt, tp->high_seq)) { + if (flag & FLAG_DATA_SACKED || is_dupack) + tp->frto = 0; /* Step 3.a. loss was real */ } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { tp->high_seq = tp->snd_nxt; __tcp_push_pending_frames(sk, tcp_current_mss(sk), @@ -2732,8 +2737,6 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) else if (flag & FLAG_SND_UNA_ADVANCED) tcp_reset_reno_sack(tp); } - if (tcp_try_undo_loss(sk, false)) - return; tcp_xmit_retransmit_queue(sk); } @@ -3283,7 +3286,9 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { u32 delta = ack - tp->snd_una; + u64_stats_update_begin(&tp->syncp); tp->bytes_acked += delta; + u64_stats_update_end(&tp->syncp); tp->snd_una = ack; } @@ -3292,7 +3297,9 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt; + u64_stats_update_begin(&tp->syncp); tp->bytes_received += delta; + u64_stats_update_end(&tp->syncp); tp->rcv_nxt = seq; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e5d7649136fc..17e7339ee5ca 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -300,7 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; - tw->tw_flowlabel = np->flow_label >> 12; + tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK); tw->tw_ipv6only = sk->sk_ipv6only; } #endif @@ -420,7 +420,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) rcu_read_unlock(); } - if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner)) + /* If no valid choice made yet, assign current system default ca. */ + if (!ca_got_dst && + (!icsk->icsk_ca_setsockopt || + !try_module_get(icsk->icsk_ca_ops->owner))) tcp_assign_congestion_control(sk); tcp_set_ca_state(sk, TCP_CA_Open); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d10b7e0112eb..1c92ea67baef 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1345,10 +1345,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 31f1b5d5e2ef..7c07ce36aae2 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -248,7 +248,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) aead_givcrypt_set_crypt(req, sg, sg, clen, iv); aead_givcrypt_set_assoc(req, asg, assoclen); aead_givcrypt_set_giv(req, esph->enc_data, - XFRM_SKB_CB(skb)->seq.output.low); + XFRM_SKB_CB(skb)->seq.output.low + + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_givencrypt(req); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 96dbffff5a24..bde57b113009 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -693,6 +693,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, { struct rt6_info *iter = NULL; struct rt6_info **ins; + struct rt6_info **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -716,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (iter->dst.dev == rt->dst.dev && @@ -753,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (iter->rt6i_metric > rt->rt6i_metric) break; +next_iter: ins = &iter->dst.rt6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = *ins; + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; @@ -815,6 +829,8 @@ add: } } else { + int nsiblings; + if (!found) { if (add) goto add; @@ -835,8 +851,27 @@ add: info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->rt6i_nsiblings; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); + + if (nsiblings) { + /* Replacing an ECMP route, remove all siblings */ + ins = &rt->dst.rt6_next; + iter = *ins; + while (iter) { + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->dst.rt6_next; + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); + nsiblings--; + } else { + ins = &iter->dst.rt6_next; + } + iter = *ins; + } + WARN_ON(nsiblings != 0); + } } return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c21777565c58..bc09cb97b840 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1300,8 +1300,10 @@ emsgsize: /* If this is the first and only packet and device * supports checksum offloading, let's use it. + * Use transhdrlen, same as IPv4, because partial + * sums only work when transhdrlen is set. */ - if (!skb && sk->sk_protocol == IPPROTO_UDP && + if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && length + fragheaderlen < mtu && rt->dst.dev->features & NETIF_F_V6_CSUM && !exthdrlen) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ed9d681207fa..0224c032dca5 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -322,7 +322,6 @@ static int vti6_rcv(struct sk_buff *skb) } XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; - skb->mark = be32_to_cpu(t->parms.i_key); rcu_read_unlock(); @@ -342,6 +341,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) struct pcpu_sw_netstats *tstats; struct xfrm_state *x; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + u32 orig_mark = skb->mark; + int ret; if (!t) return 1; @@ -358,7 +359,11 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) x = xfrm_input_state(skb); family = x->inner_mode->afinfo->family; - if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + skb->mark = be32_to_cpu(t->parms.i_key); + ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); + skb->mark = orig_mark; + + if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); @@ -430,6 +435,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct net_device *tdev; struct xfrm_state *x; int err = -1; + int mtu; if (!dst) goto tx_err_link_failure; @@ -463,6 +469,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + + return -EMSGSIZE; + } + err = dst_output(skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); @@ -495,7 +514,6 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) int ret; memset(&fl, 0, sizeof(fl)); - skb->mark = be32_to_cpu(t->parms.o_key); switch (skb->protocol) { case htons(ETH_P_IPV6): @@ -516,6 +534,9 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; } + /* override mark with tunnel output key */ + fl.flowi_mark = be32_to_cpu(t->parms.o_key); + ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 1a732a1d3c8e..62f5b0d0bc9b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1275,6 +1275,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1822,6 +1825,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d3588885f097..c73ae5039e46 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2504,9 +2504,9 @@ static int ip6_route_multipath(struct fib6_config *cfg, int add) int attrlen; int err = 0, last_err = 0; + remaining = cfg->fc_mp_len; beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - remaining = cfg->fc_mp_len; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { @@ -2536,15 +2536,19 @@ beginning: * next hops that have been already added. */ add = 0; + remaining = cfg->fc_mp_len - remaining; goto beginning; } } /* Because each route is added like a single route we remove - * this flag after the first nexthop (if there is a collision, - * we have already fail to add the first nexthop: - * fib6_add_rt2node() has reject it). + * these flags after the first nexthop: if there is a collision, + * we have already failed to add the first nexthop: + * fib6_add_rt2node() has rejected it; when replacing, old + * nexthops have been replaced by first new, the rest should + * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); rtnh = rtnh_next(rtnh, &remaining); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d665568..3adffb300238 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -914,7 +914,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3477c919fcc8..e51fc3eee6db 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,10 +525,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -731,7 +729,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 265e42721a66..ff347a0eebd4 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2495,51 +2495,22 @@ static bool ieee80211_coalesce_started_roc(struct ieee80211_local *local, struct ieee80211_roc_work *new_roc, struct ieee80211_roc_work *cur_roc) { - unsigned long j = jiffies; - unsigned long cur_roc_end = cur_roc->hw_start_time + - msecs_to_jiffies(cur_roc->duration); - struct ieee80211_roc_work *next_roc; - int new_dur; + unsigned long now = jiffies; + unsigned long remaining = cur_roc->hw_start_time + + msecs_to_jiffies(cur_roc->duration) - + now; if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun)) return false; - if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end)) + /* if it doesn't fit entirely, schedule a new one */ + if (new_roc->duration > jiffies_to_msecs(remaining)) return false; ieee80211_handle_roc_started(new_roc); - new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j); - - /* cur_roc is long enough - add new_roc to the dependents list. */ - if (new_dur <= 0) { - list_add_tail(&new_roc->list, &cur_roc->dependents); - return true; - } - - new_roc->duration = new_dur; - - /* - * if cur_roc was already coalesced before, we might - * want to extend the next roc instead of adding - * a new one. - */ - next_roc = list_entry(cur_roc->list.next, - struct ieee80211_roc_work, list); - if (&next_roc->list != &local->roc_list && - next_roc->chan == new_roc->chan && - next_roc->sdata == new_roc->sdata && - !WARN_ON(next_roc->started)) { - list_add_tail(&new_roc->list, &next_roc->dependents); - next_roc->duration = max(next_roc->duration, - new_roc->duration); - next_roc->type = max(next_roc->type, new_roc->type); - return true; - } - - /* add right after cur_roc */ - list_add(&new_roc->list, &cur_roc->list); - + /* add to dependents so we send the expired event properly */ + list_add_tail(&new_roc->list, &cur_roc->dependents); return true; } @@ -2652,17 +2623,9 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, * In the offloaded ROC case, if it hasn't begun, add * this new one to the dependent list to be handled * when the master one begins. If it has begun, - * check that there's still a minimum time left and - * if so, start this one, transmitting the frame, but - * add it to the list directly after this one with - * a reduced time so we'll ask the driver to execute - * it right after finishing the previous one, in the - * hope that it'll also be executed right afterwards, - * effectively extending the old one. - * If there's no minimum time left, just add it to the - * normal list. - * TODO: the ROC type is ignored here, assuming that it - * is better to immediately use the current ROC. + * check if it fits entirely within the existing one, + * in which case it will just be dependent as well. + * Otherwise, schedule it by itself. */ if (!tmp->hw_begun) { list_add_tail(&roc->list, &tmp->dependents); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ab46ab4a7249..c0a9187bc3a9 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -205,6 +205,8 @@ enum ieee80211_packet_rx_flags { * @IEEE80211_RX_CMNTR: received on cooked monitor already * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported * to cfg80211_report_obss_beacon(). + * @IEEE80211_RX_REORDER_TIMER: this frame is released by the + * reorder buffer timeout timer, not the normal RX path * * These flags are used across handling multiple interfaces * for a single frame. @@ -212,6 +214,7 @@ enum ieee80211_packet_rx_flags { enum ieee80211_rx_flags { IEEE80211_RX_CMNTR = BIT(0), IEEE80211_RX_BEACON_REPORTED = BIT(1), + IEEE80211_RX_REORDER_TIMER = BIT(2), }; struct ieee80211_rx_data { @@ -325,12 +328,6 @@ struct mesh_preq_queue { u8 flags; }; -#if HZ/100 == 0 -#define IEEE80211_ROC_MIN_LEFT 1 -#else -#define IEEE80211_ROC_MIN_LEFT (HZ/100) -#endif - struct ieee80211_roc_work { struct list_head list; struct list_head dependents; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index bab5c63c0bad..84cef600c573 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -522,6 +522,12 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) memcpy(sdata->vif.hw_queue, master->vif.hw_queue, sizeof(sdata->vif.hw_queue)); sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; + + mutex_lock(&local->key_mtx); + sdata->crypto_tx_tailroom_needed_cnt += + master->crypto_tx_tailroom_needed_cnt; + mutex_unlock(&local->key_mtx); + break; } case NL80211_IFTYPE_AP: diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 2291cd730091..a907f2d5c12d 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -58,6 +58,22 @@ static void assert_key_lock(struct ieee80211_local *local) lockdep_assert_held(&local->key_mtx); } +static void +update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) +{ + struct ieee80211_sub_if_data *vlan; + + if (sdata->vif.type != NL80211_IFTYPE_AP) + return; + + mutex_lock(&sdata->local->mtx); + + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt += delta; + + mutex_unlock(&sdata->local->mtx); +} + static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) { /* @@ -79,6 +95,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net */ + update_vlan_tailroom_need_count(sdata, 1); + if (!sdata->crypto_tx_tailroom_needed_cnt++) { /* * Flush all XMIT packets currently using HW encryption or no @@ -88,6 +106,15 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) } } +static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata, + int delta) +{ + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta); + + update_vlan_tailroom_need_count(sdata, -delta); + sdata->crypto_tx_tailroom_needed_cnt -= delta; +} + static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; @@ -144,7 +171,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)); @@ -541,7 +568,7 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key, schedule_delayed_work(&sdata->dec_tailroom_needed_wk, HZ/2); } else { - sdata->crypto_tx_tailroom_needed_cnt--; + decrease_tailroom_need_count(sdata, 1); } } @@ -631,6 +658,7 @@ void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom) void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; + struct ieee80211_sub_if_data *vlan; ASSERT_RTNL(); @@ -639,7 +667,14 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt = 0; + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || + vlan->crypto_tx_tailroom_pending_dec); + } list_for_each_entry(key, &sdata->key_list, list) { increment_tailroom_need_count(sdata); @@ -649,6 +684,22 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_unlock(&sdata->local->key_mtx); } +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_sub_if_data *vlan; + + mutex_lock(&sdata->local->key_mtx); + + sdata->crypto_tx_tailroom_needed_cnt = 0; + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + vlan->crypto_tx_tailroom_needed_cnt = 0; + } + + mutex_unlock(&sdata->local->key_mtx); +} + void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, @@ -688,8 +739,8 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, { struct ieee80211_key *key, *tmp; - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); @@ -709,6 +760,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vlan; + struct ieee80211_sub_if_data *master; struct ieee80211_key *key, *tmp; LIST_HEAD(keys); @@ -728,8 +780,20 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, false); - WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || - sdata->crypto_tx_tailroom_pending_dec); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (sdata->bss) { + master = container_of(sdata->bss, + struct ieee80211_sub_if_data, + u.ap); + + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt != + master->crypto_tx_tailroom_needed_cnt); + } + } else { + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || + sdata->crypto_tx_tailroom_pending_dec); + } + if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || @@ -793,8 +857,8 @@ void ieee80211_delayed_tailroom_dec(struct work_struct *wk) */ mutex_lock(&sdata->local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt -= - sdata->crypto_tx_tailroom_pending_dec; + decrease_tailroom_need_count(sdata, + sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; mutex_unlock(&sdata->local->key_mtx); } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index c5a31835be0e..96557dd1e77d 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -161,6 +161,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta); void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata); +void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata); #define key_mtx_dereference(local, ref) \ rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx))) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 260eed45b6d2..5793f75c5ffd 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2121,7 +2121,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->local->napi) + if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) && + rx->local->napi) napi_gro_receive(rx->local->napi, skb); else netif_receive_skb(skb); @@ -3231,7 +3232,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .flags = 0, + .flags = IEEE80211_RX_REORDER_TIMER, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 79412f16b61d..b864ebc6ab8f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2023,6 +2023,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add back keys */ list_for_each_entry(sdata, &local->interfaces, list) + ieee80211_reset_crypto_tx_tailroom(sdata); + + list_for_each_entry(sdata, &local->interfaces, list) if (ieee80211_sdata_running(sdata)) ieee80211_enable_keys(sdata); diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index a4220e92f0cc..efa3f48f1ec5 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); - if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN || - skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) + if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) return NULL; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -167,6 +166,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, size_t len; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; + if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) + return -1; + iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); if (!iv) return -1; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f70e34a68f70..a0f3e6a3c7d1 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -863,6 +863,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES @@ -1356,6 +1357,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 49532672f66d..285eae3a1454 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3823,6 +3823,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); ip_vs_stop_estimator(net, &ipvs->tot_stats); + + if (!net_eq(net, &init_net)) + kfree(ipvs->sysctl_tbl); } #else diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 5caa0c41bf26..70383de72054 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -202,7 +202,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ @@ -261,7 +261,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ @@ -906,6 +906,7 @@ static int tcp_packet(struct nf_conn *ct, 1 : ct->proto.tcp.last_win; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = ct->proto.tcp.last_wscale; + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; memset(&ct->proto.tcp.seen[dir], 0, @@ -923,7 +924,9 @@ static int tcp_packet(struct nf_conn *ct, * may be in sync but we are not. In that case, we annotate * the TCP options and let the packet go through. If it is a * valid SYN packet, the server will reply with a SYN/ACK, and - * then we'll get in sync. Otherwise, the server ignores it. */ + * then we'll get in sync. Otherwise, the server potentially + * responds with a challenge ACK if implementing RFC5961. + */ if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { struct ip_ct_tcp_state seen = {}; @@ -939,6 +942,13 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_SACK_PERM; } + /* Mark the potential for RFC5961 challenge ACK, + * this pose a special problem for LAST_ACK state + * as ACK is intrepretated as ACKing last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK) + ct->proto.tcp.last_flags |= + IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) @@ -970,6 +980,25 @@ static int tcp_packet(struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid state "); return -NF_ACCEPT; + case TCP_CONNTRACK_TIME_WAIT: + /* RFC5961 compliance cause stack to send "challenge-ACK" + * e.g. in response to spurious SYNs. Conntrack MUST + * not believe this ACK is acking last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK && + index == TCP_ACK_SET && + ct->proto.tcp.last_dir != dir && + ct->proto.tcp.last_index == TCP_SYN_SET && + (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) { + /* Detected RFC5961 challenge ACK */ + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; + spin_unlock_bh(&ct->lock); + if (LOG_INVALID(net, IPPROTO_TCP)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_tcp: challenge-ACK ignored "); + return NF_ACCEPT; /* Don't change state */ + } + break; case TCP_CONNTRACK_CLOSE: if (index == TCP_RST_SET && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ad9d11fb29fd..34ded09317e7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4472,9 +4472,9 @@ EXPORT_SYMBOL_GPL(nft_data_init); */ void nft_data_uninit(const struct nft_data *data, enum nft_data_types type) { - switch (type) { - case NFT_DATA_VALUE: + if (type < NFT_DATA_VERDICT) return; + switch (type) { case NFT_DATA_VERDICT: return nft_verdict_uninit(data); default: diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3ad91266c821..4ef1fae8445e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1073,7 +1073,13 @@ static struct pernet_operations nfnl_log_net_ops = { static int __init nfnetlink_log_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_log_net_ops); + if (status < 0) { + pr_err("failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); @@ -1088,28 +1094,23 @@ static int __init nfnetlink_log_init(void) goto cleanup_subsys; } - status = register_pernet_subsys(&nfnl_log_net_ops); - if (status < 0) { - pr_err("failed to register pernet ops\n"); - goto cleanup_logger; - } return status; -cleanup_logger: - nf_log_unregister(&nfulnl_logger); cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); +out: return status; } static void __exit nfnetlink_log_fini(void) { - unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); } MODULE_DESCRIPTION("netfilter userspace logging"); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 0b98c7420239..11c7682fa0ea 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1317,7 +1317,13 @@ static struct pernet_operations nfnl_queue_net_ops = { static int __init nfnetlink_queue_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_queue_net_ops); + if (status < 0) { + pr_err("nf_queue: failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); @@ -1326,19 +1332,13 @@ static int __init nfnetlink_queue_init(void) goto cleanup_netlink_notifier; } - status = register_pernet_subsys(&nfnl_queue_net_ops); - if (status < 0) { - pr_err("nf_queue: failed to register pernet ops\n"); - goto cleanup_subsys; - } register_netdevice_notifier(&nfqnl_dev_notifier); nf_register_queue_handler(&nfqh); return status; -cleanup_subsys: - nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); +out: return status; } @@ -1346,9 +1346,9 @@ static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); - unregister_pernet_subsys(&nfnl_queue_net_ops); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index daa0b818174b..bf6e76643f78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -89,7 +89,7 @@ static inline int netlink_is_kernel(struct sock *sk) return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; } -struct netlink_table *nl_table; +struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); @@ -1081,6 +1081,7 @@ static int netlink_insert(struct sock *sk, u32 portid) if (err) { if (err == -EEXIST) err = -EADDRINUSE; + nlk_sk(sk)->portid = 0; sock_put(sk); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b6ef9a04de06..a75864d93142 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) struct tcf_proto_ops *t; int rc = -ENOENT; + /* Wait for outstanding call_rcu()s, if any, from a + * tcf_proto_ops's destroy() handler. + */ + rcu_barrier(); + write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { if (t == ops) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ad9eed70bc8f..1e1c89e51a11 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); - if (new && new->ops->attach) { - new->ops->attach(new); - num_q = 0; - } + if (new && new->ops->attach) + goto skip; for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = dev_ingress_queue(dev); @@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_destroy(old); } +skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) atomic_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; + + if (new && new->ops->attach) + new->ops->attach(new); } else { notify_and_destroy(net, skb, n, classid, old, new); } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 46568b85c333..055453d48668 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -338,7 +338,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, fi, tos, type, nlflags, tb_id); if (!err) - fi->fib_flags |= RTNH_F_EXTERNAL; + fi->fib_flags |= RTNH_F_OFFLOAD; } return err; @@ -364,7 +364,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, const struct swdev_ops *ops; int err = 0; - if (!(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; dev = netdev_switch_get_dev_by_nhs(fi); @@ -376,7 +376,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, fi, tos, type, tb_id); if (!err) - fi->fib_flags &= ~RTNH_F_EXTERNAL; + fi->fib_flags &= ~RTNH_F_OFFLOAD; } return err; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5266ea7b922b..06430598cf51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1880,6 +1880,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, unix_state_unlock(sk); timeo = freezable_schedule_timeout(timeo); unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) + break; + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } @@ -1939,6 +1943,10 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, struct sk_buff *skb, *last; unix_state_lock(sk); + if (sock_flag(sk, SOCK_DEAD)) { + err = -ECONNRESET; + goto unlock; + } last = skb = skb_peek(&sk->sk_receive_queue); again: if (skb == NULL) { diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 526c4feb3b50..b58286ecd156 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -13,6 +13,8 @@ #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> +#include <net/ip_tunnels.h> +#include <net/ip6_tunnel.h> static struct kmem_cache *secpath_cachep __read_mostly; @@ -186,6 +188,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) struct xfrm_state *x = NULL; xfrm_address_t *daddr; struct xfrm_mode *inner_mode; + u32 mark = skb->mark; unsigned int family; int decaps = 0; int async = 0; @@ -203,6 +206,18 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); family = XFRM_SPI_SKB_CB(skb)->family; + /* if tunnel is present override skb->mark value with tunnel i_key */ + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) { + switch (family) { + case AF_INET: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); + break; + case AF_INET6: + mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); + break; + } + } + /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; @@ -229,7 +244,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family); + x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index dab57daae408..4fd725a0c500 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -99,6 +99,7 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(x->replay.oseq == 0)) { x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); @@ -177,6 +178,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; + XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(replay_esn->oseq == 0)) { replay_esn->oseq--; xfrm_audit_state_replay_overflow(x, skb); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f5e39e35d73a..96688cd0f6f1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -927,8 +927,8 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, x->id.spi != spi) continue; - spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_hold(x); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); |