diff options
Diffstat (limited to 'net')
46 files changed, 290 insertions, 159 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9096bcb08132..ee070722a3a3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -463,7 +463,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ - return NOTIFY_BAD; + if (vlan_uses_dev(dev)) + return NOTIFY_BAD; + break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index fbbf1fa00940..65e06abe023f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -366,6 +366,13 @@ EXPORT_SYMBOL(vlan_vids_del_by_dev); bool vlan_uses_dev(const struct net_device *dev) { - return rtnl_dereference(dev->vlan_info) ? true : false; + struct vlan_info *vlan_info; + + ASSERT_RTNL(); + + vlan_info = rtnl_dereference(dev->vlan_info); + if (!vlan_info) + return false; + return vlan_info->grp.nr_vlan_devs ? true : false; } EXPORT_SYMBOL(vlan_uses_dev); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 0a9084ad19a6..fd8d5afec0dd 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1167,6 +1167,8 @@ int batadv_bla_init(struct batadv_priv *bat_priv) uint16_t crc; unsigned long entrytime; + spin_lock_init(&bat_priv->bla.bcast_duplist_lock); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hash registering\n"); /* setting claim destination address */ @@ -1210,8 +1212,8 @@ int batadv_bla_init(struct batadv_priv *bat_priv) /** * batadv_bla_check_bcast_duplist * @bat_priv: the bat priv with all the soft interface information - * @bcast_packet: originator mac address - * @hdr_size: maximum length of the frame + * @bcast_packet: encapsulated broadcast frame plus batman header + * @bcast_packet_len: length of encapsulated broadcast frame plus batman header * * check if it is on our broadcast list. Another gateway might * have sent the same packet because it is connected to the same backbone, @@ -1224,20 +1226,22 @@ int batadv_bla_init(struct batadv_priv *bat_priv) */ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct batadv_bcast_packet *bcast_packet, - int hdr_size) + int bcast_packet_len) { - int i, length, curr; + int i, length, curr, ret = 0; uint8_t *content; uint16_t crc; struct batadv_bcast_duplist_entry *entry; - length = hdr_size - sizeof(*bcast_packet); + length = bcast_packet_len - sizeof(*bcast_packet); content = (uint8_t *)bcast_packet; content += sizeof(*bcast_packet); /* calculate the crc ... */ crc = crc16(0, content, length); + spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); + for (i = 0; i < BATADV_DUPLIST_SIZE; i++) { curr = (bat_priv->bla.bcast_duplist_curr + i); curr %= BATADV_DUPLIST_SIZE; @@ -1259,9 +1263,12 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, /* this entry seems to match: same crc, not too old, * and from another gw. therefore return 1 to forbid it. */ - return 1; + ret = 1; + goto out; } - /* not found, add a new entry (overwrite the oldest entry) */ + /* not found, add a new entry (overwrite the oldest entry) + * and allow it, its the first occurence. + */ curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; @@ -1270,8 +1277,10 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, memcpy(entry->orig, bcast_packet->orig, ETH_ALEN); bat_priv->bla.bcast_duplist_curr = curr; - /* allow it, its the first occurence. */ - return 0; +out: + spin_unlock_bh(&bat_priv->bla.bcast_duplist_lock); + + return ret; } diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 939fc01371df..376b4cc6ca82 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1124,8 +1124,14 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, spin_unlock_bh(&orig_node->bcast_seqno_lock); + /* keep skb linear for crc calculation */ + if (skb_linearize(skb) < 0) + goto out; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + /* check whether this has been sent by another originator before */ - if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, hdr_size)) + if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, skb->len)) goto out; /* rebroadcast packet */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 2ed82caacdca..ac1e07a80454 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -205,6 +205,8 @@ struct batadv_priv_bla { struct batadv_hashtable *backbone_hash; struct batadv_bcast_duplist_entry bcast_duplist[BATADV_DUPLIST_SIZE]; int bcast_duplist_curr; + /* protects bcast_duplist and bcast_duplist_curr */ + spinlock_t bcast_duplist_lock; struct batadv_bla_claim_dst claim_dest; struct delayed_work work; }; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 159aa8bef9e7..3ef1759403b4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2300,10 +2300,11 @@ restart: mutex_unlock(&con->mutex); return; } else { - con->ops->put(con); dout("con_work %p FAILED to back off %lu\n", con, con->delay); + set_bit(CON_FLAG_BACKOFF, &con->flags); } + goto done; } if (con->state == CON_STATE_STANDBY) { @@ -2749,7 +2750,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); if (con->state != CON_STATE_OPEN) { - ceph_msg_put(msg); + if (msg) + ceph_msg_put(msg); return -EAGAIN; } con->in_msg = msg; diff --git a/net/core/dev.c b/net/core/dev.c index 09cb3f6dc40c..bda6d004f9f0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1666,7 +1666,7 @@ static inline int deliver_skb(struct sk_buff *skb, static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { - if (ptype->af_packet_priv == NULL) + if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 87cc17db2d56..b079c7bbc157 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -319,7 +319,8 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 76d4c2c3c89b..fad649ae4dec 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2192,7 +2192,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - portid, seq, 0, NTF_SELF); + portid, seq, + RTM_NEWNEIGH, NTF_SELF); if (err < 0) return err; skip: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6e04b1fa11f2..4007c1437fda 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3379,10 +3379,12 @@ EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { - if (head_stolen) + if (head_stolen) { + skb_release_head_state(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } } EXPORT_SYMBOL(kfree_skb_partial); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 535584c00f91..0c34bfabc11f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -892,13 +892,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) { const struct inet_diag_handler *handler; + int err = 0; handler = inet_diag_lock_handler(r->sdiag_protocol); if (!IS_ERR(handler)) handler->dump(skb, cb, r, bc); + else + err = PTR_ERR(handler); inet_diag_unlock_handler(handler); - return skb->len; + return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5eea4a811042..14bbfcf717ac 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -457,19 +457,28 @@ static int do_ip_setsockopt(struct sock *sk, int level, struct inet_sock *inet = inet_sk(sk); int val = 0, err; - if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) | - (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) | - (1<<IP_RETOPTS) | (1<<IP_TOS) | - (1<<IP_TTL) | (1<<IP_HDRINCL) | - (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) | - (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | - (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | - (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) || - optname == IP_UNICAST_IF || - optname == IP_MULTICAST_TTL || - optname == IP_MULTICAST_ALL || - optname == IP_MULTICAST_LOOP || - optname == IP_RECVORIGDSTADDR) { + switch (optname) { + case IP_PKTINFO: + case IP_RECVTTL: + case IP_RECVOPTS: + case IP_RECVTOS: + case IP_RETOPTS: + case IP_TOS: + case IP_TTL: + case IP_HDRINCL: + case IP_MTU_DISCOVER: + case IP_RECVERR: + case IP_ROUTER_ALERT: + case IP_FREEBIND: + case IP_PASSSEC: + case IP_TRANSPARENT: + case IP_MINTTL: + case IP_NODEFRAG: + case IP_UNICAST_IF: + case IP_MULTICAST_TTL: + case IP_MULTICAST_ALL: + case IP_MULTICAST_LOOP: + case IP_RECVORIGDSTADDR: if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1831092f999f..858fddf6482a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -338,12 +338,17 @@ static int vti_rcv(struct sk_buff *skb) if (tunnel != NULL) { struct pcpu_tstats *tstats; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + return -1; + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); + skb->mark = 0; + secpath_reset(skb); skb->dev = tunnel->dev; return 1; } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 9e0ffaf1d942..a82047282dbb 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -184,7 +184,8 @@ nf_nat_ipv4_out(unsigned int hooknum, if ((ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET) < 0) ret = NF_DROP; @@ -221,6 +222,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET) < 0) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 432f4bb77238..a8c651216fa6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1163,8 +1163,12 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { - struct rtable *orig; - + struct rtable *orig = rcu_dereference(fnhe->fnhe_rth); + if (orig && rt_is_expired(orig)) { + fnhe->fnhe_gw = 0; + fnhe->fnhe_pmtu = 0; + fnhe->fnhe_expires = 0; + } if (fnhe->fnhe_pmtu) { unsigned long expires = fnhe->fnhe_expires; unsigned long diff = expires - jiffies; @@ -1181,7 +1185,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, } else if (!rt->rt_gateway) rt->rt_gateway = daddr; - orig = rcu_dereference(fnhe->fnhe_rth); rcu_assign_pointer(fnhe->fnhe_rth, rt); if (orig) rt_free(orig); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f32c02e2a543..083092e3aed6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -549,14 +549,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { - struct sk_buff *skb; answ = tp->rcv_nxt - tp->copied_seq; - /* Subtract 1, if FIN is in queue. */ - skb = skb_peek_tail(&sk->sk_receive_queue); - if (answ && skb) - answ -= tcp_hdr(skb)->fin; + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; } else answ = tp->urg_seq - tp->copied_seq; release_sock(sk); @@ -1214,7 +1212,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) @@ -1225,7 +1223,7 @@ wait_for_memory: } out: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); return copied + copied_syn; @@ -2766,6 +2764,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; + if (tp->syn_data_acked) + info->tcpi_options |= TCPI_OPT_SYN_DATA; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 813b43a76fec..834857f3c871 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, .tcpv_rttcnt = ca->cnt_rtt, .tcpv_minrtt = ca->base_rtt, }; - u64 t = ca->sum_rtt; - do_div(t, ca->cnt_rtt); - info.tcpv_rtt = t; + if (info.tcpv_rttcnt > 0) { + u64 t = ca->sum_rtt; + do_div(t, info.tcpv_rttcnt); + info.tcpv_rtt = t; + } nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 432c36649db3..609ff98aeb47 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4529,6 +4529,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) struct tcphdr *th; bool fragstolen; + if (size == 0) + return 0; + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; @@ -5310,11 +5313,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, goto discard; } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 3: check security and precedence [ignored] */ /* step 4: Check for a SYN @@ -5549,6 +5547,11 @@ step5: if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5646,6 +5649,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_rearm_rto(sk); return true; } + tp->syn_data_acked = tp->syn_data; return false; } @@ -5963,7 +5967,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, req = tp->fastopen_rsk; if (req != NULL) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); if (tcp_check_req(sk, skb, req, NULL, true) == NULL) @@ -6052,7 +6056,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ - if (acceptable && req != NULL) { + if (req != NULL) { + /* Return RST if ack_seq is invalid. + * Note that RFC793 only says to generate a + * DUPACK for it but for TCP Fast Open it seems + * better to treat this case like TCP_SYN_RECV + * above. + */ + if (!acceptable) + return 1; /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); @@ -6118,6 +6130,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ef998b008a57..0c4a64355603 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1461,6 +1461,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, skb_set_owner_r(skb, child); __skb_queue_tail(&child->sk_receive_queue, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tp->syn_data_acked = 1; } sk->sk_data_ready(sk, 0); bh_unlock_sock(child); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4c752a6e0bcd..53bc5847bfa8 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -864,7 +864,7 @@ static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, } a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6]; if (a) { - if (nla_len(a) != sizeof(sizeof(struct in6_addr))) + if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; addr->family = AF_INET6; memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 27536ba16c9d..a7302d974f32 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -510,6 +510,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); newtp->fastopen_rsk = NULL; + newtp->syn_data_acked = 0; TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cfe6ffe1c177..2798706cb063 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1986,6 +1986,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + goto repair; /* Skip network transmission */ + cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) break; @@ -2026,6 +2029,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; +repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index fc04711e80c8..d47c1b4421a3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk) return; } if (tp->fastopen_rsk) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && - sk->sk_state != TCP_FIN_WAIT1); + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d7c56f8a5b4e..0424e4e27414 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3064,14 +3064,15 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) struct hlist_node *n; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; /* sync with offset */ if (p < state->offset) { p++; continue; } state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } /* prepare for next bucket */ @@ -3089,18 +3090,20 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct hlist_node *n = &ifa->addr_lst; hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0185679c5f53..d5cb3c4e66f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1633,9 +1633,9 @@ static size_t ip6gre_get_size(const struct net_device *dev) /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ @@ -1659,8 +1659,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ba6d13d1f1e1..e02faed6d17e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -827,6 +827,7 @@ pref_skip_coa: if (val < 0 || val > 255) goto e_inval; np->min_hopcount = val; + retv = 0; break; case IPV6_DONTFRAG: np->dontfrag = valbool; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ff36194a71aa..2edce30ef733 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -535,7 +535,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr; + struct in6_addr mcaddr = IN6ADDR_LINKLOCAL_ALLNODES_INIT; idev = in6_dev_get(dev); if (!idev) @@ -543,7 +543,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - addrconf_addr_solict_mult(&ifa->addr, &mcaddr); ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index e418bd6350a4..d57dab17a182 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -186,7 +186,8 @@ nf_nat_ipv6_out(unsigned int hooknum, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET6) < 0) ret = NF_DROP; @@ -222,6 +223,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET6)) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 18bd9bbbd1c6..22c8ea951185 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -85,7 +85,7 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { } }; -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -127,7 +127,7 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #else -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7c7e963260e1..b1e6cf0b95fd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -219,7 +219,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { }; static const u32 ip6_template_metrics[RTAX_MAX] = { - [RTAX_HOPLIMIT - 1] = 255, + [RTAX_HOPLIMIT - 1] = 0, }; static const struct rt6_info ip6_null_entry_template = { @@ -1232,7 +1232,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 95a3a7a336ba..496ce2cebcd7 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -421,6 +421,8 @@ static int ircomm_tty_install(struct tty_driver *driver, struct tty_struct *tty) hashbin_insert(ircomm_tty, (irda_queue_t *) self, line, NULL); } + tty->driver_data = self; + return tty_port_install(&self->port, driver, tty); } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 37b8b8ba31f7..76125c57ee6d 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -291,6 +291,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p out_del_dev: free_netdev(dev); + spriv->dev = NULL; out_del_session: l2tp_session_delete(session); out: diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7e7198b51c06..c4ee43710aab 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2589,6 +2589,8 @@ __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) struct ip_vs_proto_data *pd; #endif + memset(u, 0, sizeof (*u)); + #ifdef CONFIG_IP_VS_PROTO_TCP pd = ip_vs_proto_data_get(net, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; @@ -2766,7 +2768,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - memset(&t, 0, sizeof(t)); __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1b30b0dee708..962795e839ab 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -753,7 +753,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi4_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi4_to_flowi(&fl2), false)) { - if (rt1->rt_gateway == rt2->rt_gateway && + if (rt_nexthop(rt1, fl1.daddr) == + rt_nexthop(rt2, fl2.daddr) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 16c712563860..ae7f5daeee43 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -180,9 +180,9 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, typeof(nf_ct_timeout_find_get_hook) timeout_find_get; struct ctnl_timeout *timeout; struct nf_conn_timeout *timeout_ext; - const struct ipt_entry *e = par->entryinfo; struct nf_conntrack_l4proto *l4proto; int ret = 0; + u8 proto; rcu_read_lock(); timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook); @@ -192,9 +192,11 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, goto out; } - if (e->ip.invflags & IPT_INV_PROTO) { + proto = xt_ct_find_proto(par); + if (!proto) { ret = -EINVAL; - pr_info("You cannot use inversion on L4 protocol\n"); + pr_info("You must specify a L4 protocol, and not use " + "inversions on it.\n"); goto out; } @@ -214,7 +216,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, /* Make sure the timeout policy matches any existing protocol tracker, * otherwise default to generic. */ - l4proto = __nf_ct_l4proto_find(par->family, e->ip.proto); + l4proto = __nf_ct_l4proto_find(par->family, proto); if (timeout->l4proto->l4proto != l4proto->l4proto) { ret = -EINVAL; pr_info("Timeout policy `%s' can only be used by L4 protocol " diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index ee2e5bc5a8c7..bd93e51d30ac 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -70,6 +70,7 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl4.daddr = info->gw.ip; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return false; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index 81aafa8e4fef..bea7464cc43f 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -111,7 +111,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .family = NFPROTO_IPV4, .table = "nat", .hooks = (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT), + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { @@ -123,7 +123,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .family = NFPROTO_IPV4, .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_LOCAL_IN), + (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, { @@ -133,7 +133,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT), + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { @@ -143,7 +143,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_LOCAL_IN), + (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 01e944a017a4..4da797fa5ec5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -138,6 +138,8 @@ static int netlink_dump(struct sock *sk); static DEFINE_RWLOCK(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); +#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); + static ATOMIC_NOTIFIER_HEAD(netlink_chain); static inline u32 netlink_group_mask(u32 group) @@ -345,6 +347,11 @@ netlink_update_listeners(struct sock *sk) struct hlist_node *node; unsigned long mask; unsigned int i; + struct listeners *listeners; + + listeners = nl_deref_protected(tbl->listeners); + if (!listeners) + return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; @@ -352,7 +359,7 @@ netlink_update_listeners(struct sock *sk) if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } - tbl->listeners->masks[i] = mask; + listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ @@ -536,7 +543,11 @@ static int netlink_release(struct socket *sock) if (netlink_is_kernel(sk)) { BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { - kfree(nl_table[sk->sk_protocol].listeners); + struct listeners *old; + + old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); + RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); + kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].flags = 0; @@ -982,7 +993,7 @@ int netlink_has_listeners(struct sock *sk, unsigned int group) rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); - if (group - 1 < nl_table[sk->sk_protocol].groups) + if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); @@ -1625,7 +1636,7 @@ int __netlink_change_ngroups(struct sock *sk, unsigned int groups) new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; - old = rcu_dereference_protected(tbl->listeners, 1); + old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f0dd83cff906..9687fa1c2275 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -84,18 +84,19 @@ * grp->index is the index of the group; and grp->slot_shift * is the shift for the corresponding (scaled) sigma_i. */ -#define QFQ_MAX_INDEX 19 -#define QFQ_MAX_WSHIFT 16 +#define QFQ_MAX_INDEX 24 +#define QFQ_MAX_WSHIFT 12 #define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT) -#define QFQ_MAX_WSUM (2*QFQ_MAX_WEIGHT) +#define QFQ_MAX_WSUM (16*QFQ_MAX_WEIGHT) #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) #define IWSUM (ONE_FP/QFQ_MAX_WSUM) -#define QFQ_MTU_SHIFT 11 +#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_SLOT_SHIFT (FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX) +#define QFQ_MIN_LMAX 256 /* min possible lmax for a class */ /* * Possible group states. These values are used as indexes for the bitmaps @@ -231,6 +232,32 @@ static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl, q->wsum += delta_w; } +static void qfq_update_reactivate_class(struct qfq_sched *q, + struct qfq_class *cl, + u32 inv_w, u32 lmax, int delta_w) +{ + bool need_reactivation = false; + int i = qfq_calc_index(inv_w, lmax); + + if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { + /* + * shift cl->F back, to not charge the + * class for the not-yet-served head + * packet + */ + cl->F = cl->S; + /* remove class from its slot in the old group */ + qfq_deactivate_class(q, cl); + need_reactivation = true; + } + + qfq_update_class_params(q, cl, lmax, inv_w, delta_w); + + if (need_reactivation) /* activate in new group */ + qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); +} + + static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg) { @@ -238,7 +265,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct qfq_class *cl = (struct qfq_class *)*arg; struct nlattr *tb[TCA_QFQ_MAX + 1]; u32 weight, lmax, inv_w; - int i, err; + int err; int delta_w; if (tca[TCA_OPTIONS] == NULL) { @@ -270,16 +297,14 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) { + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { pr_notice("qfq: invalid max length %u\n", lmax); return -EINVAL; } } else - lmax = 1UL << QFQ_MTU_SHIFT; + lmax = psched_mtu(qdisc_dev(sch)); if (cl != NULL) { - bool need_reactivation = false; - if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), @@ -291,24 +316,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (lmax == cl->lmax && inv_w == cl->inv_w) return 0; /* nothing to update */ - i = qfq_calc_index(inv_w, lmax); sch_tree_lock(sch); - if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { - /* - * shift cl->F back, to not charge the - * class for the not-yet-served head - * packet - */ - cl->F = cl->S; - /* remove class from its slot in the old group */ - qfq_deactivate_class(q, cl); - need_reactivation = true; - } - - qfq_update_class_params(q, cl, lmax, inv_w, delta_w); - - if (need_reactivation) /* activate in new group */ - qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); + qfq_update_reactivate_class(q, cl, inv_w, lmax, delta_w); sch_tree_unlock(sch); return 0; @@ -663,15 +672,48 @@ static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) /* - * XXX we should make sure that slot becomes less than 32. - * This is guaranteed by the input values. - * roundedS is always cl->S rounded on grp->slot_shift bits. + * If the weight and lmax (max_pkt_size) of the classes do not change, + * then QFQ guarantees that the slot index is never higher than + * 2 + ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM). + * + * With the current values of the above constants, the index is + * then guaranteed to never be higher than 2 + 256 * (1 / 16) = 18. + * + * When the weight of a class is increased or the lmax of the class is + * decreased, a new class with smaller slot size may happen to be + * activated. The activation of this class should be properly delayed + * to when the service of the class has finished in the ideal system + * tracked by QFQ. If the activation of the class is not delayed to + * this reference time instant, then this class may be unjustly served + * before other classes waiting for service. This may cause + * (unfrequently) the above bound to the slot index to be violated for + * some of these unlucky classes. + * + * Instead of delaying the activation of the new class, which is quite + * complex, the following inaccurate but simple solution is used: if + * the slot index is higher than QFQ_MAX_SLOTS-2, then the timestamps + * of the class are shifted backward so as to let the slot index + * become equal to QFQ_MAX_SLOTS-2. This threshold is used because, if + * the slot index is above it, then the data structure implementing + * the bucket list either gets immediately corrupted or may get + * corrupted on a possible next packet arrival that causes the start + * time of the group to be shifted backward. */ static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl, u64 roundedS) { u64 slot = (roundedS - grp->S) >> grp->slot_shift; - unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS; + unsigned int i; /* slot index in the bucket list */ + + if (unlikely(slot > QFQ_MAX_SLOTS - 2)) { + u64 deltaS = roundedS - grp->S - + ((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift); + cl->S -= deltaS; + cl->F -= deltaS; + slot = QFQ_MAX_SLOTS - 2; + } + + i = (grp->front + slot) % QFQ_MAX_SLOTS; hlist_add_head(&cl->next, &grp->slots[i]); __set_bit(slot, &grp->full_slots); @@ -892,6 +934,13 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); + if (unlikely(cl->lmax < qdisc_pkt_len(skb))) { + pr_debug("qfq: increasing maxpkt from %u to %u for class %u", + cl->lmax, qdisc_pkt_len(skb), cl->common.classid); + qfq_update_reactivate_class(q, cl, cl->inv_w, + qdisc_pkt_len(skb), 0); + } + err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index c3bea269faf4..9966e7b16451 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -102,7 +102,7 @@ static const struct file_operations sctp_snmp_seq_fops = { .open = sctp_snmp_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; /* Set up the proc fs entry for 'snmp' object. */ @@ -251,7 +251,7 @@ static const struct file_operations sctp_eps_seq_fops = { .open = sctp_eps_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'eps' object. */ @@ -372,7 +372,7 @@ static const struct file_operations sctp_assocs_seq_fops = { .open = sctp_assocs_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'assocs' object. */ @@ -517,7 +517,7 @@ static const struct file_operations sctp_remaddr_seq_fops = { .open = sctp_remaddr_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; int __net_init sctp_remaddr_proc_init(struct net *net) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 57f7de839b03..6773d7803627 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1642,8 +1642,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc->outqueue.outstanding_bytes; sackh.num_gap_ack_blocks = 0; sackh.num_dup_tsns = 0; + chunk->subh.sack_hdr = &sackh; sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, - SCTP_SACKH(&sackh)); + SCTP_CHUNK(chunk)); break; case SCTP_CMD_DISCARD_PACKET: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 59d16ea927f0..a60d1f8b41c5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -974,7 +974,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk, void *addr_buf; struct sctp_af *af; - SCTP_DEBUG_PRINTK("sctp_setsocktopt_bindx: sk %p addrs %p" + SCTP_DEBUG_PRINTK("sctp_setsockopt_bindx: sk %p addrs %p" " addrs_size %d opt %d\n", sk, addrs, addrs_size, op); if (unlikely(addrs_size <= 0)) diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 5a3d675d2f2f..a9c0bbccad6b 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -172,7 +172,7 @@ out_free: xprt_free_allocation(req); dprintk("RPC: setup backchannel transport failed\n"); - return -1; + return -ENOMEM; } EXPORT_SYMBOL_GPL(xprt_setup_backchannel); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2a68bb3db772..fc2f7aa4dca7 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1409,11 +1409,11 @@ static ssize_t read_flush(struct file *file, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { - char tbuf[20]; + char tbuf[22]; unsigned long p = *ppos; size_t len; - sprintf(tbuf, "%lu\n", convert_to_wallclock(cd->flush_time)); + snprintf(tbuf, sizeof(tbuf), "%lu\n", convert_to_wallclock(cd->flush_time)); len = strlen(tbuf); if (p >= len) return 0; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index aaaadfbe36e9..75853cabf4c9 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -254,7 +254,6 @@ struct sock_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); - void (*old_error_report)(struct sock *); }; /* @@ -737,10 +736,10 @@ static int xs_tcp_send_request(struct rpc_task *task) dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); case -ECONNRESET: - case -EPIPE: xs_tcp_shutdown(xprt); case -ECONNREFUSED: case -ENOTCONN: + case -EPIPE: clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); } @@ -781,7 +780,6 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk) transport->old_data_ready = sk->sk_data_ready; transport->old_state_change = sk->sk_state_change; transport->old_write_space = sk->sk_write_space; - transport->old_error_report = sk->sk_error_report; } static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk) @@ -789,7 +787,6 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_data_ready = transport->old_data_ready; sk->sk_state_change = transport->old_state_change; sk->sk_write_space = transport->old_write_space; - sk->sk_error_report = transport->old_error_report; } static void xs_reset_transport(struct sock_xprt *transport) @@ -1453,7 +1450,7 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt) xprt_clear_connecting(xprt); } -static void xs_sock_mark_closed(struct rpc_xprt *xprt) +static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_clear_bit(); clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); @@ -1461,6 +1458,11 @@ static void xs_sock_mark_closed(struct rpc_xprt *xprt) clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_clear_bit(); +} + +static void xs_sock_mark_closed(struct rpc_xprt *xprt) +{ + xs_sock_reset_connection_flags(xprt); /* Mark transport as closed and wake up all pending tasks */ xprt_disconnect_done(xprt); } @@ -1516,6 +1518,7 @@ static void xs_tcp_state_change(struct sock *sk) case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ xprt->connect_cookie++; + clear_bit(XPRT_CONNECTED, &xprt->state); xs_tcp_force_close(xprt); case TCP_CLOSING: /* @@ -1540,25 +1543,6 @@ static void xs_tcp_state_change(struct sock *sk) read_unlock_bh(&sk->sk_callback_lock); } -/** - * xs_error_report - callback mainly for catching socket errors - * @sk: socket - */ -static void xs_error_report(struct sock *sk) -{ - struct rpc_xprt *xprt; - - read_lock_bh(&sk->sk_callback_lock); - if (!(xprt = xprt_from_sock(sk))) - goto out; - dprintk("RPC: %s client %p...\n" - "RPC: error %d\n", - __func__, xprt, sk->sk_err); - xprt_wake_pending_tasks(xprt, -EAGAIN); -out: - read_unlock_bh(&sk->sk_callback_lock); -} - static void xs_write_space(struct sock *sk) { struct socket *sock; @@ -1858,7 +1842,6 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; xprt_clear_connected(xprt); @@ -1983,7 +1966,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; @@ -2050,10 +2032,8 @@ static void xs_abort_connection(struct sock_xprt *transport) any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); if (!result) - xs_sock_mark_closed(&transport->xprt); - else - dprintk("RPC: AF_UNSPEC connect return code %d\n", - result); + xs_sock_reset_connection_flags(&transport->xprt); + dprintk("RPC: AF_UNSPEC connect return code %d\n", result); } static void xs_tcp_reuse_connection(struct sock_xprt *transport) @@ -2098,7 +2078,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 111ff8300ae5..b36f0fcd9bdf 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -116,7 +116,6 @@ void tipc_handler_stop(void) return; handler_enabled = 0; - tasklet_disable(&tipc_tasklet); tasklet_kill(&tipc_tasklet); spin_lock_bh(&qitem_lock); |