diff options
Diffstat (limited to 'net')
57 files changed, 954 insertions, 449 deletions
diff --git a/net/Kconfig b/net/Kconfig index b0937a700f01..2eeb0e55f7c9 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -189,7 +189,6 @@ config BRIDGE_NETFILTER depends on NETFILTER_ADVANCED select NETFILTER_FAMILY_BRIDGE select SKB_EXTENSIONS - default m ---help--- Enabling this option will let arptables resp. iptables see bridged ARP resp. IP traffic. If you want a bridging firewall, you probably diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index dc3d2c1dd9d5..0e3dbc5f3c34 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,7 +34,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; const unsigned char *dest; - struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -54,15 +53,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); - eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) goto out; if (IS_ENABLED(CONFIG_INET) && - (eth->h_proto == htons(ETH_P_ARP) || - eth->h_proto == htons(ETH_P_RARP)) && + (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || + eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 6856a6d9282b..1f14b8455345 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -63,7 +63,8 @@ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; - list_for_each_entry_rcu(p, &br->port_list, list) { + list_for_each_entry_rcu(p, &br->port_list, list, + lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } diff --git a/net/core/dev.c b/net/core/dev.c index a6316b336128..c6c985fe7b1b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -331,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; @@ -3071,6 +3076,8 @@ static u16 skb_tx_hash(const struct net_device *dev, if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); + if (hash >= qoffset) + hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; @@ -3657,26 +3664,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -7201,8 +7190,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7214,6 +7203,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { diff --git a/net/core/devlink.c b/net/core/devlink.c index 549ee56b7a21..5e220809844c 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2103,11 +2103,11 @@ err_action_values_put: static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, - const char *table_name) + const char *table_name, struct devlink *devlink) { struct devlink_dpipe_table *table; - - list_for_each_entry_rcu(table, dpipe_tables, list) { + list_for_each_entry_rcu(table, dpipe_tables, list, + lockdep_is_held(&devlink->lock)) { if (!strcmp(table->name, table_name)) return table; } @@ -2226,7 +2226,7 @@ static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -2382,7 +2382,7 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -6854,7 +6854,7 @@ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); enabled = false; if (table) enabled = table->counters_enabled; @@ -6878,26 +6878,34 @@ int devlink_dpipe_table_register(struct devlink *devlink, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; - - if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) - return -EEXIST; + int err = 0; if (WARN_ON(!table_ops->size_get)) return -EINVAL; + mutex_lock(&devlink->lock); + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, + devlink)) { + err = -EEXIST; + goto unlock; + } + table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; + if (!table) { + err = -ENOMEM; + goto unlock; + } table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; - mutex_lock(&devlink->lock); list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); +unlock: mutex_unlock(&devlink->lock); - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); @@ -6914,7 +6922,7 @@ void devlink_dpipe_table_unregister(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) goto unlock; list_del_rcu(&table->list); @@ -7071,7 +7079,7 @@ int devlink_dpipe_table_resource_set(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) { err = -EINVAL; goto out; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3e7e15278c46..bd7eba9066f8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 09c44bf2e1d2..e1152f4ffe33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3504,27 +3504,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, if (err) return err; - alt_ifname = nla_data(attr); + alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + if (cmd == RTM_NEWLINKPROP) { - alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); - if (!alt_ifname) - return -ENOMEM; err = netdev_name_node_alt_create(dev, alt_ifname); - if (err) { - kfree(alt_ifname); - return err; - } + if (!err) + alt_ifname = NULL; } else if (cmd == RTM_DELLINKPROP) { err = netdev_name_node_alt_destroy(dev, alt_ifname); - if (err) - return err; } else { - WARN_ON(1); - return 0; + WARN_ON_ONCE(1); + err = -EINVAL; } - *changed = true; - return 0; + kfree(alt_ifname); + if (!err) + *changed = true; + return err; } static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 864cb9e9622f..e1101a4f90a6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -467,7 +467,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -527,7 +526,6 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -4805,9 +4803,9 @@ static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { - switch (proto) { - int err; + int err; + switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index fce45dac4205..ef9197541cb3 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -305,7 +305,8 @@ nla_put_failure: static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, - [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, + ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, @@ -447,7 +448,10 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, "mask only allowed in compact bitset"); return -EINVAL; } + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h index b8247e34109d..b849f9d19676 100644 --- a/net/ethtool/bitset.h +++ b/net/ethtool/bitset.h @@ -3,6 +3,8 @@ #ifndef _NET_ETHTOOL_BITSET_H #define _NET_ETHTOOL_BITSET_H +#define ETHNL_MAX_BITSET_SIZE S16_MAX + typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN]; int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 364ea2cc028e..3ba7f61be107 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -155,7 +155,8 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, new_node->seq_out[i] = seq_out; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list) { + list_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 376882215919..0bd10a1f477f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 316ebdf8151d..6b6b57000dad 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { struct request_sock *req; - tcp_try_undo_loss(sk, false); + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db76b9609299..08a41f1e1cd2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1857,8 +1857,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 58fbde244381..72abf892302f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1102,8 +1102,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1146,7 +1145,9 @@ next_iter: } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 55bfc5149d0c..781ca8c07a0d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -437,8 +437,6 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return -ENOENT; switch (type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -452,7 +450,10 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; } return 0; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -468,6 +469,7 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, t->parms.name); } return 0; + } case ICMPV6_PKT_TOOBIG: ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5d65436ad5ad..4703b09808d0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -517,8 +517,6 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, err = 0; switch (*type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -531,7 +529,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -548,7 +549,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, t->parms.name); } break; - case ICMPV6_PKT_TOOBIG: + } + case ICMPV6_PKT_TOOBIG: { + __u32 mtu; + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; @@ -562,6 +566,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 79fc012dd2ca..debdaeba5d8c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,9 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } break; - + } else { + break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4fbdc60b4e07..2931224b674e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5198,6 +5198,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e041af2f021a..88d7a692a965 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2959,7 +2959,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2967,10 +2967,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0e05ff037672..0ba98ad9bc85 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4114,7 +4114,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&local->sta_mtx); - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata && (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) continue; diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 49f6054e7f4e..a9ed3bf1d93f 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -4,6 +4,7 @@ config MPTCP depends on INET select SKB_EXTENSIONS select CRYPTO_LIB_SHA256 + select CRYPTO help Multipath TCP (MPTCP) connections send and receive data over multiple subflows in order to utilize multiple network paths. Each subflow diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 030dee668e0a..3c19a8efdcea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -543,6 +543,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } } +static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) +{ + return 0; +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -551,6 +556,7 @@ static int __mptcp_init_sock(struct sock *sk) __set_bit(MPTCP_SEND_SPACE, &msk->flags); msk->first = NULL; + inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; return 0; } @@ -755,60 +761,50 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); /* @@ the meaning of setsockopt() when the socket is connected and - * there are multiple subflows is not defined. + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when TCP socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_setsockopt(ssock->sk, level, optname, optval, + optlen); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); - /* @@ the meaning of getsockopt() when the socket is connected and - * there are multiple subflows is not defined. + /* @@ the meaning of setsockopt() when the socket is connected and + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_getsockopt(ssock->sk, level, optname, optval, + option); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_getsockopt(ssk, level, optname, optval, option); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_get_port(struct sock *sk, unsigned short snum) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8a99a2930284..9f8663b30456 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -56,8 +56,8 @@ #define MPTCP_DSS_FLAG_MASK (0x1F) /* MPTCP socket flags */ -#define MPTCP_DATA_READY BIT(0) -#define MPTCP_SEND_SPACE BIT(1) +#define MPTCP_DATA_READY 0 +#define MPTCP_SEND_SPACE 1 /* MPTCP connection sock */ struct mptcp_sock { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69c107f9ba8d..8dd17589217d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7480ce55b5c8..e52d7b7597a0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,13 +7,21 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -72,11 +80,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -162,6 +194,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -205,10 +241,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -247,10 +285,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) @@ -275,8 +315,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -288,21 +327,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -414,28 +476,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -547,7 +644,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -555,7 +652,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -563,10 +662,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -583,88 +680,124 @@ retry: ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + kfree(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -677,15 +810,44 @@ out: return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -698,32 +860,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -737,38 +916,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -776,28 +954,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -820,13 +1002,41 @@ overwrite_extensions: if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -840,13 +1050,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -857,8 +1077,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -866,20 +1085,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -898,7 +1130,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -906,6 +1139,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -991,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1022,6 +1266,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1033,23 +1278,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1071,7 +1307,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1091,15 +1327,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1141,8 +1377,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1208,6 +1443,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1226,6 +1462,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1294,6 +1531,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + kfree(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1304,9 +1550,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1329,12 +1576,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d1305423640f..1927fc296f95 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -894,32 +894,175 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } } -/* Resolve race on insertion if this protocol allows this. */ +static void __nf_conntrack_insert_prepare(struct nf_conn *ct) +{ + struct nf_conn_tstamp *tstamp; + + atomic_inc(&ct->ct_general.use); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_get_real_ns(); +} + +static int __nf_ct_resolve_clash(struct sk_buff *skb, + struct nf_conntrack_tuple_hash *h) +{ + /* This is the conntrack entry already in hashes that won race. */ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + + loser_ct = nf_ct_get(skb, &ctinfo); + + if (nf_ct_is_dying(ct)) + return NF_DROP; + + if (!atomic_inc_not_zero(&ct->ct_general.use)) + return NF_DROP; + + if (((ct->status & IPS_NAT_DONE_MASK) == 0) || + nf_ct_match(ct, loser_ct)) { + struct net *net = nf_ct_net(ct); + + nf_ct_acct_merge(ct, ctinfo, loser_ct); + nf_ct_add_to_dying_list(loser_ct); + nf_conntrack_put(&loser_ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + + NF_CT_STAT_INC(net, insert_failed); + return NF_ACCEPT; + } + + nf_ct_put(ct); + return NF_DROP; +} + +/** + * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry + * + * @skb: skb that causes the collision + * @repl_idx: hash slot for reply direction + * + * Called when origin or reply direction had a clash. + * The skb can be handled without packet drop provided the reply direction + * is unique or there the existing entry has the identical tuple in both + * directions. + * + * Caller must hold conntrack table locks to prevent concurrent updates. + * + * Returns NF_DROP if the clash could not be handled. + */ +static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) +{ + struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb); + const struct nf_conntrack_zone *zone; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct net *net; + + zone = nf_ct_zone(loser_ct); + net = nf_ct_net(loser_ct); + + /* Reply direction must never result in a clash, unless both origin + * and reply tuples are identical. + */ + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) { + if (nf_ct_key_equal(h, + &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple, + zone, net)) + return __nf_ct_resolve_clash(skb, h); + } + + /* We want the clashing entry to go away real soon: 1 second timeout. */ + loser_ct->timeout = nfct_time_stamp + HZ; + + /* IPS_NAT_CLASH removes the entry automatically on the first + * reply. Also prevents UDP tracker from moving the entry to + * ASSURED state, i.e. the entry can always be evicted under + * pressure. + */ + loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH; + + __nf_conntrack_insert_prepare(loser_ct); + + /* fake add for ORIGINAL dir: we want lookups to only find the entry + * already in the table. This also hides the clashing entry from + * ctnetlink iteration, i.e. conntrack -L won't show them. + */ + hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + + hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, + &nf_conntrack_hash[repl_idx]); + return NF_ACCEPT; +} + +/** + * nf_ct_resolve_clash - attempt to handle clash without packet drop + * + * @skb: skb that causes the clash + * @h: tuplehash of the clashing entry already in table + * @hash_reply: hash slot for reply direction + * + * A conntrack entry can be inserted to the connection tracking table + * if there is no existing entry with an identical tuple. + * + * If there is one, @skb (and the assocated, unconfirmed conntrack) has + * to be dropped. In case @skb is retransmitted, next conntrack lookup + * will find the already-existing entry. + * + * The major problem with such packet drop is the extra delay added by + * the packet loss -- it will take some time for a retransmit to occur + * (or the sender to time out when waiting for a reply). + * + * This function attempts to handle the situation without packet drop. + * + * If @skb has no NAT transformation or if the colliding entries are + * exactly the same, only the to-be-confirmed conntrack entry is discarded + * and @skb is associated with the conntrack entry already in the table. + * + * Failing that, the new, unconfirmed conntrack is still added to the table + * provided that the collision only occurs in the ORIGINAL direction. + * The new entry will be added after the existing one in the hash list, + * so packets in the ORIGINAL direction will continue to match the existing + * entry. The new entry will also have a fixed timeout so it expires -- + * due to the collision, it will not see bidirectional traffic. + * + * Returns NF_DROP if the clash could not be resolved. + */ static __cold noinline int -nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h, + u32 reply_hash) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); const struct nf_conntrack_l4proto *l4proto; - enum ip_conntrack_info oldinfo; - struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + struct net *net; + int ret; + + loser_ct = nf_ct_get(skb, &ctinfo); + net = nf_ct_net(loser_ct); l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->allow_clash && - !nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use)) { - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || - nf_ct_match(ct, loser_ct)) { - nf_ct_acct_merge(ct, ctinfo, loser_ct); - nf_conntrack_put(&loser_ct->ct_general); - nf_ct_set(skb, ct, oldinfo); - return NF_ACCEPT; - } - nf_ct_put(ct); - } + if (!l4proto->allow_clash) + goto drop; + + ret = __nf_ct_resolve_clash(skb, h); + if (ret == NF_ACCEPT) + return ret; + + ret = nf_ct_resolve_clash_harder(skb, reply_hash); + if (ret == NF_ACCEPT) + return ret; + +drop: + nf_ct_add_to_dying_list(loser_ct); NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC(net, insert_failed); return NF_DROP; } @@ -932,7 +1075,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -989,6 +1131,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (unlikely(nf_ct_is_dying(ct))) { nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, insert_failed); goto dying; } @@ -1009,13 +1152,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; - atomic_inc(&ct->ct_general.use); - ct->status |= IPS_CONFIRMED; - /* set conntrack timestamp, if enabled. */ - tstamp = nf_conn_tstamp_find(ct); - if (tstamp) - tstamp->start = ktime_get_real_ns(); + __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers @@ -1035,11 +1173,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: - nf_ct_add_to_dying_list(ct); - ret = nf_ct_resolve_clash(net, skb, ctinfo, h); + ret = nf_ct_resolve_clash(skb, h, reply_hash); dying: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7365b43f8f98..760ca2422816 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,6 +81,18 @@ static bool udp_error(struct sk_buff *skb, return false; } +static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + u32 extra_jiffies) +{ + if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && + ct->status & IPS_NAT_CLASH)) + nf_ct_kill(ct); + else + nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); +} + /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -116,8 +128,8 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -198,8 +210,8 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 83e1db37c3b0..06f00cdc3891 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -847,9 +847,6 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, { int err; - if (!nf_flowtable_hw_offload(flowtable)) - return 0; - if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -876,6 +873,9 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct flow_block_offload bo; int err; + if (!nf_flowtable_hw_offload(flowtable)) + return 0; + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index f0cb1e13af50..4fc0c924ed5d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -203,7 +203,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * * Matching @@ -298,7 +298,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * the matching element is at 0x42. * @@ -503,7 +503,7 @@ static int pipapo_refill(unsigned long *map, int len, int rules, return -1; } - if (unlikely(match_only)) { + if (match_only) { bitmap_clear(map, i, 1); return i; } @@ -1766,11 +1766,13 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { - const u8 *data = (const u8 *)elem->key.val.data; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; + struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; - struct nft_pipapo_elem *e; + const u8 *data; + + data = (const u8 *)nft_set_ext_key(&e->ext); e = pipapo_get(net, set, data, 0); if (IS_ERR(e)) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index bccd47cd7190..8c835ad63729 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ @@ -114,7 +115,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -315,7 +316,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -401,15 +402,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) remove_proc_entry(hinfo->name, parent); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) -{ - cancel_delayed_work_sync(&hinfo->gc_work); - htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, true); - kfree(hinfo->name); - vfree(hinfo); -} - static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) @@ -420,7 +412,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -429,12 +421,16 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); - htable_destroy(hinfo); + htable_remove_proc_entry(hinfo); + mutex_unlock(&hashlimit_mutex); + + cancel_delayed_work_sync(&hinfo->gc_work); + htable_selective_cleanup(hinfo, true); + kfree(hinfo->name); + vfree(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -837,6 +833,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } +#define HASHLIMIT_MAX_SIZE 1048576 + static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, @@ -847,6 +845,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; + if (cfg->size > HASHLIMIT_MAX_SIZE) { + cfg->size = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); + } + if (cfg->max > HASHLIMIT_MAX_SIZE) { + cfg->max = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); + } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f5d34da0646e..a1f2320ecc16 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -143,7 +143,8 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain, if (domain != NULL) { bkt = netlbl_domhsh_hash(domain); bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_domhsh_lock)) if (iter->valid && netlbl_family_match(iter->family, family) && strcmp(iter->domain, domain) == 0) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index d2e4ab8d1cb1..77bb1bb22c3b 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -207,7 +207,8 @@ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4e31721e7293..edf3e285e242 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1014,7 +1014,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1033,7 +1034,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0522b2b1fd95..9f357aa22b94 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -497,8 +497,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); - if (err && parallel) { - kfree(attrbuf); + if (err) { + if (parallel) + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 659c2a790fe7..c047afd12116 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -179,7 +179,8 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -2042,7 +2043,8 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2061,7 +2063,8 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) dp->max_headroom = new_headroom; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7da4230627f5..288122eec7c8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2708,10 +2708,6 @@ static int validate_set(const struct nlattr *a, return -EINVAL; switch (key_type) { - const struct ovs_key_ipv4 *ipv4_key; - const struct ovs_key_ipv6 *ipv6_key; - int err; - case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: @@ -2723,7 +2719,9 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - case OVS_KEY_ATTR_TUNNEL: + case OVS_KEY_ATTR_TUNNEL: { + int err; + if (masked) return -EINVAL; /* Masked tunnel set not supported. */ @@ -2732,8 +2730,10 @@ static int validate_set(const struct nlattr *a, if (err) return err; break; + } + case OVS_KEY_ATTR_IPV4: { + const struct ovs_key_ipv4 *ipv4_key; - case OVS_KEY_ATTR_IPV4: if (eth_type != htons(ETH_P_IP)) return -EINVAL; @@ -2753,8 +2753,10 @@ static int validate_set(const struct nlattr *a, return -EINVAL; } break; + } + case OVS_KEY_ATTR_IPV6: { + const struct ovs_key_ipv6 *ipv6_key; - case OVS_KEY_ATTR_IPV6: if (eth_type != htons(ETH_P_IPV6)) return -EINVAL; @@ -2781,7 +2783,7 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - + } case OVS_KEY_ATTR_TCP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 5904e93e5765..fd8a01ca7a2d 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -585,7 +585,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, head = find_bucket(ti, hash); (*n_mask_hit)++; - hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -769,7 +770,8 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); - hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548..5010d1ddd4bd 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -61,7 +61,8 @@ static struct dp_meter *lookup_meter(const struct datapath *dp, struct hlist_head *head; head = meter_hash_bucket(dp, meter_id); - hlist_for_each_entry_rcu(meter, head, dp_hash_node) { + hlist_for_each_entry_rcu(meter, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (meter->id == meter_id) return meter; } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 5da9392b03d6..47febb4504f0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -96,7 +96,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - hlist_for_each_entry_rcu(vport, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node, + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 3341eee87bf9..585e6b3b69ce 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -162,10 +162,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, if (write) gup_flags |= FOLL_WRITE; - ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); + ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { - while (ret--) - put_page(pages[ret]); + unpin_user_pages(pages, ret); ret = -EFAULT; } @@ -300,8 +299,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * to release anything. */ if (!need_odp) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); + unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); @@ -325,7 +323,12 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, if (cookie_ret) *cookie_ret = cookie; - if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) { + if (args->cookie_addr && + put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { + if (!need_odp) { + unpin_user_pages(pages, nr_pages); + kfree(sg); + } ret = -EFAULT; goto out; } @@ -496,9 +499,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) * is the case for a RDMA_READ which copies from remote * to local memory */ - if (!ro->op_write) - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } @@ -515,8 +516,7 @@ void rds_atomic_free_op(struct rm_atomic_op *ao) /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; @@ -944,7 +944,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, return ret; err: if (page) - put_page(page); + unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 90a31b15585f..8c466a712cda 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -186,6 +186,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) /* TCA_STATS_PKT64 */ diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7e54d2ab5254..d32d4233d337 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 748e3b19ec1d..6a16af4b1ef6 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 90988a511cd5..6fd44bdb0fc3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -512,15 +512,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_abort(struct smc_sock *smc, int reason_code, int local_contact) { + bool is_smcd = smc->conn.lgr->is_smcd; + if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - if (smc->conn.lgr->is_smcd) + smc_lgr_cleanup_early(&smc->conn); + else + smc_conn_free(&smc->conn); + if (is_smcd) /* there is only one lgr role for SMC-D; use server lock */ mutex_unlock(&smc_server_lgr_pending); else mutex_unlock(&smc_client_lgr_pending); - smc_conn_free(&smc->conn); smc->connect_nonblock = 0; return reason_code; } @@ -1091,7 +1094,6 @@ static void smc_listen_out_err(struct smc_sock *new_smc) if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; - smc_conn_free(&new_smc->conn); smc_listen_out(new_smc); } @@ -1102,12 +1104,13 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, { /* RDMA setup failed, switch back to TCP */ if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); if (reason_code < 0) { /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } - smc_conn_free(&new_smc->conn); smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { @@ -1170,16 +1173,18 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, new_smc->conn.lgr->vlan_id, new_smc->conn.lgr->smcd)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_SMCDNOTALK; } /* Create send and receive buffers */ if (smc_buf_create(new_smc, true)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_MEM; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2249de5379ee..5b085efa3bce 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -162,6 +162,18 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +void smc_lgr_cleanup_early(struct smc_connection *conn) +{ + struct smc_link_group *lgr = conn->lgr; + + if (!lgr) + return; + + smc_conn_free(conn); + smc_lgr_forget(lgr); + smc_lgr_schedule_free_work_fast(lgr); +} + /* Send delete link, either as client to request the initiation * of the DELETE LINK sequence from server; or as server to * initiate the delete processing. See smc_llc_rx_delete_link(). diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c472e12951d1..234ae25f0025 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -296,6 +296,7 @@ struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); +void smc_lgr_cleanup_early(struct smc_connection *conn); void smc_lgr_terminate(struct smc_link_group *lgr, bool soft); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, @@ -316,7 +317,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); -void smcd_conn_free(struct smc_connection *conn); void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); int smc_core_init(void); void smc_core_exit(void); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 548632621f4b..d6ba186f67e2 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -573,6 +573,8 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) struct smc_ib_device *smcibdev; smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1ba5a92832bb..1c5574e2e058 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -593,7 +593,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -605,6 +605,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, struct tls_record_info, list); if (!info) return NULL; + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 62c12cb5763e..68debcb28fa4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -682,6 +682,7 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +#ifdef CONFIG_PROC_FS static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; @@ -692,6 +693,9 @@ static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); } } +#else +#define unix_show_fdinfo NULL +#endif static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9c5b2a91baad..a5f28708e0e7 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,6 +451,12 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (vsk->transport == new_transport) return 0; + /* transport->release() must be called with sock lock acquired. + * This path can only be taken during vsock_stream_connect(), + * where we have already held the sock lock. + * In the other cases, this function is called on a new socket + * which is not assigned to any transport. + */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); } @@ -753,20 +759,18 @@ static void __vsock_release(struct sock *sk, int level) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - /* The release call is supposed to use lock_sock_nested() - * rather than lock_sock(), if a sock lock should be acquired. - */ - if (vsk->transport) - vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) - vsock_remove_sock(vsk); - /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); + + if (vsk->transport) + vsk->transport->release(vsk); + else if (sk->sk_type == SOCK_STREAM) + vsock_remove_sock(vsk); + sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 3492c021925f..630b851f8150 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -526,12 +526,9 @@ static bool hvs_close_lock_held(struct vsock_sock *vsk) static void hvs_release(struct vsock_sock *vsk) { - struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index d9f0c9c5425a..f3c4bab2f737 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -829,7 +829,6 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); @@ -837,7 +836,6 @@ void virtio_transport_release(struct vsock_sock *vsk) list_del(&pkt->list); virtio_transport_free_pkt(pkt); } - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index cedf17d4933f..5b19e9fac4aa 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -20,6 +20,7 @@ #include <linux/netlink.h> #include <linux/nospec.h> #include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <net/net_namespace.h> #include <net/genetlink.h> #include <net/cfg80211.h> @@ -4800,8 +4801,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); @@ -4823,6 +4823,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } wdev_unlock(wdev); +out: kfree(params.acl); return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index fff9a74891fc..1a8218f1bbe0 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2276,7 +2276,7 @@ static void handle_channel_custom(struct wiphy *wiphy, break; } - if (IS_ERR(reg_rule)) { + if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index df600487a68d..356f90e4522b 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -217,6 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); + __xskq_cons_release(xs->umem->fq); sock_def_readable(&xs->sk); } @@ -304,6 +305,7 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bec2af11853a..89a01ac4e079 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -271,7 +271,8 @@ static inline void xskq_cons_release(struct xsk_queue *q) { /* To improve performance, only update local state here. * Reflect this to global state when we get new entries - * from the ring in xskq_cons_get_entries(). + * from the ring in xskq_cons_get_entries() and whenever + * Rx or Tx processing are completed in the NAPI loop. */ q->cached_cons++; } |